CN116976960A - Data processing method and system for two-dimensional code payment - Google Patents
Data processing method and system for two-dimensional code payment Download PDFInfo
- Publication number
- CN116976960A CN116976960A CN202311230010.XA CN202311230010A CN116976960A CN 116976960 A CN116976960 A CN 116976960A CN 202311230010 A CN202311230010 A CN 202311230010A CN 116976960 A CN116976960 A CN 116976960A
- Authority
- CN
- China
- Prior art keywords
- payment
- data
- behavior
- preference
- attention
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 230000006399 behavior Effects 0.000 claims abstract description 304
- 238000012549 training Methods 0.000 claims abstract description 81
- 238000010801 machine learning Methods 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 149
- 230000004927 fusion Effects 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 12
- 230000003993 interaction Effects 0.000 claims description 10
- 238000001212 derivatisation Methods 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000007423 decrease Effects 0.000 claims description 2
- 230000009471 action Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/085—Payment architectures involving remote charge determination or related payment systems
- G06Q20/0855—Payment architectures involving remote charge determination or related payment systems involving a third party
-
- 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
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
- G06Q20/32—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
- G06Q20/327—Short range or proximity payments by means of M-devices
- G06Q20/3276—Short range or proximity payments by means of M-devices using a pictured code, e.g. barcode or QR-code, being read by the M-device
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the application provides a data processing method and a system for two-dimensional code payment, which are used for determining a target training error network layer according to an example payment behavior track data sequence which is monitored and generated in the process of acquiring the two-dimensional code payment and first payment preference information corresponding to each group of example payment behavior track data in the example payment behavior track data sequence, learning knowledge of a candidate machine learning network is carried out by the payment preference information and the target training error network layer according to a training error minimization strategy through the example payment behavior track data sequence, a target payment preference prediction network is generated, and the payment preference prediction network is trained according to the example payment behavior track data sequence containing payment attention behavior data and reference priori payment behavior data and the payment preference information, so that the accuracy of payment preference prediction is improved.
Description
Technical Field
The application relates to the technical field of payment, in particular to a data processing method and system for two-dimensional code payment.
Background
In the related art, through analyzing the payment preference of the user, the related service providers can be helped to better know the user demands, and various online services which better meet the user demands can be provided. For example, a user may have different payment preferences, such as willingness-to-pay preferences for different items, in the context of online shopping, offline physical store shopping, dining entertainment, etc. How to combine the payment behavior track data of the user in the two-dimensional code payment process so as to improve the accuracy of payment preference prediction is a technical problem to be solved in the technical field.
Disclosure of Invention
In view of the above, the present application aims to provide a data processing method and system for two-dimensional code payment.
Based on a first aspect of the present application, there is provided a data processing method for two-dimensional code payment, applied to a self-service payment service system, the method comprising:
acquiring an example payment behavior track data sequence generated by monitoring in a two-dimensional code payment process, and first payment preference information corresponding to each group of example payment behavior track data in the example payment behavior track data sequence, wherein each group of example payment behavior track data in the example payment behavior track data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the first payment preference information comprises first preference tag field data and first preference positioning data of each payment preference object in the payment attention behavior data;
determining a target training error network layer, wherein the target training error network layer comprises a preference label field training error network layer and a preference positioning training error network layer;
according to a training error minimization strategy, based on the sample payment behavior track data sequence, the payment preference information and the target training error network layer conduct knowledge learning on a candidate machine learning network to generate a target payment preference prediction network, wherein the target payment preference prediction network is used for determining preference positioning data and preference tag field data in candidate payment attention behavior data, the candidate machine learning network is used for extracting a first payment attention behavior vector of the payment attention behavior data and a second payment attention behavior vector of the reference priori payment behavior data, and generating second payment preference information of the payment attention behavior data based on the first payment attention behavior vector and the second payment attention behavior vector, and the second preference tag field data and the second preference positioning data of each payment preference object in the payment attention behavior data determined by the candidate machine learning network are included in the second payment preference information.
