Address analysis using morphemes

1. A computer-implemented method comprising:

receiving a first address and a second address representing one or more physical locations involved in an online transaction, the first address including n morphemes and the second address including m morphemes, wherein a morpheme is a smallest semantic unit in an address, and wherein n and m are both natural numbers;

determining first correlation values between the n morphemes and the m morphemes;

for each of the n morphemes as a first morpheme:

selecting a second morpheme of the m morphemes that best matches the first morpheme based on the first correlation values and a preset algorithm; and

recording a target correlation value between the first morpheme and the second morpheme as part of a set of n target correlation values;

obtaining a second correlation value between the first address and the second address based on the n target correlation values, wherein the second correlation value is a summation of a plurality of values of the n target correlation values; and

analyzing a correlation between the first address and the second address based on the second correlation value.

2. The computer-implemented method of claim 1 , wherein determining the first correlation values comprises determining the first correlation values between each of the n morphemes and the m morphemes to obtain n×m first correlation values.

3. The computer-implemented method of claim 2 , wherein selecting the second morpheme that best matches the first morpheme comprises:

constructing an n×m matrix based on the n×m first correlation values; and

pre-processing the n×m matrix based on the preset algorithm.

4. The computer-implemented method of claim 3 , further comprising selecting the second morpheme based on the pre-processed n×m matrix.

5. The computer-implemented method of claim 1 , wherein a value of the first correlation values is an edit distance value, a hamming distance value, a Jaccard distance value, an N-Gram distance value, a Jaro-Winkler (JW) distance value, or a cosine distance value.

6. A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

receiving a first address and a second address representing one or more physical locations involved in an online transaction, the first address including n morphemes and the second address including m morphemes, wherein a morpheme is a smallest semantic unit in an address, and wherein n and m are both natural numbers;

determining first correlation values between the n morphemes and the m morphemes;

for each of the n morphemes as a first morpheme:

selecting a second morpheme of the m morphemes that best matches the first morpheme based on the first correlation values and a preset algorithm; and

recording a target correlation value between the first morpheme and the second morpheme as part of a set of n target correlation values;

obtaining a second correlation value between the first address and the second address based on the n target correlation values, wherein the second correlation value is a summation of a plurality of values of the n target correlation values; and

analyzing a correlation between the first address and the second address based on the second correlation value.

7. The non-transitory, computer-readable medium of claim 6 , wherein determining the first correlation values comprises determining the first correlation values between each of the n morphemes and the m morphemes to obtain n×m first correlation values.

8. The non-transitory, computer-readable medium of claim 7 , wherein selecting the second morpheme that best matches the first morpheme comprises:

constructing an n×m matrix based on the n×m first correlation values; and

pre-processing the n×m matrix based on the preset algorithm.

9. The non-transitory, computer-readable medium of claim 8 , the operations further comprising selecting the second morpheme based on the pre-processed n×m matrix.

10. The non-transitory, computer-readable medium of claim 6 , wherein a value of the first correlation values is an edit distance value, a hamming distance value, a Jaccard distance value, an N-Gram distance value, a Jaro-Winkler (JW) distance value, or a cosine distance value.

11. A computer-implemented system, comprising: one or more computers; and

one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:

receiving a first address and a second address representing one or more physical locations involved in an online transaction, the first address including n morphemes and the second address including m morphemes, wherein a morpheme is a smallest semantic unit in an address, and wherein n and m are both natural numbers;

determining first correlation values between the n morphemes and the m morphemes;

for each of the n morphemes as a first morpheme:

selecting a second morpheme of the m morphemes that best matches the first morpheme based on the first correlation values and a preset algorithm; and

recording a target correlation value between the first morpheme and the second morpheme as part of a set of n target correlation values;

obtaining a second correlation value between the first address and the second address based on the n target correlation values, wherein the second correlation value is a summation of a plurality of values of the n target correlation values; and

analyzing a correlation between the first address and the second address based on the second correlation value.

12. The computer-implemented system of claim 11 , wherein determining the first correlation values comprises determining the first correlation values between each of the n morphemes and the m morphemes to obtain n×m first correlation values.

13. The computer-implemented system of claim 12 , wherein selecting the second morpheme that best matches the first morpheme comprises:

constructing an n×m matrix based on the n×m first correlation values; and

pre-processing the n×m matrix based on the preset algorithm.

14. The computer-implemented system of claim 13 , the operations further comprising selecting the second morpheme based on the pre-processed n×m matrix.

15. The computer-implemented system of claim 11 , wherein a value of the first correlation values is an edit distance value, a hamming distance value, a Jaccard distance value, an N-Gram distance value, a Jaro-Winkler (JW) distance value, or a cosine distance value.

16. The computer-implemented method of claim 1 , further comprising pre-processing the first address by varying a writing order of the first address to account for regional differences.

17. The non-transitory, computer-readable medium of claim 6 , further comprising pre-processing the first address by varying a writing order of the first address to account for regional differences.