CN109285009B - Bill brushing identification method and bill brushing identification device - Google Patents
Bill brushing identification method and bill brushing identification device Download PDFInfo
- Publication number
- CN109285009B CN109285009B CN201810886770.9A CN201810886770A CN109285009B CN 109285009 B CN109285009 B CN 109285009B CN 201810886770 A CN201810886770 A CN 201810886770A CN 109285009 B CN109285009 B CN 109285009B
- Authority
- CN
- China
- Prior art keywords
- subset
- cluster
- type
- users
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
Landscapes
- Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method for recognizing a brush receipt, which comprises the following steps: determining a second set of second type users suspected to cooperate to brush the order according to order information of the first type users in the first set of the first type users suspected to brush the order; expanding the first type users in the first set according to the order information of the second type users in the second set; clustering the first set and the second set respectively to obtain a first subset and a second subset; determining a first type of user and a second type of user for the collaborative swipes in the first subset and the second subset. According to the embodiment of the disclosure, the set formed by the users can be identified, which is beneficial to improving the identification efficiency, and the complex group cooperation list-brushing scene can be effectively identified.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method and an apparatus for recognizing a swipe form, an electronic device, and a computer-readable storage medium.
Background
At present, a mode of identifying network appointment list brushing is mainly to identify according to order features and driver figures, the judging mode is mainly to judge individual targets, on one hand, the efficiency is low, and on the other hand, the mode is difficult to effectively identify for complex group cooperation list brushing scenes.
Disclosure of Invention
According to a first aspect of an embodiment of the present invention, a method for identifying a brush statement is provided, including:
determining a second set of second type users suspected to cooperate to brush the order according to order information of the first type users in the first set of the first type users suspected to brush the order;
expanding the first type users in the first set according to the order information of the second type users in the second set;
clustering the first set and the second set respectively to obtain a first subset and a second subset;
determining a first type of user and a second type of user for the collaborative swipes in the first subset and the second subset.
Optionally, the method further comprises:
expanding the second type users in the second set ith time according to the order information of the first type users in the first set expanded ith time, wherein i is a positive integer;
expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set expanded for the ith time;
clustering the second type users in the first set of the (i + 1) th expansion and the second set of the (i) th expansion to obtain a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster;
determining whether a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster converge;
if the first subset of the (i + 1) th cluster and the second subset of the ith cluster are converged, determining a first type user and a second type user which are matched and used for refreshing the list in the first subset of the (i + 1) th cluster and the second subset of the ith cluster;
and if the first type user and the second type user of the cooperative billing are determined, taking the first subset of the i + 1-time clusters as the ith expanded first set, increasing i by 1, and expanding the second type user in the second set for the ith time according to the order information of the first type user in the ith expanded first set until the first subset of the i + 1-time clusters or the second subset of the ith cluster converges, or until the first type user and the second type user of the cooperative billing are determined not to be available.
Optionally, the determining whether the first subset of the i +1 th-order cluster and the second subset of the i-th-order cluster converge comprises:
determining whether the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and whether the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster;
and if the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster, determining that the first subset of the (i + 1) th cluster and the second subset of the (i + 1) th cluster converge.
Optionally, the clustering the second type users in the i +1 th-order expanded first set and the i-order expanded second set to obtain a first subset of the i +1 th-order cluster and a second subset of the i-order cluster includes:
performing spatial representation on the first type user in the first set expanded for the (i + 1) th time according to the characteristic information of the first type user, and performing spatial representation on the second type user in the second set expanded for the ith time according to the characteristic information of the second type user;
determining a first distance between every two first-type users in the first set of the (i + 1) th expansion through a clustering algorithm, and determining a second distance between every two second-type users in the second set of the (i + 1) th expansion;
and forming a first subset of the (i + 1) th cluster based on the first type of users with the first distance smaller than the first preset distance, and forming a second subset of the (i) th cluster based on the second type of users with the second distance smaller than the second preset distance.
Optionally, the determining the first type of users and the second type of users who collaboratively scrub in the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster includes:
and verifying whether the users in the first subset of the (i + 1) th clustering and the users in the second subset of the (i) th clustering cooperate to swipe the order or not based on a verification model obtained through machine learning.
According to a second aspect of the embodiments of the present invention, there is provided a bill identification device, including:
the collection determination module is used for determining a second collection of second-type users suspected to cooperate to brush the list according to order information of the first-type users in the first collection of the first-type users suspected to brush the list;
the set expansion module is used for expanding the first type users in the first set according to the order information of the second type users in the second set;
the clustering module is used for clustering the first set and the second set respectively to obtain a first subset and a second subset;
a swipe determination module to determine a first type of user and a second type of user of a collaborative swipe in the first subset and the second subset.
Optionally, the set expansion module is configured to expand the second type user in the second set i-th time according to the order information of the first type user in the first set expanded i-th time, where i is a positive integer; expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set expanded for the ith time;
the clustering module is used for clustering the second type users in the (i + 1) th expanded first set and the (i) th expanded second set to obtain a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster;
the device further comprises:
a convergence determining module for determining whether a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster converge;
the order-brushing determining module determines a first type user and a second type user which are matched for brushing orders in the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster under the condition that the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster are converged;
and if the first type user and the second type user of the cooperative waybill are determined, the first subset of the i + 1-time clusters is used as the ith expanded first set, i is increased by 1, the set expansion module is used for expanding the second type user in the second set for the ith time according to the order information of the first type user in the ith expanded first set until the first subset of the i + 1-time clusters or the second subset of the ith cluster is converged, or until the first type user and the second type user of the cooperative waybill are not determined.
