Conversational natural language processing method and device

Abstract

The invention discloses a conversational natural language processing method and device. The method comprises the following steps: segmenting chapter-level words into a character string by utilizing symbols, extracting language linear structures and language chunks from the segmented character string, respectively carrying out inverted arrangement on the extracted language linear structures and language chunks, creating sub-indexes of the language linear structures and the language chunks and forming a holistic index; providing a conversational interface and receiving a retrieve input character string of a user on the basis of the conversational interface; extracting the language linear structure and the language chunk of the retrieve input character string from the retrieve input character string and confirming a preset interest word from the extracted language chunk; and retrieving reply message matched with the language linear structure and the language chunk which are extracted from the retrieve input character string of the user according to the holistic index. By applying the method disclosed by the invention, the correlation interpretant of the interest word in the next round of conversation is confirmed through memorizing the trigger operation of a trigger control, so that the natural language processing accuracy is increased.

Description

technical field

[0001] The present invention relates to the field of natural language processing and / or search. More specifically, it relates to a conversational natural language processing method and device. Background technique

[0002] Natural language processing (Information Retrieval) refers to the process and technology of organizing information in a certain way and finding relevant information according to the needs of information users. Natural language processing in a narrow sense is the second half of the natural language processing process, that is, the process of finding the required information from the information collection, which is what we often call information search (InformationSearch or InformationSeek).

[0003] Currently commonly used natural language processing methods usually include: common method, retrospective method and segmentation method. The common law is a method of searching literature and materials by using retrieval tools such as bibliog...

Examples

example 2

[0039] By analyzing the above two examples, it can be found that:

[0040] "Rural tourism", "Chinese tourism" and "tourism development" are equivalent to the variables in Example 1, because by replacing the corresponding parts (ie variables), their semantic meaning can basically be preserved. And "x is an important part of x and an important support to promote x" (where x represents blank) is equivalent to the linear structure of Example 1, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0041] Similarly, "China's economy", "world economy", and "global financial stability" are equivalent to the variables in Example 2, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x is an important component of x and an important support to promote x" (where x represents blank) is equivalent to the linear structure of Example 2, which is the constant of language, because the ...

example 4

[0048] By analyzing the above two examples, it can be found that "Avatar" and "China" are equivalent to the variables in Example 3, because by replacing the corresponding parts (ie variables), their semantic meaning can basically be preserved. And "x boom sweeps x" (where x represents blank) is equivalent to the linear structure of example 3, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0049] Similarly, "stock trading" and "world" are equivalent to the variables in Example 4, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x boom sweeps x" (where x represents blank) is equivalent to the linear structure of example 4, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0050] It can be found that the linear structure of the two examples is the same, the difference is only in the variables. "X craze sweep...

example 8

[0056] By analyzing the above four examples, it can be found that:

[0057] "They", "European Commission" and "Application for Market Economy Treatment of Chinese Enterprises" are equivalent to the variables in Example 5, because by replacing the corresponding parts (namely variables), their semantic meaning can basically be preserved. And "x appeals to x to treat x objectively and fairly" (where x represents blank) is equivalent to the linear structure of example 5, which is a constant of language, because the meaning of language is hidden in this linear structure.

[0058] Similarly, "FIFA", "Ireland" and "the result of the World Cup qualifier against France" are equivalent to the variables in Example 6, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x appeals to x to treat x objectively and fairly" (where x represents blank) is equivalent to the linear structure of example 6, which is a constant of language, bec...

technical field

[0001] The present invention relates to the field of natural language processing and / or search. More specifically, it relates to a conversational natural language processing method and device. Background technique

[0002] Natural language processing (Information Retrieval) refers to the process and technology of organizing information in a certain way and finding relevant information according to the needs of information users. Natural language processing in a narrow sense is the second half of the natural language processing process, that is, the process of finding the required information from the information collection, which is what we often call information search (InformationSearch or InformationSeek).

[0003] Currently commonly used natural language processing methods usually include: common method, retrospective method and segmentation method. The common law is a method of searching literature and materials by using retrieval tools such as bibliog...

Examples

example 2

[0039] By analyzing the above two examples, it can be found that:

[0040] "Rural tourism", "Chinese tourism" and "tourism development" are equivalent to the variables in Example 1, because by replacing the corresponding parts (ie variables), their semantic meaning can basically be preserved. And "x is an important part of x and an important support to promote x" (where x represents blank) is equivalent to the linear structure of Example 1, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0041] Similarly, "China's economy", "world economy", and "global financial stability" are equivalent to the variables in Example 2, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x is an important component of x and an important support to promote x" (where x represents blank) is equivalent to the linear structure of Example 2, which is the constant of language, because the ...

example 4

[0048] By analyzing the above two examples, it can be found that "Avatar" and "China" are equivalent to the variables in Example 3, because by replacing the corresponding parts (ie variables), their semantic meaning can basically be preserved. And "x boom sweeps x" (where x represents blank) is equivalent to the linear structure of example 3, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0049] Similarly, "stock trading" and "world" are equivalent to the variables in Example 4, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x boom sweeps x" (where x represents blank) is equivalent to the linear structure of example 4, which is the constant of language, because the meaning of language is hidden in this linear structure.

[0050] It can be found that the linear structure of the two examples is the same, the difference is only in the variables. "X craze sweep...

example 8

[0056] By analyzing the above four examples, it can be found that:

[0057] "They", "European Commission" and "Application for Market Economy Treatment of Chinese Enterprises" are equivalent to the variables in Example 5, because by replacing the corresponding parts (namely variables), their semantic meaning can basically be preserved. And "x appeals to x to treat x objectively and fairly" (where x represents blank) is equivalent to the linear structure of example 5, which is a constant of language, because the meaning of language is hidden in this linear structure.

[0058] Similarly, "FIFA", "Ireland" and "the result of the World Cup qualifier against France" are equivalent to the variables in Example 6, because by replacing the corresponding parts (ie variables), their semantics can basically be preserved. And "x appeals to x to treat x objectively and fairly" (where x represents blank) is equivalent to the linear structure of example 6, which is a constant of language, bec...

Images