CN113609864B - Text semantic recognition processing system and method based on industrial control system - Google Patents
Text semantic recognition processing system and method based on industrial control system Download PDFInfo
- Publication number
- CN113609864B CN113609864B CN202110899216.6A CN202110899216A CN113609864B CN 113609864 B CN113609864 B CN 113609864B CN 202110899216 A CN202110899216 A CN 202110899216A CN 113609864 B CN113609864 B CN 113609864B
- Authority
- CN
- China
- Prior art keywords
- keyword
- keywords
- speech
- grammar
- segmented
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
Abstract
The invention discloses a text semantic recognition processing system based on an industrial control system, which comprises a keyword screening module, a keyword segmentation module and a text semantic recognition processing module, wherein the keyword screening module is used for segmenting sentences in a text according to separators and segmenting keywords in the sentences after the text is segmented through a keyword segmentation database; and the keyword analysis and identification module is used for acquiring the keywords divided by the keyword screening module, comparing each keyword with the keyword analysis database and identifying the semantics and the corresponding part of speech of each keyword. The invention not only effectively improves the precision of text semantic recognition, but also enables the text semantic recognition processing system to have growth, and further effectively improves the efficiency of text semantic recognition by continuously updating each database.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a text semantic recognition processing system and method based on an industrial control system.
Background
With the rapid development of computer technology, the wide application of computer technology brings great convenience to people, and in the aspect of industrial application, people can control an industrial system through computer technology, especially in the aspect of post-processing of text data, and can effectively recognize semantic information corresponding to a text through processing text information, so that the text information can be directly processed correspondingly, and the control of industry is achieved. However, the existing industrial control system only simply identifies and processes text information through keywords, so that the identification of the text is not accurate enough, and misoperation of the industrial control system is often caused, and further the industrial process is influenced.
In view of the above situation, there is a need for a text semantic recognition processing system and method based on an industrial control system, wherein when text semantics are recognized, not only keywords in a text are analyzed, but also semantics of the keywords and grammars corresponding to statements in the text are analyzed, and for unrecognizable text statements, a manual recognition mode is adopted, and each database for performing text semantic recognition in the text semantic recognition processing system is updated according to a processing process of manual recognition.
Disclosure of Invention
The invention aims to provide a text semantic recognition processing system and method based on an industrial control system, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a text semantic recognition processing system based on an industrial control system comprises:
the keyword screening module is used for segmenting sentences in the text according to the separators and segmenting keywords in the sentences after the text is segmented through the keyword segmentation database;
the keyword analysis and identification module is used for acquiring the keywords divided by the keyword screening module, comparing each keyword with the keyword analysis database and identifying the semantics and the corresponding part of speech of each keyword;
the grammar recognition module acquires sentences obtained by segmenting the text by the keyword screening module, further analyzes corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword, and then matches the keywords with a grammar database to acquire grammars corresponding to each segmented sentence;
the text semantic recognition module is used for acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module, sequencing primary and secondary relations of part of speech at each position in the grammar, and acquiring final semantic recognition results of segmented sentences corresponding to the text by combining analysis results of the semantics and part of speech of each keyword of the keyword analysis recognition module;
the manual recognition module can automatically extract the segmentation sentences and recognize the segmentation sentences in a manual recognition mode when the grammar recognition module cannot acquire grammars corresponding to the segmentation sentences, and can automatically update the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process after recognition;
when the keyword screening module is used for segmenting sentences in a text according to the separators, firstly acquiring the separators in the text and the corresponding positions of the separators, segmenting the text into the sentences with different lengths according to the positions corresponding to the separators, storing each separator and the content between the separator and the last separator together as the segmented sentences, sequencing the segmented sentences according to the sequence of the positions of the separators in the text, and marking the segmented sentences by using sequence numbers,
if a certain separator has no previous separator, directly taking the separator and the content before the separator as a divided statement;
after the keyword screening module is used for segmenting sentences in a text, the keyword screening module can segment keywords according to the sequence numbers of segmented sentence marks from small to large, and uniformly store the keywords segmented from the segmented sentences with the same mark sequence numbers, and the method for segmenting the keywords in the sentences segmented by the keyword screening module comprises the following steps:
s1.1, extracting segmented sentences corresponding to the serial numbers of all marks according to a sequence from small to large, and acquiring the length a1 of each keyword and the length a2 corresponding to the longest keyword in a keyword segmentation database;
s1.2, taking the current recognition position in the segmented sentence extracted in the step S1.1 as a recognition starting point;
s1.3, judging the length a3 from the identified starting point to the delimiter in the segmented sentence, comparing a2 with a3, correcting the keyword comparison length a4 according to the comparison result, wherein a4 is used for acquiring the keyword length to be compared, the initial value of a4 is 0,
when a3 is greater than or equal to a2, the value of a4 is corrected to make the value of a4 equal to the value of a2,
when a3 is less than a2, correcting the value of a4 so that the value of a4 is equal to the value of a 3;
s1.4, obtaining the content with the length of a4 from the starting point to the back of the starting point in the segmented sentence, marking as a comparison keyword b1, obtaining all keywords with the length of a4 in the keyword screening database, marking as a keyword b2 to be compared, comparing b1 with b2,
when the b1 is the same as one of the b2, the content of b1 is determined to be the segmented keyword, the length of b1 is recorded as the final keyword comparison length a5,
when the keywords in b1 and b2 are different, the length of the comparison keyword needs to be adjusted;
s1.5, when the keywords in b1 and b2 are different, obtaining the value of a4 in the step S1.4, correcting the value of a4, namely subtracting 1 from the value of a4, taking the obtained result as a new value of a4,
b1 and b2 are corrected, the content corresponding to a new a4 from the starting point to the position after the starting point in the segmented sentence is obtained, the obtained result is marked as a new b1, all keywords with the length equal to the new a4 in the keyword screening database are obtained and marked as new b2, the new b1 is compared with the new b2,
when the new b1 is the same as one of the new b2, the content of the new b1 is determined to be the segmented keyword, the length of the new b1 is recorded as the final keyword comparison length a5,
