CN113051612B - Consumer account classification method, apparatus, computer device and storage medium - Google Patents
Consumer account classification method, apparatus, computer device and storage medium Download PDFInfo
- Publication number
- CN113051612B CN113051612B CN202110277529.8A CN202110277529A CN113051612B CN 113051612 B CN113051612 B CN 113051612B CN 202110277529 A CN202110277529 A CN 202110277529A CN 113051612 B CN113051612 B CN 113051612B
- Authority
- CN
- China
- Prior art keywords
- consumption
- items
- item
- frequent
- account
- 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
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000000354 decomposition reaction Methods 0.000 claims description 39
- 230000001186 cumulative effect Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 6
- 238000005065 mining Methods 0.000 description 5
- 230000002068 genetic effect Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000001010 compromised effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
Abstract
The application relates to a consumption account classification method, a consumption account classification device, computer equipment and a storage medium. The method comprises the following steps: acquiring a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts; determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record; wherein the occurrence frequency of the frequent consumption items meets a preset condition; according to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item; and classifying the consumption accounts according to the virtual consumption condition. By adopting the method, the private data of the user can be prevented from being revealed.
Description
Technical Field
The present application relates to the field of artificial intelligence and data mining technologies, and in particular, to a method and apparatus for classifying consumption accounts, a computer device, and a storage medium.
Background
In the related technology, detailed payment flow data generated during shopping consumption of a user are often needed to describe the user portrait, however, the more detailed payment flow data has higher potential safety hazards at the back, so that the risk of revealing user privacy data is continuously improved, and the burden of guaranteeing user data privacy and data safety is also improved.
Accordingly, there is a problem in the related art that user privacy data is easily compromised.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a consumer account classification method, apparatus, computer device, and storage medium that can avoid revealing user privacy data.
A method of consumer account classification, the method comprising:
acquiring a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts;
determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record; wherein the occurrence frequency of the frequent consumption items meets a preset condition;
According to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item;
and classifying the consumption accounts according to the virtual consumption condition.
A consumer account sorting apparatus, the apparatus comprising:
the acquisition module is used for acquiring the consumption data of the user; wherein, the user consumption data records consumption items corresponding to consumption accounts;
the determining module is used for determining frequent consumption items in the consumption items based on the occurrence times corresponding to each item in the consumption items in the user consumption data; the occurrence times corresponding to the frequent consumption items meet preset conditions;
the decomposing module is used for decomposing the actual consumption result of the consumption account according to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item;
and the classification module is used for classifying the consumption account according to the virtual consumption condition.
A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:
Acquiring a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts;
determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record; wherein the occurrence frequency of the frequent consumption items meets a preset condition;
according to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item;
and classifying the consumption accounts according to the virtual consumption condition.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts;
determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record; wherein the occurrence frequency of the frequent consumption items meets a preset condition;
According to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item;
and classifying the consumption accounts according to the virtual consumption condition.
The consumption account classification method, the consumption account classification device, the computer equipment and the storage medium are characterized in that the user consumption records comprising at least two consumption items corresponding to the consumption accounts are obtained; each consumption item has a corresponding consumption amount, and based on the occurrence times of the consumption items in the user consumption record, frequent consumption items with the occurrence times meeting preset conditions are determined in the consumption items; and the virtual consumption condition of the consumption account in the frequent consumption items is obtained by decomposing the actual consumption total amount of the consumption account according to the consumption amount corresponding to the frequent consumption items, so that the actual consumption characteristics of the consumption account are accurately represented, the classification processing of the consumption account by adopting the virtual consumption condition in the follow-up process is realized, the user portrait of the consumption account is prevented from being directly represented by adopting complete and detailed consumption flow data, the user privacy data is prevented from being revealed, and the privacy and the data safety of the user data are ensured.
Drawings
FIG. 1 is a flow diagram of a method of classifying consumer accounts according to one embodiment;
FIG. 2 is a schematic diagram of classification of clustered consumption accounts in one embodiment;
FIG. 3 is a flow diagram of a method of consumer account classification in one embodiment;
FIG. 4 is a flow diagram of another method of consumer account classification in one embodiment;
FIG. 5 is a block diagram of a consumer account sorting apparatus in one embodiment;
fig. 6 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
In one embodiment, as shown in fig. 1, a method for classifying a consumption account is provided, which is taken as an example of application of the method to a server, wherein the server may be implemented by a stand-alone server or a server cluster formed by a plurality of servers, and the method for classifying the consumption account includes the following steps:
step S110, obtaining a user consumption record.
The user consumption record may refer to a data record generated when the consumption account consumes. Such as a payment data record for the user on a particular merchandise item.
The user consumption record comprises at least two consumption items corresponding to the consumption account, and each consumption item has a corresponding consumption amount. Of course, the user consumption record may also be named a user payment record. In practice, a consumption item may refer to a pay-per-play item (a virtual game resource) in a game.
