Order Allocation Processing Method and System Based on Decision Tree Algorithm

Abstract

The present invention provides an order allocation processing method and system based on a decision tree algorithm. By determining an order allocation channel sequence based on the decision tree algorithm and constructing an order allocation knowledge network, it can effectively integrate the association information between service orders and order allocation channels, providing a comprehensive and systematic knowledge framework for order allocation. By screening out reference order allocation channels that conform to the service logic in the order allocation knowledge network and calculating comprehensive cost parameters in combination with predicted allocation instance data to determine the target order allocation channel, it realizes a more scientific and accurate order allocation, improves the rationality and efficiency of order allocation, reduces the allocation cost, and helps to improve the overall service quality and operational efficiency.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to an order allocation processing method and system based on a decision tree algorithm. Background Art

[0002] In the current era of rapid digital and information development, the number of orders in the service industry has increased explosively. The efficiency and rationality of order allocation are crucial for the operation and development of enterprises. Traditional order allocation methods often rely on manual experience or simple rule matching, and there are many limitations.

[0003] On the one hand, the method of manually allocating orders is inefficient and difficult to handle the processing requirements of a large number of orders. With the continuous expansion of the business scale and the sharp increase in the number of orders, manual processing becomes overwhelmed and prone to problems such as untimely and inaccurate allocation, thus affecting the customer experience and the service quality of the enterprise.

[0004] On the other hand, the order allocation method based on simple rule matching lacks flexibility and intelligence. This method usually can only allocate orders according to pre-set fixed rules and cannot fully consider the diverse characteristics and complex business logics of service orders. For example, different service orders may have different service requirements, customer preferences, time requirements, etc., and simple rule matching is difficult to comprehensively analyze these factors, resulting in the order allocation result may not conform to the actual service scenario, unable to achieve the optimal allocation of resources, and increasing the operating cost of the enterprise.

[0005] In addition, the existing order allocation methods have poor adaptability in the face of dynamic business environments and data. Factors such as market demand and customer behavior are constantly changing, and traditional methods are difficult to make timely adjustments and optimizations based on real-time data, unable to meet the requirements of enterprises for the accuracy and efficiency of order allocation in a complex and changeable market environment. Summary of the Invention

[0006] In view of the above-mentioned problems, in combination with the first aspect of the present invention, embodiments of the present invention provide an order allocation processing method based on a decision tree algorithm, and the method includes:

[0007] Obtain a service order sequence, obtain the attention tag data corresponding to the service orders in the service order sequence, and based on the attention tag data, determine the order allocation channel sequence associated with the service order sequence through a decision tree algorithm;

[0008] Construct index association information for the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence, and construct an order allocation knowledge network based on the service order sequence, the order allocation channel sequence, and the index association information; a is a positive integer;

[0009] In the order allocation knowledge network, output the internal network path corresponding to the a-th service order as an order network path sequence, and output the basic order allocation channels corresponding to the internal network paths that conform to the service logic in the order network path sequence as the reference order allocation channels corresponding to the a-th service order;

[0010] Obtain the predicted allocation instance data between each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, and based on the predicted allocation instance data corresponding to the reference order allocation channels of each service order, obtain the comprehensive cost parameters corresponding to the reference order allocation channels of each service order, and output the reference order allocation channel corresponding to the smallest comprehensive cost parameter as the target order allocation channel;

[0011] Perform order allocation on the a-th service order based on the target order allocation channel.

[0012] On the other hand, an embodiment of the present invention further provides an order allocation processing system based on a decision tree algorithm, including a processor and a machine-readable storage medium. The machine-readable storage medium is connected to the processor. The machine-readable storage medium is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the machine-readable storage medium to implement the above method.

[0013] Based on the above aspects, the embodiments of the present application can effectively integrate the association information between service orders and order allocation channels by determining the order allocation channel sequence based on the decision tree algorithm and constructing an order allocation knowledge network, providing a comprehensive and systematic knowledge architecture for order allocation. By screening out the reference order allocation channels that conform to the service logic in the order allocation knowledge network and calculating the comprehensive cost parameters in combination with the predicted allocation instance data to determine the target order allocation channel, more scientific and accurate order allocation is achieved, the rationality and efficiency of order allocation are improved, the allocation cost is reduced, and it helps to improve the overall service quality and operation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a schematic execution flowchart of an order allocation processing method based on a decision tree algorithm provided by an embodiment of the present invention.

[0015] Figure 2It is a schematic diagram of the hardware architecture of an order allocation processing system based on a decision tree algorithm provided by an embodiment of the present invention. Detailed implementation manners

[0016] The present invention will be specifically described below with reference to the accompanying drawings of the specification. Figure 1 It is a schematic flowchart of an order allocation processing method based on a decision tree algorithm provided by an embodiment of the present invention. The order allocation processing method based on the decision tree algorithm will be introduced in detail below.

[0017] Step S110: Obtain a service order sequence, obtain the attention tag data corresponding to the service orders in the service order sequence, and based on the attention tag data, determine the order allocation channel sequence associated with the service order sequence through a decision tree algorithm.

[0018] In this embodiment, when a financial service institution platform processes e-commerce service orders, it is first necessary to obtain a service order sequence. For example, an e-commerce platform under a large financial service institution receives a large number of service orders every day. These orders form a service order sequence according to the receiving time sequence or according to rules such as order types. Suppose this sequence includes multiple orders such as Order A, Order B, and Order C.

[0019] For these service orders, each order has corresponding attention tag data. Taking Order A as an example, its attention tag data may include the customer's credit rating (such as high credit rating, medium credit rating, low credit rating), the order amount range (such as small orders, medium-sized orders, large orders), the service type (such as payment service, refund service, account query service, etc.), and the customer's membership level (such as ordinary member, silver card member, gold card member, etc.).

[0020] Based on this attention tag data, the order allocation channel sequence associated with the service order sequence is determined through a decision tree algorithm. For example, the decision tree algorithm will first divide according to the service type of the order. If it is an order of the payment service type, it may further determine the order allocation channel according to the amount range and the customer's credit rating. For an order of a small payment and a high-credit customer, it may be assigned to the fast payment channel sequence; while for an order of a large payment and a medium-credit customer, it may be assigned to the payment channel sequence that requires manual review. For an order of the refund service type, if it is an order of a silver card member and a small refund, it may be assigned to the automatic refund channel sequence; while for an order of a gold card member and a large refund, it may be assigned to the special advanced customer service processing refund channel sequence. Through such hierarchical decision tree analysis, the order allocation channel sequence associated with the entire service order sequence is finally determined.

[0021] Step S120: Construct index association information for the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence, and construct an order allocation knowledge network based on the service order sequence, the order allocation channel sequence, and the index association information. a is a positive integer.

[0022] Suppose in the above service order sequence, the a-th service order is order B. First, obtain the order attribute reference template associated with the service order sequence by the financial service institution platform. This order attribute reference template contains the reference methods and formats of various attribute information of the order, such as the definitions and storage formats of attributes such as order number, order placement time, service request content, etc.

[0023] Construct a service order record corresponding to order B based on this order attribute reference template. This service order record details various attribute information of order B. For example, the number of order B is 12345, the order placement time is 10:00 on October 1, 2023, and the service request content is to pay a commodity fee of 500 yuan, etc.

[0024] Then construct index association information for the service order record corresponding to order B and the basic order allocation channel of order B in the order allocation channel sequence. For example, if the basic order allocation channel assigned to order B is the quick payment channel, then the index association information may establish an association between the order number of order B and the channel number of the quick payment channel, and at the same time associate information such as order placement time and payment amount for subsequent query and processing.

[0025] Finally, use the service order records corresponding to all service orders in the service order sequence and the order allocation channel sequence as entity objects, and use the index association information as the internal network path to generate an order allocation knowledge network. This order allocation knowledge network is like a huge relational graph, where each service order record and order allocation channel are nodes, and the index association information is the path connecting these nodes, completely describing the relationship between service orders and order allocation channels.

[0026] Step S130: Output the internal network path corresponding to the a-th service order in the order allocation knowledge network as an order network path sequence, and output the basic order allocation channels corresponding to the internal network paths that conform to the service logic in the order network path sequence as the reference order allocation channels corresponding to the a-th service order.

[0027] In the constructed order allocation knowledge network, for order B (i.e., the a-th service order), its corresponding internal network path is output as an order network path sequence. This order network path sequence contains all the path information from order B to its associated order allocation channels (such as the fast payment channel), including the intermediate nodes passed through (such as the order verification node, payment risk assessment node, etc.) and the relationships connecting these nodes (such as the sequence, conditional judgment, etc.).

