CN109829713B - Mobile payment mode identification method based on common drive of knowledge and data - Google Patents
Mobile payment mode identification method based on common drive of knowledge and data Download PDFInfo
- Publication number
- CN109829713B CN109829713B CN201910077711.1A CN201910077711A CN109829713B CN 109829713 B CN109829713 B CN 109829713B CN 201910077711 A CN201910077711 A CN 201910077711A CN 109829713 B CN109829713 B CN 109829713B
- Authority
- CN
- China
- Prior art keywords
- mobile payment
- data
- frequency
- event
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of mobile payment information processing, and discloses a mobile payment mode identification method based on knowledge and data common drive, which comprises the steps of collecting mobile user internet access behavior data, filling missing time sequences, counting the frequency of internet access behaviors per second, and constructing a time sequence-frequency matrix; dividing the user internet behavior by the matrix based on an event-driven automatic user internet behavior time sequence segmentation method; extracting relevant characteristics of payment events according to the divided internet access behaviors, and constructing a mobile payment event identification model based on data driving so as to identify the mobile payment event; constructing a subject word extraction model based on a knowledge-driven mobile payment mode based on a word frequency-inverse document frequency algorithm, and extracting subject words; and fusing the identification model and the extraction model to identify the mobile payment mode of the user. The invention identifies the payment event from the mass internet behavior data, and can extract the subject term related to the mobile payment mode, thereby greatly improving the identification performance and the identification efficiency.
Description
Technical Field
The invention relates to the technical field of mobile payment information processing and computer application, in particular to a mobile payment mode identification method based on knowledge and data common driving.
Background
Mobile payment (also called mobile payment) refers to a new payment method for users to purchase physical or virtual goods and various services through wireless network (including mobile communication network and wide area network) by using mobile handheld devices. The system has the characteristics of mobility, timeliness, integration and the like.
Mobile payment means is a basic attribute for understanding the mobile payment behavior of a user. The mobile payment state of the user always shows a certain regularity, and the identification of the mobile payment mode can show the regularity, and the user can be provided with specific services, such as that the user often carries out mobile payment in a certain time period, and corresponding service push can be provided in the time period. The identification of the mobile payment mode can also provide rich information for the individual payment behavior habit, and can also know the mobile payment mode and the development change of the user in time. In addition, mobile payment risk identification and abnormity detection can be performed through identification of a mobile payment mode, and if multiple mobile payments are performed in a certain unfamiliar area by a user in a specific time, the fact that the payment event is probably stolen for payment can be judged. And hot spot payment areas and group payment behavior patterns in cities can be detected based on mobile payment mode identification of a plurality of users. Therefore, the identification of the mobile payment mode of the user has important significance and value for analyzing the user behavior.
At present, the payment of mobile users through client APP software such as Payment treasure, WeChat payment, wing payment, cloud flash payment and Wo payment becomes the mainstream mobile payment mode in China. In addition, the mobile payment process of the user can generate behavior data such as online transaction logs, fund consumption prompting short messages, mobile phone signaling and the like which are closely related to the mobile payment mode. However, due to the fact that mobile payment involves an encryption algorithm, a mobile base station device is in a fault or abnormal state, and the like, when the data is collected, a lot of important data which cannot be analyzed often exist, and therefore, the mobile payment method for efficiently, quickly and accurately identifying the user is challenged.
The current mobile payment mode identification method can be divided into two types: one is a mobile payment mode identification method based on knowledge rule matching; the other is a mobile payment mode identification method based on machine learning.
The mobile payment mode identification method based on knowledge rule matching is a traditional algorithm designed for one or more payment modes by utilizing knowledge in the field of mobile payment. The basic idea of the identification method is to manually extract the characteristics of the mobile payment mode based on the knowledge in the mobile payment field and identify the mobile payment mode by matching with the knowledge rules set manually. Such identification methods can only identify parsed data, but cannot design a corresponding algorithm for effective identification of unresolved data, which may include important and encrypted payment data. Meanwhile, the identification method can only identify part of mobile payment modes, the identification performance is strongly correlated with the manually set knowledge rule, and the method is lack of good self-adaptability and generalization and far short of the commercial standard of the current industry.
The mobile payment mode identification method based on machine learning is an algorithm for automatically extracting relevant characteristics of a mobile payment mode by utilizing a machine learning technology and carrying out payment identification. The basic idea of the identification method is to extract relevant mobile payment features to construct a feature matrix, add labels, perform model training by using a machine learning model, and finally send test data into the trained model for identification. The identification method has the advantages of high flexibility and universality, strong self-adaption and generalization performance, no need of background field knowledge and the like. The method effectively utilizes the unresolved data and improves the performance of the model, but the data model adopted by the method is a 'black box' model, the data construction completely depends on the data, and the method has no explanation meaning on the mobile payment mode.
