Path selection method and apparatus, terminal and storage medium

Abstract

This application relates to the field of big data intelligent analysis technology, and particularly to a path selection method, apparatus, terminal, and storage medium. The path selection method includes: acquiring a set of account information; inputting a first subset of account information from the set of account information into a target neural network model to obtain a first probability corresponding to any node in a set of business nodes, wherein the first probability indicates a predicted probability of successfully selecting the given node; inputting a second subset of account information from the set of account information into an artificial intelligence model to obtain the business processing time corresponding to the given node; and determining a target business process path corresponding to the account information during the business process path selection process based on the first probability and business processing time of at least one node in the set of business nodes. Using this application can improve the accuracy of business process selection and reduce the processing time of business processes.

Description

Technical Field

[0001] This application relates to the field of big data intelligent analysis technology, and in particular to a path selection method, apparatus, terminal and storage medium. Background Technology

[0002] With economic and technological development and the increasing pace of life and work intensity, improving user experience has become a central focus across all industries. Each process has a fixed format, requiring step-by-step completion according to requirements. At each node in the process, multiple choices often arise, leading to different business flows depending on the specific business type and customer characteristics. While the experience and expertise of the personnel involved can be relied upon to determine the appropriate workflow, this approach introduces significant uncertainty. Inappropriate choices can result in lengthy processes, poor outcomes, or even process errors leading to business failure. Therefore, improving the accuracy and efficiency of business process selection has become a key concern for users. Summary of the Invention

[0003] This application provides a path selection method, apparatus, terminal, and storage medium, the main purpose of which is to improve the accuracy of business process selection and reduce the time consumption of business processes.

[0004] According to one aspect of this application, a path selection method is provided, comprising:

[0005] Retrieve a collection of account information;

[0006] The first subset of account information in the account information set is input into the target neural network model to obtain the first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node;

[0007] Input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node;

[0008] Based on the first probability and business duration corresponding to at least one node in the business node set, the target business process path corresponding to the account information is determined during the business process path selection process.

[0009] Optionally, after obtaining the service consumption time corresponding to any of the nodes, the method further includes:

[0010] Display the first probability corresponding to any of the nodes and the service duration.

[0011] Optionally, the step of inputting a first subset of account information from the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set includes:

[0012] Input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set;

[0013] Based on the third subset of account information in the account information set and the integration algorithm, obtain the second probability corresponding to any node;

[0014] Based on the first probability and the second probability, the first probability is corrected to obtain the corrected first probability.

[0015] Optionally, determining the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set includes:

[0016] Based on the first probability corresponding to at least one node in the set of business nodes, obtain the path probability corresponding to at least one path.

[0017] Based on the service time duration corresponding to at least one node in the service node set, obtain the path time duration corresponding to the at least one path;

[0018] Based on the path probability and path duration of the at least one path, the target business process path corresponding to the account information is determined during the business process path selection process.

[0019] Optionally, determining the target business process path corresponding to the account information during the business process path selection process based on the path probability and path duration corresponding to the at least one path includes:

[0020] Receive selection instructions for path probability and path duration;

[0021] Based on the selection instruction, determine the third weight corresponding to the path probability and the fourth weight corresponding to the path duration;

[0022] Based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

[0023] Optionally, determining the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration includes:

[0024] The path time corresponding to the at least one path is normalized to obtain the processed path time corresponding to the at least one path.

[0025] Based on the path probability corresponding to the at least one path, the path duration corresponding to the at least one processed path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

[0026] Optionally, the method further includes:

[0027] Obtain a set of historical account information and a set of historical node selection information corresponding to the set of historical account information;

[0028] Based on the set of historical node selection information, determine the first selection success probability corresponding to any given node;

[0029] The initial neural network model is trained based on the set of historical account information. When the second success probability of the initial neural network model matches the first success probability of the initial selection, the target neural network model is obtained.

[0030] According to one aspect of this application, a path selection device is provided, comprising:

[0031] The collection retrieval unit is used to retrieve a collection of account information.

[0032] The probability acquisition unit is used to input a first subset of account information in the account information set into the target neural network model to obtain a first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node.

[0033] The duration acquisition unit is used to input the second subset of account information in the account information set into the artificial intelligence model to obtain the business consumption duration corresponding to any node.

[0034] The path selection unit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set.

[0035] Optionally, the device further includes a duration display unit, used to display the first probability corresponding to any node and the duration of the service consumption corresponding to any node after obtaining the service consumption duration corresponding to any node.

[0036] Optionally, the probability acquisition unit includes a probability acquisition subunit and a probability correction subunit. The probability acquisition unit is used to input a first subset of account information from the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set:

[0037] The probability acquisition subunit is used to input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set.

[0038] The probability acquisition subunit is further configured to acquire the second probability corresponding to any node based on the third account information subset in the account information set and the integration algorithm;

[0039] The probability correction subunit is used to correct the first probability based on the first probability and the second probability to obtain the corrected first probability.

