Equity attribution method and apparatus

Abstract

The application discloses a kind of equity attribution method and device, it is related to data analysis technical field.The specific embodiment of the method includes: obtaining the order information of multiple orders corresponding to target product, the order information includes: equity information;The multiple orders are clustered, and multiple order clusters are obtained;For each order: according to the order cluster corresponding to the order, determine the equity attribution model corresponding to the order;The order information of the order is input into the equity attribution model, and the equity attribution information corresponding to the order is obtained, the equity attribution information includes: equity identifier and its corresponding weight;According to the equity attribution information corresponding to each order, determine the equity contribution information for the target product.This embodiment can accurately carry out equity attribution.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, and in particular to an equity attribution method and apparatus. Background Technology

[0002] Rights and benefits, manifested as specific forms of discounts or preferential equivalents, are marketing tools in digital operations. Enterprises use various rights and benefits incentives to maintain or grow their daily operations. Identifying which rights and benefits drive successful transactions enables enterprises to effectively allocate these benefits and avoid duplicate allocations. Therefore, rights and benefits attribution becomes particularly important. However, current technologies lack methods for accurately attributing rights and benefits. Summary of the Invention

[0003] In view of this, embodiments of the present invention provide a method and apparatus for attributing rights, which can accurately perform rights attribution.

[0004] In a first aspect, embodiments of the present invention provide a method for attributing rights, including:

[0005] Obtain order information for multiple orders corresponding to the target product, wherein the order information includes: benefits information;

[0006] Cluster the multiple orders to obtain multiple order clusters;

[0007] For each order: Based on the order cluster corresponding to the order, determine the rights attribution model corresponding to the order; input the order information of the order into the rights attribution model to obtain the rights attribution information corresponding to the order, wherein the rights attribution information includes: rights identifier and its corresponding weight;

[0008] Based on the equity attribution information corresponding to each order, determine the equity contribution information for the target product.

[0009] Optionally, the step of clustering the multiple orders to obtain multiple order clusters includes:

[0010] Determine the digital information and / or data quality information corresponding to each of the aforementioned orders;

[0011] For each order: determine the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order.

[0012] Optionally, determining the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order includes:

[0013] If the digital information and / or data quality information corresponding to the order meets the first condition, the order is classified into the first cluster.

[0014] If the digital information and / or data quality information corresponding to the order meets the second condition, the order is classified into the second cluster.

[0015] If the digital information and / or data quality information corresponding to the order does not meet the first condition and the second condition, the order is classified into a third cluster.

[0016] Optionally, the digital information corresponding to each of the orders is determined, including:

[0017] Determine the quantity of valid information in the order;

[0018] The digital information of the order is determined based on the amount of valid information.

[0019] Optionally, the data quality information corresponding to each order is determined, including:

[0020] Determine the channel information and labeling information corresponding to the order;

[0021] Based on the channel information and the annotation information, the data quality information corresponding to the order is determined.

[0022] Optionally, determining the equity attribution model corresponding to the order based on the order clustering corresponding to the order includes:

[0023] In response to the order clustering being classified as a first cluster, the equity attribution model is determined to be a first attribution model, which is established based on the initial attribution model and the Markov attribution model.

[0024] In response to the order clustering being classified as a second cluster, the equity attribution model is determined to be a second attribution model, which is established based on a Markov attribution model;

[0025] In response to the order cluster being classified as a third cluster, the equity attribution model is determined to be a third attribution model, which is established based on the first attribution model and the second attribution model.

[0026] Optionally, the equity attribution model is a third attribution model, which is established based on the first attribution model and the second attribution model;

[0027] The step of inputting the order information of the order into the equity attribution model to obtain the equity attribution information corresponding to the order includes:

[0028] The order information of the order is input into the first attribution model to obtain the first equity attribution information;

[0029] The order information of the order is input into the second attribution model to obtain the second equity attribution information;

[0030] Determine the first weight corresponding to the first attribution model and the second weight corresponding to the second attribution model;

[0031] Based on the first equity attribution information, the second equity attribution information, the first weight, and the second weight, the equity attribution information corresponding to the order is obtained.

[0032] In a second aspect, embodiments of the present invention provide an attribution device, comprising:

[0033] The information acquisition module is used to acquire order information for multiple orders corresponding to the target product, wherein the order information includes: rights and benefits information;

[0034] The order clustering module is used to cluster the multiple orders to obtain multiple order clusters;

[0035] The information determination module is used for each order to: determine the rights attribution model corresponding to the order based on the order cluster corresponding to the order; input the order information of the order into the rights attribution model to obtain the rights attribution information corresponding to the order, wherein the rights attribution information includes: rights identifier and its corresponding weight;

[0036] The attribution module is used to determine the equity contribution information for the target product based on the equity attribution information corresponding to each order.

[0037] Optionally, the order clustering module is specifically used for:

[0038] Determine the digital information and / or data quality information corresponding to each of the aforementioned orders;

[0039] For each order: determine the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order.

[0040] Optionally, the order clustering module is specifically used for:

[0041] If the digital information and / or data quality information corresponding to the order meets the first condition, the order is classified into the first cluster.

[0042] If the digital information and / or data quality information corresponding to the order meets the second condition, the order is classified into the second cluster.

[0043] If the digital information and / or data quality information corresponding to the order does not meet the first condition and the second condition, the order is classified into a third cluster.

[0044] Optionally, the order clustering module is further used for:

[0045] Determine the quantity of valid information in the order;

[0046] The digital information of the order is determined based on the amount of valid information.

[0047] Optionally, the order clustering module is further used for:

[0048] Determine the channel information and labeling information corresponding to the order;

[0049] Based on the channel information and the annotation information, the data quality information corresponding to the order is determined.

[0050] Thirdly, embodiments of the present invention provide an electronic device, comprising:

[0051] One or more processors;

[0052] Storage device for storing one or more programs.

[0053] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0054] Fourthly, embodiments of the present invention provide a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above embodiments.

[0055] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the above embodiments.

[0056] One embodiment of the above invention has the following advantages or beneficial effects: multiple orders for the target product are clustered to obtain multiple order clusters. Based on the order clusters corresponding to the orders, the corresponding equity attribution model for each order is determined. Using different equity attribution models, equity attribution information corresponding to different orders is obtained, thereby determining the equity contribution information of the target product. Different equity attribution models are designed for the data conditions and characteristics of different orders. Therefore, the solution of this invention has a wide range of applications and can accurately obtain equity contribution information for the target product.

[0057] The further effects of the aforementioned unconventional alternative methods will be explained below in conjunction with specific implementation methods. Attached Figure Description

[0058] The accompanying drawings are provided to better understand the invention and are not intended to unduly limit the scope of the invention. Wherein:

[0059] Figure 1 This is a flowchart illustrating an equity attribution method provided in the first embodiment of the present invention;

[0060] Figure 2 This is a flowchart illustrating an equity attribution method provided in the second embodiment of the present invention;

[0061] Figure 3 This is a flowchart illustrating an equity attribution method provided in the third embodiment of the present invention;

[0062] Figure 4 This is a schematic diagram of the structure of an attribution device provided in an embodiment of the present invention;

[0063] Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing terminal devices or servers of the present invention. Detailed Implementation

[0064] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention, including various details to aid understanding. These details should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0065] It should be noted that the collection, analysis, use, transmission, and storage of user personal information involved in the technical solution of this invention all comply with relevant laws and regulations, are used for legitimate and reasonable purposes, and are not shared, disclosed, or sold outside of these legitimate uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken to prevent unauthorized access to such personal information data, ensure that personnel authorized to access personal information data comply with relevant laws and regulations, and ensure the security of user personal information. Once this user personal information data is no longer needed, the risk should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0066] Figure 1 This is a flowchart illustrating an equity attribution method provided in the first embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0067] Step 101: Obtain order information for multiple orders corresponding to the target product. The order information includes: benefits information.

[0068] The target product can be set according to business needs. The target product can be a physical product, financial product, or service product that the company sells.

[0069] Order information refers to the information of orders related to the target product. Order information may include: user information, merchant type information, and benefits information. Benefits information refers to information related to the benefits or combinations of benefits involved in the order. Benefits are represented by a specific form of discount or discount equivalent. Benefits can take various forms such as points, vouchers, discount activities, and incentive bonuses.

[0070] The statistical period can be determined, and successful order transaction information for the target product within the statistical period can be filtered out. Then, the order transaction information is correlated with the log information to generate the order information in step 101.