In a possible implementation manner of the first aspect, the step of generating the target payment preference prediction network based on the example payment behavior trace data sequence according to a training error minimization policy, wherein the payment preference information and the target training error network layer perform knowledge learning on candidate machine learning networks includes:
respectively loading the payment attention behavior data and the reference priori payment behavior data into the candidate machine learning network, and acquiring second payment preference information generated by the candidate machine learning network;
loading the first bias label field data and the second bias label field data into the bias label field training error network layer to generate a first training error value, loading the first bias positioning data and the second bias positioning data into the bias positioning training error network layer to generate a second training error value, and then storing the first training error value and the second training error value;
updating network weight information of the candidate machine learning network based on the first training error value and the second training error value according to a training error minimization strategy;
and acquiring all the stored first training error values and the second training error values, determining that the updated candidate machine learning network is the target payment preference prediction network when the first training error values and the second training error values meet convergence requirements, otherwise, returning to execute the step of loading the payment attention behavior data and the reference priori payment behavior data into the candidate machine learning network respectively, and acquiring second payment preference information generated by the candidate machine learning network, wherein the convergence requirements comprise that the sum of the continuous N first training error values and the second training error values does not continuously decline.
In a possible implementation manner of the first aspect, the step of loading the payment attention behavior data and the reference a priori payment behavior data into the candidate machine learning network, and obtaining second payment preference information generated by the candidate machine learning network includes:
loading the payment attention behavior data and the reference priori payment behavior data into an encoder of the candidate machine learning network, wherein the encoder is used for extracting the payment attention behavior vectors in the payment attention behavior data and the reference priori payment behavior data to obtain a first payment attention behavior vector and a second payment attention behavior vector;
the second payment preference information generated by the candidate machine learning network based on the first payment attention behavior vector and the second payment attention behavior vector is acquired.
In a possible implementation manner of the first aspect, the candidate machine learning network further includes a fusion unit and a target tracking unit, where the fusion unit is configured to obtain a first target behavior vector based on the first payment attention behavior vector and the second payment attention behavior vector, and load the first target behavior vector into the target tracking unit; the target tracking unit is configured to generate the second payment preference information based on the first target behavior vector.
In a possible implementation manner of the first aspect, the fusion unit includes a first fusion unit, where the first fusion unit is configured to interact the first payment attention behavior vector and the second payment attention behavior vector to generate an interaction behavior vector, a feature attribute value of any one feature vector in the interaction behavior vector matches a feature attribute contrast value of a first feature vector and a second feature vector corresponding to the any one feature vector, where the first feature vector is a feature vector corresponding to the any one feature vector in the first payment attention behavior vector, and the second feature vector is a feature vector corresponding to the any one feature vector in the second payment attention behavior vector;
converging the interaction behavior vector and the first payment attention behavior vector to generate a second target behavior vector;
and encoding the second target behavior vector through a target encoding unit to generate the first target behavior vector.
In a possible implementation manner of the first aspect, the fusing unit includes a second fusing unit, where the second fusing unit is configured to encode the first payment attention behavior vector and the second payment attention behavior vector according to a target encoding unit, and generate the first target behavior vector based on the encoded first payment attention behavior vector and the second payment attention behavior vector, where a feature attribute value of any one feature vector in the first target behavior vector matches a feature attribute fusion value of a first feature vector and a second feature vector corresponding to the any one feature vector.
In a possible implementation manner of the first aspect, the step of determining that the updated candidate machine learning network is the target payment preference prediction network includes:
acquiring a test case payment behavior trace data sequence and third payment preference information corresponding to each set of case payment behavior trace data in the test case payment behavior trace data sequence, wherein each set of case payment behavior trace data in the test case payment behavior trace data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the third payment preference information comprises third preference tag field data and third preference positioning data of each payment preference object in the payment attention behavior data;
determining a mean accuracy of each updated candidate machine learning network of a plurality of updated candidate machine learning networks based on the test case payment behavior trace data sequence and the third payment preference information when the number of updated candidate machine learning networks is a plurality;
and determining the updated candidate machine learning network with the maximum mean value accuracy as the target payment preference prediction network.