[0028] Obtain the service efficiency data corresponding to each internal network path in the order network path sequence. Taking one of the internal network paths as an example, this path contains an order verification node, a payment risk assessment node, and a fast payment channel node. The calculation of its service efficiency data is as follows:

[0029] Path length indicator: There are 3 connections from the order verification node to the fast payment channel node, so the path length is 3.

[0030] Number of nodes indicator in the internal network path: This path contains 3 nodes, so the number of nodes is 3.

[0031] Connection strength indicator between nodes: The historical interaction frequency between the order verification node and the payment risk assessment node is relatively high, the interaction success rate is 95%, and the average interaction response time is 2 seconds; the historical interaction frequency between the payment risk assessment node and the fast payment channel node is also relatively high, the interaction success rate is 98%, and the average interaction response time is 1 second. The connection strength indicator is obtained according to a specific calculation method (such as weighted calculation).

[0032] Average processing time indicator in the historical service record: Statistically calculate the average time for these 3 nodes to process similar service orders (such as payment orders with similar amounts) in history. Assume that the average processing time of the order verification node is 5 seconds, the average processing time of the payment risk assessment node is 3 seconds, and the average processing time of the fast payment channel node is 2 seconds. The average processing time indicator is obtained through comprehensive calculation.

[0033] Processing success rate indicator in the historical service record: Calculate the success ratio of these 3 nodes to process similar service orders in history. Assume that the success ratio of the order verification node is 90%, the success ratio of the payment risk assessment node is 92%, and the success ratio of the fast payment channel node is 95%. The processing success rate indicator is obtained through comprehensive calculation.

[0034] Customer feedback data indicator: Collect the evaluation data of customers on the services of these 3 nodes. For example, the customer satisfaction of the order verification node is 80%, the customer satisfaction of the payment risk assessment node is 85%, and the customer satisfaction of the fast payment channel node is 90%. The customer feedback data indicator is obtained through comprehensive analysis.

[0035] Determine the wandering priorities corresponding to each internal network path based on these service efficiency data. For example, according to a preset calculation rule (such as weighted summation of various metrics), calculate the scores of each path, and the path with a higher score has a higher wandering priority.

[0036] Compare the basic order allocation channels and service logics corresponding to each internal network path in the order network path sequence according to the wandering priorities. Assume that the service logic requires that the processing time of the payment order be within 10 seconds and the success rate be above 90%. If the basic order allocation channel (such as the fast payment channel) corresponding to a certain internal network path meets this service logic, then output this fast payment channel as the reference order allocation channel corresponding to order B.

[0037] Step S140: Obtain the predicted allocation instance data between each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, and based on the predicted allocation instance data corresponding to the reference order allocation channels of each service order, obtain the comprehensive cost parameters corresponding to the reference order allocation channels of each service order, and output the reference order allocation channel corresponding to the smallest comprehensive cost parameter as the target order allocation channel.

[0038] In this embodiment, obtain the predicted allocation instance data between each service order (such as order A, order B, order C, etc.) in the service order sequence and the reference order allocation channel (such as the fast payment channel) corresponding to order B.

[0039] First, obtain the order node data corresponding to each service order. Taking order A as an example, its order node data includes that the order type is a payment order, the order status is pending, the order priority is normal priority, the order creation time is 15:00 on September 30, 2023, the order expected completion time is 12:00 on October 1, 2023, and the customer information associated with the order (such as the customer name is Zhang San and the credit rating is high credit rating, etc.).

[0040] Based on these order node data and the reference order allocation channel (fast payment channel) corresponding to order B, determine the instance allocation search range and obtain the service transfer data therein.

[0041] Extract the order node data corresponding to each service order from the service order sequence to form an ordered set of order node data.

[0042] Extract the key feature information for the fast payment channel, such as the channel type is a payment channel, the processing capacity is 10 orders per minute, the historical service efficiency is an average processing time of 5 seconds, the service response time is within 3 seconds, the current load status is 50% (that is, the number of orders being processed currently accounts for 50% of its processing capacity), and the supported service type is small - value payment, etc. Integrate these key feature information to generate a feature vector.

[0043] Based on the order node data set and the feature vector, initially construct an instance allocation search range. For example, filter out all service order node data of the payment type and small - value payment according to the channel type and service type; set the service efficiency threshold to an average processing time of 8 seconds according to the processing capacity and historical service efficiency, and filter out the service order node data whose service efficiency is not less than this threshold; set the response time range to 25 seconds and the load status range to 30% - 70% according to the service response time and the current load status, and finally filter out the service order node data whose service response time is within this range and the load status is within this range from the second - filtered service order node data. Take the time period or the set of processing nodes corresponding to the finally - filtered service order node data as the initial construction result of the instance allocation search range.

[0044] Dynamically adjust the initially constructed instance allocation search range. For example, according to the historical service efficiency information of the fast payment channel, if it is found that its service efficiency shows an upward trend in the recent period, expand the range of the instance allocation search range according to the first preset expansion strategy; if the load corresponding to the current load status information is less than the first load (assuming the first load is 40%), expand the range of the instance allocation search range according to the second preset expansion strategy; at the same time, according to the priority information of the service orders in the order node data set, adjust the priority of the instance allocation search range, such as increasing the weight of the instance allocation search range corresponding to high - priority orders.

[0045] Based on the instance allocation search range after dynamic adjustment, determine the service transfer data acquisition strategy. Determine the data source information of the service transfer data, such as obtaining data from the historical service record database of financial service institutions, the real - time service monitoring system, and the customer service feedback system of e - commerce platforms. According to the range of the instance allocation search range, set the acquisition conditions of the service transfer data, such as obtaining service transfer data between September 25, 2023 and October 1, 2023, with the service type being payment service, the processing node being payment - related nodes, and the customer type being high - credit - level customers. The acquisition method is batch acquisition. At the same time, determine the corresponding data encryption and desensitization strategies, as well as determine the storage and management method of the service transfer data.

[0046] Obtain the corresponding service transfer data according to the service transfer data acquisition strategy, match it with the instance allocation search range, filter out the service transfer data that meets the instance allocation search range, extract and analyze the features of the service transfer data that meets the instance allocation search range, and generate the feature analysis result of the service transfer data.

[0047] Based on the feature analysis result of the service transfer data, filter and evaluate the instances in the service transfer data, optimize and recommend the set of service transfer data instances after filtering and evaluation, and generate the optimized set of service transfer data instances.

[0048] Assume that the instance allocation limit requirements include service channel type information (such as the requirement is the payment channel) and service response time limit information (such as the requirement is to respond within 5 seconds). Output the order node data corresponding to each service order in the service order sequence as the initial order node, and output the reference order allocation channel (fast payment channel) corresponding to order B as the termination order node, and perform instance retrieval in the service transfer data to generate the basic instance sequence. If a certain basic instance K in the basic instance sequence does not meet the service channel type information (such as it is not the payment channel), or does not meet the service response time limit information (such as the response time exceeds 5 seconds), then delete this basic instance K from the basic instance sequence, and output the remaining basic instances in the basic instance sequence as the predicted allocation instance data.

[0049] Based on the predicted allocation instance data corresponding to the reference order allocation channel (fast payment channel) of each service order, obtain the comprehensive cost parameter corresponding to the reference order allocation channel of each service order. The calculation of the comprehensive cost parameter may involve multiple factors, such as processing cost, risk cost, impact on customer satisfaction, etc. For example, for a certain order, there may be certain handling fees (processing cost) for processing through the fast payment channel, and there is also a very small payment risk (risk cost), but the customer satisfaction is relatively high (has a good impact on customer satisfaction). Combine these factors to calculate the comprehensive cost parameter. Output the reference order allocation channel corresponding to the smallest comprehensive cost parameter as the target order allocation channel.

[0050] Step S150, perform order allocation on the a-th service order based on the target order allocation channel.

[0051] In this embodiment, perform order allocation on order B based on the determined target order allocation channel (such as the fast payment channel). The financial service institution platform directs the payment request of order B to the fast payment channel, and the payment system, risk control system, etc. related to the fast payment channel process order B according to their respective processes, such as performing payment verification, risk assessment, fund transfer and other operations to ensure that the service of order B can be completed efficiently, accurately and safely.

[0052] Based on the above steps, in the embodiments of the present application, by determining the order allocation channel sequence based on the decision tree algorithm and constructing the order allocation knowledge network, the correlation information between service orders and order allocation channels can be effectively integrated, providing a comprehensive and systematic knowledge framework for order allocation. By screening out the reference order allocation channels that conform to the service logic in the order allocation knowledge network and calculating the comprehensive cost parameters in combination with the predicted allocation instance data to determine the target order allocation channel, a more scientific and accurate order allocation is achieved, improving the rationality and efficiency of order allocation, reducing the allocation cost, and helping to improve the overall service quality and operational efficiency.

[0053] In a possible implementation manner, step S110 includes:

[0054] Step S111, based on the channel association knowledge data in the concerned tag data, determine the order allocation search service domain, and call the business logic tool to obtain the service channel data within the order allocation search service domain.

[0055] Step S112, obtain the service tag knowledge data in the concerned tag data, determine the service channels that match the service tag knowledge data in the service channel data within the order allocation search service domain, and load the service channels into the order allocation channel sequence associated with the service order sequence.

[0056] In this embodiment, in the e-commerce service operation of a financial service institution, each service order carries rich concerned tag data. The channel association knowledge data in these concerned tag data is of great significance. For example, the channel association knowledge data may contain the potential relationship rules between different types of service orders and specific service channels. Based on these channel association knowledge data, the order allocation search service domain can be determined. Taking the payment order on an e-commerce platform as an example, if the channel association knowledge data indicates that high-value orders are associated with payment channels of a specific security level, then an order allocation search service domain centered on high-security payment services can be determined. Then, call the business logic tool to obtain the service channel data within this order allocation search service domain. The business logic tool is a tool developed within the financial service institution according to business rules, which can screen out the required service channel data from the huge service channel database. For example, this tool may screen out the relevant channel data within the high-security payment service domain from various service channels such as payment channels and refund channels according to the set security level, service type, etc.

[0057] Next, obtain the service label knowledge data in the attention label data. The service label knowledge data is information describing the specific service requirement characteristics of the service order. For example, for an e-commerce service order, the service label knowledge data may include whether the service is a one-time payment, installment payment, or refund operation, whether it is a domestic payment or a cross-border payment, etc. Among the service channel data within the order allocation search service domain that has been obtained, determine the service channels that match this service label knowledge data. If the service label knowledge data indicates a domestic small one-time payment, then find the service channels suitable for domestic small one-time payments in the previously filtered service channel data, such as certain fast payment channels in cooperation with domestic banks. Finally, load the found service channels into the order allocation channel sequence associated with the service order sequence. This order allocation channel sequence is an ordered set that contains the possible allocation channels for each order determined according to different service order characteristics, laying the foundation for the subsequent order allocation process.

[0058] In a possible implementation manner, step S120 includes:

[0059] Step S121, obtain the order attribute reference template associated with the service order sequence, and construct a service order record corresponding to the service order in the service order sequence based on the order attribute reference template.

[0060] Step S122, construct index association information for the service order record corresponding to the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence.

[0061] Step S123, use the service order records corresponding to the service orders in the service order sequence and the order allocation channel sequence as entity objects, and use the index association information as the internal network path to generate the order allocation knowledge network.

[0062] When a financial service institution processes an e-commerce service order, it first needs to obtain an order attribute reference template associated with the service order sequence. This order attribute reference template is a standardized definition and reference method for various attribute information of the service order. For example, it stipulates the storage format and reference rules of attributes such as order number, order placement time, service type, and customer identity identifier in the database. Based on this order attribute reference template, a service order record corresponding to the service order in the service order sequence is constructed. Taking a specific e-commerce service order as an example, assume the order number is 56789, the order placement time is 14:00 on November 10, 2023, the service type is cross-border payment, and the customer identity identifier is customer number 123456. According to the order attribute reference template, these information will be constructed into a complete service order record in the specified format, which details the key attributes of the service order.

[0063] Then, index association information is constructed for the service order record corresponding to the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence. Assume the a-th service order is the cross-border payment order with the order number 56789 mentioned above, and its basic order allocation channel in the order allocation channel sequence is a certain international payment channel. The index association information will associate the key information in this service order record, such as order number and customer identity identifier, with the relevant identification information of the international payment channel. This association may include establishing associated key-value pairs in the database or establishing specific pointing relationships in the data structure, etc., so as to quickly query and obtain relevant information.

[0064] Finally, using the service order records corresponding to the service orders in the service order sequence and the order allocation channel sequence as entity objects, and the index association information as the internal network path, an order allocation knowledge network is generated. In the e-commerce service order processing system of this financial service institution, all service order records and order allocation channel sequences are entity objects in the network. The service order records contain the detailed information of each service order, and the order allocation channel sequence contains the possible allocation channels for different orders. The index association information is like a bridge connecting these entity objects, forming the internal network path. For example, the customer identity identifier in a service order record is connected to the specific identifier of a certain order allocation channel through the index association information, forming a complete order allocation knowledge network. This order allocation knowledge network can comprehensively reflect the complex relationship between service orders and order allocation channels, providing a solid data foundation for subsequent order allocation decision-making, path finding, and efficiency optimization operations. In this order allocation knowledge network, according to various attribute information of the service order, the appropriate order allocation channel can be quickly located through the index association information. At the same time, according to the relevant information of the order allocation channel, the corresponding service order record can be traced back, thus realizing the efficient integration and utilization of information.

[0065] In a possible implementation manner, step S130 includes:

[0066] Step S131, obtaining the service efficiency data corresponding to each internal network path in the order network path sequence, determining the walking priority corresponding to each internal network path in the order network path sequence based on the service efficiency data, and comparing the basic order allocation channels corresponding to each internal network path in the order network path sequence with the service logic according to the walking priority.

[0067] Step S132, if there is a basic order allocation channel corresponding to an internal network path in the order network path sequence that conforms to the service logic, output the basic order allocation channel that conforms to the service logic as the reference order allocation channel corresponding to the a-th service order.

[0068] In a possible implementation manner, step S131 includes:

[0069] Step S1311: Construct a service efficiency evaluation index system. The input of this service efficiency evaluation index system is the initial description data of each internal network path in the order network path sequence. The initial description data includes the path length of the internal network path, the number of nodes included in the internal network path, the connection strength between nodes, the average processing time in the historical service record, the processing success rate in the historical service record, and the customer feedback data. The output of this service efficiency evaluation index system is a customized service efficiency evaluation index set for each internal network path. The service efficiency evaluation indexes in this service efficiency evaluation index set are used to measure the efficiency performance of the internal network path when processing service orders. Among them, the path length index is obtained by calculating the total number of steps or total connections from the start node to the end node in the internal network path. The index of the number of nodes included in the internal network path directly counts the number of all nodes in the internal network path. The connection strength index between nodes is comprehensively calculated based on the historical interaction frequency, interaction success rate, and interaction response time between nodes. The average processing time index in the historical service record is obtained by statistically calculating the average time for all nodes in the internal network path to process the same type of service orders in history. The processing success rate index in the historical service record is obtained by calculating the success ratio of all nodes in the internal network path to process the same type of service orders in history. The customer feedback data index is obtained by collecting and analyzing the evaluation data of customers on the services of each node in the internal network path.

[0070] Step S1312: Preprocess the service efficiency evaluation index set and the original service data of the corresponding internal network path to generate a preprocessed service efficiency data set.

[0071] Step S1313: Apply a multi-source information fusion algorithm to fuse the preprocessed service efficiency data set and the supplementary data from different sources to generate the fused service efficiency data.

[0072] Step S1314: Calculate the service efficiency scores of each internal network path based on the fused service efficiency data. The specific calculation process includes setting corresponding weights for each service efficiency evaluation index according to the service efficiency evaluation indexes in the service efficiency evaluation index set. The magnitude of the weight reflects the importance of the service efficiency evaluation index in evaluating service efficiency. Then, use a linear weighted sum, a non-linear model, or a machine learning algorithm to combine the service efficiency data in the fused service efficiency data set with the weights of the service efficiency evaluation indexes, calculate the service efficiency scores of each internal network path, and perform normalization processing on the calculated service efficiency scores.

[0073] Step S1315: Based on the service efficiency scores of each internal network path and historical service efficiency data, perform dynamic adjustment to generate the dynamically adjusted service efficiency scores. Specifically, first analyze the historical service efficiency data, identify the change trend of service efficiency over time, and after setting corresponding adjustment rules according to the change trend, apply the adjustment rules to dynamically adjust the service efficiency scores of each internal network path to obtain the adjusted service efficiency scores.

