Hybrid supervision-based double-layer matching coding mapping recommendation method.
A technology for coding mapping and recommending methods, which is applied in the fields of instrumentation, computing, and electrical digital data processing to achieve the effect of improving stability, reducing workload, and achieving generalization.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0051] Embodiment 1 of the present application provides a method such as figure 1 and Figure 4 Shown is a recommendation method based on mixed-supervised two-layer matching encoding mapping:
[0052] Step 1, use the acquisition device to collect the original KKS code list and the new KKS code list stored in the database through the interface provided by the database, and store the original KKS code list and the new KKS code list;
[0053] The original KKS code list is:
[0054]
[0055] In the above formula, to It is the English code in the original KKS code list, to It is the Chinese description in the original KKS code list;
[0056] The new KKS code list is:
[0057]
[0058] In the above formula, to It is the English code in the new KKS code list, to It is the Chinese description in the new KKS code list;
[0059] Step 2. Manually match the original KKS code list obtained in step 1 with the new KKS code list:
[0060]
[0061] Get supervised...
Embodiment 2
[0068] On the basis of Embodiment 1, Embodiment 2 of the present application provides the following Figure 5 The specific implementation process of step 3 shown:
[0069] Step 3.1, Supervised matching model training data set D The data in Jieba (Python Chinese word segmentation component) is used for word segmentation to obtain word segmentation results, and then N-Gram is used for vectorization to obtain vectorized training data sets ;
[0070] Step 3.2, the vectorized training data set Input to supervised matching model model ; Firstly, sparse features are generated by a two-layer MLP encoding network, where the first layer of MLP encoding network is , the second-layer MLP encoding network is ; Then the reconstruction features are generated by the two-layer MLP decoding network, where the first layer of MLP decoding network is , the second layer MLP decoding network is :
[0071]
[0072]
[0073] In the above formula, Sparse features generated for the...
Embodiment 3
[0079] On the basis of Embodiment 1 and Embodiment 2, Embodiment 3 of the present application provides such Figure 4 The specific implementation process of step 4 shown:
[0080] Step 4.1. Obtain the description word segmentation of the original KKS code and the new KKS code respectively by word segmentation ,in w for subparticiple, i is the number of participle words;
[0081] Step 4.2, the original KKS code obtained by step 4.1 and the description word segmentation of the new KKS code, adopt the minimum edit distance ( Eidt distance ) Calculate the similarity of the word segmentation results, and get the similarity score of the edit distance between the original KKS code and the new KKS code Score ;
[0082] Step 4.3, the similarity score obtained by step 4.2 Score According to the similarity threshold Filter, if the similarity score Score lower than , then the matching fails and proceeds to step 5 for supervised matching; if the similarity score Score hig...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More