when the keywords in the new b1 and the new b2 are different from each other, the length of the comparison keyword needs to be adjusted, that is, the step is repeated until the segmented keyword is obtained, and the length of the obtained segmented keyword is recorded as the final keyword comparison length a 5;
s1.6, obtaining a starting point in the segmented sentence and the final keyword comparison length a5 corresponding to the starting point, then moving backwards by the length corresponding to the value of a5 by taking the starting point as the starting point, taking the obtained result as a new starting point in the segmented sentence, and starting to execute again from the step S1.3 according to the obtained new starting point until the content behind the starting point in the segmented sentence is a separator;
the keyword analysis and identification module acquires the keywords divided by the keyword screening module, different semantics and parts of speech are bound to different keywords in the keyword analysis database, and one keyword can be bound with multiple semantics or parts of speech, the keywords bound in the keyword analysis database correspond to the keywords in the keyword screening database one by one,
obtaining the keywords to be compared, calculating the length c1 of the keywords, screening out all bound keywords with the length c1 in a keyword analysis database, matching the screened keywords with the keywords to be compared,
obtaining semantics and parts of speech corresponding to the keywords which are the same as the keywords to be compared in the screened keywords, binding the obtained result with the keywords to be compared, and storing the result;
the method for matching the part of speech and the corresponding position of the processed keyword with the grammar database comprises the following steps of:
s2.1, acquiring the parts of speech of the processed keywords one by one according to the position sequence, and numbering the acquired parts of speech according to the acquired sequence, wherein the maximum number is n;
s2.2, screening the grammar with the part of speech same as the part of speech with the number of 1 in the grammar database according to the part of speech with the number of 1, and recording the obtained result as d 1;
s2.3, further screening the grammar in the d1 according to the part of speech with the number of 2, and recording the obtained result as d 2;
···
s2 (n +1), further screening the grammar in d (n-1) according to the part of speech with the number n, and recording the obtained result as dn;
s2, (n +2), judging whether the grammar in dn exists and the number is unique,
when the grammars in dn exist and are unique in number, the grammars in dn are judged to be the grammars corresponding to the parts of speech of the processed keywords, namely the grammars corresponding to the segmented sentences,
and when the grammar in the dn is absent or the number of the grammars is not unique, judging that the grammar corresponding to the part of speech of the processed keyword is absent, namely the grammar corresponding to the segmented sentence is absent.
The text semantic recognition processing system and the text semantic recognition processing method jointly realize effective recognition of the text by the text semantic recognition processing system through the cooperative cooperation of all the modules, analyze and process the keywords in the text, the corresponding semantics and parts of speech of the keywords and the grammar corresponding to each sentence in the text, and can effectively improve the accuracy of the text semantic recognition processing system in recognizing the text semantic. The keyword screening module realizes the segmentation of the text sentences through the separators, one separator corresponds to one text sentence, and the purpose of storing the separators after the text sentences together is to judge whether to stop segmenting the keywords in the text sentences when segmenting the keywords in the text sentences. When the keyword screening module is used for segmenting the keywords, whether the segmented content is the keywords or not is judged, and different segmented contents are obtained by adjusting the segmentation position in the judgment process. The keyword analysis module of the invention can obtain corresponding keyword semantics and part of speech by the binding relationship between the keywords and semantics and part of speech and comparing the obtained keywords with the bound keywords. Since there is a case where one keyword corresponds to different semantics or parts of speech, there may be a variety of cases in the acquired keyword semantics and parts of speech. The grammar recognition module can accurately lock the comparison result by comparing the parts of speech of the keywords one by one, and avoids the situation of error in comparison.
Further, if there is a plurality of parts of speech corresponding to a keyword in the keywords obtained by the grammar recognition module, the parts of speech of the keyword need to be judged, and the method for judging the parts of speech of the keyword by the grammar recognition module includes the following steps:
s3.1, acquiring a plurality of parts of speech corresponding to the keyword and corresponding semantics of each part of speech, judging the corresponding semantics of each part of speech,
when the corresponding semanteme of a part of speech corresponding to the keyword is related to industry, judging that the part of speech is the part of speech of the keyword, analyzing the position and the part of speech of the keyword segmented in the segmented sentence with the same mark serial number, matching the part of speech and the corresponding position of the processed keyword with a grammar database,
the method for judging whether the semantics corresponding to a part of speech corresponding to the keyword is related to the industry comprises the following steps:
A. extracting the key words from the corresponding semanteme of the part of speech corresponding to the key words,
B. respectively matching the keywords extracted in the step A with an industrial keyword database,
when the keywords extracted in the step A are not stored in the industrial keyword database, the semantics corresponding to the part of speech corresponding to the keywords are judged to be irrelevant to the industry,
when one or more of the keywords extracted in the step A are stored in an industrial keyword database, determining that the semantics corresponding to the part of speech corresponding to the keyword are related to the industry;
s3.2, when the corresponding semantics of each part of speech corresponding to the keyword are not related to the industry, combining each part of speech corresponding to the keyword and the position of the keyword with the positions and parts of speech of other keywords separated from the divided sentences with the same mark serial number respectively to obtain different combination results;
s3.3, respectively obtaining different combination results in the step S3.2, respectively analyzing and processing the position and the part of speech of each keyword in each combination result, matching the part of speech and the corresponding position of the processed keyword in each combination result with a grammar database,
s3.4, obtaining the matching result corresponding to each combination result in the step S3.3,
when no grammar is matched in the matching results corresponding to the combined results or the total number of matched grammars exceeds 1, judging that the grammar corresponding to the segmented sentence does not exist;
and when the number of the grammars matched in the matching result corresponding to each combination result is equal to 1, judging that the matched grammars are the grammars corresponding to the divided sentences.
If a keyword corresponding to multiple parts of speech exists in the keywords acquired by the grammar recognition module, the parts of speech of the keyword need to be judged, in the judging process, whether the semantics corresponding to a certain part of speech corresponding to the keyword are related to industry is judged firstly, if so, the part of speech is more reasonable, the probability that the keyword is the part of speech in the segmented sentence is higher, if not, the part of speech of the keyword needs to be combined with the parts of speech corresponding to other keywords respectively and matched with a grammar database, and if only one matching result exists, the probability that the part of speech of the keyword corresponding to the matching result is correct is higher.