[0040] Optionally, the path selection unit, when determining the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time corresponding to at least one node in the business node set, specifically uses the following:

[0041] Based on the first probability corresponding to at least one node in the set of business nodes, obtain the path probability corresponding to at least one path.

[0042] Based on the service time duration corresponding to at least one node in the service node set, obtain the path time duration corresponding to the at least one path;

[0043] Based on the path probability and path duration of the at least one path, the target business process path corresponding to the account information is determined during the business process path selection process.

[0044] Optionally, the path selection unit includes an instruction acquisition subunit, a weight determination subunit, and a path selection subunit. The path selection unit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability and path duration corresponding to the at least one path.

[0045] The instruction acquisition subunit is used to receive selection instructions for path probability and path duration.

[0046] The weight determination subunit is used to determine the third weight corresponding to the path probability and the fourth weight corresponding to the path duration according to the selection instruction.

[0047] The path selection subunit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration.

[0048] Optionally, the path selection subunit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path consumption time corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path consumption time. Specifically, it is used for:

[0049] The path time corresponding to the at least one path is normalized to obtain the processed path time corresponding to the at least one path.

[0050] Based on the path probability corresponding to the at least one path, the path duration corresponding to the at least one processed path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

[0051] Optionally, the device further includes a model training unit for acquiring a set of historical account information and a set of historical node selection information corresponding to the set of historical account information;

[0052] Based on the set of historical node selection information, determine the first selection success probability corresponding to any given node;

[0053] The initial neural network model is trained based on the set of historical account information. When the second success probability of the initial neural network model matches the first success probability of the initial selection, the target neural network model is obtained.

[0054] According to one aspect of this application, a terminal is provided, comprising:

[0055] At least one processor; and

[0056] A memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method described in any one of the preceding aspects.

[0058] According to one aspect of this application, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described in any one of the preceding aspects.

[0059] According to one aspect of this application, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the method described in any one of the preceding aspects.

[0060] In one or more embodiments of this application, an account information set is obtained; first account information from the account information set is input into a target neural network model to obtain a first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node; second account information from the account information set is input into an artificial intelligence model to obtain the business time duration corresponding to any node; and the target business process path corresponding to the account information is determined during the business process path selection process based on the first probability and business time duration of at least one node in the business node set. Therefore, the process path can be determined based on the first probability of the node and the business time duration, reducing the possibility of uncertainty in the business path due to relying solely on the work experience and competence of the personnel involved. This can reduce the possibility of lengthy business processes, poor business results, or even business failures caused by improper selection, thereby increasing the success probability of business process selection and reducing the time duration of business processes, and thus improving the convenience and accuracy of business process selection.

[0061] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0062] The accompanying drawings are provided for a better understanding of this solution and do not constitute a limitation of this application. Wherein:

[0063] Figure 1 This diagram illustrates the background of a path selection method provided in an embodiment of this application.

[0064] Figure 2 A flowchart illustrating the first path selection method provided in an embodiment of this application is shown.

[0065] Figure 3A flowchart illustrating the second path selection method provided in an embodiment of this application is shown.

[0066] Figure 4 A flowchart illustrating the third path selection method provided in an embodiment of this application is shown.

[0067] Figure 5 A flowchart illustrating the fourth path selection method provided in an embodiment of this application is shown.

[0068] Figure 6 This diagram shows a structural schematic of the first path selection device provided in an embodiment of this application;

[0069] Figure 7 This diagram illustrates the structure of a second path selection device provided in an embodiment of this application.

[0070] Figure 8 This diagram illustrates the structure of the third path selection device provided in an embodiment of this application.

[0071] Figure 9 This diagram illustrates the structure of the fourth path selection device provided in an embodiment of this application.

[0072] Figure 10 This diagram illustrates the structure of the fifth path selection device provided in an embodiment of this application.

[0073] Figure 11 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Detailed Implementation

[0074] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0075] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this application, it should be noted that, unless otherwise expressly specified and limited, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist; for example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0076] With economic and technological development, and the increasing pace of life and work intensity, improving user experience has become a central focus for all industries. Every bank has various processes in place to improve the speed and success rate of business processing.

[0077] Optionally, each process has a fixed format, requiring completion step-by-step according to requirements. For nodes within a process, multiple choices often arise, resulting in different business flows depending on the specific business type, customer characteristics, and other factors. In most business scenarios, there are no pre-defined rules for choosing the next step at nodes with multiple options; rather, the personnel responsible for the task must determine which choice at the current node offers the most advantageous business flow in terms of functionality and timeliness.

[0078] In situations where different choices lead to different business workflows, relying solely on the experience and competence of the personnel involved can introduce significant uncertainty. This is especially true for inexperienced newcomers, who are prone to making inappropriate choices that result in lengthy processes, poor outcomes, or even process errors leading to business failure. Therefore, improving the success rate and efficiency of business process selection becomes a key focus for users.

[0079] For example, Figure 1 This diagram illustrates a background illustration of a path selection method provided in an embodiment of this application. For example... Figure 1As shown, the process includes multiple nodes. Boxes and their text represent nodes, arrows represent the sequence of steps in the process, text on the arrow lines describes the operational behavior, and numbers in parentheses represent the probability of success in proceeding to the current step. The probability of success in proceeding to the current step is obtained based on the neural network model and / or ensemble algorithm of this disclosure embodiment.

[0080] The present application will now be described in detail with reference to specific embodiments.

[0081] First Embodiment

[0082] In one embodiment, such as Figure 2 As shown, Figure 2 The diagram illustrates a flowchart of a first path selection method provided in an embodiment of this application. This method can be implemented using a computer program and can run on a device including a display screen. The computer program can be integrated into an application or run as a standalone utility application.

[0083] Specifically, the path selection method includes:

[0084] S101, Obtain the account information set;

[0085] According to some embodiments, the execution subject of this application embodiment is a path selection device. This path selection device can be a device with path selection function, or a device with a display screen. The path selection device can be a terminal with path selection function, including but not limited to: wearable devices, handheld devices, personal computers, tablets, in-vehicle devices, smartphones, computing devices, or other processing devices connected to a wireless modem. In different networks, the terminal can be called by different names, such as: user equipment, access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device, cellular phone, cordless phone, personal digital assistant (PDA), 5th generation mobile communication technology (5G) network, 4th generation mobile communication technology (4G) network, 3rd generation mobile communication technology (3G) network, or a terminal in a future evolved network, etc.

[0086] It is easy to understand that an account information set refers to a collection of at least one account information for the same user. This account information set does not refer to a specific, fixed set. For example, when the number of account information entries included in the account information set changes, the account information set itself may also change accordingly. Similarly, when the specific account information included in the account information set changes, the account information set itself may also change accordingly.

[0087] According to some embodiments, when a terminal device executes a node selection method, it can obtain a set of account information. For example, the terminal can obtain at least one set of account information.

[0088] S102, input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set;

[0089] According to some embodiments, a first subset of account information refers to a collection of at least one set of account information, and all account information included in the first subset is contained within a set of account information. This first subset of account information does not specifically refer to a fixed subset of account information; for example, the account information included in the first subset may be the same as the account information included in the set of account information. For instance, the account information included in the first subset may also be a portion of the account information included in the set of account information.

[0090] It's easy to understand that a target neural network model refers to a neural network model that has already been trained or fitted. This target neural network model does not specifically refer to a single, fixed neural network model. For example, when the specific model corresponding to the target neural network model changes, the target neural network model can also change accordingly. For example, when the model parameters corresponding to the target neural network model change, the target neural network model can also change accordingly. This target neural network model is used to predict the probability of a node being successfully selected. This target neural network model refers to a neural network model that can be applied to big data.

[0091] Optionally, a business node set refers to at least one business node included in a business process. This business node set does not specifically refer to a particular set of business nodes. Different business nodes are used to execute different business functions. The at least one node included in this business node set does not specifically refer to a fixed set. For example, when the number of nodes included in the business node set changes, the business node set can also change accordingly.

[0092] According to some embodiments, any node refers to any node included in the set of business nodes.

[0093] It is easy to understand that the first probability is used to indicate the predicted probability of successfully selecting any node. The "first" in the first probability is only used to distinguish it from the second probability. This first probability does not refer to a specific fixed probability. For example, when any node changes, the first probability may also change accordingly. For example, when the first subset of account information in the account information set changes, the first probability may also change accordingly.

[0094] In some embodiments, when the terminal device executes the node selection method, it can obtain a set of account information. The terminal device can input a first subset of account information from the set of account information into the target neural network model to obtain a first probability corresponding to any node in the set of business nodes.

[0095] S103, input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node;

[0096] According to some embodiments, the execution order of steps S102 and S103 is not limited. For example, the terminal may execute step S102 first and then step S103, or the terminal may execute step S103 first and then step S102, or execute steps S102 and S103 simultaneously.

[0097] It is easy to understand that the second subset of account information refers to the subset used to obtain the business time consumption duration corresponding to any node. This second subset of account information can be the same as or different from the first subset of account information. The "second" in the second subset of account information is only used to distinguish it from the first subset of account information and does not specifically refer to a fixed subset of account information. For example, if the account information included in the second subset changes, the second subset of account information can also change accordingly.

[0098] In some embodiments, the artificial intelligence model refers to a model used to obtain the duration of business operations, and this artificial intelligence model may be a pre-trained artificial intelligence model.

[0099] It is easy to understand that the business processing time refers to the time taken for the current node to enter the next node step. This business processing time can be, for example, the time required for any node.

[0100] In some embodiments, when a terminal device executes a node selection method, it can obtain a set of account information. The terminal device can input a second subset of account information from the set of account information into an artificial intelligence model to obtain the service duration corresponding to any node.

[0101] S104, Based on the first probability and business duration corresponding to at least one node in the business node set, determine the target business process path corresponding to the account information during the business process path selection process.

[0102] According to some embodiments, when the terminal obtains the first probability corresponding to at least one node in the service node set and the service consumption time corresponding to at least one node, the terminal can determine the target business process path corresponding to the account information during the business process path selection process based on the first probability corresponding to at least one node in the service node set and the service consumption time.