Optionally, the convergence determining module includes:
the identical determining module is used for determining whether the first subset of the (i + 1) th-time cluster is identical to the first subset of the (i-1) th-time cluster and whether the second subset of the (i + 1) th-time cluster is identical to the second subset of the (i-1) th-time cluster;
and if the first subset of the (i + 1) th-time cluster is the same as the first subset of the (i) th-time cluster, and the second subset of the (i) th-time cluster is the same as the second subset of the (i-1) th-time cluster, determining that the first subset of the (i + 1) th-time cluster and the second subset of the (i + 1) th-time cluster converge.
Optionally, the clustering module comprises:
the spatial characterization submodule is used for spatially characterizing the first type users in the first set of the (i + 1) th expansion according to the feature information of the first type users, and spatially characterizing the second type users in the second set of the (i) th expansion according to the feature information of the second type users;
a distance determining submodule for determining a first distance between every two first type users in the first set of the (i + 1) th expansion and a second distance between every two second type users in the second set of the (i + 1) th expansion by a clustering algorithm;
and the user clustering sub-module is used for forming a first subset of the (i + 1) th clustering based on the first type users with the first distance smaller than the first preset distance, and forming a second subset of the (i) th clustering based on the second type users with the second distance smaller than the second preset distance.
Optionally, the brush order determination module includes:
and the verification sub-module is used for verifying whether the users in the first subset of the (i + 1) th-time cluster and the users in the second subset of the (i) th-time cluster cooperate to refresh the list or not based on a verification model obtained through machine learning.
According to a third aspect of the embodiments of the present invention, there is provided an electronic apparatus, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the steps of the method for identifying a brush bill according to any of the above embodiments.
According to a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and the program, when executed by a processor, performs the steps in the method for identifying a brush receipt according to any of the embodiments.
According to the embodiment of the invention, compared with the situation that the identification is carried out on the individual in the related art, the set formed by the users can be identified, the identification efficiency is favorably improved, and the identification can be effectively carried out on the complex group cooperation list brushing scene.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a method of brush statement identification in accordance with an embodiment of the present invention.
FIG. 2 is a schematic flow chart diagram illustrating another method of brush statement identification in accordance with an embodiment of the present invention.
FIG. 3 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention.
FIG. 4 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention.
FIG. 5 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention.
Fig. 6 is a hardware configuration diagram of a server in which the swipe recognition apparatus is located according to an embodiment of the present invention.
Fig. 7 is a schematic block diagram illustrating a swipe recognition apparatus according to an embodiment of the present invention.
Fig. 8 is a schematic block diagram illustrating another apparatus for recognizing a brush receipt according to an embodiment of the present invention.
FIG. 9 is a schematic block diagram illustrating a convergence determination module in accordance with an embodiment of the present invention.
FIG. 10 is a schematic block diagram illustrating a brush order determination module in accordance with an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
FIG. 1 is a schematic flow chart diagram illustrating a method of brush statement identification in accordance with an embodiment of the present invention. The method for recognizing the swipe bill can be applied to at least two kinds of scenes where the users perform transactions. For example, a net car appointment scenario, where one class of users is drivers and another class of users is passengers; such as an online shopping scenario, where one type of user is a merchant and another type of user is a customer. Of course, the applicable scenarios of the method shown in this embodiment are not limited to the above scenarios, and may be specifically set according to needs. The following description is given primarily for illustrative purposes in a network appointment scenario.
As shown in fig. 1, the method for identifying a swipe form may include the following steps:
step S1, determining a second set of users of a second type suspected to cooperate to swipe the order according to the order information of the first type of user in the first set of users of the first type suspected to swipe the order.
In one embodiment, if the first type of user is a driver, then the second type of user is a passenger; if the first type of user is a passenger, then the second type of user is a driver. The following description of embodiments of the invention is mainly given in the case where the first type of user is a driver and the second type of user is a passenger.
In one embodiment, for a driver, the driver suspected of brushing an order can be determined based on the driver's route information for completing the order, order frequency information, order subsidy information, and the like.
For example, taking the route information as an example, if the proportion of the orders completing a certain route in the orders completed by the driver is large, the driver can be determined as the driver suspected to brush the order.
For example, in the case of order frequency information, if the driver has a large number of orders completed in a unit time, the driver can be determined as the driver suspected to have a list.
For example, taking the order subsidy information as an example, if the proportion of the orders for which subsidies are obtained to the total orders among the orders completed by the driver is large, the driver can be determined to be the driver suspected to brush the orders.
It should be noted that the information according to which the first type of user who determines the suspected statement of credit is determined is not limited to the above, and may be set as needed. And when the first type of users suspected to swipe the bill is determined according to the various information, a weight value can be set for each type of information respectively.
In one embodiment, the number of drivers of the determined suspected brush list may be one or more, and the drivers of the determined suspected brush list may form the first set. For each driver in the first set, the passengers suspected of collaborative billing may be determined according to the driver's order information, and the determined passengers suspected of collaborative billing may form a second set. For a suspected scrub list driver, there may be one or more passengers determined to be suspected to be collaborating in scrubbing the list. The following describes an embodiment of the present invention mainly in the case where there is one driver who is suspected of brushing a bill.