Furthermore, the text semantic recognition module acquires the recognition result of each segmented sentence grammar in the text in the grammar recognition module, judges the part of speech of each position in the recognized grammar, divides the part of speech into two classes according to the primary and secondary relations, the first class is a main class and comprises the part of speech containing substantive content in the grammar, the second class is a secondary class and comprises the part of speech containing decorative content in the grammar,
extracting keywords corresponding to the word characters in the segmented sentences in the main class corresponding to the grammar of the segmented sentences in the text, marking the keywords as e, splicing and combining the semantics corresponding to the keywords in the e according to the appearance sequence of the keywords to obtain a semantic splicing result, wherein the semantic splicing result is the final semantic recognition result of the segmented sentences corresponding to the text.
The text semantic recognition module divides the recognized semantic information into a primary category and a secondary category according to the part of speech, the information of the secondary category belongs to modified content, the influence on the whole recognition information is not great, and meanwhile, the more the recognized content is, the more combination situations appear when the text semantic recognition processing system analyzes the recognized content are, the slower the processing effect is, therefore, the information is simplified, only the main information is reserved, the influence on the recognized content is not great, the efficiency of the text semantic recognition processing system in analyzing the recognized content can be effectively improved, and the time of data analysis is saved.
Further, the text semantic recognition module obtains the segmented sentences corresponding to the serial numbers of the marks obtained after the text segmentation, performs semantic recognition on the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers, respectively obtains the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks, and summarizes the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers,
in the process of performing semantic recognition or summarization, when the grammar corresponding to the segmented sentence corresponding to the sequence number of a certain mark does not exist, the segmented sentence corresponding to the sequence number of the mark is directly skipped, and the semantic recognition or summarization is performed on the segmented sentence corresponding to the sequence number of the next mark.
In the process of recognizing the text, the text semantic recognition module recognizes the segmented sentences according to the sequence, and simultaneously processes the situation that the grammar corresponding to the segmented sentences corresponding to the sequence numbers of certain marks does not exist in the process of semantic recognition or summarization, thereby ensuring the normal operation of the text semantic recognition processing system.
Further, when the grammar recognition module can not obtain the grammar corresponding to the segmentation sentence, the segmentation sentences are automatically extracted and identified by a manual identification mode, after recognition, the manual recognition module automatically records the segmented keywords and the corresponding semantics and parts of speech of each keyword in the manual recognition process, extracts the keywords which are not in the keyword segmentation data in the segmented keywords, adding the extracted keywords which do not exist in the keyword segmentation data into the bound keywords in the keyword analysis database, and adding the extracted semantics and parts of speech which do not exist in the keyword segmentation data into the semantics and parts of speech which correspond to the bound keywords in the keyword analysis database;
the manual recognition module can also automatically record the grammar recognized in the manual recognition process, judge whether the grammar exists in the grammar database, and if the grammar does not exist, add the grammar to the grammar database.
The manual identification module stores the data in the manual identification process and updates each database according to the stored data, so that the text semantic identification processing system has growth, and the efficiency of text semantic identification is effectively improved.
A text semantic recognition processing method based on an industrial control system comprises the following steps:
s1, the keyword screening module divides sentences in the text according to the separators, and the keywords in the sentences after the text division are divided through the keyword division database;
s2, obtaining the keywords divided by the keyword screening module through the keyword analyzing and identifying module, comparing each keyword with the keyword analyzing database, and identifying the semantics and the corresponding part of speech of each keyword;
s3, sentences segmented by the text by the keyword screening module are obtained by the grammar recognition module, corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword are further analyzed, and then the sentences are matched with a grammar database to obtain grammars corresponding to each segmented sentence;
s4, acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module through the text semantic recognition module, sequencing the primary and secondary relations of the part of speech of each position in the grammar, and acquiring the final semantic recognition results of the segmented sentences corresponding to the text by combining the analysis results of the keyword analysis recognition module on the semantics and the part of speech of each keyword;
and S5, when the grammar recognition module cannot acquire the grammar corresponding to the segmentation sentence, the manual recognition module automatically extracts the segmentation sentence, recognizes the segmentation sentence in a manual recognition mode, and after recognition, the manual recognition module automatically updates the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process.
