Profit distribution settlement control method and device based on reference chain contribution evaluation

Abstract

The application relates to a profit distribution settlement control method and device based on referral chain contribution evaluation, which comprises the following steps: calling a preset contribution evaluation model, calculating and determining the contribution score of an intermediate referral node according to the propagation distance factor, response timeliness score, historical matching success rate and credit activity fusion index of the intermediate referral node; calculating the distribution profit amount corresponding to each intermediate referral node according to the contribution score of each intermediate referral node, and calling the corresponding payment interface to transfer the distribution profit amount to the corresponding intermediate referral node; and packing the profit distribution key data corresponding to the profit distribution settlement process to generate a summary hash, and writing the summary hash into a block chain or a judicial evidence platform for evidence preservation, so as to complete the profit distribution settlement control based on the referral chain contribution evaluation. The application can greatly improve the fairness of the referral chain profit distribution settlement.

Description

Technical Field

[0001] This application relates to the field of data processing, and in particular to a profit distribution settlement control method and corresponding apparatus based on referral chain contribution assessment. Background Technology

[0002] In internet platforms such as resource sharing, social e-commerce, and online consulting, to incentivize users to actively spread their needs and refer high-quality resources, platforms typically implement profit-sharing mechanisms. This means that after a transaction is completed, intermediaries at each node in the referral chain receive a certain percentage of the revenue as a reward according to pre-defined rules. A reasonable profit-sharing mechanism is a crucial driver of platform user growth and ecosystem activity. However, existing profit distribution and settlement methods still suffer from the following technical shortcomings:

[0003] First, the contribution assessment method is subjective and the allocation is not fair enough. Existing schemes mostly adopt a fixed-level proportional allocation model, which strongly binds the allocation ratio to the referral level and fails to take into account the differentiated contributions of the referrer in the transaction process.

[0004] Secondly, the settlement process is cumbersome and relies on manual intervention. From profit sharing calculation and fund allocation to tax processing, each step still relies heavily on manual operation, which not only results in low efficiency but also easily introduces human errors such as calculation errors, omissions, and incorrect payments, making it difficult to support the platform's large-scale operation needs.

[0005] Third, there is a centralized trust risk in fund management. The profit-sharing funds are centrally controlled by the platform's centralized account. The process of fund collection, retention, and allocation lacks effective third-party supervision and public verification mechanisms, which poses trust risks such as misappropriation, malicious retention, or delayed payment, thereby harming the rights and interests of the referrer.

[0006] Fourth, referral chain data is easily tampered with, making it difficult to trace the source of disputes. Referral chain records are mostly stored in the platform's centralized database, and the platform has the technical capability to unilaterally modify the data. Once a profit-sharing dispute occurs, it is difficult to provide credible evidence with legal force, increasing the difficulty of dispute resolution and arbitration costs.

[0007] In summary, in view of the problems existing in the technology, such as subjective contribution assessment methods, insufficient fund security and weak data anti-tampering capabilities, the applicant has made corresponding explorations to solve these problems. Summary of the Invention

[0008] The purpose of this application is to solve the above problems by providing a profit distribution settlement control method and corresponding apparatus based on referral chain contribution assessment.

[0009] To achieve the various objectives of this application, the following technical solution is adopted:

[0010] A profit distribution settlement control method based on referral chain contribution assessment, proposed to meet one of the purposes of this application, includes:

[0011] In response to the current demand completion event of the Internet platform to trigger the profit distribution and settlement process, the referral chain node sequence corresponding to the current demand is obtained, wherein the referral chain node sequence includes at least one intermediate referral node;

[0012] For each intermediate referral node in the referral chain node sequence, a propagation distance factor is determined based on the number of referral levels between the intermediate referral node and the demand solver; a response timeliness score is determined based on the demand response time and demand release time of the intermediate referral node; a historical matching success rate is determined based on the proportion of demands referred by the intermediate referral node within a preset historical period; and a credit activity fusion index is determined based on the credit score and activity score of the intermediate referral node.

[0013] The preset contribution evaluation model is invoked, and the contribution score of the intermediate referral node is calculated and determined based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node.

[0014] Based on the contribution scores of each intermediate referral node, calculate the allocated profit amount for each intermediate referral node, and call its corresponding payment interface to transfer the allocated profit amount to its corresponding intermediate referral node.

[0015] The key data of profit distribution corresponding to the profit distribution settlement process is packaged to generate a digest hash, which is then written into a blockchain or judicial evidence storage platform for evidence storage, so as to complete the profit distribution settlement control based on the referral chain contribution assessment.

[0016] Optionally, the step of determining the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver includes:

[0017] Obtain the referral level between the intermediate referral node and the demand solver in the referral chain node sequence;

[0018] The reciprocal of the referral level number is used as the propagation distance factor of the intermediate referral node.

[0019] Optionally, the step of determining the response timeliness score based on the demand response time and demand release time of the intermediate referral node includes:

[0020] Obtain the demand response time of the intermediate referral node and the demand release time of the demand initiator;

[0021] Calculate and determine a first difference between the demand response time and the demand release time to determine the demand response time difference;

[0022] Calculate the first ratio between the demand response time difference and the demand timeliness threshold, and calculate the second difference between the first value and the first ratio;

[0023] The maximum value between the second difference and zero is taken as the response time score of the intermediate referral node.

[0024] Optionally, the step of determining the credit activity fusion index based on the credit score and activity score of the intermediate referral node includes:

[0025] Obtain the credit score and its corresponding credit score weight, activity score and its corresponding activity score weight of the intermediate referral node, wherein the credit score ranges from zero to one hundred, and the activity score ranges from zero to nine hundred and ninety-nine.

[0026] Calculate a second ratio between the credit score and the value of one hundred, and calculate and determine a first product between the second ratio and the weight of the credit score;

[0027] Calculate the third ratio between the activity score and the value 999, and calculate and determine the second product between the third ratio and the activity score weight;

[0028] Calculate the first sum between the first product and the second product, and use the first sum as the credit activity fusion index of the intermediate referral node.

[0029] Optionally, the steps for constructing a contribution assessment model include:

[0030] Obtain the first weight coefficient corresponding to the propagation distance factor, the second weight coefficient corresponding to the response time score, the third weight coefficient corresponding to the historical matching success rate, and the fourth weight coefficient corresponding to the credit activity fusion index of the intermediate referral node, wherein the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient is a value of one;

[0031] Calculate the third product between the propagation distance factor and the first weight coefficient, calculate the fourth product between the response time score and the second weight coefficient, calculate the fifth product between the historical matching success rate and the third weight coefficient, and calculate the sixth product between the credit activity fusion index and the fourth weight coefficient;

[0032] Calculate the second sum among the third, fourth, fifth, and sixth products, and use the second sum as the contribution score of the intermediate referral node to construct a contribution evaluation model.

[0033] Optionally, the step of determining the initial values ​​of the first, second, third, and fourth weighting coefficients of the contribution assessment model includes:

[0034] When the internet platform has no historical operational data, the analytic hierarchy process is used to determine the initial weights. Multiple platform operation experts compare and assign values ​​to the importance of the propagation distance factor, the response timeliness score, the historical matching success rate, and the credit activity fusion index in pairs to construct a judgment matrix.

[0035] The judgment matrix is ​​normalized, and the maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated.

[0036] Calculate the consistency ratio of the judgment matrix. When the consistency ratio is less than a preset threshold, determine the acceptable consistency of the judgment matrix. Normalize the feature vector and use it as the initial weight vector. The initial weight vector includes the initial values ​​of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient.

