CN111027319A - Method and device for analyzing natural language time words and computer equipment - Google Patents
Method and device for analyzing natural language time words and computer equipment Download PDFInfo
- Publication number
- CN111027319A CN111027319A CN201911045300.0A CN201911045300A CN111027319A CN 111027319 A CN111027319 A CN 111027319A CN 201911045300 A CN201911045300 A CN 201911045300A CN 111027319 A CN111027319 A CN 111027319A
- Authority
- CN
- China
- Prior art keywords
- time
- words
- word
- merged
- time words
- 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.)
- Pending
Links
Images
Classifications
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/355—Class or cluster creation or modification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Machine Translation (AREA)
Abstract
The application provides a method and a device for analyzing natural language time words, computer equipment and a computer readable storage medium, which relate to the field of semantic analysis, wherein the method comprises the following steps: acquiring an input text; removing preset characters of an input text to obtain a preprocessed text; segmenting words to obtain a plurality of time words; data encapsulation is carried out to obtain first time words corresponding to the time words; merging all the first time words to obtain a plurality of second time words; and analyzing to obtain the time interval corresponding to each second time word. According to the method and the device, the corresponding time words are extracted from the input text through the multiple recognition rules, the time words are merged according to the arrangement positions of the time words in the input text and the association among the recognition rules, and finally the merged time words are parsed according to the word senses to obtain the corresponding time intervals, so that the parsing of all the time words in the natural language is realized, and the comprehensiveness and the accuracy of recognition of the time words in the input text are effectively improved.
Description
Technical Field
The present application relates to the field of semantic parsing technologies, and in particular, to a method and an apparatus for parsing a natural language time word, and a computer device.
Background
When natural language is analyzed, time information is an indispensable element for completely analyzing natural language semantics. The existing method for recognizing time information in natural language mainly extracts time words by matching a fixed rule with a text based on recognition of the fixed rule, for example, extracting a time word representing a date such as "9/10 in 2018". The identification method needs to construct a large number of rules, and on one hand, the identification method is too complex and inflexible and is inconvenient for later developers to understand and modify; on the other hand, the time words extracted from the text by the fixed rule are not comprehensive enough, and the accuracy is low.
Disclosure of Invention
The application mainly aims to provide a method, a device and computer equipment for analyzing natural language time words, and aims to overcome the defects that the existing time word analyzing method is too stiff, and has low accuracy and integrity.
In order to achieve the above object, the present application provides a method for parsing a natural language time word, including:
acquiring an input text;
removing preset characters in the input text to obtain a preprocessed text;
performing word segmentation on the preprocessed text according to a first preset rule to obtain a plurality of time words;
performing data encapsulation on each time word to obtain a first time word corresponding to each time word;
merging the first time words according to a second preset rule to obtain a plurality of second time words;
and respectively analyzing each second time word to obtain a time interval corresponding to each second time word.
Further, the step of segmenting the preprocessed text according to a first preset rule to obtain a plurality of time words includes:
loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
and screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
Further, the step of combining the first time words according to a second preset rule to obtain a plurality of second time words includes:
according to the sequence of the arrangement positions, sequentially screening and combining a plurality of first time words with continuity at the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set respectively according to the sequence of the arrangement positions to obtain at least one first time word set;
screening all the time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merging for the second time to obtain second merged time words;
and taking the first merging time word and the second merging time word as the second time word.
Further, the step of sequentially screening a plurality of first time words with continuity at the arrangement positions according to the sequence of the arrangement positions to merge the first time words to obtain first merged time words includes:
judging whether the end position of one first time word is adjacent to the start position of another first time word;
if the arrangement position of the first time word is adjacent to the starting position of the other first time word, judging that the arrangement positions corresponding to the two first time words have continuity;
and traversing all the first time words in sequence according to the sequence of the arrangement positions, and combining the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first combined time words.
Further, the step of merging the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words includes:
and sequentially combining a plurality of first time words according to the arrangement positions corresponding to the first time words to obtain the first combined time words.
Further, the step of screening, in the same first time word set, each time word to be merged corresponding to the identification rule having an association relationship and performing secondary merging to obtain a second merged time word includes:
classifying the time words to be merged according to the identification rules corresponding to the time words to be merged to obtain a plurality of second time word sets;
respectively merging the second time word sets corresponding to the identification rules with the association relationship to obtain a plurality of third time word sets;
and screening at least two time words to be merged which are contained in the third time word set and the first time word set at the same time, and merging to obtain the second merged time word.
Further, the step of analyzing each second time word respectively to obtain a time interval corresponding to each second time word includes:
judging whether the second time word belongs to a pre-constructed marked time word or not;
if the time interval does not belong to the pre-constructed marked time word, obtaining the corresponding time interval according to the starting time and the ending time of the second time word;
if the time words belong to the pre-constructed time words, acquiring a current reference time point;
and calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
The application also provides a natural language time word analysis device, which comprises:
the acquisition module is used for acquiring an input text;
the processing module is used for removing preset characters in the input text to obtain a preprocessed text;
the word segmentation module is used for segmenting words of the preprocessed text according to a first preset rule to obtain a plurality of time words;
the encapsulation module is used for carrying out data encapsulation on each time word to obtain a first time word corresponding to each time word;
the merging module is used for merging the first time words according to a second preset rule to obtain a plurality of second time words;
and the analysis module is used for respectively analyzing the second time words to obtain the time intervals corresponding to the second time words.