Compared with the prior art, the invention has the following beneficial effects: when the text semantics are recognized, the method analyzes not only the keywords in the text, but also the semantics and the part of speech of the keywords and the corresponding grammar of each sentence in the text, adopts a manual recognition mode aiming at the text sentences which cannot be recognized, and updates each database for performing text semantics recognition in the text semantics recognition processing system according to the processing process of manual recognition.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic structural diagram of a text semantic recognition processing system based on an industrial control system according to the present invention;
FIG. 2 is a schematic flow chart of a method for segmenting keywords in sentences after text segmentation by a keyword screening module of a text semantic recognition processing system based on an industrial control system according to the present invention;
FIG. 3 is a flow chart of a method for matching parts of speech and corresponding positions of keywords processed in a grammar recognition module of a text semantic recognition processing system based on an industrial control system with a grammar database according to the invention;
FIG. 4 is a flow chart of a part-of-speech determination method for keywords by a grammar recognition module in a text semantic recognition processing system based on an industrial control system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-4, the present invention provides the following technical solutions: a text semantic recognition processing system based on an industrial control system comprises:
the keyword screening module is used for segmenting sentences in the text according to the separators and segmenting keywords in the sentences after the text is segmented through the keyword segmentation database;
the keyword analysis and identification module is used for acquiring the keywords divided by the keyword screening module, comparing each keyword with the keyword analysis database and identifying the semantics and the corresponding part of speech of each keyword;
the grammar recognition module acquires sentences obtained by segmenting the text by the keyword screening module, further analyzes corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword, and then matches the keywords with a grammar database to acquire grammars corresponding to each segmented sentence;
the text semantic recognition module is used for acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module, sequencing primary and secondary relations of part of speech at each position in the grammar, and acquiring final semantic recognition results of segmented sentences corresponding to the text by combining analysis results of the semantics and part of speech of each keyword of the keyword analysis recognition module;
the manual recognition module can automatically extract the segmentation sentences and recognize the segmentation sentences in a manual recognition mode when the grammar recognition module cannot acquire grammars corresponding to the segmentation sentences, and can automatically update the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process after recognition;
when the keyword screening module is used for segmenting sentences in a text according to the separators, firstly acquiring the separators in the text and the corresponding positions of the separators, segmenting the text into the sentences with different lengths according to the positions corresponding to the separators, storing each separator and the content between the separator and the last separator together as the segmented sentences, sequencing the segmented sentences according to the sequence of the positions of the separators in the text, and marking the segmented sentences by using sequence numbers,
if a certain separator has no previous separator, directly taking the separator and the content before the separator as a divided statement;
after the keyword screening module is used for segmenting sentences in a text, the keyword screening module can segment keywords according to the sequence numbers of segmented sentence marks from small to large, and uniformly store the keywords segmented from the segmented sentences with the same mark sequence numbers, and the method for segmenting the keywords in the sentences segmented by the keyword screening module comprises the following steps:
s1.1, extracting segmented sentences corresponding to the serial numbers of all marks according to a sequence from small to large, and acquiring the length a1 of each keyword and the length a2 corresponding to the longest keyword in a keyword segmentation database;
s1.2, taking the current recognition position in the segmented sentence extracted in the step S1.1 as a recognition starting point;
s1.3, judging the length a3 from the identified starting point to the delimiter in the segmented sentence, comparing a2 with a3, correcting the keyword comparison length a4 according to the comparison result, wherein a4 is used for acquiring the keyword length to be compared, the initial value of a4 is 0,
when a3 is greater than or equal to a2, the value of a4 is corrected to make the value of a4 equal to the value of a2,
when a3 is less than a2, correcting the value of a4 so that the value of a4 is equal to the value of a 3;
s1.4, obtaining the content with the length of a4 from the starting point to the back of the starting point in the segmented sentence, marking as a comparison keyword b1, obtaining all keywords with the length of a4 in the keyword screening database, marking as a keyword b2 to be compared, comparing b1 with b2,
when the b1 is the same as one of the b2, the content of b1 is determined to be the segmented keyword, the length of b1 is recorded as the final keyword comparison length a5,
when the keywords in b1 and b2 are different, the length of the comparison keyword needs to be adjusted;
s1.5, when the keywords in b1 and b2 are different, obtaining the value of a4 in the step S1.4, correcting the value of a4, namely subtracting 1 from the value of a4, taking the obtained result as a new value of a4,
b1 and b2 are corrected, the content corresponding to a new a4 from the starting point to the position after the starting point in the segmented sentence is obtained, the obtained result is marked as a new b1, all keywords with the length equal to the new a4 in the keyword screening database are obtained and marked as new b2, the new b1 is compared with the new b2,
when the new b1 is the same as one of the new b2, the content of the new b1 is determined to be the segmented keyword, the length of the new b1 is recorded as the final keyword comparison length a5,
when the keywords in the new b1 and the new b2 are different from each other, the length of the comparison keyword needs to be adjusted, that is, the step is repeated until the segmented keyword is obtained, and the length of the obtained segmented keyword is recorded as the final keyword comparison length a 5;
s1.6, obtaining a starting point in the segmented sentence and the final keyword comparison length a5 corresponding to the starting point, then moving backwards by the length corresponding to the value of a5 by taking the starting point as the starting point, taking the obtained result as a new starting point in the segmented sentence, and starting to execute again from the step S1.3 according to the obtained new starting point until the content behind the starting point in the segmented sentence is a separator;
the keyword analysis and identification module acquires the keywords divided by the keyword screening module, different semantics and parts of speech are bound to different keywords in the keyword analysis database, and one keyword can be bound with multiple semantics or parts of speech, the keywords bound in the keyword analysis database correspond to the keywords in the keyword screening database one by one,
obtaining the keywords to be compared, calculating the length c1 of the keywords, screening out all bound keywords with the length c1 in a keyword analysis database, matching the screened keywords with the keywords to be compared,
obtaining semantics and parts of speech corresponding to the keywords which are the same as the keywords to be compared in the screened keywords, binding the obtained result with the keywords to be compared, and storing the result;
the method for matching the part of speech and the corresponding position of the processed keyword with the grammar database comprises the following steps of:
s2.1, acquiring the parts of speech of the processed keywords one by one according to the position sequence, and numbering the acquired parts of speech according to the acquired sequence, wherein the maximum number is n;
s2.2, screening the grammar with the part of speech same as the part of speech with the number of 1 in the grammar database according to the part of speech with the number of 1, and recording the obtained result as d 1;
s2.3, further screening the grammar in the d1 according to the part of speech with the number of 2, and recording the obtained result as d 2;
···
s2 (n +1), further screening the grammar in d (n-1) according to the part of speech with the number n, and recording the obtained result as dn;
s2, (n +2), judging whether the grammar in dn exists and the number is unique,
when the grammars in dn exist and are unique in number, the grammars in dn are judged to be the grammars corresponding to the parts of speech of the processed keywords, namely the grammars corresponding to the segmented sentences,
and when the grammar in the dn is absent or the number of the grammars is not unique, judging that the grammar corresponding to the part of speech of the processed keyword is absent, namely the grammar corresponding to the segmented sentence is absent.
The text semantic recognition processing system and the text semantic recognition processing method jointly realize effective recognition of the text by the text semantic recognition processing system through the cooperative cooperation of all the modules, analyze and process the keywords in the text, the corresponding semantics and parts of speech of the keywords and the grammar corresponding to each sentence in the text, and can effectively improve the accuracy of the text semantic recognition processing system in recognizing the text semantic. The keyword screening module realizes the segmentation of the text sentences through the separators, one separator corresponds to one text sentence, and the purpose of storing the separators after the text sentences together is to judge whether to stop segmenting the keywords in the text sentences when segmenting the keywords in the text sentences. When the keyword screening module is used for segmenting the keywords, whether the segmented content is the keywords or not is judged, and different segmented contents are obtained by adjusting the segmentation position in the judgment process. The keyword analysis module of the invention can obtain corresponding keyword semantics and part of speech by the binding relationship between the keywords and semantics and part of speech and comparing the obtained keywords with the bound keywords. Since there is a case where one keyword corresponds to different semantics or parts of speech, there may be a variety of cases in the acquired keyword semantics and parts of speech. The grammar recognition module can accurately lock the comparison result by comparing the parts of speech of the keywords one by one, and avoids the situation of error in comparison.