In one embodiment, the passengers for the collaborative ticketing are determined based on driver's order information, wherein the driver's order information may include at least one of: image information, path information, order frequency information, order subsidy information, and evaluation information.
For example, taking the route information as an example, if the number of orders completing a certain route in the orders completed by the driver is similar to the number of orders completing a certain route in the orders completed by the passenger, the passenger can be determined to be the passenger who collaboratively swipes the order.
For example, taking the order frequency information as an example, if the number of completed orders in a certain time period unit time in the orders completed by the driver is similar to the number of completed orders in a certain time period unit time in the orders completed by the passenger, the passenger can be determined to be a cooperative passenger for taking a bill.
It should be noted that the information according to which the second type of user determines the collaborative swipe is not limited to the above, and may be set as needed. And when determining the second type of user of the collaborative ticketing according to the multiple information, a weight may be set for each type of information separately.
Step S2, expanding the first type users in the first set according to the order information of the second type users in the second set.
In one embodiment, after determining the second set of suspected collaborative billing passengers, for each suspected collaborative billing passenger in the second set, a driver of the suspected collaborative billing may be further determined according to passenger order information, and for each suspected collaborative billing passenger determined, the first set may be expanded to add drivers of the suspected collaborative billing in the first set.
Wherein the passenger's order information may include at least one of: image information, path information, order frequency information, order subsidy information, and evaluation information.
For example, taking the route information as an example, if the number of orders for completing a certain route in the orders completed by the passenger is similar to the number of orders for completing a certain route in the orders completed by the driver, the driver can be determined to be a suspected collaborative swiped driver.
For example, taking the order frequency information as an example, if the number of orders completed within a certain time period unit time in the orders completed by the passengers is similar to the number of orders completed within a certain time period unit time in the orders completed by the driver, the driver can be determined as the suspected collaborative swipes driver.
Step S3, clustering the first set and the second set respectively to obtain a first subset and a second subset.
Since the drivers in the first set are suspected drivers of brushing the order, i.e., may include both drivers who do not actually brush the order with the passenger and drivers who do not brush the order with the passenger, the second set may include both passengers who do not actually brush the order with the driver and passengers who do not brush the order with the driver. Therefore, if the passenger and the driver of the cooperative scrub are directly determined based on the first set and the second set, it is more likely that the driver and the passenger who do not have the cooperative scrub will be considered, resulting in not only an increase in the amount of data to be processed, but also the driver and the passenger who do not have the cooperative scrub may be mistaken for the cooperative scrub.
In one embodiment, spatial characterization may be performed on drivers in a first set according to characteristic information of the drivers, spatial characterization may be performed on passengers in a second set according to characteristic information of the passengers, then the first set may be clustered to obtain a first subset, and the second set may be clustered to obtain a second subset, where elements in the subset after clustering are closer to elements in the set before clustering, that is, the characteristic information is closer.
The characteristic information is characteristic information related to the cooperative billing, and the closer characteristic information indicates that the characteristics of the driver billing in the first subset are more obvious, and indicates that the characteristics of the driver billing in the first subset are more obvious, that is, the probability mean of the driver cooperative billing in the first subset is larger than the probability mean of the driver cooperative billing in the first set. Similarly, the average probability of the passenger cooperative billing in the second subset is greater relative to the average probability of the passenger cooperative billing in the second subset.
Accordingly, the passenger and the driver of the collaborative brushorder may be subsequently determined based on the first subset and the second subset, and the data volume of the processed data may be reduced and the accuracy of determining the driver and the passenger of the collaborative brushorder may be improved relative to directly determining the passenger and the driver of the collaborative brushorder based on the first set and the second set.
Step S4, determining a first type of user and a second type of user of the collaborative swipe in the first subset and the second subset.
In one embodiment, a verification model may be trained in advance through machine learning, the verification model may embody a relationship when a group of drivers who swipe a list and a group of passengers who swipe the list cooperate to swipe the list, a first type user and a second type user of the cooperation list in the first subset and the second subset may be identified based on the verification model, and the first type user and the second type user of the cooperation list may be output for analysis and viewing by an operator.
Compared with the situation of identifying individuals in the related art, the method and the device can identify the set formed by the users, such as the set of passengers and the set of drivers, which is beneficial to improving the identification efficiency, and can also effectively identify the complex group cooperation billing scene.
FIG. 2 is a schematic flow chart diagram illustrating another method of brush statement identification in accordance with an embodiment of the present invention. As shown in fig. 2, on the basis of the embodiment shown in fig. 1, the method further includes:
step S5, according to the order information of the first type user in the ith expanded first set, the second type user in the second set is expanded ith time, and i is a positive integer;
step S6, expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set for the (i) th expansion;
step S7, clustering the second type users in the first set of the (i + 1) th expansion and the second set of the (i) th expansion to obtain a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster;
step S8, determining whether the first subset of the i +1 th-order cluster and the second subset of the i-th-order cluster converge;
step S9, if the first subset of the (i + 1) th cluster and the second subset of the (i) th cluster converge, determining a first type user and a second type user which cooperate to swipe a bill in the first subset of the (i + 1) th cluster and the second subset of the (i) th cluster;
and if the first type user and the second type user of the cooperative waybill are determined, the first subset of the (i + 1) th-time cluster is used as the first expanded set of the (i) th time, i is increased by 1, and the second type user in the second set is expanded for the (i) th time according to the order information of the first type user in the first expanded set of the (i) th time until the first subset of the (i + 1) th-time cluster or the second subset of the (i) th-time cluster converges, or until the first type user and the second type user of the cooperative waybill are not determined.
In one embodiment, in addition to the first set, the second set may be expanded, for example, after the first set is expanded the ith time, the second type users in the second set may be expanded the ith time according to the order information of the first type users in the first set expanded the ith time, and further the first set may be expanded again, the first type users in the first set may be expanded the i +1 times according to the order information of the second type users in the second set expanded the ith time, and so on, the first set and the second set may be expanded multiple times so that the first set contains as many first type users as possible, and the second set contains as many second type users as possible, so as to identify the efficiency of the first type users and the second type users of the collaborative brush as much as possible through the subsequent steps, thereby improving the recognition efficiency.
In addition, the first set and the second set after each expansion can be clustered, for example, the first set expanded for the (i + 1) th time is clustered to obtain a first subset of the (i + 1) th time cluster, the second set expanded for the (i) th time is clustered to obtain a second subset of the (i) th time cluster, and then the sets are expanded on the basis of the subsets of the clusters, so that users in the expanded sets can be guaranteed, and the users can be more likely to collaboratively refresh the list.
It should be noted that the expansion of the first set and the second set may be stopped in some cases, for example, when the first subset of the i +1 th cluster and the second subset of the i-th cluster converge, or when the first type user and the second type user of the collaborative filtering are determined not to be available, the continuation may be stopped.
If the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster converge, it indicates that the first set and the second set have been expanded to a degree that meets the requirement, for example, the number of users in the set is not increased after the first set and the second set are expanded, and the expansion does not need to be continued, so that the expansion can be stopped. If the first type user and the second type user of the collaborative waybill cannot be determined, it is indicated that a problem occurs in the expansion of the first set and the second set, and if the expansion is continued, the first set and the second set may contain more users who do not collaboratively waybill, which leads to more incapability of determining the first type user and the second type user of the collaborative waybill, and therefore, the expansion may also be stopped.
And if the first type user and the second type user of the cooperative billing can be determined, and the first subset of the (i + 1) th-order cluster or the second subset of the (i) th-order cluster is not converged, the first subset of the (i + 1) th-order cluster can be used as the ith expanded first set, i is increased by 1, and the second type user in the second set is expanded for the ith time according to the order information of the first type user in the ith expanded first set, so that the first set and the second set are continuously expanded.
In addition, when the i is 1, if the first type user and the second type user of the collaborative swipe list are not specified, it is possible to newly select the first type user to form the first set, which indicates that the initially specified first set is incorrect.
FIG. 3 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention. As shown in fig. 3, on the basis of the embodiment shown in fig. 2, the determining whether the first subset of the i +1 th-order cluster and the second subset of the i-th-order cluster converge includes:
step S801, determining whether the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and whether the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster;
step S802, if the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster, determining that the first subset of the (i + 1) th cluster and the second subset of the (i + 1) th cluster converge.
In an embodiment, if the first subset of the i +1 th-order cluster is the same as the first subset of the i-th-order cluster, that is, the first subset determined according to the newly expanded first subset is the same as the first subset determined according to the previously expanded first subset, this indicates that the expansion does not increase the number of users in the first subset, and therefore the first set does not need to be expanded. Correspondingly, if the second subset of the ith cluster is the same as the second subset of the i-1 st cluster, it means that the users in the second subset are not increased through the expansion, and therefore the second set does not need to be expanded.
In addition to determining whether the first subset and the second subset converge according to the embodiment shown in fig. 3, other manners may be selected for determination according to needs.
For example, if the first subset of the (i + 1) th cluster is different from the first subset of the (i) th cluster, a first relative complement of the first subset of the (i + 1) th cluster in the first subset of the (i) th cluster may be determined; if the second subset of the ith cluster is different from the second subset of the i-1 st cluster, a second relative complement of the second subset of the ith cluster in the second subset of the i-1 st cluster may be determined.
The relative complement refers to a set of elements that the B set does not include in the a set, that is, a relative complement of the a set in the B set. For example, a first relative complement refers to a set of drivers that a first subset of the ith-order cluster contained in a first subset of the (i + 1) th-order cluster does not have, and a second relative complement refers to a set of passengers that a second subset of the (i-1) th-order cluster contained in a second subset of the ith-order cluster does not have.
If the first type user and the second type user of the collaborative filtering are identified, it is indicated that the newly determined subset expands a new user relative to the previously determined subset, and the expanded new user is the collaborative filtering, so that the continued expansion of the previously determined subset can make the newly determined subset include more users of the collaborative filtering, that is, when the first type user and the second type user of the collaborative filtering are identified based on the first relative complement set and the second relative complement set, it can be determined that the first subset and the second subset do not converge, so that the continued expansion of the first set and the second set can be performed to increase the users in the first subset and the second subset.
If the first type user and the second type user of the cooperative statement of credit are not identified based on the first relative complement and the second relative complement, that is, even if the first set and the second set are re-expanded, the new expanded user is not the user of the cooperative statement of credit, so that the first subset and the second subset can be determined to be converged, and the expansion of the first set and the second set is stopped.
In addition, whether convergence is performed or not can be determined according to the value of i, if i is larger, for example, larger than a preset value, which indicates that the number of times of expansion of the first set and the second set is larger, it can be determined that the first subset and the second subset converge, so that the first set and the second set continue to be expanded, and resources are wasted.