[0074] Step S1316: Set the calculation rules for the wandering priority according to the predefined business requirement strategy, and apply the calculation rules to process the dynamically adjusted service efficiency scores to calculate the wandering priority of each internal network path.

[0075] In this embodiment, in the e-commerce service order processing flow of a financial service institution, when it comes to the order network path sequence, it is first necessary to obtain the service efficiency data corresponding to each internal network path in the order network path sequence. Taking the financial service institution's processing of e-commerce payment orders as an example, the order network path sequence includes each intermediate node from the order initiation node to the final payment completion and the paths connecting them. For each internal network path among them, the acquisition of its corresponding service efficiency data is crucial.

[0076] In terms of constructing the service efficiency evaluation index system, the system takes the initial description data of each internal network path in the order network path sequence as input. For example, in a typical e-commerce payment order network path, the path length of the internal network path is a key factor. The path length index is obtained by calculating the total number of steps or total connections from the starting node (such as the order submission node) to the ending node (such as the payment success node) in the internal network path. Suppose an internal network path starts from order submission, goes through nodes such as risk assessment, payment channel selection, identity verification, and finally reaches payment success, and the number of connections between these nodes is 5, then the path length of this internal network path is 5.

[0077] The index of the number of nodes included in the internal network path directly counts the number of all nodes in the internal network path. Taking the above-mentioned internal network path of the payment order as an example, it includes 5 nodes: order submission, risk assessment, payment channel selection, identity verification, and payment success, so the number of nodes is 5.

[0078] The connection strength index between nodes is calculated comprehensively based on the historical interaction frequency, interaction success rate, and interaction response time between nodes. For example, between the risk assessment node and the payment channel selection node, they interact 10 times per hour historically (historical interaction frequency), the interaction success rate is 90%, and the average interaction response time is 2 seconds. According to a specific calculation formula (taking into account the weight relationship of these three factors), the connection strength index between these two nodes can be obtained.

[0079] The average processing time index in the historical service records is obtained by statistically calculating the average time of all nodes in the internal path of the network for processing the same type of service orders (such as orders within the same amount range and of the same payment type). For example, the average time for the identity verification node to process similar payment orders is 3 seconds, and for the payment channel selection node is 2 seconds, etc. The average processing time index for the entire internal path of the network is calculated comprehensively.

[0080] The processing success rate index in the historical service records is obtained by calculating the success ratio of all nodes in the internal path of the network for processing the same type of service orders. Suppose the success ratio of the risk assessment node for processing similar orders is 92%, and for the payment channel selection node is 95%, etc. The processing success rate index for the entire internal path of the network is calculated by integrating the success rates of these nodes.

[0081] The customer feedback data index is obtained by collecting and analyzing the evaluation data of customers on the services of each node in the internal path of the network. For example, the service evaluation of the identity verification node by customers is a satisfaction rate of 80%, and for the payment channel selection node is a satisfaction rate of 85%, etc. The customer feedback data index is obtained by integrating these evaluation data.

[0082] Based on these initial description data, the service efficiency evaluation index system outputs a set of customized service efficiency evaluation indexes for each internal path of the network. These evaluation indexes are used to measure the efficiency performance of the internal path of the network when processing service orders.

[0083] Next, preprocess the set of service efficiency evaluation indexes and the original service data of the corresponding internal path of the network to generate a set of preprocessed service efficiency data. The preprocessing process may include data cleaning (removing outliers, incorrect data, etc.), data standardization (converting data of different magnitudes into the same magnitude), etc. For example, if there are abnormally high values in the processing time data of some nodes (possibly due to incorrect system failure records), they will be identified and corrected or removed during the preprocessing process, and then the processed service efficiency evaluation index data and the original service data will be integrated to generate a set of preprocessed service efficiency data.

[0084] Apply the multi-source information fusion algorithm to fuse the preprocessed service efficiency data set and supplementary data from different sources to generate the fused service efficiency data. The supplementary data may come from the evaluation data of financial service efficiency by external market research institutions, industry average service efficiency data, etc. The multi-source information fusion algorithm will perform weighted fusion on the data from different sources according to factors such as data reliability and relevance. For example, a relatively high weight is given to internal historical data, and a relatively low weight is given to external market research data, so as to generate the fused service efficiency data.

[0085] Calculate the service efficiency scores of each internal path in the network based on the fused service efficiency data. In the specific calculation process, according to the service efficiency evaluation indicators in the service efficiency evaluation indicator set, corresponding weights are set for each service efficiency evaluation indicator. The setting of weights reflects the importance of service efficiency evaluation indicators in evaluating service efficiency. For example, in the payment order processing, the processing success rate indicator may be given a relatively high weight because it is directly related to whether the order can be successfully completed. Then, use the linear weighted sum, non-linear model or machine learning algorithm to combine the service efficiency data in the fused service efficiency data set with the weights of the service efficiency evaluation indicators to calculate the service efficiency scores of each internal path in the network. For example, using the linear weighted sum method, if the weight of the path length indicator is 0.1, the weight of the node number indicator is 0.1, the weight of the connection strength indicator is 0.2, the weight of the average processing time indicator is 0.3, the weight of the processing success rate indicator is 0.2, and the weight of the customer feedback data indicator is 0.1, calculate the service efficiency score according to the data values and weights of each indicator. After calculating the service efficiency scores, perform normalization processing on them to make the service efficiency scores of all internal paths in the network within the same magnitude range for easy comparison.

[0086] Based on the service efficiency scores of each internal path in the network and the historical service efficiency data, perform dynamic adjustment to generate the dynamically adjusted service efficiency scores. First, analyze the historical service efficiency data to identify the change trend of service efficiency over time. For example, for a certain internal path in the network, it is found that its average processing time has gradually shortened in the past period, indicating that the service efficiency shows an upward trend. Set corresponding adjustment rules according to this change trend. If the service efficiency increases, the weight of its service efficiency score may be appropriately increased or a certain score may be directly added to the original score; if the service efficiency decreases, the weight is correspondingly reduced or the score is decreased. Apply this adjustment rule to dynamically adjust the service efficiency scores of each internal path in the network to obtain the adjusted service efficiency scores.

[0087] Set the calculation rules for the wandering priority according to the predefined business requirement strategy, and apply this calculation rule to process the service efficiency score after dynamic adjustment to calculate the wandering priority of each internal network path. The business requirement strategy may be formulated based on factors such as the business objectives of the financial service institution and the market competition situation. For example, if the current focus of the financial service institution is to improve customer satisfaction, then when calculating the wandering priority, the service efficiency score corresponding to the customer feedback data index will be given a higher weight in the calculation rule. Through this calculation rule, calculate the service efficiency score after dynamic adjustment to obtain the wandering priority of each internal network path.

[0088] Finally, compare the basic order allocation channels and service logics corresponding to each internal network path in the order network path sequence according to the calculated wandering priority. The service logic is determined based on factors such as business rules, compliance requirements, and customer needs in the e-commerce service order processing of the financial service institution. For example, the service logic requires that the processing time of the payment order cannot exceed 10 seconds and the processing success rate should reach more than 90%. Check the internal network paths in descending order of the wandering priority. If the basic order allocation channel (such as a specific payment channel) corresponding to a certain internal network path meets this service logic, then output this basic order allocation channel that meets the service logic as the reference order allocation channel corresponding to the a-th service order. For example, if the payment channel corresponding to a certain internal network path can complete the payment processing within 8 seconds and the processing success rate reaches 92%, meeting the service logic requirements, then this payment channel is determined as the reference order allocation channel corresponding to the a-th service order, providing an important reference basis for subsequent order allocation.

[0089] In a possible implementation manner, step S140 includes:

[0090] Step S141, obtain the order node data corresponding to each service order in the service order sequence. Based on the order node data corresponding to each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, determine the instance allocation search interval and obtain the service transfer data in the instance allocation search interval.

[0091] Step S142, based on the service transfer data and the allocation instance limit requirements in the attention label data, perform allocation instance prediction on each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order to generate the predicted allocation instance data.

[0092] In a possible implementation manner, step S141 includes:

[0093] Step S1411: Extract the order node data corresponding to each service order from the service order sequence. The order node data of each service order includes order type, order status, order priority, order creation time, order estimated completion time, and customer information associated with the order.

[0094] Step S1412: Arrange the order node data in the order of the service order sequence to generate an ordered set of order node data.

[0095] Step S1413: Allocate a channel for the reference order corresponding to the a-th service order, extract the corresponding key feature information, and integrate the key feature information to generate a feature vector. The key feature information includes channel type information, processing capacity information, historical service efficiency information, service response time information, current load status information, and supported service type information of the reference order allocation channel.

[0096] Step S1414: Based on the set of order node data and the feature vector, preliminarily construct a corresponding instance allocation search range. Specifically, according to the channel type information and service type information of the reference order allocation channel, screen out all service order node data with matching types from the set of order node data, and set a service efficiency threshold according to the processing capacity information and historical service efficiency information of the reference order allocation channel. Then, screen out the service order node data with service efficiency not less than the service efficiency threshold from the screened service order node data. Next, set a response time range and a load status range according to the service response time information and current load status information of the reference order allocation channel, and finally screen out the service order node data with service response time within the response time range and load status within the load status range from the secondarily screened service order node data. Use the time period or set of processing nodes corresponding to the finally screened service order node data as the preliminary construction result of the instance allocation search range.

[0097] Step S1415: Dynamically adjust the instance allocation search range initially constructed to generate an instance allocation search range after dynamic adjustment. Specifically, based on the historical service efficiency information in the feature vector of the reference order allocation channel, analyze the changing trend of service efficiency over time. If the service efficiency shows an upward trend, expand the range of the instance allocation search range based on the first preset expansion strategy; otherwise, narrow the range of the instance allocation search range based on the first preset contraction strategy. Meanwhile, according to the current load status information of the reference order allocation channel, if the load corresponding to the current load status information is less than the first load, expand the range of the instance allocation search range based on the second preset expansion strategy; otherwise, narrow the range of the instance allocation search range based on the second preset contraction strategy. In addition, perform priority adjustment on the instance allocation search range according to the priority information of the service orders in the order node data set.

[0098] Step S1416: Determine the service transfer data acquisition strategy based on the instance allocation search range after dynamic adjustment. Specifically, determine the data source information of the service transfer data, where the source information includes the historical service record database, real-time service monitoring system, customer service feedback system, and third-party service data providers. Then, according to the range of the instance allocation search range, set the acquisition conditions for the service transfer data, where the acquisition conditions include time range, service type, processing node, and customer type. Then, determine the acquisition method of the service transfer data, where the acquisition method includes batch acquisition, real-time acquisition, scheduled acquisition, or on-demand acquisition. At the same time, determine the corresponding data encryption and desensitization strategy, and determine the storage and management method of the service transfer data.

[0099] Step S1417: Acquire the corresponding service transfer data according to the service transfer data acquisition strategy, match the service transfer data with the instance allocation search range, filter out the service transfer data that meets the range of the instance allocation search range, extract and analyze the features of the service transfer data that meets the range of the instance allocation search range, and generate the feature analysis result of the service transfer data.

[0100] Step S1418: Based on the feature analysis result of the service transfer data, screen and evaluate the instances in the service transfer data, optimize and recommend the set of service transfer data instances after screening and evaluation, and generate an optimized set of service transfer data instances.

[0101] In a possible implementation manner, the instance allocation limit requirements include service channel type information and service response time limit information.

[0102] Step S142 includes:

[0103] Step S1421: Output the order node data corresponding to each service order in the service order sequence as an initial order node, output the reference order allocation channel corresponding to the a-th service order as a termination order node, and perform instance retrieval in the service flow data to generate a basic instance sequence.

[0104] Step S1422: If the basic instance K in the basic instance sequence does not conform to the service channel type information or does not conform to the service response time limit information, delete the basic instance K from the basic instance sequence, and output the remaining basic instances in the basic instance sequence as the predicted allocation instance data.

[0105] In this embodiment, in the system of a financial service institution for processing e-commerce service orders, each service order has rich order node data. Taking the e-commerce payment order of a financial service institution as an example, the order type may be online payment, installment payment, refund, or other types. The order status may include different states such as submitted, processing, completed, or failed. The order priority can be determined according to the customer's membership level, order amount, or business urgency. For example, orders of high-value customers or gold card members may have a higher priority. The order creation time accurately records the moment when the order is generated, which is very important for analyzing the timeliness of the order and the time management of the processing flow. The order expected completion time is the estimated order completion moment based on business rules and historical data. For example, for an ordinary small-value payment order, it is expected to be completed within 10 minutes after submission. The customer information associated with the order covers aspects such as the customer's identity identification, credit rating, and membership level. This information helps the financial service institution classify customers and provide personalized services. After extracting these order node data one by one from the service order sequence and arranging them in the order of the service order sequence, an ordered set of order node data is generated.

[0106] For the reference order allocation channel corresponding to the a-th service order, it is necessary to extract the corresponding key feature information and integrate it into a feature vector. Suppose the a-th service order is a specific e-commerce payment order, and its corresponding reference order allocation channel is a specific payment channel. The channel type information of this payment channel indicates that it is an online payment channel, which may be a fast payment method in cooperation with a specific bank. The processing capacity information reflects the number of orders that this payment channel can process per hour. For example, it can process 500 payment orders per hour. The historical service efficiency information includes data such as the average processing time and success rate of this payment channel for processing similar orders in the past. For example, the average processing time for processing similar payment orders in the past was 5 seconds, and the success rate was 95%. The service response time information stipulates the time requirement from receiving a payment request to giving a response. For example, it is required to give a response within 3 seconds. The current load status information shows the proportion of the number of orders currently being processed by this payment channel to its processing capacity. Suppose the current load is 40%. The supported service type information indicates that this payment channel mainly supports services such as small-value payments and domestic payments. Integrating these key feature information generates a feature vector.

[0107] Based on the above order node data set and feature vector, initially construct the corresponding instance allocation search interval. For this specific payment channel, first, according to its channel type information and service type information, screen out all service order node data with matching types from the order node data set. For example, if the payment channel is domestic fast payment and supports small-value payments, then screen out all order node data related to domestic payment orders with small amounts from the order node data set. Then, according to the processing capacity information and historical service efficiency information of the reference order allocation channel, set a service efficiency threshold. For example, according to the historical service efficiency of this payment channel, set the service efficiency threshold that the average processing time does not exceed 8 seconds, and screen out the service order node data with service efficiency not less than this threshold from the previously screened service order node data. Then, according to the service response time information and current load status information of the reference order allocation channel, set a response time range and a load status range. Suppose the service response time range is set to 2 - 5 seconds, and the load status range is set to 30% - 70%. Finally, screen out the service order node data with service response time within this range and load status within this range from the secondarily screened service order node data. Take the time period or processing node set corresponding to the finally screened service order node data as the initial construction result of the instance allocation search interval.

[0108] Subsequently, the search range of the instance allocation initially constructed is dynamically adjusted. Based on the historical service efficiency information in the feature vector of the reference order allocation channel, the changing trend of service efficiency over time is analyzed. If it is found that the historical service efficiency of this payment channel shows an upward trend, for example, its average processing time has gradually decreased from 6 seconds to 5 seconds in the past few months, the range of the instance allocation search range is expanded based on the first preset expansion strategy. This may mean that more order node data can be included for subsequent analysis because the service efficiency of this payment channel is improving and it has the ability to process more types of orders. Conversely, if the historical service efficiency shows a downward trend, such as the average processing time increasing from 5 seconds to 6 seconds, the range of the instance allocation search range is narrowed based on the first preset narrowing strategy to ensure that the subsequent processed orders are more in line with the actual processing capacity of this payment channel. At the same time, according to the current load status information of the reference order allocation channel, if the load corresponding to the current load status information is less than the first load (assuming the first load is 40%), this indicates that there is still a lot of remaining processing capacity for this payment channel, then the range of the instance allocation search range is expanded based on the second preset expansion strategy. If the current load is greater than the first load, for example, the current load is 60%, the range of the instance allocation search range is narrowed based on the second preset narrowing strategy to avoid allocating too many orders to this payment channel that is already close to full load. In addition, according to the priority information of the service orders in the order node data set, the priority of the instance allocation search range is adjusted. For high-priority orders, such as high-value orders or orders of gold card members, the weight or range of these orders in the instance allocation search range can be appropriately expanded to ensure that these important orders can be processed preferentially.

[0109] Based on the instance allocation search range after dynamic adjustment, determine the service transfer data acquisition strategy. Determine the data source information of the service transfer data, including the historical service record database, real-time service monitoring system, customer service feedback system, and third-party service data providers. The historical service record database stores detailed processing records of all past service orders, including information such as processing time, processing results, and service channels involved. The real-time service monitoring system can obtain the status information of currently processing service orders in real time, such as which orders are currently being processed on a specific payment channel and which stage of processing they have reached. The customer service feedback system collects information such as customer evaluations and complaints about the service, which helps to understand the service quality and customer satisfaction. Third-party service data providers may provide supplementary information such as market data and industry average data. Then, according to the range of the instance allocation search range, set the acquisition conditions for the service transfer data. The acquisition conditions include time range, such as obtaining service transfer data related to the instance allocation search range within the last month; service type, such as only obtaining transfer data related to payment services; processing node, such as focusing on transfer data involving specific payment channel processing nodes; customer type, such as transfer data for gold card members or customers with high credit ratings. Then determine the acquisition method of the service transfer data, including batch acquisition, real-time acquisition, scheduled acquisition, or on-demand acquisition. If a large amount of historical data needs to be obtained at one time for analysis, the batch acquisition method may be used; if the transfer situation of currently processing orders needs to be monitored in a timely manner, the real-time acquisition method is used; if data is obtained at fixed time intervals (such as daily, weekly), the scheduled acquisition method is used; and for some special requirements, such as temporarily analyzing the transfer data of a specific order, the on-demand acquisition method is used. At the same time, determine the corresponding data encryption and desensitization strategies to protect customer privacy and data security. For sensitive information, such as customer ID numbers and bank card numbers, encryption technology is used for protection, and desensitization processing is carried out during data use, only showing some key information. Determine the storage and management method of the service transfer data, for example, using a distributed storage system to classify and store data according to different service types, time ranges, etc., for subsequent query and analysis.

[0110] Obtain the corresponding service transfer data according to the service transfer data acquisition strategy, and match the service transfer data with the instance allocation search range to filter out the service transfer data that meets the instance allocation search range. For example, after obtaining the service transfer data from the historical service record database according to conditions such as the set time range and service type, match it with the order node data, processing nodes, etc. within the instance allocation search range. For the service transfer data that meets the instance allocation search range, perform feature extraction and analysis to generate the feature analysis result of the service transfer data. Feature extraction may include extracting information such as the processing time, processing result, and changes in service channels involved in the key links of the service transfer process, analyzing the relationships between these features and the impact on service order processing, such as analyzing whether the extension of the processing time in a certain link will lead to the failure of the entire order processing or a decrease in customer satisfaction, etc.

[0111] Based on the feature analysis result of the service transfer data, filter and evaluate the instances in the service transfer data. For each instance in the service transfer data, evaluate it according to the previously analyzed feature analysis result. For example, if the processing time of a certain link in an instance is too long or the processing result is a failure, this instance may be marked or its evaluation score may be reduced. Optimize and recommend the set of service transfer data instances that have been filtered and evaluated to generate an optimized set of service transfer data instances. The optimization process may include removing those instances that obviously do not meet the requirements or have poor quality, sorting the remaining instances according to their evaluation scores, and recommending those instances with higher evaluation scores as better quality service transfer data instances.

[0112] For the process of "predicting the allocation instances for each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order based on the allocation instance restriction requirements in the service transfer data and the attention tag data, and generating the predicted allocation instance data":

[0113] Assume that the allocation instance restriction requirements include service channel type information and service response time limit information. Output the order node data corresponding to each service order in the service order sequence as the initial order node, and output the reference order allocation channel corresponding to the a-th service order (such as the specific payment channel mentioned above) as the termination order node, and perform instance retrieval in the service transfer data to generate a basic instance sequence. In this process, find all possible instance paths from the initial order node to the termination order node in the service transfer data, and these instance paths constitute the basic instance sequence.

[0114] If the basic instance K in the basic instance sequence does not conform to the service channel type information, for example, the basic instance K involves a refund channel instead of the required payment channel, or the basic instance K does not conform to the service response time limit information, such as the service response time in the basic instance K exceeding the specified time limit, then this basic instance K is deleted from the basic instance sequence. After such screening, the remaining basic instances in the basic instance sequence are output as predicted allocation instance data. These predicted allocation instance data provide an important basis for subsequently determining the target order allocation channel, helping the financial service institution to select the most compliant and optimized order allocation scheme among many possible allocation instances, thereby improving the efficiency, accuracy, and customer satisfaction of e-commerce service order processing.

[0115] In a possible implementation manner, the method further includes:

[0116] Step A110, sending the predicted allocation instance data corresponding to the a-th service order to the order service system associated with the a-th service order, so that the order service system presents the predicted allocation instance data corresponding to the a-th service order.

[0117] Step A110, obtaining the allocation response data returned by the order service system. The allocation response data includes the candidate order allocation channels selected by the a-th service order from the predicted allocation instance data corresponding to the a-th service order.

[0118] Then step S140 further includes:

[0119] Step S143, obtaining the candidate order allocation channels corresponding to each service order in the service order sequence, and statistically calculating the order support probabilities corresponding to the candidate order allocation channels.

[0120] Step S144, outputting the candidate order allocation channel corresponding to the maximum order support probability as the target order allocation channel, and associating the target order allocation channel with each service order.

[0121] In this embodiment, in the e-commerce service architecture of a financial service institution, the a-th service order may be a typical e-commerce payment order. After determining the predicted allocation instance data corresponding to this e-commerce payment order, it is necessary to send this predicted allocation instance data to the associated order service system. This order service system is a system specifically designed to handle the business logic related to this service order, and it encompasses a series of functional modules from order reception, processing to final completion. The predicted allocation instance data contains the possible allocation instance information related to this order filtered through a series of complex processes before, such as the relevant data of different payment channels for processing this order under specific conditions. After sending this data to the order service system, the order service system will present the predicted allocation instance data corresponding to the a-th service order according to its internal display logic and business rules. This presentation process is to enable relevant modules or personnel in the system (if there is any part involving manual intervention) to clearly see various possible allocation instance situations for this order, so as to perform subsequent operations.

[0122] Next, obtain the allocation response data returned by the order service system. After receiving the predicted allocation instance data and presenting it, the order service system will generate allocation response data according to its own business logic and possible external interventions (such as manual selection or automatic selection based on internal system algorithms). Taking the previous e-commerce payment order as an example, this allocation response data includes the candidate order allocation channels selected by the a-th service order from its corresponding predicted allocation instance data. For example, if the predicted allocation instance data contains three payment channels A, B, and C as possible allocation instances, and the order service system selects payment channel A according to its own load situation, the priority setting of the payment channels, or manual selection, then payment channel A becomes the selection of this order in the candidate order allocation channels, and this selection information is included in the allocation response data.

[0123] Then, based on the predicted allocation instance data corresponding to the reference order allocation channels of each service order, obtain the comprehensive cost parameters corresponding to the reference order allocation channels of each service order, and determine the target order allocation channel. For each service order in the service order sequence, first obtain their respective candidate order allocation channels. In the process of a financial service institution handling e-commerce service orders, each service order has its specific business requirements and conditions, and these conditions will affect the determination of the candidate order allocation channels. For example, for a high-value e-commerce payment order, its candidate order allocation channels may tend to those payment channels with high security and high processing capabilities; while for a small payment order with high requirements for processing speed, it may tend to choose payment channels with fast processing speed and simple procedures. After obtaining the candidate order allocation channels of each service order, it is necessary to count the order support probabilities corresponding to these candidate order allocation channels.

[0124] The statistics of the order support probability involve multiple factors. Taking the payment order as an example, for a payment channel as a candidate order allocation channel, its order support probability may be related to factors such as its historical processing success rate, current load status, compatibility with relevant business systems, and customer preferences. From the perspective of the historical processing success rate, if a payment channel has a very high success rate in processing similar payment orders in the past, for example, reaching 98%, then its order support probability in this regard will be relatively high. The current load status will also affect the order support probability. If a payment channel is already close to full load and has limited ability to process new orders, then its order support probability will decrease. Compatibility with relevant business systems is equally important. If a payment channel has good compatibility with other business systems of a financial service institution (such as a risk assessment system, customer information management system, etc.) and can smoothly exchange data and collaborate, then its order support probability will increase. In addition, customer preferences will also affect the order support probability to a certain extent. If it is found from the customer's historical order data that the customer is more inclined to use a certain payment channel, then the order support probability of this payment channel for the customer's order will also increase accordingly.

[0125] After the order support probabilities corresponding to each candidate order allocation channel are statistically calculated, the candidate order allocation channel corresponding to the maximum order support probability is output as the target order allocation channel. For example, in a service order sequence, there are multiple orders, and each order has its own candidate order allocation channel. After statistically calculating the order support probabilities of these candidate order allocation channels, it is found that for a certain order, the order support probability of payment channel D is the highest. Then payment channel D is output as the target order allocation channel for this order. Finally, this target order allocation channel is associated with each service order, which means that in the subsequent order processing process, each service order will be processed according to this target order allocation channel. For example, the order will be directed to payment channel D for payment processing, and relevant business logics (such as fund transfer, risk control, etc.) will also be carried out around the characteristics and requirements of payment channel D, so as to ensure the efficiency, accuracy, and reliability of the entire e-commerce service order processing process. Through such a process, the most suitable target order allocation channel for each service order can be selected from multiple candidate order allocation channels, improving the overall efficiency of the financial service institution in processing e-commerce service orders.

[0126] In a possible implementation manner, the method further includes:

[0127] Step B110, when it is monitored that the service process corresponding to the target order allocation channel issues a business congestion notice, obtain the current order node data corresponding to the service orders included in the service order sequence.

[0128] Step B120: Based on the order allocation knowledge network and the current order node data corresponding to the service orders included in the service order sequence, re-determine the target order allocation channel.

[0129] In this embodiment, when a business congestion notice is sent by the service process corresponding to the target order allocation channel, it indicates that the current service process has a situation of resource tension or insufficient processing capacity. Taking the e-commerce payment service of a financial service institution as an example, the target order allocation channel may be a specific payment channel. When the service process corresponding to this payment channel sends a business congestion notice, it means that this payment channel may be processing a large number of payment orders and has approached or exceeded the limit of its processing capacity. At this time, it is necessary to obtain the current order node data corresponding to the service orders included in the service order sequence. Each service order in the service order sequence has its specific current order node data, which reflects various status information of the order at the current moment. For example, for an e-commerce payment order, its current order node data includes the order type (such as regular payment, installment payment, etc.), order status (such as being processed, waiting for verification, etc.), order priority (determined according to factors such as customer level, amount, etc.), order creation time, order expected completion time, and customer information associated with the order (such as customer identity identifier, credit rating, etc.). By obtaining these detailed current order node data, the current situation of each service order can be comprehensively understood, providing a basis for re-determining the target order allocation channel.

[0130] On this basis, the order allocation knowledge network is a network structure previously constructed that includes service order records, order allocation channel sequences, and index association information. This order allocation knowledge network structure comprehensively reflects the relationship between service orders and order allocation channels. For example, in this network, information such as the order type and customer credit rating in the service order record is connected to different order allocation channels through index association information. Based on this order allocation knowledge network, combined with the current order node data of the service order obtained previously, the applicability of each order allocation channel to the current service order can be re-evaluated. Taking an e-commerce payment order in a waiting verification state as an example, if the associated target order allocation channel (a certain payment channel) issues a business congestion notice, then search for other possible order allocation channels in the order allocation knowledge network. If it is found that another payment channel has slightly weaker processing capabilities but lower current load and matches the order type (regular payment) and customer credit rating (higher level) of this order, through the comprehensive analysis of the association information in the order allocation knowledge network and the current order node data, this payment channel can be re-determined as the target order allocation channel. This re-determination process is a process of comprehensively considering multiple factors, which requires in-depth analysis of various entity objects and internal network paths in the order allocation knowledge network, and at the same time combines the current specific situation of the service order to ensure that the re-determined target order allocation channel can effectively process the service order, avoid problems such as service delay and failure caused by business congestion, and improve the overall efficiency and reliability of the e-commerce service order processing of financial service institutions.

[0131] Figure 2 FIG. shows the hardware structure diagram of an order allocation processing system 100 based on a decision tree algorithm provided by an embodiment of the present invention for implementing the above-mentioned order allocation processing method based on a decision tree algorithm, as Figure 2 shown, the order allocation processing system 100 based on a decision tree algorithm may include a processor 110, a machine-readable storage medium 120, a bus 130, and a communication unit 140.

[0132] The machine-readable storage medium 120 can store data and / or instructions. In some embodiments, the machine-readable storage medium 120 can store data obtained from an external terminal. In some embodiments, the machine-readable storage medium 120 can store data and / or instructions used by the order allocation processing system 100 based on a decision tree algorithm to execute or use to complete the exemplary methods described in the present invention.

[0133] In a specific implementation process, one or more processors 110 execute computer-executable instructions stored in a machine-readable storage medium 120, enabling the processors 110 to execute the order allocation processing method based on the decision tree algorithm in the above method embodiments. The processors 110, the machine-readable storage medium 120, and the communication unit 140 are connected through a bus 130, and the processors 110 can be used to control the transceiver actions of the communication unit 140.

[0134] For the specific implementation process of the processors 110, reference can be made to the respective method embodiments executed by the order allocation processing system 100 based on the decision tree algorithm above. Their implementation principles and technical effects are similar, and will not be elaborated here in this embodiment.

[0135] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When a processor executes the computer-executable instructions, the order allocation processing method based on the decision tree algorithm as above is implemented.

[0136] It should be noted that, in order to simplify the description of the present invention disclosure and thus help the understanding of one or more embodiments of the invention, in the previous description of the embodiments of the present invention, sometimes multiple features are merged into one embodiment, drawing, or description thereof.

Claims

1. An order allocation processing method based on a decision tree algorithm, characterized in that, The method includes: Obtain a service order sequence, obtain the attention tag data corresponding to the service orders in the service order sequence, and based on the attention tag data, determine the order allocation channel sequence associated with the service order sequence through a decision tree algorithm; Construct index association information for the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence, and construct an order allocation knowledge network based on the service order sequence, the order allocation channel sequence, and the index association information; a is a positive integer; In the order allocation knowledge network, output the internal network path corresponding to the a-th service order as an order network path sequence, and output the basic order allocation channel corresponding to the internal network path that conforms to the service logic in the order network path sequence as the reference order allocation channel corresponding to the a-th service order; Obtain the predicted allocation instance data between each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, and based on the predicted allocation instance data corresponding to the reference order allocation channels of each service order, obtain the comprehensive cost parameter corresponding to the reference order allocation channel of each service order, and output the reference order allocation channel corresponding to the smallest comprehensive cost parameter as the target order allocation channel; Perform order allocation for the a-th service order based on the target order allocation channel; The method further includes: Send the predicted allocation instance data corresponding to the a-th service order to the order service system associated with the a-th service order, so that the order service system presents the predicted allocation instance data corresponding to the a-th service order; Obtain the allocation response data returned by the order service system; the allocation response data includes the candidate order allocation channels selected by the a-th service order in the predicted allocation instance data corresponding to the a-th service order; The obtaining the comprehensive cost parameter corresponding to the reference order allocation channel of each service order based on the predicted allocation instance data corresponding to the reference order allocation channels of each service order, and outputting the reference order allocation channel corresponding to the smallest comprehensive cost parameter as the target order allocation channel includes: Obtain the candidate order allocation channels corresponding to each service order in the service order sequence, and count the order support probabilities corresponding to the candidate order allocation channels; Output the candidate order allocation channel corresponding to the largest order support probability as the target order allocation channel, and associate the target order allocation channel with each service order.

2. The order allocation processing method based on the decision tree algorithm according to claim 1, wherein The determining the order allocation channel sequence associated with the service order sequence through a decision tree algorithm based on the attention tag data includes: Based on the channel association knowledge data in the attention tag data, determine an order allocation search service domain, and call a business logic tool to obtain service channel data within the order allocation search service domain; Obtain the service label knowledge data in the concerned label data, determine the service channels that match the service label knowledge data in the service channel data within the order allocation search service domain, and load the service channels into the order allocation channel sequence associated with the service order sequence.

3. The order allocation processing method based on the decision tree algorithm according to claim 1, characterized in that Construct index association information for the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence. Based on the service order sequence, the order allocation channel sequence, and the index association information, construct an order allocation knowledge network, including: Obtain the order attribute reference template associated with the service order sequence, and construct service order records corresponding to the service orders in the service order sequence based on the order attribute reference template; Construct index association information for the service order record corresponding to the a-th service order in the service order sequence and the basic order allocation channel of the a-th service order in the order allocation channel sequence; Use the service order records corresponding to the service orders in the service order sequence and the order allocation channel sequence as entity objects, and use the index association information as the internal network path to generate the order allocation knowledge network.

4. The order allocation processing method based on the decision tree algorithm according to claim 1, wherein Output the basic order allocation channels corresponding to the internal network paths that conform to the service logic in the order network path sequence as the reference order allocation channels corresponding to the a-th service order, including: Obtain the service efficiency data corresponding to each internal network path in the order network path sequence, determine the walking priorities corresponding to each internal network path in the order network path sequence based on the service efficiency data, and compare the basic order allocation channels corresponding to each internal network path in the order network path sequence with the service logic according to the walking priorities; If there are basic order allocation channels corresponding to the internal network paths in the order network path sequence that conform to the service logic, output the basic order allocation channels that conform to the service logic as the reference order allocation channels corresponding to the a-th service order; Among them, the steps of obtaining the service efficiency data corresponding to each internal network path in the order network path sequence and determining the walking priorities corresponding to each internal network path in the order network path sequence based on the service efficiency data include: Construct a service efficiency evaluation index system. The input of this service efficiency evaluation index system is the initial description data of each internal network path in the order network path sequence. The initial description data includes the path length of the internal network path, the number of nodes contained in the internal network path, the connection strength between nodes, the average processing time in the historical service record, the processing success rate in the historical service record, and the customer feedback data. The output of this service efficiency evaluation index system is a customized service efficiency evaluation index set for each internal network path. The service efficiency evaluation indexes in this service efficiency evaluation index set are used to measure the efficiency performance of the internal network path when processing service orders. Among them, the path length index is obtained by calculating the total number of steps or total connections from the starting node to the ending node in the internal network path. The index of the number of nodes contained in the internal network path directly counts the number of all nodes in the internal network path. The connection strength index between nodes is comprehensively calculated based on the historical interaction frequency, interaction success rate, and interaction response time between nodes. The average processing time index in the historical service record is obtained by statistically calculating the average time for all nodes in the internal network path to process the same type of service order in history. The processing success rate index in the historical service record is obtained by calculating the success ratio of all nodes in the internal network path to process the same type of service order in history. The customer feedback data index is obtained by collecting and analyzing the evaluation data of customers on the services of each node in the internal network path; Preprocess the service efficiency evaluation index set and the original service data of the corresponding internal network path to generate a preprocessed service efficiency data set; Apply a multi-source information fusion algorithm to fuse the preprocessed service efficiency data set and the supplementary data from different sources to generate the fused service efficiency data; Calculate the service efficiency scores of each internal network path based on the fused service efficiency data. The specific calculation process includes setting corresponding weights for each service efficiency evaluation index according to the service efficiency evaluation indexes in the service efficiency evaluation index set. The magnitude of the weight reflects the importance of the service efficiency evaluation index in evaluating service efficiency. Then, use the linear weighted sum, non-linear model, or machine learning algorithm to combine the service efficiency data in the fused service efficiency data set with the weights of the service efficiency evaluation indexes, calculate the service efficiency scores of each internal network path, and perform normalization processing on the calculated service efficiency scores; Perform dynamic adjustment based on the service efficiency scores of each internal network path and the historical service efficiency data to generate the dynamically adjusted service efficiency scores. Specifically, first analyze the historical service efficiency data, identify the change trend of service efficiency over time, and after setting the corresponding adjustment rules according to the change trend, apply the adjustment rules to dynamically adjust the service efficiency scores of each internal network path to obtain the adjusted service efficiency scores; Set the calculation rules for the wandering priority according to the predefined business requirement strategies, and apply the calculation rules to process the service efficiency scores after dynamic adjustment to calculate the wandering priority of each internal network path.

5. The order allocation processing method based on the decision tree algorithm according to claim 1, characterized in that The obtaining of the predicted allocation instance data between each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order includes: Obtain the order node data corresponding to each service order in the service order sequence. Based on the order node data corresponding to each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, determine the instance allocation search interval, and obtain the service transfer data in the instance allocation search interval; Based on the service transfer data and the allocation instance restriction requirements in the attention label data, perform allocation instance prediction on each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order to generate the predicted allocation instance data.

6. The order allocation processing method based on the decision tree algorithm according to claim 5, wherein The step of determining the instance allocation search interval based on the order node data corresponding to each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, and obtaining the service transfer data in the instance allocation search interval includes: Extract the order node data corresponding to each service order from the service order sequence. The order node data of each service order includes order type, order status, order priority, order creation time, order expected completion time, and customer information associated with the order; Arrange the order node data in the order of the service order sequence to generate an ordered set of order node data; For the reference order allocation channel corresponding to the a-th service order, extract the corresponding key feature information, and integrate the key feature information to generate a feature vector. The key feature information includes channel type information, processing capacity information, historical service efficiency information, service response time information, current load status information, and supported service type information of the reference order allocation channel; Based on the order node data set and the feature vector, preliminarily construct the corresponding instance allocation search interval. Specifically, according to the channel type information and service type information of the reference order allocation channel, screen out all service order node data with matching types from the order node data set, and set a service efficiency threshold based on the processing capacity information and historical service efficiency information of the reference order allocation channel. Then, screen out the service order node data with service efficiency not less than the service efficiency threshold from the screened service order node data. Next, set a response time range and a load status range based on the service response time information and current load status information of the reference order allocation channel, and finally screen out the service order node data with service response time within the response time range and load status within the load status range from the secondarily screened service order node data. Take the time period or processing node set corresponding to the finally screened service order node data as the preliminary construction result of the instance allocation search interval; Dynamically adjust the preliminarily constructed instance allocation search interval to generate the instance allocation search interval after dynamic adjustment. Specifically, according to the historical service efficiency information in the feature vector of the reference order allocation channel, analyze the change trend of service efficiency over time. If the service efficiency shows an upward trend, expand the range of the instance allocation search interval based on the first preset expansion strategy; otherwise, shrink the range of the instance allocation search interval based on the first preset contraction strategy. At the same time, according to the current load status information of the reference order allocation channel, if the load corresponding to the current load status information is less than the first load, expand the range of the instance allocation search interval based on the second preset expansion strategy; otherwise, shrink the range of the instance allocation search interval based on the second preset contraction strategy. In addition, adjust the priority of the instance allocation search interval according to the priority information of the service orders in the order node data set; Based on the instance allocation search interval after dynamic adjustment, determine the service transfer data acquisition strategy. Specifically, determine the data source information of the service transfer data, and the source information includes the historical service record database, real-time service monitoring system, customer service feedback system, and third-party service data provider. Then, set the acquisition conditions of the service transfer data according to the range of the instance allocation search interval, and the acquisition conditions include time range, service type, processing node, and customer type. Next, determine the acquisition method of the service transfer data, and the acquisition method includes batch acquisition, real-time acquisition, timed acquisition, or on-demand acquisition. At the same time, determine the corresponding data encryption and desensitization strategy, and determine the storage and management method of the service transfer data; Obtain the corresponding service transfer data according to the service transfer data acquisition strategy, match the service transfer data with the instance allocation search interval, screen out the service transfer data that meets the range of the instance allocation search interval, perform feature extraction and analysis on the service transfer data that meets the range of the instance allocation search interval, and generate the feature analysis result of the service transfer data; Based on the feature analysis results of the service transfer data, screen and evaluate the instances in the service transfer data, optimize and recommend the set of service transfer data instances that have been screened and evaluated, and generate an optimized set of service transfer data instances.

7. The order allocation processing method based on the decision tree algorithm according to claim 5, characterized in that, The allocation instance limit requirements include service channel type information and service response time limit information; Based on the service transfer data and the allocation instance limit requirements in the attention tag data, perform allocation instance prediction on each service order in the service order sequence and the reference order allocation channel corresponding to the a-th service order, and generate the predicted allocation instance data, including: Output the order node data corresponding to each service order in the service order sequence as an initial order node, output the reference order allocation channel corresponding to the a-th service order as a termination order node, and perform instance retrieval in the service transfer data to generate a basic instance sequence; If the basic instance K in the basic instance sequence does not meet the service channel type information or the basic instance K does not meet the service response time limit information, delete the basic instance K from the basic instance sequence, and output the remaining basic instances in the basic instance sequence as the predicted allocation instance data.

8. The order allocation processing method based on the decision tree algorithm according to claim 1, wherein, The method further includes: When it is monitored that the service process corresponding to the target order allocation channel issues a business congestion notice, obtain the current order node data corresponding to the service orders included in the service order sequence; Based on the order allocation knowledge network and the current order node data corresponding to the service orders included in the service order sequence, re-determine the target order allocation channel.

9. An order allocation processing system based on a decision tree algorithm, characterized in that, The order allocation processing system based on the decision tree algorithm includes a processor and a memory. The memory is connected to the processor. The memory is used to store programs, instructions, or codes, and the processor is used to execute the programs, instructions, or codes in the memory to implement the order allocation processing method based on the decision tree algorithm according to any one of claims 1-8 above.

Images