Disclosure of Invention
Aiming at the defects of the various methods, the invention aims to provide a mobile payment mode identification method based on common drive of knowledge and data, and the mobile payment mode identification method can effectively identify the mobile payment mode of a user, master the consumption habit of the user and meet various service requirements.
The invention provides a mobile payment mode identification method based on knowledge and data common drive, aiming at the problems in the existing mobile payment mode identification method. The method makes full use of the respective advantages of knowledge rule matching and machine learning models, not only can effectively fuse relevant knowledge in the mobile payment field and the characteristics of the data models, but also can maximally utilize unresolved data to improve the recognition performance of the data models, and can reduce the complexity of the algorithm to increase the recognition efficiency.
The technical scheme for solving the problems is to provide a mobile payment mode identification method based on knowledge and data common drive, which comprises the following steps:
step 1), collecting the internet access behavior data of a mobile user, filling a missing time sequence (accurate to the second level), counting the frequency of the internet access behavior data of the user per second, and constructing a time sequence-frequency matrix;
step 2), dividing the user internet behavior by the time sequence-frequency matrix according to an event-driven automatic user internet behavior time sequence segmentation method;
step 3), extracting relevant characteristics of the payment event by utilizing the divided user internet behavior event, and constructing a mobile payment event identification model based on data driving so as to identify the mobile payment event;
step 4), constructing a mobile payment mode subject word extraction model based on knowledge driving based on a word frequency-inverse document frequency algorithm, thereby extracting the subject words of the mobile payment mode;
and 5), fusing the mobile payment event recognition model based on data driving and the mobile payment mode subject word extraction model based on knowledge driving, constructing a mobile payment mode recognition method based on knowledge and data driving, and finally recognizing the mobile payment mode of the user.
The user internet behavior data in the step 1) includes, but is not limited to, user internet log data and user short message ticket data.
The method for automatically segmenting the time sequence of the user internet surfing behavior based on the event driving in the step 2) specifically comprises the following steps: firstly, the break points of the frequency of the log data of the internet surfing are utilized to determine the dividing points of the occurrence of the events, and the adjacent dividing points must meet the time limit of the minimum event (the mobile payment event model identification performance is optimal when the time limit of the minimum event is 6 minutes through experimental verification). If the starting point time of the current user internet behavior is 20190121090000, the end point time is 20190121100000, and each second time sequence corresponds to one internet data frequency, firstly, the time starting point and the end point are connected to form a straight line, a point with the maximum distance from the straight line is selected as a dividing point, the dividing point is sequentially connected with the time starting point and the time end point, if the time interval between the dividing point and the time starting point or the time end point meets the time limit (6 minutes) of the minimum event, then, the point with the maximum distance from the straight line connecting the time starting point or the end point is selected as the dividing point, the division is continued according to the principle, then, the front top-k dividing points with the maximum distance value are selected, finally, the dividing point is further determined by using the short message ticket data of the user, and the dividing points are sequentially connected to form the user internet behavior.
The payment event related characteristics in the step 3) include, but are not limited to, internet log data frequency, unresolved internet log data frequency, short message ticket data frequency and single internet log data highest frequency in the event.
Wherein, the step 3) of constructing the mobile payment event recognition model based on data driving specifically comprises the following steps: firstly, extracting relevant characteristics of payment events from divided user internet behavior events, wherein the characteristics include but are not limited to internet log data frequency, unresolved internet log data frequency, short message ticket data frequency and single internet log data highest frequency in the events; then dividing the labeled payment event characteristic data set into a training set and a testing set, and sending the training set into a machine learning model (such as a support vector machine model) for training; and finally, sending the test set into a trained machine learning model for testing, adjusting relevant parameters of the machine learning model according to the test performance to reach the performance standard, and finally identifying the mobile payment event.
The fusion mode of the mobile payment event recognition model based on data driving and the mobile payment mode subject word extraction model based on knowledge driving in the step 5) is as follows: mobile payment event recognition model function f with internal function as data drived(x，θd) And the foreign function is a knowledge-driven mobile payment mode subject term extraction model function fk(x，θk) The function of the mobile payment mode identification method based on common driving of knowledge and data is fk(fd(x，θd)，θk). Wherein x represents input data, including internet log data and the like; f. ofkAnd fdRespectively a knowledge-driven submodel and a data-driven submodel function, thetakAnd thetadCorresponding to knowledge-driven submodel and data-driven submodel parameters, i.e. theta, respectivelykExpressed as k keywords selected from the theme word model of the mobile payment mode, namely thetadRepresented as training parameters of a machine learning model in the mobile payment event recognition model.