FIG. 4 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention. As shown in fig. 4, on the basis of the embodiment shown in fig. 2, the clustering the second type users in the i +1 th-order expanded first set and the i-order expanded second set to obtain the first subset of the i +1 th-order cluster and the second subset of the i-order cluster includes:
step S701, performing spatial representation on the first type user in the first set expanded for the (i + 1) th time according to the feature information of the first type user, and performing spatial representation on the second type user in the second set expanded for the ith time according to the feature information of the second type user;
step S702, determining a first distance between every two first-type users in the first set expanded for the (i + 1) th time and determining a second distance between every two second-type users in the second set expanded for the ith time through a clustering algorithm;
step S703 is to form a first subset of the (i + 1) th cluster based on the first type of users whose first distance is smaller than the first preset distance, and to form a second subset of the (i) th cluster based on the second type of users whose second distance is smaller than the second preset distance.
In one embodiment, the feature information may be extracted separately for the driver and the passenger, wherein the extracted feature information may be one kind or a plurality of kinds, preferably, a plurality of kinds. The extracted feature information can be used as a dimension, each feature information can be used as a dimension, and further, the driver and the user can be subjected to space representation through the feature information, the driver and the user are represented in a coordinate form, and values in the coordinates are values of the features.
For example, for the driver and the passenger, the extracted feature information includes at least one of: image information, path information, order frequency information, order subsidy information, and evaluation information. Of course, the feature information is not limited to the above, and may be specifically set and selected as needed.
In one embodiment, for a spatially characterized driver and passenger, the distance between the driver and the distance between the passenger and the passenger, respectively, can be calculated, and further for the driver and the passenger, clustering can be performed by a clustering algorithm, respectively, based on the determined distances.
For example, for the drivers, the distance between every two drivers in the first set may be calculated, and then clustering is performed through unsupervised learning, wherein the adopted clustering algorithm may be a KNN (K nearest neighbor) classification algorithm, or a hierarchical clustering algorithm.
The characteristic information is characteristic information related to the cooperative waybill, the closer characteristic information shows that the characteristics of the driver waybill in the first subset are more obvious, and shows that the characteristics of the driver waybill in the first subset are more obvious, that is, the probability mean value of the driver cooperative waybill in the first subset is larger than the probability mean value of the driver cooperative waybill in the first set. Similarly, the average probability of the passenger cooperative billing in the second subset is greater relative to the average probability of the passenger cooperative billing in the second subset.
FIG. 5 is a schematic flow chart diagram illustrating yet another method of brush statement identification, in accordance with an embodiment of the present invention. As shown in fig. 5, on the basis of the embodiment shown in fig. 2, the determining the first type of users and the second type of users who collaboratively scrub in the first subset of the i +1 th-order cluster and the second subset of the i-th-order cluster includes:
step S901, based on a verification model obtained by machine learning, verifies whether or not the users in the first subset of the i +1 th-order cluster and the users in the second subset of the i-th-order cluster cooperate to swipe a ticket.
In one embodiment, the first type of user and the second type of user that do collaboratively scrub may be determined from historical data as samples to form a set of samples, and the verification model may be derived by machine learning based on the samples in the set of samples.
In one embodiment, the first type user and the second type user of the swipe list may be determined in the extended first set and the extended second set, for example, by way of offline verification or according to a preset rule, and then the determined first type user and the determined second type user are combined to form a sample set, so that the authentication model may be obtained through machine learning based on the samples in the sample set.
Wherein, the first type user and the second type user of the list brushing are determined according to a preset rule, a first distribution of the number of completed orders in unit time (for example, one day) can be calculated for part of the drivers in the first set, a second distribution of the number of completed orders in unit time can be calculated for part of the passengers in the second set, then the similarity of the first distribution and the second distribution is calculated, and if the similarity is higher, the part of the drivers and the part of the passengers are determined to brush the list in a cooperation mode.
It should be noted that the machine learning may be supervised learning, and the adopted machine learning algorithm may be logistic regression, gradient boosting tree, neural network, or the like.
In one embodiment, if the first type of user and the second type of user of the scrub are determined in the expanded first set and the expanded second set as samples to form a sample set, then determining the first type of user and the second type of user of the collaborative scrub based on the verification model may be for the first type of user and the second type of user in the first set and the second set that are not samples.
Corresponding to the embodiment of the method for identifying the brush receipt, the application also provides an embodiment of the device for identifying the brush receipt.
The brushing list recognition device provided by the embodiment of the invention can be applied to a server. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a logical device, the device is formed by reading corresponding computer program instructions in the nonvolatile memory into the memory for operation through the processor of the server where the device is located. In terms of hardware, as shown in fig. 6, the hardware structure diagram of the server where the ticket swiping identification apparatus is located is shown according to the embodiment of the present invention, except for the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 6, the server where the apparatus is located in the embodiment may also include other hardware according to the actual function of the server, which is not described again.
Fig. 7 is a schematic block diagram illustrating a swipe recognition apparatus according to an embodiment of the present invention. The device for recognizing the swipe bill shown in the embodiment can be applied to at least two kinds of scenes of transactions conducted by users. For example, a net car appointment scenario, where one class of users is drivers and another class of users is passengers; such as an online shopping scenario, where one type of user is a merchant and another type of user is a customer. Of course, the applicable scenarios of the apparatus shown in this embodiment are not limited to the above scenarios, and may be specifically set according to needs. The following description is given primarily for illustrative purposes in a network appointment scenario.
