A string processing method and device
A processing method and string technology, applied in the computer field, can solve the problems of poor processing accuracy, poor identification and classification processing accuracy, low string similarity of accuracy, etc., and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] figure 1 The flow of the string processing method provided in Embodiment 1 of the present application mainly refers to decomposing the string into character substrings with semantic weights, calculating the semantic edit distance between each string according to the semantic weights, and then performing similar Degree calculation can effectively improve the similarity of strings according to semantic units, and facilitate subsequent processing such as classification and recognition of strings. Including the following steps:
[0035] S101: Obtain a character string to be recognized.
[0036] The acquired character string S to be recognized includes one or more of company name, address, product name, blacklist, problem name or description input by the user.
[0037] For example, users need to enter delivery addresses on some service websites, service providers need to enter commodity names, and some users may need to set some blacklists. And all these data may have a s...
example 1
[0064] Example 1: When the obtained character string S to be recognized is "ABC Information Technology Co., Ltd."; then the character string S to be recognized is segmented to obtain each character substring S={ABC, information, technology, limited, company} , i=5; Find the target character string T from the target string database according to the character substring to be identified, assuming that one of the target character strings is found to be "XYZ Information Technology Co., Ltd."; the target character string T carries out participle processing to obtain the target character substring target character substring T={XYZ, information, technology, limited, company}, j=5; and semantic weight table W n The internal weights of the character substrings are shown in Table 1 below:
[0065] substring ABC XYZ information technology limited company Weights 0.98 0.99 0.02 0.02 0.01 0.01
[0066] Table 1
[0067] Then obtain the character substri...
example 2
[0073] Example 2: when the acquired character string S to be recognized is "ABC company"; then the character string S to be recognized is segmented to obtain each character substring S={ABC, company}, i=2; according to the character string to be recognized Recognize the character substring to find the target character string T from the target string database, assuming that one of the target character strings is found to be "ABC Information Technology Co., Ltd."; the target character string T is carried out word segmentation to obtain the target character substring Target character substring T={ABC, information, technology, limited, company}, j=5; and semantic weight table W n The internal weights of the character substrings are shown in Table 3 below:
[0074] substring ABC information technology limited company Weights 0.98 0.02 0.02 0.01 0.01
[0075] table 3
[0076] Then obtain the character substring to be recognized with semantic weigh...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