If one keyword in the keywords acquired by the grammar recognition module corresponds to multiple parts of speech, the parts of speech of the keyword need to be judged, and the method for judging the parts of speech of the keyword by the grammar recognition module comprises the following steps:
s3.1, acquiring a plurality of parts of speech corresponding to the keyword and corresponding semantics of each part of speech, judging the corresponding semantics of each part of speech,
when the corresponding semanteme of a part of speech corresponding to the keyword is related to industry, judging that the part of speech is the part of speech of the keyword, analyzing the position and the part of speech of the keyword segmented in the segmented sentence with the same mark serial number, matching the part of speech and the corresponding position of the processed keyword with a grammar database,
the method for judging whether the semantics corresponding to a part of speech corresponding to the keyword is related to the industry comprises the following steps:
C. extracting the key words from the corresponding semanteme of the part of speech corresponding to the key words,
D. respectively matching the keywords extracted in the step A with an industrial keyword database,
when the keywords extracted in the step A are not stored in the industrial keyword database, the semantics corresponding to the part of speech corresponding to the keywords are judged to be irrelevant to the industry,
when one or more of the keywords extracted in the step A are stored in an industrial keyword database, determining that the semantics corresponding to the part of speech corresponding to the keyword are related to the industry;
s3.2, when the corresponding semantics of each part of speech corresponding to the keyword are not related to the industry, combining each part of speech corresponding to the keyword and the position of the keyword with the positions and parts of speech of other keywords separated from the divided sentences with the same mark serial number respectively to obtain different combination results;
s3.3, respectively obtaining different combination results in the step S3.2, respectively analyzing and processing the position and the part of speech of each keyword in each combination result, matching the part of speech and the corresponding position of the processed keyword in each combination result with a grammar database,
s3.4, obtaining the matching result corresponding to each combination result in the step S3.3,
when no grammar is matched in the matching results corresponding to the combined results or the total number of matched grammars exceeds 1, judging that the grammar corresponding to the segmented sentence does not exist;
and when the number of the grammars matched in the matching result corresponding to each combination result is equal to 1, judging that the matched grammars are the grammars corresponding to the divided sentences.
If a keyword corresponding to multiple parts of speech exists in the keywords acquired by the grammar recognition module, the parts of speech of the keyword need to be judged, in the judging process, whether the semantics corresponding to a certain part of speech corresponding to the keyword are related to industry is judged firstly, if so, the part of speech is more reasonable, the probability that the keyword is the part of speech in the segmented sentence is higher, if not, the part of speech of the keyword needs to be combined with the parts of speech corresponding to other keywords respectively and matched with a grammar database, and if only one matching result exists, the probability that the part of speech of the keyword corresponding to the matching result is correct is higher.
The text semantic recognition module acquires the recognition result of each segmented sentence grammar in the text in the grammar recognition module, judges the part of speech of each position in the recognized grammar, and divides the part of speech into two classes according to the primary and secondary relations, wherein the first class is a main class and comprises the part of speech containing substantive content in the grammar, the second class is a secondary class and comprises the part of speech containing decorative content in the grammar,
extracting keywords corresponding to the word characters in the segmented sentences in the main class corresponding to the grammar of the segmented sentences in the text, marking the keywords as e, splicing and combining the semantics corresponding to the keywords in the e according to the appearance sequence of the keywords to obtain a semantic splicing result, wherein the semantic splicing result is the final semantic recognition result of the segmented sentences corresponding to the text.
The text semantic recognition module divides the recognized semantic information into a primary category and a secondary category according to the part of speech, the information of the secondary category belongs to modified content, the influence on the whole recognition information is not great, and meanwhile, the more the recognized content is, the more combination situations appear when the text semantic recognition processing system analyzes the recognized content are, the slower the processing effect is, therefore, the information is simplified, only the main information is reserved, the influence on the recognized content is not great, the efficiency of the text semantic recognition processing system in analyzing the recognized content can be effectively improved, and the time of data analysis is saved.
The text semantic recognition module acquires the segmented sentences corresponding to the serial numbers of the marks obtained after the text segmentation, performs semantic recognition on the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers, respectively obtains the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks, and summarizes the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers,
in the process of performing semantic recognition or summarization, when the grammar corresponding to the segmented sentence corresponding to the sequence number of a certain mark does not exist, the segmented sentence corresponding to the sequence number of the mark is directly skipped, and the semantic recognition or summarization is performed on the segmented sentence corresponding to the sequence number of the next mark.
In the process of recognizing the text, the text semantic recognition module recognizes the segmented sentences according to the sequence, and simultaneously processes the situation that the grammar corresponding to the segmented sentences corresponding to the sequence numbers of certain marks does not exist in the process of semantic recognition or summarization, thereby ensuring the normal operation of the text semantic recognition processing system.
The manual recognition module can automatically extract the segmentation sentences when the grammar recognition module cannot acquire grammars corresponding to the segmentation sentences, and recognize the segmentation sentences in a manual recognition mode, after recognition, the manual recognition module can automatically record keywords segmented in the manual recognition process and semantics and parts of speech corresponding to the keywords, extract the keywords which do not exist in the keyword segmentation data in the segmented keywords and add the extracted keywords which do not exist in the keyword segmentation data into bound keywords in a keyword analysis database, and add the extracted semantics and parts of speech corresponding to the keywords which do not exist in the keyword segmentation data into the semantics and parts of speech corresponding to the bound keywords in the keyword analysis database;
the manual recognition module can also automatically record the grammar recognized in the manual recognition process, judge whether the grammar exists in the grammar database, and if the grammar does not exist, add the grammar to the grammar database.
