Equity data conversion method and system based on artificial intelligence

Abstract

The present invention discloses a method and system for converting rights and interests data based on artificial intelligence, the method comprising: in response to a conversion request of a target user, obtaining the member parameters and member rights and interests data of the target user; analyzing the cost rules and regional rules corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request; determining a conversion prediction neural network model and multiple conversion computing devices from multiple candidate models and multiple candidate computing devices according to the cost rules and the regional rules; sending the member rights and interests data to the conversion prediction neural network model in the multiple conversion computing devices for conversion calculation to calculate the converted member data. It can be seen that the present invention can effectively improve the efficiency of the conversion calculation of member rights and interests data, improve the accuracy of data conversion, reduce errors, and reduce the cost of manual verification.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an equity data conversion method and system based on artificial intelligence. Background Art

[0002] With the development of data processing technology, most merchants also use data to represent the membership benefits they provide to their members. For example, members’ benefits and historical usage records are saved through physical cards or databases for verification or calculation during subsequent member consumption. However, when dealing with the conversion needs of merchant member benefit data, such as the update of merchant member versions or the need for users to change their membership types, existing data processing technologies do not fully consider the cost information, regional information and other parameters of member data to achieve more accurate data conversion, nor do they consider the use of distributed algorithms to improve conversion efficiency. Therefore, their processing efficiency is low, and manual access is often required, which is costly and prone to errors. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide an equity data conversion method and system based on artificial intelligence, which can effectively improve the efficiency of the conversion calculation of member equity data, improve the accuracy of data conversion, reduce errors, and reduce manual verification costs.

[0004] In order to solve the above technical problems, the first aspect of the present invention discloses an equity data conversion method based on artificial intelligence, the method comprising:

[0005] In response to a conversion request of a target user, obtaining membership parameters and membership rights and interests data of the target user;

[0006] analyzing the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request;

[0007] Determining a conversion prediction neural network model and a plurality of conversion computing devices from a plurality of candidate models and a plurality of candidate computing devices according to the cost rule and the region rule;

[0008] The member benefit data is sent to the conversion prediction neural network model in the multiple conversion calculation devices for conversion calculation to calculate and obtain the converted member data.

[0009] As an optional implementation, in the first aspect of the present invention, the conversion type is a cross-region conversion type, a cross-store conversion type, a new-old card conversion type, a customer subjective conversion type, or a merchant objective conversion type.

[0010] As an optional implementation, in the first aspect of the present invention, the member information includes member personal information and member historical consumption records.

[0011] As an optional implementation manner, in the first aspect of the present invention, analyzing the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request includes:

[0012] Determining a plurality of first region information according to the native place information, residence information and delivery address information in the member personal information;

[0013] Determining a plurality of second region information according to historical consumption locations in the member's historical consumption records;

[0014] Determine the regional rule corresponding to the conversion request according to the first regional information and the second regional information

[0015] Determining a pre-conversion rule type and a post-conversion rule type according to a conversion type corresponding to the conversion request;

[0016] Determining a first cost accounting record corresponding to the pre-conversion rule type;

[0017] Determining a second cost accounting record corresponding to the converted rule type;

[0018] A cost rule corresponding to the conversion request is determined according to the first cost accounting record and the second cost accounting record.

[0019] As an optional implementation, in the first aspect of the present invention, determining the regional rule corresponding to the conversion request according to the first regional information and the second regional information includes:

[0020] Calculate the intersection between all the first region information and all the second region information to obtain a plurality of intersection regions;

[0021] For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area;

[0022] The union of the competitive relationships among the merchants' products in all the intersection areas is determined as the area rule corresponding to the conversion request.

[0023] As an optional implementation, in the first aspect of the present invention, determining the cost rule corresponding to the conversion request according to the first cost accounting record and the second cost accounting record includes:

[0024] Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold;

[0025] The differences between the cost item types and cost values ​​corresponding to all the high-difference record pairs are determined as the cost rules corresponding to the conversion request.