Further, the word segmentation module includes:
the loading submodule is used for loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
and the first screening submodule is used for screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
Further, the first time word carries a time word attribute, the time word attribute includes the identification rule corresponding to the first time word and an arrangement position of the first time word in the input text, and the merging module includes:
the second screening submodule is used for screening and combining a plurality of first time words with continuity at the arrangement positions in sequence according to the sequence of the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
the classification submodule is used for classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set according to the sequence of the arrangement positions to obtain at least one first time word set;
the merging submodule is used for screening each time word to be merged corresponding to the identification rule with the incidence relation in the same first time word set for secondary merging to obtain a second merged time word;
and the marking submodule is used for taking the first merging time word and the second merging time word as the second time word.
Further, the arrangement position includes a start position and an end position, and the second filter submodule includes:
the judging unit is used for judging whether the ending position of one first time word is adjacent to the starting position of another first time word;
a determination unit, configured to determine that the arrangement positions corresponding to the two first time words have continuity if the arrangement positions are adjacent to the start position of another first time word;
and the traversing unit is used for sequentially traversing all the first time words according to the sequence of the arrangement positions, and merging the first time words respectively corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words.
Further, the determination unit includes:
and the merging subunit is configured to sequentially merge the plurality of first time words according to the respective corresponding arrangement positions to obtain the first merged time word.
Further, the merge sub-module includes:
the classification unit is used for classifying the time words to be merged according to the corresponding identification rules to obtain a plurality of second time word sets;
the first merging unit is used for merging the second time word sets corresponding to the identification rules with the association relationship respectively to obtain a plurality of third time word sets;
and the second merging unit is used for screening and merging at least two time words to be merged which are simultaneously contained in the third time word set and the first time word set to obtain the second merged time word.
Further, the parsing module includes:
the judgment submodule is used for judging whether the second time word belongs to a pre-constructed marked time word;
the first calculation submodule is used for obtaining the corresponding time interval according to the starting time and the ending time of the second time word if the second time word does not belong to the pre-constructed marked time word;
the acquisition submodule is used for acquiring a current reference time point if the current reference time point belongs to a pre-constructed time word;
and the second calculation submodule is used for calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of any of the above.
According to the method, the device and the computer equipment for analyzing the natural language time words, firstly, a plurality of time words are extracted from an input text through a plurality of pre-constructed identification rules, then corresponding time word combination is carried out according to the arrangement positions of the time words in the input text and the association between the identification rules, and finally the combined time words are analyzed according to corresponding word senses to obtain corresponding time intervals, so that the analysis of all the time words in the natural language is realized, and the comprehensiveness and the accuracy of time word identification in the input text are effectively improved.
Drawings
FIG. 1 is a diagram illustrating steps of a method for parsing time words in natural language according to an embodiment of the present application;
fig. 2 is a block diagram illustrating an overall structure of a device for parsing time words in natural language according to an embodiment of the present application;
fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a method for parsing a natural language time word, including:
s1: acquiring an input text;
s2: removing preset characters in the input text to obtain a preprocessed text;
s3: performing word segmentation on the preprocessed text according to a first preset rule to obtain a plurality of time words;
s4: performing data encapsulation on each time word to obtain a first time word corresponding to each time word;
s5: merging the first time words according to a second preset rule to obtain a plurality of second time words;
s6: and respectively analyzing each second time word to obtain a time interval corresponding to each second time word.
In this embodiment, the natural language refers to a language of natural narration of human, such as a piece of voice or text. If the analysis system receives the voice information of the user, the voice information needs to be converted into character information. And after receiving the natural language input by the user, the analysis system converts the natural language into information in a text format, thereby obtaining an input text. The analysis system needs to preprocess the input text, recognize preset characters in the input text by means of marking sensitive characters and the like, and remove the preset characters, so that the preprocessed text is obtained, and the processing complexity of subsequent word segmentation is reduced. For example, the input text is: "net profit of the last month in the second quarter of 2018", by marking the sensitive character "so that the preprocessed text after removing the preset characters is: "net profit in the last month of the second quarter of 2018". The analysis system is pre-constructed with a rule base which is a regular expression, the rule base is composed of a plurality of identification rules, each identification rule comprises a plurality of different identification parameters, and one identification rule is used for identifying a class of time words. After the rule base is loaded, the analysis system respectively calls each recognition rule in the rule base to perform word segmentation on the preprocessed text, so that one or more time words corresponding to each recognition rule are obtained. For example, the preprocessed text is: "net profit of last month in second quarter of 2018", the identification parameter of the identification rule a includes "year", so the time word obtained by segmenting the preprocessed text by the identification rule a is: 2018; the recognition parameters of the recognition rule B include "quarter", so that the time words obtained after the pre-processed text is segmented by the recognition rule B are: the second quarter. And the analysis system performs data encapsulation on each time word after word segmentation, so that the formats of the time words are unified, and the corresponding first time words are obtained. The first time word carries a time word attribute, and the time word attribute includes an identification rule corresponding to the first time word, an arrangement position of the first time word in the input text, and other corresponding information, such as: the first time word: in 2018, the corresponding rule: identification rule a, start position: 0, end position: 4. after the data encapsulation is finished, the analysis system firstly screens two or more first time words with continuous arrangement positions according to the arrangement positions of the first time words in the input text to be combined to obtain first combined time words, and marks a plurality of first time words with discontinuous arrangement positions as time words to be combined. Then, classifying each time word to be merged with the arrangement position within a preset range respectively to form a plurality of first time word sets, namely, in the same first time word set, the time word to be merged must be within the preset range with the arrangement position of another time word to be merged. And the analysis system screens a plurality of time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merges the time words to be merged to obtain a plurality of second merged time words. And the analysis system synthesizes each first merged time word and each second merged time word to obtain each second time word. And the analysis system correspondingly analyzes the second time word and obtains a corresponding time interval according to the starting time and the ending time corresponding to the second time word. For example, the second time word is: in 2018, the corresponding time interval is: 1/0 in 2018-12/31/24 in 2018. Further, the analysis system outputs the time interval according to a preset format, for example, the time interval between 1 month and 1 day 0 in 2018 and the time interval between 12 months and 31 days in 2018 is output as follows: 2018-01-01-0: 00-2018-12-31-24: 00.
further, the step of segmenting the preprocessed text according to a first preset rule to obtain a plurality of time words includes:
s301: loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
s302: and screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
In this embodiment, a rule base is pre-constructed in the parsing system, and the rule base is a regular expression. The rule base is composed of a plurality of identification rules, and each identification rule comprises a plurality of identification parameters. Besides the conventional identification parameters such as "year" and "quarter", the identification library also includes special identification parameters such as "before", "after", "the day", "yesterday", and the like, and can be used for identifying time words such as "after 6 days". And the analysis system screens one or more time words from the preprocessed text through the recognition parameters in each recognition rule to realize word segmentation of the preprocessed text. The time words obtained by screening based on the same identification rule belong to the same class and correspond to the identification rule.
Further, the step of combining the first time words according to a second preset rule to obtain a plurality of second time words includes:
s501: according to the sequence of the arrangement positions, sequentially screening and combining a plurality of first time words with continuity at the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
s502: classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set respectively according to the sequence of the arrangement positions to obtain at least one first time word set;
s503: screening all the time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merging for the second time to obtain second merged time words;
s504: and taking the first merging time word and the second merging time word as the second time word.
In this embodiment, the time word attribute carried by the first time word includes an identification rule corresponding to the first time word, and a start position and an end position, that is, an arrangement position, of the first time word in the input text. The analysis system judges whether the ending position of one first time word is adjacent to the starting position of another first time word, and if the ending position is adjacent to the starting position, the arrangement positions corresponding to the two first time words are respectively judged to have continuity. The analysis system screens out a plurality of first time words with continuity in arrangement positions according to the method and merges the first time words to obtain one or more first merged time words. Further, in the process of merging the first time words according to the continuity of the arrangement positions, the parsing system may merge a plurality of first time words continuously, for example, the first time word a has continuity with the first time word B, and the first time word B has continuity with the first time word C, and then the parsing system may merge the first time word a, the first time word B, and the first time word C to obtain a first merged time word. And the analysis system marks a plurality of first time words with non-continuity of arrangement positions as time words to be merged so as to use another rule for merging. Specifically, the parsing system compares the arrangement positions of the time words to be merged in a group of two time words to be merged according to the sequence of the arrangement positions of the time words to be merged in the input text, and if the arrangement positions are within a preset range, for example, the end position of the time word a to be merged is 5, the start position of the time word B to be merged is 8, the end position of the time word B to be merged is 10, the start position of the time word C to be merged is 12, and the preset range is 3, the time word a to be merged, the time word B to be merged, and the time word C to be merged may be included in the same time word set. The analysis system forms one or more first time word sets according to the method, then screens a plurality of time words to be merged corresponding to the identification rules with the association relationship in the same first time word set according to the association relationship among the pre-established identification rules, and merges the time words to be merged, so as to obtain second merged time words. And the analysis system synthesizes the first time word to be combined and the second time word to be combined to obtain a second time word.
Further, the step of sequentially screening a plurality of first time words with continuity at the arrangement positions according to the sequence of the arrangement positions to merge the first time words to obtain first merged time words includes:
s5011: judging whether the end position of one first time word is adjacent to the start position of another first time word;
s5012: if the arrangement position of the first time word is adjacent to the starting position of the other first time word, judging that the arrangement positions corresponding to the two first time words have continuity;
s5013: and traversing all the first time words in sequence according to the sequence of the arrangement positions, and combining the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first combined time words.
In this embodiment, the arrangement position of the first time word in the input text includes a start position and an end position. The parsing system determines whether an end position of one first time word is adjacent to a start position of another first time word. If the end position of one first time word is adjacent to the start position of another first time word, the analysis system judges that the arrangement positions of the two first time words have continuity. For example, the start position of the first time word a is 3, and the end position is 6; the starting position of the first time word B is 7, and the ending position of the first time word B is 9; since the ending position "6" of the first time word a is adjacent to the starting position "7" of the first time word B, the system determines that the arrangement positions corresponding to the first time word a and the first time word B respectively have continuity. And the analysis system sequentially traverses all the first time words according to the sequence of the arrangement positions of the first time words in the input text, screens out the first time words respectively corresponding to the arrangement positions with continuity according to the judgment method, and sequentially merges according to the arrangement positions of the time words to obtain one or more first merged time words.
Further, the step of merging the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words includes:
s50131: and sequentially combining a plurality of first time words according to the arrangement positions corresponding to the first time words to obtain the first combined time words.
In this embodiment, when the parsing system merges two or more first time words with continuous arrangement positions, the first time words need to be sequentially merged according to the respective arrangement positions of the first time words in the input text. Specifically, the parsing system may determine, according to a size relationship between start positions or end positions corresponding to two first time words, an arrangement position between the two first time words in the input text, where for example, a start position of the first time word a is 5, a start position of the first time word B is 9, and the first time word a is smaller than a start article of the first time word B, and therefore must be arranged before the first time word B. Because the input text is obtained according to the natural language input by the user, the time words in the natural language have specific logicality and sequence, for example, when we speak, we will normally speak only 2018 for 9 months, but not 9 months for 2018, so the parsing system needs to merge two first time words according to the sequence of the arrangement positions, thereby obtaining a first merged time word.
Further, the step of screening, in the same first time word set, each time word to be merged corresponding to the identification rule having an association relationship and performing secondary merging to obtain a second merged time word includes:
s5031: classifying the time words to be merged according to the identification rules corresponding to the time words to be merged to obtain a plurality of second time word sets;
s5032: respectively merging the second time word sets corresponding to the identification rules with the association relationship to obtain a plurality of third time word sets;
s5033: and screening at least two time words to be merged which are contained in the third time word set and the first time word set at the same time, and merging to obtain the second merged time word.
In this embodiment, the parsing system classifies each time word to be merged according to a corresponding recognition rule, so as to obtain one or more second time word sets, where each time word to be merged in the same second time word set is obtained by screening the same recognition rule. The identification rules in the rule base are pre-established with an association relationship, for example, the identification rule a can identify the time word "year", the identification rule B can identify the time word "month", and the identification rule a and the identification rule B are associated with each other, so that the time word "year" and the time word "month" are combined later. And the analysis system respectively merges two or more second time word sets corresponding to the identification rules with the incidence relation, so as to obtain one or more third time word sets. If the two time words to be merged are contained in the third time word set and the first time word set at the same time, it is indicated that the arrangement positions of the two time words to be merged are within the preset range, and the corresponding recognition rules have association relations. Therefore, the analysis system only needs to screen and merge at least two time words to be merged which are simultaneously contained in the first time word set and the third time word set, and then the second merged time word with logic association can be obtained.
Further, the step of analyzing each second time word respectively to obtain a time interval corresponding to each second time word includes:
s601: judging whether the second time word belongs to a pre-constructed marked time word or not;
s602: if the time interval does not belong to the pre-constructed marked time word, obtaining the corresponding time interval according to the starting time and the ending time of the second time word;
s603: if the time words belong to the pre-constructed time words, acquiring a current reference time point;
s604: and calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
In this embodiment, the second time word obtained after the analysis system merges has two forms, one of which is: the time words with semanteme determination such as 2018, 8 months and 9 days are the following words: and today, the following days and 6 days later, developers set the semantic fuzzy time words as the marked time words, and the processing methods of the second time words in different forms are different in the analysis process. The analysis system firstly judges whether the second time word is the marked time word, if not, the corresponding time interval can be directly obtained according to the starting time and the ending time of the second time word. For example, the second time word is: in 2018, in month 6, the corresponding time interval is: 0 point in 6/1/0 in 2018-0 point in 24/6/30 in 2018. Specifically, during the execution of the machine, the corresponding interval is as accurate as microseconds, which is not described in detail herein. If the time word is marked, the analysis system needs to acquire a current reference time point, specifically, the reference time point is obtained according to the current time zone of the user, that is, the reference time point corresponds to the current time zone of the user. The analysis system calculates a corresponding time interval according to the reference time point and the word meaning of the second time word, for example, the reference time point is: 24/6/2018, and the second time word is: after 3 days, the corresponding time interval is 0 minutes at 27 days 6 and 27 in 2018, to 0 minutes at 24 days 27 and 6 in 2018.
The method for analyzing the time words in the natural language provided by the embodiment includes the steps of firstly extracting a plurality of time words from an input text through a plurality of pre-established identification rules, then merging the corresponding time words according to the arrangement positions of the time words in the input text and the association between the identification rules, and finally analyzing the merged time words according to corresponding word senses to obtain corresponding time intervals, so that analysis of all the time words in the natural language is achieved, and comprehensiveness and accuracy of identification of the time words in the input text are effectively improved.
Referring to fig. 2, an embodiment of the present application further provides an apparatus for parsing a natural language time word, including:
the acquisition module 1 is used for acquiring an input text;
the processing module 2 is used for removing preset characters in the input text to obtain a preprocessed text;
the word segmentation module 3 is used for segmenting words of the preprocessed text according to a first preset rule to obtain a plurality of time words;
the encapsulation module 4 is used for carrying out data encapsulation on each time word to obtain a first time word corresponding to each time word;
the merging module 5 is configured to merge the first time words according to a second preset rule to obtain a plurality of second time words;
and the analysis module 6 is configured to analyze each second time word respectively to obtain a time interval corresponding to each second time word.
Further, the analysis device further comprises an output module, configured to output each time interval to a display interface according to a preset format.
In this embodiment, the implementation processes of the functions and actions of the obtaining module 1, the processing module 2, the word segmentation module 3, the encapsulation module 4, the merging module 5, and the analysis module 6 in the plug-in detection device are specifically detailed in the implementation processes corresponding to steps S1 to S6 in the plug-in detection method based on login data, and are not described herein again.
Further, the word segmentation module 3 includes:
the loading submodule is used for loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
and the first screening submodule is used for screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
In this embodiment, the implementation processes of the functions and functions of the loading submodule and the first screening submodule in the plug-in detection device are specifically detailed in the implementation processes corresponding to steps S301 to S302 in the plug-in detection method based on login data, and are not described herein again.
Further, the first time word carries a time word attribute, the time word attribute includes the identification rule corresponding to the first time word and an arrangement position of the first time word in the input text, and the merging module 5 includes:
the second screening submodule is used for screening and combining a plurality of first time words with continuity at the arrangement positions in sequence according to the sequence of the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
the classification submodule is used for classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set according to the sequence of the arrangement positions to obtain at least one first time word set;
the merging submodule is used for screening each time word to be merged corresponding to the identification rule with the incidence relation in the same first time word set for secondary merging to obtain a second merged time word;
and the marking submodule is used for taking the first merging time word and the second merging time word as the second time word.
In this embodiment, the implementation processes of the functions and functions of the second screening submodule, the classifying submodule, the merging submodule and the marking submodule in the plug-in detection device are specifically detailed in the implementation processes corresponding to steps S501 to S504 in the plug-in detection method based on login data, and are not described herein again.
Further, the arrangement position includes a start position and an end position, and the second filter submodule includes:
the judging unit is used for judging whether the ending position of one first time word is adjacent to the starting position of another first time word;
a determination unit, configured to determine that the arrangement positions corresponding to the two first time words have continuity if the arrangement positions are adjacent to the start position of another first time word;
and the traversing unit is used for sequentially traversing all the first time words according to the sequence of the arrangement positions, and merging the first time words respectively corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words.
In this embodiment, the implementation processes of the functions and actions of the determining unit, and the jumping unit in the plug-in detection device are specifically detailed in the implementation processes corresponding to steps S5011 to S5013 in the plug-in detection method based on login data, and are not described herein again.
Further, the determination unit includes:
and the merging subunit is configured to sequentially merge the plurality of other first time words according to the arrangement positions corresponding to the first time words, so as to obtain the first merged time words.
In this embodiment, the implementation process of the function and the action of the merging subunit in the plug-in detection device is specifically described in the implementation process corresponding to step S50131 in the plug-in detection method based on login data, and is not described herein again.
Further, the merge sub-module includes:
the classification unit is used for classifying the time words to be merged according to the corresponding identification rules to obtain a plurality of second time word sets;
the first merging unit is used for merging the second time word sets corresponding to the identification rules with the association relationship respectively to obtain a plurality of third time word sets;
and the second merging unit is used for screening and merging at least two time words to be merged which are simultaneously contained in the third time word set and the first time word set to obtain the second merged time word.
In this embodiment, the detailed implementation processes of the functions and functions of the classification unit, the first merging unit, and the second merging unit in the plug-in detection device are the implementation processes corresponding to steps S5031 to S5033 in the plug-in detection method based on login data, and are not described herein again.
Further, the parsing module 6 includes:
the judgment submodule is used for judging whether the second time word belongs to a pre-constructed marked time word;
the first calculation submodule is used for obtaining the corresponding time interval according to the starting time and the ending time of the second time word if the second time word does not belong to the pre-constructed marked time word;
the acquisition submodule is used for acquiring a current reference time point if the current reference time point belongs to a pre-constructed time word;
and the second calculation submodule is used for calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
In this embodiment, the implementation processes of the functions and functions of the judgment sub-module, the first calculation sub-module, the obtaining sub-module, and the second calculation sub-module in the plug-in detection device are specifically detailed in the implementation processes corresponding to steps S601 to S604 in the plug-in detection method based on login data, and are not described herein again
According to the natural language time word analysis device provided by the embodiment, firstly, a plurality of time words are extracted from an input text through a plurality of pre-constructed recognition rules, then, corresponding time word combination is carried out according to the respective corresponding arrangement positions of the time words in the input text and the association between the recognition rules, and finally, the combined time words are analyzed according to corresponding word senses to obtain corresponding time intervals, so that the analysis of all the time words in the natural language is realized, and the comprehensiveness and accuracy of time word recognition in the input text are effectively improved.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing data such as a rule base. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of parsing a natural language time word.
The processor executes the steps of the method for analyzing the natural language time words:
s1: acquiring an input text;
s2: removing preset characters in the input text to obtain a preprocessed text;
s3: performing word segmentation on the preprocessed text according to a first preset rule to obtain a plurality of time words;
s4: performing data encapsulation on each time word to obtain a first time word corresponding to each time word;
s5: merging the first time words according to a second preset rule to obtain a plurality of second time words;
s6: and respectively analyzing each second time word to obtain a time interval corresponding to each second time word.
Further, the step of segmenting the preprocessed text according to a first preset rule to obtain a plurality of time words includes:
s301: loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
s302: and screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
Further, the step of combining the first time words according to a second preset rule to obtain a plurality of second time words includes:
s501: according to the sequence of the arrangement positions, sequentially screening and combining a plurality of first time words with continuity at the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
s502: classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set respectively according to the sequence of the arrangement positions to obtain at least one first time word set;
s503: screening all the time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merging for the second time to obtain second merged time words;
s504: and taking the first merging time word and the second merging time word as the second time word.
Further, the step of sequentially screening a plurality of first time words with continuity at the arrangement positions according to the sequence of the arrangement positions to merge the first time words to obtain first merged time words includes:
s5011: judging whether the end position of one first time word is adjacent to the start position of another first time word;
s5012: if the arrangement position of the first time word is adjacent to the starting position of the other first time word, judging that the arrangement positions corresponding to the two first time words have continuity;
s5013: and traversing all the first time words in sequence according to the sequence of the arrangement positions, and combining the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first combined time words.
Further, the step of merging the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words includes:
s50131: and sequentially combining a plurality of first time words according to the arrangement positions corresponding to the first time words to obtain the first combined time words.
Further, the step of screening, in the same first time word set, each time word to be merged corresponding to the identification rule having an association relationship and performing secondary merging to obtain a second merged time word includes:
s5031: classifying the time words to be merged according to the identification rules corresponding to the time words to be merged to obtain a plurality of second time word sets;
s5032: respectively merging the second time word sets corresponding to the identification rules with the association relationship to obtain a plurality of third time word sets;
s5033: and screening at least two time words to be merged which are contained in the third time word set and the first time word set at the same time, and merging to obtain the second merged time word.
Further, the step of analyzing each second time word respectively to obtain a time interval corresponding to each second time word includes:
s601: judging whether the second time word belongs to a pre-constructed marked time word or not;
s602: if the time interval does not belong to the pre-constructed marked time word, obtaining the corresponding time interval according to the starting time and the ending time of the second time word;
s603: if the time words belong to the pre-constructed time words, acquiring a current reference time point;
s604: and calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for parsing a natural language time word, and specifically includes:
s1: acquiring an input text;
s2: removing preset characters in the input text to obtain a preprocessed text;
s3: performing word segmentation on the preprocessed text according to a first preset rule to obtain a plurality of time words;
s4: performing data encapsulation on each time word to obtain a first time word corresponding to each time word;
s5: merging the first time words according to a second preset rule to obtain a plurality of second time words;
s6: and respectively analyzing each second time word to obtain a time interval corresponding to each second time word.
Further, the step of segmenting the preprocessed text according to a first preset rule to obtain a plurality of time words includes:
s301: loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
s302: and screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
Further, the step of combining the first time words according to a second preset rule to obtain a plurality of second time words includes:
s501: according to the sequence of the arrangement positions, sequentially screening and combining a plurality of first time words with continuity at the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
s502: classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set respectively according to the sequence of the arrangement positions to obtain at least one first time word set;
s503: screening all the time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merging for the second time to obtain second merged time words;
s504: and taking the first merging time word and the second merging time word as the second time word.
Further, the step of sequentially screening a plurality of first time words with continuity at the arrangement positions according to the sequence of the arrangement positions to merge the first time words to obtain first merged time words includes:
s5011: judging whether the end position of one first time word is adjacent to the start position of another first time word;
s5012: if the arrangement position of the first time word is adjacent to the starting position of the other first time word, judging that the arrangement positions corresponding to the two first time words have continuity;
s5013: and traversing all the first time words in sequence according to the sequence of the arrangement positions, and combining the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first combined time words.
Further, the step of merging the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first merged time words includes:
s50131: and sequentially combining a plurality of first time words according to the arrangement positions corresponding to the first time words to obtain the first combined time words.
Further, the step of screening, in the same first time word set, each time word to be merged corresponding to the identification rule having an association relationship and performing secondary merging to obtain a second merged time word includes:
s5031: classifying the time words to be merged according to the identification rules corresponding to the time words to be merged to obtain a plurality of second time word sets;
s5032: respectively merging the second time word sets corresponding to the identification rules with the association relationship to obtain a plurality of third time word sets;
s5033: and screening at least two time words to be merged which are contained in the third time word set and the first time word set at the same time, and merging to obtain the second merged time word.
Further, the step of analyzing each second time word respectively to obtain a time interval corresponding to each second time word includes:
s601: judging whether the second time word belongs to a pre-constructed marked time word or not;
s602: if the time interval does not belong to the pre-constructed marked time word, obtaining the corresponding time interval according to the starting time and the ending time of the second time word;
s603: if the time words belong to the pre-constructed time words, acquiring a current reference time point;
s604: and calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by hardware associated with instructions of a computer program, which may be stored on a non-volatile computer-readable storage medium, and when executed, may include processes of the above embodiments of the methods. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method 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, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A method for parsing time words in natural language, comprising:
acquiring an input text;
removing preset characters in the input text to obtain a preprocessed text;
performing word segmentation on the preprocessed text according to a first preset rule to obtain a plurality of time words;
performing data encapsulation on each time word to obtain a first time word corresponding to each time word;
merging the first time words according to a second preset rule to obtain a plurality of second time words;
and respectively analyzing each second time word to obtain a time interval corresponding to each second time word.
2. The method for parsing time words in natural language according to claim 1, wherein the step of segmenting the preprocessed text according to a first preset rule to obtain a plurality of time words comprises:
loading a pre-constructed rule base, wherein the rule base consists of a plurality of identification rules, and a single identification rule comprises a plurality of identification parameters;
and screening the preprocessed text to obtain a plurality of time words respectively corresponding to the identification parameters of the identification rules.
3. The method for parsing time words in natural language according to claim 2, wherein the first time words carry time word attributes, the time word attributes include the recognition rules corresponding to the first time words and arrangement positions of the first time words in the input text, and the step of combining the first time words according to a second preset rule to obtain a plurality of second time words includes:
according to the sequence of the arrangement positions, sequentially screening and combining a plurality of first time words with continuity at the arrangement positions to obtain first combined time words, and marking the plurality of first time words without continuity at the arrangement positions as time words to be combined;
classifying the time words to be merged, of which the arrangement positions are within a preset range, into the same set respectively according to the sequence of the arrangement positions to obtain at least one first time word set;
screening all the time words to be merged corresponding to the identification rules with the association relationship in the same first time word set, and merging for the second time to obtain second merged time words;
and taking the first merging time word and the second merging time word as the second time word.
4. The method for parsing a natural language time word according to claim 3, wherein the arrangement position includes a start position and an end position, and the step of sequentially screening a plurality of first time words having continuity at the arrangement position according to the sequence of the arrangement position and merging the first time words to obtain a first merged time word comprises:
judging whether the end position of one first time word is adjacent to the start position of another first time word;
if the arrangement position of the first time word is adjacent to the starting position of the other first time word, judging that the arrangement positions corresponding to the two first time words have continuity;
and traversing all the first time words in sequence according to the sequence of the arrangement positions, and combining the first time words corresponding to the plurality of arrangement positions with the continuity to obtain first combined time words.
5. The method for parsing time words in natural language according to claim 4, wherein the step of merging the first time words corresponding to the plurality of arrangement positions with the continuity to obtain the first merged time words comprises:
and sequentially combining a plurality of first time words according to the arrangement positions corresponding to the first time words to obtain the first combined time words.
6. The method for analyzing time words in natural language according to claim 3, wherein the step of screening, in the same first time word set, each time word to be merged corresponding to the identification rule having an association relationship and performing secondary merging to obtain a second merged time word includes:
classifying the time words to be merged according to the identification rules corresponding to the time words to be merged to obtain a plurality of second time word sets;
respectively merging the second time word sets corresponding to the identification rules with the association relationship to obtain a plurality of third time word sets;
and screening at least two time words to be merged which are contained in the third time word set and the first time word set at the same time, and merging to obtain the second merged time word.
7. The method according to claim 1, wherein the step of analyzing each of the second time words to obtain a time interval corresponding to each of the second time words comprises:
judging whether the second time word belongs to a pre-constructed marked time word or not;
if the time interval does not belong to the pre-constructed marked time word, obtaining the corresponding time interval according to the starting time and the ending time of the second time word;
if the time words belong to the pre-constructed time words, acquiring a current reference time point;
and calculating to obtain the corresponding time interval according to the reference time point and the word meaning of the second time word.
8. An apparatus for parsing a time word in a natural language, comprising:
the acquisition module is used for acquiring an input text;
the processing module is used for removing preset characters in the input text to obtain a preprocessed text;
the word segmentation module is used for segmenting words of the preprocessed text according to a first preset rule to obtain a plurality of time words;
the encapsulation module is used for carrying out data encapsulation on each time word to obtain a first time word corresponding to each time word;
the merging module is used for merging the first time words according to a second preset rule to obtain a plurality of second time words;
and the analysis module is used for respectively analyzing the second time words to obtain the time intervals corresponding to the second time words.
9. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045300.0A CN111027319A (en) | 2019-10-30 | 2019-10-30 | Method and device for analyzing natural language time words and computer equipment |
| PCT/CN2020/093111 WO2021082424A1 (en) | 2019-10-30 | 2020-05-29 | Parsing method and apparatus for natural language time words, and computer device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045300.0A CN111027319A (en) | 2019-10-30 | 2019-10-30 | Method and device for analyzing natural language time words and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111027319A true CN111027319A (en) | 2020-04-17 |
Family
ID=70200542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911045300.0A Pending CN111027319A (en) | 2019-10-30 | 2019-10-30 | Method and device for analyzing natural language time words and computer equipment |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN111027319A (en) |
| WO (1) | WO2021082424A1 (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082424A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Parsing method and apparatus for natural language time words, and computer device |
| CN113988067A (en) * | 2021-11-12 | 2022-01-28 | 北京嘉和海森健康科技有限公司 | Sentence segmentation method and device and electronic equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729314A (en) * | 2017-09-29 | 2018-02-23 | 东软集团股份有限公司 | A kind of Chinese time recognition methods, device and storage medium, program product |
| CN107894978A (en) * | 2017-11-14 | 2018-04-10 | 北京神州泰岳软件股份有限公司 | The abstracting method and device of time word |
| CN108549694A (en) * | 2018-04-16 | 2018-09-18 | 南京云问网络技术有限公司 | The processing method of temporal information in a kind of text |
| CN109190119A (en) * | 2018-08-22 | 2019-01-11 | 腾讯科技（深圳）有限公司 | Time extracting method and device, storage medium and electronic device |
| CN109657237A (en) * | 2018-06-08 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | time word extraction method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3553762B2 (en) * | 1997-04-25 | 2004-08-11 | 三洋電機株式会社 | Document processing device |
| CN109885659B (en) * | 2019-02-20 | 2022-12-16 | 安徽省泰岳祥升软件有限公司 | Method and device for normalizing time information in text |
| CN111027319A (en) * | 2019-10-30 | 2020-04-17 | 平安科技（深圳）有限公司 | Method and device for analyzing natural language time words and computer equipment |
-
2019
- 2019-10-30 CN CN201911045300.0A patent/CN111027319A/en active Pending
-
2020
- 2020-05-29 WO PCT/CN2020/093111 patent/WO2021082424A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729314A (en) * | 2017-09-29 | 2018-02-23 | 东软集团股份有限公司 | A kind of Chinese time recognition methods, device and storage medium, program product |
| CN107894978A (en) * | 2017-11-14 | 2018-04-10 | 北京神州泰岳软件股份有限公司 | The abstracting method and device of time word |
| CN108549694A (en) * | 2018-04-16 | 2018-09-18 | 南京云问网络技术有限公司 | The processing method of temporal information in a kind of text |
| CN109657237A (en) * | 2018-06-08 | 2019-04-19 | 安徽省泰岳祥升软件有限公司 | time word extraction method and device |
| CN109190119A (en) * | 2018-08-22 | 2019-01-11 | 腾讯科技（深圳）有限公司 | Time extracting method and device, storage medium and electronic device |
Non-Patent Citations (1)
| Title |
|---|
| 黎巎著: "《旅游大数据研究》", 31 July 2018 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082424A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Parsing method and apparatus for natural language time words, and computer device |
| CN113988067A (en) * | 2021-11-12 | 2022-01-28 | 北京嘉和海森健康科技有限公司 | Sentence segmentation method and device and electronic equipment |
| CN113988067B (en) * | 2021-11-12 | 2024-06-25 | 北京嘉和海森健康科技有限公司 | Sentence word segmentation method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021082424A1 (en) | 2021-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110444198B (en) | Retrieval method, retrieval device, computer equipment and storage medium | |
| EP3588279B1 (en) | Automated extraction of rules embedded in software application code using machine learning | |
| CN111444723B (en) | Information extraction method, computer device, and storage medium | |
| CN110688454A (en) | Method, device, equipment and storage medium for processing consultation conversation | |
| CN109740159B (en) | Processing method and device for named entity recognition | |
| CN112036153B (en) | Work order error correction method and device, computer readable storage medium and computer equipment | |
| CN110765235A (en) | Training data generation method and device, terminal and readable medium | |
| CN111860669A (en) | Training method and device of OCR recognition model and computer equipment | |
| CN110459223B (en) | Data tracking processing method, device, storage medium and apparatus | |
| CN111859093A (en) | Sensitive word processing method and device and readable storage medium | |
| US20200285810A1 (en) | System and method for extracting information from unstructured or semi-structured textual sources | |
| CN112699923A (en) | Document classification prediction method and device, computer equipment and storage medium | |
| US11574491B2 (en) | Automated classification and interpretation of life science documents | |
| CN111027319A (en) | Method and device for analyzing natural language time words and computer equipment | |
| CN111190946A (en) | Report generation method and device, computer equipment and storage medium | |
| CN113255343A (en) | Semantic identification method and device for label data, computer equipment and storage medium | |
| CN111126058A (en) | Text information automatic extraction method and device, readable storage medium and electronic equipment | |
| CN111599382B (en) | Voice analysis method, device, computer equipment and storage medium | |
| CN113849644A (en) | Text classification model configuration method and device, computer equipment and storage medium | |
| CN113434631A (en) | Emotion analysis method and device based on event, computer equipment and storage medium | |
| CN111274156B (en) | Automatic identification method and device compatible with multi-frame pages | |
| CN111552785A (en) | Method and device for updating database of human-computer interaction system, computer equipment and medium | |
| CN109344385B (en) | Natural language processing method, device, computer equipment and storage medium | |
| CN114969544A (en) | Hot data-based recommended content generation method, device, equipment and medium | |
| CN113065360B (en) | Word semantic model construction method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 40018615 Country of ref document: HK |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200417 |