In practical application, the user consumption record may be recorded as d= { m i }. For example, d= {1,2,1,3,2,1}, where it is indicated that the user consumption record includes three consumption items, respectively consumption items with a consumption amount of "1A consumption item with a consumption amount of "2" and a consumption item with a consumption amount of "3".
In practical applications, the user consumption record may also be recorded as d= { (t) i ,m i ) }. For example, d= { (1, 1) (2, 2) (1, 3) }, it indicates that the user consumption record includes three consumption items, namely, a consumption item with a consumption amount of "1", a consumption item with a consumption amount of "2", and a consumption item with a consumption amount of "3", and the number of occurrences of the consumption item with a consumption amount of "1" is 1, the number of occurrences of the consumption item with a consumption amount of "2" is 2, and the number of occurrences of the consumption item with a consumption amount of "3" is 1.
In practice, the consumer items may also be named paypoints.
In a specific implementation, the server obtains a data record generated when the consumption account is consumed, namely a user consumption record.
Step S120, determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record.
Wherein the occurrence number of the frequent consumption items satisfies a preset condition.
In a specific implementation, after the server obtains the user consumption record, the server determines the occurrence number of each consumption item in the user consumption record, and determines frequent consumption items in each consumption item based on the occurrence number of each consumption item in the user consumption record. Specifically, the server may employ a frequent item set mining method, such as Apriori or FP-growth, to mine frequent consumption items among consumption items.
For example, knowing the user consumption record d= {1,2,1,3,2,1}, the frequent consumption item is determined as a consumption item whose consumption amount is "1" and a consumption item whose consumption amount is "2" among the consumption items based on the number of occurrences of the consumption item in the user consumption record.
And step S130, decomposing the actual consumption total of the consumption account according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item.
In a specific implementation, after the server determines the frequent consumption items, the serverAnd then the actual consumption total of each consumption account can be subjected to natural number decomposition according to the consumption amount corresponding to the frequent consumption item, so as to obtain the virtual consumption condition of the consumption account in the frequent consumption item. Specifically, the server will finally determine the decomposition result u= { u of the user payment on the frequently consumed items according to the frequently consumed item set T 1 ,…,u T }. The decomposition result represents the virtual consumption condition of the consumption account in the frequent consumption item.
And step S140, classifying the consumption accounts according to the virtual consumption condition.
In the specific implementation, after determining that the consumption account is in the virtual consumption condition of the frequent consumption item, the server classifies the consumption account according to the virtual consumption condition of the consumption account in the frequent consumption item. For example, if the virtual consumption condition of the consumption account at each frequent consumption item is greater than 1, which indicates that the consumption account pays at each frequent consumption item, the server classifies the consumption account as an account with high payment capability. If the virtual consumption condition of the consumption account in each frequent consumption item is 0, which indicates that the consumption account does not pay in each frequent consumption item, the server classifies the consumption account as an account with weak payment capability. In this way, assistance may be provided for artificial intelligence based item recommendations, content recommendations, and the like.
Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, reasoning and decision.
The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
In the above-mentioned consumption account classification method, the user consumption records including at least two consumption items corresponding to the consumption account are obtained; each consumption item has a corresponding consumption amount, and based on the occurrence times of the consumption items in the user consumption record, frequent consumption items with the occurrence times meeting preset conditions are determined in the consumption items; and the virtual consumption condition of the consumption account in the frequent consumption items is obtained by decomposing the actual consumption total amount of the consumption account according to the consumption amount corresponding to the frequent consumption items, so that the actual consumption characteristics of the consumption account are accurately represented, the classification processing of the consumption account by adopting the virtual consumption condition in the follow-up process is realized, the user portrait of the consumption account is prevented from being directly represented by adopting complete and detailed consumption flow data, the user privacy data is prevented from being revealed, and the privacy and the data safety of the user data are ensured.
In one embodiment, determining frequent consumption items among the consumption items based on the number of occurrences of the consumption items in the user consumption record includes: determining a target consumption item in the consumption items according to the occurrence times of the consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items is larger than a preset ratio threshold, and the occurrence number of each target consumption item is larger than or equal to the occurrence number of unselected consumption items; and taking each item in the target consumption items as a frequent consumption item.
Wherein the total number of occurrences of the target consumption item may refer to a sum of the number of occurrences of each item in the target consumption item.
Wherein the total number of occurrences of the consumption item may refer to a sum of the number of occurrences of the respective consumption item.
For example, given that the user consumption record is d= {1,2,1,3,2,1}, and the target consumption item is a consumption item whose consumption amount is "1" and a consumption item whose consumption amount is "2", the total number of occurrences of the target consumption item is 5 times, and the total number of occurrences of the consumption item is 6 times.
In a specific implementation, in the process of determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption records, the server can determine a target consumption item in the consumption items according to the occurrence times of the consumption items. Specifically, the server may sort the individual consumption items in descending order according to the number of occurrences of the consumption item; then, the server selects k values with the largest occurrence number, and records the k values as an intermediate frequent consumption point H= { H 1 ,…,h k I.e. the target consumer item.
In practical applications, since the frequency of the consumption amount usually shows a long tail distribution, k can be selected according to the two-eight rule, i.e. the sum of the first k occurrences is 80% of the total number.
Finally, the server takes each item in the target consumption items as a frequent consumption item.
According to the technical scheme, in the process of determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption records, a target consumption item is determined in the consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items is larger than a preset ratio threshold, the occurrence number of each target consumption item is larger than or equal to the occurrence number of unselected consumption items, so that frequent-payment consumption items of a consumption account are mined out from all consumption items in a user consumption record, and payment characteristics of payment business can be described based on the frequent-consumption items.
In one embodiment, determining the target consumption item from the consumption items according to the occurrence number of the consumption items comprises: sequencing the consumption items according to the sequence from the big appearance times to the small appearance times to obtain sequenced consumption items; counting the cumulative percentage of the occurrence times corresponding to each item in the ordered consumption items; determining a target consumption item from the ordered consumption items according to the cumulative percentage of the occurrence times; the cumulative percentage of the occurrence times corresponding to the target consumption items is smaller than or equal to a preset percentage threshold value.
In a specific implementation, the server determines a target consumption item in the consumption items according to the occurrence times of the consumption items, and specifically includes: the server sorts all the consumption items according to the sequence from the big appearance times to the small appearance times to obtain sorted consumption items; counting the cumulative percentage of the occurrence times corresponding to each item in the ordered consumption items; determining a target consumption item from the ordered consumption items according to the cumulative percentage of the occurrence times; the cumulative percentage of the occurrence times corresponding to the target consumption items is smaller than or equal to a preset percentage threshold value.
For example, consider that d= {1,2,1,3,2,1} contains a payment amount, and the number of payments is omitted due to the absence. The following results are obtained after counting the times and reversing the rows:
| consumption item (consumption amount) | Number of occurrences | Cumulative percentage of occurrences |
| 1 | 3 | 3/6＝50％ |
| 2 | 2 | 5/6＝83％ |
| 3 | 1 | 6/6＝100％ |
Then, the server selects 2 payment amounts to take values 1 and 2 according to the rule of two eight, and the target consumption item H= {1,2}. That is, the cumulative percentage of occurrences corresponding to the consumption item with the consumption amount of "1" is less than the preset percentage threshold value 83%, and the cumulative percentage of occurrences corresponding to the consumption item with the consumption amount of "2" is equal to the preset percentage threshold value 83%.
According to the technical scheme of the embodiment, a target consumption item is determined in the consumption items according to the occurrence times of the consumption items, the consumption items are obtained after the sequencing by sequencing the consumption items according to the sequence from the large occurrence times to the small occurrence times, and the cumulative percentage of the occurrence times corresponding to the consumption items after the sequencing is counted; finally, determining a target consumption item from the ordered consumption items according to the accumulated percentage of the occurrence times; wherein, the cumulative percentage of the occurrence times corresponding to the target consumption item is smaller than or equal to a preset percentage threshold; thus, the method can quickly and accurately mine the consumption items with frequent payment of the consumption account in the consumption items as target consumption items.
In one embodiment, if the user consumption record further includes occurrence information of the consumption item, determining frequent consumption items among the consumption items based on occurrence times corresponding to the consumption items in the user consumption data includes: grouping all items in the consumption items according to the occurrence number information of the consumption items to obtain grouped consumption items; wherein, the corresponding appearance times of each item in the consumption items after each group of grouping are equal; determining a target consumption item from the grouped consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items after grouping is larger than a preset ratio threshold; and combining various items in each group of target consumption items to obtain a consumption item set as frequent consumption items.
In a specific implementation, if the user consumption record further includes information about the occurrence number of the consumption item, the server determines, based on the occurrence number corresponding to the consumption item in the user consumption data, a frequent consumption item in the consumption item, and specifically includes: the server groups each item in the consumption items according to the occurrence number information of the consumption items to obtain grouped consumption items; wherein the number of occurrences corresponding to each of the grouped consumer items is equal.
Then, the server determines a target consumption item from the grouped consumption items; wherein the ratio between the total number of occurrences of the target consumer item and the total number of occurrences of the consumer item after grouping is greater than a preset ratio threshold. And finally, the server combines various items in each group of target consumption items to obtain a consumption item set as frequent consumption items.
Specifically, first, the user payment data sets are grouped according to the payment Fei Cishu, and the consumption items with the same occurrence number are grouped into one group, so as to obtain the grouped consumption items. The post-grouping consumption term of the payment number i is G i ＝{m j And the element is various payment amounts when the payment number is i. Then, the server for each G i Frequent item set mining is carried out to obtain G i Frequent payment item set H i . The server then aggregates all H' s i To obtain H= U-shaped gate i {(i，h)|h∈G i Each frequent flyer additionally has corresponding flyer information.
