Unlock instant, AI-driven research and patent intelligence for your innovation.

Logistics address feature extraction method, system and device and storage medium

A feature extraction and address technology, applied in the field of data processing, can solve problems such as error accumulation, sparse representation vectors, and unfavorable operations

Pending Publication Date: 2021-03-12
上海寻梦信息技术有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing address processing steps mainly include text preprocessing, feature extraction, and specific downstream business models. Most of the text preprocessing methods are different, resulting in inconsistent data usage. Different processing logic may be designed for different data, and Will cause waste of data usage
In addition, the existing address feature representation is strongly dependent on the preprocessing rules, which is easy to cause error accumulation, and the representation vector is extremely sparse, which is not conducive to the calculation when applied to subsequent models

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Logistics address feature extraction method, system and device and storage medium
  • Logistics address feature extraction method, system and device and storage medium
  • Logistics address feature extraction method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0054] Furthermore, the drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be impleme...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a logistics address feature extraction method, system and device and a storage medium. The method comprises the steps of connecting information, corresponding to all attributes,of a logistics address in series to obtain a text character string; mapping the text character string into an ID sequence based on a text mapping dictionary, wherein the text mapping dictionary comprises preset mapping relationships between various attribute values of each attribute and IDs; mapping the ID sequence into a vector sequence by adopting an embedded layer; and inputting the vector sequence into an interactive feature extraction model, and extracting address features from output data of the interactive feature extraction model. The invention provides a unified text representation method based on pre-training, and the method comprises the steps of firstly mapping a text to an ID sequence based on a pre-processed text mapping dictionary, then mapping the ID sequence to a vector sequence through an embedded layer, carrying out the feature extraction in the vector sequence, and obtaining a logistics address feature in a unified form through extraction; therefore, unified representation after address feature extraction is realized.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a logistics address feature extraction method, system, equipment and storage medium. Background technique [0002] In logistics business scenarios, addresses are used everywhere, including address transfer to longitude and latitude, intelligent order distribution, and recommendation of collection points. Since each business scenario is relatively independent of each other, there are often differences in the processing and use of the address text. [0003] The existing address processing steps mainly include text preprocessing, feature extraction, and specific downstream business models. Most of the text preprocessing methods are different, resulting in inconsistent data usage. Different processing logics may be designed for different data, and It will cause waste of data usage. In addition, the existing address feature representation is strongly dependent on the preproc...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06K9/62G06Q10/08
CPCG06Q10/083G06F18/214
Inventor 余超
Owner 上海寻梦信息技术有限公司