In a possible implementation manner of the first aspect, the step of acquiring the generated sample payment behavior trace data sequence during the two-dimensional code payment process includes:
acquiring first payment attention behavior data and first reference priori payment behavior data corresponding to the first payment attention behavior data;
and carrying out feature derivatization on the first payment attention behavior data and the first reference priori payment behavior data according to the same feature derivatization rule, taking the first payment attention behavior data derivatized by the feature as the payment attention behavior data, and taking the first reference priori payment behavior data derivatized by the feature as reference priori payment attention behavior data.
In a possible implementation manner of the first aspect, the preference tag field data includes a preference tag field ID of the preference, and the preference positioning data includes preference positioning data of a preference node corresponding to the preference.
The method further comprises the steps of:
determining candidate payment concern behavior data and reference priori payment behavior data corresponding to the candidate payment concern behavior data;
loading the candidate payment attention behavior data and the reference priori payment behavior data into a target payment preference prediction network, and acquiring preference positioning data and preference tag field data generated by the target payment preference prediction network, wherein the target payment preference prediction network is used for extracting a third payment attention behavior vector of the candidate payment attention behavior data and a fourth payment attention behavior vector of the reference priori payment behavior data, and generating the preference positioning data and the preference tag field data based on the three payment attention behavior vectors and the fourth payment attention behavior vector;
determining a set number of target preferences of the candidate payment attention behavior data, which deviate from the minimum cluster characteristic cluster center of the candidate payment attention behavior data, based on the preference positioning data;
and determining a predicted probability value of each target preference in the set number of target preferences, and determining a preference tag field of the target preference with the largest predicted probability value as a preference tag field of the candidate payment attention behavior data.
Based on a second aspect of the present application, there is provided a self-service payment service system comprising a processor and a readable storage medium storing a program which when executed by the processor implements the data processing method of two-dimensional code payment described above.
Based on a third aspect of the present application, there is provided a computer-readable storage medium having stored therein computer-executable instructions for implementing the aforementioned data processing method for two-dimensional code payment when it is monitored that the computer-executable instructions are executed.
Based on any one of the above aspects, in the present application, according to an example payment behavior trace data sequence generated by monitoring in a two-dimensional code payment process, and first payment preference information corresponding to each set of example payment behavior trace data in the example payment behavior trace data sequence, each set of example payment behavior trace data in the example payment behavior trace data sequence includes payment attention behavior data, and reference priori payment behavior data corresponding to the payment attention behavior data, the first payment preference information includes first preference tag field data and first preference positioning data of each payment preference object in the payment attention behavior data; determining a target training error network layer, wherein the target training error network layer comprises a preference label field training error network layer and a preference positioning training error network layer; according to a training error minimization strategy, knowledge learning is conducted on candidate machine learning networks through an example payment behavior track data sequence, a target payment preference prediction network is generated through payment preference information and a target training error network layer, the target payment preference prediction network is used for determining preference positioning data and preference tag field data in candidate payment behavior data, the candidate machine learning network is used for extracting a first payment behavior vector of payment behavior data and a second payment behavior vector of reference priori payment behavior data, second payment preference information of the payment behavior data is generated based on the first payment behavior vector and the second payment behavior vector, the second payment preference information comprises second preference tag field data and second preference positioning data of each payment preference object in the payment behavior data determined by the candidate machine learning network, and the payment preference prediction network is trained according to the example payment behavior track data sequence containing the payment behavior data and the reference priori payment behavior data and the payment preference information, so that accuracy of payment preference prediction is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a data processing method for two-dimensional code payment according to an embodiment of the present application;
fig. 2 is a schematic component structure diagram of a self-service payment service system for implementing the data processing method for two-dimensional code payment according to the embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art in light of the embodiments of the present application without undue burden, are intended to be within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Fig. 1 is a flow chart illustrating a two-dimensional code payment data processing method according to an embodiment of the present application, and it should be understood that in other embodiments, the order of part of the steps in the two-dimensional code payment data processing method according to the present embodiment may be interchanged according to actual needs, or part of the steps may be omitted or deleted. The detailed steps of the data processing method for two-dimensional code payment are described as follows.
Step S102, an example payment behavior track data sequence which is generated in a monitoring manner in a two-dimensional code payment process and first payment preference information corresponding to each group of example payment behavior track data in the example payment behavior track data sequence are obtained, each group of example payment behavior track data in the example payment behavior track data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the first payment preference information comprises first preference tag field data and first preference positioning data of each payment preference object in the payment attention behavior data;
for example, an example payment behavior trace data sequence may be processed in accordance with the following embodiments:
step S202, acquiring first payment attention behavior data and first reference priori payment behavior data corresponding to the first payment attention behavior data;
step S204, feature derivatization is carried out on the first payment attention behavior data and the first reference priori payment behavior data according to the same feature derivatization rule, the first payment attention behavior data subjected to feature derivatization is used as reference payment attention behavior data, and the first reference priori payment behavior data subjected to feature derivatization is used as reference priori payment attention behavior data.
Step S104, determining a target training error network layer, wherein the target training error network layer comprises a preference label field training error network layer and a preference positioning training error network layer;
step S106, according to the training error minimization strategy, knowledge learning is conducted on the candidate machine learning network through the sample payment behavior track data sequence, the payment preference information and the target training error network layer, the target payment preference prediction network is generated, the target payment preference prediction network is used for determining preference positioning data and preference tag field data in the candidate payment attention behavior data, the candidate machine learning network is used for extracting a first payment attention behavior vector of the payment attention behavior data and a second payment attention behavior vector of the reference priori payment behavior data, second payment preference information of the payment attention behavior data is generated based on the first payment attention behavior vector and the second payment attention behavior vector, and the second preference tag field data and the second preference positioning data of each payment preference object in the payment preference behavior data determined by the candidate machine learning network are included in the second payment preference information.
Knowledge learning of the target payment preference prediction network in step S106 may include the steps of:
step S1062, loading the payment attention behavior data and the reference priori payment behavior data into the candidate machine learning network, respectively, and obtaining second payment preference information generated by the candidate machine learning network, where the second payment preference information includes second preference tag field data and second preference positioning data of each payment preference object in the payment attention behavior data determined by the candidate machine learning network;
step S1064, loading the first bias label field data and the second bias label field data into a bias label field training error network layer to generate a first training error value, loading the first bias positioning data and the second bias positioning data into a bias positioning training error network layer to generate a second training error value, and storing the first training error value and the second training error value;
step S1066, updating the network weight information of the candidate machine learning network according to the training error minimization strategy by the first training error value and the second training error value;
step S1068, obtaining all the saved first training error values and second training error values, determining that the updated candidate machine learning network is the target payment preference prediction network when the first training error values and the second training error values meet the convergence requirement, otherwise, jumping to step S1062.
The convergence requirement may be that the first and second training error values do not continue to drop.
Step S1062 may include the steps of:
step S302, payment attention behavior data and reference priori payment behavior data are loaded into encoders of candidate machine learning networks, wherein the encoders are used for extracting payment attention behavior vectors in the payment attention behavior data and the reference priori payment behavior data, and obtaining a first payment attention behavior vector and a second payment attention behavior vector;
step S304, obtaining second payment preference information generated by the candidate machine learning network based on the first payment attention behavior vector and the second payment attention behavior vector.
The candidate machine learning network may further include a fusion unit and a target tracking unit, where the fusion unit is configured to obtain a first target behavior vector based on the first payment attention behavior vector and the second payment attention behavior vector, and load the first target behavior vector into the target tracking unit; the target tracking unit is used for outputting second payment preference information based on the first target behavior vector.
For example, the fusion unit comprises a first fusion unit. The first fusion unit is used for carrying out interaction on the first payment attention action vector and the second payment attention action vector to generate an interaction action vector, the characteristic attribute value of any one characteristic vector in the interaction action vector is matched with the characteristic attribute contrast value of the first characteristic vector and the second characteristic vector corresponding to any one characteristic vector, the first characteristic vector is the characteristic vector corresponding to any one characteristic vector in the first payment attention action vector, and the second characteristic vector is the characteristic vector corresponding to any one characteristic vector in the second payment attention action vector; converging the interaction behavior vector and the first payment attention behavior vector to generate a second target behavior vector; and encoding the second target behavior vector by the target encoding unit to generate a first target behavior vector.