[0103] In one or more embodiments of this application, an account information set is obtained; first account information from the account information set is input into a target neural network model to obtain a first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node; second account information from the account information set is input into an artificial intelligence model to obtain the business time duration corresponding to any node; and the target business process path corresponding to the account information is determined during the business process path selection process based on the first probability and business time duration of at least one node in the business node set. Therefore, the process path can be determined based on the first probability of the node and the business time duration, reducing the possibility of uncertainty in the business path due to relying solely on the work experience and competence of the personnel involved. This can reduce the possibility of lengthy business processes, poor business results, or even business failures caused by improper selection, thereby increasing the success probability of business process selection and reducing the time duration of business processes, and thus improving the convenience and accuracy of business process selection.

[0104] Second Embodiment

[0105] Please see Figure 3 , Figure 3 This diagram illustrates a flowchart of the second path selection method provided in an embodiment of this application. Specifically:

[0106] S201, Obtain a collection of account information;

[0107] The specific process is as described above and will not be repeated here.

[0108] According to some embodiments, different business processes may correspond to different sets of account information.

[0109] In some embodiments, the set of account information may include, for example, age, gender, education level, credit score, etc.

[0110] S202, input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set;

[0111] The specific process is as described above and will not be repeated here.

[0112] According to some embodiments, the first probability is used to indicate the predicted probability of successfully selecting any node.

[0113] According to some embodiments, the method further includes: obtaining a set of historical account information and a set of historical node selection information corresponding to the set of historical account information; determining a first success probability for any node based on the set of historical node selection information; training an initial neural network model based on the set of historical account information; and obtaining a target neural network model when the second success probability corresponding to the initial neural network model matches the first success probability. Obtaining the target neural network model based on the first and second success probabilities can reduce the possibility of inaccurate first probabilities output by the target neural network model and improve the output accuracy of the neural network model.

[0114] In some embodiments, the historical node selection information set may include selection information for any given node, and a first selection success probability for any given node can be determined based on this historical node selection information set. The first selection success probability refers to the ratio of successful selection information for any given node in the historical node selection information set to the total selection information.

[0115] It is easy to understand that the second success probability refers to the probability obtained by training the initial neural network model with the set of historical account information. That is, the target neural network model can be obtained by fitting the initial neural network model based on the first success probability.

[0116] S203, input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node;

[0117] The specific process is as described above and will not be repeated here.

[0118] S204 displays the first probability and service duration for any given node.

[0119] According to some embodiments, when the terminal obtains the first probability corresponding to any node and the service consumption time corresponding to any node, the terminal can directly display the first probability corresponding to any node and the service consumption time corresponding to any node.

[0120] In one or more embodiments of this application, by obtaining an account information set, inputting a first subset of account information from the account information set into a target neural network model to obtain a first probability corresponding to any node in the business node set, and inputting a second subset of account information from the account information set into an artificial intelligence model to obtain the business time consumption time corresponding to any node, the first probability and business time consumption time corresponding to any node are displayed. Therefore, when determining the first probability and business time consumption time of a node, the first probability and business time consumption time of that node can be directly displayed, reducing the situation where relying solely on the work experience and competence of the personnel involved would lead to uncertainty in the first probability and business time consumption time. This can reduce the situation where improper selection leads to lengthy business processes, poor business results, or even business failures due to process errors, thereby increasing the success rate of business process selection and reducing the time consumption of business processes, and thus improving the convenience and accuracy of business process selection.

[0121] Third Embodiment

[0122] Please see Figure 4 , Figure 4 This diagram illustrates a flowchart of the third path selection method provided in an embodiment of this application. Specifically:

[0123] S301, retrieve account information set;

[0124] The specific process is as described above and will not be repeated here.

[0125] S302, input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set;

[0126] The specific process is as described above and will not be repeated here.

[0127] According to some embodiments, the first probability corresponding to any node in the service node set obtained by the terminal may be, for example, P1.

[0128] S303, based on the third subset of account information in the account information set and the ensemble algorithm, obtain the second probability corresponding to any node;

[0129] According to some embodiments, the ensemble algorithm includes, but is not limited to, XGboost, lightGBM, etc. This ensemble algorithm is used to correct the first probability.

[0130] As is easily understood, the third subset of account information refers to a subset of the account information set. This third subset of account information can be the same as the second subset of account information, or it can be the same as the first subset of account information. The "third" in this third subset of account information is only used to distinguish it from the other subsets of account information.

[0131] Optionally, the terminal can obtain a second probability corresponding to any node based on a third subset of account information in the account information set and an ensemble algorithm. The second probability obtained by the terminal could be, for example, P2.

[0132] S304, Based on the first probability and the second probability, the first probability is corrected to obtain the corrected first probability;

[0133] According to some embodiments, when the terminal obtains a first probability and a second probability, it can modify the first probability based on the first probability and the second probability to obtain a modified first probability.