As shown in fig. 7, the illustrated ticket recognition apparatus includes:
the collection determination module 1 is configured to determine a second collection of second-type users suspected to cooperate to swipe a bill according to order information of the first-type users in the first collection of first-type users suspected to swipe a bill;
the set expansion module 2 is used for expanding the first type users in the first set according to the order information of the second type users in the second set;
the clustering module 3 is used for respectively clustering the first set and the second set to obtain a first subset and a second subset;
a swipe determination module 4, configured to determine a first type of user and a second type of user of the collaborative swipe in the first subset and the second subset.
Fig. 8 is a schematic block diagram illustrating another apparatus for recognizing a brush receipt according to an embodiment of the present invention. As shown in fig. 8, on the basis of the embodiment shown in fig. 7, the set expanding module 2 is configured to expand the second type users in the second set i-th time according to the order information of the first type users in the first set expanded i-th time, where i is a positive integer; expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set expanded for the ith time;
the clustering module 3 is used for clustering the second type users in the i +1 th expanded first set and the i-th expanded second set to obtain a first subset of the i +1 th cluster and a second subset of the i-th cluster;
the device further comprises:
a convergence determining module 5, configured to determine whether a first subset of the (i + 1) th-order cluster and a second subset of the (i) th-order cluster converge;
the order-brushing determining module 4 determines a first type user and a second type user which are cooperatively brushed in the first subset of the (i + 1) th cluster and the second subset of the ith cluster under the condition that the first subset of the (i + 1) th cluster and the second subset of the ith cluster are converged;
if the first type user and the second type user of the cooperative billing are determined, the first subset of the i + 1-time cluster is used as the ith expanded first set, i is increased by 1, and the set expansion module 2 is used for expanding the second type user in the second set for the ith time according to the order information of the first type user in the ith expanded first set until the first subset of the i + 1-time cluster or the second subset of the ith cluster converges, or until the first type user and the second type user of the cooperative billing cannot be determined.
FIG. 9 is a schematic block diagram illustrating a convergence determination module in accordance with an embodiment of the present invention. As shown in fig. 9, based on the embodiment shown in fig. 7 or fig. 8, the convergence determining module 5 includes:
an identity determination submodule 501, configured to determine whether the first subset of the (i + 1) th-order cluster is the same as the first subset of the (i-1) th-order cluster, and whether the second subset of the (i-1) th-order cluster is the same as the second subset of the (i-1) th-order cluster;
and if the first subset of the (i + 1) th-time cluster is the same as the first subset of the (i) th-time cluster, and the second subset of the (i) th-time cluster is the same as the second subset of the (i-1) th-time cluster, determining that the first subset of the (i + 1) th-time cluster and the second subset of the (i + 1) th-time cluster converge.
On the basis of the embodiment shown in fig. 7 or fig. 8, the clustering module 3 includes:
the spatial characterization submodule is used for spatially characterizing the first type users in the first set of the (i + 1) th expansion according to the feature information of the first type users, and spatially characterizing the second type users in the second set of the (i) th expansion according to the feature information of the second type users;
a distance determining submodule for determining a first distance between every two first type users in the first set of the (i + 1) th expansion and a second distance between every two second type users in the second set of the (i + 1) th expansion by a clustering algorithm;
and the user clustering sub-module is used for forming a first subset of the (i + 1) th clustering based on the first type users with the first distance smaller than the first preset distance, and forming a second subset of the (i) th clustering based on the second type users with the second distance smaller than the second preset distance.
FIG. 10 is a schematic block diagram illustrating a brush order determination module in accordance with an embodiment of the present invention. As shown in fig. 10, based on the embodiment shown in fig. 7 or fig. 8, the brush order determination module 4 includes:
the verification sub-module 401 is configured to verify whether the users in the first subset of the (i + 1) th-order cluster and the users in the second subset of the (i) th-order cluster cooperate to swipe a bill based on a verification model obtained through machine learning.
The implementation process of the functions and actions of each module in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
An embodiment of the present invention further provides an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the steps of the method for identifying a brush bill according to any of the above embodiments.
Embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, performs the steps in the method for identifying a brush receipt according to any of the above embodiments.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (12)
1. A method for identifying a billing, comprising:
determining a second set of second type users suspected to cooperate to brush the order according to order information of the first type users in the first set of the first type users suspected to brush the order;
expanding the first type users in the first set according to the order information of the second type users in the second set;
clustering the first set and the second set respectively to obtain a first subset and a second subset;
determining a first type of user and a second type of user for the collaborative swipes in the first subset and the second subset.
2. The method of claim 1, further comprising:
expanding the second type users in the second set ith time according to the order information of the first type users in the first set expanded ith time, wherein i is a positive integer;
expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set expanded for the ith time;
clustering the second type users in the first set of the (i + 1) th expansion and the second set of the (i) th expansion to obtain a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster;
determining whether a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster converge;
if the first subset of the (i + 1) th cluster and the second subset of the ith cluster are converged, determining a first type user and a second type user which are matched and used for refreshing the list in the first subset of the (i + 1) th cluster and the second subset of the ith cluster;
and if the first type user and the second type user of the cooperative billing are determined, taking the first subset of the i + 1-time clusters as the ith expanded first set, increasing i by 1, and expanding the second type user in the second set for the ith time according to the order information of the first type user in the ith expanded first set until the first subset of the i + 1-time clusters or the second subset of the ith cluster converges, or until the first type user and the second type user of the cooperative billing are determined not to be available.