[0071] The rights and benefits information can be a collection of rights and benefits data used in an order. The rights and benefits information includes at least one piece of rights and benefits data. Each piece of rights and benefits data may include: the time of occurrence, the rights and benefits identifier, the rights and benefits name, and the rights and benefits amount, etc.

[0072] Step 102: Cluster the multiple orders to obtain multiple order clusters.

[0073] Orders can be clustered based on multiple dimensions of information. For example, they can be clustered based on the order channel, separating online and offline transactions into two distinct clusters. Furthermore, multiple orders can be clustered based on their corresponding digital information and data quality information.

[0074] Step 103: For each order: Determine the equity attribution model corresponding to the order based on the order cluster.

[0075] Different attribution models are set up for different order clusters. The attribution model can be built based on the final interaction attribution model, linear attribution model, Markov attribution model, first interaction attribution model, etc.

[0076] Step 104: Input the order information into the equity attribution model to obtain the equity attribution information corresponding to the order. The equity attribution information includes: equity identifier and its corresponding weight.

[0077] Rights identifiers are used to identify various rights and combinations of rights. Rights product information can be pre-stored in the system, including: rights identifier, rights name, rights amount, etc.

[0078] The equity attribution model outputs equity attribution information for each order. This information includes at least one equity identifier and its corresponding weight. The weight of each equity identifier represents the degree to which the equity corresponding to that identifier contributes to the order.

[0079] Step 105: Determine the equity contribution information for the target product based on the equity attribution information corresponding to each order.

[0080] Based on the attribution information for each order, the contribution information of the overall entity, different merchants, and different user groups to the target product can be calculated. Specifically, multiple target orders corresponding to the overall entity, different merchants, and different user groups can be selected first, and then the attribution information of multiple target orders can be obtained. By combining the attribution information of multiple target orders, the contribution information of the overall entity, different merchants, and different user groups to the target product can be obtained.

[0081] The benefit contribution information may include: at least one weight identifier and the contribution weight corresponding to each weight identifier. The contribution weight corresponding to the benefit identifier is used to characterize the degree to which the benefit corresponding to that benefit identifier contributes to the order conversion of the target product.

[0082] It can calculate the statistical value of each weight identifier in each target order and use the statistical value of the weight as the contribution weight corresponding to each weight identifier. The statistical value of the weight may include: weight mean, weight median, and weight mode, etc. The weight identifiers are sorted from largest to smallest according to their contribution weight. Based on business needs, a preset number of weight identifiers with the largest contribution weight are selected, and the selected weight identifiers and their corresponding contribution weights are combined into equity contribution information for the target product.

[0083] In this embodiment of the invention, multiple orders for the target product are clustered to obtain multiple order clusters. Based on the order clusters corresponding to the orders, the corresponding equity attribution model is determined. Using different equity attribution models, equity attribution information for different orders is obtained, thereby determining the equity contribution information for the target product. Different equity attribution models are designed for the data conditions and characteristics of different orders. Therefore, the solution of this embodiment of the invention has a wide range of applications and can accurately obtain equity contribution information for the target product.

[0084] Figure 2 This is a flowchart illustrating an equity attribution method provided in the second embodiment of the present invention, as shown below. Figure 2 As shown, the method includes:

[0085] Step 201: Obtain order information for multiple orders corresponding to the target product. The order information includes: benefits information.

[0086] Step 202: Determine the digital information and / or data quality information corresponding to each order.

[0087] Because orders are generated from multiple channels, the system may lack a lot of order-related information. Digital information is used to characterize the degree of digitalization of an order. The digital information for each order can be determined as follows: determine the amount of valid information in the order; based on the amount of valid information, determine the order's digital information.

[0088] Specifically, determine the total amount of information corresponding to each order, and divide the number of valid pieces of information by the total amount of information to obtain the digitized information of the order. For example, if the order information is: order number, order time, order items, and order amount, then the total amount of information is 4. The information corresponding to the target order is: 0001, empty, item 1, 100. It can be seen that the order time is empty, the number of valid pieces of information for this target order is 3, and therefore the digitized information of the target order is 75%.

[0089] Data quality information is used to characterize the quality level of order information. Data quality information can be categorized into Level 1, Level 2, Level 3, etc. The data quality information for each order can be determined as follows: determine the channel information and labeling information corresponding to the order; based on the channel information and labeling information, determine the data quality information corresponding to the order.

[0090] Different data quality information corresponding to different channel information and annotation information can be set according to specific needs. For example: if the channel information represents online orders, the data quality information is level 1. If the channel information represents offline orders and the annotation information represents manual annotation, the data quality information is level 2. If the channel information represents offline orders and the annotation information represents no manual annotation, the data quality information is level 3.

[0091] Step 203: For each order: Determine the order cluster based on the digital information and / or data quality information corresponding to the order.

[0092] Multiple order clusters can be set according to business needs, with each order cluster corresponding to a clustering condition. For example, the system can set two order clusters, with the first cluster corresponding to the first condition and the second cluster corresponding to the second condition.

[0093] In one embodiment of the present invention, the system is configured with three order clusters. In response to the digital information and / or data quality information corresponding to an order meeting a first condition, the order is assigned to the first cluster; in response to the digital information and / or data quality information corresponding to an order meeting a second condition, the order is assigned to the second cluster; in response to the digital information and / or data quality information corresponding to an order not meeting either the first or second condition, the order is assigned to the third cluster.

[0094] The first, second, and third conditions can all be flexibly set according to business needs. For example, the first condition can be that the digitized information is greater than 75% and the data quality information is level one. The second condition can be that the digitized information is less than 50% and the data quality information is level three. Orders that do not meet the first and second conditions are orders that meet the third condition.

[0095] In the example above, the first cluster mainly includes online orders with high digitization levels and good data quality. The second cluster mainly includes offline orders with low digitization levels and poor data quality. Orders not belonging to the first or second cluster are assigned to the third cluster. Different equity attribution models are used for attribution analysis for each of these clusters representing different levels of digital operation.

[0096] Step 204: For each order: Determine the equity attribution model corresponding to the order based on the order cluster.

[0097] Step 205: Input the order information into the equity attribution model to obtain the equity attribution information corresponding to the order. The equity attribution information includes: equity identifier and its corresponding weight.

[0098] Step 206: Determine the equity contribution information for the target product based on the equity attribution information corresponding to each order.

[0099] In the embodiments of this invention, for scenarios involving single-benefit marketing incentives and combined-benefit marketing incentives for different merchants and user groups, and addressing issues such as how to effectively distribute benefits, how to avoid duplicate benefit distribution, and how to avoid wasting combined benefits, attribution analysis models and decision algorithms are established and implemented. Different benefit attribution models are proposed to address the digital information and data quality information of different orders. Using different benefit attribution models, accurate benefit attribution information can be obtained.

[0100] The rights attribution method provided by the embodiments of the present invention can clearly identify the first, second, and third attributions of rights for the growth of marketing transaction volume of different merchants and the growth of marketing transaction volume of different user groups, and provide rights marketing link evaluation for transaction volume rights marketing effect for the whole, different merchants, and different user groups.

[0101] Figure 3 This is a flowchart illustrating an equity attribution method provided in the first embodiment of the present invention, as shown below. Figure 3 As shown, the method includes:

[0102] Step 301: Obtain order information for multiple orders corresponding to the target product. The order information includes: benefits information.

[0103] Step 302: Cluster the multiple orders to obtain multiple order clusters.

[0104] Step 303: If the order cluster corresponding to the order is the first cluster, determine the equity attribution model as the first attribution model.

[0105] The first attribution model is built upon the first-time attribution model and the Markov attribution model. The first-time attribution model allocates all marketing credit for a successful transaction to the benefits or bundled benefits that bring the first visitor to the target product, or the benefits or bundled benefits that generate the first user awareness of the target product. If a successful transaction involves bundled benefits, the conversion credit is allocated according to the contribution of each benefit amount, which is the Markov attribution model.

[0106] Step 304: If the order cluster corresponding to the order is the second cluster, determine the equity attribution model as the second attribution model.

[0107] The second attribution model is based on the Markov attribution model. The Markov attribution model is suitable for scenarios with multiple channels and a large number of channels.

[0108] Step 305: If the order cluster corresponding to the order is the third cluster, determine the equity attribution model as the third attribution model.

[0109] The third attribution model is based on the first and second attribution models.

[0110] The first cluster primarily includes online orders with high digitization levels and good data quality. The second cluster primarily includes offline orders with low digitization levels and poor data quality. Orders not belonging to either the first or second cluster are assigned to the third cluster. Different equity attribution models are used for attribution analysis for each of these clusters representing different levels of digital operations.

[0111] Step 306: Input the order information into the equity attribution model to obtain the equity attribution information corresponding to the order. The equity attribution information includes: equity identifier and its corresponding weight.

[0112] If the equity attribution model is a third attribution model, the order information of the order is input into the equity attribution model to obtain the equity attribution information corresponding to the order. This includes: inputting the order information of the order into a first attribution model to obtain first equity attribution information; inputting the order information of the order into a second attribution model to obtain second equity attribution information; determining the first weight corresponding to the first attribution model and the second weight corresponding to the second attribution model; and obtaining the equity attribution information corresponding to the order based on the first equity attribution information, the second equity attribution information, the first weight, and the second weight.

[0113] The weights corresponding to each right identifier in the first right attribution information are multiplied by a first weight to obtain the first weighted information. The weights corresponding to each right identifier in the second right attribution information are multiplied by a second weight to obtain the second weighted information. The weighted sums corresponding to each right identifier are calculated separately, that is, the weights corresponding to the right identifiers are obtained from the first and second weighted information respectively, and the obtained weights are added together. The right identifiers and their corresponding weighted sums are combined to obtain the right attribution information corresponding to the order.

[0114] Step 307: Determine the equity contribution information for the target product based on the equity attribution information corresponding to each order.

[0115] In this embodiment of the invention, considering the current state of enterprise digital operation channels and the different levels of digital operation across channels (i.e., the sufficiency of data elements), a customized attribution model for equity marketing is proposed. For channels with high levels of digital operation, the achieved marketing transaction volume is assessed by combining the initial attribution model with an enhanced Markov attribution model. For channels with low levels of digital operation, such as telephone or offline channels, manual annotation is prioritized, combined with the initial attribution model and the enhanced Markov attribution model. For other scenarios, a history-based Markov attribution model is used.

[0116] This invention involves various types of data, which can be provided by different backends or systems. By filtering and correlating these various data, order information for multiple orders corresponding to a target product can be obtained. These orders can correspond to different user groups, different merchants, and different order statuses. The data involved in this invention includes:

[0117] Online Channel Vector Group: A vector group of enumerated values ​​for the types of online channels, which can be provided by the marketing back-end system.

[0118] Offline Channel Vector Group: A vector group of enumerated values ​​for the types of offline channels, which can be provided by the marketing back-end system.

[0119] Equity Product Vector Group: Equity product number vector group, which can be provided by the equity platform system.

[0120] Order types: first-time purchase, repeat purchase, etc., which can be provided by the order center system.

[0121] Order status: payment successful, pending payment, actively cancelled, cancelled after timeout, etc.

[0122] Order data, including order number, order time, order items, and order amount, is provided by the order center system.

[0123] Transaction data, such as order number and order payment time, is provided by the transaction center system.

[0124] The rights dataset used in the order: This is a collection of rights data used in the order, including single rights and combined rights. Each piece of data in the collection includes the rights product number, rights name, and rights amount, and is provided by the trading center system.

[0125] First Order Click Log: Click logs for channel marketing links, provided by the online marketing system or the offline marketing back-end system.

[0126] Second click log for orders: Click logs on the product page of channel marketing, provided by the online marketing system or the offline marketing back-end system.

[0127] Third click log for orders: Order generation log, i.e., the log of adding an order to the shopping cart, is provided by the order center system.

[0128] Fourth click log for the order: Order payment calculation data, provided by the order center system.

[0129] Fifth click log for orders: Order payment data, provided by the transaction center system.

[0130] This invention also provides an attribution system, which includes the following modules:

[0131] Data acquisition module: Collects relevant data involved in the embodiments of this invention.

[0132] Index Association Module: This module associates order logs, establishing a link between orders and click logs. Click logs can include: first click log, second click log, third click log, fourth click log, and fifth click log.

[0133] The classification and cleaning module uses the order number of a successful transaction as the primary key to clean and label the data so that it can be entered into the corresponding accurate sub-model in the equity attribution module for modeling. The data will be clustered by the order number of the successful transaction, and related data will be marked as the first or second cluster. Other data that are not highly correlated with the order number data and whose relationship cannot be determined cannot be clustered and will be marked as the third cluster.

[0134] The equity attribution module provides a way to categorize data by online and offline channels. The equity attribution method implemented in this embodiment employs two attribution model algorithms. The first attribution model is built using an initial attribution model and an enhanced Markov attribution model, while the second attribution model is built based on a historical Markov attribution model.

[0135] In the classification and cleaning module, orders and related data marked as the first cluster are entered into the first attribution model for modeling; orders and related data marked as the second cluster are entered into the second attribution model for modeling; and other data that cannot be clustered and are marked as the third cluster are entered into the first attribution model and the second attribution model for modeling, respectively.

[0136] In the rights attribution weight correction submodule, the weights output by the first attribution model are corrected. For rights attribution outputs from the same user group, the same merchant, and in the same order, a simple mean adjustment is performed. The weights output by the second attribution model are adjusted by a coefficient of 1, meaning they are not adjusted for now. After the submodule's adjustments, a set of rights attribution weight vectors is output.

[0137] Decision module: Based on the rights attribution weight vector set for each order, the order's usage rights dataset, and order data, it calculates the overall, different merchant, and different user group's rights marketing effectiveness evaluation. The rights attribution information is stored in the form of rights attribution weight vector sets.

[0138] In this embodiment of the invention, the lifecycle of orders from different marketing channels in a digital business scenario is defined, and data elements within the order lifecycle are correlated. Based on the data elements, orders are clustered, and corresponding equity attribution models and decision algorithms are established for different clusters. The dynamically analyzed first, second, and third equity attributions of marketing transaction volume are applicable to equity marketing scenarios such as single equity and combined equity, providing a more accurate and dynamic evaluation of the effectiveness of transaction volume equity marketing for the whole, different merchants, and different user groups. Furthermore, because the applicability can be classified and accurately modeled based on the sufficiency of data elements, the equity attribution method has a wider range of applications.

[0139] Figure 4 This is a schematic diagram of the structure of an attribution device provided in an embodiment of the present invention, as shown below. Figure 4 As shown, the device includes:

[0140] The information acquisition module 401 is used to acquire order information for multiple orders corresponding to the target product. The order information includes: rights and benefits information.

[0141] The order clustering module 402 is used to cluster multiple orders to obtain multiple order clusters;

[0142] The information determination module 403 is used for each order to: determine the equity attribution model corresponding to the order based on the order cluster corresponding to the order; input the order information of the order into the equity attribution model to obtain the equity attribution information corresponding to the order, which includes: equity identifier and its corresponding weight;

[0143] Attribution module 404 is used to determine the equity contribution information for the target product based on the equity attribution information corresponding to each order.

[0144] Optionally, the order clustering module 402 is specifically used for:

[0145] Determine the digital information and / or data quality information corresponding to each order;

[0146] For each order: Determine the order cluster based on the digital information and / or data quality information corresponding to the order.

[0147] Optionally, the order clustering module 402 is specifically used for:

[0148] If the digital information and / or data quality information corresponding to the order meets the first condition, the order is classified into the first cluster.

[0149] If the digital information and / or data quality information corresponding to the order meets the second condition, the order is classified into the second cluster.

[0150] If the digital information and / or data quality information corresponding to an order does not meet the first and second conditions, the order will be classified into the third cluster.

[0151] Optionally, the order clustering module 402 is also used for:

[0152] Determine the quantity of valid information in the order;

[0153] The digital information of the order is determined based on the amount of valid information.

[0154] Optionally, the order clustering module 402 is also used for:

[0155] Determine the channel information and labeling information corresponding to the order;

[0156] Based on channel information and labeling information, determine the data quality information corresponding to the order.

[0157] Optionally, the information determination module 403 is specifically used for:

[0158] In response to the order clustering being classified as the first cluster, the equity attribution model is determined to be the first attribution model, which is established based on the initial attribution model and the Markov attribution model.

[0159] In response to the order clustering being classified as a second cluster, the equity attribution model is determined to be a second attribution model, which is based on the Markov attribution model.

[0160] In response to the order clustering being classified as the third cluster, the equity attribution model is determined to be the third attribution model, which is established based on the first and second attribution models.

[0161] Optionally, the equity attribution model is a third attribution model, which is established based on the first and second attribution models;

[0162] The information determination module 403 is specifically used for:

[0163] The order information is input into the first attribution model to obtain the first equity attribution information;

[0164] The order information is input into the second attribution model to obtain the second equity attribution information;

[0165] Determine the first weight corresponding to the first attribution model and the second weight corresponding to the second attribution model;

[0166] Based on the first equity attribution information, the second equity attribution information, the first weight, and the second weight, the equity attribution information corresponding to the order is obtained.

[0167] This invention provides an electronic device, comprising:

[0168] One or more processors;

[0169] Storage device for storing one or more programs.

[0170] When one or more programs are executed by one or more processors, the one or more processors implement the methods of any of the above embodiments.

[0171] This invention provides a computer program product, including a computer program that, when executed by a processor, implements the enterprise risk assessment method of this invention.

[0172] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing a terminal device of the present invention. Figure 5 The terminal device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0173] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 502 or programs loaded from storage section 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the system 500. The CPU 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0174] The following components are connected to I / O interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to I / O interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 510 as needed so that computer programs read from it can be installed into storage section 508 as needed.

[0175] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by central processing unit (CPU) 501, it performs the functions defined above in the system of this invention.

[0176] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0177] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0178] The modules described in the embodiments of the present invention can be implemented in software or hardware. The described modules can also be housed in a processor, and for example, can be described as: an information acquisition module, an order clustering module, an information determination module, and an attribution module. The names of these modules do not necessarily limit the module itself; for example, the information acquisition module can also be described as "a module that acquires order information for multiple orders corresponding to a target product."

[0179] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include:

[0180] Obtain order information for multiple orders corresponding to the target product, wherein the order information includes: benefits information;

[0181] Cluster the multiple orders to obtain multiple order clusters;

[0182] For each order: Based on the order cluster corresponding to the order, determine the rights attribution model corresponding to the order; input the order information of the order into the rights attribution model to obtain the rights attribution information corresponding to the order, wherein the rights attribution information includes: rights identifier and its corresponding weight;

[0183] Based on the equity attribution information corresponding to each order, determine the equity contribution information for the target product.

[0184] According to the technical solution of this invention, multiple orders for a target product are clustered to obtain multiple order clusters. Based on the order clusters corresponding to the orders, the corresponding equity attribution model is determined. Using different equity attribution models, equity attribution information corresponding to different orders is obtained, thereby determining the equity contribution information of the target product. Different equity attribution models are designed for the data conditions and characteristics of different orders. Therefore, the solution of this invention has a wide range of applications and can accurately obtain equity contribution information for the target product.

[0185] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for attributing rights, characterized in that, include: Obtain order information for multiple orders corresponding to the target product, wherein the order information includes: benefits information; Cluster the multiple orders to obtain multiple order clusters; For each order: Based on the order cluster corresponding to the order, determine the rights attribution model corresponding to the order; input the order information of the order into the rights attribution model to obtain the rights attribution information corresponding to the order, wherein the rights attribution information includes: rights identifier and its corresponding weight; Based on the equity attribution information corresponding to each order, determine the equity contribution information for the target product, including: first, filtering out multiple target orders corresponding to the whole, different merchants, and different user groups; then, obtaining the equity attribution information of multiple target orders; and combining the equity attribution information of multiple target orders to obtain the equity contribution information for the target product for the whole, different merchants, and different user groups. The step of clustering the multiple orders to obtain multiple order clusters includes: determining the digital information and / or data quality information corresponding to each order; for each order: determining the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order; wherein, the digital information is used to characterize the degree of digitalization of the order, and the data quality information is used to characterize the quality level of the order information, and the multiple order clusters include: a first cluster, a second cluster, and a third cluster, wherein the first cluster includes online orders with high degree of digitalization and good data quality, the second cluster includes offline orders with low degree of digitalization and poor data quality, and the remaining orders that do not belong to the first cluster and the second cluster are classified into the third cluster; The equity attribution model is a third attribution model, which is established based on the first and second attribution models. The step of inputting the order information of the order into the equity attribution model to obtain the equity attribution information corresponding to the order includes: inputting the order information of the order into the first attribution model to obtain first equity attribution information; inputting the order information of the order into the second attribution model to obtain second equity attribution information; determining the first weight corresponding to the first attribution model and the second weight corresponding to the second attribution model; and obtaining the equity attribution information corresponding to the order based on the first equity attribution information, the second equity attribution information, the first weight, and the second weight. The first attribution model is established based on the initial attribution model and the Markov attribution model, and the second attribution model is established based on the Markov attribution model.

2. The method according to claim 1, characterized in that, The step of determining the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order includes: If the digital information and / or data quality information corresponding to the order meets the first condition, the order is classified into the first cluster. If the digital information and / or data quality information corresponding to the order meets the second condition, the order is classified into the second cluster. If the digital information and / or data quality information corresponding to the order does not meet the first condition and the second condition, the order is classified into a third cluster.

3. The method according to claim 1, characterized in that, Determine the digital information corresponding to each of the aforementioned orders, including: Determine the quantity of valid information in the order; The digital information of the order is determined based on the amount of valid information.

4. The method according to claim 1, characterized in that, Determine the data quality information corresponding to each of the aforementioned orders, including: Determine the channel information and labeling information corresponding to the order; Based on the channel information and the annotation information, the data quality information corresponding to the order is determined.

5. The method according to claim 1, characterized in that, The step of determining the equity attribution model corresponding to the order based on the order clustering corresponding to the order includes: In response to the order clustering being classified as the first cluster, the equity attribution model is determined to be the first attribution model; In response to the order clustering being classified as a second cluster, the equity attribution model is determined to be a second attribution model. In response to the order clustering being classified as a third cluster, the equity attribution model is determined to be a third attribution model.

6. An attribution device, characterized in that, include: The information acquisition module is used to acquire order information for multiple orders corresponding to the target product, wherein the order information includes: rights and benefits information; The order clustering module is used to cluster the multiple orders to obtain multiple order clusters; The information determination module is used for each order to: determine the rights attribution model corresponding to the order based on the order cluster corresponding to the order; input the order information of the order into the rights attribution model to obtain the rights attribution information corresponding to the order, wherein the rights attribution information includes: rights identifier and its corresponding weight; The attribution module is used to determine the equity contribution information for the target product based on the equity attribution information corresponding to each order. The order clustering module is specifically used for: determining the digital information and / or data quality information corresponding to each order; for each order: determining the order cluster corresponding to the order based on the digital information and / or data quality information corresponding to the order; wherein, the digital information is used to characterize the degree of digitalization of the order, and the data quality information is used to characterize the quality level of the order information, and the multiple order clusters include: a first cluster, a second cluster, and a third cluster, wherein the first cluster includes online orders with high degree of digitalization and good data quality, the second cluster includes offline orders with low degree of digitalization and poor data quality, and the remaining orders that do not belong to the first cluster and the second cluster are classified into the third cluster; The information determination module is specifically used for: the equity attribution model is a third attribution model, which is established based on the first attribution model and the second attribution model; the step of inputting the order information of the order into the equity attribution model to obtain the equity attribution information corresponding to the order includes: inputting the order information of the order into the first attribution model to obtain first equity attribution information; inputting the order information of the order into the second attribution model to obtain second equity attribution information; determining the first weight corresponding to the first attribution model and the second weight corresponding to the second attribution model; and obtaining the equity attribution information corresponding to the order based on the first equity attribution information, the second equity attribution information, the first weight, and the second weight. The attribution module is specifically used to: firstly filter out multiple target orders corresponding to the whole, different merchants, and different user groups; then obtain the rights attribution information of multiple target orders; and combine the rights attribution information of multiple target orders to obtain the rights contribution information of the whole, different merchants, and different user groups for the target product. The first attribution model is established based on the initial attribution model and the Markov attribution model, and the second attribution model is established based on the Markov attribution model.

7. The apparatus according to claim 6, characterized in that, The order clustering module is specifically used for: If the digital information and / or data quality information corresponding to the order meets the first condition, the order is classified into the first cluster. If the digital information and / or data quality information corresponding to the order meets the second condition, the order is classified into the second cluster. If the digital information and / or data quality information corresponding to the order does not meet the first condition and the second condition, the order is classified into a third cluster.

8. The apparatus according to claim 6, characterized in that, The order clustering module is also used for: Determine the quantity of valid information in the order; The digital information of the order is determined based on the amount of valid information.

9. The apparatus according to claim 6, characterized in that, The order clustering module is also used for: Determine the channel information and labeling information corresponding to the order; Based on the channel information and the annotation information, the data quality information corresponding to the order is determined.

10. An electronic device, characterized in that, include: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1-5.

11. A computer-readable medium having a computer program stored thereon, characterized in that... When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images