[0134] It is easy to understand that when the terminal corrects the first probability, it can determine the first weight corresponding to the first probability and the weight corresponding to the second probability. After weighting the first probability and the second probability, the corrected first probability can be obtained.

[0135] Optionally, the weighted calculation formula can be, for example, as shown in formula (1).

[0136] P = First weight * P1 + Second weight * P2 (1)

[0137] According to some embodiments, the first weight may be, for example, 0.95, and the second weight may be, for example, 0.05.

[0138] S305, input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node;

[0139] The specific process is as described above and will not be repeated here.

[0140] According to some embodiments, the terminal can use artificial intelligence models and logistic regression algorithms to obtain the service duration corresponding to any node.

[0141] In essence, the terminal can obtain a set of historical account information and the corresponding historical node consumption durations. Using these historical node consumption durations as the objective function, it performs a fitting prediction, ensuring that the difference between the predicted business consumption duration output by the AI ​​model and logistic regression algorithm and a duration threshold meets the model requirements. For example, the predicted business consumption duration could be T0. The terminal can determine the duration standard deviation σ0 based on the historical node consumption durations corresponding to the historical account information set. When the predicted business consumption duration falls within the interval I = [T0 - 1.5 * σ0, T0 + 1.5 * σ0], the obtained AI model and logistic regression algorithm are deemed to meet the duration acquisition requirements.

[0142] S306, Based on the corrected first probability and business duration corresponding to at least one node in the business node set, determine the target business process path corresponding to the account information during the business process path selection process.

[0143] The specific process is as described above and will not be repeated here.

[0144] According to some embodiments, when a target business process path corresponding to account information is determined during the business process path selection process, the terminal can display the target business process path. When the terminal obtains the first probability corresponding to any node in the set of business nodes and the business time consumption corresponding to any node, it can obtain the probability of that node being selected in historical data records, as well as the operation failure information corresponding to that node. The terminal can then display this operation failure information. This operation failure information includes historical failure selection probabilities, main reasons for failure, etc.

[0145] In one or more embodiments of this application, by obtaining an account information set, a first subset of account information in the account information set is input into a target neural network model to obtain a first probability corresponding to any node in the business node set. Based on a third subset of account information in the account information set and an ensemble algorithm, a second probability corresponding to any node is obtained. The first probability is then corrected based on the first and second probabilities to obtain a corrected first probability. Therefore, the first probability can be corrected, improving the accuracy of its acquisition and thus the accuracy of business path determination. Next, the second subset of account information in the account information set is input into an artificial intelligence model to obtain the business time duration corresponding to any node. Based on the corrected first probability and business time duration corresponding to at least one node in the business node set, the target business process path corresponding to the account information is determined during the business process path selection process. Therefore, the process path can be determined based on the first probability of the node and the business time duration. This reduces the possibility of uncertainty in the business path due to relying solely on the work experience and competence of the personnel in charge. It can also reduce the possibility of lengthy business processes, poor business results, or even business failures caused by improper selection. This can increase the success rate of business process selection and reduce the time duration of business processes, thereby improving the convenience and accuracy of business process selection.

[0146] Fourth embodiment

[0147] Please see Figure 5 , Figure 5 This diagram illustrates a flowchart of the fourth path selection method provided in an embodiment of this application. Specifically:

[0148] S401, retrieve account information set;

[0149] The specific process is as described above and will not be repeated here.

[0150] S402, input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set;

[0151] The specific process is as described above and will not be repeated here.

[0152] S403, input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node;

[0153] The specific process is as described above and will not be repeated here.

[0154] S404, based on the first probability corresponding to at least one node in the business node set, obtain the path probability corresponding to at least one path;

[0155] The specific process is as described above and will not be repeated here.

[0156] According to some embodiments, when a terminal obtains a first probability corresponding to at least one node in a set of service nodes, the terminal can determine the node corresponding to at least one path. Based on the first probability corresponding to the node of the at least one path, the path probability corresponding to the at least one path can be obtained. This path probability refers to the probability that the path will be successfully executed.

[0157] S405, based on the business time duration corresponding to at least one node in the business node set, obtain the path time duration corresponding to at least one path;

[0158] The specific process is as described above and will not be repeated here.

[0159] According to some embodiments, when a terminal obtains the service duration corresponding to at least one node in a service node set, the terminal can determine the node corresponding to at least one path. Based on the service duration corresponding to the node of the at least one path, the path duration corresponding to the at least one path can be obtained. The path duration refers to the time taken to complete the execution of the path.

[0160] S406, Based on the path probability and path duration of at least one path, determine the target business process path corresponding to the account information during the business process path selection process.

[0161] According to some embodiments, when the path probability and path duration of at least one path are obtained, the target business process path corresponding to the account information can be determined during the business process path selection process based on the path probability and path duration of at least one path.