The manual identification module stores the data in the manual identification process and updates each database according to the stored data, so that the text semantic identification processing system has growth, and the efficiency of text semantic identification is effectively improved.
A text semantic recognition processing method based on an industrial control system comprises the following steps:
s1, the keyword screening module divides sentences in the text according to the separators, and the keywords in the sentences after the text division are divided through the keyword division database;
s2, obtaining the keywords divided by the keyword screening module through the keyword analyzing and identifying module, comparing each keyword with the keyword analyzing database, and identifying the semantics and the corresponding part of speech of each keyword;
s3, sentences segmented by the text by the keyword screening module are obtained by the grammar recognition module, corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword are further analyzed, and then the sentences are matched with a grammar database to obtain grammars corresponding to each segmented sentence;
s4, acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module through the text semantic recognition module, sequencing the primary and secondary relations of the part of speech of each position in the grammar, and acquiring the final semantic recognition results of the segmented sentences corresponding to the text by combining the analysis results of the keyword analysis recognition module on the semantics and the part of speech of each keyword;
and S5, when the grammar recognition module cannot acquire the grammar corresponding to the segmentation sentence, the manual recognition module automatically extracts the segmentation sentence, recognizes the segmentation sentence in a manual recognition mode, and after recognition, the manual recognition module automatically updates the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A text semantic recognition processing system based on an industrial control system is characterized by comprising:
the keyword screening module is used for segmenting sentences in the text according to the separators and segmenting keywords in the sentences after the text is segmented through the keyword segmentation database;
the keyword analysis and identification module is used for acquiring the keywords divided by the keyword screening module, comparing each keyword with the keyword analysis database and identifying the semantics and the corresponding part of speech of each keyword;
the grammar recognition module acquires sentences obtained by segmenting the text by the keyword screening module, further analyzes corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword, and then matches the keywords with a grammar database to acquire grammars corresponding to each segmented sentence;
the text semantic recognition module is used for acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module, sequencing primary and secondary relations of part of speech at each position in the grammar, and acquiring final semantic recognition results of segmented sentences corresponding to the text by combining analysis results of the semantics and part of speech of each keyword of the keyword analysis recognition module;
the manual recognition module can automatically extract the segmentation sentences and recognize the segmentation sentences in a manual recognition mode when the grammar recognition module cannot acquire grammars corresponding to the segmentation sentences, and can automatically update the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process after recognition;
when the keyword screening module is used for segmenting sentences in a text according to the separators, firstly acquiring the separators in the text and the corresponding positions of the separators, segmenting the text into the sentences with different lengths according to the positions corresponding to the separators, storing each separator and the content between the separator and the last separator together as the segmented sentences, sequencing the segmented sentences according to the sequence of the positions of the separators in the text, and marking the segmented sentences by using sequence numbers,
if a certain separator has no previous separator, directly taking the separator and the content before the separator as a divided statement;
after the keyword screening module is used for segmenting sentences in a text, the keyword screening module can segment keywords according to the sequence numbers of segmented sentence marks from small to large, and uniformly store the keywords segmented from the segmented sentences with the same mark sequence numbers, and the method for segmenting the keywords in the sentences segmented by the keyword screening module comprises the following steps:
s1.1, extracting segmented sentences corresponding to the serial numbers of all marks according to a sequence from small to large, and acquiring the length a1 of each keyword and the length a2 corresponding to the longest keyword in a keyword segmentation database;
s1.2, taking the current recognition position in the segmented sentence extracted in the step S1.1 as a recognition starting point;
s1.3, judging the length a3 from the identified starting point to the delimiter in the segmented sentence, comparing a2 with a3, correcting the keyword comparison length a4 according to the comparison result, wherein a4 is used for acquiring the keyword length to be compared, the initial value of a4 is 0,
when a3 is greater than or equal to a2, the value of a4 is corrected to make the value of a4 equal to the value of a2,
when a3 is less than a2, correcting the value of a4 so that the value of a4 is equal to the value of a 3;
s1.4, obtaining the content with the length of a4 from the starting point to the back of the starting point in the segmented sentence, marking as a comparison keyword b1, obtaining all keywords with the length of a4 in the keyword screening database, marking as a keyword b2 to be compared, comparing b1 with b2,
when the b1 is the same as one of the b2, the content of b1 is determined to be the segmented keyword, the length of b1 is recorded as the final keyword comparison length a5,
when the keywords in b1 and b2 are different, the length of the comparison keyword needs to be adjusted;
s1.5, when the keywords in b1 and b2 are different, obtaining the value of a4 in the step S1.4, correcting the value of a4, namely subtracting 1 from the value of a4, taking the obtained result as a new value of a4,
b1 and b2 are corrected, the content corresponding to a new a4 from the starting point to the position after the starting point in the segmented sentence is obtained, the obtained result is marked as a new b1, all keywords with the length equal to the new a4 in the keyword screening database are obtained and marked as new b2, the new b1 is compared with the new b2,
when the new b1 is the same as one of the new b2, the content of the new b1 is determined to be the segmented keyword, the length of the new b1 is recorded as the final keyword comparison length a5,
when the keywords in the new b1 and the new b2 are different from each other, the length of the comparison keyword needs to be adjusted, that is, the step is repeated until the segmented keyword is obtained, and the length of the obtained segmented keyword is recorded as the final keyword comparison length a 5;
s1.6, obtaining a starting point in the segmented sentence and the final keyword comparison length a5 corresponding to the starting point, then moving backwards by the length corresponding to the value of a5 by taking the starting point as the starting point, taking the obtained result as a new starting point in the segmented sentence, and starting to execute again from the step S1.3 according to the obtained new starting point until the content behind the starting point in the segmented sentence is a separator;
the keyword analysis and identification module acquires the keywords divided by the keyword screening module, different semantics and parts of speech are bound to different keywords in the keyword analysis database, and one keyword can be bound with multiple semantics or parts of speech, the keywords bound in the keyword analysis database correspond to the keywords in the keyword screening database one by one,
obtaining the keywords to be compared, calculating the length c1 of the keywords, screening out all bound keywords with the length c1 in a keyword analysis database, matching the screened keywords with the keywords to be compared,
obtaining semantics and parts of speech corresponding to the keywords which are the same as the keywords to be compared in the screened keywords, binding the obtained result with the keywords to be compared, and storing the result;
the method for matching the part of speech and the corresponding position of the processed keyword with the grammar database comprises the following steps of:
s2.1, acquiring the parts of speech of the processed keywords one by one according to the position sequence, and numbering the acquired parts of speech according to the acquired sequence, wherein the maximum number is n;
s2.2, screening the grammar with the part of speech same as the part of speech with the number of 1 in the grammar database according to the part of speech with the number of 1, and recording the obtained result as d 1;
s2.3, further screening the grammar in the d1 according to the part of speech with the number of 2, and recording the obtained result as d 2;
···
s2 (n +1), further screening the grammar in d (n-1) according to the part of speech with the number n, and recording the obtained result as dn;
s2, (n +2), judging whether the grammar in dn exists and the number is unique,
when the grammars in dn exist and are unique in number, the grammars in dn are judged to be the grammars corresponding to the parts of speech of the processed keywords, namely the grammars corresponding to the segmented sentences,
and when the grammar in the dn is absent or the number of the grammars is not unique, judging that the grammar corresponding to the part of speech of the processed keyword is absent, namely the grammar corresponding to the segmented sentence is absent.