According to the technical scheme of the embodiment, each item in the consumption items is grouped according to the occurrence number information of the consumption items, so that the consumption items after grouping are obtained; wherein, the corresponding appearance times of each item in the consumption items after each group of grouping are equal; determining a target consumption item from the grouped consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items after grouping is larger than a preset ratio threshold; combining each item in each group of target consumption items to obtain a consumption item set as a frequent consumption item; therefore, frequent item mining processing of the consumption items after each grouping can be realized by taking the group as a unit, the data processing amount of the server for each frequent item mining processing is reduced, and the efficiency of the server for mining the frequent consumption items is improved.
In one embodiment, if the user consumption record does not include the occurrence information of the consumption item, the method further includes: performing frequency statistics on the user consumption records to obtain frequency statistics results; the frequency statistics include the number of occurrences of the consumption item in the user consumption record.
In the specific implementation, if the server detects that the user consumption record does not include the occurrence number information of the consumption items, the server performs frequency statistics processing on each consumption item in the user consumption record to obtain a frequency statistics result. Wherein the frequency statistics include the number of occurrences of the consumption item in the user consumption record.
According to the technical scheme, if the server detects that the user consumption record does not comprise the occurrence number information of the consumption items, the server performs frequency statistics processing on each consumption item in the user consumption record, so that a frequency statistics result comprising the occurrence number information of the consumption items in the user consumption record is accurately obtained, and the server can conveniently and accurately mine frequent consumption items based on the occurrence number of the consumption items in the user consumption record.
In one embodiment, according to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item, including: and carrying out natural number optimal decomposition on the actual consumption total according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item, so that the difference between the virtual consumption total and the actual consumption total of the frequent consumption item of the consumption account determined according to the virtual consumption condition meets a preset difference threshold.
In a specific implementation, the server decomposes the actual consumption total of the consumption account according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item, and specifically includes: the server can perform natural number optimal decomposition on the actual consumption total according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item, so that the difference between the virtual consumption total and the actual consumption total of the frequent consumption item of the consumption account determined according to the virtual consumption condition meets a preset difference threshold.
Specifically, the server may decompose the actual total consumption of each consumption account with the consumption amount corresponding to the frequent consumption item H based on a greedy algorithm. The method comprises the following specific steps:
step 1: the actual consumption sum of the consumption account is M, the decomposition result is initialized to v= (0, …, 0), and the length is k.
Step 2: if M is greater than the sum of all the amounts in H, then let all the elements in v be 1, i.e. the user pays for every frequent pay point, and end the decomposition to obtain the decomposition result v= (1, …, 1);
otherwise, the sum of all the amounts in M is smaller than H, and the step 3 is executed.
Step 3: if the maximum payment value smaller than the total actual consumption exists in H, the maximum payment value is not recorded as m j At the same time let the j-th element v in the corresponding v j Increase 1, update M to M-M j Then repeating the step 3; ending the decomposition until all the amounts in H are greater than M to obtain a decomposition result v= (v) 1 ,…，v k )。
For example, assuming that three consumption accounts are provided, the actual consumption totals are 4,3,2, respectively. Meanwhile, the frequent consumption items are consumption items with a consumption amount of "1" and consumption items with a consumption amount of "2". I.e., t= {1,2}.
For a consumption account with a total of "4" for actual consumption: since 4 is greater than 1+2=3, determining that each frequent item of the consumption account is paid by the above-described decomposition step, resulting in a decomposition result of (1, 1);
for a consumption account with a total of "3" for actual consumption: since 3 is not greater than 1+2=3, the maximum amount of not greater than 3 is selected to be 2, v 2 Adding 1, and then updating 3-2 to 1; the maximum amount of not more than 1 is 1, v j Adding 1, updating 1-1 to 0, and stopping decomposition to obtain a decomposition result (1, 1) if no payment amount smaller than 0 exists;
similarly, for a consumption account with an actual consumption total of "2", the decomposition result is (1, 0).
In addition, a genetic algorithm can be adopted to decompose the actual total consumption of each consumption account by using the consumption amount corresponding to the frequent consumption item H. The method comprises the following specific steps:
first, the decomposition result is encoded as v= (v 1 ,…,v k ) The length is the number of elements in H; each element v i The value of (1) is 0 or 1, representing whether the user is at the corresponding payment point h i ＝(a i ，b i ) Payment; then the virtual consumption sum of the user is m= Σaccording to the code v i v i ×b i The number of payments by the user is n= Σ i v i ×a i The method comprises the steps of carrying out a first treatment on the surface of the The M is the actual sum of the consumption of the user, and N is the payment number of the user.
The objective of the genetic algorithm is then to minimize M-M, the constraints being M < M and n=n, and the genetic algorithm is used to solve the optimal code v.
It should be noted that, the genetic algorithm may be replaced by any other integer programming solution method, the optimization objective may be changed to |m-m|, and the constraint of M < M is removed, that is, the decomposed result is allowed to be slightly larger than the original payment amount, because the payment may have a discount, resulting in a nominal real payment slightly lower than the nominal payment.
According to the technical scheme of the embodiment, the virtual consumption condition of the consumption account in the frequent consumption item is obtained by carrying out natural number optimal decomposition on the actual consumption total according to the consumption amount corresponding to the frequent consumption item, so that the difference between the virtual consumption total and the actual consumption total of the consumption account in the frequent consumption item determined according to the virtual consumption condition meets a preset difference threshold, and the consumption characteristics of the consumption account can be properly represented by the virtual consumption condition of the consumption account in the frequent consumption item obtained through decomposition.
In one embodiment, classifying the consumption account according to the virtual consumption condition includes: clustering the consumption accounts according to the virtual consumption condition and the consumption amount corresponding to the frequent consumption items to obtain clustered consumption accounts; and generating user portrait information corresponding to the consumption account according to the clustered consumption account.
In a specific implementation, the classifying process of the consumption account by the server according to the virtual consumption condition comprises the following steps: the server obtains virtual consumption conditions of the consumption account in the frequent consumption items; clustering the consumption accounts according to the virtual consumption condition and the consumption amount corresponding to the frequent consumption items to obtain clustered consumption accounts; and generating user portrait information corresponding to the consumption account according to the clustered consumption account.
The user portrait information may refer to information used to characterize consumption capabilities of a consumption account.
FIG. 2 also provides a schematic classification diagram of clustered consumption accounts for ease of understanding by those skilled in the art; the classification diagram may be presented in the form of a radar chart, where the consumption account is exemplified by a consumption account in game a, and the game a has 7 frequent consumption items (frequent consumption points); in practical application, each frequently consumed item corresponds to a paid virtual prop in game A; the clustered consumption accounts can comprise 6 series of consumption accounts, namely a series 1 consumption account to a series 7 consumption account, the frequent consumption items are represented by 1-7 around the radar chart, namely the payment virtual prop 1-7 are represented respectively, and the amounts of the payment virtual props are sequentially increased. The consumption accounts of the series 5 cover other series of consumption accounts, the consumption accounts of the series 5 generate consumption behaviors on the payment virtual props 1 to 7, the consumption amount of each payment virtual prop is larger than that of the other series of consumption accounts, and the consumption account of the series 5 is reflected to be highest in the consumption account in the game A; similarly, the consumption accounts of the series 1, 2, 3 and 4 are mainly concentrated on the payment virtual props 1 to 3 for consumption, and the consumption accounts of the series 1, 2, 3 and 4 have lower consumption capacity compared with the consumption accounts of the series 5 because the amounts of the payment virtual props 1 to 3 are smaller than the payment virtual props 4 to 7.
According to the technical scheme, in the classifying process of the consumption accounts according to the virtual consumption condition, the consumption accounts are clustered according to the consumption amount corresponding to the virtual consumption condition and the frequent consumption items to obtain clustered consumption accounts, user portrait information corresponding to the consumption accounts is accurately generated according to the clustered consumption accounts, and finally, auxiliary effects are provided for prop recommendation, content recommendation and other operation activities.
FIG. 3 also provides a flow chart diagram of a method of classifying consumer accounts for ease of understanding by those skilled in the art; the method comprises the following steps of: the server first determines whether the user consumption record (user payment data set D) includes payment number information, that is, determines whether the user consumption record has the occurrence number information of each consumption item in the user consumption record recorded therein.
If the server determines that the user consumption record does not record the occurrence frequency information of each consumption item in the user consumption record, the server adopts a greedy decomposition algorithm (a natural number optimal decomposition algorithm) to decompose the user payment data set D only by using payment amount data, so as to obtain an intermediate payment point set H= { H 1 ，…，h k And an intermediate decomposition result v= { v for each user based on H 1 ，…，v k }. Then, according to the intermediate decomposition result v= { v 1 ，…,v k Determining a first set of frequent flyer points T Greedy decomposition ＝{T 1 ,…,T K }。
If the server determines that the user consumption record has the occurrence number information of each consumption item in the user consumption record, the server adopts a grouping decomposition algorithm, namely groups each consumption item according to the same payment number, and then decomposes the user payment data set D according to the occurrence number of the consumption item in the user consumption record from small to large to obtain an intermediate payment point set H= { h_1, \cds, h_k } and an intermediate decomposition result v= { v of each consumption account based on H 1 ，…，v k }. Then, according to the intermediate decomposition result v= { v 1 ，…，v k Determining a second set of frequent paypoints T Packet decomposition ＝{T 1 ,…，T K }。
Then, since the frequent pay point set in the user consumption record is determined by adopting both greedy decomposition and grouping decomposition, the server can determine the first frequent pay point set T Greedy decomposition ＝{T 1 ,…,T K Sum of second frequent flyer sets T Packet decomposition ＝{T 1 ,…,T K Merging, and taking the union of the two sets as a final fixed-frequency pay point set T= { T 1 ,…,T K }。
Finally, according to the frequent pay point set T, the decomposition result u= { u of the consumption account on the frequent pay points is finally determined by the re-decomposition 1 ,…,u T }. The server characterizes virtual consumption conditions of the consumption account on the frequent consumption items through decomposition results of the consumption account on the frequent payment points. It should be noted that, the specific limitation of the above steps may be referred to the specific limitation of a method for classifying consumption accounts, which is not described herein.
In one embodiment, as shown in fig. 4, another method for classifying a consumption account is provided, which is described by taking application of the method to a server as an example, and the method for classifying a consumption account includes the following steps: step S410, obtaining a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts. And step S420, sorting the consumption items according to the order of the occurrence times in the user consumption records from large to small to obtain sorted consumption items. Step S430, counting the cumulative percentage of the occurrence times of each item in the sequenced consumption items. Step S440, determining the target consumption item in the ordered consumption items according to the cumulative percentage of the occurrence times; and the cumulative percentage of the occurrence times corresponding to the target consumption item is smaller than or equal to a preset percentage threshold value. And step S450, taking each item in the target consumption items as a frequent consumption item. Step S460, according to the consumption amount corresponding to the frequent consumption item, carrying out natural number optimal decomposition on the actual consumption total to obtain a virtual consumption condition of the consumption account in the frequent consumption item; and the difference between the virtual consumption total sum and the actual consumption total sum of the consumption account determined according to the virtual consumption condition meets a preset difference threshold. And step S470, clustering the consumption accounts according to the virtual consumption condition and the consumption amount corresponding to the frequent consumption items to obtain clustered consumption accounts. Step S480, user portrait information corresponding to the consumption account is generated according to the clustered consumption account. It should be noted that, the specific limitation of the above steps may be referred to the specific limitation of a method for classifying consumption accounts, which is not described herein.
It should be understood that, although the steps in the flowcharts of fig. 2 and 4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least a portion of the steps in fig. 2 and 4 may include a plurality of steps or stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the execution of the steps or stages is not necessarily sequential, but may be performed in turn or alternately with at least a portion of the steps or stages in other steps or other steps.
In one embodiment, as shown in fig. 5, a consumer account sorting apparatus is provided, which may employ a software module or a hardware module, or a combination of both, as part of a computer device, the apparatus specifically comprising: an acquisition module 510, a determination module 520, a decomposition module 530, and a classification module 540, wherein:
an obtaining module 510, configured to obtain user consumption data; wherein, the user consumption data records consumption items corresponding to consumption accounts;
A determining module 520, configured to determine frequent consumption items among the consumption items based on the number of occurrences corresponding to each of the consumption items in the user consumption data; the occurrence times corresponding to the frequent consumption items meet preset conditions;
the decomposing module 530 is configured to decompose an actual consumption result of the consumption account according to the frequent consumption item, so as to obtain a virtual consumption condition of the consumption account on the frequent consumption item;
and the classification module 540 is configured to perform classification processing on the consumption account according to the virtual consumption situation.
In one embodiment, the determining module 520 is specifically configured to determine a target consumption item from the consumption items according to the occurrence number of the consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items is larger than a preset ratio threshold, and the occurrence number of each target consumption item is larger than or equal to the occurrence number of the unselected consumption items; and taking each item in the target consumption items as the frequent consumption item.
In one embodiment, the determining module 520 is specifically configured to sort the consumption items according to the order from the big to the small occurrence number, so as to obtain the sorted consumption items; counting the cumulative percentage of the occurrence times corresponding to each item in the ordered consumption items; determining the target consumption item from the sequenced consumption items according to the cumulative percentage of the occurrence times; and the cumulative percentage of the occurrence times corresponding to the target consumption item is smaller than or equal to a preset percentage threshold value.
In one embodiment, if the user consumption record further includes occurrence information of the consumption item, the determining module 520 is specifically configured to group each item in the consumption item according to the occurrence information of the consumption item, so as to obtain a grouped consumption item; wherein, the appearance times of each item in each group of grouped consumption items are equal; determining a target consumption item in the grouped consumption items; wherein the ratio between the total occurrence number of the target consumption items and the total occurrence number of the grouped consumption items is greater than a preset ratio threshold; and combining each item in each group of target consumption items to obtain a consumption item set serving as the frequent consumption item.
In one embodiment, if the user consumption record does not include the occurrence information of the consumption item, the consumption account classification device further includes: the statistics module is used for carrying out frequency statistics processing on the user consumption records to obtain frequency statistics results; the frequency statistics include the number of occurrences of the consumption item in the user consumption record.
In one embodiment, the decomposition module 530 is specifically configured to perform natural number optimal decomposition on the actual total consumption according to the consumption amount corresponding to the frequent consumption item, so as to obtain a virtual consumption condition of the consumption account in the frequent consumption item; and the difference between the virtual consumption total sum and the actual consumption total sum of the consumption account determined according to the virtual consumption condition meets a preset difference threshold.