[0162] According to some embodiments, when determining the target business process path corresponding to account information during the business process path selection process based on the path probability and path duration corresponding to at least one path, a selection instruction for the path probability and path duration can be received; based on the selection instruction, a third weight corresponding to the path probability and a fourth weight corresponding to the path duration are determined; by determining the target business process path corresponding to account information during the business process path selection process based on the path probability, the path duration corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the accuracy of the target business process path determination can be improved, and the mismatch between the target business process path and the selection instruction can be reduced.

[0163] According to some embodiments, when determining the target business process path corresponding to account information during the business process path selection process based on the path probability corresponding to at least one path, the path duration corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the path duration corresponding to at least one path can be normalized to obtain the processed path duration corresponding to at least one path; the target business process path corresponding to account information during the business process path selection process is determined based on the path probability corresponding to at least one path, the processed path duration corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration.

[0164] According to some embodiments, when the terminal obtains the first probability corresponding to at least one node in the service node set, it can traverse all possible path process combinations and multiply the success rate of the path operation (i.e., the first probability) of each node in the path combination to obtain the final success rate prediction value P of the path process. final The time T of each path step in the path combination. o The final predicted time T for this path process is obtained by adding them together. final .

[0165] It is easy to understand that the terminal can transmit T final The numerical values ​​are normalized. A specific method could be to organize the calculated time for all paths into a set T, and then... final Transform it into its quantile value T in dataset T quan This value must be within the range of 0-1, so that it can be compared with the success rate prediction value P. final Correspondingly. Finally, put T quan and P final The final score S = ω1*T is obtained by weighting and combining the results. quan +ω2*P finalWhere ω1 + ω2 = 1, they are T quan and P final The weight of ω1 has no fixed value and can be determined based on the selection command. It depends on whether success rate or time consumption is prioritized. ω1 is the fourth weight, and ω2 is the third weight. The terminal can select the process path with the highest final score S as the target business process path.

[0166] In one or more embodiments of this application, by obtaining an account information set, inputting a first subset of account information from the account information set into a target neural network model to obtain a first probability corresponding to any node in the business node set, inputting a second subset of account information from the account information set into an artificial intelligence model to obtain the business time duration corresponding to any node, obtaining the path probability corresponding to at least one path based on the first probability corresponding to at least one node in the business node set, and obtaining the path time duration corresponding to at least one path based on the business time duration corresponding to at least one node in the business node set; and determining the target business process path corresponding to the account information during the business process path selection process based on the path probability and the path time duration corresponding to at least one path. Therefore, based on the first probability of the node and the business time duration, the path probability and the path time duration corresponding to at least one path can be determined to determine the process path. This reduces the situation where relying solely on the work experience and competence of the personnel involved leads to uncertainty in the business path, reduces the possibility of inappropriate selection resulting in lengthy business processes, poor business results, or even business failures due to process errors, improves the success probability of business process selection, and reduces the time duration of business processes, thereby improving the convenience and accuracy of business process selection.

[0167] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0168] Please see Figure 6 This illustration shows a schematic diagram of the structure of a first path selection device provided in an exemplary embodiment of this application. The path selection device can be implemented as all or part of a device through software, hardware, or a combination of both. The path selection device 600 includes a set acquisition unit 601, a probability acquisition unit 602, a duration acquisition unit 603, and a path selection unit 604, wherein:

[0169] The set acquisition unit 601 is used to acquire a set of account information;

[0170] The probability acquisition unit 602 is used to input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node;

[0171] The duration acquisition unit 603 is used to input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node.

[0172] The path selection unit 604 is used to determine the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set.

[0173] According to some embodiments, Figure 7 This diagram illustrates the structure of a second path selection device provided in an embodiment of this application. Figure 7 As shown, the device 600 also includes a duration display unit 605, which is used to display the first probability and the duration of the service corresponding to any node after obtaining the service duration corresponding to any node.

[0174] According to some embodiments, Figure 8 This diagram illustrates the structure of a third path selection device provided in an embodiment of this application. Figure 8 As shown, the probability acquisition unit 602 includes a probability acquisition subunit 612 and a probability correction subunit 622. The probability acquisition unit 602 is used to input a first subset of account information from the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set:

[0175] The probability acquisition subunit 612 is used to input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set.

[0176] The probability acquisition subunit 612 is also used to obtain the second probability corresponding to any node based on the third account information subset in the account information set and the ensemble algorithm;

[0177] The probability correction subunit 622 is used to correct the first probability based on the first probability and the second probability to obtain the corrected first probability.

[0178] According to some embodiments, when determining the target business process path corresponding to the account information during the business process path selection process based on the first probability and business duration corresponding to at least one node in the business node set, the path selection unit 604 is specifically used for:

[0179] Based on the first probability corresponding to at least one node in the business node set, obtain the path probability corresponding to at least one path.

[0180] Based on the business time duration corresponding to at least one node in the business node set, obtain the path time duration corresponding to at least one path.

[0181] Based on the path probability and path duration of at least one path, the target business process path corresponding to the account information is determined during the business process path selection process.

[0182] According to some embodiments, Figure 9 This diagram illustrates the structure of a fourth path selection device provided in an embodiment of this application. Figure 9 As shown, the path selection unit 604 includes an instruction acquisition subunit 614, a weight determination subunit 624, and a path selection subunit 634. The path selection unit 604 is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability and path consumption time of at least one path.