The invention has the following beneficial effects:
the invention relates to a mobile payment mode identification method based on knowledge and data common drive. The method makes full use of the respective advantages of knowledge rule matching and machine learning models, not only can effectively fuse relevant knowledge in the mobile payment field and the characteristics of the data models, but also can maximally utilize unresolved data to improve the recognition performance of the data models, and can reduce the complexity of the algorithm to increase the recognition efficiency.
Drawings
FIG. 1 is a functional block diagram of the method of the present invention;
FIG. 2 is a flow chart of the method of the present invention;
FIG. 3 is a flowchart of a method for automatically segmenting a time sequence of a user surfing behavior based on event driving according to the present invention;
FIG. 4 is a flow diagram of a data-driven based mobile payment event recognition model of the present invention;
FIG. 5 is a flow chart of the knowledge-driven-based mobile payment method topic word extraction model of the present invention;
fig. 6 is a flow chart of the mobile payment mode identification method based on knowledge and data co-driving of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly and completely apparent, the technical solutions in the embodiments of the present invention are described below with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Examples
As shown in fig. 1 and fig. 2, the invention provides a mobile payment mode identification method based on knowledge and data common drive, which comprises the following steps:
step 1), collecting the internet access behavior data of a mobile user, filling a missing time sequence (accurate to the second level), counting the frequency of the internet access behavior data of the user per second (namely the frequency of the data corresponding to the missing time sequence is zero), and constructing a time sequence-frequency matrix; the specific time series-frequency matrix is shown in table 1:
TABLE 1 time series-frequency matrix for network loading behavior
| Time series | Data frequency of internet access behavior |
| 20190121101718 | 5 |
| 20190121101719 | 0 |
| 20190121101720 | 3 |
| 20190121101721 | 6 |
| … | … |
The user internet behavior data in the step 1) includes, but is not limited to, user internet log data and user short message ticket data.
Step 2), dividing the user internet behavior by the time sequence-frequency matrix according to an event-driven automatic user internet behavior time sequence segmentation method to form a user internet behavior event;
as shown in fig. 3, the method for automatically segmenting the time sequence of the user internet surfing behavior based on event driving in step 2) specifically comprises the following steps: firstly, determining the division points of the occurrence of events by using the mutation points of the frequency of the log data of the Internet surfing, wherein the adjacent division points must meet the time limit of the minimum event, then selecting the division points with the maximum top-k distance values, and finally further determining the division points by using the short message ticket data of the user, and sequentially connecting the division points to form the behavior event of the Internet surfing of the user.
Step 3), extracting relevant characteristics of the payment event by utilizing the divided user internet behavior event, and constructing a mobile payment event identification model based on data driving so as to identify the mobile payment event;
the payment event related characteristics in the step 3) include, but are not limited to, internet log data frequency, unresolved internet log data frequency, short message ticket data frequency and single internet log data highest frequency in the event.
As shown in fig. 4, the step 3) of constructing the mobile payment event recognition model based on data driving specifically includes: firstly, extracting relevant characteristics of payment events from divided user internet behavior events, wherein the characteristics include but are not limited to internet log data frequency, unresolved internet log data frequency, short message ticket data frequency and single internet log data highest frequency in the events; then dividing the labeled payment event characteristic data set into a training set and a testing set, and sending the training set into a machine learning model (such as a support vector machine model) for training; and finally, sending the test set into a trained machine learning model for testing, adjusting relevant parameters of the machine learning model according to the test performance to reach the performance standard, and finally identifying the mobile payment event.
Step 4), constructing a knowledge-driven mobile payment mode subject word extraction model based on a Term Frequency-Inverse Document Frequency (TF-IDF) algorithm, and extracting subject words of a mobile payment mode;
as shown in fig. 5, the step 4) of constructing the subject term extraction model based on the knowledge-driven mobile payment method specifically includes: firstly, normalizing the internet log data, removing redundant information of the internet log data, and extracting keywords (the internet log data is URL type data, and the keywords are HOST values of the internet log data); then, calculating the word frequency-inverse document frequency value of each extracted keyword, and sequencing; and finally, taking the top-k keywords with the maximum word frequency-inverse document frequency value to form the subject words of the mobile payment mode (k is about 5-10 optimal keywords).
And 5), fusing the mobile payment event recognition model based on data driving and the mobile payment mode subject word extraction model based on knowledge driving, constructing a mobile payment mode recognition method based on knowledge and data driving, and finally recognizing the mobile payment mode of the user.
As shown in fig. 6, the fusion mode of the data-driven-based mobile payment event identification model and the knowledge-driven-based mobile payment mode subject word extraction model in step 5) is as follows: mobile payment event recognition model function f with internal function as data drived(x，θd) And the foreign function is a knowledge-driven mobile payment mode subject term extraction model function fk(x，θk) The function of the mobile payment mode identification method based on common driving of knowledge and data is fk(fd(x，θd)，θk). Wherein f iskAnd fdRespectively a knowledge-driven submodel and a data-driven submodel function, thetakAnd thetadCorresponding to knowledge-driven submodel and data-driven submodel parameters, i.e. theta, respectivelykExpressed as k keywords selected from the theme word model of the mobile payment mode, namely thetadRepresented as training parameters of a machine learning model in the mobile payment event recognition model.
From the technical point of view, the invention discloses a mobile payment mode identification method based on common driving of knowledge and data. Compared with the existing knowledge rule matching and machine learning model method, the method fully utilizes the respective advantages of the knowledge rule matching and the machine learning model, not only can effectively fuse the relevant knowledge in the mobile payment field and the characteristics of the data model, but also can maximally utilize the unresolved data to improve the recognition performance of the data, and can reduce the complexity of the algorithm to increase the recognition efficiency.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: ROM, RAM, magnetic or optical disks, and the like.
The above-mentioned embodiments, which further illustrate the objects, technical solutions and advantages of the present invention, should be understood that the above-mentioned embodiments are only preferred embodiments of the present invention, and should not be construed as limiting the present invention, and any modifications, equivalents, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A mobile payment mode identification method based on knowledge and data common drive is characterized by comprising the following steps:
step 1) collecting the internet access behavior data of a mobile user, filling a time sequence, counting the internet access behavior data frequency of the mobile user per second, and constructing a time-frequency matrix between the time sequence and the data frequency;
step 2) automatically dividing the time-frequency matrix according to an event-driven user internet behavior time sequence, determining division points of behavior events by using mutation points of user internet log data frequency, selecting the division points with the first k largest distance values, further determining the division points by using user short message ticket data, and sequentially connecting the division points to form the user internet behavior events; dividing each internet behavior event of the user;
step 3) extracting relevant characteristics of the mobile payment event by utilizing the divided internet behavior event, constructing a mobile payment event identification model based on data driving, and extracting relevant characteristics of the payment event from the divided user internet behavior event; dividing the labeled payment event characteristic data set into a training set and a testing set, and sending the training set into a machine learning model for training; sending the test set into a trained machine learning model for testing, and adjusting relevant parameters of the machine learning model according to test performance so as to reach performance standards; thereby identifying mobile payment events in the time-frequency matrix;
step 4) constructing a mobile payment mode subject word extraction model based on knowledge driving according to a word frequency-inverse document frequency algorithm, normalizing the internet log data, removing redundant information of the internet log data, and extracting keywords; calculating the word frequency-inverse document frequency value of each extracted keyword, and sequencing; taking the key words with the maximum first k word frequency-inverse document frequency values to form a subject word of a mobile payment mode; extracting subject terms in a mobile payment mode from the time-frequency matrix;
step 5) fusing the mobile payment event recognition model and the mobile payment mode subject word extraction model, constructing a mobile payment mode recognition method based on common driving of knowledge and data, setting a fusion function, and taking an internal function as a mobile payment event recognition model function f driven by datad(x,θd) The foreign function is used as a knowledge-driven mobile payment mode subject term extraction model function fk(x,θk) The function of the mobile payment mode identification method based on common driving of knowledge and data is fk(fd(x,θd),θk) (ii) a Thereby identifying the user mobile payment mode in the time-frequency matrix;
wherein x represents the input data; f. ofkAnd fdRespectively as a mobile payment mode subject term extraction model and a mobile payment event recognition model function, thetakExpressed as k keywords theta selected in a mobile payment mode subject term extraction modeldRepresented as training parameters of a machine learning model in the mobile payment event recognition model.
2. The mobile payment mode identification method based on knowledge and data common drive of claim 1, wherein the user internet behavior data in step 1) comprises user internet log data and user short message ticket data.
3. The knowledge-and-data-driven mobile payment mode identification method according to claim 1, wherein the machine learning model comprises any one or more of a vector support machine, a decision tree model and an integration model.
4. The mobile payment method based on knowledge and data common drive of claim 1, wherein the payment event related characteristics comprise internet log data frequency, unresolved internet log data frequency, short message ticket data frequency and single internet log data highest frequency in the behavior event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910077711.1A CN109829713B (en) | 2019-01-28 | 2019-01-28 | Mobile payment mode identification method based on common drive of knowledge and data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910077711.1A CN109829713B (en) | 2019-01-28 | 2019-01-28 | Mobile payment mode identification method based on common drive of knowledge and data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109829713A CN109829713A (en) | 2019-05-31 |
| CN109829713B true CN109829713B (en) | 2020-09-15 |
Family
ID=66862591
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910077711.1A Active CN109829713B (en) | 2019-01-28 | 2019-01-28 | Mobile payment mode identification method based on common drive of knowledge and data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829713B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110495408B (en) * | 2019-09-20 | 2021-08-17 | 重庆工商大学 | Fish, shrimp and ginseng breeding decision system and device based on common driving of data and knowledge |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| US8850537B1 (en) * | 2012-09-27 | 2014-09-30 | Emc Corporation | Self-tuning knowledge-based authentication |
| CN106250855A (en) * | 2016-08-02 | 2016-12-21 | 南京邮电大学 | A kind of multi-modal emotion identification method based on Multiple Kernel Learning |
| CN108229963A (en) * | 2016-12-12 | 2018-06-29 | 阿里巴巴集团控股有限公司 | The Risk Identification Method and device of user's operation behavior |
| CN108280766A (en) * | 2017-01-06 | 2018-07-13 | 阿里巴巴集团控股有限公司 | Trading activity Risk Identification Method and device |
| CN109165284A (en) * | 2018-08-22 | 2019-01-08 | 重庆邮电大学 | A kind of financial field human-computer dialogue intension recognizing method based on big data |
-
2019
- 2019-01-28 CN CN201910077711.1A patent/CN109829713B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8850537B1 (en) * | 2012-09-27 | 2014-09-30 | Emc Corporation | Self-tuning knowledge-based authentication |
| CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
| CN106250855A (en) * | 2016-08-02 | 2016-12-21 | 南京邮电大学 | A kind of multi-modal emotion identification method based on Multiple Kernel Learning |
| CN108229963A (en) * | 2016-12-12 | 2018-06-29 | 阿里巴巴集团控股有限公司 | The Risk Identification Method and device of user's operation behavior |
| CN108280766A (en) * | 2017-01-06 | 2018-07-13 | 阿里巴巴集团控股有限公司 | Trading activity Risk Identification Method and device |
| CN109165284A (en) * | 2018-08-22 | 2019-01-08 | 重庆邮电大学 | A kind of financial field human-computer dialogue intension recognizing method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 数据驱动的信息行为研究的回顾与展望;李月琳 等;《信息资源管理学报》;20180630(第2期);第13-23页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109829713A (en) | 2019-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108322473B (en) | User behavior analysis method and device | |
| WO2020073714A1 (en) | Training sample obtaining method, account prediction method, and corresponding devices | |
| US20210035126A1 (en) | Data processing method, system and computer device based on electronic payment behaviors | |
| CN105187242B (en) | A kind of user's anomaly detection method excavated based on variable-length pattern | |
| CN108304426B (en) | Identification obtaining method and device | |
| CN103544436A (en) | System and method for distinguishing phishing websites | |
| WO2020257991A1 (en) | User identification method and related product | |
| WO2021174812A1 (en) | Data cleaning method and apparatus for profile, and medium and electronic device | |
| CN110781381B (en) | Data verification method, device, equipment and storage medium based on neural network | |
| CN109858919A (en) | Determination method and device, online ordering method and the device of abnormal account | |
| CN109063433B (en) | False user identification method and device and readable storage medium | |
| CN111798241A (en) | Transaction data processing method and device, electronic equipment and readable storage medium | |
| CN105550253B (en) | Method and device for acquiring type relationship | |
| CN111949702B (en) | Abnormal transaction data identification method, device and equipment | |
| CN104915399A (en) | Recommended data processing method based on news headline and recommended data processing method system based on news headline | |
| CN113449753B (en) | Service risk prediction method, device and system | |
| US10706371B2 (en) | Data processing techniques | |
| WO2017143703A1 (en) | Offline resource mining method and device | |
| CN115577172A (en) | Article recommendation method, device, equipment and medium | |
| CN110807667B (en) | Method and device for activating sleeping clients | |
| CN109829713B (en) | Mobile payment mode identification method based on common drive of knowledge and data | |
| CN109271495B (en) | Question-answer recognition effect detection method, device, equipment and readable storage medium | |
| CN110728582B (en) | Information processing method, device, storage medium and processor | |
| CN114841705B (en) | Anti-fraud monitoring method based on scene recognition | |
| CN111209391A (en) | Information identification model establishing method and system and interception method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |