Payment detection and processing method and device

Abstract

This specification provides a payment detection processing method and apparatus. One payment detection processing method includes: acquiring a protocol payment channel opened by an associated user for a payment user; performing interaction type detection based on first interaction data between the payment user and the associated user; if the detection fails, performing interaction attenuation calculation based on second interaction data between the payment user and the associated user; if the calculated interaction attenuation value is less than an attenuation threshold, calling a relationship prediction model to predict the termination of the relationship between the payment user and the associated user; if the relationship is determined to be terminated based on the prediction result, marking the protocol payment channel.

Description

[0001] This patent application is a divisional application of Chinese patent application No. 202211591168.5, filed on December 12, 2022, entitled "Payment Detection Processing Method and Apparatus". Technical Field

[0002] This document relates to the field of data processing technology, and in particular to a payment detection processing method and apparatus. Background Technology

[0003] With the continuous development and promotion of the Internet, the application scope of online payment based on the Internet is becoming wider and wider, gradually covering most users. In this context, various forms of online payment have emerged, such as mutual payment between users, making online payments more convenient for users. However, at the same time, complex user relationships may lead to risks in mutual payment between users. In view of this, how to improve payment security in the online payment process and reduce the possibility of user financial loss has become a new challenge for payment platforms in providing payment services to users. Summary of the Invention

[0004] This specification provides one or more embodiments of a payment detection processing method, including: obtaining the protocol payment channel opened by an associated user for a payment user; performing interaction type detection based on first interaction data between the payment user and the associated user; if the detection fails, performing interaction attenuation calculation based on second interaction data between the payment user and the associated user; if the calculated interaction attenuation value is less than an attenuation threshold, invoking a relationship prediction model to predict the termination of the relationship between the payment user and the associated user; if the relationship is determined to be terminated based on the prediction result, marking the protocol payment channel.

[0005] This specification provides one or more embodiments of a second payment detection processing method, applied to a user terminal of a payment user. The method includes: submitting a payment access request to a server based on the payment user's payment operation; receiving and displaying a set of payment channels containing protocol payment channels issued by the server; marking the protocol payment channels after performing interaction type detection, interaction attenuation calculation, and relationship dissolution prediction on the payment user and associated users who have activated the protocol payment channels; and sending a payment processing request to the server to confirm payment for the protocol payment channel for the associated users if a payment instruction for the protocol payment channel is detected.

[0006] This specification provides one or more embodiments of a third payment detection processing method applied to a server. The method includes: obtaining the protocol payment channels opened by an associated user for the paying user based on a payment access request submitted by the paying user's user terminal; performing relationship detection processing between the paying user and the associated user based on interaction data between the paying user and the associated user; the relationship detection processing including interaction type detection, interaction decay calculation, and relationship termination prediction; if the relationship detection fails, marking the protocol payment channels and sending a set of payment channels carrying the protocol payment channels to the user terminal; and performing payment confirmation for the associated user based on the payment processing request sent by the user terminal for the protocol payment channels.

[0007] This specification provides one or more embodiments of a payment detection processing apparatus, comprising: a protocol payment channel acquisition module configured to acquire protocol payment channels opened by an associated user for a payment user; an interaction type detection module configured to perform interaction type detection based on first interaction data between the payment user and the associated user; an interaction attenuation calculation module configured to perform interaction attenuation calculation based on second interaction data between the payment user and the associated user if the detection fails; a relationship termination prediction module configured to invoke a relationship prediction model to predict the termination of the relationship between the payment user and the associated user if the calculated interaction attenuation value is less than an attenuation threshold; and a marking processing module configured to mark the protocol payment channels if the relationship is determined to be terminated based on the prediction result.

[0008] This specification provides one or more embodiments of a second payment detection and processing device, operating on a user terminal of a payment user. The device includes: a payment access request submission module configured to submit a payment access request to a server based on the payment user's payment operation; a payment channel display module configured to receive and display a set of payment channels containing protocol payment channels issued by the server; the protocol payment channels are marked after interaction type detection, interaction attenuation calculation, and relationship dissolution prediction for the payment user and associated users who have activated the protocol payment channels; and a payment processing request sending module configured to send a payment processing request to the server if a payment instruction for the protocol payment channel is detected, to confirm payment for the associated user through the protocol payment channel.

[0009] This specification provides one or more embodiments of a third payment detection processing device, running on a server. The device includes: a protocol payment channel acquisition module, configured to acquire protocol payment channels opened by an associated user for the paying user based on a payment access request submitted by the paying user's user terminal; a relationship detection processing module, configured to perform relationship detection processing between the paying user and the associated user based on interaction data between the paying user and the associated user. The relationship detection processing includes interaction type detection, interaction decay calculation, and relationship termination prediction; a marking processing module, configured to mark the protocol payment channels if the relationship detection fails, and send a set of payment channels carrying the protocol payment channels to the user terminal; and a payment confirmation module, configured to confirm payment for the associated user for the protocol payment channels based on a payment processing request sent by the user terminal.

[0010] This specification provides one or more embodiments of a payment detection processing device, including: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: acquire a protocol payment channel opened by an associated user for a paying user; perform interaction type detection based on first interaction data between the paying user and the associated user; if the detection fails, perform interaction attenuation calculation based on second interaction data between the paying user and the associated user; if the calculated interaction attenuation value is less than an attenuation threshold, invoke a relationship prediction model to predict the termination of the relationship between the paying user and the associated user; if the relationship is determined to be terminated based on the prediction result, mark the protocol payment channel.

[0011] This specification provides one or more embodiments of a second payment detection and processing device, comprising: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: submit a payment access request to a server based on the payment operation of the paying user; receive and display a set of payment channels containing protocol payment channels issued by the server; mark the protocol payment channels after performing interaction type detection, interaction attenuation calculation, and relationship dissolution prediction on the paying user and associated users who have activated the protocol payment channels; and if a payment instruction for the protocol payment channel is detected, send a payment processing request to the server to confirm payment for the associated user through the protocol payment channel.

[0012] This specification provides one or more embodiments of a third payment detection processing device, comprising: a processor; and a memory configured to store computer-executable instructions, which, when executed, cause the processor to: obtain, based on a payment access request submitted by a user terminal of a payment user, a protocol payment channel opened by an associated user for the payment user; perform relationship detection processing between the payment user and the associated user based on interaction data between the payment user and the associated user; the relationship detection processing includes interaction type detection, interaction decay calculation, and relationship termination prediction; if the relationship detection fails, the protocol payment channel is marked, and a set of payment channels carrying the protocol payment channel is sent to the user terminal; and, based on a payment processing request sent by the user terminal for the protocol payment channel, perform payment confirmation for the associated user for the protocol payment channel.

[0013] This specification provides one or more embodiments of a storage medium for storing computer-executable instructions that, when executed by a processor, implement the following process: obtaining the protocol payment channel opened by the associated user for the paying user; performing interaction type detection based on first interaction data between the paying user and the associated user; if the detection fails, performing interaction attenuation calculation based on second interaction data between the paying user and the associated user; if the calculated interaction attenuation value is less than an attenuation threshold, invoking a relationship prediction model to predict the termination of the relationship between the paying user and the associated user; if the prediction result determines that the relationship is terminated, marking the protocol payment channel.

[0014] This specification provides one or more embodiments of a second storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following process: submitting a payment access request to a server based on the payment operation of the paying user; receiving and displaying a set of payment channels containing protocol payment channels issued by the server; marking the protocol payment channels after performing interaction type detection, interaction attenuation calculation, and relationship dissolution prediction on the paying user and associated users who have activated the protocol payment channels; and sending a payment processing request to the server to confirm payment for the protocol payment channels for the associated users if a payment instruction for the protocol payment channels is detected.

[0015] This specification provides one or more embodiments of a third storage medium for storing computer-executable instructions, which, when executed by a processor, implement the following process: Based on a payment access request submitted by a payment user's user terminal, obtain the protocol payment channels opened by the associated user for the payment user. Based on the interaction data between the payment user and the associated user, perform relationship detection processing between the payment user and the associated user. The relationship detection processing includes interaction type detection, interaction decay calculation, and relationship termination prediction. If the relationship detection fails, mark the protocol payment channels and send a set of payment channels carrying the protocol payment channels to the user terminal. Based on the payment processing request sent by the user terminal for the protocol payment channels, perform payment confirmation for the associated user for the protocol payment channels. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in one or more embodiments of this specification or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Figure 1 A flowchart illustrating a payment detection processing method provided in one or more embodiments of this specification; Figure 2 A flowchart illustrating an interaction type detection process provided for one or more embodiments of this specification; Figure 3 A schematic diagram of graph-structured interactive data provided in one or more embodiments of this specification; Figure 4 A flowchart illustrating an interactive attenuation calculation process provided for one or more embodiments of this specification; Figure 5 A flowchart illustrating a relationship termination prediction process provided for one or more embodiments of this specification; Figure 6 A schematic diagram of the model framework for a relationship prediction model provided in one or more embodiments of this specification; Figure 7 A schematic diagram illustrating a list of payment channels provided for one or more embodiments of this specification; Figure 8 A schematic diagram of a payment application page provided for one or more embodiments of this specification; Figure 9 A schematic diagram of a payment confirmation page provided for one or more embodiments of this specification; Figure 10This is a flowchart illustrating the second payment detection processing method provided in one or more embodiments of this specification. Figure 11 A flowchart illustrating a payment detection and processing method for intimate payment scenarios, provided in one or more embodiments of this specification. Figure 12 A flowchart illustrating the third payment detection processing method provided in one or more embodiments of this specification; Figure 13 A schematic diagram of a payment detection and processing device provided in one or more embodiments of this specification; Figure 14 A schematic diagram of a second payment detection processing device provided in one or more embodiments of this specification; Figure 15 A schematic diagram of a third payment detection processing device provided in one or more embodiments of this specification; Figure 16 A schematic diagram of the structure of a payment detection and processing device provided in one or more embodiments of this specification; Figure 17 A schematic diagram of the structure of a second payment detection and processing device provided in one or more embodiments of this specification; Figure 18 This is a schematic diagram of the structure of a third payment detection and processing device provided in one or more embodiments of this specification. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of this document.

[0018] This specification provides an example of a payment detection and processing method: In real-world scenarios, when users activate a payment agreement through a signed agreement, the user whose agreement was activated can use the activating user's payment channels to make payments. This greatly facilitates payments, especially for users with limited or no payment capabilities. They no longer need to perform complex payment top-ups or payment channel configurations themselves; they can use the payment agreement activated by family members or other users for convenient and quick payments. Users who activate payment agreements often have some kind of relationship in real life. The constraints of this relationship can ensure payment security and avoid payment disputes. However, the real-life relationship between users may change or even break down. In such cases, not only does the possibility of payment disputes increase, but the security of the payment agreement also faces challenges.

[0019] The payment detection and processing method provided in this embodiment, based on the fact that the associated user opens a protocol payment channel to the paying user, detects the relationship between the paying user and the associated user before the paying user uses the protocol payment channel for payment processing. Specifically, firstly, the interaction type between the paying user and the associated user is detected. If the detection fails, the interaction attenuation between the paying user and the associated user is further calculated. If the calculated interaction attenuation value is less than the attenuation threshold, the relationship between the paying user and the associated user is further predicted to be dissolved. Based on the prediction result, it is determined whether the protocol payment channel can be used. If the relationship between the paying user and the associated user is determined to be dissolved based on the prediction result, the protocol payment channel is marked. This method portrays the relationship between the paying user and the associated user more deeply and comprehensively from three levels, enabling efficient and accurate identification of the relationship between the paying user and the associated user. This reduces the probability of the protocol payment channel being used and causing financial loss when the user relationship changes or is dissolved, and improves the security of users using the protocol payment channel for payment.

[0020] Step S102: Obtain the protocol payment channel opened by the associated user for the payment user.

[0021] In this embodiment, the payment user includes the user of the party whose payment channel has been activated, also known as the target user; the associated user includes the user of the party who activated the payment channel for the payment user. The associated user can be a specific user who has a relationship with the payment user, such as a relative of the payment user, or a social user who has a social relationship with the payment user.

[0022] The aforementioned agreement payment channel refers to a payment channel opened to the payment user based on an agreement signed between the associated user and the payment user. This agreement payment channel can be a payment channel specified in the agreement. It should be noted that when an associated user opens an agreement payment channel to a payment user through an agreement signed with the payment user, this agreement payment channel is presented to the payment user. The payment user can use this agreement payment channel for payment processing, but the actual outflow of funds or resources generated by using this agreement payment channel is borne by the associated user. In other words, the agreement payment channel is linked to the associated user's payment account.

[0023] In practice, obtaining the protocol payment channels activated by the associated user for the paying user can be done during the paying user's payment processing. For example, during the paying user's initiation of an operation, the paying user's own payment channel list needs to be returned to the paying user. Before returning the payment channel list, the paying user's protocol payment channels can be detected. Based on the detection results, the protocol payment channels in the payment channel list can be marked. Finally, the payment channel list containing the marked protocol payment channels is returned to the paying user. In addition, the paying user's protocol payment channels can be detected periodically according to a preset detection cycle.

[0024] It should be noted that this embodiment uses the payment detection process of one protocol payment channel as an example for illustration. If the payment user has multiple protocol payment channels, payment detection processing can be performed for each protocol payment channel separately. The payment detection processing process of the protocol payment channel provided in this embodiment can be referred to, and will not be described in detail in this embodiment.

[0025] Specifically, in the process of payment detection and processing for multiple payment channels of a payment user, batch processing can be used to process multiple payment channels, or payment detection and processing can be performed on each payment channel sequentially. For example, payment detection and processing can be performed on each payment channel in descending order of payment priority. In addition, in order to reduce the detection time of payment detection and processing for multiple payment channels and improve the detection response efficiency of payment channels, a multi-threaded processing method can also be used, with one thread allocated to each payment channel, so as to achieve fast detection and response of payment channels.

[0026] Step S104: Detect the interaction type based on the first interaction data between the payment user and the associated user.

[0027] In this embodiment, based on the first interaction data between the paying user and the associated user, the interaction type between the paying user and the associated user is detected by performing interaction type detection. Specifically, it can detect whether the interaction between the paying user and the associated user is a negative interaction or a positive interaction, so as to quickly identify the paying user and the associated user with positive interaction. For the paying user and the associated user with negative interaction, in-depth and comprehensive detection can be carried out through subsequent interaction attenuation calculation and relationship dissolution prediction.

[0028] Here, negative interaction refers to interactive behavior that indicates an abnormal relationship between the paying user and the associated user, such as the interaction of the paying user deleting the associated user from being friends; positive interaction refers to interactive behavior that indicates a normal relationship between the paying user and the associated user, such as the interaction of the paying user adding the associated user as friends.

[0029] In specific implementation, by configuring the interaction type as a positive or negative interaction type, the interaction relationship between the payment user and the associated user can be quickly identified, achieving rapid response in interaction type detection. Specifically, in an optional implementation method provided in this embodiment, interaction type detection is performed based on the first interaction data between the payment user and the associated user, including: Detect whether the interaction type carried by the first interaction data is a negative interaction type; If the interaction is negative, the payment channel of the protocol will be marked. If it is a positive interaction type, check whether the generation time of the first interaction data is greater than a preset time threshold. If yes, confirm that the detection has failed; if no, no processing is required, or mark the protocol payment channel as a normal payment status.

[0030] In practice, to improve the effectiveness of interaction type detection, the first interaction data can be selected from the latest one or more interaction records between the payment user and the associated user. This will improve the real-time performance and effectiveness of interaction type detection based on the first interaction data.

[0031] For example, after User B and User A sign an Intimacy Payment Agreement, and the agreement takes effect, User A can use the Intimacy Payment channel to make payments based on the agreement. The funds generated by User A using this channel are paid by User B and deducted from User B's account. During the process of User A using the Intimacy Payment channel, it is necessary to perform interaction type detection between User A and User B, such as... Figure 2 The interaction type detection process is shown below: Step S202: Query the latest interaction message between user A and user B after they signed the Intimacy Payment Agreement; Step S204: Query the interaction type of the interaction message; Step S206: Determine whether the interaction type is a negative interaction type; If so, proceed to step S208; If not, proceed to steps S210 and S212; Step S208: Determine that the Intimate Payment channel poses a payment risk; Given the payment risks associated with the Intimate Payment payment channel, User A requires User B's confirmation before making a payment when using this channel. Step S210: Calculate the number of days between the interaction time of the message and the current time. Step S212: Determine whether the interval number of days is less than the specified number of days threshold; If so, proceed to step S214; If not, proceed to step S216; Step S214: Determine that there is no payment risk in the Intimate Payment channel; Step S216: Proceed to the next stage of interactive attenuation calculation.

[0032] Optionally, the first interaction data includes graph structure interaction data stored in a graph database; wherein, the data nodes in the graph structure interaction data correspond to the user identifier of the paying user and the user identifier of the associated user; the data connections in the graph structure interaction data correspond to a data sequence composed of the user identifier of the paying user, the user identifier of the associated user, interaction type and / or time information.

[0033] For example, Figure 3 The graph structure interaction data shown consists of nodes and edges. The node ID is the user ID. An edge is uniquely identified by four elements: the starting node ID, the target node ID, the interaction type (TYPE), and the timestamp (TIME). Figure 3 The leftmost edge can be represented as: 2088xxx03-Add Friend-2022 / 09 / 12 10:00:00-2088xxx01.

[0034] Step S106: If the detection fails, perform interaction attenuation calculation based on the second interaction data between the payment user and the associated user.

[0035] In real-world scenarios, when the interaction between the paying user and the associated user is a negative interaction type—meaning that the relationship between the paying user and the associated user has become abnormal or broken—the interaction between the paying user and the associated user may decrease. In other words, the less interaction the paying user has with the associated user, the greater the likelihood that the relationship between the paying user and the associated user has become abnormal or broken. On the other hand, the frequency of interaction between the paying user and the associated user is positively correlated with the activity level of both users. That is, the decrease in the interaction frequency of highly active users after the relationship becomes abnormal or broken is more significant than the decrease in the interaction frequency of inactive users after the relationship becomes abnormal or broken.

[0036] This embodiment detects the possibility of an anomaly or breakdown in the relationship between the paying user and the associated user by calculating the attenuation of the interaction frequency between the two parties. Here, the interaction attenuation calculation refers to calculating the attenuation of the interaction frequency between the paying user and the associated user, thereby characterizing the possibility of an anomaly or breakdown in the relationship between the paying user and the associated user.

[0037] In one optional implementation of this embodiment, interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user, including: Based on the total number of interactions contained in the second interaction data, the cumulative interaction frequency between the payment user and the associated user is calculated. Based on the average activity and interaction interval of the payment user and the associated user contained in the second interaction data, a time decay score is calculated; The interaction decay value is calculated based on the cumulative interaction frequency and the time decay fraction.

[0038] The second interaction data may be the interaction data between the paying user and the associated user within a specific time interval in the past.

[0039] Furthermore, after calculating the interaction attenuation based on the second interaction data between the paying user and the associated user, if the calculated interaction attenuation value is greater than or equal to the attenuation threshold, it indicates that the attenuation of the interaction between the paying user and the associated user is relatively large. In this case, optionally, the protocol payment channel can be marked.

[0040] Continuing with the previous example, the process of calculating the interaction decay for users A and B is as follows: Figure 4 As shown: Step S402: Query the total number of interactions between user A and user B in the past year, cnt. Step S404: Query the number of days t between the latest interaction time of user A and user B and the current time; Step S406: Calculate the average avg of the monthly active days for user A and user B; Step S408: Calculate the interaction attenuation score S between user A and user B using the interaction attenuation scoring formula; The specific formula for calculating interaction decay is as follows:

[0041] Where a, b, c, d, and f are pre-set constants, cnt is the total number of interactions, avg is the average number of monthly active days for user A and user B, and t is the number of days between the latest interaction time between user A and user B and the current time. Step S410: Determine whether the interaction decay score S exceeds the preset score threshold; If so, proceed to step S412; If not, proceed to step S414; Step S412: Determine that the Intimate Payment channel poses a payment risk; Given the payment risks associated with the Intimate Payment payment channel, User A requires User B's confirmation before making a payment when using this channel. Step S414: Proceed to the next stage of relationship termination prediction processing.

[0042] Step S108: If the calculated interaction attenuation value is less than the attenuation threshold, the relationship prediction model is invoked to predict the termination of the relationship between the payment user and the associated user.

[0043] If the interaction attenuation value obtained from the above interaction attenuation calculation is less than the attenuation threshold, it indicates that the attenuation of the interaction between the paying user and the associated user is relatively small. In this case, the relationship prediction model is invoked to predict the dissolution of the relationship between the paying user and the associated user, further detecting the relationship between the two parties. The relationship dissolution prediction refers to predicting the probability of the dissolution of the user relationship between the paying user and the associated user by detecting unique or exclusive user relationships.

[0044] In the specific detection process, starting from the relationship between the paying user and the associated user, the system checks whether there are any user relationships that conflict with the current relationship. This is used to detect anomalies or breakdowns in the current relationship between the paying user and the associated user. For example, for user relationships such as "couples" or "married couples," because these user relationships are unique or exclusive, if the paying user and the associated user are currently in a "couple" or "married" relationship, and it is detected that the paying user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user is likely to have been dissolved or broken. Alternatively, if it is detected that the associated user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user may also have been dissolved or broken.

[0045] In one optional implementation of this embodiment, the method of calling a relationship prediction model to predict the dissolution of the relationship between the paying user and the associated user includes: Obtain the first user data of the first associated user set of the payment user, and the second user data of the second associated user set of the associated user; The first user data and the second user data are input into the relationship prediction model to predict the value of the termination of the relationship between the paying user and the associated user as the prediction result.

[0046] Furthermore, in the process of predicting the value of the relationship termination between the paying user and the associated user, the efficiency and accuracy of the relationship termination value prediction are improved by deploying a neural network in the relationship prediction model. Optionally, the relationship prediction model includes a first neural network, a second neural network, and a third neural network. To further improve the accuracy of relationship termination numerical prediction, an attention mechanism is introduced for relationship termination numerical calculation. Specifically, in one optional implementation of this embodiment, the prediction of the relationship termination numerical value between the paying user and the associated user includes: The first concatenated vector from the vector set of the payment users and the second concatenated vector from the vector set of the associated users are respectively input into the corresponding first neural network for vector transformation to obtain the transformed vector; The attention weights of the transformation vector are calculated using the second neural network, and normalized weights are calculated based on the calculated attention weights. The weighted vector is calculated based on the normalized weights and the transformation vector, and then the weighted vector is input into the third neural network for calculation to obtain the relationship dissolution value.

[0047] Optionally, the attention weights include: a first attention weight between the paying user and the candidate associated users of the paying user, and a second attention weight between the associated user and the candidate associated users of the associated user. Based on this, in an optional implementation of this embodiment, the step of calculating the normalized weights based on the calculated attention weights includes: calculating the sum of the first attention weights and the second attention weights; and calculating the ratio of the first attention weights to the sum of the weights as the normalized weights.

[0048] Based on the above-mentioned optional implementation method for predicting the relationship between the paying user and the associated user, in order to reduce the computational load required for vector calculation and improve computational efficiency, this embodiment reduces the computational load required for vector calculation by mapping high-dimensional vectors to low-dimensional vectors. Specifically, in one optional implementation method provided in this embodiment, before inputting the first concatenated vector in the vector set of the paying user and the second concatenated vector in the vector set of the associated user into the corresponding first neural network for vector transformation, the following vector mapping operation is performed: The initial feature vector and initial relation vector of the payment user are vector-mapped to obtain the first feature mapping vector and the first relation mapping vector; The first concatenated vector is obtained by concatenating the first feature mapping vector and the first relation mapping vector. And / or, The initial feature vector and initial relationship vector of the associated user are vector-mapped to obtain the second feature mapping vector and the second relationship mapping vector. The second concatenated vector is obtained by concatenating the second feature mapping vector and the second relation mapping vector.

[0049] Specifically, in determining the initial feature vector of the paying user and the initial feature vector of the associated user, the feature vectors of the paying user, the associated user, and the candidate associated user of the paying user are fused together, and the feature vectors of the paying user, the associated user, and the candidate associated user of the associated user are also fused together. Based on these two fused vectors, calculations are performed to transform the user relationship conflict calculation into a binary classification problem, thereby enabling the detection of unique or exclusive user relationships. In one optional implementation of this embodiment, the initial feature vector of the paying user is obtained as follows: A first feature vector of the paying user, a second feature vector of the associated user, and a third feature vector of the candidate associated user of the paying user are obtained; the first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the initial feature vector of the paying user.

[0050] In one optional implementation of this embodiment, the initial relationship vector of the payment user is obtained as follows: obtain the first interaction relationship vector between the payment user and the associated user, and the second interaction relationship vector between the payment user and the candidate associated user; concatenate the first interaction relationship vector and the second interaction relationship vector to obtain the initial relationship vector of the payment user.

[0051] The above describes the process for determining the initial feature vector and initial relationship vector of a payment user. The process for determining the initial feature vector and initial relationship vector of an associated user is similar. Specifically, in an optional implementation of this embodiment, the initial feature vector of the associated user is obtained as follows: the first feature vector of the payment user, the second feature vector of the associated user, and the fourth feature vector of the candidate associated user of the associated user are obtained; the first feature vector, the second feature vector, and the fourth feature vector are concatenated to obtain the initial feature vector of the associated user.

[0052] Furthermore, in an optional implementation of this embodiment, the initial relationship vector of the associated user is obtained as follows: obtaining the first interaction relationship vector between the payment user and the associated user, and the third interaction relationship vector between the associated user and the candidate associated user of the associated user; concatenating the first interaction relationship vector and the third interaction relationship vector to obtain the initial relationship vector of the associated user.

[0053] Optionally, candidate associated users of a payment user are obtained by filtering from the payment user's set of interacting users based on the relationship tags between the payment user and associated users; specifically, interactive users whose relationship tags are the same as those between the payment user and associated users are selected from the payment user's set of interacting users as candidate associated users of the payment user.

[0054] Similarly, candidate related users of related users can also be obtained by filtering from the set of interactive users of related users based on the relationship tags between the payment user and the related user. Specifically, interactive users whose relationship tags are the same as those between the payment user and the related user are selected from the set of interactive users of related users as candidate related users of related users.

[0055] The relationship label between the paying user and the associated user can be determined based on the relationship keywords configured by the paying user or the associated user, or by inputting the user data of the paying user and the user data of the associated user into the relationship detection model to perform user relationship detection and obtain the relationship label between the paying user and the associated user.

[0056] Based on similar logic, the relationship labels between paying users and their interacting users can be determined based on the relationship keywords configured by either the paying user or the interacting user. Alternatively, the user data of both the paying user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the paying user and the interacting user. Similarly, the relationship labels between associated users and their interacting users can be determined based on the relationship keywords configured by either the associated user or the interacting user. Alternatively, the user data of both the associated user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the associated user and the interacting user.

[0057] In specific implementation, after calling the relationship prediction model to predict the termination of the relationship between the paying user and the associated user, in an optional implementation of this embodiment, if it is determined based on the prediction result that the relationship between the paying user and the associated user has not been terminated, then the payment status of the protocol payment channel is confirmed to be normal.

[0058] In the process of determining whether the relationship between the paying user and the associated user has been terminated based on the prediction results, the relationship termination value output by the relationship prediction model can be used to determine whether the relationship termination value is greater than a preset relationship termination threshold. If it is less than or equal to the relationship termination threshold, it indicates that the relationship between the paying user and the associated user is abnormal or that the possibility of termination is small, that is, the relationship between the paying user and the associated user is determined not to be terminated based on the prediction results; if it is greater than the relationship termination threshold, it indicates that the relationship between the paying user and the associated user is abnormal or that the possibility of termination is large, that is, the relationship between the paying user and the associated user is determined to be terminated based on the prediction results.

[0059] Continuing with the previous example, the process for predicting the termination of the relationship between user A and user B is as follows: Figure 5 As shown: Step S502: Identify whether the intimate relationship between user A and user B is a marital relationship; If so, proceed to step S504; If not, proceed to steps S506 to S512; Step S504: Determine that there is no payment risk in the Intimate Payment channel; Step S506: Recall the set of users who may have a marital relationship with user B. ; Step S508: Recall the set of users who may have a marital relationship with user A. ; Step S510: Deprecate the predicted score by predicting the relationship between user A and user B using the relationship prediction model; Step S512: Determine whether the relationship termination prediction score is greater than the relationship termination threshold; If so, proceed to step S514; If not, proceed to step S504; Step S514: Determine that the Intimate Payment channel poses a payment risk.

[0060] Among them, the relationship between user B and user A is...<u,v> And the set of users who may have a marital relationship with user B. The k1th user Extract the feature vectors of these three elements at the user level, such as the user's date of birth, asset information, and consumption preferences, and then concatenate these feature vectors to obtain... ; and extract the relationship vector representing the user relationship between user B and user A, and extract the relationship vector representing the user relationship between user B and user A. The relationship vectors of user relationships can be concatenated to obtain the following: ; Similarly, for user B's n potential spouses, a set of feature vectors is obtained. and relation vector set Similarly, for user A, the set of feature vectors is obtained from m users who may be in a marital relationship. and relation vector set ; Map the feature vectors from the two feature vector sets and the relation vectors from the two relation vector sets obtained above to a low-dimensional vector space, respectively. Then, concatenate the mapped feature vectors of user B with the relation vectors to obtain a concatenated vector set. ki And concatenate the feature vector mapped from user A with the relation vector to obtain a set of concatenated vectors. ki .

[0061] like Figure 6 The model framework of the relationship prediction model shown adds a fully connected neural network to each concatenated vector in the two concatenated vector sets to perform vector transformation: and

[0062] in, and The weight matrix and bias represent the weights of user B and the i-th user who may be in a marital relationship with user B, ultimately resulting in two sets of transformation vectors: ki , ki ; Considering that different users who may have a marital relationship with User B contribute differently to the prediction of the current relationship's dissolution, they cannot be treated equally. Therefore, an attention mechanism is introduced to learn the attention weight of each user who may have a marital relationship with User B. Specifically, a two-layer fully connected neural network is used to implement the attention mechanism. and

[0063] in, , , , as well as , , , These are parameters obtained in advance through model training; and Merging can yield The attention weights are calculated using the following formula:

[0064] After calculating the attention weights, according to The overall normalized weights can be calculated:

[0065] in, ; Finally, the predicted score is calculated using a single-layer fully connected neural network. :

[0066] Where W and b represent the weight matrix and bias, respectively.

[0067] Step S110: If the relationship is determined to be terminated based on the prediction result, the payment channel of the agreement is marked.

[0068] In this embodiment, by marking the protocol payment channel, the payment user can perceive any abnormality or breakdown in the relationship between the associated user who opened the protocol payment channel and the payment user, thereby improving the payment success rate. For the associated user who opened the protocol payment channel to the payment user, the probability of the protocol payment channel being used and resulting in financial loss due to changes or termination of the user relationship is reduced, ensuring the safety of the associated user's funds.

[0069] In one optional implementation of this embodiment, the protocol payment channel is marked, including: Mark the protocol payment channel as an abnormal payment status; and / or, downgrade the payment priority of the protocol payment channel based on the abnormal payment status.

[0070] In practical implementation, to reduce the probability of financial loss due to the use of the agreement payment channel when user relationships change or are terminated, and to ensure the safety of associated users' funds, this embodiment further improves the payment success rate of payment users by processing payment instructions by sending payment confirmation to associated users. Specifically, in one optional implementation of this embodiment, after marking the agreement payment channel, payment confirmation is performed in the following manner: According to the payment instructions of the payment channel in the agreement, a payment confirmation message is sent to the associated user; If a confirmation instruction from the payment confirmation message is detected, payment processing is performed based on the payment channel of the protocol.

[0071] For example, in User A's payment channel list, if the payment priority of the "Intimate Payment" channel with User B is moved from first to last, User A's payment channel list after the adjustment will look like this: Figure 7 As shown, simultaneously, the Intimate Payment channel displays an error message: "Payment risk exists; this payment requires confirmation." An access interface, "Request Payment Confirmation from User B," is configured to request confirmation from User B for the current payment. If User A clicks the "Request Payment Confirmation from User B" interface, a payment confirmation will be generated. Figure 8 On the payment application page shown, after user A clicks the "OK" button, a payment confirmation message will be sent to user B. After user B triggers the payment confirmation message, they will enter... Figure 9 The payment confirmation page shown.

[0072] It should be noted that the payment detection processing method provided in this application employs three processing methods—interaction type detection, interaction decay calculation, and relationship dissolution prediction—in sequence during the relationship detection processing of payment users and associated users. Furthermore, in the specific execution process, any one or any two of these three processing methods can be selected for relationship detection processing according to specific needs. The execution order of these three processing methods can also be adjusted accordingly, using the adjusted order for relationship detection. Similarly, the execution order of any two of these three processing methods can be adjusted during relationship detection processing, using the adjusted order for relationship detection.

[0073] The following provides implementation methods for relation detection: selecting any one of the three processing methods (interaction type detection, interaction decay calculation, and relation dissolution prediction); selecting any two of the three processing methods (interaction type detection, interaction decay calculation, and relation dissolution prediction); adjusting the execution order of the three processing methods before performing relation detection; and selecting any two of the three processing methods (interaction type detection, interaction decay calculation, and relation dissolution prediction) and adjusting the execution order of any two before performing relation detection. Other implementation methods can be found in the examples of the four implementation methods provided below, and will not be elaborated further in this embodiment.

[0074] (1) Implementation method of relation detection processing: select any one of the three processing methods: interaction type detection, interaction decay calculation, and relation dissolution prediction. Obtain the protocol payment channels opened by the associated user for the paying user; Interaction type detection is performed based on the first interaction data between the payment user and the associated user; If the test fails, the payment channel of the protocol will be marked. or, Obtain the protocol payment channels opened by the associated user for the paying user; Interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the protocol payment channel is marked.

[0075] or, Obtain the protocol payment channels opened by the associated user for the paying user; The relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0076] (2) Implementation method of relation detection processing by selecting any two of the three processing methods: interaction type detection, interaction decay calculation, and relation dissolution prediction. Obtain the protocol payment channels opened by the associated user for the paying user; Interaction type detection is performed based on the first interaction data between the payment user and the associated user; If the detection fails, an interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user. If the calculated interaction attenuation value is less than the attenuation threshold, the protocol payment channel is marked.

[0077] or, Obtain the protocol payment channels opened by the associated user for the paying user; Interaction type detection is performed based on the first interaction data between the payment user and the associated user; If the detection fails, the relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0078] or, Obtain the protocol payment channels opened by the associated user for the paying user; Interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0079] (3) Implementation method of relation detection after the execution order of the three processing methods, namely interaction type detection, interaction decay calculation and relation dissolution prediction, is adjusted. Obtain the protocol payment channels opened by the associated user for the paying user; Interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the interaction type is detected based on the first interaction data between the payment user and the associated user. If the detection fails, the relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0080] (4) Implementation method of performing relation detection processing after selecting any two of the three processing methods: interaction type detection, interaction decay calculation, and relation dissolution prediction, and adjusting the execution order of any two. Obtain the protocol payment channels opened by the associated user for the paying user; Interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the interaction type is detected based on the first interaction data between the payment user and the associated user. If the test fails, the payment channel of the protocol will be marked.

[0081] It should be noted that for the specific implementation details of the various implementation methods provided here, please refer to the corresponding content in steps S102 to S110 above. This embodiment will not repeat them one by one here.

[0082] This specification provides an example of the second payment detection processing method: Step S1002: Submit a payment access request to the server based on the payment operation of the paying user.

[0083] In this embodiment, the paying user includes the user whose payment channel has been activated and who initiates the payment. The other user, opposite the paying user, is the associated user, which includes the user who activated the payment channel for the paying user. The associated user can be a specific user with a relationship to the paying user, such as a relative of the paying user or a social user with a social connection to the paying user. The payment operation can be for online orders awaiting payment or for offline orders.

[0084] Step S1004: Receive and display the payment channel set containing the protocol payment channels sent by the server.

[0085] The aforementioned agreement payment channel refers to a payment channel opened to the payment user based on an agreement signed between the associated user and the payment user. This agreement payment channel can be a payment channel specified in the agreement. It should be noted that when an associated user opens an agreement payment channel to a payment user through an agreement signed with the payment user, this agreement payment channel is presented to the payment user. The payment user can use this agreement payment channel for payment processing, but the actual outflow of funds or resources generated by using this agreement payment channel is borne by the associated user. In other words, the agreement payment channel is linked to the associated user's payment account.

[0086] The aforementioned payment access request is submitted to the server. Upon receiving the payment access request, the server first obtains a payment channel set consisting of at least one payment channel for the paying user. If the payment channel set includes a protocol payment channel, the server performs relationship detection processing on the paying user and associated users who have activated the protocol payment channel. Based on the detection results, the protocol payment channels in the payment channel list are marked. Finally, the payment channel list containing the marked protocol payment channels is returned to the paying user. Optionally, the protocol payment channel is marked after interaction type detection, interaction decay calculation, and relationship dissolution prediction are performed on the paying user and associated users who have activated the protocol payment channel.

[0087] In specific implementation, during the relationship detection process between the payment user and the associated user who has activated the payment channel, the server can perform interaction type detection, interaction attenuation calculation, and relationship dissolution prediction for the payment user and the associated user. The interaction type detection can be based on the first interaction data between the payment user and the associated user, the interaction attenuation calculation can be based on the second interaction data, and the relationship dissolution prediction can be performed by calling a relationship prediction model. Furthermore, the interaction attenuation calculation can be performed if the interaction type detection fails, and the relationship dissolution prediction can be performed if the interaction attenuation value obtained from the interaction attenuation calculation is less than the attenuation threshold.

[0088] In one optional implementation of this embodiment, the interaction type detection is implemented in the following manner: Detect whether the interaction type carried in the first interaction data between the payment user and the associated user is a negative interaction type; If the interaction is negative, the payment channel of the protocol will be marked. If it is a positive interaction type, check whether the generation time of the first interaction data is greater than a preset time threshold. If so, perform the interaction attenuation calculation.

[0089] Here, based on the initial interaction data between the paying user and the associated user, the interaction type detection is performed on the paying user and the associated user to detect the interaction type between the two parties. Specifically, it can detect whether the interaction between the paying user and the associated user is a negative interaction or a positive interaction, so as to quickly identify the paying user and the associated user with a positive interaction. For the paying user and the associated user with a negative interaction, a deeper and more comprehensive detection can be carried out through subsequent interaction decay calculation and relationship dissolution prediction.

[0090] Negative interaction refers to interaction behavior that indicates an abnormal relationship between the paying user and the associated user, such as the interaction behavior of the paying user deleting the associated user from being friends; positive interaction refers to interaction behavior that indicates a normal relationship between the paying user and the associated user, such as the interaction behavior of the paying user adding the associated user as friends.

[0091] Optionally, the first interaction data includes graph structure interaction data stored in a graph database; wherein, the data nodes in the graph structure interaction data correspond to the user identifier of the paying user and the user identifier of the associated user; the data connections in the graph structure interaction data correspond to a data sequence composed of the user identifier of the paying user, the user identifier of the associated user, interaction type and / or time information.

[0092] To improve the effectiveness of interaction type detection, the first interaction data can be selected from the latest one or more interaction records between the payment user and the associated user. This improves the real-time performance and effectiveness of interaction type detection based on the first interaction data.

[0093] In real-world scenarios, when the interaction between the paying user and the associated user is a negative interaction type—meaning the relationship between them is abnormal or broken—the interaction between the paying user and the associated user may decrease. In other words, the less interaction the paying user interacts with the associated user, the greater the likelihood of an abnormal or broken relationship. Furthermore, the frequency of interaction between the paying user and the associated user is positively correlated with the activity level of both users. That is, the decrease in interaction frequency after an abnormal or broken relationship occurs is more pronounced for highly active users than for less active users. This embodiment detects the possibility of an abnormal or broken relationship between the paying user and the associated user by calculating the degree of decrease in interaction frequency. Here, the interaction decrease calculation refers to calculating the degree of decrease in interaction frequency between the paying user and the associated user to characterize the possibility of an abnormal or broken relationship.

[0094] In one optional implementation of this embodiment, the interactive attenuation calculation is implemented in the following manner: Based on the total number of interactions contained in the second interaction data between the payment user and the associated user, the cumulative interaction frequency between the payment user and the associated user is calculated. Based on the average activity and interaction interval of the payment user and the associated user contained in the second interaction data, a time decay score is calculated; The interaction decay value is calculated based on the cumulative interaction frequency and the time decay fraction, and the relationship disintegration prediction is performed if the interaction decay value is less than the decay threshold.

[0095] The second interaction data may be the interaction data between the paying user and the associated user within a specific time interval in the past.

[0096] In one optional implementation of this embodiment, the relationship termination prediction is achieved in the following manner: The first concatenated vector from the vector set of the payment users and the second concatenated vector from the vector set of the associated users are respectively input into the corresponding first neural network for vector transformation to obtain the transformed vector; The attention weights of the transformation vector are calculated using a second neural network, and normalized weights are calculated based on the calculated attention weights. The weighted vector is calculated based on the normalized weights and feature vectors, and the weighted vector is input into the third neural network for calculation. The labeling process is performed when the obtained relation dissolution value is greater than a preset threshold.

[0097] Optionally, the attention weights include: a first attention weight between the paying user and the candidate associated users of the paying user, and a second attention weight between the associated user and the candidate associated users of the associated user. Based on this, in an optional implementation of this embodiment, the step of calculating the normalized weights based on the calculated attention weights includes: calculating the sum of the first attention weights and the second attention weights; and calculating the ratio of the first attention weights to the sum of the weights as the normalized weights.

[0098] The above method starts from the relationship between the paying user and the associated user, detecting whether there are any user relationships that conflict with the current relationship. This is used to detect anomalies or breakdowns in the current relationship between the paying user and the associated user. For example, for user relationships such as "couple" or "married couple," because these user relationships are unique or exclusive, if the paying user and the associated user are currently in a "couple" or "married" relationship, and it is detected that the paying user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user is likely to have been dissolved or broken. Alternatively, if it is detected that the associated user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user may also have been dissolved or broken.

[0099] Based on the optional implementation method for predicting relationship termination provided above, in order to reduce the computational load required for vector computation and improve computational efficiency, this embodiment reduces the computational load required for vector computation by mapping high-dimensional vectors to low-dimensional vectors. Specifically, in one optional implementation method provided in this embodiment, before inputting the first concatenated vector from the vector set of the paying user and the second concatenated vector from the vector set of the associated user into the corresponding first neural network for vector transformation to obtain the transformed vector, the following vector mapping operation is performed: The initial feature vector and initial relation vector of the payment user are vector-mapped to obtain the first feature mapping vector and the first relation mapping vector; The first concatenated vector is obtained by concatenating the first feature mapping vector and the first relation mapping vector. And / or, The initial feature vector and initial relationship vector of the associated user are vector-mapped to obtain the second feature mapping vector and the second relationship mapping vector. The second concatenated vector is obtained by concatenating the second feature mapping vector and the second relation mapping vector.

[0100] Specifically, in determining the initial feature vector of the paying user and the initial feature vector of the associated user, the feature vectors of the paying user, the associated user, and the candidate associated user of the paying user are fused together, and the feature vectors of the paying user, the associated user, and the candidate associated user of the associated user are also fused together. Based on these two fused vectors, calculations are performed to transform the user relationship conflict calculation into a binary classification problem, thereby enabling the detection of unique or exclusive user relationships. In one optional implementation of this embodiment, the initial feature vector of the paying user is obtained as follows: A first feature vector of the paying user, a second feature vector of the associated user, and a third feature vector of the candidate associated user of the paying user are obtained; the first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the initial feature vector of the paying user.

[0101] In one optional implementation of this embodiment, the initial relationship vector of the payment user is obtained as follows: obtain the first interaction relationship vector between the payment user and the associated user, and the second interaction relationship vector between the payment user and the candidate associated user; concatenate the first interaction relationship vector and the second interaction relationship vector to obtain the initial relationship vector of the payment user.

[0102] The above describes the process for determining the initial feature vector and initial relationship vector of a payment user. The process for determining the initial feature vector and initial relationship vector of an associated user is similar. Specifically, in an optional implementation of this embodiment, the initial feature vector of the associated user is obtained as follows: the first feature vector of the payment user, the second feature vector of the associated user, and the fourth feature vector of the candidate associated user of the associated user are obtained; the first feature vector, the second feature vector, and the fourth feature vector are concatenated to obtain the initial feature vector of the associated user.

[0103] Furthermore, in an optional implementation of this embodiment, the initial relationship vector of the associated user is obtained as follows: obtaining the first interaction relationship vector between the payment user and the associated user, and the third interaction relationship vector between the associated user and the candidate associated user of the associated user; concatenating the first interaction relationship vector and the third interaction relationship vector to obtain the initial relationship vector of the associated user.

[0104] Optionally, candidate associated users of a payment user are obtained by filtering from the payment user's set of interacting users based on the relationship tags between the payment user and associated users; specifically, interactive users whose relationship tags are the same as those between the payment user and associated users are selected from the payment user's set of interacting users as candidate associated users of the payment user.

[0105] Similarly, candidate related users of related users can also be obtained by filtering from the set of interactive users of related users based on the relationship tags between the payment user and the related user. Specifically, interactive users whose relationship tags are the same as those between the payment user and the related user are selected from the set of interactive users of related users as candidate related users of related users.

[0106] The relationship label between the paying user and the associated user can be determined based on the relationship keywords configured by the paying user or the associated user, or by inputting the user data of the paying user and the user data of the associated user into the relationship detection model to perform user relationship detection and obtain the relationship label between the paying user and the associated user.

[0107] Based on similar logic, the relationship labels between paying users and their interacting users can be determined based on the relationship keywords configured by either the paying user or the interacting user. Alternatively, the user data of both the paying user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the paying user and the interacting user. Similarly, the relationship labels between associated users and their interacting users can be determined based on the relationship keywords configured by either the associated user or the interacting user. Alternatively, the user data of both the associated user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the associated user and the interacting user.

[0108] It should be noted that during the relationship detection process for payment users and associated users, the three processing methods—interaction type detection, interaction decay calculation, and relationship dissolution prediction—can be used simultaneously and sequentially. Furthermore, in the specific execution process, any one or any two of these three methods can be selected for relationship detection, depending on the specific needs. The execution order of these three methods can also be adjusted accordingly, using the adjusted order for relationship detection. Similarly, the execution order of any two of these methods can be adjusted during relationship detection, using the adjusted order for relationship detection.

[0109] It should also be noted that the interaction type detection, interaction attenuation calculation and relationship dissolution prediction processes provided in this embodiment are merely illustrative. The specific processing procedures and execution examples of interaction type detection, interaction attenuation calculation and relationship dissolution prediction can be found in the corresponding content provided in steps S104 to S108 of the above method embodiment, and will not be repeated here.

[0110] In this embodiment, by marking the protocol payment channel, the paying user can perceive any abnormality or breakdown in the relationship between the associated user who opened the protocol payment channel and the paying user, thereby improving the payment success rate. For the associated user who opened the protocol payment channel, this reduces the probability of financial loss due to the use of the protocol payment channel in the event of a change or termination of the user relationship, ensuring the safety of the associated user's funds. In one optional implementation of this embodiment, marking the protocol payment channel includes: marking the protocol payment channel as having an abnormal payment status; and / or, downgrading the payment priority of the protocol payment channel based on the abnormal payment status.

[0111] Step S1006: If a payment instruction for the protocol payment channel is detected, a payment processing request is sent to the server to confirm the payment for the associated user through the protocol payment channel.

[0112] In practical implementation, to reduce the probability of financial loss due to the use of the agreement payment channel when user relationships change or are terminated, and to ensure the fund security of associated users, this embodiment further improves the payment success rate of paying users by processing payment instructions from associated users through payment confirmation. Specifically, in one optional implementation of this embodiment, payment confirmation for the agreement payment channel for the associated user includes: sending a payment confirmation message to the associated user and receiving a confirmation instruction from the payment confirmation message; and processing the payment through the agreement payment channel based on the confirmation instruction.

[0113] The implementation process of the second payment detection processing method provided above can be executed by the user terminal. The implementation process of the third payment detection processing method provided in the following method embodiments can be executed by the server. The two cooperate with each other during the execution process. Therefore, when reading the above implementation process, you can refer to the corresponding content of the third method embodiment below. Correspondingly, when reading the implementation process of the third method embodiment below, you can also refer to the corresponding content of the above method embodiments.

[0114] The following example illustrates the application of a payment detection and processing method provided in this embodiment in a close-knit payment scenario. Figure 11The payment detection processing method provided in this embodiment will be further explained below. See [link to documentation]. Figure 11 The payment detection and processing method applied to intimate payment scenarios includes the following steps.

[0115] Step S1102: Obtain the order payment operation initiated by user A.

[0116] Step S1104: Submit a payment access request for the order payment operation to the server.

[0117] Step S1118: Receive and display the payment channel set sent by the server, which includes the tagged and processed intimate payment channels.

[0118] Step S1120: A payment instruction for the intimate payment channel is detected.

[0119] Step S1122: Send a payment processing request for the intimate payment channel to the server.

[0120] The steps S1102 to S1104 and S1118 to S1122 provided in this embodiment are executed by the client. It should be noted that the client's execution of the above steps S1102 to S1104 and S1118 to S1122 is coordinated with the server's execution of steps S1106 to S1116 and S1124 to S1126 in the following embodiment. Therefore, when reading this embodiment, please refer to the corresponding content of steps S1106 to S1116 and S1124 to S1126 below. Correspondingly, when reading steps S1106 to S1116 and S1124 to S1126 below, please also refer to the corresponding content of steps S1102 to S1104 and S1118 to S1122 provided in this embodiment.

[0121] This manual provides an example of the third payment detection processing method: Step S1202: Based on the payment access request submitted by the user terminal of the payment user, obtain the protocol payment channel opened by the associated user to the payment user.

[0122] In this embodiment, the payment user includes the user of the party whose payment channel has been activated, also known as the target user; the associated user includes the user of the party who activated the payment channel for the payment user. The associated user can be a specific user who has a relationship with the payment user, such as a relative of the payment user, or a social user who has a social relationship with the payment user.

[0123] The aforementioned agreement payment channel refers to a payment channel opened to the payment user based on an agreement signed between the associated user and the payment user. This agreement payment channel can be a payment channel specified in the agreement. It should be noted that when an associated user opens an agreement payment channel to a payment user through an agreement signed with the payment user, this agreement payment channel is presented to the payment user. The payment user can use this agreement payment channel for payment processing, but the actual outflow of funds or resources generated by using this agreement payment channel is borne by the associated user. In other words, the agreement payment channel is linked to the associated user's payment account.

[0124] In practice, obtaining the protocol payment channels activated by the associated user for the paying user can be done during the paying user's payment processing. For example, during the paying user's initiation of an operation, the paying user's own payment channel list needs to be returned to the paying user. Before returning the payment channel list, the paying user's protocol payment channels can be detected. Based on the detection results, the protocol payment channels in the payment channel list can be marked. Finally, the payment channel list containing the marked protocol payment channels is returned to the paying user. In addition, the paying user's protocol payment channels can be detected periodically according to a preset detection cycle.

[0125] It should be noted that this embodiment uses the payment detection process of one protocol payment channel as an example for illustration. If the payment user has multiple protocol payment channels, payment detection processing can be performed for each protocol payment channel separately. The payment detection processing process of the protocol payment channel provided in this embodiment can be referred to, and will not be described in detail in this embodiment.

[0126] Specifically, in the process of payment detection and processing for multiple payment channels of a payment user, batch processing can be used to process multiple payment channels, or payment detection and processing can be performed on each payment channel sequentially. For example, payment detection and processing can be performed on each payment channel in descending order of payment priority. In addition, in order to reduce the detection time of payment detection and processing for multiple payment channels and improve the detection response efficiency of payment channels, a multi-threaded processing method can also be used, with one thread allocated to each payment channel, so as to achieve fast detection and response of payment channels.

[0127] Step S1204: Based on the interaction data between the payment user and the associated user, perform relationship detection processing between the payment user and the associated user.

[0128] Optionally, the relationship detection process includes interaction type detection, interaction attenuation calculation, and relationship dissolution prediction. Specifically, the interaction type detection can be based on first interaction data between the paying user and the associated user; the interaction attenuation calculation can be based on second interaction data; and the relationship dissolution prediction can be performed by calling a relationship prediction model. Furthermore, the interaction attenuation calculation can be performed if the interaction type detection fails, and the relationship dissolution prediction can be performed if the interaction attenuation value obtained from the interaction attenuation calculation is less than an attenuation threshold.

[0129] In one optional implementation of this embodiment, the interaction type detection is implemented in the following manner: Detect whether the interaction type carried in the first interaction data between the payment user and the associated user is a negative interaction type; If the interaction is negative, the payment channel of the protocol will be marked. If it is a positive interaction type, check whether the generation time of the first interaction data is greater than a preset time threshold. If so, perform the interaction attenuation calculation.

[0130] Here, based on the initial interaction data between the paying user and the associated user, the interaction type detection is performed on the paying user and the associated user to detect the interaction type between the two parties. Specifically, it can detect whether the interaction between the paying user and the associated user is a negative interaction or a positive interaction, so as to quickly identify the paying user and the associated user with a positive interaction. For the paying user and the associated user with a negative interaction, a deeper and more comprehensive detection can be carried out through subsequent interaction decay calculation and relationship dissolution prediction.

[0131] Negative interaction refers to interaction behavior that indicates an abnormal relationship between the paying user and the associated user, such as the interaction behavior of the paying user deleting the associated user from being friends; positive interaction refers to interaction behavior that indicates a normal relationship between the paying user and the associated user, such as the interaction behavior of the paying user adding the associated user as friends.

[0132] To improve the effectiveness of interaction type detection, the first interaction data can be selected from the latest one or more interaction records between the payment user and the associated user. This improves the real-time performance and effectiveness of interaction type detection based on the first interaction data.

[0133] For example, after User B and User A sign an Intimacy Payment Agreement, and the agreement takes effect, User A can use the Intimacy Payment channel to make payments based on the agreement. The funds generated by User A using this channel are paid by User B and deducted from User B's account. During the process of User A using the Intimacy Payment channel, it is necessary to perform interaction type detection between User A and User B, such as... Figure 2 The interaction type detection process is shown below: Step S202: Query the latest interaction message between user A and user B after they signed the Intimacy Payment Agreement; Step S204: Query the interaction type of the interaction message; Step S206: Determine whether the interaction type is a negative interaction type; If so, proceed to step S208; If not, proceed to steps S210 and S212; Step S208: Determine that the Intimate Payment channel poses a payment risk; Given the payment risks associated with the Intimate Payment payment channel, User A requires User B's confirmation before making a payment when using this channel. Step S210: Calculate the number of days between the interaction time of the message and the current time. Step S212: Determine whether the interval number of days is less than the specified number of days threshold; If so, proceed to step S214; If not, proceed to step S216; Step S214: Determine that there is no payment risk in the Intimate Payment channel; Step S216: Proceed to the next stage of interactive attenuation calculation.

[0134] Optionally, the first interaction data includes graph structure interaction data stored in a graph database; wherein, the data nodes in the graph structure interaction data correspond to the user identifier of the paying user and the user identifier of the associated user; the data connections in the graph structure interaction data correspond to a data sequence composed of the user identifier of the paying user, the user identifier of the associated user, interaction type and / or time information.

[0135] For example, Figure 3 The graph structure interaction data shown consists of nodes and edges. The node ID is the user ID. An edge is uniquely identified by four elements: the starting node ID, the target node ID, the interaction type (TYPE), and the timestamp (TIME). Figure 3The leftmost edge can be represented as: 2088xxx03-Add Friend-2022 / 09 / 12 10:00:00-2088xxx01.

[0136] In real-world scenarios, when the interaction between the paying user and the associated user is a negative interaction type—meaning the relationship between them is abnormal or broken—the interaction between the paying user and the associated user may decrease. In other words, the less interaction the paying user interacts with the associated user, the greater the likelihood of an abnormal or broken relationship. Furthermore, the frequency of interaction between the paying user and the associated user is positively correlated with the activity level of both users. That is, the decrease in interaction frequency after an abnormal or broken relationship occurs is more pronounced for highly active users than for less active users. This embodiment detects the possibility of an abnormal or broken relationship between the paying user and the associated user by calculating the degree of decrease in interaction frequency. Here, the interaction decrease calculation refers to calculating the degree of decrease in interaction frequency between the paying user and the associated user to characterize the possibility of an abnormal or broken relationship.

[0137] In one optional implementation of this embodiment, the interactive attenuation calculation is implemented in the following manner: Based on the total number of interactions contained in the second interaction data between the payment user and the associated user, the cumulative interaction frequency between the payment user and the associated user is calculated. Based on the average activity and interaction interval of the payment user and the associated user contained in the second interaction data, a time decay score is calculated; The interaction decay value is calculated based on the cumulative interaction frequency and the time decay fraction, and the relationship disintegration prediction is performed if the interaction decay value is less than the decay threshold.

[0138] The second interaction data may be the interaction data between the paying user and the associated user within a specific time interval in the past.

[0139] Continuing with the previous example, the process of calculating the interaction decay for users A and B is as follows: Figure 4 As shown: Step S402: Query the total number of interactions between user A and user B in the past year, cnt. Step S404: Query the number of days t between the latest interaction time of user A and user B and the current time; Step S406: Calculate the average avg of the monthly active days for user A and user B; Step S408: Calculate the interaction attenuation score S between user A and user B using the interaction attenuation scoring formula; The specific formula for calculating interaction decay is as follows:

[0140] Where a, b, c, d, and f are pre-set constants, cnt is the total number of interactions, avg is the average number of monthly active days for user A and user B, and t is the number of days between the latest interaction time between user A and user B and the current time. Step S410: Determine whether the interaction decay score S exceeds the preset score threshold; If so, proceed to step S412; If not, proceed to step S414; Step S412: Determine that the Intimate Payment channel poses a payment risk; Given the payment risks associated with the Intimate Payment payment channel, User A requires User B's confirmation before making a payment when using this channel. Step S414: Proceed to the next stage of relationship termination prediction processing.

[0141] In one optional implementation of this embodiment, the relationship termination prediction is achieved in the following manner: The first concatenated vector from the vector set of the payment users and the second concatenated vector from the vector set of the associated users are respectively input into the corresponding first neural network for vector transformation to obtain the transformed vector; The attention weights of the transformation vector are calculated using a second neural network, and normalized weights are calculated based on the calculated attention weights. The weighted vector is calculated based on the normalized weights and feature vectors, and the weighted vector is input into the third neural network for calculation. The labeling process is performed when the obtained relation dissolution value is greater than a preset threshold.

[0142] Optionally, the attention weights include: a first attention weight between the paying user and the candidate associated users of the paying user, and a second attention weight between the associated user and the candidate associated users of the associated user. Based on this, in an optional implementation of this embodiment, the step of calculating the normalized weights based on the calculated attention weights includes: calculating the sum of the first attention weights and the second attention weights; and calculating the ratio of the first attention weights to the sum of the weights as the normalized weights.

[0143] The above method starts from the relationship between the paying user and the associated user, detecting whether there are any user relationships that conflict with the current relationship. This is used to detect anomalies or breakdowns in the current relationship between the paying user and the associated user. For example, for user relationships such as "couple" or "married couple," because these user relationships are unique or exclusive, if the paying user and the associated user are currently in a "couple" or "married" relationship, and it is detected that the paying user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user is likely to have been dissolved or broken. Alternatively, if it is detected that the associated user has established a "couple" or "married" relationship with other users, it indicates that the "couple" or "married" relationship between the paying user and the associated user may also have been dissolved or broken.

[0144] Based on the optional implementation method for predicting relationship termination provided above, in order to reduce the computational load required for vector computation and improve computational efficiency, this embodiment reduces the computational load required for vector computation by mapping high-dimensional vectors to low-dimensional vectors. Specifically, in one optional implementation method provided in this embodiment, before inputting the first concatenated vector from the vector set of the paying user and the second concatenated vector from the vector set of the associated user into the corresponding first neural network for vector transformation to obtain the transformed vector, the following vector mapping operation is performed: The initial feature vector and initial relation vector of the payment user are vector-mapped to obtain the first feature mapping vector and the first relation mapping vector; The first concatenated vector is obtained by concatenating the first feature mapping vector and the first relation mapping vector. And / or, The initial feature vector and initial relationship vector of the associated user are vector-mapped to obtain the second feature mapping vector and the second relationship mapping vector. The second concatenated vector is obtained by concatenating the second feature mapping vector and the second relation mapping vector.

[0145] Specifically, in determining the initial feature vector of the paying user and the initial feature vector of the associated user, the feature vectors of the paying user, the associated user, and the candidate associated user of the paying user are fused together, and the feature vectors of the paying user, the associated user, and the candidate associated user of the associated user are also fused together. Based on these two fused vectors, calculations are performed to transform the user relationship conflict calculation into a binary classification problem, thereby enabling the detection of unique or exclusive user relationships. In one optional implementation of this embodiment, the initial feature vector of the paying user is obtained as follows: A first feature vector of the paying user, a second feature vector of the associated user, and a third feature vector of the candidate associated user of the paying user are obtained; the first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the initial feature vector of the paying user.

[0146] In one optional implementation of this embodiment, the initial relationship vector of the payment user is obtained as follows: obtain the first interaction relationship vector between the payment user and the associated user, and the second interaction relationship vector between the payment user and the candidate associated user; concatenate the first interaction relationship vector and the second interaction relationship vector to obtain the initial relationship vector of the payment user.

[0147] The above describes the process for determining the initial feature vector and initial relationship vector of a payment user. The process for determining the initial feature vector and initial relationship vector of an associated user is similar. Specifically, in an optional implementation of this embodiment, the initial feature vector of the associated user is obtained as follows: the first feature vector of the payment user, the second feature vector of the associated user, and the fourth feature vector of the candidate associated user of the associated user are obtained; the first feature vector, the second feature vector, and the fourth feature vector are concatenated to obtain the initial feature vector of the associated user.

[0148] Furthermore, in an optional implementation of this embodiment, the initial relationship vector of the associated user is obtained as follows: obtaining the first interaction relationship vector between the payment user and the associated user, and the third interaction relationship vector between the associated user and the candidate associated user of the associated user; concatenating the first interaction relationship vector and the third interaction relationship vector to obtain the initial relationship vector of the associated user.

[0149] Optionally, candidate associated users of a payment user are obtained by filtering from the payment user's set of interacting users based on the relationship tags between the payment user and associated users; specifically, interactive users whose relationship tags are the same as those between the payment user and associated users are selected from the payment user's set of interacting users as candidate associated users of the payment user.

[0150] Similarly, candidate related users of related users can also be obtained by filtering from the set of interactive users of related users based on the relationship tags between the payment user and the related user. Specifically, interactive users whose relationship tags are the same as those between the payment user and the related user are selected from the set of interactive users of related users as candidate related users of related users.

[0151] The relationship label between the paying user and the associated user can be determined based on the relationship keywords configured by the paying user or the associated user, or by inputting the user data of the paying user and the user data of the associated user into the relationship detection model to perform user relationship detection and obtain the relationship label between the paying user and the associated user.

[0152] Based on similar logic, the relationship labels between paying users and their interacting users can be determined based on the relationship keywords configured by either the paying user or the interacting user. Alternatively, the user data of both the paying user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the paying user and the interacting user. Similarly, the relationship labels between associated users and their interacting users can be determined based on the relationship keywords configured by either the associated user or the interacting user. Alternatively, the user data of both the associated user and the interacting user can be input into a relationship detection model to perform user relationship detection and obtain the relationship labels between the associated user and the interacting user.

[0153] Continuing with the previous example, the process for predicting the termination of the relationship between user A and user B is as follows: Figure 5 As shown: Step S502: Identify whether the intimate relationship between user A and user B is a marital relationship; If so, proceed to step S504; If not, proceed to steps S506 to S512; Step S504: Determine that there is no payment risk in the Intimate Payment channel; Step S506: Recall the set of users who may have a marital relationship with user B. ; Step S508: Recall the set of users who may have a marital relationship with user A. ; Step S510: Deprecate the predicted score by predicting the relationship between user A and user B using the relationship prediction model; Step S512: Determine whether the relationship termination prediction score is greater than the relationship termination threshold; If so, proceed to step S514; If not, proceed to step S504; Step S514: Determine that the Intimate Payment channel poses a payment risk.

[0154] Among them, the relationship between user B and user A is...<u,v> And the set of users who may have a marital relationship with user B. The k1th user Extract the feature vectors of these three elements at the user level, such as the user's date of birth, asset information, and consumption preferences, and then concatenate these feature vectors to obtain... ; and extract the relationship vector representing the user relationship between user B and user A, and extract the relationship vector representing the user relationship between user B and user A. The relationship vectors of user relationships can be concatenated to obtain the following: ; Similarly, for user B's n potential spouses, a set of feature vectors is obtained. and relation vector set Similarly, for user A, the set of feature vectors is obtained from m users who may be in a marital relationship. and relation vector set ; Map the feature vectors from the two feature vector sets and the relation vectors from the two relation vector sets obtained above to a low-dimensional vector space, respectively. Then, concatenate the mapped feature vectors of user B with the relation vectors to obtain a concatenated vector set. ki And concatenate the feature vector mapped from user A with the relation vector to obtain a set of concatenated vectors. ki .

[0155] like Figure 6 The model framework of the relationship prediction model shown adds a fully connected neural network to each concatenated vector in the two concatenated vector sets to perform vector transformation: and

[0156] in, and The weight matrix and bias represent the weights of user B and the i-th user who may be in a marital relationship with user B, ultimately resulting in two sets of transformation vectors: ki , ki ; Considering that different users who may have a marital relationship with User B contribute differently to the prediction of the current relationship's dissolution, they cannot be treated equally. Therefore, an attention mechanism is introduced to learn the attention weight of each user who may have a marital relationship with User B. Specifically, a two-layer fully connected neural network is used to implement the attention mechanism. and

[0157] in, , , , as well as , , , These are parameters obtained in advance through model training; and Merging can yield The attention weights are calculated using the following formula:

[0158] After calculating the attention weights, according to The overall normalized weights can be calculated:

[0159] in, ; Finally, the predicted score is calculated using a single-layer fully connected neural network. :

[0160] Where W and b represent the weight matrix and bias, respectively.

[0161] It should be noted that during the relationship detection process for payment users and associated users, the three processing methods—interaction type detection, interaction decay calculation, and relationship dissolution prediction—can be used simultaneously and sequentially. Furthermore, in the specific execution process, any one or any two of these three methods can be selected for relationship detection, depending on the specific needs. The execution order of these three methods can also be adjusted accordingly, using the adjusted order for relationship detection. Similarly, the execution order of any two of these methods can be adjusted during relationship detection, using the adjusted order for relationship detection.

[0162] It should also be noted that the interaction type detection, interaction attenuation calculation and relationship dissolution prediction processes provided in this embodiment are merely illustrative. The specific processing procedures and execution examples of interaction type detection, interaction attenuation calculation and relationship dissolution prediction can be found in the corresponding content provided in steps S104 to S108 of the above method embodiment, and will not be repeated here.

[0163] Step S1206: If the relationship detection fails, the protocol payment channel is marked, and a payment channel set carrying the protocol payment channel is sent to the user terminal.

[0164] In this embodiment, by marking the protocol payment channel, the payment user can perceive any abnormality or breakdown in the relationship between the associated user who opened the protocol payment channel and the payment user, thereby improving the payment success rate. For the associated user who opened the protocol payment channel to the payment user, the probability of the protocol payment channel being used and resulting in financial loss due to changes or termination of the user relationship is reduced, ensuring the safety of the associated user's funds.

[0165] In one optional implementation of this embodiment, the marking process for the protocol payment channel includes: marking the protocol payment channel as an abnormal payment state; and / or, downgrading the payment priority of the protocol payment channel based on the abnormal payment state.

[0166] Step S1208: Based on the payment processing request of the protocol payment channel sent by the user terminal, confirm the payment of the protocol payment channel for the associated user.

[0167] In practical implementation, to reduce the probability of financial loss due to the use of the agreement payment channel when user relationships change or are terminated, and to ensure the fund security of associated users, this embodiment further improves the payment success rate of paying users by processing payment instructions from associated users through payment confirmation. Specifically, in one optional implementation of this embodiment, payment confirmation for the agreement payment channel for the associated user includes: sending a payment confirmation message to the associated user and receiving a confirmation instruction from the payment confirmation message; and processing the payment through the agreement payment channel based on the confirmation instruction.

[0168] For example, in User A's payment channel list, if the payment priority of the "Intimate Payment" channel with User B is moved from first to last, User A's payment channel list after the adjustment will look like this: Figure 7 As shown, simultaneously, the Intimate Payment channel displays an error message: "Payment risk exists; this payment requires confirmation." An access interface, "Request Payment Confirmation from User B," is configured to request confirmation from User B for the current payment. If User A clicks the "Request Payment Confirmation from User B" interface, a payment confirmation will be generated. Figure 8 On the payment application page shown, after user A clicks the "OK" button, a payment confirmation message will be sent to user B. After user B triggers the payment confirmation message, they will enter... Figure 9 The payment confirmation page shown.

[0169] The following example illustrates the application of a payment detection and processing method provided in this embodiment in a close-knit payment scenario. Figure 11 The payment detection processing method provided in this embodiment will be further explained below. See [link to documentation]. Figure 11 The payment detection and processing method applied to intimate payment scenarios includes the following steps.

[0170] Step S1106: Based on the payment access request submitted by user A's user terminal, obtain the intimate payment channel opened by user B for intimate payment to user A.

[0171] Step S1108: Detect the interaction type based on the first interaction data between user A and user B; If the test fails, proceed to step S1110; If the test passes, it confirms that there is no payment risk in the intimate payment channel.

[0172] Step S1110: Perform interaction attenuation calculation based on the second interaction data between user A and user B; If the calculated interaction attenuation value is less than the attenuation threshold, proceed to step S1112. If the calculated interaction attenuation value is greater than or equal to the attenuation threshold, proceed to step S1114. Step S1112: Call the relationship prediction model to predict the relationship termination value between user A and user B; If the relationship termination value exceeds the relationship termination threshold, proceed to step S1114; If the relationship termination value does not exceed the relationship termination threshold, it is confirmed that there is no payment risk in the intimate payment channel.

[0173] Step S1114: If it is confirmed that there is a payment risk in the intimate payment channel, the intimate payment channel is marked.

[0174] Step S1116: Send a set of payment channels containing the marked intimate payment channels to user A's user terminal.

[0175] Step S1124: Send a payment confirmation message to user B according to the processing request for payment through the intimate payment channel.

[0176] After receiving the payment confirmation message, User B can click on the payment confirmation message to enter the payment confirmation page. If User B agrees to User A using Intimate Payment, User B can submit a confirmation instruction to the server by triggering the payment confirmation control configured on the payment confirmation page.

[0177] Step S1126: Based on the confirmation instruction, process the order payment through the intimate payment channel.

[0178] The following is an embodiment of a payment detection and processing device provided in this specification: In the above embodiments, a payment detection processing method is provided, and correspondingly, a payment detection processing device is also provided, which will be described below with reference to the accompanying drawings.

[0179] Reference Figure 13 The diagram shows a payment detection and processing device provided in this embodiment.

[0180] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0181] This embodiment provides a payment detection and processing device, including: The protocol payment channel acquisition module 1302 is configured to acquire the protocol payment channels opened by the associated user to the payment user; The interaction type detection module 1304 is configured to perform interaction type detection based on the first interaction data between the payment user and the associated user; The interaction attenuation calculation module 1306 is configured to perform interaction attenuation calculation based on the second interaction data between the payment user and the associated user if the detection fails. The relationship termination prediction module 1308 is configured to call the relationship prediction model to predict the termination of the relationship between the payment user and the associated user when the calculated interaction attenuation value is less than the attenuation threshold. The marking processing module 1310 is configured to mark the protocol payment channel if the relationship is determined to be terminated based on the prediction result.

[0182] The second payment detection and processing device embodiment provided in this specification is as follows: In the above embodiments, a second payment detection processing method is provided, and correspondingly, a second payment detection processing device is also provided, which will be described below with reference to the accompanying drawings.

[0183] Reference Figure 14 The diagram shows a payment detection and processing device provided in this embodiment.

[0184] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0185] This embodiment provides a payment detection and processing device that operates on a user terminal of a payment user. The device includes: The payment access request submission module 1402 is configured to submit a payment access request to the server based on the payment operation of the payment user. The payment channel display module 1404 is configured to receive and display a set of payment channels containing protocol payment channels sent by the server; the protocol payment channels are marked after the payment user and the associated user who has opened the protocol payment channel are subjected to interaction type detection, interaction attenuation calculation and relationship dissolution prediction. The payment processing request sending module 1406 is configured to send a payment processing request to the server if a payment instruction for the protocol payment channel is detected, so as to confirm the payment for the associated user through the protocol payment channel.

[0186] The third type of payment detection and processing device provided in this manual is exemplified as follows: In the above embodiments, a third payment detection processing method is provided, and correspondingly, a third payment detection processing device is also provided, which will be described below with reference to the accompanying drawings.

[0187] Reference Figure 15The diagram shows a payment detection and processing device provided in this embodiment.

[0188] Since the apparatus embodiments correspond to the method embodiments, the descriptions are relatively simple. For relevant parts, please refer to the corresponding descriptions of the method embodiments provided above. The apparatus embodiments described below are merely illustrative.

[0189] This embodiment provides a payment detection and processing device, which runs on a server, and the device includes: The protocol payment channel acquisition module 1502 is configured to acquire the protocol payment channel opened by the associated user to the payment user based on the payment access request submitted by the payment user's user terminal; The relationship detection and processing module 1504 is configured to perform relationship detection and processing between the payment user and the associated user based on the interaction data between the payment user and the associated user; the relationship detection and processing includes interaction type detection, interaction decay calculation and relationship termination prediction; The marking processing module 1506 is configured to mark the protocol payment channel if the relationship detection fails, and send a set of payment channels carrying the protocol payment channel to the user terminal; The payment confirmation module 1508 is configured to confirm the payment for the associated user through the payment channel based on the payment processing request sent by the user terminal.

[0190] This specification provides an example of a payment detection and processing device as follows: Corresponding to the payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a payment detection processing device, which is used to execute the payment detection processing method provided above. Figure 16 This is a schematic diagram of the structure of a payment detection and processing device provided for one or more embodiments of this specification.

[0191] This embodiment provides a payment detection and processing device, including: like Figure 16As shown, payment detection and processing devices can vary significantly due to differences in configuration or performance. They may include one or more processors 1601 and memory 1602, with memory 1602 storing one or more application programs or data. Memory 1602 can be temporary or persistent storage. The application programs stored in memory 1602 may include one or more modules (not shown), each module including a series of computer-executable instructions from the payment detection and processing device. Furthermore, processor 1601 may be configured to communicate with memory 1602, executing the series of computer-executable instructions in memory 1602 on the payment detection and processing device. The payment detection and processing device may also include one or more power supplies 1603, one or more wired or wireless network interfaces 1604, one or more input / output interfaces 1605, one or more keyboards 1606, etc.

[0192] In one specific embodiment, the payment detection processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the payment detection processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Obtain the protocol payment channels opened by the associated user for the paying user; Interaction type detection is performed based on the first interaction data between the payment user and the associated user; If the detection fails, an interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user. If the calculated interaction attenuation value is less than the attenuation threshold, the relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0193] The second type of payment detection and processing equipment provided in this manual is exemplified as follows: Corresponding to the second payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a second payment detection processing device, which is used to execute the payment detection processing method provided above. Figure 17 This is a schematic diagram of the structure of a second payment detection and processing device provided in one or more embodiments of this specification.

[0194] This embodiment provides a payment detection and processing device, including: like Figure 17 As shown, payment detection and processing devices can vary significantly due to differences in configuration or performance. They may include one or more processors 1701 and memory 1702, with memory 1702 storing one or more application programs or data. Memory 1702 can be temporary or persistent storage. The application programs stored in memory 1702 may include one or more modules (not shown), each module including a series of computer-executable instructions from the payment detection and processing device. Furthermore, processor 1701 may be configured to communicate with memory 1702, executing the series of computer-executable instructions in memory 1702 on the payment detection and processing device. The payment detection and processing device may also include one or more power supplies 1703, one or more wired or wireless network interfaces 1704, one or more input / output interfaces 1705, one or more keyboards 1706, etc.

[0195] In one specific embodiment, the payment detection processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the payment detection processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Based on the payment user's payment operation, a payment access request is submitted to the server; The system receives and displays a set of payment channels containing protocol payment channels from the server; the protocol payment channels are marked after the payment user and associated users who have activated the protocol payment channels have undergone interaction type detection, interaction decay calculation, and relationship dissolution prediction. If a payment instruction for the protocol payment channel is detected, a payment processing request is sent to the server to confirm the payment for the associated user through the protocol payment channel.

[0196] The third type of payment detection and processing equipment provided in this manual is exemplified as follows: Corresponding to the third payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a third payment detection processing device, which is used to execute the payment detection processing method provided above. Figure 18 This is a schematic diagram of the structure of a third payment detection and processing device provided in one or more embodiments of this specification.

[0197] This embodiment provides a payment detection and processing device, including: like Figure 18 As shown, payment detection and processing devices can vary significantly due to differences in configuration or performance. They may include one or more processors 1801 and memory 1802, with memory 1802 storing one or more application programs or data. Memory 1802 can be temporary or persistent storage. The application programs stored in memory 1802 may include one or more modules (not shown), each module including a series of computer-executable instructions from the payment detection and processing device. Furthermore, processor 1801 may be configured to communicate with memory 1802, executing the series of computer-executable instructions stored in memory 1802 on the payment detection and processing device. The payment detection and processing device may also include one or more power supplies 1803, one or more wired or wireless network interfaces 1804, one or more input / output interfaces 1805, one or more keyboards 1806, etc.

[0198] In one specific embodiment, the payment detection processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the payment detection processing device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Based on the payment access request submitted by the user terminal of the payment user, obtain the protocol payment channel opened by the associated user to the payment user; Based on the interaction data between the payment user and the associated user, a relationship detection process is performed between the payment user and the associated user; the relationship detection process includes interaction type detection, interaction decay calculation, and relationship termination prediction. If the relationship detection fails, the protocol payment channel is marked, and a payment channel set carrying the protocol payment channel is sent to the user terminal; Based on the payment processing request sent by the user terminal for the protocol payment channel, payment confirmation is performed for the associated user through the protocol payment channel.

[0199] This specification provides an example of a storage medium as follows: Corresponding to the payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a storage medium.

[0200] The storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed by a processor, implement the following process: Obtain the protocol payment channels opened by the associated user for the paying user; Interaction type detection is performed based on the first interaction data between the payment user and the associated user; If the detection fails, an interaction attenuation calculation is performed based on the second interaction data between the payment user and the associated user. If the calculated interaction attenuation value is less than the attenuation threshold, the relationship prediction model is invoked to predict the termination of the relationship between the paying user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

[0201] It should be noted that the embodiment of a storage medium in this specification and the embodiment of a payment detection processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0202] The second type of storage medium provided in this specification is as follows: Corresponding to the second payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a second storage medium.

[0203] The storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed by a processor, implement the following process: Based on the payment user's payment operation, a payment access request is submitted to the server; The system receives and displays a set of payment channels containing protocol payment channels from the server; the protocol payment channels are marked after the payment user and associated users who have activated the protocol payment channels have undergone interaction type detection, interaction decay calculation, and relationship dissolution prediction. If a payment instruction for the protocol payment channel is detected, a payment processing request is sent to the server to confirm the payment for the associated user through the protocol payment channel.

[0204] It should be noted that the embodiments of the second type of storage medium in this specification and the embodiments of the second type of payment detection processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0205] The third storage medium embodiment provided in this specification is as follows: Corresponding to the third payment detection processing method described above, based on the same technical concept, one or more embodiments of this specification also provide a third storage medium.

[0206] The storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed by a processor, implement the following process: Based on the payment access request submitted by the user terminal of the payment user, obtain the protocol payment channel opened by the associated user to the payment user; Based on the interaction data between the payment user and the associated user, a relationship detection process is performed between the payment user and the associated user; the relationship detection process includes interaction type detection, interaction decay calculation, and relationship termination prediction. If the relationship detection fails, the protocol payment channel is marked, and a payment channel set carrying the protocol payment channel is sent to the user terminal; Based on the payment processing request sent by the user terminal for the protocol payment channel, payment confirmation is performed for the associated user through the protocol payment channel.

[0207] It should be noted that the embodiments of the third storage medium in this specification and the embodiments of the third payment detection processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can be referred to the implementation of the corresponding method described above, and the repeated parts will not be described again.

[0208] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0209] In the 1930s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many improvements to the methodology today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that an improvement to the methodology cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0210] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0211] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0212] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0213] Those skilled in the art will understand that one or more embodiments of this specification can be provided as a method, system, or computer program product. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this specification may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0214] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0215] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0216] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0217] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0218] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0219] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0220] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0221] One or more embodiments of this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a particular task or implement a particular abstract data type. One or more embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0222] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0223] The above description is merely an embodiment of this document and is not intended to limit the scope of this document. Various modifications and variations can be made to this document by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this document should be included within the scope of the claims of this document.

Claims

1. A payment detection processing method, comprising: Obtain the protocol payment channel opened by the associated user for the payment user; the protocol payment channel is bound to the payment account of the associated user; Interaction attenuation calculation is performed based on the interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated user are obtained and input into the relationship prediction model to perform the relationship unprediction between the payment user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

2. The payment detection processing method according to claim 1, wherein the interaction data includes graph structure interaction data stored in a graph database; in, The data nodes in the graph structure interaction data correspond to the user identifier of the payment user and the user identifier of the associated user. The data connections in the graph structure interaction data correspond to a data sequence composed of the user identifier of the payment user, the user identifier of the associated user, the interaction type, and / or time information.

3. The payment detection processing method according to claim 1, wherein the step of calculating interaction attenuation based on the interaction data between the payment user and the associated user includes: Based on the total number of interactions contained in the interaction data, calculate the cumulative interaction frequency between the payment user and the associated user; Based on the average activity and interaction interval of the paying user and the associated user contained in the interaction data, a time decay score is calculated; The interaction decay value is calculated based on the cumulative interaction frequency and the time decay fraction.

4. The payment detection processing method according to claim 1, after the step of performing the interaction attenuation calculation based on the interaction data between the payment user and the associated user if the detection fails, further includes: If the calculated interaction attenuation value is greater than or equal to the attenuation threshold, the protocol payment channel is marked.

5. The payment detection processing method according to claim 1, wherein the relationship termination prediction includes: The predicted value of the relationship between the payment user and the associated user is used as the prediction result.

6. The payment detection processing method according to claim 5, wherein the relationship prediction model comprises a first neural network, a second neural network, and a third neural network; Accordingly, the predicted value for resolving the relationship between the payment user and the associated user includes: The first concatenated vector from the vector set of the payment users and the second concatenated vector from the vector set of the associated users are respectively input into the corresponding first neural network for vector transformation to obtain the transformed vector; The attention weights of the transformation vector are calculated using the second neural network, and normalized weights are calculated based on the calculated attention weights. The weighted vector is calculated based on the normalized weights and the transformation vector, and then the weighted vector is input into the third neural network for calculation to obtain the relationship dissolution value.

7. The payment detection processing method according to claim 6, before the sub-step of inputting the first concatenated vector in the vector set of the payment user and the second concatenated vector in the vector set of the associated user into the corresponding first neural network for vector transformation to obtain the transformed vector, further includes: The initial feature vector and initial relation vector of the payment user are vector-mapped to obtain the first feature mapping vector and the first relation mapping vector; The first concatenated vector is obtained by concatenating the first feature mapping vector and the first relation mapping vector. And / or, The initial feature vector and initial relationship vector of the associated user are vector-mapped to obtain the second feature mapping vector and the second relationship mapping vector. The second concatenated vector is obtained by concatenating the second feature mapping vector and the second relation mapping vector.

8. The payment detection processing method according to claim 7, wherein the initial feature vector of the payment user is obtained in the following manner: Obtain the first feature vector of the payment user, the second feature vector of the associated user, and the third feature vector of the candidate associated user of the payment user; The first feature vector, the second feature vector, and the third feature vector are concatenated to obtain the initial feature vector of the payment user.

9. The payment detection processing method according to claim 7, wherein the initial relationship vector of the payment user is obtained in the following manner: Obtain the first interaction relationship vector between the payment user and the associated user, and the second interaction relationship vector between the payment user and the candidate associated user; The first interaction relationship vector and the second interaction relationship vector are concatenated to obtain the initial relationship vector of the payment user.

10. The payment detection processing method according to claim 6, wherein the attention weight comprises: The first attention weight between the paying user and the candidate associated users of the paying user, and the second attention weight between the associated user and the candidate associated users of the paying user; Accordingly, the step of calculating the normalized weights based on the calculated attention weights includes: Calculate the sum of the weights of the first attention weight and the second attention weight; The ratio of the first attention weight to the sum of the weights is calculated as the normalized weight.

11. The payment detection processing method according to claim 1, after obtaining the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated users and inputting them into the relationship prediction model to perform the relationship unprediction operation between the payment user and the associated users, it further includes: If the prediction results determine that the relationship between the paying user and the associated user has not been terminated, then the payment status of the protocol payment channel is confirmed to be normal.

12. The payment detection processing method according to claim 1, wherein the marking process for the protocol payment channel includes: Mark the aforementioned payment channel as an abnormal payment status; The payment priority of the protocol payment channel is downgraded based on the abnormal payment status.

13. The payment detection processing method according to claim 1, after the step of marking the protocol payment channel if the relationship is determined to be terminated based on the prediction result, further includes: According to the payment instructions of the payment channel in the agreement, a payment confirmation message is sent to the associated user; If a confirmation instruction from the payment confirmation message is detected, payment processing is performed based on the payment channel of the protocol.

14. A payment detection processing method, applied to a user terminal of a payment user, the method comprising: Based on the payment user's payment operation, a payment access request is submitted to the server; Receive and display the payment channel set containing the protocol payment channels sent by the server; The protocol payment channel is linked to the payment account of the associated user; the protocol payment channel is marked after performing interaction attenuation calculation and relationship dissolution prediction on the payment user and the associated user who has opened the protocol payment channel; The relationship termination prediction includes: obtaining the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated users, and inputting them into the relationship prediction model to perform relationship termination prediction between the payment user and the associated users; If a payment instruction for the protocol payment channel is detected, a payment processing request is sent to the server to confirm the payment for the associated user through the protocol payment channel.

15. The payment detection processing method according to claim 14, wherein the marking process includes: Mark the aforementioned payment channel as an abnormal payment status; The payment priority of the protocol payment channel is downgraded based on the abnormal payment status. Accordingly, the payment confirmation for the associated user via the payment channel includes: Send a payment confirmation message to the associated user and receive a confirmation instruction from the payment confirmation message; Based on the confirmation instruction, payment is processed through the agreed payment channel.

16. The payment detection processing method according to claim 14, further comprising: Interaction type detection; The interaction type detection is implemented in the following way: Detect whether the interaction type carried in the first interaction data between the payment user and the associated user is a negative interaction type; If the interaction is negative, the payment channel of the protocol will be marked. If it is a positive interaction type, check whether the generation time of the first interaction data is greater than a preset time threshold. If so, perform the interaction attenuation calculation.

17. The payment detection processing method according to claim 14, wherein the interaction attenuation calculation is implemented in the following manner: Based on the total number of interactions contained in the second interaction data between the payment user and the associated user, the cumulative interaction frequency between the payment user and the associated user is calculated. Based on the average activity and interaction interval of the payment user and the associated user contained in the second interaction data, a time decay score is calculated; The interaction decay value is calculated based on the cumulative interaction frequency and the time decay fraction, and the relationship disintegration prediction is performed if the interaction decay value is less than the decay threshold.

18. The payment detection processing method according to claim 14, wherein the relationship termination prediction is implemented in the following manner: The first concatenated vector from the vector set of the payment users and the second concatenated vector from the vector set of the associated users are respectively input into the corresponding first neural network for vector transformation to obtain the transformed vector; The attention weights of the transformation vector are calculated using a second neural network, and normalized weights are calculated based on the calculated attention weights. The weighted vector is calculated based on the normalized weights and feature vectors, and the weighted vector is input into the third neural network for calculation. The labeling process is performed when the obtained relation dissolution value is greater than a preset threshold.

19. A payment detection processing method, applied to a server, the method comprising: Based on the payment access request submitted by the user terminal of the payment user, obtain the protocol payment channel opened by the associated user for the payment user, and the protocol payment channel is bound to the payment account of the associated user; Based on the interaction data between the payment user and the associated user, a relationship detection process is performed between the payment user and the associated user; the relationship detection process includes interaction decay calculation and relationship dissolution prediction; If the relationship detection fails, the protocol payment channel is marked, and a payment channel set carrying the protocol payment channel is sent to the user terminal; Based on the payment processing request sent by the user terminal for the protocol payment channel, payment confirmation is performed for the associated user through the protocol payment channel.

20. A payment detection and processing device, comprising: The protocol payment channel acquisition module is configured to acquire the protocol payment channel opened by the associated user for the payment user, wherein the protocol payment channel is bound to the payment account of the associated user; The interaction attenuation calculation module is configured to perform interaction attenuation calculation based on the interaction data between the payment user and the associated user; The relationship dissolution prediction module is configured to, when the calculated interaction decay value is less than the decay threshold, acquire the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated user, and input them into the relationship prediction model to predict the dissolution of the relationship between the payment user and the associated user. The marking processing module is configured to mark the protocol payment channel if the relationship is determined to be terminated based on the prediction result.

21. A payment detection and processing device, operating on a user terminal of a payment user, the device comprising: The payment access request submission module is configured to submit a payment access request to the server based on the payment operation of the payment user; The payment channel display module is configured to receive and display a set of payment channels containing protocol payment channels sent by the server; the protocol payment channels are bound to the payment accounts of associated users; the protocol payment channels are marked after interaction attenuation calculation and relationship dissolution prediction are performed on the payment users and associated users who have activated the protocol payment channels; The relationship termination prediction includes: obtaining the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated users, and inputting them into the relationship prediction model to perform relationship termination prediction between the payment user and the associated users; The payment processing request sending module is configured to send a payment processing request to the server if a payment instruction for the protocol payment channel is detected, so as to confirm the payment for the associated user through the protocol payment channel.

22. A payment detection and processing device, operating on a server, the device comprising: The protocol payment channel acquisition module is configured to acquire the protocol payment channel opened by the associated user to the payment user based on the payment access request submitted by the payment user's user terminal, and the protocol payment channel is bound to the payment account of the associated user; The relationship detection and processing module is configured to perform relationship detection and processing between the payment user and the associated user based on the interaction data between the payment user and the associated user; The relationship detection process includes interaction decay calculation and relationship dissolution prediction; The marking processing module is configured to mark the protocol payment channel if the relationship detection fails, and send a set of payment channels carrying the protocol payment channel to the user terminal; The payment confirmation module is configured to confirm the payment for the associated user through the payment channel based on the payment processing request sent by the user terminal.

23. A payment detection and processing device, comprising: processor; And, a memory configured to store computer-executable instructions, which, when executed, cause the processor to: Obtain the protocol payment channel opened by the associated user for the payment user; the protocol payment channel is bound to the payment account of the associated user; Interaction attenuation calculation is performed based on the interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated user are obtained and input into the relationship prediction model to perform the relationship unprediction between the payment user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

24. A storage medium for storing computer-executable instructions, which, when executed by a processor, perform the following process: Obtain the protocol payment channel opened by the associated user for the payment user; the protocol payment channel is bound to the payment account of the associated user; Interaction attenuation calculation is performed based on the interaction data between the payment user and the associated user; If the calculated interaction attenuation value is less than the attenuation threshold, the first user data of the first associated user set of the payment user and the second user data of the second associated user set of the associated user are obtained and input into the relationship prediction model to perform the relationship unprediction between the payment user and the associated user. If the relationship is determined to be terminated based on the prediction results, the payment channel of the agreement will be marked.

Images