[0037] Optionally, the steps of updating the first, second, third, and fourth weighting coefficients of the contribution assessment model include:

[0038] When the number of historical profit distribution transactions accumulated by the Internet platform reaches a preset threshold, the average satisfaction score of all intermediate referral nodes in the historical profit distribution transactions on the profit distribution settlement results is obtained, and the objective function is to maximize the average satisfaction score.

[0039] The weight vector is used as the optimization variable, wherein the weight vector is constructed by the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient, and the constraint is that the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient is one, and each weight coefficient is greater than or equal to zero.

[0040] The particle swarm optimization algorithm iteratively searches for the weight combination that maximizes the objective function, updating the particle position and velocity in each iteration until a preset number of iterations is reached or the objective function value converges.

[0041] The optimized weight coefficients are updated in the weight configuration table and used as the current values ​​of each weight coefficient in the subsequent profit distribution settlement.

[0042] Optionally, after calling a preset contribution evaluation model and calculating the contribution score of the intermediate referral node based on the propagation distance factor, response timeliness score, historical matching success rate, and credit activity fusion index, the process includes:

[0043] Obtain the contribution score of each intermediate referral node, calculate the overall quality score of the referral chain, and when the overall quality score of the referral chain is higher than the preset quality score threshold, mark the referral chain as a high-quality referral pattern and store it in the pattern library; in subsequent demand referral matching, use the path with the highest similarity to the propagation path of the high-quality referral pattern in the pattern library for demand diffusion.

[0044] The contribution scores of the intermediate referral nodes are aggregated and statistically analyzed in multiple dimensions according to the scenario dimension and / or organization dimension to generate operational indicators under the scenario dimension and / or organization dimension. When the operational indicators meet the preset conditions, the corresponding operational actions are automatically triggered, and the operational indicators are displayed in real time on the platform management backend. The operational indicators include at least one of the following: the average contribution score of the intermediate referral nodes in each scenario, the proportion of high-contribution users in each organization, and the time-series change trend of the contribution scores.

[0045] Optionally, the step of calculating the profit allocation amount corresponding to each intermediate referral node based on the contribution score of each intermediate referral node includes:

[0046] For a single referral chain, obtain the total amount of the current required profit distribution pool, and the contribution score of each intermediate referral node in the referral chain node sequence. Calculate the sum of the contribution scores of all intermediate referral nodes and determine it as the total contribution score.

[0047] For each intermediate referral node, its corresponding contribution score is divided by the total contribution score to obtain the contribution percentage of the intermediate referral node.

[0048] Multiply the total amount of the profit distribution pool by the contribution ratio of the intermediate referral node to obtain the initial profit amount allocated to the intermediate referral node.

[0049] When the initial allocated profit amount exceeds the preset single-node allocation limit, the initial allocated profit amount is truncated to the single-node allocation limit, and the excess portion is redistributed to other intermediate referral nodes according to the contribution ratio of each intermediate referral node.

[0050] When the initial allocated profit amount does not exceed the single node allocation limit, the initial allocated profit amount is directly used as the final allocated profit amount for the intermediate referral node.

[0051] A profit distribution settlement control device based on referral chain contribution assessment, provided for another purpose of this application, includes:

[0052] The referral chain acquisition module is configured to respond to the current demand completion event of the Internet platform to trigger the profit distribution settlement process, and acquire the referral chain node sequence corresponding to the current demand, wherein the referral chain node sequence includes at least one intermediate referral node.

[0053] The contribution parameter determination module is configured to determine the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver for each intermediate referral node in the referral chain node sequence; determine the response timeliness score based on the demand response time and demand release time of the intermediate referral node; determine the historical matching success rate based on the proportion of demands referred by the intermediate referral node within a preset historical period; and determine the credit activity fusion index based on the credit score and activity score of the intermediate referral node.

[0054] The contribution evaluation module is set to call a preset contribution evaluation model and calculate the contribution score of the intermediate referral node based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node.

[0055] The profit distribution and settlement module is configured to calculate the profit distribution amount corresponding to each intermediate referral node based on the contribution score of each intermediate referral node, and call its corresponding payment interface to transfer the profit distribution amount to its corresponding intermediate referral node.

[0056] The profit distribution notarization module is configured to package the key profit distribution data corresponding to the profit distribution settlement process, generate a digest hash, and write it into a blockchain or judicial notarization platform for notarization, so as to complete the profit distribution settlement control based on the referral chain contribution assessment.

[0057] Compared to existing technologies, this application addresses the problems of subjective contribution assessment methods, insufficient fund security, and weak data tamper resistance in existing technologies. This application offers the following beneficial effects, including but not limited to:

[0058] First, this application breaks through the limitations of the existing fixed-level proportional allocation model. By constructing a contribution evaluation model that integrates propagation distance factor, response time score, historical matching success rate and credit activity index, it quantifies the referrer's position value in the propagation chain, the initiative to respond to demand, the effectiveness of historical referrals, and the platform's reputation and participation activity.

[0059] Secondly, this application uses contribution score as the sole basis for allocation. The profit amount allocated to each intermediate referral node is directly proportional to its contribution score relative to the total contribution score, and the allocation rules are transparent and verifiable. At the same time, an event-driven mechanism enables fully automated, unattended operation of the entire process from triggering, calculation, payment to evidence storage, avoiding the inefficiency and errors of manual operation and directly linking the allocation results to objective contribution.

[0060] Third, this application packages key profit distribution data into a digest hash and writes it to a blockchain or judicial evidence storage platform for preservation. Any modification to the original data can be quickly identified through hash verification, ensuring the authenticity and traceability of the profit distribution basis and results, providing credible evidence with judicial validity for dispute arbitration, and effectively restraining the platform's unilateral data tampering behavior.

[0061] Fourth, at the path quality analysis level, high-quality referral patterns are identified and stored in the pattern library by calculating the overall quality score of the referral chain. In subsequent demand matching, the high-quality propagation path with the highest similarity is prioritized, so that the data accumulated in a single profit sharing is transformed into strategic assets for continuously optimizing referral efficiency. At the operation dashboard level, contribution scores are aggregated in multiple dimensions by scenario and organization, generating operational indicators such as average contribution of each scenario, proportion of high-contribution users in each organization, and time-series trend of contribution changes. These indicators are displayed in real time and can automatically trigger operational actions when the indicators meet preset conditions, thus upgrading the profit sharing settlement module from a one-time calculation tool to a continuous data-driven engine.

[0062] Fifth, this application utilizes data accumulated from feedback to drive adaptive optimization of weight coefficients. In the early stages of the platform's launch, the analytic hierarchy process (AHP) is used to scientifically determine the initial weights, avoiding arbitrary settings. After accumulating sufficient historical data, with the goal of maximizing the average satisfaction of referrers, the particle swarm optimization algorithm is used to automatically iterate and search for the optimal weight combination and update it to the weight configuration table monthly. At the same time, different business scenarios use independent weight configurations for separate optimization, enabling the weight coefficients to evolve from manually static settings to a data-driven, continuously optimized adaptive mechanism, ensuring the long-term effectiveness of the evaluation model. Attached Figure Description

[0063] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0064] Figure 1 This is a flowchart illustrating the profit distribution and settlement control method based on referral chain contribution assessment in the embodiments of this application.

[0065] Figure 2 This is a schematic diagram illustrating the process of determining the historical matching success rate in an embodiment of this application;

[0066] Figure 3This is a schematic diagram of the process for determining the propagation distance factor in an embodiment of this application;

[0067] Figure 4 This is a flowchart illustrating the process of determining the response timeliness score in an embodiment of this application;

[0068] Figure 5 This is a flowchart illustrating the process of determining the credit activity fusion index in the embodiments of this application;

[0069] Figure 6 This is a schematic diagram illustrating the process of constructing the contribution evaluation model in an embodiment of this application;

[0070] Figure 7 This is a flowchart illustrating the process of determining initial weights using the analytic hierarchy process in an embodiment of this application.

[0071] Figure 8 This is a schematic diagram of the process of updating weight coefficients using the particle swarm optimization algorithm in the embodiments of this application;

[0072] Figure 9 This is a schematic diagram illustrating the process of demand diffusion in this embodiment of the application, which uses the path with the highest similarity to the propagation path of high-quality referral patterns in the pattern library.

[0073] Figure 10 This is a flowchart illustrating the process of calculating the allocated profit amount for each intermediate referral node in this embodiment of the application.

[0074] Figure 11 This is a schematic diagram of the profit distribution settlement control device based on referral chain contribution assessment in the embodiments of this application;

[0075] Figure 12 This is a schematic diagram of the structure of the computer device in the embodiments of this application. Detailed Implementation

[0076] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0077] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof. It should be understood that when we say an element is “connected” or “coupled” to another element, it can be directly connected or coupled to the other element, or there may be intermediate elements. Furthermore, “connected” or “coupled” as used herein can include wireless connections or wireless coupling. The term “and / or” as used herein includes all or any units and all combinations of one or more associated listed items.

[0078] It will be understood by those skilled in the art that, unless otherwise defined, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. It should also be understood that terms such as those defined in general dictionaries should be understood to have the same meaning as in the context of the prior art, and should not be interpreted in an idealized or overly formal sense unless specifically defined as herein.

[0079] Those skilled in the art will understand that the terms "client," "terminal," and "terminal device" as used herein include both devices that receive wireless signals, devices that only possess wireless signal receiver capabilities without transmission capabilities, and devices with receiving and transmitting hardware, devices that have receiving and transmitting hardware capable of bidirectional communication over a bidirectional communication link. Such devices may include: cellular or other communication devices such as personal computers or tablets, having single-line displays, multi-line displays, or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service) that can combine voice, data processing, fax, and / or data communication capabilities; PDAs (Personal Digital Assistants) that may include radio frequency receivers, pagers, internet / intranet access, web browsers, notebooks, calendars, and / or GPS (Global Positioning System) receivers; and conventional laptops and / or handheld computers or other devices that have and / or include radio frequency receivers. As used herein, "client," "terminal," and "terminal device" can be portable, transportable, installed in a means of transportation (air, sea, and / or land), or suitable and / or configured to operate locally and / or in a distributed manner, operating in any other location on Earth and / or in space. "Client," "terminal," and "terminal device" as used herein can also be a communication terminal, an internet access terminal, or a music / video playback terminal, such as a PDA, a MID (Mobile Internet Device), and / or a mobile phone with music / video playback capabilities, or a smart TV, set-top box, etc.

[0080] The hardware referred to by the names "server," "client," and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann architecture, such as a central processing unit (including an arithmetic logic unit and a control unit), memory, input devices, and output devices. The computer program is stored in its memory, and the central processing unit loads the program stored in the secondary storage into the main memory to run it, execute the instructions in the program, and interact with the input and output devices to complete specific functions.

[0081] It should be noted that the concept of "server" used in this application can also be extended to the case of server clusters. Based on the network deployment principles understood by those skilled in the art, the servers should be logically divided. Physically, these servers can be independent of each other but accessible through interfaces, or they can be integrated into a single physical computer or a computer cluster. Those skilled in the art should understand this flexibility and should not use it to constrain the implementation of the network deployment method in this application.

[0082] One or more of the technical features of this application, unless explicitly specified herein, can be deployed on a server and accessed by a client remotely calling the online service interface provided by the server, or can be directly deployed and run on a client for access.

[0083] Unless otherwise specified, the neural network models referenced or potentially referenced in this application may be deployed on a remote server and invoked remotely on the client, or deployed on a client with the capability to invoke directly. In some embodiments, when running on the client, the corresponding intelligence may be acquired through transfer learning in order to reduce the requirements on the client's hardware resources and avoid excessive consumption of the client's hardware resources.

[0084] Unless otherwise specified, all data involved in this application may be stored remotely on a server or on a local terminal device, as long as it is suitable for use by the technical solution of this application.

[0085] Those skilled in the art will understand that although the various methods in this application are described based on the same concept and thus present commonality among them, they can be performed independently unless otherwise specified. Similarly, the various embodiments disclosed in this application are all based on the same inventive concept; therefore, concepts expressed in the same way, as well as concepts that are appropriately changed for convenience but are expressed differently, should be understood equivalently.

[0086] Unless otherwise expressly stated, the various embodiments disclosed in this application can be combined in a cross-cutting manner to flexibly construct new embodiments, as long as such combination does not depart from the inventive spirit of this application and can meet the needs of the prior art or solve a certain deficiency in the prior art. Those skilled in the art should be aware of such modifications.

[0087] Please see Figure 1 In one embodiment of the profit distribution settlement control method based on referral chain contribution assessment of this application, the method includes:

[0088] Step S10: In response to the current demand completion event of the Internet platform to trigger the profit distribution settlement process, obtain the referral chain node sequence corresponding to the current demand, wherein the referral chain node sequence includes at least one intermediate referral node;

[0089] The profit distribution and settlement control system in the terminal device can respond to the current demand completion event of the Internet platform to trigger the profit distribution and settlement process, and obtain the referral chain node sequence corresponding to the current demand, wherein the referral chain node sequence includes at least one intermediate referral node; wherein the Internet platform includes resource sharing, social e-commerce, online consultation and other platforms.

[0090] Specifically, the profit distribution and settlement control system in the server can continuously monitor the status of all demand orders in real time. The order status is marked as "completed" by the system, which means that the service corresponding to the demand has been delivered and the user who initiated the demand has confirmed the payment of the reward and platform service fee. The profit distribution and settlement control system responds to the current demand completion event of the Internet platform to trigger the profit distribution and settlement process; if the order is not paid, canceled midway or a refund is initiated, the subsequent profit distribution and settlement will not be triggered.

[0091] After the profit distribution and settlement process is triggered, the system retrieves the referral chain node sequence bound to the order from the blockchain or tamper-proof storage medium. ,in, Indicates the party initiating the request; Indicates the party providing the solution to the problem; This represents each intermediate referral node, which symbolizes the intermediate referrer at each level.

[0092] Step S20: For each intermediate referral node in the referral chain node sequence, determine the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver; determine the response timeliness score based on the demand response time and demand release time of the intermediate referral node; determine the historical matching success rate based on the proportion of demands referred by the intermediate referral node within a preset historical period; and determine the credit activity fusion index based on the credit score and activity score of the intermediate referral node.

[0093] In response to a current demand completion event on an internet platform, triggering a profit distribution and settlement process, the system obtains a referral chain node sequence corresponding to the current demand. This referral chain node sequence includes at least one intermediate referral node. For each intermediate referral node in the referral chain node sequence, a propagation distance factor is determined based on the referral level of the intermediate referral node from the demand solver. A response timeliness score is determined based on the demand response time and demand release time of the intermediate referral node. A historical matching success rate is determined based on the proportion of demands successfully matched by the intermediate referral node within a preset historical period. Finally, a credit activity fusion index is determined based on the credit score and activity score of the intermediate referral node.

[0094] In some embodiments, please refer to Figure 2 The step of determining the historical matching success rate based on the proportion of transactions completed by the intermediate referral node within a preset historical period includes:

[0095] Step S21: Obtain the total number of referrals by the intermediate referral node within a preset historical period, and the number of completed orders referred by the intermediate referral node within the preset historical period;

[0096] The preset historical period can be the past 6 months or the past 12 months, etc., and those skilled in the art can determine the preset historical period as needed according to the actual scenario; the system uses a single intermediate referral node. For statistical purposes, data is filtered from the data table storing referral records by the unique user identifier of the node, and then all referral records for a preset historical period are locked based on the time field.

[0097] Obtain the total number of referrals made by the intermediate referral node within a preset historical time period. The number of completed orders referred by the intermediate referral node within the preset historical time period. ;

[0098] Step S22: Calculate the ratio between the number of referred orders and the total number of referrals, determine the proportion of the intermediate referral node's referrals that were completed within a preset historical period, and use the ratio as the historical matching success rate.

[0099] Calculate the number of referred completed orders. With the total number of referrals The ratio between the two values ​​determines the proportion of transactions completed by the intermediate referral node in the referral requests within a preset historical period, and the ratio is used as the historical matching success rate.

[0100] Specifically, the formula for calculating the historical matching success rate is as follows:

[0101]

[0102] in, Indicates the first Historical matching success rate of intermediate referral nodes; Indicates the first The number of orders referred and completed by each intermediate referral node within a preset historical time period; Indicates the first The total number of referrals by each intermediate referral node within a preset historical period.

[0103] Furthermore, if the first The intermediate referral node has no historical referral records (new users), and directly uses the historical matching success rate. The value is assigned to the system default value of 0.5.

[0104] In some embodiments, please refer to Figure 3 The step of determining the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver includes:

[0105] Step S201: Obtain the referral level between the intermediate referral node and the demand solver in the referral chain node sequence; wherein, when the referral level is one, it represents direct referral, meaning that the intermediate referral node directly recommends the demand solver to the demand initiator; when the referral level is two, it represents indirect referral, meaning that the first intermediate referral node recommends the second intermediate referral node to the demand initiator, and the second intermediate referral node recommends the demand solver to the demand initiator; when the referral level is greater than two, and so on, the larger the referral level, the farther the intermediate referral node is from the demand solver.

[0106] For the first in the referral chain Each intermediate referral node is accessed by the system via the referral chain reading module, which retrieves the stored referral chain node sequence. Directly extract the referral level number corresponding to the intermediate referral node. ;

[0107] When the referral level When the value is 1, it indicates a direct referral, meaning that the intermediate referral node directly refers the request to the initiator. Recommended final solution ;

[0108] When the referral level When the value is 2, it represents indirect referral, meaning that the intermediate referral node first passes the request to the next level intermediate referral node, and the next level intermediate referral node then recommends a solution provider to the request initiator.

[0109] When the referral level When the value is greater than 2, the hierarchy definition follows the same pattern. The larger the value, the closer the intermediate referral node is to the solution provider. The link layer is further away.

[0110] Step S202: Use the reciprocal of the referral level number as the propagation distance factor of the intermediate referral node.

[0111] Get referral level reciprocal The reciprocal value That is, the first The propagation distance factor corresponding to each intermediate referral node; due to the number of referral levels The value of the propagation distance factor is a positive integer greater than or equal to 1. The calculated value range naturally falls within (0,1], and no additional normalization conversion is required.

[0112] In some embodiments, please refer to Figure 4 The steps for determining the response timeliness score based on the demand response time and demand release time of the intermediate referral node include:

[0113] Step S2001: Obtain the demand response time of the intermediate referral node and the demand release time of the demand initiator;

[0114] Step S2002: Calculate and determine the first difference between the demand response time and the demand release time to determine the demand response time difference;

[0115] Step S2003: Calculate the first ratio between the demand response time difference and the demand timeliness threshold, and calculate the second difference between the first value and the first ratio;

[0116] Step S2004: Take the maximum value between the second difference and zero as the response timeliness score of the intermediate referral node. When the demand response time difference is less than the demand timeliness threshold, the response timeliness score is greater than zero; when the demand response time difference is greater than or equal to the demand timeliness threshold, the response timeliness score is equal to zero. The value range of the response timeliness score is between zero and one. The larger the response timeliness score, the more timely the response of the intermediate referral node to the demand.

[0117] The formula for calculating the response timeliness score is as follows:

[0118]

[0119] in, Indicates the first The response time score of each intermediate referral node; This indicates the response time of the intermediate referral node. Indicates the time when the request was published by the request initiator; This represents the first difference between the demand response time and the demand release time, i.e., the demand response time difference; This represents the first ratio between the demand response time difference and the demand timeliness threshold. This represents the second difference between the first value and the first ratio; This represents the maximum value between the second difference and zero. When the demand response time difference... When the time difference is less than the demand timeliness threshold, the response timeliness score is greater than zero; when the demand response time difference is greater than or equal to the demand timeliness threshold, the response timeliness score is equal to zero; the value range of the response timeliness score is between zero and one, and the larger the response timeliness score, the more timely the intermediate referral node's response to the demand.

[0120] In some embodiments, please refer to Figure 5 The step of determining the credit activity fusion index based on the credit score and activity score of the intermediate referral node includes:

[0121] Step S20001: Obtain the credit score of the intermediate referral node and its corresponding credit score weight, activity score and its corresponding activity score weight, wherein the sum of the credit score weight and the activity score weight is a value of one, the value range of the credit score is from zero to one hundred, and the value range of the activity score is from zero to nine hundred and ninety-nine.

[0122] Step S20002: Calculate the second ratio between the credit score and the value of one hundred, and calculate and determine the first product between the second ratio and the credit score weight;

[0123] Step S20003: Calculate the third ratio between the activity score and the value 999, and calculate the second product between the third ratio and the activity score weight;

[0124] Step S20004: Calculate the first sum between the first product and the second product, and use the first sum as the credit activity fusion index of the intermediate referral node.

[0125] The formula for calculating the credit activity fusion index of the intermediate referral node is as follows:

[0126]

[0127] in, Indicates the first The credit activity fusion index of each intermediate referral node has a value range of 0 to 100. Indicates the first The credit score of each intermediate referral node ranges from 0 to 999. Indicates the first The activity score of each intermediate referral node; 0.6 is the weight of the credit score, and 0.4 is the weight of the activity score; This represents the second ratio between the credit score and the numerical value of one hundred.

[0128] This represents the third ratio between the activity score and the numerical value of 999.

[0129] Step S30: Call the preset contribution evaluation model, and calculate and determine the contribution score of the intermediate referral node based on the propagation distance factor, response time score, historical matching success rate and credit activity fusion index of the intermediate referral node.

[0130] For each intermediate referral node in the referral chain node sequence, a propagation distance factor is determined based on the number of referral levels between the intermediate referral node and the demand solver; a response timeliness score is determined based on the demand response time and demand release time of the intermediate referral node; a historical matching success rate is determined based on the proportion of demands referred by the intermediate referral node within a preset historical period; and a credit activity fusion index is determined based on the credit score and activity score of the intermediate referral node. Then, a preset contribution evaluation model is invoked to calculate and determine the contribution score of the intermediate referral node based on the propagation distance factor, the response timeliness score, the historical matching success rate, and the credit activity fusion index.

[0131] In some embodiments, please refer to Figure 6 The steps for constructing a contribution assessment model include:

[0132] Step S31: Obtain the first weight coefficient corresponding to the propagation distance factor, the second weight coefficient corresponding to the response time score, the third weight coefficient corresponding to the historical matching success rate, and the fourth weight coefficient corresponding to the credit activity fusion index of the intermediate referral node, wherein the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient is a value of one.

[0133] Step S32: Calculate the third product between the propagation distance factor and the first weight coefficient, calculate the fourth product between the response time score and the second weight coefficient, calculate the fifth product between the historical matching success rate and the third weight coefficient, and calculate the sixth product between the credit activity fusion index and the fourth weight coefficient.

[0134] Step S33: Calculate the second sum among the third product, the fourth product, the fifth product, and the sixth product, and use the second sum as the contribution score of the intermediate referral node to construct a contribution evaluation model.

[0135] Specifically, the calculation formula for the contribution assessment model is expressed as follows:

[0136]

[0137] in, Indicates the first The contribution score corresponding to each intermediate referral node; Indicates the first The propagation distance factor corresponding to each intermediate referral node; Indicates the first The response time score of each intermediate referral node; Indicates the first Historical matching success rate of intermediate referral nodes; Indicates the first Credit activity fusion index of each intermediate referral node; This represents the first weighting coefficient corresponding to the propagation distance factor; This represents the second weighting coefficient corresponding to the response timeliness score; The third weighting coefficient represents the historical matching success rate. This represents the fourth weighting coefficient corresponding to the credit activity fusion index.

[0138] For further embodiments, please refer to Figure 7 The steps for determining the initial values ​​of the first, second, third, and fourth weighting coefficients of the contribution assessment model include:

[0139] Step S301: When there is no historical operation data on the Internet platform, the analytic hierarchy process is used to determine the initial weights. Multiple platform operation experts compare the importance of the propagation distance factor, the response time score, the historical matching success rate, and the credit activity fusion index pairwise and assign values ​​to construct a judgment matrix.

[0140] The applicable scenarios are the initial stage of platform launch, when the system has not accumulated referrals, and when there is historical operational data related to transactions. At this time, the initial weights are solved by relying on the Analytic Hierarchy Process (AHP). At least three platform operation experts are organized to conduct pairwise importance comparisons and scores on four dimensions: dissemination distance factor, response time score, historical matching success rate, and credit activity integration index.

[0141] The scoring rules use a 1 to 9 scale: scale 1 represents that the two comparison dimensions are equally important, and scale 9 represents that one dimension is extremely important compared to the other. All scoring results are summarized to generate a judgment matrix A.

[0142] Step S302: Normalize the judgment matrix and calculate the maximum eigenvalue of the judgment matrix and its corresponding eigenvector;

[0143] Based on the normalized matrix, mathematical eigenvalues ​​are obtained to determine the largest eigenvalue of the judgment matrix. And the eigenvector that uniquely corresponds to the largest eigenvalue, which is an unnormalized intermediate weight result.

[0144] Step S303: Calculate the consistency ratio of the judgment matrix. When the consistency ratio is less than a preset threshold, determine the acceptable consistency of the judgment matrix. Normalize the feature vector and use it as the initial weight vector. The initial weight vector includes the initial values ​​of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient.

[0145] Substitute into the formula Solving for the consistency index Combined with the preset random consistency index ,according to The consistency ratio was calculated. Consistency ratio Compared to the preset threshold of 0.1, when the consistency ratio When the score is less than the preset threshold of 0.1, the expert scoring logic of the current judgment matrix is ​​deemed to have acceptable consistency; the feature vector obtained in step S302 is normalized again, and the initial weight vector is output after normalization. ;in, The initial value of the first weighting coefficient. This is the initial value for the second weighting coefficient. The initial value of the third weighting coefficient. This is the initial value for the fourth weighting coefficient, and the sum of the four initial weighting coefficients equals 1. Wherein, This represents a consistency index, used in the Analytic Hierarchy Process (AHP) to evaluate the internal logical consistency of a matrix. This represents the largest eigenvalue of the judgment matrix; In this embodiment, the order of the judgment matrix is ​​indicated. The value is 4.

[0146] For further embodiments, please refer to Figure 8 The steps for updating the first, second, third, and fourth weight coefficients of the contribution assessment model include:

[0147] Step S3001: When the number of historical profit distribution transactions accumulated by the Internet platform reaches a preset threshold, obtain the average satisfaction score of all intermediate referral nodes in the historical profit distribution transactions for the profit distribution settlement results, and take maximizing the average satisfaction score as the objective function.

[0148] When the platform's historical profit distribution transaction volume If the number of transactions exceeds a preset threshold (e.g., 1000 transactions), the particle swarm optimization process is initiated; all valid historical profit distribution transactions are traversed, and the [number of transactions]th [transaction] is extracted. The corresponding historical profit distribution transaction , For the first In a historical profit distribution transaction, the average satisfaction score of all intermediate referral nodes with the profit distribution settlement result ranges from 0 to 1.

[0149] With maximizing the average satisfaction rating as the objective function, the expression for the average satisfaction rating is as follows:

[0150]

[0151] in, The objective function value represents the overall average satisfaction score of all intermediate referral nodes with the profit distribution settlement results under all historical profit distribution transactions. This indicates the total number of historical profit distribution transactions included in the statistics; The index of the transaction sample is a value ranging from 1 to... Used to distinguish different historical transactions; For the first In a historical profit distribution transaction, the average satisfaction score of all intermediate referral nodes on the profit distribution settlement result ranges from 0 to 1.

[0152] Step S3002: Use the weight vector as an optimization variable, wherein the weight vector is constructed by the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient, and the constraint condition is that the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient is one, and each weight coefficient is greater than or equal to zero.

[0153] Set the optimization variable as a weight vector Weight vector Within, the first weighting coefficients corresponding to the propagation distance factor are respectively... The second weighting coefficient corresponding to the response timeliness score. The third weighting coefficient corresponding to the historical matching success rate The fourth weighting coefficient corresponding to the credit activity fusion index ;

[0154] The particle swarm optimization algorithm solves for conditions with hard constraints applied throughout the process, as follows: , This is to avoid the distortion of contribution scoring logic caused by negative weights.

[0155] Step S3003: Iteratively search for the weight combination that maximizes the objective function using the particle swarm optimization algorithm, updating the particle position and velocity in each iteration until the preset number of iterations or the objective function value converges.

[0156] Based on the particle swarm optimization (PSO) algorithm, a weight combination that maximizes the objective function S is searched iteratively within the constraints. After each round of iteration, the particle position parameters and particle velocity parameters are updated synchronously to continuously approach the optimal weight solution; the iteration termination judgment is: until the preset number of iterations is reached or the objective function value converges, the preset number of iterations can be 500 times, etc.

[0157] Step S3004: Update the optimized weight coefficients to the weight configuration table as the current values ​​of each weight coefficient in the subsequent profit distribution settlement.

[0158] After iteration terminates, the output is the optimal weight combination that satisfies the constraints and maximizes the average satisfaction of the referrer. Synchronously overwrite the system weight configuration table; Business activation rules: Subsequent calls to the profit distribution settlement model calculate the contribution score of each intermediate referral node. At that time, the weighting calculation is completed by directly reading the updated weight coefficients in the weight configuration table.

[0159] In some embodiments, please refer to Figure 9After calling a preset contribution evaluation model and calculating the contribution score of the intermediate referral node based on its propagation distance factor, response timeliness score, historical matching success rate, and credit activity fusion index, the process includes:

[0160] Step S30001: Obtain the contribution score of each intermediate referral node, calculate the overall quality score of the referral chain, and when the overall quality score of the referral chain is higher than the preset quality score threshold, mark the referral chain as a high-quality referral pattern and store it in the pattern library; in subsequent demand referral matching, use the path with the highest similarity to the propagation path of the high-quality referral pattern in the pattern library for demand diffusion.

[0161] The formula for calculating the overall quality score of the referral chain is as follows:

[0162]

[0163] in, Indicates the first The contribution score of each intermediate referral node is calculated by the contribution evaluation model, which integrates the propagation distance factor, response time score, historical matching success rate, and credit activity index. This represents the total number of all intermediate referral nodes within a single referral chain; This indicates the overall quality score of the referral chain.

[0164] For a single referral chain, read the contribution score corresponding to each intermediate referral node in the chain. At the same time, the total number of intermediate referral nodes in the referral chain is counted. Score based on contribution and the total number of intermediate referral nodes Calculate the overall quality score of the referral chain. When the overall quality score of the referral chain When the score exceeds a preset quality score threshold, the referral chain is determined to be a high-quality referral pattern, and the complete propagation path of the referral chain (e.g., alumni association → industry peers → experts) is simultaneously stored in the system pattern library. When the platform receives a new demand referral matching task, it searches all high-quality referral patterns in the pattern library, selects the link with the highest propagation path similarity as the priority diffusion path, and improves the overall referral conversion efficiency by relying on mature high-quality links. The preset quality score threshold can be 0.7, etc., and those skilled in the art can determine it as needed according to the actual application scenario, without any limitation.

[0165] Step S30002: Perform multi-dimensional aggregation and statistics on the contribution scores of the intermediate referral nodes according to the scenario dimension and / or organization dimension to generate operational indicators under the scenario dimension and / or organization dimension. When the operational indicators meet the preset conditions, automatically trigger the operational actions corresponding to the preset conditions, and display the operational indicators in real time on the platform management backend. The operational indicators include at least one of the following: the average contribution score of intermediate referral nodes in each scenario, the proportion of high-contribution users in each organization, and the time-series change trend of contribution scores.

[0166] The average contribution score of intermediate referral nodes in each scenario is used to evaluate the overall quality of referrals in different business scenarios; the proportion of high-contribution users in each organization is used to assess community activity and the maturity of the platform's referral culture; the time-series trend of contribution scores is used to monitor the health of the platform's referral settlement mechanism in the long term.

[0167] Scoring based on the contribution of each intermediate referral node Based on this foundation, the system aggregates and statistically analyzes data according to scenario dimensions (finding experts, services, resources, etc.) and organizational dimensions (alumni associations, chambers of commerce, etc.). All aggregated operational metrics are pushed to the platform's management backend data dashboard in real time for easy viewing by operations personnel. An automatic operational trigger mechanism continuously monitors operational metric values, and automatically triggers corresponding operational adjustments when the metrics meet preset system criteria. For example, if the average contribution score for a certain scenario continuously declines, the system automatically pushes an adjustment to the first weight coefficient corresponding to the propagation distance factor in the contribution assessment model for that scenario. The second weighting coefficient corresponding to the response time score The third weighting coefficient corresponding to the historical matching success rate And the fourth weighting coefficient corresponding to the credit activity fusion index .

[0168] In a further embodiment, the contribution score of a single intermediate referral node across all referral links is aggregated monthly. Calculate the average contribution score of a single intermediate referral node across all referral links for the current month. The average contribution score for the month. The updated credit score is generated by inputting the data into the credit score update formula; the higher the monthly average contribution score of a node, the greater the single increase in credit score; the updated credit score is then incorporated into the credit activity fusion index. The calculation ensures that high-quality referral nodes receive higher weight in subsequent referral matching and contribution scoring, creating a positive cycle: high-quality referrals → improved credit score → increased referral matching weight → more referral opportunities. The credit score update formula is as follows:

[0169]

[0170] in, This represents the original credit score before the update by a single intermediary referral node. This represents the average contribution score of a single intermediate referral node across all referral links in the current month. This indicates the preset update coefficient for the credit score, with a value range of 0.1 to 0.5, which can be customized by the platform administrator in the backend. This represents the updated user credit score from a single intermediary referral node.

[0171] Step S40: Calculate the profit allocation amount corresponding to each intermediate referral node based on the contribution score of each intermediate referral node, and call its corresponding payment interface to transfer the profit allocation amount to its corresponding intermediate referral node.

[0172] The system invokes a preset contribution evaluation model. Based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node, it calculates the contribution score of the intermediate referral node. Then, based on the contribution score of each intermediate referral node, it calculates the allocated profit amount for each intermediate referral node and invokes its corresponding payment interface to transfer the allocated profit amount to its corresponding intermediate referral node.

[0173] In some embodiments, please refer to Figure 10 The steps for calculating the profit allocation amount for each intermediate referral node based on its contribution score include:

[0174] Step S401: For a single referral chain, obtain the total amount of the current required profit distribution pool, and the contribution score of each intermediate referral node in the referral chain node sequence. Calculate the sum of the contribution scores of all intermediate referral nodes and determine it as the total contribution score.

[0175] Step S402: For each intermediate referral node, divide its corresponding contribution score by the total contribution score to obtain the contribution percentage of the intermediate referral node.

[0176] Step S403: Multiply the total amount of the profit distribution pool by the contribution ratio of the intermediate referral node to obtain the initial profit distribution amount of the intermediate referral node.

[0177] Step S404: When the initial allocated profit amount exceeds the preset single-node allocation limit, the initial allocated profit amount is truncated to the single-node allocation limit, and the excess part is redistributed to other intermediate referral nodes according to the contribution ratio of each intermediate referral node.

[0178] Step S405: When the initial allocated profit amount does not exceed the single node allocation limit, the initial allocated profit amount is directly used as the final allocated profit amount of the intermediate referral node.

[0179] The single-node allocation limit can be 50% of the total profit distribution pool of the current referral chain, etc.; for a single referral chain, the first... The formula for calculating the initial profit allocation of each intermediate referral node is as follows:

[0180]

[0181] in, Indicates the first The initial profit allocation amount for each intermediate referral node; This represents the total profit distribution pool (referral reward pool) of the current referral chain, which is generated from the total transaction amount according to a fixed extraction ratio, such as 15% or 20%. This represents the total number of all intermediate referral nodes within a single referral chain; Indicates the first in the referral chain The contribution score of each intermediate referral node; The total contribution score is the sum of the contribution scores of all intermediate referral nodes in the referral chain. Indicates the first The contribution score of each intermediate referral node; Indicates the first The contribution percentage of each intermediate referral node.

[0182] Step S50: Package the key data of profit distribution corresponding to the profit distribution settlement process to generate a digest hash, and write it into a blockchain or judicial evidence storage platform for evidence storage, so as to complete the profit distribution settlement control based on the referral chain contribution assessment.

[0183] Based on the contribution scores of each intermediate referral node, the profit allocation amount corresponding to each intermediate referral node is calculated, and its corresponding payment interface is called to transfer the profit allocation amount to its corresponding intermediate referral node. Then, the key data of the profit allocation settlement process is packaged to generate a digest hash, which is written into the blockchain or judicial evidence storage platform for evidence storage, so as to complete the profit allocation settlement control based on the referral chain contribution assessment.

[0184] In a specific embodiment, the platform calls a third-party payment interface or its own wallet system to transfer reward funds to the corresponding referrer's account based on the final profit distribution amount after the upper limit is truncated and excess redistribution for each node; the fund transfer operation generates electronic vouchers simultaneously, and retains complete details of each profit distribution as the original record of fund flow.

[0185] According to tax law, referral rewards obtained by referrers are considered labor remuneration income, and the platform, as the payer, is obligated to withhold and pay individual income tax on their behalf. The system has a built-in withholding tax rate table ranging from 20% to 40%. Before the fund transfer is executed, the corresponding tax payable is calculated and deducted based on the final profit distribution amount of the node. The platform uniformly submits the corresponding tax declaration data to the tax authorities, and the actual amount received in the referrer's account is the after-tax amount after deducting individual income tax.

[0186] All key data from this profit distribution transaction, such as order ID, referral chain hash value, final profit distribution amount of each intermediate referral node, and withheld individual income tax amount, are packaged together, and a digest hash is calculated. The digest hash is then written into a blockchain or judicial evidence storage platform for permanent storage. The stored data is used for subsequent financial audits and transaction dispute arbitration verification.

[0187] If a referrer has any objection to their profit distribution amount or tax deduction amount, they can initiate a profit distribution appeal on the client side. The platform retrieves the profit distribution details and the original hash data of the referral chain that have been stored on the blockchain or judicial platform, and conducts a second verification on the entire chain of contribution score, profit distribution ratio, cap redistribution, and tax deduction calculation. If the verification confirms that there is an error in the system's calculation and distribution, the platform will automatically perform an adjustment operation and reissue the difference reward to the corresponding referrer.

[0188] As can be seen from the above embodiments, compared with the prior art, this application addresses the problems of subjective contribution evaluation methods, insufficient fund security, and weak data anti-tampering capabilities in the prior art. This application includes, but is not limited to, the following beneficial effects:

[0189] First, this application breaks through the limitations of the existing fixed-level proportional allocation model. By constructing a contribution evaluation model that integrates propagation distance factor, response time score, historical matching success rate and credit activity index, it quantifies the referrer's position value in the propagation chain, the initiative to respond to demand, the effectiveness of historical referrals, and the platform's reputation and participation activity.

[0190] Secondly, this application uses contribution score as the sole basis for allocation. The profit amount allocated to each intermediate referral node is directly proportional to its contribution score relative to the total contribution score, and the allocation rules are transparent and verifiable. At the same time, an event-driven mechanism enables fully automated, unattended operation of the entire process from triggering, calculation, payment to evidence storage, avoiding the inefficiency and errors of manual operation and directly linking the allocation results to objective contribution.

[0191] Third, this application packages key profit distribution data into a digest hash and writes it to a blockchain or judicial evidence storage platform for preservation. Any modification to the original data can be quickly identified through hash verification, ensuring the authenticity and traceability of the profit distribution basis and results, providing credible evidence with judicial validity for dispute arbitration, and effectively restraining the platform's unilateral data tampering behavior.

[0192] Fourth, at the path quality analysis level, high-quality referral patterns are identified and stored in the pattern library by calculating the overall quality score of the referral chain. In subsequent demand matching, the high-quality propagation path with the highest similarity is prioritized, so that the data accumulated in a single profit sharing is transformed into strategic assets for continuously optimizing referral efficiency. At the operation dashboard level, contribution scores are aggregated in multiple dimensions by scenario and organization, generating operational indicators such as average contribution of each scenario, proportion of high-contribution users in each organization, and time-series trend of contribution changes. These indicators are displayed in real time and can automatically trigger operational actions when the indicators meet preset conditions, thus upgrading the profit sharing settlement module from a one-time calculation tool to a continuous data-driven engine.

[0193] Fifth, this application utilizes data accumulated from feedback to drive adaptive optimization of weight coefficients. In the early stages of the platform's launch, the analytic hierarchy process (AHP) is used to scientifically determine the initial weights, avoiding arbitrary settings. After accumulating sufficient historical data, with the goal of maximizing the average satisfaction of referrers, the particle swarm optimization algorithm is used to automatically iterate and search for the optimal weight combination and update it to the weight configuration table monthly. At the same time, different business scenarios use independent weight configurations for separate optimization, enabling the weight coefficients to evolve from manually static settings to a data-driven, continuously optimized adaptive mechanism, ensuring the long-term effectiveness of the evaluation model.

[0194] Please see Figure 11A profit distribution settlement control device based on referral chain contribution assessment, provided to meet one of the purposes of this application, includes: a referral chain acquisition module 1100, configured to respond to a current demand completion event on an internet platform to trigger a profit distribution settlement process, and acquire a referral chain node sequence corresponding to the current demand, wherein the referral chain node sequence includes at least one intermediate referral node; a contribution parameter determination module 1200, configured to, for each intermediate referral node in the referral chain node sequence, determine a propagation distance factor based on the referral level of the intermediate referral node from the demand solver; determine a response timeliness score based on the demand response time and demand release time of the intermediate referral node; determine a historical matching success rate based on the proportion of demands referred by the intermediate referral node within a preset historical period; and determine a credit activity fusion index based on the credit score and activity score of the intermediate referral node. The contribution evaluation module 1300 is configured to call a preset contribution evaluation model and calculate the contribution score of the intermediate referral node based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node. The profit distribution and settlement module 1400 is configured to calculate the allocated profit amount for each intermediate referral node based on its contribution score and call its corresponding payment interface to transfer the allocated profit amount to its corresponding intermediate referral node. The profit distribution notarization module 1500 is configured to package the key profit distribution data corresponding to the profit distribution and settlement process to generate a digest hash and write it to a blockchain or judicial notarization platform for notarization, so as to complete the profit distribution and settlement control based on the referral chain contribution evaluation.

[0195] Based on any embodiment of this application, please refer to Figure 12 Another embodiment of this application also provides an electronic device, which can be implemented by a computer device, such as... Figure 12 The diagram shows the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. The computer-readable storage medium stores an operating system, a database, and computer-readable instructions. The database may store a sequence of control information. When executed by the processor, the computer-readable instructions enable the processor to implement a profit distribution settlement control method based on referral chain contribution evaluation. The processor provides computing and control capabilities to support the operation of the entire computer device. The memory stores computer-readable instructions, which, when executed by the processor, enable the processor to execute the profit distribution settlement control method based on referral chain contribution evaluation of this application. The network interface of the computer device is used for communication with a terminal. Those skilled in the art will understand that… Figure 12 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0196] In this embodiment, the processor is used to execute... Figure 11 The specific functions of each module are defined within the memory, which stores the program code and various data required to execute these modules. A network interface is used for data transmission between the user terminal and the server. In this embodiment, the memory stores the program code and data required to execute all modules in the profit distribution settlement control device based on referral chain contribution evaluation of this application. The server can call the server's program code and data to execute the functions of all modules.

[0197] This application also provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the steps of the profit distribution settlement control method based on referral chain contribution assessment as described in any embodiment of this application.

[0198] This application also provides a computer program product, including a computer program / instructions that, when executed by one or more processors, implement the steps of the profit distribution settlement control method based on referral chain contribution assessment as described in any embodiment of this application.

[0199] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0200] The above description is only a partial embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A profit distribution settlement control method based on referral chain contribution assessment, characterized in that, include: In response to the current demand completion event of the Internet platform to trigger the profit distribution and settlement process, the referral chain node sequence corresponding to the current demand is obtained, wherein the referral chain node sequence includes at least one intermediate referral node; For each intermediate referral node in the referral chain node sequence, a propagation distance factor is determined based on the number of referral levels between the intermediate referral node and the demand solver; a response timeliness score is determined based on the demand response time and demand release time of the intermediate referral node; a historical matching success rate is determined based on the proportion of demands referred by the intermediate referral node within a preset historical period; and a credit activity fusion index is determined based on the credit score and activity score of the intermediate referral node. The preset contribution evaluation model is invoked, and the contribution score of the intermediate referral node is calculated and determined based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node. Based on the contribution scores of each intermediate referral node, calculate the allocated profit amount for each intermediate referral node, and call its corresponding payment interface to transfer the allocated profit amount to its corresponding intermediate referral node. The key data of profit distribution corresponding to the profit distribution settlement process is packaged to generate a digest hash, which is then written into a blockchain or judicial evidence storage platform for evidence storage, so as to complete the profit distribution settlement control based on the referral chain contribution assessment.

2. The profit distribution and settlement control method based on referral chain contribution assessment according to claim 1, characterized in that, The step of determining the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver includes: Obtain the referral level between the intermediate referral node and the demand solver in the referral chain node sequence; The reciprocal of the referral level number is used as the propagation distance factor of the intermediate referral node.

3. The profit distribution and settlement control method based on referral chain contribution assessment according to claim 1, characterized in that, The steps for determining the response timeliness score based on the demand response time and demand release time of the intermediate referral nodes include: Obtain the demand response time of the intermediate referral node and the demand release time of the demand initiator; Calculate and determine a first difference between the demand response time and the demand release time to determine the demand response time difference; Calculate the first ratio between the demand response time difference and the demand timeliness threshold, and calculate the second difference between the first value and the first ratio; The maximum value between the second difference and zero is taken as the response time score of the intermediate referral node.

4. The profit distribution and settlement control method based on referral chain contribution assessment according to claim 1, characterized in that, The step of determining the credit activity fusion index based on the credit score and activity score of the intermediate referral node includes: Obtain the credit score and its corresponding credit score weight, activity score and its corresponding activity score weight of the intermediate referral node, wherein the credit score ranges from zero to one hundred, and the activity score ranges from zero to nine hundred and ninety-nine. Calculate a second ratio between the credit score and the value of one hundred, and calculate and determine a first product between the second ratio and the weight of the credit score; Calculate the third ratio between the activity score and the value 999, and calculate and determine the second product between the third ratio and the activity score weight; Calculate the first sum between the first product and the second product, and use the first sum as the credit activity fusion index of the intermediate referral node.

5. The profit distribution settlement control method based on referral chain contribution assessment according to any one of claims 2 to 4, characterized in that, The steps to construct a contribution assessment model include: Obtain the first weight coefficient corresponding to the propagation distance factor, the second weight coefficient corresponding to the response time score, the third weight coefficient corresponding to the historical matching success rate, and the fourth weight coefficient corresponding to the credit activity fusion index of the intermediate referral node, wherein the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient is a value of one; Calculate the third product between the propagation distance factor and the first weight coefficient, calculate the fourth product between the response time score and the second weight coefficient, calculate the fifth product between the historical matching success rate and the third weight coefficient, and calculate the sixth product between the credit activity fusion index and the fourth weight coefficient; Calculate the second sum among the third, fourth, fifth, and sixth products, and use the second sum as the contribution score of the intermediate referral node to construct a contribution evaluation model.

6. The profit distribution settlement control method based on referral chain contribution assessment according to claim 5, characterized in that, The steps for determining the initial values ​​of the first, second, third, and fourth weighting coefficients of the contribution assessment model include: When the internet platform has no historical operational data, the analytic hierarchy process is used to determine the initial weights. Multiple platform operation experts compare and assign values ​​to the importance of the propagation distance factor, the response timeliness score, the historical matching success rate, and the credit activity fusion index in pairs to construct a judgment matrix. The judgment matrix is ​​normalized, and the maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated. Calculate the consistency ratio of the judgment matrix. When the consistency ratio is less than a preset threshold, determine the acceptable consistency of the judgment matrix. Normalize the feature vector and use it as the initial weight vector. The initial weight vector includes the initial values ​​of the first weight coefficient, the second weight coefficient, the third weight coefficient, and the fourth weight coefficient.

7. The profit distribution settlement control method based on referral chain contribution assessment according to claim 5, characterized in that, The steps for updating the first, second, third, and fourth weighting coefficients of the contribution assessment model include: When the number of historical profit distribution transactions accumulated by the Internet platform reaches a preset threshold, the average satisfaction score of all intermediate referral nodes in the historical profit distribution transactions on the profit distribution settlement results is obtained, and the objective function is to maximize the average satisfaction score. The weight vector is used as the optimization variable, wherein the weight vector is constructed by the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient, and the constraint is that the sum of the first weight coefficient, the second weight coefficient, the third weight coefficient and the fourth weight coefficient is one, and each weight coefficient is greater than or equal to zero. The particle swarm optimization algorithm iteratively searches for the weight combination that maximizes the objective function, updating the particle position and velocity in each iteration until a preset number of iterations is reached or the objective function value converges. The optimized weight coefficients are updated in the weight configuration table and used as the current values ​​of each weight coefficient in the subsequent profit distribution settlement.

8. The profit distribution settlement control method based on referral chain contribution assessment according to claim 1, characterized in that, After invoking a preset contribution evaluation model and calculating the contribution score of the intermediate referral node based on its propagation distance factor, response timeliness score, historical matching success rate, and credit activity fusion index, the process includes: Obtain the contribution score of each intermediate referral node, calculate the overall quality score of the referral chain, and when the overall quality score of the referral chain is higher than the preset quality score threshold, mark the referral chain as a high-quality referral pattern and store it in the pattern library; in subsequent demand referral matching, use the path with the highest similarity to the propagation path of the high-quality referral pattern in the pattern library for demand diffusion. The contribution scores of the intermediate referral nodes are aggregated and statistically analyzed in multiple dimensions according to the scenario dimension and / or organization dimension to generate operational indicators under the scenario dimension and / or organization dimension. When the operational indicators meet the preset conditions, the corresponding operational actions are automatically triggered, and the operational indicators are displayed in real time on the platform management backend. The operational indicators include at least one of the following: the average contribution score of the intermediate referral nodes in each scenario, the proportion of high-contribution users in each organization, and the time-series change trend of the contribution scores.

9. The profit distribution settlement control method based on referral chain contribution assessment according to claim 1, characterized in that, The steps for calculating the profit allocation amount for each intermediate referral node based on its contribution score include: For a single referral chain, obtain the total amount of the current required profit distribution pool, and the contribution score of each intermediate referral node in the referral chain node sequence. Calculate the sum of the contribution scores of all intermediate referral nodes and determine it as the total contribution score. For each intermediate referral node, its corresponding contribution score is divided by the total contribution score to obtain the contribution percentage of the intermediate referral node. Multiply the total amount of the profit distribution pool by the contribution ratio of the intermediate referral node to obtain the initial profit amount allocated to the intermediate referral node. When the initial allocated profit amount exceeds the preset single-node allocation limit, the initial allocated profit amount is truncated to the single-node allocation limit, and the excess portion is redistributed to other intermediate referral nodes according to the contribution ratio of each intermediate referral node. When the initial allocated profit amount does not exceed the single node allocation limit, the initial allocated profit amount is directly used as the final allocated profit amount for the intermediate referral node.

10. A profit distribution settlement control device based on referral chain contribution evaluation, characterized in that, include: The referral chain acquisition module is configured to respond to the current demand completion event of the Internet platform to trigger the profit distribution settlement process, and acquire the referral chain node sequence corresponding to the current demand, wherein the referral chain node sequence includes at least one intermediate referral node. The contribution parameter determination module is configured to determine the propagation distance factor based on the number of referral levels between the intermediate referral node and the demand solver for each intermediate referral node in the referral chain node sequence; determine the response timeliness score based on the demand response time and demand release time of the intermediate referral node; determine the historical matching success rate based on the proportion of demands referred by the intermediate referral node within a preset historical period; and determine the credit activity fusion index based on the credit score and activity score of the intermediate referral node. The contribution evaluation module is set to call a preset contribution evaluation model and calculate the contribution score of the intermediate referral node based on the propagation distance factor, response time score, historical matching success rate, and credit activity fusion index of the intermediate referral node. The profit distribution and settlement module is configured to calculate the profit distribution amount corresponding to each intermediate referral node based on the contribution score of each intermediate referral node, and call its corresponding payment interface to transfer the profit distribution amount to its corresponding intermediate referral node. The profit distribution notarization module is configured to package the key profit distribution data corresponding to the profit distribution settlement process, generate a digest hash, and write it into a blockchain or judicial notarization platform for notarization, so as to complete the profit distribution settlement control based on the referral chain contribution assessment.

Images