[0026] As an optional implementation, in the first aspect of the present invention, determining a conversion prediction neural network model and a plurality of conversion computing devices from a plurality of candidate models and a plurality of candidate computing devices according to the cost rule and the regional rule comprises:

[0027] For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model;

[0028] Calculating a first similarity between the rule annotation information of the model training data and a rule set; the rule set includes the cost rule and the region rule;

[0029] Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set;

[0030] Calculating the product of the first similarity and the second similarity to obtain a priority parameter of the candidate model;

[0031] Determine the candidate model with the highest priority parameter as a conversion prediction neural network model; the conversion prediction neural network model is a training data set including a plurality of training member equity data and corresponding converted data annotations;

[0032] Based on the historical calculation records and device performance parameters of multiple candidate computing devices, multiple conversion computing devices and corresponding device data allocation strategies are screened and determined; the device data allocation strategy is used to limit the data portion of the member equity data that each of the conversion computing devices needs to predict and calculate.

[0033] As an optional implementation, in the first aspect of the present invention, the screening and determining of multiple conversion computing devices and corresponding device data allocation strategies based on historical computing records and device performance parameters of multiple candidate computing devices includes:

[0034] For each candidate computing device, calculating a third similarity between a user parameter of input computing data in a historical computing record of the candidate computing device and the member parameter;

[0035] Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value;

[0036] Calculating the product of the performance prediction value and the third similarity to obtain a device priority parameter;

[0037] Sorting all the candidate computing devices according to the device priority parameter to obtain a device sequence;

[0038] Screening out all the candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices;

[0039] The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all conversion computing devices; the second level is the size order of the device priority parameter in the device priority parameters of all conversion computing devices;

[0040] Setting the restriction condition includes that the amount of data of the data portion allocated to each conversion computing device is greater than a first data threshold and the amount of data of the data portion allocated to each conversion computing device is less than a performance restriction threshold; the performance restriction threshold is proportional to the corresponding performance prediction value;

[0041] According to the objective function and the restriction conditions, based on the particle swarm algorithm, the member equity data is iteratively allocated to obtain the data portion allocated to each conversion computing device, and obtain the device data allocation strategy.

[0042] A second aspect of an embodiment of the present invention discloses an equity data conversion system based on artificial intelligence, the system comprising:

[0043] An acquisition module, configured to acquire membership parameters and membership rights data of a target user in response to a conversion request of the target user;

[0044] An analysis module, configured to analyze a cost rule and a regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request;

[0045] A determination module, configured to determine a conversion prediction neural network model and a plurality of conversion computing devices from a plurality of candidate models and a plurality of candidate computing devices according to the cost rule and the region rule;

[0046] The calculation module is used to send the member benefit data to the conversion prediction neural network model in the multiple conversion calculation devices for conversion calculation to calculate the converted member data.

[0047] As an optional implementation, in the second aspect of the present invention, the conversion type is a cross-region conversion type, a cross-store conversion type, a new-old card conversion type, a customer subjective conversion type, or a merchant objective conversion type.

[0048] As an optional implementation, in the second aspect of the present invention, the member information includes member personal information and member historical consumption records.

[0049] As an optional implementation manner, in the second aspect of the present invention, analyzing the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request includes:

[0050] Determining a plurality of first region information according to the native place information, residence information and delivery address information in the member personal information;

[0051] Determining a plurality of second region information according to historical consumption locations in the member's historical consumption records;

[0052] Determine the regional rule corresponding to the conversion request according to the first regional information and the second regional information

[0053] Determining a pre-conversion rule type and a post-conversion rule type according to a conversion type corresponding to the conversion request;

[0054] Determining a first cost accounting record corresponding to the pre-conversion rule type;

[0055] Determining a second cost accounting record corresponding to the converted rule type;

[0056] A cost rule corresponding to the conversion request is determined according to the first cost accounting record and the second cost accounting record.

[0057] As an optional implementation, in the second aspect of the present invention, determining the regional rule corresponding to the conversion request according to the first regional information and the second regional information includes:

[0058] Calculate the intersection between all the first region information and all the second region information to obtain a plurality of intersection regions;

[0059] For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area;

[0060] The union of the competitive relationships among the merchants' products in all the intersection areas is determined as the area rule corresponding to the conversion request.

[0061] As an optional implementation, in the second aspect of the present invention, the specific manner in which the analysis module determines the cost rule corresponding to the conversion request according to the first cost accounting record and the second cost accounting record includes:

[0062] Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold;

[0063] The differences between the cost item types and cost values ​​corresponding to all the high-difference record pairs are determined as the cost rules corresponding to the conversion request.

[0064] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the conversion prediction neural network model and the multiple conversion computing devices from the multiple candidate models and the multiple candidate computing devices according to the cost rule and the regional rule includes:

[0065] For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model;

[0066] Calculating a first similarity between the rule annotation information of the model training data and a rule set; the rule set includes the cost rule and the region rule;

[0067] Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set;

[0068] Calculating the product of the first similarity and the second similarity to obtain a priority parameter of the candidate model;

[0069] Determine the candidate model with the highest priority parameter as a conversion prediction neural network model; the conversion prediction neural network model is a training data set including a plurality of training member equity data and corresponding converted data annotations;

[0070] Based on the historical calculation records and device performance parameters of multiple candidate computing devices, multiple conversion computing devices and corresponding device data allocation strategies are screened and determined; the device data allocation strategy is used to limit the data portion of the member equity data that each of the conversion computing devices needs to predict and calculate.

[0071] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module screens and determines multiple conversion computing devices and corresponding device data allocation strategies based on historical computing records and device performance parameters of multiple candidate computing devices includes:

[0072] For each candidate computing device, calculating a third similarity between a user parameter of input computing data in a historical computing record of the candidate computing device and the member parameter;

[0073] Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value;

[0074] Calculating the product of the performance prediction value and the third similarity to obtain a device priority parameter;

[0075] Sorting all the candidate computing devices according to the device priority parameter to obtain a device sequence;

[0076] Screening out all the candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices;

[0077] The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all conversion computing devices; the second level is the size order of the device priority parameter in the device priority parameters of all conversion computing devices;

[0078] Setting the restriction condition includes that the amount of data of the data portion allocated to each conversion computing device is greater than a first data threshold and the amount of data of the data portion allocated to each conversion computing device is less than a performance restriction threshold; the performance restriction threshold is proportional to the corresponding performance prediction value;

[0079] According to the objective function and the restriction conditions, based on the particle swarm algorithm, the member equity data is iteratively allocated to obtain the data portion allocated to each conversion computing device, and obtain the device data allocation strategy.

[0080] The third aspect of the present invention discloses another equity data conversion system based on artificial intelligence, the system comprising:

[0081] A memory storing executable program code;

[0082] a processor coupled to the memory;

[0083] The processor calls the executable program code stored in the memory to execute part or all of the steps in the artificial intelligence-based equity data conversion method disclosed in the first aspect of the present invention.

[0084] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the artificial intelligence-based equity data conversion method disclosed in the first aspect of the present invention.

[0085] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0086] The present invention can analyze the cost and regional rules corresponding to the conversion request, and based on this, determine the computing device and the algorithm model for prediction, so as to realize the conversion calculation of member rights data based on the prediction algorithm and distributed computing, thereby effectively improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0088] Figure 1 It is a flowchart of an equity data conversion method based on artificial intelligence disclosed in an embodiment of the present invention.

[0089] Figure 2 It is a structural diagram of an equity data conversion system based on artificial intelligence disclosed in an embodiment of the present invention.

[0090] Figure 3 It is a structural diagram of another equity data conversion system based on artificial intelligence disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0091] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0092] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0093] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0094] The present invention discloses a method and system for converting equity data based on artificial intelligence, which can analyze the cost and regional rules corresponding to the conversion request, and determine the computing device and the algorithm model for prediction based on this, so as to realize the conversion calculation of member equity data based on the prediction algorithm and distributed computing, thereby effectively improving the efficiency of the conversion calculation of member equity data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification. The following are detailed descriptions.

[0095] Embodiment 1

[0096] See also Figure 1 , Figure 1 This is a flow chart of a method for converting equity data based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The described AI-based equity data conversion method can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the equity data conversion method based on artificial intelligence may include the following operations:

[0097] 101. In response to a conversion request of a target user, obtain membership parameters and membership rights and interests data of the target user.

[0098] 102. Analyze the cost rule and regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request.

[0099] 103. According to the cost rule and the regional rule, a conversion prediction neural network model and a plurality of conversion computing devices are determined from a plurality of candidate models and a plurality of candidate computing devices.

[0100] 104. Send the member benefit data to the conversion prediction neural network model in multiple conversion calculation devices for conversion calculation to calculate and obtain the converted member data.

[0101] It can be seen that the above-mentioned embodiments of the invention can analyze the rules of the cost and region corresponding to the conversion request, and based on this, determine the computing device and the algorithm model for prediction, so as to realize the conversion calculation of member rights data based on the prediction algorithm and distributed computing, thereby effectively improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0102] As an optional embodiment, in the above steps, the conversion type is a cross-region conversion type, a cross-store conversion type, a new-old card conversion type, a customer's subjective conversion type, or a merchant's objective conversion type.

[0103] It can be seen that through the above optional embodiments, the details of the conversion type corresponding to the conversion request are clarified, so that the conversion type can accurately characterize the purpose and source of the user's conversion, so as to accurately analyze the cost rules and regional rules in the subsequent process, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0104] As an optional embodiment, in the above steps, the member information includes member personal information and member historical consumption records.

[0105] It can be seen that through the above optional embodiments, the content details of the member information are clarified, so that the member information can accurately characterize the user's information characteristics, so as to accurately analyze the cost rules and regional rules in the subsequent period, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0106] As an optional embodiment, in the above steps, analyzing the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request includes:

[0107] Determine multiple first region information based on the native place information, residence information and delivery address information in the member's personal information;

[0108] Determine multiple second region information according to historical consumption locations in the member's historical consumption records;

[0109] Determine the regional rule corresponding to the conversion request according to the first regional information and the second regional information

[0110] Determine the pre-conversion rule type and the post-conversion rule type according to the conversion type corresponding to the conversion request;

[0111] Determine the first cost accounting record corresponding to the rule type before conversion;

[0112] Determine the second cost accounting record corresponding to the converted rule type;

[0113] A cost rule corresponding to the conversion request is determined according to the first cost accounting record and the second cost accounting record.

[0114] It can be seen that through the above-mentioned optional embodiments, the cost rules and regional rules corresponding to the conversion request can be determined by analyzing the member information and the cost accounting records of the rules before and after the conversion, so as to accurately determine the computing equipment and the algorithm model for prediction in the future, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0115] As an optional embodiment, in the above step, determining the regional rule corresponding to the conversion request according to the first regional information and the second regional information includes:

[0116] Calculate the intersection between all the first region information and all the second region information to obtain multiple intersection regions;

[0117] For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area;

[0118] The union of the competitive relationships among the merchants' products in all the intersection areas is determined as the regional rule corresponding to the conversion request.

[0119] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the union of the competition relationships of merchant products in the intersection area through the intersection calculation of the regional information and the preset merchant competition relationship, so as to determine the regional rules corresponding to the conversion request, so as to accurately determine the computing device and the algorithm model for prediction in the subsequent process, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0120] As an optional embodiment, in the above step, determining the cost rule corresponding to the conversion request according to the first cost accounting record and the second cost accounting record includes:

[0121] Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; optionally, the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold;

[0122] The differences between the cost item types and cost values ​​corresponding to all high-difference record pairs are determined as the cost rules corresponding to the conversion request.

[0123] It can be seen that through the above-mentioned optional embodiments, multiple high-difference record pairs can be obtained by calculating and screening the cost value differences between cost accounting records, so as to determine the cost rules corresponding to the conversion requests, so as to accurately determine the calculation equipment and the algorithm model for prediction in the subsequent period, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0124] As an optional embodiment, in the above steps, determining the conversion prediction neural network model and the multiple conversion computing devices from the multiple candidate models and the multiple candidate computing devices according to the cost rule and the regional rule includes:

[0125] For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model;

[0126] Calculating a first similarity between rule annotation information of model training data and a rule set; optionally, the rule set includes a cost rule and a regional rule;

[0127] Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set;

[0128] Calculate the product of the first similarity and the second similarity to obtain the priority parameter of the candidate model;

[0129] Determine the candidate model with the highest priority parameter as the conversion prediction neural network model; Optionally, the conversion prediction neural network model includes a training data set including a plurality of training member equity data and corresponding converted data annotations;

[0130] Based on the historical calculation records and device performance parameters of multiple candidate computing devices, multiple conversion computing devices and corresponding device data allocation strategies are screened and determined; the device data allocation strategy is used to limit the data portion of the member equity data that each conversion computing device needs to predict and calculate.

[0131] It can be seen that through the above-mentioned optional embodiments, the priority parameters of the candidate models can be obtained by analyzing and calculating the model training data and the historical usage records of the models corresponding to the candidate models, so as to screen out targeted algorithm models for prediction, and determine multiple conversion computing devices and corresponding device data allocation strategies based on the historical computing records and device performance parameters of the candidate computing devices, so as to improve the efficiency of the conversion calculation of member rights data, improve the accuracy of data conversion, reduce errors, and reduce the cost of manual verification through the determined devices and algorithm models.

[0132] As an optional embodiment, in the above step, screening and determining multiple conversion computing devices and corresponding device data allocation strategies according to historical computing records and device performance parameters of multiple candidate computing devices includes:

[0133] For each candidate computing device, calculating a third similarity between a user parameter and a member parameter of input computing data in a historical computing record of the candidate computing device;

[0134] Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value;

[0135] Calculate the product of the performance prediction value and the third similarity to obtain the device priority parameter;

[0136] Sort all candidate computing devices according to the device priority parameter to obtain a device sequence;

[0137] Screening out all candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices;

[0138] The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; optionally, the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all the conversion computing devices allocated; the second level is the size order of the device priority parameter in the device priority parameters of all the conversion computing devices;

[0139] The setting restriction condition includes that the data amount of the data portion allocated to each conversion computing device is greater than a first data threshold and the data amount of the data portion allocated to each conversion computing device is less than a performance restriction threshold; optionally, the performance restriction threshold is proportional to the corresponding performance prediction value;

[0140] According to the objective function and constraints, based on the particle swarm algorithm, the member equity data is iteratively allocated to obtain the data portion allocated to each conversion computing device and obtain the device data allocation strategy.

[0141] It can be seen that through the above-mentioned optional embodiments, the device priority parameters can be calculated based on the historical calculation records and device performance parameters of the candidate computing devices to determine multiple conversion computing devices, and the device data allocation strategy can be iteratively calculated based on the particle swarm algorithm, objective function and constraints, so as to improve the efficiency of the conversion calculation of member rights data, improve the accuracy of data conversion, reduce errors, and reduce the cost of manual verification through the determined equipment and algorithm model.

[0142] Embodiment 2

[0143] See also Figure 2 , Figure 2 : is a schematic diagram of a structure of an equity data conversion system based on artificial intelligence disclosed in an embodiment of the present invention. Figure 2 The described AI-based equity data conversion system can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the equity data conversion system based on artificial intelligence may include:

[0144] The acquisition module 201 is used to acquire the membership parameters and membership rights data of the target user in response to the conversion request of the target user.

[0145] The analysis module 202 is used to analyze the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request.

[0146] The determination module 203 is used to determine a conversion prediction neural network model and a plurality of conversion computing devices from a plurality of candidate models and a plurality of candidate computing devices according to a cost rule and a regional rule.

[0147] The calculation module 204 is used to send the member benefit data to the conversion prediction neural network model in multiple conversion calculation devices for conversion calculation to calculate the converted member data.

[0148] It can be seen that the above-mentioned embodiments of the invention can analyze the rules of the cost and region corresponding to the conversion request, and based on this, determine the computing device and the algorithm model for prediction, so as to realize the conversion calculation of member rights data based on the prediction algorithm and distributed computing, thereby effectively improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0149] As an optional embodiment, the conversion type is a cross-region conversion type, a cross-store conversion type, a new-old card conversion type, a customer subjective conversion type, or a merchant objective conversion type.

[0150] It can be seen that through the above optional embodiments, the details of the conversion type corresponding to the conversion request are clarified, so that the conversion type can accurately characterize the purpose and source of the user's conversion, so as to accurately analyze the cost rules and regional rules in the subsequent process, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0151] As an optional embodiment, the member information includes member personal information and member historical consumption records.

[0152] It can be seen that through the above optional embodiments, the content details of the member information are clarified, so that the member information can accurately characterize the user's information characteristics, so as to accurately analyze the cost rules and regional rules in the subsequent period, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0153] As an optional embodiment, according to the member information and the conversion type corresponding to the conversion request, the cost rule and the regional rule corresponding to the conversion request are analyzed, including:

[0154] Determine multiple first region information based on the native place information, residence information and delivery address information in the member's personal information;

[0155] Determine multiple second region information according to historical consumption locations in the member's historical consumption records;

[0156] Determine the regional rule corresponding to the conversion request according to the first regional information and the second regional information

[0157] Determine the pre-conversion rule type and the post-conversion rule type according to the conversion type corresponding to the conversion request;

[0158] Determine the first cost accounting record corresponding to the rule type before conversion;

[0159] Determine the second cost accounting record corresponding to the converted rule type;

[0160] A cost rule corresponding to the conversion request is determined according to the first cost accounting record and the second cost accounting record.

[0161] It can be seen that through the above-mentioned optional embodiments, the cost rules and regional rules corresponding to the conversion request can be determined by analyzing the member information and the cost accounting records of the rules before and after the conversion, so as to accurately determine the computing equipment and the algorithm model for prediction in the future, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0162] As an optional embodiment, determining a region rule corresponding to the conversion request according to the first region information and the second region information includes:

[0163] Calculate the intersection between all the first region information and all the second region information to obtain multiple intersection regions;

[0164] For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area;

[0165] The union of the competitive relationships among the merchants' products in all the intersection areas is determined as the regional rule corresponding to the conversion request.

[0166] It can be seen that through the above-mentioned optional embodiments, it is possible to determine the union of the competition relationships of merchant products in the intersection area through the intersection calculation of the regional information and the preset merchant competition relationship, so as to determine the regional rules corresponding to the conversion request, so as to accurately determine the computing device and the algorithm model for prediction in the subsequent process, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0167] As an optional embodiment, the analysis module determines a specific manner of determining the cost rule corresponding to the conversion request according to the first cost accounting record and the second cost accounting record, including:

[0168] Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; optionally, the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold;

[0169] The differences between the cost item types and cost values ​​corresponding to all high-difference record pairs are determined as the cost rules corresponding to the conversion request.

[0170] It can be seen that through the above-mentioned optional embodiments, multiple high-difference record pairs can be obtained by calculating and screening the cost value differences between cost accounting records, so as to determine the cost rules corresponding to the conversion requests, so as to accurately determine the calculation equipment and the algorithm model for prediction in the subsequent period, and assist in improving the efficiency of the conversion calculation of member rights data, improving the accuracy of data conversion, reducing errors, and reducing the cost of manual verification.

[0171] As an optional embodiment, the determination module determines the specific manner of converting the prediction neural network model and the multiple conversion computing devices from the multiple candidate models and the multiple candidate computing devices according to the cost rule and the regional rule, including:

[0172] For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model;

[0173] Calculating a first similarity between rule annotation information of model training data and a rule set; optionally, the rule set includes a cost rule and a regional rule;

[0174] Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set;

[0175] Calculate the product of the first similarity and the second similarity to obtain the priority parameter of the candidate model;

[0176] Determine the candidate model with the highest priority parameter as the conversion prediction neural network model; Optionally, the conversion prediction neural network model includes a training data set including a plurality of training member equity data and corresponding converted data annotations;

[0177] Based on the historical calculation records and device performance parameters of multiple candidate computing devices, multiple conversion computing devices and corresponding device data allocation strategies are screened and determined; the device data allocation strategy is used to limit the data portion of the member equity data that each conversion computing device needs to predict and calculate.

[0178] It can be seen that through the above-mentioned optional embodiments, the priority parameters of the candidate models can be obtained by analyzing and calculating the model training data and the historical usage records of the models corresponding to the candidate models, so as to screen out targeted algorithm models for prediction, and determine multiple conversion computing devices and corresponding device data allocation strategies based on the historical computing records and device performance parameters of the candidate computing devices, so as to improve the efficiency of the conversion calculation of member rights data, improve the accuracy of data conversion, reduce errors, and reduce the cost of manual verification through the determined devices and algorithm models.

[0179] As an optional embodiment, the specific manner in which the determination module screens and determines multiple conversion computing devices and corresponding device data allocation strategies based on historical computing records and device performance parameters of multiple candidate computing devices includes:

[0180] For each candidate computing device, calculating a third similarity between a user parameter and a member parameter of input computing data in a historical computing record of the candidate computing device;

[0181] Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value;

[0182] Calculate the product of the performance prediction value and the third similarity to obtain the device priority parameter;

[0183] Sort all candidate computing devices according to the device priority parameter to obtain a device sequence;

[0184] Screening out all candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices;

[0185] The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; optionally, the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all the conversion computing devices allocated; the second level is the size order of the device priority parameter in the device priority parameters of all the conversion computing devices;

[0186] The setting restriction condition includes that the data amount of the data portion allocated to each conversion computing device is greater than a first data threshold and the data amount of the data portion allocated to each conversion computing device is less than a performance restriction threshold; optionally, the performance restriction threshold is proportional to the corresponding performance prediction value;

[0187] According to the objective function and constraints, based on the particle swarm algorithm, the member equity data is iteratively allocated to obtain the data portion allocated to each conversion computing device and obtain the device data allocation strategy.

[0188] It can be seen that through the above-mentioned optional embodiments, the device priority parameters can be calculated based on the historical calculation records and device performance parameters of the candidate computing devices to determine multiple conversion computing devices, and the device data allocation strategy can be iteratively calculated based on the particle swarm algorithm, objective function and constraints, so as to improve the efficiency of the conversion calculation of member rights data, improve the accuracy of data conversion, reduce errors, and reduce the cost of manual verification through the determined equipment and algorithm model.

[0189] Embodiment 3

[0190] See also Figure 3 , Figure 3 It is another equity data conversion system based on artificial intelligence disclosed in the embodiment of the present invention. Figure 3 The described AI-based equity data conversion system is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the equity data conversion system based on artificial intelligence may include:

[0191] A memory 301 storing executable program codes;

[0192] a processor 302 coupled to the memory 301;

[0193] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the equity data conversion method based on artificial intelligence described in the first embodiment.

[0194] Embodiment 4

[0195] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the equity data conversion method based on artificial intelligence described in the first embodiment.

[0196] Embodiment 5

[0197] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the equity data conversion method based on artificial intelligence described in Example 1.

[0198] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0199] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0200] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0201] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0202] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0203] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0204] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0205] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0206] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0207] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0208] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0209] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0210] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0211] Finally, it should be noted that the equity data conversion method and system based on artificial intelligence disclosed in the embodiment of the present invention discloses only the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. An equity data conversion method based on artificial intelligence, characterized in that: The method comprises: In response to the conversion request of the target user, obtaining the member information and member rights data of the target user; the member information includes member personal information and member historical consumption records; Analyzing the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request, including: Determining a plurality of first region information according to the native place information, residence information and delivery address information in the member personal information; Determining a plurality of second region information according to historical consumption locations in the member's historical consumption records; Calculate the intersection between all the first region information and all the second region information to obtain a plurality of intersection regions; For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area; Determine the union of the competitive relationships of the merchants' products in all the intersection areas as the area rule corresponding to the conversion request; Determining a pre-conversion rule type and a post-conversion rule type according to a conversion type corresponding to the conversion request; Determining a first cost accounting record corresponding to the pre-conversion rule type; Determining a second cost accounting record corresponding to the converted rule type; Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold; Determine the difference between the cost item type and the cost value corresponding to all the high-difference record pairs as the cost rule corresponding to the conversion request; According to the cost rule and the region rule, a conversion prediction neural network model and a plurality of conversion computing devices are determined from a plurality of candidate models and a plurality of candidate computing devices, including: For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model; Calculating a first similarity between the rule annotation information of the model training data and a rule set; the rule set includes the cost rule and the region rule; Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set; Calculating the product of the first similarity and the second similarity to obtain a priority parameter of the candidate model; Determine the candidate model with the highest priority parameter as a conversion prediction neural network model; the conversion prediction neural network model is a training data set including a plurality of training member equity data and corresponding converted data annotations; For each candidate computing device, calculating a third similarity between a user parameter of input computing data in a historical computing record of the candidate computing device and the member information; Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value; Calculating the product of the performance prediction value and the third similarity to obtain a device priority parameter; Sorting all the candidate computing devices according to the device priority parameter to obtain a device sequence; Screening out all the candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices; The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all conversion computing devices; the second level is the size order of the device priority parameter in the device priority parameters of all conversion computing devices; The setting restriction condition includes that the data amount of the data part allocated to each conversion computing device is greater than a first data threshold and the data amount of the data part allocated to each conversion computing device is less than a performance restriction threshold; the performance restriction threshold is proportional to the corresponding performance prediction value; According to the objective function and the restriction condition, based on the particle swarm algorithm, the member equity data is iteratively allocated and calculated to obtain the data portion allocated to each conversion calculation device, and obtain a device data allocation strategy; the device data allocation strategy is used to limit the data portion of the member equity data that each conversion calculation device needs to predict and calculate; The member benefit data is sent to the conversion prediction neural network model in the multiple conversion calculation devices for conversion calculation to calculate and obtain the converted member data.

2. The method for converting equity data based on artificial intelligence according to claim 1, characterized in that: The conversion type is a cross-region conversion type, a cross-store conversion type, a new-to-old card conversion type, a customer's subjective conversion type, or a merchant's objective conversion type.

3. An equity data conversion system based on artificial intelligence, characterized in that: The system comprises: An acquisition module, for acquiring membership information and membership rights data of a target user in response to a conversion request of the target user; the membership information includes member personal information and member historical consumption records; The analysis module is used to analyze the cost rule and the regional rule corresponding to the conversion request according to the member information and the conversion type corresponding to the conversion request, including: Determining a plurality of first region information according to the native place information, residence information and delivery address information in the member personal information; Determining a plurality of second region information according to historical consumption locations in the member's historical consumption records; Calculate the intersection between all the first region information and all the second region information to obtain a plurality of intersection regions; For each intersection area, the competition relationship of the goods of the merchants corresponding to the intersection area is determined according to the competition relationship of the merchants corresponding to the preset area; Determine the union of the competitive relationships of the merchants' products in all the intersection areas as the area rule corresponding to the conversion request; Determining a pre-conversion rule type and a post-conversion rule type according to a conversion type corresponding to the conversion request; Determining a first cost accounting record corresponding to the pre-conversion rule type; Determining a second cost accounting record corresponding to the converted rule type; Screening out a plurality of high-difference record pairs from the first cost accounting record and the second cost accounting record; the high-difference record pairs include two cost records of the same cost item type from the first cost accounting record and the second cost accounting record, respectively, and the difference in cost values ​​between the two cost records is greater than a preset difference threshold; Determine the difference between the cost item type and the cost value corresponding to all the high-difference record pairs as the cost rule corresponding to the conversion request; A determination module, used to determine a conversion prediction neural network model and a plurality of conversion computing devices from a plurality of candidate models and a plurality of candidate computing devices according to the cost rule and the region rule, comprising: For each candidate model, obtain the model training data and model historical usage records corresponding to the candidate model; Calculating a first similarity between the rule annotation information of the model training data and a rule set; the rule set includes the cost rule and the region rule; Calculating a second similarity between the rule information of the input data in the historical usage record of the model and the rule set; Calculating the product of the first similarity and the second similarity to obtain a priority parameter of the candidate model; Determine the candidate model with the highest priority parameter as a conversion prediction neural network model; the conversion prediction neural network model is a training data set including a plurality of training member equity data and corresponding converted data annotations; For each candidate computing device, calculating a third similarity between a user parameter of input computing data in a historical computing record of the candidate computing device and the member information; Inputting the device performance parameters of the candidate computing device into the performance prediction neural network to obtain a corresponding performance prediction value; Calculating the product of the performance prediction value and the third similarity to obtain a device priority parameter; Sorting all the candidate computing devices according to the device priority parameter to obtain a device sequence; Screening out all the candidate computing devices of the first preset number of the device sequence and whose device priority parameters are greater than the parameter threshold, to obtain a plurality of conversion computing devices; The objective function is set to minimize the level difference between the data volume of the data portion allocated to each conversion computing device and the device priority parameter corresponding to the conversion computing device; the level difference is the difference between the first level of the data volume and the second level of the device priority parameter; the first level is the size order of the data volume in the data volume of all conversion computing devices; the second level is the size order of the device priority parameter in the device priority parameters of all conversion computing devices; The setting restriction condition includes that the data amount of the data part allocated to each conversion computing device is greater than a first data threshold and the data amount of the data part allocated to each conversion computing device is less than a performance restriction threshold; the performance restriction threshold is proportional to the corresponding performance prediction value; According to the objective function and the restriction condition, based on the particle swarm algorithm, the member equity data is iteratively allocated and calculated to obtain the data portion allocated to each conversion calculation device, and obtain a device data allocation strategy; the device data allocation strategy is used to limit the data portion of the member equity data that each conversion calculation device needs to predict and calculate; The calculation module is used to send the member benefit data to the conversion prediction neural network model in the multiple conversion calculation devices for conversion calculation to calculate the converted member data.

4. An equity data conversion system based on artificial intelligence, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based equity data conversion method as described in any one of claims 1-2.

Images