[0183] The instruction acquisition subunit 614 is used to receive selection instructions for path probability and path duration.

[0184] The weight determination subunit 624 is used to determine the third weight corresponding to the path probability and the fourth weight corresponding to the path duration based on the selection instruction.

[0185] The path selection subunit 634 is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path consumption time corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path consumption time.

[0186] According to some embodiments, the path selection subunit 634 is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path consumption time corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path consumption time. Specifically, it is used for:

[0187] Normalize the path time for at least one path to obtain the processed path time for at least one path.

[0188] Based on the path probability corresponding to at least one path, the path duration corresponding to at least one processed path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

[0189] According to some embodiments, Figure 10 This diagram illustrates the structure of the fifth path selection device provided in an embodiment of this application. Figure 10 As shown, the device 600 also includes a model training unit 606, used to obtain a set of historical account information and a set of historical node selection information corresponding to the set of historical account information;

[0190] Based on the historical node selection information set, determine the probability of success of the first selection for any given node;

[0191] The initial neural network model is trained based on the set of historical account information. When the success probability of the second choice corresponding to the initial neural network model matches the success probability of the first choice, the target neural network model is obtained.

[0192] It should be noted that the path selection device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the path selection method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the path selection device and the path selection method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0193] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0194] In one or more embodiments of this application, a set acquisition unit is used to acquire a set of account information; a probability acquisition unit is used to input a first subset of account information from the set of account information into a target neural network model to acquire a first probability corresponding to any node in the set of business nodes, wherein the first probability is used to indicate the predicted probability of successfully selecting any node; a duration acquisition unit is used to input a second subset of account information from the set of account information into an artificial intelligence model to acquire the business time duration corresponding to any node; and a path selection unit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the first probability and business time duration of at least one node in the set of business nodes. Therefore, the process path can be determined based on the first probability of the node and the business time duration, reducing the situation where relying solely on the work experience and competence of the personnel involved leads to uncertainty in the business path. This can reduce the situation where improper selection leads to lengthy business processes, poor business results, or even business failures due to process errors. It can improve the success probability of business process selection and reduce the time duration of business processes, thereby improving the convenience and accuracy of business process selection.

[0195] This application also provides a computer storage medium that can store multiple instructions, which are adapted to be loaded and executed by a processor as described above. Figures 2-5 The path selection method described in the illustrated embodiment can be found in the following document for a detailed execution process: Figures 2-5 The specific details of the illustrated embodiments will not be elaborated here.

[0196] This application also provides a computer program product storing at least one instruction, which is loaded and executed by the processor as described above. Figures 2-5 The path selection method described in the illustrated embodiment can be found in the following documentation for its specific execution process. Figures 2-5 The specific details of the illustrated embodiments will not be elaborated here.

[0197] Please see Figure 11 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application. Figure 11 As shown, the terminal 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102.

[0198] The communication bus 1102 is used to realize the connection and communication between these components.

[0199] The user interface 1103 may include a camera and a display screen. Optionally, the user interface 1103 may also include a standard wired interface or a wireless interface.

[0200] The network interface 1104 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0201] The processor 1101 may include one or more processing cores. The processor 1101 connects to various parts within the terminal 1100 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling data stored in the memory 1105. Optionally, the processor 1101 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1101 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 1101.

[0202] The memory 1105 may include random access memory (RAM) or read-only memory. Optionally, the memory 1105 may include a non-transitory computer-readable storage medium. The memory 1105 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1105 may also be at least one storage device located remotely from the aforementioned processor 1101. Figure 11 As shown, the memory 1105, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for path selection.

[0203] exist Figure 11In the terminal 1100 shown, the user interface 1103 is mainly used to provide an input interface for the user and obtain the user input data; while the processor 1101 can be used to call the path selection application stored in the memory 1105 and specifically execute the above methods.

[0204] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0205] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the terminal state determination methods described in the above method embodiments.

[0206] Those skilled in the art will clearly understand that the technical solutions of this application can be implemented using software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware capable of independently performing or cooperating with other components to perform specific functions. Hardware may include, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0207] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0208] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0209] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0210] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0211] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0212] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0213] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0214] The above description is merely an exemplary embodiment of this application and should not be construed as limiting the scope of this application. Any equivalent changes and modifications made in accordance with the teachings of this application shall still fall within the scope of this application. Those skilled in the art will readily conceive of other embodiments of this application upon considering the specification and practicing the application herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are considered exemplary only, and the scope and spirit of this application are defined by the claims.

Claims

1. A path selection method characterized by, include: Retrieve a collection of account information; The first subset of account information in the account information set is input into the target neural network model to obtain the first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node; Input the second subset of account information from the account information set into the artificial intelligence model to obtain the business time duration corresponding to any node; Based on the first probability and business duration corresponding to at least one node in the business node set, the target business process path corresponding to the account information is determined during the business process path selection process.

2. The method of claim 1, wherein, After obtaining the service consumption time corresponding to any of the nodes, the process further includes: Display the first probability corresponding to any of the nodes and the service duration.

3. The method of claim 1, wherein, The step of inputting a first subset of account information from the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set includes: Input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set; Based on the third subset of account information in the account information set and the integration algorithm, obtain the second probability corresponding to any node; Based on the first probability and the second probability, the first probability is corrected to obtain the corrected first probability.

4. The method of claim 1, wherein, The step of determining the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set includes: Based on the first probability corresponding to at least one node in the set of business nodes, obtain the path probability corresponding to at least one path. Based on the service time duration corresponding to at least one node in the service node set, obtain the path time duration corresponding to the at least one path; Based on the path probability and path duration of the at least one path, the target business process path corresponding to the account information is determined during the business process path selection process.

5. The method of claim 4, wherein, The step of determining the target business process path corresponding to the account information during the business process path selection process based on the path probability and path duration of the at least one path includes: Receive selection instructions for path probability and path duration; Based on the selection instruction, determine the third weight corresponding to the path probability and the fourth weight corresponding to the path duration; Based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

6. The method of claim 5, wherein, The step of determining the target business process path corresponding to the account information during the business process path selection process, based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, includes: The path time corresponding to the at least one path is normalized to obtain the processed path time corresponding to the at least one path. Based on the path probability corresponding to the at least one path, the path duration corresponding to the at least one processed path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

7. The method of claim 1, wherein, The method further includes: Obtain a set of historical account information and a set of historical node selection information corresponding to the set of historical account information; Based on the set of historical node selection information, determine the first selection success probability corresponding to any given node; The initial neural network model is trained based on the set of historical account information. When the second success probability of the initial neural network model matches the first success probability of the initial selection, the target neural network model is obtained.

8. A path selection apparatus characterized by comprising: include: The collection retrieval unit is used to retrieve a collection of account information. The probability acquisition unit is used to input a first subset of account information in the account information set into the target neural network model to obtain a first probability corresponding to any node in the business node set, wherein the first probability is used to indicate the predicted probability of successfully selecting any node. The duration acquisition unit is used to input the second subset of account information in the account information set into the artificial intelligence model to obtain the business consumption duration corresponding to any node. The path selection unit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set.

9. The apparatus according to claim 8, characterized in that, The device further includes a duration display unit, which is used to display the first probability corresponding to any node and the duration of the service consumption corresponding to any node after obtaining the service consumption duration corresponding to any node.

10. The apparatus according to claim 8, characterized in that, The probability acquisition unit includes a probability acquisition subunit and a probability correction subunit. The probability acquisition unit is used to input a first subset of account information from the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set: The probability acquisition subunit is used to input the first subset of account information in the account information set into the target neural network model to obtain the first probability corresponding to any node in the business node set. The probability acquisition subunit is further configured to acquire the second probability corresponding to any node based on the third account information subset in the account information set and the integration algorithm; The probability correction subunit is used to correct the first probability based on the first probability and the second probability to obtain the corrected first probability.

11. The apparatus of claim 8, wherein, The path selection unit, when determining the target business process path corresponding to the account information during the business process path selection process based on the first probability and business consumption time of at least one node in the business node set, is specifically used for: Based on the first probability corresponding to at least one node in the set of business nodes, obtain the path probability corresponding to at least one path. Based on the service time duration corresponding to at least one node in the service node set, obtain the path time duration corresponding to the at least one path; Based on the path probability and path duration of the at least one path, the target business process path corresponding to the account information is determined during the business process path selection process.

12. The apparatus of claim 11, wherein, The path selection unit includes an instruction acquisition subunit, a weight determination subunit, and a path selection subunit. The path selection unit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability and path duration corresponding to the at least one path. The instruction acquisition subunit is used to receive selection instructions for path probability and path duration. The weight determination subunit is used to determine the third weight corresponding to the path probability and the fourth weight corresponding to the path duration according to the selection instruction. The path selection subunit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path duration corresponding to the at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration.

13. The apparatus according to claim 12, characterized in that, The path selection subunit is used to determine the target business process path corresponding to the account information during the business process path selection process based on the path probability corresponding to at least one path, the path consumption time corresponding to at least one path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path consumption time. Specifically, it is used for: The path time corresponding to the at least one path is normalized to obtain the processed path time corresponding to the at least one path. Based on the path probability corresponding to the at least one path, the path duration corresponding to the at least one processed path, the third weight corresponding to the path probability, and the fourth weight corresponding to the path duration, the target business process path corresponding to the account information is determined during the business process path selection process.

14. The apparatus of claim 8, wherein, The device further includes a model training unit, used to obtain a set of historical account information and a set of historical node selection information corresponding to the set of historical account information; Based on the set of historical node selection information, determine the first selection success probability corresponding to any given node; The initial neural network model is trained based on the set of historical account information. When the second success probability of the initial neural network model matches the first success probability of the initial selection, the target neural network model is obtained.

15. A terminal, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-7.

17. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-7.

Images