For another example, the fusion unit includes a second fusion unit, where the second fusion unit is configured to encode the first payment attention behavior vector and the second payment attention behavior vector according to the target encoding unit, and generate the first target behavior vector based on the encoded first payment attention behavior vector and the second payment attention behavior vector, where a feature attribute value of any one feature vector in the first target behavior vector matches a feature attribute fusion value of a first feature vector and a second feature vector corresponding to the any one feature vector.
Step S402, a test case payment behavior trace data sequence and third payment preference information corresponding to each group of case payment behavior trace data in the test case payment behavior trace data sequence are obtained, each group of case payment behavior trace data in the test case payment behavior trace data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the third payment preference information comprises third preference tag field data and third preference positioning data of each payment preference object in the payment attention behavior data;
step S404, when the number of the updated candidate machine learning networks is a plurality, determining the average accuracy of each updated candidate machine learning network in the plurality of updated candidate machine learning networks by testing the example payment behavior trace data sequence and the third payment preference information;
step S406, determining the updated candidate machine learning network with the highest mean accuracy as the target payment preference prediction network.
Based on the above steps, by acquiring an example payment behavior trace data sequence generated by monitoring in a two-dimensional code payment process and first payment preference information corresponding to each group of example payment behavior trace data in the example payment behavior trace data sequence, each group of example payment behavior trace data in the example payment behavior trace data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the first payment preference information comprises first preference tag field data and first preference positioning data of each payment preference object in the payment attention behavior data; determining a target training error network layer, wherein the target training error network layer comprises a preference label field training error network layer and a preference positioning training error network layer; according to the training error minimization strategy, knowledge learning is carried out on the candidate machine learning network through the sample payment behavior track data sequence, the payment preference information and the target training error network layer, a target payment preference prediction network is generated, and the target payment preference prediction network is used for determining preference positioning data and preference tag field data in the candidate payment attention behavior data, so that accuracy of payment preference prediction is improved.
Further embodiments are described below, which may include the steps of:
step S502, determining candidate payment attention behavior data and reference priori payment behavior data corresponding to the candidate payment attention behavior data;
step S504, loading the candidate payment attention behavior data and the reference priori payment behavior data into a target payment preference prediction network, obtaining preference positioning data and preference tag field data generated by the target payment preference prediction network, wherein the target payment preference prediction network is used for extracting a third payment attention behavior vector of the candidate payment attention behavior data and a fourth payment attention behavior vector of the reference priori payment behavior data, and generating preference positioning data and preference tag field data based on the three payment attention behavior vectors and the fourth payment attention behavior vector;
step S506, determining a set number of target preferences closest to cluster feature cluster centers of the candidate payment attention behavior data in the candidate payment attention behavior data based on the preference positioning data;
in step S508, a predicted probability value of each target preference in the set number of target preferences is determined, and a preference tag field of the target preference having the largest predicted probability value is determined as a preference tag field of the candidate payment focus behavior data.
Further, fig. 2 shows a schematic hardware structure of an apparatus for implementing the method provided by the embodiment of the present application. As shown in fig. 2, the self-service payment service system 100 may include one or more processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA), a memory 104 for storing data, and a transmission 106 for communication functions, and a controller 108. It will be appreciated by those of ordinary skill in the art that the configuration shown in fig. 2 is merely illustrative and is not intended to limit the configuration of the self-service payment service system 100 described above. For example, the self-service payment service system 100 may also include more or fewer components than shown in FIG. 2, or have a different configuration than shown in FIG. 2.
The memory 104 may be used to store software programs and modules of application software, such as program instructions corresponding to the above-described method embodiments in the embodiments of the present application, and the processor 102 executes the software programs and modules stored in the memory 104, thereby executing various functional applications and data processing, that is, implementing a two-dimensional code payment data processing method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located with respect to the processor 102, which may be connected to the self-service payment service system 100 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the self-service payment service system 100. In one example, the transmission device 106 includes a network adapter that can connect to other network equipment through a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency module for communicating wirelessly with the internet.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The embodiments of the present application are described in a progressive manner, and identical and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described as a difference from other embodiments. In particular, for the different embodiments above, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program for instructing relevant hardware, where the program may be stored in a computer readable storage medium, and the storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Claims (10)
1. The data processing method for two-dimensional code payment is characterized by comprising the following steps:
acquiring an example payment behavior track data sequence generated by monitoring in a two-dimensional code payment process, and first payment preference information corresponding to each group of example payment behavior track data in the example payment behavior track data sequence, wherein each group of example payment behavior track data in the example payment behavior track data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the first payment preference information comprises first preference tag field data and first preference positioning data of each payment preference object in the payment attention behavior data;
determining a target training error network layer, wherein the target training error network layer comprises a preference label field training error network layer and a preference positioning training error network layer;
according to a training error minimization strategy, based on the sample payment behavior track data sequence, the payment preference information and the target training error network layer conduct knowledge learning on a candidate machine learning network to generate a target payment preference prediction network, wherein the target payment preference prediction network is used for determining preference positioning data and preference tag field data in candidate payment attention behavior data, the candidate machine learning network is used for extracting a first payment attention behavior vector of the payment attention behavior data and a second payment attention behavior vector of the reference priori payment behavior data, and generating second payment preference information of the payment attention behavior data based on the first payment attention behavior vector and the second payment attention behavior vector, and the second preference tag field data and the second preference positioning data of each payment preference object in the payment attention behavior data determined by the candidate machine learning network are included in the second payment preference information.
2. The two-dimensional code payment data processing method according to claim 1, wherein the step of generating a target payment preference prediction network based on the example payment behavior trace data sequence according to a training error minimization policy, wherein the payment preference information and the target training error network layer perform knowledge learning on candidate machine learning networks comprises:
respectively loading the payment attention behavior data and the reference priori payment behavior data into the candidate machine learning network, and acquiring second payment preference information generated by the candidate machine learning network;
loading the first bias label field data and the second bias label field data into the bias label field training error network layer to generate a first training error value, loading the first bias positioning data and the second bias positioning data into the bias positioning training error network layer to generate a second training error value, and then storing the first training error value and the second training error value;
updating network weight information of the candidate machine learning network based on the first training error value and the second training error value according to a training error minimization strategy;
and acquiring all the stored first training error values and the second training error values, determining that the updated candidate machine learning network is the target payment preference prediction network when the first training error values and the second training error values meet convergence requirements, otherwise, returning to execute the step of loading the payment attention behavior data and the reference priori payment behavior data into the candidate machine learning network respectively, and acquiring second payment preference information generated by the candidate machine learning network, wherein the convergence requirements comprise that the sum of the continuous N first training error values and the second training error values does not continuously decline.
3. The method for processing two-dimensional code payment data according to claim 2, wherein the steps of loading the payment attention behavior data and the reference prior payment behavior data into the candidate machine learning network, and acquiring second payment preference information generated by the candidate machine learning network, respectively, include:
loading the payment attention behavior data and the reference priori payment behavior data into an encoder of the candidate machine learning network, wherein the encoder is used for extracting the payment attention behavior vectors in the payment attention behavior data and the reference priori payment behavior data to obtain a first payment attention behavior vector and a second payment attention behavior vector;
the second payment preference information generated by the candidate machine learning network based on the first payment attention behavior vector and the second payment attention behavior vector is acquired.
4. The two-dimensional code payment data processing method according to claim 3, wherein the candidate machine learning network further comprises a fusion unit and a target tracking unit, wherein the fusion unit is used for obtaining a first target behavior vector based on the first payment attention behavior vector and the second payment attention behavior vector, and loading the first target behavior vector into the target tracking unit; the target tracking unit is configured to generate the second payment preference information based on the first target behavior vector.