2. The text semantic recognition processing system based on the industrial control system as claimed in claim 1, characterized in that: if one keyword in the keywords acquired by the grammar recognition module corresponds to multiple parts of speech, the parts of speech of the keyword need to be judged, and the method for judging the parts of speech of the keyword by the grammar recognition module comprises the following steps:
s3.1, acquiring a plurality of parts of speech corresponding to the keyword and corresponding semantics of each part of speech, judging the corresponding semantics of each part of speech,
when the corresponding semanteme of a part of speech corresponding to the keyword is related to industry, judging that the part of speech is the part of speech of the keyword, analyzing the position and the part of speech of the keyword segmented in the segmented sentence with the same mark serial number, matching the part of speech and the corresponding position of the processed keyword with a grammar database,
the method for judging whether the semantics corresponding to a part of speech corresponding to the keyword is related to the industry comprises the following steps:
A. extracting the key words from the corresponding semanteme of the part of speech corresponding to the key words,
B. respectively matching the keywords extracted in the step A with an industrial keyword database,
when the keywords extracted in the step A are not stored in the industrial keyword database, the semantics corresponding to the part of speech corresponding to the keywords are judged to be irrelevant to the industry,
when one or more of the keywords extracted in the step A are stored in an industrial keyword database, determining that the semantics corresponding to the part of speech corresponding to the keyword are related to the industry;
s3.2, when the corresponding semantics of each part of speech corresponding to the keyword are not related to the industry, combining each part of speech corresponding to the keyword and the position of the keyword with the positions and parts of speech of other keywords separated from the divided sentences with the same mark serial number respectively to obtain different combination results;
s3.3, respectively obtaining different combination results in the step S3.2, respectively analyzing and processing the position and the part of speech of each keyword in each combination result, and matching the part of speech and the corresponding position of the processed keyword in each combination result with a grammar database;
s3.4, obtaining the matching result corresponding to each combination result in the step S3.3,
when no grammar is matched in the matching results corresponding to the combined results or the total number of matched grammars exceeds 1, judging that the grammar corresponding to the segmented sentence does not exist;
and when the number of the grammars matched in the matching result corresponding to each combination result is equal to 1, judging that the matched grammars are the grammars corresponding to the divided sentences.
3. The text semantic recognition processing system based on the industrial control system as claimed in claim 2, characterized in that: the text semantic recognition module acquires the recognition result of each segmented sentence grammar in the text in the grammar recognition module, judges the part of speech of each position in the recognized grammar, and divides the part of speech into two classes according to the primary and secondary relations, wherein the first class is a main class and comprises the part of speech containing substantive content in the grammar, the second class is a secondary class and comprises the part of speech containing decorative content in the grammar,
extracting keywords corresponding to the word characters in the segmented sentences in the main class corresponding to the grammar of the segmented sentences in the text, marking the keywords as e, splicing and combining the semantics corresponding to the keywords in the e according to the appearance sequence of the keywords to obtain a semantic splicing result, wherein the semantic splicing result is the final semantic recognition result of the segmented sentences corresponding to the text.
4. The text semantic recognition processing system based on the industrial control system as claimed in claim 3, characterized in that: the text semantic recognition module acquires the segmented sentences corresponding to the serial numbers of the marks obtained after the text segmentation, performs semantic recognition on the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers, respectively obtains the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks, and summarizes the final semantic recognition results corresponding to the segmented sentences corresponding to the serial numbers of the marks according to the sequence from small to large of the serial numbers,
in the process of performing semantic recognition or summarization, when the grammar corresponding to the segmented sentence corresponding to the sequence number of a certain mark does not exist, the segmented sentence corresponding to the sequence number of the mark is directly skipped, and the semantic recognition or summarization is performed on the segmented sentence corresponding to the sequence number of the next mark.
5. The text semantic recognition processing system based on the industrial control system as claimed in claim 4, wherein: the manual recognition module can automatically extract the segmentation sentences when the grammar recognition module cannot acquire grammars corresponding to the segmentation sentences, and recognize the segmentation sentences in a manual recognition mode, after recognition, the manual recognition module can automatically record keywords segmented in the manual recognition process and semantics and parts of speech corresponding to the keywords, extract the keywords which do not exist in the keyword segmentation data in the segmented keywords and add the extracted keywords which do not exist in the keyword segmentation data into bound keywords in a keyword analysis database, and add the extracted semantics and parts of speech corresponding to the keywords which do not exist in the keyword segmentation data into the semantics and parts of speech corresponding to the bound keywords in the keyword analysis database;
the manual recognition module can also automatically record the grammar recognized in the manual recognition process, judge whether the grammar exists in the grammar database, and if the grammar does not exist, add the grammar to the grammar database.
6. The text semantic recognition processing method based on the industrial control system of the text semantic recognition processing system based on the industrial control system, which is characterized by applying any one of the claims 1 to 5, is as follows: the method comprises the following steps:
s1, the keyword screening module divides sentences in the text according to the separators, and the keywords in the sentences after the text division are divided through the keyword division database;
s2, obtaining the keywords divided by the keyword screening module through the keyword analyzing and identifying module, comparing each keyword with the keyword analyzing database, and identifying the semantics and the corresponding part of speech of each keyword;
s3, sentences segmented by the text by the keyword screening module are obtained by the grammar recognition module, corresponding keywords in each segmented sentence and corresponding semantics and parts of speech of each keyword are further analyzed, and then the sentences are matched with a grammar database to obtain grammars corresponding to each segmented sentence;
s4, acquiring recognition results of each segmented sentence grammar in the text in the grammar recognition module through the text semantic recognition module, sequencing the primary and secondary relations of the part of speech of each position in the grammar, and acquiring the final semantic recognition results of the segmented sentences corresponding to the text by combining the analysis results of the keyword analysis recognition module on the semantics and the part of speech of each keyword;
and S5, when the grammar recognition module cannot acquire the grammar corresponding to the segmentation sentence, the manual recognition module automatically extracts the segmentation sentence, recognizes the segmentation sentence in a manual recognition mode, and after recognition, the manual recognition module automatically updates the keyword segmentation database, the keyword analysis database and the grammar database according to the manual recognition process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110899216.6A CN113609864B (en) | 2021-08-06 | 2021-08-06 | Text semantic recognition processing system and method based on industrial control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110899216.6A CN113609864B (en) | 2021-08-06 | 2021-08-06 | Text semantic recognition processing system and method based on industrial control system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113609864A CN113609864A (en) | 2021-11-05 |
| CN113609864B true CN113609864B (en) | 2022-02-11 |
Family
ID=78307312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110899216.6A Active CN113609864B (en) | 2021-08-06 | 2021-08-06 | Text semantic recognition processing system and method based on industrial control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113609864B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114328389B (en) * | 2021-12-31 | 2022-06-17 | 浙江汇鼎华链科技有限公司 | Big data file analysis processing system and method under cloud computing environment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304374A (en) * | 2017-10-27 | 2018-07-20 | 深圳市腾讯计算机系统有限公司 | Information processing method and related product |
| CN109448493A (en) * | 2018-12-27 | 2019-03-08 | 中国电子科技集团公司第十五研究所 | Tower control simulated training system, voice control order identify and enter for method |
| CN110232112A (en) * | 2019-05-31 | 2019-09-13 | 北京创鑫旅程网络技术有限公司 | Keyword extracting method and device in article |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110347787B (en) * | 2019-06-12 | 2022-12-09 | 平安科技（深圳）有限公司 | Interview method and device based on AI auxiliary interview scene and terminal equipment |
| CN112035506A (en) * | 2019-10-28 | 2020-12-04 | 竹间智能科技（上海）有限公司 | Semantic recognition method and equipment |
| CN111079442B (en) * | 2019-12-20 | 2021-05-18 | 北京百度网讯科技有限公司 | Vectorization representation method and device of document and computer equipment |
| CN111144100B (en) * | 2019-12-24 | 2023-08-18 | 五八有限公司 | Question text recognition method and device, electronic equipment and storage medium |
| CN113095080B (en) * | 2021-06-08 | 2021-08-06 | 腾讯科技（深圳）有限公司 | Theme-based semantic recognition method and device, electronic equipment and storage medium |
-
2021
- 2021-08-06 CN CN202110899216.6A patent/CN113609864B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108304374A (en) * | 2017-10-27 | 2018-07-20 | 深圳市腾讯计算机系统有限公司 | Information processing method and related product |
| CN109448493A (en) * | 2018-12-27 | 2019-03-08 | 中国电子科技集团公司第十五研究所 | Tower control simulated training system, voice control order identify and enter for method |
| CN110232112A (en) * | 2019-05-31 | 2019-09-13 | 北京创鑫旅程网络技术有限公司 | Keyword extracting method and device in article |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113609864A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108304372B (en) | Entity extraction method and device, computer equipment and storage medium | |
| CN107045496B (en) | Error correction method and error correction device for text after voice recognition | |
| CN109697162B (en) | Software defect automatic detection method based on open source code library | |
| CN108027814B (en) | Stop word recognition method and device | |
| CN110941720B (en) | Knowledge base-based specific personnel information error correction method | |
| CN114036930A (en) | Text error correction method, device, equipment and computer readable medium | |
| CN110119510A (en) | A kind of Relation extraction method and device based on transmitting dependence and structural auxiliary word | |
| CN112395392A (en) | Intention identification method and device and readable storage medium | |
| CN110399493B (en) | Author disambiguation method based on incremental learning | |
| CN113609864B (en) | Text semantic recognition processing system and method based on industrial control system | |
| CN108920500B (en) | Time analysis method | |
| CN114357206A (en) | Education video color subtitle generation method and system based on semantic analysis | |
| CN112380848B (en) | Text generation method, device, equipment and storage medium | |
| CN113642327A (en) | Method and device for constructing standard knowledge base | |
| CN113761137B (en) | Method and device for extracting address information | |
| CN109960707B (en) | College recruitment data acquisition method and system based on artificial intelligence | |
| CN111291535A (en) | Script processing method and device, electronic equipment and computer readable storage medium | |
| CN117216214A (en) | Question and answer extraction generation method, device, equipment and medium | |
| CN109325098B (en) | Reference resolution method for semantic analysis of mathematical questions | |
| CN110765107A (en) | Question type identification method and system based on digital coding | |
| CN111126201A (en) | Method and device for identifying people in script | |
| JP2000089786A (en) | Method for correcting speech recognition result and apparatus therefor | |
| CN114003750B (en) | Material online method, device, equipment and storage medium | |
| WO2021196835A1 (en) | Method and apparatus for extracting time character string, and computer device and storage medium | |
| CN114528824A (en) | Text error correction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |