CN110850998A - Intelligent word-forming calculation optimization method and device for Chinese input method - Google Patents
Intelligent word-forming calculation optimization method and device for Chinese input method Download PDFInfo
- Publication number
- CN110850998A CN110850998A CN201911065130.2A CN201911065130A CN110850998A CN 110850998 A CN110850998 A CN 110850998A CN 201911065130 A CN201911065130 A CN 201911065130A CN 110850998 A CN110850998 A CN 110850998A
- Authority
- CN
- China
- Prior art keywords
- syllable
- input
- calculation
- module
- calculation result
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Document Processing Apparatus (AREA)
Abstract
The invention provides a method and a device for intelligently computing and optimizing word combinations by a Chinese input method, wherein the method comprises the following steps: obtaining a pinyin string input by a user; performing standard pinyin syllable dividing operation on the pinyin string, and dividing the pinyin string into a plurality of syllable combinations; and calling an input syllable matching module, matching the syllable combination with the existing calculation result record, directly obtaining the corresponding calculation result by the same syllable, and calling an HMM language model for calculation by the different syllables. The method greatly improves the input response efficiency of the original HMM model, and improves the calculation capacity of the optimized model by 30-40% compared with the original HMM language model.
Description
Technical Field
The invention relates to the technical field of input method processing, in particular to an intelligent word combination calculation optimization method and device for a Chinese input method.
Background
The home-made information platform is gradually growing, and more organizations and individuals in China begin to use related devices and systems for home-made. The Chinese input method is used as a basic and important ring in Chinese office software, the performance of the Chinese input method is good and bad, and the experience of a user in working with Chinese can be directly influenced.
The existing domestic platform has insufficient computing capability, so that the phenomenon that a user inputs a card pause when a long pinyin string is input and deleted in a Chinese input method is caused.
Some input methods can respond to the input of the user quickly, but the generated candidate sentences are often short, and are not beneficial to the input processing of long sentences. In addition, most of the existing schemes improve the computational efficiency of word combination results by compressing the candidate set of the language model, which may cause that the language model cannot correctly combine the word combinations desired by the user in some cases.
Disclosure of Invention
In view of the above, in order to solve the problems in the prior art, the invention provides an optimization method and device for intelligent word formation calculation of a Chinese input method under a domestic platform. The method is based on the existing language model of the popular HMM, and the Pinyin character string is converted into the Chinese character.
The technical scheme of the invention is as follows:
in a first aspect, the invention provides an intelligent word-forming calculation optimization method for a Chinese input method, which is characterized by comprising the following steps: the method comprises the following steps:
step S1, obtaining a pinyin string input by a user;
step S2, performing standard pinyin syllable dividing operation on the pinyin string, and dividing the pinyin string into a plurality of syllable combinations;
and step S3, calling an input syllable matching module, matching the syllable combination with the existing calculation result record, directly obtaining the corresponding calculation result by the same syllable, and calling an HMM language model for calculation by the different syllables.
Further, the step S3 includes:
s301, calling an input syllable matching module, and searching a calculation result completely matched with the syllable combination;
step S302, if a calculation result completely matched with the syllable combination is found, directly outputting the calculation result, and if the calculation result is not found, turning to step S303;
step S303, calling an input syllable matching module to find whether a result of maximum approximate matching with the current syllable combination exists; if the input syllable combination is not found, calling an HMM language model, calculating the calculation result of the best Chinese word combination of the current input syllable combination, and turning to the step S305; if the data is found, go to step S304;
step S304, calling a similar pinyin string calculation module, and directly obtaining the calculation result of the same syllable for the syllable part which has the same result with the maximum approximate matching in the syllable combination; for different syllable portions, using HMM language model calculation to obtain calculation results of different syllable portions, and concatenating the calculation results of the same syllable and the calculation results of different syllables to obtain a calculation result of the best chinese word group of the currently input syllable combination, proceeding to step S305;
and S305, compressing and storing the calculation result of the optimal Chinese word group and the intermediate calculation result into a storage management module, and outputting the calculation result of the optimal Chinese word group.
Further, the calculation result of the optimal Chinese word combination means that the result with the highest occurrence probability in all syllable combinations is finally obtained through the calculation of an HMM language model.
Further, the intermediate calculation result refers to a dynamic planning path diagram obtained by calculation through a dynamic planning method in the process of using the HMM language model.
Further, the process of maximum approximate matching includes:
step S3031, matching the syllable combination with the character string stored in the storage management module to obtain the character string with the longest common prefix;
step S3032, searching back from the last syllable of the character string with the longest public prefix to obtain a character string e, wherein the character string e is a word group result with the largest word group length which can be searched in the existing calculation result record;
step S3033, the character string f is obtained by removing the character string e from the character string with the same prefix, that is, the character string of the result of the maximum approximate matching.
In a second aspect, the present invention provides an intelligent word-composing device for a chinese input method, which is characterized in that: the input end of the input syllable acquisition module acquires a pinyin string input by a user, and the output end of the input syllable acquisition module is connected with the input end of the input syllable matching module; the output end of the input syllable matching module is respectively connected with the input end of the output module and the input end of the similar pinyin string calculation module; the output end of the similar pinyin string calculation module is connected with the input end of the HMM language model; the output end of the HMM language model is connected with the input end of the storage management module, the output end of the storage management module is connected with the input end of the output module, and the output end of the output module outputs the optimal calculation result of Chinese word formation.
Furthermore, the input syllable acquisition module divides the pinyin string input by the user into a plurality of syllable combinations and outputs the syllable combinations to the input syllable matching module.
Further, the input syllable matching module is used for realizing rapid complete matching and maximum approximate matching between the syllable combination and the existing calculation record; the similar pinyin string calculation module calculates the pinyin string with the maximum approximate matching, the same syllables directly obtain calculation results, different syllables are calculated by using an HMM language model to obtain calculation results of different syllable parts, and the calculation results of the same syllables and the calculation results of the different syllables are spliced.
Further, the storage management module records and releases the intermediate calculation result of the HMM language model and the calculation result of the optimal Chinese word composition.
Furthermore, the HMM language model calculates syllables which are not stored in the storage management module, and outputs the calculation result of the optimal Chinese word group to the output module.
The invention has the beneficial effects that:
in the actual operation process, forward and backward calculation optimization is carried out on the intelligent word part of the HMM model by utilizing the space-time exchange thought and the invariance of a dynamic programming solution set, so that the input response efficiency of the original HMM model is greatly improved. Practical use shows that compared with the original HMM language model, the optimized model has the advantage that the calculation capacity is improved by 30-40%.
Drawings
FIG. 1 is a schematic diagram of the steps of the intelligent word-composing calculation optimization method of the present invention;
fig. 2 is a schematic structural diagram of an intelligent word forming device of a Chinese input method according to the present invention.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
Example one
The invention utilizes the space-time exchange thought and the invariance of a dynamic programming solution set to carry out forward and backward calculation optimization on the intelligent word part of the HMM model.
The forward optimization of intelligent word grouping means that S ═ c is the pinyin string currently input by the user1,c2,c3…cnThe user adds a character to become S' ═ c1,c2,c3…cn,cn+1And when the Chinese word is replaced, calculating the optimal Chinese word forming result. Through the input syllable matching module, if the user has input the pinyin string S', the best chinese word formation result stored in the storage module is directly obtained. If the user has not input the approximate phonetic string T ═ c1',c'2,c'3…c'mAnd its best Chinese word formation result. Then calculating the current user input based on the result of the approximate Pinyin stringThe best chinese word formation result of the string S'.
The reverse optimization of intelligent word combination means that S ═ c is the pinyin string currently input by the user1,c2,c3…cn,cn+1The user deletes the tail character to become S' ═ c1,c2,c3…cnAnd when the Chinese word is replaced, calculating the optimal Chinese word forming result. At this time, the best Chinese word forming result of the syllable stored in the storage module is directly obtained.
The embodiment provides an intelligent word-forming calculation optimization method for a Chinese input method, which comprises the following steps:
and step S1, acquiring a Pinyin string S input by the user.
Step S2, dividing the pinyin string into a plurality of syllable combinations by dividing the pinyin string into syllables of standard pinyin.
For example, after the input pinyin string zhonghuaarenmin is syllable-divided, it becomes zhong ' hua ' ren ' min. The operation of dividing syllables is a mature technology and will not be described in detail here.
And step S3, calling an input syllable matching module, matching the syllable combination with the calculation result stored in the storage management module, directly obtaining the corresponding calculation result by the same syllable, and calling an HMM language model for calculation by different syllables.
Further, step S3 includes:
step S301, after obtaining the information of the syllable combination, calling an input syllable matching module to search a calculation result completely matched with the current syllable combination.
The input syllable matching module is used in this step to make a fast and complete match between all syllables and the existing calculation record. The matching process realizes the matching of equal character strings through a hash table.
Step S302: if the calculation result completely matching with the syllable combination is found, the calculation result is directly output, and if the calculation result is not found, the process goes to step S303.
Step S303: and calling an input syllable matching module to search whether a result of maximum approximate matching with the current syllable combination exists. If the input syllable combination is not found, calling an HMM language model, and calculating the calculation result of the best Chinese word combination of the current input syllable combination to step S305; if found, go to step S304.
The process of maximum approximate matching is described as follows:
step S3031, matching the syllable combination with the character string stored in the storage management module to obtain the character string with the longest common prefix;
if the character string of the syllable combination inputted by the client is a ═ c1,c2,c3...cnAnd b is the character string with the largest matching length { c }1,c2,c3...cmMatching the character string a with the character string b to obtain a character string c with the longest common prefix, wherein the character string c is { c }1,c2,c3...cR},(R<n,R<m)；
Step S3032, the last syllable c of the character string cRStarting the search back, a string e is obtained, where e is { c }L+1,cL+2,cL+3...cRAnd e, enabling the character string e to be a word forming result with the largest word group length which can be found in the existing calculation result record.
For example, the character string c is wo 'men' zai 'bei' jing, the search is performed from jing back, the phrase result with the largest phrase length is found to be bei 'jing, and no phrase result such as zai' bei 'jing is available, so the character string e is bei' jing.
Step S3033 is to remove the character string e from the character string c to obtain a character string f, where f is { c {1,c2,c3...cLI.e. the string of results that we need for the maximum approximate match.
The correctness of the dynamic planning method can be ensured through the process.
Step S304: calling a similar pinyin string calculation module, and directly obtaining the calculation result of the same syllable for the same syllable part of the current input syllable combination and the matched maximum approximate matching result; for different syllable portions, HMM language model calculation is used to obtain calculation results for different syllable portions, and the calculation results for the same syllable and the calculation results for different syllables are concatenated to obtain the best calculation result for chinese word formation for the current input syllable combination, and then step S305 is performed.
For example, the following steps are carried out: assuming that the user has already input xin ' xi ' ke ' ji (information technology), the "calculation result" and the "intermediate calculation result" of the pinyin string are already stored in the storage management module.
The user then enters xin 'xi' ji 'shu (information technology) again, and the result of the maximum match that can be made in the storage management module is then xin' xi 'ke' ji (information technology).
The xin ' xi ' ke ' ji (information technology) and the xin ' xi ' ji ' shu have the same portion xin ' xi. We can directly obtain the information of the dynamic programming path map of xin 'xi part in xin' xi 'ke' ji (information technology). The dynamic planning path diagram corresponding to xin 'xi is only a part of the dynamic planning path diagram of xin' xi 'ke' ji (information technology), and not all of the dynamic planning path diagrams. The information of the dynamic planning path map of the xin 'xi part already contains the combination information of the xin' xi and the probabilities of various different combinations. For example: information, euphoria, etc. The combination corresponding to the subsequent syllable ji 'shu can be calculated by using the HMM model from the syllable ji' shu without calculating the whole syllable. Finally, the maximum combination probability of the xin ' xi ' ji ' shu is obtained as the ' information technology '.
Step S305: and compressing and storing the calculation result and the intermediate calculation result into a storage management module, and outputting the calculation result.
The calculation result refers to the result with the highest occurrence probability in all syllable combinations obtained by the HMM model. For example, the syllable combination of zhong ' hua ' ren ' min may be a plurality of combinations such as "chinese", "florist", "neutralization sensitization", and the like, wherein the character string of "chinese" is obtained by calculation, and is the result with the highest occurrence probability, that is, the calculation result. The "intermediate calculation result" refers to information of a dynamically planned path diagram calculated by a dynamic planning method in the process of using the HMM model. The HMM is a more common chinese word model in the existing NLP domain.
Example two
The embodiment provides an intelligent word forming device of a Chinese input method, which comprises an input syllable acquisition module, an input syllable matching module, a similar pinyin string calculation module, a storage management module, an HMM language model and an output module, wherein the input end of the input syllable acquisition module acquires a pinyin string input by a user, and the output end of the input syllable acquisition module is connected with the input end of the input syllable matching module; the output end of the input syllable matching module is respectively connected with the input end of the output module and the input end of the similar pinyin string calculation module; the output end of the similar pinyin string calculation module is connected with the input end of the HMM language model; the output end of the HMM language model is connected with the input end of the storage management module, and the output end of the storage management module is connected with the input end of the output module.
The input syllable acquisition module is used for acquiring a pinyin string input by a user, dividing the pinyin string into a plurality of combinations of syllables and outputting the combinations to the input syllable matching module;
and the input syllable matching module is used for realizing quick complete matching and maximum approximate matching between the syllable combination and the existing calculation record.
And the similar pinyin string calculation module is used for calculating the pinyin string with the maximum approximate matching, directly obtaining calculation results of the same syllables, calculating different syllables by using an HMM language model to obtain calculation results of different syllable parts, and splicing the calculation results of the same syllables and the calculation results of the different syllables.
And the storage management module is used for recording and releasing intermediate results and final calculation results of the language model calculation in the input process of the user.
An output module: and outputting the calculation result of the optimal Chinese word combination to the user.
HMM language model: and calculating the syllables which are not stored in the storage management module, and outputting the calculation result of the optimal Chinese word group to the output module.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (10)
1. An intelligent word-forming calculation optimization method for a Chinese input method is characterized by comprising the following steps: the method comprises the following steps:
step S1, obtaining a pinyin string input by a user;
step S2, performing standard pinyin syllable dividing operation on the pinyin string, and dividing the pinyin string into a plurality of syllable combinations;
and step S3, calling an input syllable matching module, matching the syllable combination with the existing calculation result record, directly obtaining the corresponding calculation result by the same syllable, and calling an HMM language model for calculation by the different syllables.
2. The intelligent word-forming calculation optimization method for the Chinese input method according to claim 1, characterized in that: the step S3 includes:
s301, calling an input syllable matching module, and searching a calculation result completely matched with the syllable combination;
step S302, if a calculation result completely matched with the syllable combination is found, directly outputting the calculation result, and if the calculation result is not found, turning to step S303;
step S303, calling an input syllable matching module to find whether a result of maximum approximate matching with the current syllable combination exists; if the input syllable combination is not found, calling an HMM language model, calculating the calculation result of the best Chinese word combination of the current input syllable combination, and turning to the step S305; if the data is found, go to step S304;
step S304, calling a similar pinyin string calculation module, and directly obtaining the calculation result of the same syllable for the syllable part which has the same result with the maximum approximate matching in the syllable combination; for different syllable portions, using HMM language model calculation to obtain calculation results of different syllable portions, and concatenating the calculation results of the same syllable and the calculation results of different syllables to obtain a calculation result of the best chinese word group of the currently input syllable combination, proceeding to step S305;
and S305, compressing and storing the calculation result of the optimal Chinese word group and the intermediate calculation result into a storage management module, and outputting the calculation result of the optimal Chinese word group.
3. The intelligent word-forming calculation optimization method for the Chinese input method according to claim 2, characterized in that: the optimal calculation result of Chinese word combination means that the result with the highest occurrence probability in all syllable combinations is finally obtained through calculation of an HMM language model.
4. The intelligent word-forming calculation optimization method for the Chinese input method according to claim 2, characterized in that: the intermediate calculation result refers to a dynamic planning path diagram obtained by calculation through a dynamic planning method in the process of using the HMM language model.
5. The intelligent word-forming calculation optimization method for the Chinese input method according to claim 2, characterized in that: the maximum approximate matching process comprises the following steps:
step S3031, matching the syllable combination with the character string stored in the storage management module to obtain the character string with the longest common prefix;
step S3032, searching back from the last syllable of the character string with the longest public prefix to obtain a character string e, wherein the character string e is a word group result with the largest word group length which can be searched in the existing calculation result record;
step S3033, the character string f is obtained by removing the character string e from the character string with the same prefix, that is, the character string of the result of the maximum approximate matching.
6. An intelligent word-forming device for Chinese input method is characterized in that: the input end of the input syllable acquisition module acquires a pinyin string input by a user, and the output end of the input syllable acquisition module is connected with the input end of the input syllable matching module; the output end of the input syllable matching module is respectively connected with the input end of the output module and the input end of the similar pinyin string calculation module; the output end of the similar pinyin string calculation module is connected with the input end of the HMM language model; the output end of the HMM language model is connected with the input end of the storage management module, the output end of the storage management module is connected with the input end of the output module, and the output end of the output module outputs the optimal calculation result of Chinese word formation.
7. The intelligent Chinese input method word-composing device according to claim 6, characterized in that: the input syllable acquisition module divides the pinyin string input by the user into a plurality of syllable combinations and outputs the syllable combinations to the input syllable matching module.
8. The intelligent Chinese input method word-composing device according to claim 6, characterized in that: the input syllable matching module is used for realizing rapid complete matching and maximum approximate matching between syllable combination and the existing calculation record;
the similar pinyin string calculation module calculates the pinyin string with the maximum approximate matching, the same syllables directly obtain calculation results, different syllables are calculated by using an HMM language model to obtain calculation results of different syllable parts, and the calculation results of the same syllables and the calculation results of the different syllables are spliced.
9. The intelligent Chinese input method word-composing device according to claim 6, characterized in that: the storage management module records and releases the intermediate calculation result of the HMM language model and the calculation result of the optimal Chinese word composition.
10. One of the above-mentioned claims 6
The intelligent word-forming device for the Chinese input method is characterized in that: the HMM language model calculates syllables which are not stored in the storage management module, and outputs the calculation result of the optimal Chinese word combination to the output module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065130.2A CN110850998A (en) | 2019-11-04 | 2019-11-04 | Intelligent word-forming calculation optimization method and device for Chinese input method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911065130.2A CN110850998A (en) | 2019-11-04 | 2019-11-04 | Intelligent word-forming calculation optimization method and device for Chinese input method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110850998A true CN110850998A (en) | 2020-02-28 |
Family
ID=69599430
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911065130.2A Withdrawn CN110850998A (en) | 2019-11-04 | 2019-11-04 | Intelligent word-forming calculation optimization method and device for Chinese input method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110850998A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1293428A (en) * | 2000-11-10 | 2001-05-02 | 清华大学 | Information check method based on speed recognition |
| CN102200970A (en) * | 2010-03-22 | 2011-09-28 | 腾讯科技（深圳）有限公司 | Method and device for generating whole sentence in Chinese character input process |
| CN105718070A (en) * | 2016-01-16 | 2016-06-29 | 上海高欣计算机系统有限公司 | Pinyin long sentence continuous type-in input method and Pinyin long sentence continuous type-in input system |
-
2019
- 2019-11-04 CN CN201911065130.2A patent/CN110850998A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1293428A (en) * | 2000-11-10 | 2001-05-02 | 清华大学 | Information check method based on speed recognition |
| CN102200970A (en) * | 2010-03-22 | 2011-09-28 | 腾讯科技（深圳）有限公司 | Method and device for generating whole sentence in Chinese character input process |
| CN105718070A (en) * | 2016-01-16 | 2016-06-29 | 上海高欣计算机系统有限公司 | Pinyin long sentence continuous type-in input method and Pinyin long sentence continuous type-in input system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1889170B (en) | Method and system for generating synthesized speech based on recorded speech template | |
| CN106708893B (en) | Search query word error correction method and device | |
| CN111090727B (en) | Language conversion processing method and device and dialect voice interaction system | |
| CN101326572B (en) | Speech recognition system with huge vocabulary | |
| US20200364299A1 (en) | Systems and methods for unsupervised autoregressive text compression | |
| CN103198149B (en) | Method and system for query error correction | |
| WO2020062680A1 (en) | Waveform splicing method and apparatus based on double syllable mixing, and device, and storage medium | |
| CN103268313A (en) | Method and device for semantic analysis of natural language | |
| CN111178076B (en) | Named entity recognition and linking method, device, equipment and readable storage medium | |
| CN101576929B (en) | Fast vocabulary entry prompting realization method | |
| JP2015529901A (en) | Information classification based on product recognition | |
| Bahl et al. | Automatic recognition of continuously spoken sentences from a finite state grammer | |
| CN110276080B (en) | Semantic processing method and system | |
| CN109145149A (en) | A kind of information alignment schemes, device, equipment and readable storage medium storing program for executing | |
| CN109299471A (en) | A kind of method, apparatus and terminal of text matches | |
| CN104199825A (en) | Information inquiry method and system | |
| CN101271449B (en) | Method and device for reducing vocabulary and Chinese character string phonetic notation | |
| CN105404677A (en) | Tree structure based retrieval method | |
| CN110850998A (en) | Intelligent word-forming calculation optimization method and device for Chinese input method | |
| CN108776705B (en) | Text full-text accurate query method, device, equipment and readable medium | |
| CN113724690B (en) | PPG feature output method, target audio output method and device | |
| CN113886420A (en) | SQL statement generation method and device, electronic equipment and storage medium | |
| KR102136464B1 (en) | Audio Segmentation Method based on Attention Mechanism | |
| JP5700833B2 (en) | Rearrangement model generation device, word order rearrangement device, method, and program | |
| CN112925889A (en) | Natural language processing method, 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200228 |