5. The method for processing data of two-dimensional code payment according to claim 4, wherein the fusion unit comprises a first fusion unit, the first fusion unit is used for interacting the first payment attention behavior vector and the second payment attention behavior vector to generate an interaction behavior vector, a characteristic attribute value of any one of the interaction behavior vectors is matched with a characteristic attribute contrast value of a first characteristic vector and a second characteristic vector corresponding to the any one of the characteristic vectors, the first characteristic vector is a characteristic vector corresponding to the any one of the characteristic vectors in the first payment attention behavior vector, and the second characteristic vector is a characteristic vector corresponding to the any one of the characteristic vectors in the second payment attention behavior vector;
converging the interaction behavior vector and the first payment attention behavior vector to generate a second target behavior vector;
and encoding the second target behavior vector through a target encoding unit to generate the first target behavior vector.
6. The two-dimensional code payment data processing method according to claim 4, wherein the fusion unit comprises a second fusion unit, the second fusion unit is used for encoding the first payment attention behavior vector and the second payment attention behavior vector according to a target encoding unit respectively, and generating the first target behavior vector based on the encoded first payment attention behavior vector and the second payment attention behavior vector, and a characteristic attribute value of any one of the first target behavior vectors is matched with a characteristic attribute fusion value of a first characteristic vector and a second characteristic vector corresponding to the any one of the first characteristic vectors.
7. The two-dimensional code payment data processing method according to claim 2, wherein the step of determining the updated candidate machine learning network as the target payment preference prediction network comprises:
acquiring a test case payment behavior trace data sequence and third payment preference information corresponding to each set of case payment behavior trace data in the test case payment behavior trace data sequence, wherein each set of case payment behavior trace data in the test case payment behavior trace data sequence comprises payment attention behavior data and reference priori payment behavior data corresponding to the payment attention behavior data, and the third payment preference information comprises third preference tag field data and third preference positioning data of each payment preference object in the payment attention behavior data;
determining a mean accuracy of each updated candidate machine learning network of a plurality of updated candidate machine learning networks based on the test case payment behavior trace data sequence and the third payment preference information when the number of updated candidate machine learning networks is a plurality;
and determining the updated candidate machine learning network with the maximum mean value accuracy as the target payment preference prediction network.
8. The method for processing two-dimensional code payment data according to claim 1, wherein the step of acquiring the sample payment behavior trace data sequence generated by monitoring in the two-dimensional code payment process comprises the steps of:
acquiring first payment attention behavior data and first reference priori payment behavior data corresponding to the first payment attention behavior data;
and carrying out feature derivatization on the first payment attention behavior data and the first reference priori payment behavior data according to the same feature derivatization rule, taking the first payment attention behavior data derivatized by the feature as the payment attention behavior data, and taking the first reference priori payment behavior data derivatized by the feature as reference priori payment attention behavior data.
9. The data processing method of two-dimensional code payment according to claim 1, wherein the preference tag field data includes a preference tag field ID of the preference, and the preference positioning data includes preference positioning data of a preference node corresponding to the preference;
the method further comprises the steps of:
determining candidate payment concern behavior data and reference priori payment behavior data corresponding to the candidate payment concern behavior data;
loading the candidate payment attention behavior data and the reference priori payment behavior data into a target payment preference prediction network, and acquiring preference positioning data and preference tag field data generated by the target payment preference prediction network, wherein the target payment preference prediction network is used for extracting a third payment attention behavior vector of the candidate payment attention behavior data and a fourth payment attention behavior vector of the reference priori payment behavior data, and generating the preference positioning data and the preference tag field data based on the three payment attention behavior vectors and the fourth payment attention behavior vector;
determining a set number of target preferences of the candidate payment attention behavior data, which deviate from the minimum cluster characteristic cluster center of the candidate payment attention behavior data, based on the preference positioning data;
and determining a predicted probability value of each target preference in the set number of target preferences, and determining a preference tag field of the target preference with the largest predicted probability value as a preference tag field of the candidate payment attention behavior data.
10. A self-service payment service system, characterized in that the self-service payment service system comprises a processor and a readable storage medium, the readable storage medium storing a program which, when executed by the processor, implements the data processing method of two-dimensional code payment according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230010.XA CN116976960B (en) | 2023-09-22 | 2023-09-22 | Data processing method and system for two-dimensional code payment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311230010.XA CN116976960B (en) | 2023-09-22 | 2023-09-22 | Data processing method and system for two-dimensional code payment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116976960A true CN116976960A (en) | 2023-10-31 |
| CN116976960B CN116976960B (en) | 2023-12-05 |
Family
ID=88473374
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311230010.XA Active CN116976960B (en) | 2023-09-22 | 2023-09-22 | Data processing method and system for two-dimensional code payment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116976960B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734417A (en) * | 2021-01-14 | 2021-04-30 | 广州乐摇摇信息科技有限公司 | Two-dimensional code payment method and device for self-service equipment |
| CN112801670A (en) * | 2021-04-07 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device for payment operation |
| CN113191766A (en) * | 2021-05-08 | 2021-07-30 | 上海亿为科技有限公司 | Method, device and equipment for verifying payment behavior safety based on cloud computing |
| CN113516480A (en) * | 2021-08-19 | 2021-10-19 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
| CN115271719A (en) * | 2021-12-08 | 2022-11-01 | 黄义宝 | Attack protection method based on big data and storage medium |
| CN116485391A (en) * | 2023-04-20 | 2023-07-25 | 支付宝（中国）网络技术有限公司 | Payment recommendation processing method and device |
-
2023
- 2023-09-22 CN CN202311230010.XA patent/CN116976960B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112734417A (en) * | 2021-01-14 | 2021-04-30 | 广州乐摇摇信息科技有限公司 | Two-dimensional code payment method and device for self-service equipment |
| CN112801670A (en) * | 2021-04-07 | 2021-05-14 | 支付宝(杭州)信息技术有限公司 | Risk assessment method and device for payment operation |
| CN113191766A (en) * | 2021-05-08 | 2021-07-30 | 上海亿为科技有限公司 | Method, device and equipment for verifying payment behavior safety based on cloud computing |
| CN113516480A (en) * | 2021-08-19 | 2021-10-19 | 支付宝(杭州)信息技术有限公司 | Payment risk identification method, device and equipment |
| CN115271719A (en) * | 2021-12-08 | 2022-11-01 | 黄义宝 | Attack protection method based on big data and storage medium |
| CN116485391A (en) * | 2023-04-20 | 2023-07-25 | 支付宝（中国）网络技术有限公司 | Payment recommendation processing method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116976960B (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288049B (en) | Method and apparatus for generating image recognition model | |
| CN115374186B (en) | Data processing method based on big data and AI system | |
| CN110851139B (en) | Method and device for checking codes and electronic equipment | |
| CN111198813A (en) | Interface testing method and device | |
| CN107807841B (en) | Server simulation method, device, equipment and readable storage medium | |
| CN111177433B (en) | Method and apparatus for parallel processing of information | |
| CN112200173B (en) | Multi-network model training method, image labeling method and face image recognition method | |
| CN114785685A (en) | Software differential upgrading method and device, electronic equipment and readable storage medium | |
| CN113592593B (en) | Training and application method, device, equipment and storage medium of sequence recommendation model | |
| CN116976960B (en) | Data processing method and system for two-dimensional code payment | |
| CN110929195B (en) | Data caching strategy determining method and device and electronic equipment | |
| CN113468446B (en) | Method, system and equipment for supporting identification of third party two-dimensional code data | |
| CN113271606B (en) | Service scheduling method for ensuring stability of cloud native mobile network and electronic equipment | |
| CN109712011B (en) | Community discovery method and device | |
| CN112258166A (en) | Transaction request processing method and device | |
| CN112055076A (en) | Multifunctional intelligent monitoring method and device based on Internet and server | |
| CN116501365B (en) | Resource calling method, device and equipment based on algorithm platform | |
| CN115375412B (en) | Intelligent commodity recommendation processing method and system based on image recognition | |
| CN116956030B (en) | Household business processing method and system based on artificial intelligence | |
| CN111800481B (en) | Internet-based network interaction method and device and server | |
| CN111435938B (en) | Data request processing method, device and equipment | |
| KR102167367B1 (en) | Purchasing agent server and purchasing agent service providing method | |
| CN113935613A (en) | Equipment inspection method and device, electronic equipment and computer readable medium | |
| CN114936021A (en) | Data processing method, device, equipment and medium | |
| CN117710450A (en) | Method, device, equipment and storage medium for positioning key point |
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 |