In one embodiment, the classification module 540 is configured to cluster the consumption accounts according to the virtual consumption situation and the consumption amount corresponding to the frequent consumption item, to obtain clustered consumption accounts; and generating user portrait information corresponding to the consumption account according to the clustered consumption account.
For a specific definition of a consumer account sorting apparatus, reference may be made to the definition of a consumer account sorting method hereinabove, and no further description is given here. The various modules in a consumer account sorting apparatus described above may be implemented in whole or in part in software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 6. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is for storing user consumption record data. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program when executed by a processor implements a method of consumer account classification.
It will be appreciated by those skilled in the art that the structure shown in FIG. 6 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, storing a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
In one embodiment, a computer program product or computer program is provided that includes computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-described method embodiments.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, or the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (10)
1. A method of classifying a consumer account, the method comprising:
acquiring a user consumption record; the user consumption record comprises at least two consumption items corresponding to a consumption account; each of the consumption items has a corresponding one of the consumption amounts;
determining frequent consumption items in the consumption items based on the occurrence times of the consumption items in the user consumption record; wherein the occurrence frequency of the frequent consumption items meets a preset condition;
according to the consumption amount corresponding to the frequent consumption item, decomposing the actual consumption total of the consumption account to obtain the virtual consumption condition of the consumption account in the frequent consumption item; the virtual consumption situation characterizes whether the consumption account can pay for one time on the frequent consumption item, and the difference between the virtual consumption sum and the actual consumption sum determined according to the virtual consumption situation meets a preset difference threshold;
And classifying the consumption accounts according to the virtual consumption condition.
2. The method of claim 1, wherein the determining frequent consumer items among the consumer items based on the number of occurrences of the consumer item in the user's consumer record comprises:
determining a target consumption item from the consumption items according to the occurrence times of the consumption items; the ratio between the total occurrence number of the target consumption items and the total occurrence number of the consumption items is larger than a preset ratio threshold, and the occurrence number of each target consumption item is larger than or equal to the occurrence number of the unselected consumption items;
and taking each item in the target consumption items as the frequent consumption item.
3. The method of claim 2, wherein determining a target consumption item from the consumption items based on the number of occurrences of the consumption item comprises:
sorting the consumption items according to the sequence from the big appearance times to the small appearance times to obtain sorted consumption items;
counting the cumulative percentage of the occurrence times corresponding to each item in the ordered consumption items;
determining the target consumption item from the sequenced consumption items according to the cumulative percentage of the occurrence times; and the cumulative percentage of the occurrence times corresponding to the target consumption item is smaller than or equal to a preset percentage threshold value.
4. The method of claim 1, wherein if the user consumption record further includes occurrence information of the consumption item, the determining frequent consumption items among the consumption items based on the occurrence corresponding to the consumption item in the user consumption data includes:
grouping each item in the consumption items according to the occurrence number information of the consumption items to obtain grouped consumption items; wherein, the appearance times of each item in each group of grouped consumption items are equal;
determining a target consumption item in the grouped consumption items; wherein the ratio between the total occurrence number of the target consumption items and the total occurrence number of the grouped consumption items is greater than a preset ratio threshold;
and combining each item in each group of target consumption items to obtain a consumption item set serving as the frequent consumption item.
5. The method of claim 4, wherein if the user consumption record does not include information on the number of occurrences of the consumption item, the method further comprises:
performing frequency statistics on the user consumption records to obtain frequency statistics results; the frequency statistics include the number of occurrences of the consumption item in the user consumption record.
6. The method of claim 1, wherein the decomposing the actual total consumption of the consumption account according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption of the consumption account in the frequent consumption item comprises:
and carrying out natural number optimal decomposition on the actual consumption total according to the consumption amount corresponding to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item, so that the difference between the virtual consumption total of the frequent consumption item and the actual consumption total of the consumption account determined according to the virtual consumption condition meets a preset difference threshold.
7. The method of claim 5, wherein classifying the consumption account according to the virtual consumption condition comprises:
clustering the consumption accounts according to the virtual consumption condition and the consumption amount corresponding to the frequent consumption items to obtain clustered consumption accounts;
and generating user portrait information corresponding to the consumption account according to the clustered consumption account.
8. A consumer account sorting apparatus, the apparatus comprising:
The acquisition module is used for acquiring the consumption data of the user; wherein, the user consumption data records consumption items corresponding to consumption accounts;
the determining module is used for determining frequent consumption items in the consumption items based on the occurrence times corresponding to each item in the consumption items in the user consumption data; the occurrence times corresponding to the frequent consumption items meet preset conditions;
the decomposing module is used for decomposing the actual consumption result of the consumption account according to the frequent consumption item to obtain the virtual consumption condition of the consumption account in the frequent consumption item; the virtual consumption situation characterizes whether the consumption account can pay for one time on the frequent consumption item, and the difference between the virtual consumption sum and the actual consumption sum determined according to the virtual consumption situation meets a preset difference threshold;
and the classification module is used for classifying the consumption account according to the virtual consumption condition.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110277529.8A CN113051612B (en) | 2021-03-15 | 2021-03-15 | Consumer account classification method, apparatus, computer device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110277529.8A CN113051612B (en) | 2021-03-15 | 2021-03-15 | Consumer account classification method, apparatus, computer device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113051612A CN113051612A (en) | 2021-06-29 |
| CN113051612B true CN113051612B (en) | 2023-10-27 |
Family
ID=76512463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110277529.8A Active CN113051612B (en) | 2021-03-15 | 2021-03-15 | Consumer account classification method, apparatus, computer device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113051612B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130104574A (en) * | 2012-03-14 | 2013-09-25 | (주)네오위즈게임즈 | Method and server for compensattion according to buying charged-item |
| CN107403311A (en) * | 2017-06-27 | 2017-11-28 | 阿里巴巴集团控股有限公司 | The recognition methods of account purposes and device |
| CN110111171A (en) * | 2019-04-04 | 2019-08-09 | 深圳壹账通智能科技有限公司 | Line upslide Baoding method, apparatus, electronic equipment and storage medium |
| CN110610402A (en) * | 2019-08-30 | 2019-12-24 | 恩亿科(北京)数据科技有限公司 | Commodity pushing method and computer storage medium |
| CN111222686A (en) * | 2019-11-21 | 2020-06-02 | 施甸县保施高速公路投资开发有限公司 | Method for optimizing state of service area of highway |
| CN111402002A (en) * | 2020-03-13 | 2020-07-10 | 成都魔力百聚科技有限公司 | Data analysis processing method based on user behavior information |
| CN112084242A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | Consumption information display method, device, terminal and medium |
-
2021
- 2021-03-15 CN CN202110277529.8A patent/CN113051612B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130104574A (en) * | 2012-03-14 | 2013-09-25 | (주)네오위즈게임즈 | Method and server for compensattion according to buying charged-item |
| CN107403311A (en) * | 2017-06-27 | 2017-11-28 | 阿里巴巴集团控股有限公司 | The recognition methods of account purposes and device |
| CN110111171A (en) * | 2019-04-04 | 2019-08-09 | 深圳壹账通智能科技有限公司 | Line upslide Baoding method, apparatus, electronic equipment and storage medium |
| CN110610402A (en) * | 2019-08-30 | 2019-12-24 | 恩亿科(北京)数据科技有限公司 | Commodity pushing method and computer storage medium |
| CN111222686A (en) * | 2019-11-21 | 2020-06-02 | 施甸县保施高速公路投资开发有限公司 | Method for optimizing state of service area of highway |
| CN111402002A (en) * | 2020-03-13 | 2020-07-10 | 成都魔力百聚科技有限公司 | Data analysis processing method based on user behavior information |
| CN112084242A (en) * | 2020-09-02 | 2020-12-15 | 深圳市铭数信息有限公司 | Consumption information display method, device, terminal and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113051612A (en) | 2021-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200202449A1 (en) | Risk identification model building and risk identification | |
| Wei et al. | Efficient feature selection algorithm based on particle swarm optimization with learning memory | |
| CN104391879B (en) | The method and device of hierarchical clustering | |
| CN111950656A (en) | Image recognition model generation method and device, computer equipment and storage medium | |
| CN112214499B (en) | Graph data processing method and device, computer equipment and storage medium | |
| Elish | Assessment of voting ensemble for estimating software development effort | |
| CN108804577A (en) | A kind of predictor method of information label interest-degree | |
| CN110471945A (en) | Processing method, system, computer equipment and the storage medium of alive data | |
| CN114117235A (en) | E-commerce content pushing method adopting artificial intelligence analysis and E-commerce big data system | |
| Zhao et al. | Rethinking attention mechanism in time series classification | |
| CN115965058A (en) | Neural network training method, entity information classification method, device and storage medium | |
| CN111967521B (en) | Cross-border active user identification method and device | |
| CN113569955A (en) | Model training method, user portrait generation method, device and equipment | |
| CN113051612B (en) | Consumer account classification method, apparatus, computer device and storage medium | |
| CN109558887A (en) | A kind of method and apparatus of predictive behavior | |
| US11709798B2 (en) | Hash suppression | |
| CN116187675A (en) | Task allocation method, device, equipment and storage medium | |
| CN115630514A (en) | Unmanned aerial vehicle cluster cooperative task allocation method and device | |
| CN110942345B (en) | Seed user selection method, device, equipment and storage medium | |
| CN111984842B (en) | Bank customer data processing method and device | |
| CN114881158A (en) | Defect value filling method and device based on random forest and computer equipment | |
| CN116502132A (en) | Account set identification method, device, equipment, medium and computer program product | |
| Zhang et al. | Rom: A robust online multi-task learning approach | |
| CN114676167B (en) | User persistence model training method, user persistence prediction method and device | |
| Sadiq et al. | Intelligent methods to solve null values problem in databases |
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 |