3. The method of claim 2, wherein determining whether the first subset of the i +1 th-order cluster and the second subset of the i-th-order cluster converge comprises:
determining whether the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and whether the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster;
and if the first subset of the (i + 1) th cluster is the same as the first subset of the (i) th cluster, and the second subset of the (i) th cluster is the same as the second subset of the (i-1) th cluster, determining that the first subset of the (i + 1) th cluster and the second subset of the (i + 1) th cluster converge.
4. The method according to claim 2 or 3, wherein clustering the second type of users in the i +1 th expanded first set and the i +1 th expanded second set to obtain a first subset of the i +1 th cluster and a second subset of the i +1 th cluster comprises:
performing spatial representation on the first type user in the first set expanded for the (i + 1) th time according to the characteristic information of the first type user, and performing spatial representation on the second type user in the second set expanded for the ith time according to the characteristic information of the second type user;
determining a first distance between every two first-type users in the first set of the (i + 1) th expansion through a clustering algorithm, and determining a second distance between every two second-type users in the second set of the (i + 1) th expansion;
and forming a first subset of the (i + 1) th cluster based on the first type of users with the first distance smaller than the first preset distance, and forming a second subset of the (i) th cluster based on the second type of users with the second distance smaller than the second preset distance.
5. The method of claim 2 or 3, wherein determining the first type of users and the second type of users collaboratively swiped in the first subset of the i +1 th cluster and the second subset of the i-th cluster comprises:
and verifying whether the users in the first subset of the (i + 1) th clustering and the users in the second subset of the (i) th clustering cooperate to swipe the order or not based on a verification model obtained through machine learning.
6. A device for recognizing a bill by brush, comprising:
the collection determination module is used for determining a second collection of second-type users suspected to cooperate to brush the list according to order information of the first-type users in the first collection of the first-type users suspected to brush the list;
the set expansion module is used for expanding the first type users in the first set according to the order information of the second type users in the second set;
the clustering module is used for clustering the first set and the second set respectively to obtain a first subset and a second subset;
a swipe determination module to determine a first type of user and a second type of user of a collaborative swipe in the first subset and the second subset.
7. The apparatus according to claim 6, wherein the set expansion module is configured to expand the second type users in the second set i times according to the order information of the first type users in the first set expanded i times, i being a positive integer; expanding the first type user in the first set for the (i + 1) th time according to the order information of the second type user in the second set expanded for the ith time;
the clustering module is used for clustering the second type users in the (i + 1) th expanded first set and the (i) th expanded second set to obtain a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster;
the device further comprises:
a convergence determining module for determining whether a first subset of the (i + 1) th cluster and a second subset of the (i) th cluster converge;
the order-brushing determining module determines a first type user and a second type user which are matched for brushing orders in the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster under the condition that the first subset of the (i + 1) th-order cluster and the second subset of the (i) th-order cluster are converged;
and if the first type user and the second type user of the cooperative waybill are determined, the first subset of the i + 1-time clusters is used as the ith expanded first set, i is increased by 1, the set expansion module is used for expanding the second type user in the second set for the ith time according to the order information of the first type user in the ith expanded first set until the first subset of the i + 1-time clusters or the second subset of the ith cluster is converged, or until the first type user and the second type user of the cooperative waybill are not determined.
8. The apparatus of claim 7, wherein the convergence determination module comprises:
the identical determining module is used for determining whether the first subset of the (i + 1) th-time cluster is identical to the first subset of the (i-1) th-time cluster and whether the second subset of the (i + 1) th-time cluster is identical to the second subset of the (i-1) th-time cluster;
and if the first subset of the (i + 1) th-time cluster is the same as the first subset of the (i) th-time cluster, and the second subset of the (i) th-time cluster is the same as the second subset of the (i-1) th-time cluster, determining that the first subset of the (i + 1) th-time cluster and the second subset of the (i + 1) th-time cluster converge.
9. The apparatus of claim 7 or 8, wherein the clustering module comprises:
the spatial characterization submodule is used for spatially characterizing the first type users in the first set of the (i + 1) th expansion according to the feature information of the first type users, and spatially characterizing the second type users in the second set of the (i) th expansion according to the feature information of the second type users;
a distance determining submodule for determining a first distance between every two first type users in the first set of the (i + 1) th expansion and a second distance between every two second type users in the second set of the (i + 1) th expansion by a clustering algorithm;
and the user clustering sub-module is used for forming a first subset of the (i + 1) th clustering based on the first type users with the first distance smaller than the first preset distance, and forming a second subset of the (i) th clustering based on the second type users with the second distance smaller than the second preset distance.
10. The apparatus of claim 7 or 8, wherein the brush order determination module comprises:
and the verification sub-module is used for verifying whether the users in the first subset of the (i + 1) th-time cluster and the users in the second subset of the (i) th-time cluster cooperate to refresh the list or not based on a verification model obtained through machine learning.
11. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the method of any one of claims 1 to 5.
12. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810886770.9A CN109285009B (en) | 2018-08-06 | 2018-08-06 | Bill brushing identification method and bill brushing identification device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810886770.9A CN109285009B (en) | 2018-08-06 | 2018-08-06 | Bill brushing identification method and bill brushing identification device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109285009A CN109285009A (en) | 2019-01-29 |
| CN109285009B true CN109285009B (en) | 2021-03-02 |
Family
ID=65182948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810886770.9A Active CN109285009B (en) | 2018-08-06 | 2018-08-06 | Bill brushing identification method and bill brushing identification device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109285009B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768258A (en) * | 2019-06-05 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method, device, electronic equipment and medium for identifying abnormal order |
| CN112508630B (en) * | 2021-01-29 | 2021-05-25 | 腾讯科技（深圳）有限公司 | Abnormal conversation group detection method and device, computer equipment and storage medium |
| CN114301711B (en) * | 2021-12-31 | 2024-06-25 | 招商银行股份有限公司 | Anti-riot brushing method, device, equipment, storage medium and computer program product |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016012236A (en) * | 2014-06-30 | 2016-01-21 | ぴあ株式会社 | Merchandise selling device, merchandise selling program, and merchandise selling method |
| CN105392113A (en) * | 2015-12-02 | 2016-03-09 | 百度在线网络技术（北京）有限公司 | Identification method and device for vehicle click farming |
| CN106127505A (en) * | 2016-06-14 | 2016-11-16 | 北京众成汇通信息技术有限公司 | The single recognition methods of a kind of brush and device |
| CN106384273A (en) * | 2016-10-08 | 2017-02-08 | 江苏通付盾科技有限公司 | Malicious order scalping detection system and method |
| CN106557955A (en) * | 2016-11-29 | 2017-04-05 | 流量海科技成都有限公司 | Net about car exception order recognition methodss and system |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN107872767A (en) * | 2017-11-07 | 2018-04-03 | 中国联合网络通信集团有限公司 | A kind of net about car brush single act recognition methods and identifying system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140207694A1 (en) * | 2013-01-21 | 2014-07-24 | International Foundation for Electoral Systems | Electoral integrity assessment method, and system |
| US20160217532A1 (en) * | 2015-01-23 | 2016-07-28 | Sure, Inc. | Securing Claim Data via Block-Chains for a Peer to Peer Platform |
-
2018
- 2018-08-06 CN CN201810886770.9A patent/CN109285009B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2016012236A (en) * | 2014-06-30 | 2016-01-21 | ぴあ株式会社 | Merchandise selling device, merchandise selling program, and merchandise selling method |
| CN105392113A (en) * | 2015-12-02 | 2016-03-09 | 百度在线网络技术（北京）有限公司 | Identification method and device for vehicle click farming |
| CN106127505A (en) * | 2016-06-14 | 2016-11-16 | 北京众成汇通信息技术有限公司 | The single recognition methods of a kind of brush and device |
| CN106384273A (en) * | 2016-10-08 | 2017-02-08 | 江苏通付盾科技有限公司 | Malicious order scalping detection system and method |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN106557955A (en) * | 2016-11-29 | 2017-04-05 | 流量海科技成都有限公司 | Net about car exception order recognition methodss and system |
| CN107872767A (en) * | 2017-11-07 | 2018-04-03 | 中国联合网络通信集团有限公司 | A kind of net about car brush single act recognition methods and identifying system |
Non-Patent Citations (2)
| Title |
|---|
| "基于C2C电子商务市场虚假销量识别的若干技术研究";乐元;《中国优秀硕士学位论文全文数据库 经济与管理科学辑》;20170215;全文 * |
| "基于模板用户信息搜索行为和统计分析的共谋销量欺诈识别";王忠群 等;《现代图书情报技术》;20151130;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109285009A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103171B (en) | Modeling method and device of machine learning model | |
| CN109934293B (en) | Image recognition method, device, medium and confusion perception convolutional neural network | |
| CN110837836B (en) | Semi-supervised semantic segmentation method based on maximized confidence | |
| Wang et al. | Kernel cross-modal factor analysis for information fusion with application to bimodal emotion recognition | |
| KR20180118596A (en) | Semi-automatic labeling of data sets | |
| CN109285009B (en) | Bill brushing identification method and bill brushing identification device | |
| CN109191226B (en) | Risk control method and device | |
| CN109359972B (en) | Core product pushing and core method and system | |
| CN109271958B (en) | Face age identification method and device | |
| CN108960304B (en) | Deep learning detection method for network transaction fraud behaviors | |
| CN110111136B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| CN112329816A (en) | Data classification method and device, electronic equipment and readable storage medium | |
| CN104281831B (en) | A kind of method and apparatus of person's handwriting checking | |
| CN111062486B (en) | Method and device for evaluating feature distribution and confidence of data | |
| CN107491674A (en) | Feature based information carries out the method and device of user's checking | |
| WO2015138272A1 (en) | Two stage risk model building and evaluation | |
| CN116250020A (en) | Detecting an antagonism example using a potential neighborhood graph | |
| CN113449012A (en) | Internet service mining method based on big data prediction and big data prediction system | |
| CN114638234A (en) | Big data mining method and system applied to online business handling | |
| CN112529078A (en) | Service processing method, device and equipment | |
| CN116151965B (en) | Risk feature extraction method and device, electronic equipment and storage medium | |
| CN110276802B (en) | Method, device and equipment for positioning pathological tissue in medical image | |
| CN116740866A (en) | Banknote loading and clearing system and method for self-service machine | |
| WO2020190482A1 (en) | Method and system for classifying an input data set using multiple data representation source modes | |
| CN115907954A (en) | Account identification method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |