A SaaS-based enterprise rights and interests management method and system

Abstract

The present invention discloses a SaaS-based enterprise rights and interests management method and system, which relates to the field of data management and includes a data storage module, a vertical classification module, a rights and interests delivery module, and a data security module. The data storage module is used to store customer data, rights and interests configuration data, historical data, and system log data; the vertical classification module is used to extract the consumption habit data of customers from the data storage module, perform primary classification and secondary classification on the customer data to obtain the nearest customer link, and add the identity labels of the customers in the second customer group corresponding to the nearest customer link to each customer in the first customer group according to the identity labels of the generated second customer group; the rights and interests delivery module is used to obtain the optimal rights and interests configuration and perform rights and interests delivery. The input identity labels are classified through a pre-trained BP neural network model to obtain the optimal rights and interests configuration, and the rights and interests are delivered to customers according to the optimal rights and interests configuration by using the api platform interface, and the rights and interests feedback is recorded.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a SaaS-based enterprise rights management method and system. Background Art

[0002] In recent years, thanks to the development of cloud computing and big data technology, SaaS systems have continuously made breakthroughs and innovations in the ability of banks and enterprises to invest, issue and manage equity. They can build customer preferences based on consumption data from third-party platforms, and achieve accurate equity matching and personalized services. It is an emerging trend to classify customers based on artificial intelligence and machine learning algorithms, and cooperate with various consumer platforms and institutions to provide customers with a rich variety of equity types.

[0003] At present, the Chinese invention patent with application number CN202311269650.1 discloses a digital rights SAAS system that supports multi-merchant cooperative marketing. It has basic functions including digital rights issuance, operation management, and confirmation and cancellation, and can build a business scenario that integrates the needs of the virtual and real business ecosystem. The specific technical solution of the invention is: the invention uses SAAS technology to support brand companies to pay only a small access fee to launch their own digital rights functions in a short time, thereby quickly reaching users. Using the HRC721 protocol, the issuance, confirmation and cancellation of rights are executed through smart contracts, and the entire life cycle of rights is put on the chain. Based on the blockchain, the rights data can be trusted, the cancellation can be verified, and the synthesis mechanism can be executed, and the cooperative marketing function can be innovatively realized to promote the development of the entire business ecosystem. However, the invention only focuses on the security of corporate rights, and in the rights management, it neglects the classification of customers and the personalization of rights and interests, and relies on the customer consumption habit data obtained by the third-party platform. Summary of the invention

[0004] The technical problem solved by the present invention is that traditional SaaS platforms rely on customer consumption habit data obtained from third-party platforms when allocating benefits to banking enterprises. In the absence of customer consumption habit data, they only rely on account data to classify customers, resulting in insufficient accuracy and personalization when allocating benefits.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A SaaS-based enterprise equity management system, comprising: a data storage module, a vertical classification module, an equity delivery module and a data security module;

[0007] The data storage module is used to store customer data, equity configuration data, historical data and system log data;

[0008] The vertical classification module is used to extract the consumption habit data of customers from the data storage module, perform a first classification process on the customer data to obtain a first customer group and a second customer group, perform a second classification on the first customer group to obtain the nearest customer link to the second customer group, generate an identity label for the second customer group according to the third data set, and add the identity labels of the customers in the second customer group corresponding to their nearest customer links to each customer in the first customer group;

[0009] The rights and interests delivery module is used to obtain the optimal rights and interests configuration and conduct rights and interests delivery. It performs a classification task on the input identity label through a pre-trained BP neural network model to obtain the optimal rights and interests configuration, uses the api platform interface to deliver the rights and interests to customers according to the optimal rights and interests configuration, and records the rights and interests feedback;

[0010] The data security module is used to implement access control, transmission encryption, and audit the evaluation of rights and interests delivery. It performs hierarchical control on the system access rights according to the administrator rights, operator rights, and maintenance operator rights, and audits the changes in rights and interests configuration.

[0011] Preferably, the data storage module includes a customer data unit, a rights and interests configuration data unit, a historical data unit, and a system log unit;

[0012] The customer data unit is used to store customer basic information data, account data, and consumption habit data;

[0013] The rights and interests configuration data unit is used to store rights and interests type data, rights and interests delivery rule data, and rights and interests inventory data in the current marketing activity;

[0014] The historical data unit is used to store rights and interests delivery records, rights and interests usage records, and customer feedback records in past marketing activities;

[0015] The system log unit is used to store administrator operation logs, system operation logs, and backup logs.

[0016] Preferably, the customer basic information data includes the customer's name, gender, age, place of residence, family status, and contact information;

[0017] The account data includes the account number under the customer's name, card opening time, account type, deposit data, loan data, and income and expenditure data;

[0018] The consumption habit data includes the customer's consumption expenditure area data, consumption platform search data, commodity browsing data, consumption channel data, and financial management expenditure data;

[0019] The rights and interests type data includes discount coupons, bank points, discount packages, and financial management services;

[0020] The above-mentioned rights and interests delivery rule data includes the delivery object, delivery time, type of rights and interests to be delivered, field of rights and interests to be delivered, and quantity of rights and interests to be delivered;

[0021] The above-mentioned rights and interests inventory data includes undelivered rights and interests data, delivered but unused rights and interests data, and used rights and interests data;

[0022] The above-mentioned rights and interests delivery record includes the type of rights and interests delivered in historical marketing activities, rights and interests delivery rules, and rights and interests usage conditions;

[0023] The above-mentioned rights and interests usage record includes the rights and interests usage time, rights and interests usage occasion, and quantity of rights and interests used;

[0024] The above-mentioned administrator operation log includes the administrator's login data, rights and interests creation data, rights and interests delivery data, and rights and interests modification data;

[0025] The above-mentioned backup log includes full log backup and incremental data backup.

[0026] Preferably, the vertical classification module includes a customer grouping unit, a feature extraction unit, and an identity label unit;

[0027] The customer grouping unit is used to extract the consumption habit data of customers from the data storage module, and classify the customers once based on the consumption habit data to obtain a first customer group and a second customer group;

[0028] The logic for the customer grouping unit to classify customer data once is: obtain the consumption habit data of all customers. When the number of consumption times in the consumption expenditure field data of customers is less than the first threshold, the number of searches in the consumption platform search data is less than the second threshold, and the number of views in the commodity browsing data is less than the third threshold, the judgment result is that the consumption habit data is insufficient, otherwise the judgment result is that the consumption habit data is sufficient;

[0029] The customer grouping unit divides the customers with the judgment result of insufficient consumption habit data into the first customer group, and divides the customers with the judgment result of sufficient consumption habit data into the second customer group.

[0030] Preferably, the customer grouping unit extracts the customer basic information data and account data corresponding to the first customer group from the data storage module to obtain a first data set;

[0031] The customer grouping unit extracts the customer basic information data and account data corresponding to the second customer group from the data storage module to obtain a second data set;

[0032] The customer grouping unit extracts the customer basic information data, account data, and consumption habit data corresponding to the second customer group from the data storage module to obtain a third data set.

[0033] Preferably, the feature extraction unit is used to generate a first set of feature matrices and a second set of feature matrices, and perform secondary classification on the first customer group to obtain the nearest neighbor customer links between each customer in the first customer group and the customers in the second customer group;

[0034] The feature extraction unit performs interval partitioning and one-hot encoding on gender, age, place of residence, family status, account type, deposit data, loan data, and income and expenditure data in the first dataset to obtain a first set of feature vector groups, performs vector splicing on each vector group in the first set of feature vector groups respectively to obtain a first set of spliced vectors, and performs matrix processing on the first set of feature vector groups to obtain a first set of feature matrices;

[0035] The feature extraction unit performs interval partitioning and one-hot encoding on gender, age, place of residence, family status, account type, deposit data, loan data, and income and expenditure data in the second dataset to obtain a second set of feature vector groups, performs vector splicing on each vector group in the second set of feature vector groups respectively to obtain a second set of spliced vectors, and performs matrix processing on the second set of feature vector groups to obtain a second set of feature matrices;

[0036] The processing logic of the feature extraction unit for secondary classification includes: calculating the cosine similarity between all vectors in the first set of spliced vectors and each vector in the second set of spliced vector groups respectively, calculating the cross-correlation coefficient between all matrices in the first set of feature matrices and each matrix in the second set of feature matrices respectively, obtaining the feature proximity value through linear weighted calculation of the cosine similarity and the cross-correlation coefficient, sorting the feature proximity values from largest to smallest to obtain the maximum feature proximity value, and forming links between each customer in the first customer group and the corresponding nearest neighbor customers in the second customer group based on the maximum feature proximity value to complete the secondary classification and obtain the nearest neighbor customer links. The calculation expression is:

[0037]

[0038] where DIS represents the feature proximity value, represents the cosine similarity between the vector with index i in the first set of spliced vectors and the vector with index j in the second set of spliced vector groups, represents the cosine similarity weight, represents the cross-correlation coefficient between the matrix with index i in the first set of feature matrices and the matrix with index j in the second set of feature matrices, represents the cross-correlation coefficient weight.

[0039] Preferably, the identity tag unit is used to generate identity tags of customers, generate identity tags of the second customer group according to the gender, age, family status, account type, deposit data, loan data, consumption expenditure field data, consumption platform search data, commodity browsing data, consumption path data and wealth management expenditure data of customers in the third dataset, and add the identity tags of the customers in the second customer group corresponding to the nearest neighbor customer links to each customer in the first customer group.

[0040] Preferably, the rights and interests delivery module includes a personalized delivery unit and a delivery terminal unit. The personalized delivery unit is used to select a rights and interests allocation plan according to the customer identity tag, encode the identity tags of the customers in the second customer group to obtain an input identity tag vector, and perform a classification task on the input identity tag through a pre-trained BP neural network model to obtain the best rights and interests allocation. The best rights and interests allocation is a combination of the delivery object, delivery time, delivery rights and interests type, delivery rights and interests field and delivery rights and interests quantity output by the BP neural network model;

[0041] The delivery terminal unit is used to use the api platform interface to deliver the rights and interests to the customers according to the best rights and interests allocation and record the rights and interests feedback;

[0042] The api interface platform includes a bank app, a payment app, a short message, a public account and a small program;

[0043] The rights and interests feedback includes the customer participation rate, the rights and interests utilization rate and the customer complaint rate.

[0044] Preferably, the data security module includes a data security unit and an audit unit. The data security unit is used to implement access control and transmission encryption, encrypt the customer data and rights and interests data through the SSL algorithm and the TLS algorithm during transmission, manage the user access in a hierarchical manner, and hierarchically control the system access rights according to the administrator rights, operator rights and operation and maintenance operator rights;

[0045] The audit unit is used to audit the evaluation of rights and interests delivery. The setting and adjustment operations of the rights and interests delivery parameters by the operator rights account and the operation and maintenance operator rights account need to be audited and confirmed by the administrator rights account through the audit unit before they can be executed.

[0046] A SaaS-based enterprise rights and interests management method includes:

[0047] Step S1, extract the consumption habit data of customers from the data storage module, including the consumption expenditure field data, consumption platform search data, commodity browsing data, consumption path data and wealth management expenditure data of customers;

[0048] Perform a classification process on customer data, perform threshold judgment on the number of consumption times in the customer consumption expenditure field data, the number of searches in the consumption platform search data, and the number of views in the product browsing data to obtain the judgment result of consumption habit data, and divide customers into the first customer group and the second customer group based on the judgment result of consumption habit data;

[0049] Step S2, perform a secondary classification process on the first customer group, extract the customer data corresponding to the first customer group to obtain the first data set, extract the customer data corresponding to the second customer group to obtain the second data set and the third data set, perform interval division and one-hot encoding on the first data set to obtain the first set of feature vector groups, obtain the first set of feature matrices through matrix processing, obtain the first set of concatenated vectors through vector concatenation, perform interval division and one-hot encoding on the second data set to obtain the second set of feature vector groups, obtain the second set of feature matrices through matrix processing, and obtain the second set of concatenated vectors through vector concatenation;

[0050] Calculate the cosine similarity based on the first set of concatenated vectors and the second set of concatenated vector groups, calculate the cross-correlation coefficient based on all matrices in the first set of feature matrices and the second set of feature matrices, perform linear weighted calculation on the cosine similarity and the cross-correlation coefficient to obtain the feature proximity value, sort based on the feature proximity value to obtain the maximum feature proximity value, classify the first customer group based on the maximum feature proximity value, and make the first customer group form the nearest customer link with the nearest customer in the corresponding second customer group;

[0051] Step S3, based on the identity labels of the customers in the second customer group, encode the identity labels to obtain the input identity label vector, perform a classification task on the input identity label vector through the BP neural network model to obtain the optimal rights and interests configuration, complete the delivery of rights and interests to the customers through the api platform interface based on the optimal rights and interests configuration, and record the rights and interests feedback.

[0052] The beneficial effects of the present invention: Obtaining the nearest neighbor link through the primary classification and secondary classification of customer data is beneficial to accurate classification and reduction of subsequent calculation complexity. Making full use of the customer data with sufficient consumption habit data through the machine learning model to calculate the optimal rights and interests configuration. It is beneficial to accurately provide personalized rights and interests delivery plans for different types of customers and customers with insufficient consumption habit data, effectively controlling costs while improving the marketing effect. Description of the Drawings

[0053] Figure 1 It is a framework schematic diagram of an enterprise rights and interests management system based on SaaS provided by an embodiment of the present invention;

[0054] Figure 2 It is a basic process schematic diagram of an enterprise rights and interests management method based on SaaS provided by an embodiment of the present invention. Detailed implementation manners

[0055] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe in detail the specific implementation manners of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments.

[0056] Example 1, referring to Figure 1 , which is an embodiment of the present invention, provides an enterprise rights and interests management method based on SaaS, including: An enterprise rights and interests management system based on SaaS, including: a data storage module, a vertical classification module, a rights and interests delivery module, and a data security module;

[0057] The data storage module is used to store customer data, rights and interests configuration data, historical data, and system log data;

[0058] The vertical classification module is used to extract the consumption habit data of customers from the data storage module, perform a first classification process on the customer data to obtain a first customer group and a second customer group, perform a second classification on the first customer group to obtain the nearest customer link to the second customer group, generate an identity label for the second customer group according to the third data set, and add the identity labels of the customers in the second customer group corresponding to the nearest customer link to each customer in the first customer group;

[0059] The rights and interests delivery module is used to obtain the best rights and interests configuration and perform rights and interests delivery. It performs a classification task on the input identity label through a pre-trained BP neural network model to obtain the best rights and interests configuration, uses the api platform interface to deliver the rights and interests to the customers according to the best rights and interests configuration, and records the rights and interests feedback;

[0060] The data security module is used to implement access control, transmission encryption, and audit the evaluated rights and interests delivery. It performs hierarchical control on the system access rights according to the administrator rights, operator rights, and operator and maintenance rights, and audits the changes in the rights and interests configuration.

[0061] In this embodiment, the data storage module includes a customer data unit, a rights and interests configuration data unit, a historical data unit, and a system log unit;

[0062] The customer data unit is used to store customer basic information data, account data, and consumption habit data;

[0063] The rights and interests configuration data unit is used to store rights and interests type data, rights and interests delivery rule data, and rights and interests inventory data in the current marketing activity;

[0064] The historical data unit is used to store rights and interests delivery records, rights and interests usage records, and customer feedback records in past marketing activities;

[0065] The system log unit is used to store administrator operation logs, system running logs, and backup logs.

[0066] In this embodiment, the basic customer information data includes the customer's name, gender, age, place of residence, family status, and contact information;

[0067] The account data includes the accounts under the customer's name, account opening time, account type, deposit data, loan data, and income and expenditure data;

[0068] The consumption habit data includes the customer's consumption expenditure area data, consumption platform search data, commodity browsing data, consumption channel data, and financial management expenditure data;

[0069] The rights and interests type data includes discount coupons, bank points, discount packages, and financial management services;

[0070] The rights and interests delivery rule data includes the delivery target, delivery time, type of rights and interests to be delivered, field of rights and interests to be delivered, and quantity of rights and interests to be delivered;

[0071] The rights and interests inventory data includes undelivered rights and interests data, delivered but unused rights and interests data, and used rights and interests data;

[0072] The rights and interests delivery record includes the type of rights and interests delivered in historical marketing activities, rights and interests delivery rules, and rights and interests usage conditions;

[0073] The rights and interests usage record includes the rights and interests usage time, rights and interests usage occasion, and quantity of rights and interests used;

[0074] The administrator operation logs include the administrator's login data, rights and interests creation data, rights and interests delivery data, and rights and interests modification data;

[0075] The backup logs include full - volume log backups and incremental data backups.

[0076] In this embodiment, the vertical classification module includes a customer grouping unit, a feature extraction unit, and an identity tagging unit;

[0077] The customer grouping unit is used to extract the customer's consumption habit data from the data storage module, and classify the customers once based on the consumption habit data to obtain a first customer group and a second customer group;

[0078] The logic for the customer grouping unit to classify customer data once is as follows: Obtain the consumption habit data of all customers. When the number of consumption times in the customer's consumption expenditure area data is less than the first threshold, the number of searches in the consumption platform search data is less than the second threshold, and the number of browsing in the commodity browsing data is less than the third threshold, the judgment result is that the consumption habit data is insufficient; otherwise, the judgment result is that the consumption habit data is sufficient;

[0079] The customer grouping unit divides the customers with insufficient consumption habit data in the judgment result into the first customer group, and divides the customers with sufficient consumption habit data in the judgment result into the second customer group.

[0080] In this embodiment, the customer grouping unit extracts the customer basic information data and account data corresponding to the first customer group from the data storage module to obtain a first data set;

[0081] The customer grouping unit extracts the customer basic information data and account data corresponding to the second customer group from the data storage module to obtain a second data set;

[0082] The customer grouping unit extracts the customer basic information data, account data and consumption habit data corresponding to the second customer group from the data storage module to obtain a third data set.

[0083] In this embodiment, the feature extraction unit is used to generate a first feature matrix set and a second feature matrix set, and perform secondary classification on the first customer group to obtain the nearest neighbor customer links between the customers in the first customer group and the customers in the second customer group;

[0084] The feature extraction unit performs interval division and one-hot encoding on the gender, age, place of residence, family status, account type, deposit data, loan data and income and expenditure data in the first data set to obtain a first set of feature vector groups, performs vector splicing on each vector group in the first set of feature vector groups respectively to obtain a first set of spliced vectors, and performs matrix processing on the first set of feature vector groups to obtain a first feature matrix set;

[0085] The feature extraction unit performs interval division and one-hot encoding on the gender, age, place of residence, family status, account type, deposit data, loan data and income and expenditure data in the second data set to obtain a second set of feature vector groups, performs vector splicing on each vector group in the second set of feature vector groups respectively to obtain a second set of spliced vectors, and performs matrix processing on the second set of feature vector groups to obtain a second feature matrix set;

[0086] The processing logic of the feature extraction unit for secondary classification includes: calculating the cosine similarity between all vectors in the first set of spliced vectors and each vector in the second set of spliced vector groups respectively, calculating the cross-correlation coefficient between all matrices in the first feature matrix set and each matrix in the second feature matrix set respectively, obtaining the feature proximity value through the linear weighted calculation of the cosine similarity and the cross-correlation coefficient, sorting the feature proximity values from largest to smallest to obtain the maximum feature proximity value, and forming links between each customer in the first customer group and the corresponding nearest neighbor customer in the second customer group based on the maximum feature proximity value to complete the secondary classification and obtain the nearest neighbor customer links. Its calculation expression is:

[0087]

[0088] Among them, DIS represents the feature proximity value, represents the cosine similarity between the vector with index i in the first splicing vector set and the vector with index j in the second splicing vector group set, represents the cosine similarity weight, represents the cross-correlation coefficient between the matrix with index i in the first feature matrix set and the matrix with index j in the second feature matrix set, represents the cross-correlation coefficient weight.

[0089] Among them, based on insufficient and sufficient consumption habit data, customers are classified once to obtain the first customer group and the second customer group. The feature proximity value is calculated through basic information data and account data. The customers closest to each customer in the first customer group are identified in the second customer group to obtain the nearest neighbor customer link. After generating the identity label from the data of the second customer group with sufficient consumption habit data, the same identity label is assigned to the first customer group with insufficient consumption habit data through the nearest neighbor customer link. This is beneficial to improving the accuracy of customer classification and completing the subsequent personalized configuration of rights and interests, and reducing the computational complexity of calculating the optimal rights and interests configuration.

[0090] In this embodiment, the identity label unit is used to generate the identity label of the customer, generate the identity label of the second customer group according to the gender, age, family status, account type, deposit data, loan data, consumption expenditure field data, consumption platform search data, commodity browsing data, consumption path data and financial management expenditure data of the customers in the third data set, and add the identity label of the customers in the second customer group corresponding to their nearest neighbor customer link to each customer in the first customer group.

[0091] Among them, the customer identity label includes:

[0092] Gender label: including male and female;

[0093] Age label: teenager, middle-aged, elderly;

[0094] Family status label: unmarried and childless, unmarried and with children, married and with children, married and childless;

[0095] Account type label: savings account, credit card account;

[0096] Deposit data label and loan data label: below 10,000, 10,000 to 50,000, 50,000 to 200,000, 200,000 to 1,000,000, above 1,000,000;

[0097] Consumption field data label: dining, shopping, education, medical care, tourism;

[0098] Consumer platform search data tags and browsing data tags: electronic products, household goods, clothing and beauty products, sports and fitness, mid - to - low - end brands, and high - end brands;

[0099] Consumer channel data tags: online channels and offline channels;

[0100] Financial expenditure data tags: conservative and aggressive;

[0101] In this embodiment, the rights and interests delivery module includes a personalized delivery unit and a delivery terminal unit. The personalized delivery unit is used to select a rights and interests configuration plan according to the customer identity tag, encode the identity tags of the customers in the second customer group to obtain an input identity tag vector, perform a classification task on the input identity tag through a pre - trained BP neural network model to obtain the best rights and interests configuration. The best rights and interests configuration is a combination of the delivery object, delivery time, delivery rights and interests type, delivery rights and interests field, and delivery rights and interests quantity output by the BP neural network model;

[0102] The delivery terminal unit is used to deliver the rights and interests to the customer according to the best rights and interests configuration by using the api platform interface and record the rights and interests feedback;

[0103] The api interface platform includes bank apps, payment apps, text messages, official accounts, and mini - programs;

[0104] The rights and interests feedback includes customer participation rate, rights and interests utilization rate, and customer complaint rate.

[0105] Among them, when performing a classification task on the input identity tag through a pre - trained BP neural network model, its processing logic includes: encoding the identity tag to obtain an identity tag vector through interval division and one - hot encoding in the network input layer, inputting the identity tag vector into the network hidden layer, performing a weighted operation through the network node connection weights and then adding the bias term, increasing the non - linear expression through the ReLU activation function and passing the result to the network output layer, obtaining the probability distribution of the output category through node weighted calculation and the Softmax activation function. The output category corresponds to the best delivery object, best delivery time, best delivery rights and interests type, best delivery rights and interests field, and best delivery rights and interests quantity. Combining the output results to obtain the best rights and interests configuration.

[0106] Among them, the training logic of the BP neural network model includes: The customer identity tags include gender tag, age tag, family status tag, account type tag, deposit data tag, loan data tag, consumption field data tag, platform search data tag, browsing data tag, consumption channel data tag, and financial management expenditure data tag. The number of input layer nodes is determined to be 11 according to the types of the above customer identity tags. Based on prior experience, the number of initial hidden layers and the number of nodes in each hidden layer are set, and the number of output layer nodes is determined to be 5, corresponding to the placement object, placement time, placement right type, placement right field, and placement right quantity respectively. The pre-prepared data set is divided into a training set, a validation set, and a test set according to 7:2:1. This data set contains customer identity tags and corresponding optimal right configurations. Training parameters are set, including the learning rate, the number of iterations, and the batch size. Usually, the connection weights and bias terms are initialized by the random initialization method. The customer identity tags in the training set are encoded, and the output right configuration is calculated through forward propagation. Then, the difference between the output right configuration and the actual optimal right configuration is calculated through the cross-entropy loss function. The number of hidden layers, the number of nodes in each hidden layer, and the corresponding network connection weights are updated through backpropagation. The accuracy, precision, and recall rate of the BP neural network model are calculated through the test set and the validation set to complete the training.

[0107] Among them, comprehensively considering the customer's gender, age, family status, account type, deposit and loan situation, consumption field preference, consumption platform search and browsing preference, consumption channel preference, and financial management expenditure preference is conducive to accurately analyzing the personalized needs of customers from a multi-dimensional perspective. In view of the characteristics of high dimensionality, complexity, and diversity of the current customer data, the advantages of strong feature extraction ability and non-linear processing ability of the BP neural network model are fully utilized for accurate classification and prediction. For example, for young customers who like traveling, rights such as travel-related coupons and doubled points can be provided. For middle-aged customers who are married and have children and have high consumption in the education field, discount information of educational training institutions can be pushed. This is conducive to providing personalized right placement plans for different types of customers, effectively controlling costs while improving the marketing effect.

[0108] In this embodiment, the data security module includes a data security unit and an audit unit. The data security unit is used to implement access control and transmission encryption. When transmitting customer data and right data, encryption is performed through the SSL algorithm and the TLS algorithm, and hierarchical management of user access is carried out. The system access rights are hierarchically controlled according to the administrator rights, operator rights, and operation and maintenance operator rights.

[0109] The audit unit is used to audit the evaluated right placement. The setting and adjustment operations of the right placement parameters by the operator rights account and the operation and maintenance operator rights account need to be audited and confirmed by the administrator rights account through the audit unit before they can be executed.

[0110] Example 2. Refer to Figure 2 , which is an embodiment of the present invention, provides a SaaS-based enterprise rights and interests management method, including: A SaaS-based enterprise rights and interests management method, including:

[0111] Step S1: Extract the consumption habit data of customers from the data storage module, including the consumption expenditure field data, consumption platform search data, commodity browsing data, consumption path data, and financial management expenditure data of customers;

[0112] Perform a classification process on the customer data once. Perform a threshold judgment on the consumption times in the customer consumption expenditure field data, the search times in the consumption platform search data, and the browsing quantity in the commodity browsing data to obtain the consumption habit data judgment result. Based on the consumption habit data judgment result, divide the customers into a first customer group and a second customer group;

[0113] Step S2: Perform a secondary classification process on the first customer group. Extract the customer data corresponding to the first customer group to obtain a first data set, extract the customer data corresponding to the second customer group to obtain a second data set and a third data set. Perform interval division and one-hot encoding on the first data set to obtain a first set of feature vector groups, obtain a first set of feature matrices through matrix processing, obtain a first set of concatenated vectors through vector concatenation. Perform interval division and one-hot encoding on the second data set to obtain a second set of feature vector groups, obtain a second set of feature matrices through matrix processing, and obtain a second set of concatenated vectors through vector concatenation;

[0114] Calculate the cosine similarity based on the first set of concatenated vectors and the second set of concatenated vector groups. Calculate the cross-correlation coefficient based on all matrices in the first set of feature matrices and the second set of feature matrices. Perform a linear weighted calculation on the cosine similarity and the cross-correlation coefficient to obtain the feature proximity value. Sort based on the feature proximity value to obtain the maximum feature proximity value. Classify the first customer group based on the maximum feature proximity value, and make the closest customers in the first customer group and the corresponding second customer group form the closest customer link;

[0115] Step S3: Based on the identity tags of the customers in the second customer group, encode the identity tags to obtain the input identity tag vector. Perform a classification task on the input identity tag vector through the BP neural network model to obtain the optimal rights and interests configuration. Complete the rights and interests delivery to the customers through the api platform interface based on the optimal rights and interests configuration, and record the rights and interests feedback.

[0116] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device, and the instruction device implements the process Figure 1 in one process or multiple processes and / or Figure 1 the functions specified in one block or multiple blocks.

[0117] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A SaaS-based enterprise equity management system, characterized in that: include: Data storage module, vertical classification module, equity delivery module and data security module; The data storage module is used to store customer data, equity configuration data, historical data and system log data; The vertical classification module is used to extract the consumption habit data of customers from the data storage module, perform a primary classification process on the customer data to obtain a first customer group and a second customer group, perform a secondary classification on the first customer group to obtain the nearest customer link with the second customer group, generate the identity tag of the second customer group according to the third data set, and add the identity tag of the second customer group customer corresponding to the nearest customer link to each customer in the first customer group; The equity delivery module is used to obtain the best equity configuration and carry out equity delivery. The pre-trained BP neural network model is used to perform classification tasks on the input identity tags to obtain the best equity configuration, and the API platform interface is used to deliver the equity to the customer according to the best equity configuration, and record the equity feedback; The data security module is used to implement access control, transmission encryption and audit the evaluation of equity placement, hierarchical control of system access rights according to administrator rights, operator rights and operator rights, and audit equity configuration changes; Among them, the vertical classification module includes a customer grouping unit, a feature extraction unit, and an identity labeling unit; The customer grouping unit is used to extract the consumption habit data of customers from the data storage module, and classify the customers based on the consumption habit data to obtain a first customer group and a second customer group; The logic of the customer grouping unit for classifying customer data is as follows: obtaining the consumption habit data of all customers, when the number of consumptions in the customer consumption expenditure field data is less than the first threshold, the number of searches in the consumption platform search data is less than the second threshold, and the number of visits in the product visit data is less than the third threshold, the judgment result is that the consumption habit data is insufficient, otherwise the judgment result is that the consumption habit data is sufficient; The customer grouping unit divides customers whose consumption habit data are insufficient into a first customer group, and divides customers whose consumption habit data are sufficient into a second customer group; The customer grouping unit extracts the customer basic information data and account data corresponding to the first customer group from the data storage module to obtain a first data set; The customer grouping unit extracts the customer basic information data and account data corresponding to the second customer group from the data storage module to obtain a second data set; The customer grouping unit extracts the customer basic information data, account data and consumption habit data corresponding to the second customer group from the data storage module to obtain a third data set; The feature extraction unit is used to generate a first feature matrix set and a second feature matrix set, and perform secondary classification on the first customer group to obtain the nearest customer links between each customer in the first customer group and the customers in the second customer group; The feature extraction unit performs interval division and one-hot encoding on the gender, age, place of residence, family status, account type, deposit data, loan data, and income and expenditure data in the first data set to obtain a first feature vector set, performs vector concatenation on each vector set in the first feature vector set to obtain a first concatenated vector set, and performs matrix processing on the first feature vector set to obtain a first feature matrix set; The feature extraction unit performs interval division and one-hot encoding on the gender, age, place of residence, family status, account type, deposit data, loan data, and income and expenditure data in the second data set to obtain a second feature vector set, performs vector concatenation on each vector set in the second feature vector set to obtain a second concatenated vector set, and performs matrix processing on the second feature vector set to obtain a second feature matrix set; The processing logic of the feature extraction unit for secondary classification includes: respectively calculating the cosine similarity of all vectors in the first splicing vector set and each vector in the second splicing vector set, respectively calculating the mutual correlation coefficient of all matrices in the first feature matrix set and each matrix in the second feature matrix set, obtaining the feature proximity value by linear weighted calculation of the cosine similarity and the mutual correlation coefficient, sorting the feature proximity values ​​from large to small to obtain the maximum feature proximity value, and linking each customer in the first customer group with the corresponding nearest customer in the second customer group based on the maximum feature proximity value, completing the secondary classification, and obtaining the nearest customer link, and its calculation expression is: Among them, DIS represents the feature proximity value, represents the cosine similarity between the vector with index i in the first concatenated vector set and the vector with index j in the second concatenated vector set, represents the cosine similarity weight, represents the mutual correlation coefficient between the matrix with index i in the first characteristic matrix set and the matrix with index j in the second characteristic matrix set, represents the weight of the mutual correlation coefficient; The identity tag unit is used to generate identity tags for customers, generate identity tags for the second customer group according to the gender, age, family status, account type, deposit data, loan data, consumer expenditure field data, consumer platform search data, product browsing data, consumer channel data and financial expenditure data of the customers in the third data set, and add the identity tags of the second customer group customers corresponding to their closest customer links to each customer in the first customer group; The equity delivery module includes a personalized delivery unit and a delivery terminal unit. The personalized delivery unit is used to select an equity configuration scheme according to a customer identity tag, encode the identity tags of customers in the second customer group to obtain an input identity tag vector, and perform a classification task on the input identity tag through a pre-trained BP neural network model to obtain an optimal equity configuration. The optimal equity configuration is a combination of the delivery object, delivery time, delivery equity type, delivery equity field, and delivery equity quantity output by the BP neural network model; The delivery terminal unit is used to use the API platform interface to deliver equity to customers according to the best equity configuration and record equity feedback; API interface platforms include banking apps, payment apps, SMS, official accounts and mini-programs; Equity feedback includes customer participation rate, equity utilization rate and customer complaint rate.

2. The SaaS-based enterprise equity management system according to claim 1, characterized in that: The data storage module includes a customer data unit, an equity configuration data unit, a historical data unit and a system log unit; The customer data unit is used to store basic customer information data, account data and consumption habit data; The equity configuration data unit is used to store the equity type data, equity placement rule data and equity inventory data in the current marketing activity; The historical data unit is used to store equity distribution records, equity usage records and customer feedback records in past marketing activities; The system log unit is used to store administrator operation logs, system operation logs, and backup logs.

3. The SaaS-based enterprise equity management system according to claim 2, characterized in that: The basic customer information data includes the customer's name, gender, age, place of residence, family status and contact information; The account data includes the customer's account number, card opening time, account type, deposit data, loan data, and income and expenditure data; The consumption habit data includes the customer's consumption expenditure area data, consumption platform search data, product browsing data, consumption channel data and financial expenditure data; The equity type data includes discount coupons, bank points, discount packages and financial services; The equity placement rule data includes placement objects, placement time, types of placement equity, fields of placement equity, and the number of placement equity; The equity inventory data includes uninvested equity data, invested but unused equity data and used equity data; The equity placement record includes the type of equity placed in historical marketing activities, equity placement rules and equity usage; The equity use record includes the time of equity use, the occasion of equity use and the amount of equity use; The administrator operation log includes the administrator's login data, equity creation data, equity placement data, and equity change data; The backup log includes full log backup and incremental data backup.

4. The SaaS-based enterprise equity management system according to claim 1, characterized in that: The data security module includes a data security unit and an audit unit. The data security unit is used to implement access control and transmission encryption. When transmitting customer data and equity data, the data is encrypted using the SSL algorithm and the TLS algorithm. User access is managed in a hierarchical manner, and system access rights are controlled in a hierarchical manner according to administrator rights, operator rights, and operator rights. The audit unit is used to audit the evaluation equity investment. The setting and adjustment of equity investment parameters by operator authority accounts and operator authority accounts require the audit confirmation of the administrator authority account through the audit unit before they can be executed.

5. A SaaS-based enterprise rights management method, used to implement a SaaS-based enterprise rights management system as described in any one of claims 1 to 4, characterized in that: include: Step S1, extracting the customer's consumption habit data from the data storage module, including the customer's consumption expenditure field data, consumption platform search data, product browsing data, consumption channel data and financial expenditure data; Perform a classification process on the customer data, perform threshold judgment on the number of consumptions in the customer's consumption expenditure field data, the number of searches in the consumption platform search data, and the number of visits in the product visit data to obtain a consumption habit data judgment result, and divide the customer into a first customer group and a second customer group based on the consumption habit data judgment result; Step S2, performing secondary classification processing on the first customer group, extracting customer data corresponding to the first customer group to obtain a first data set, extracting customer data corresponding to the second customer group to obtain a second data set and a third data set, performing interval partitioning and one-hot encoding based on the first data set to obtain a first feature vector set, performing matrix processing to obtain a first feature matrix set, performing vector concatenation to obtain a first concatenated vector set, performing interval partitioning and one-hot encoding based on the second data set to obtain a second feature vector set, performing matrix processing to obtain a second feature matrix set, and performing vector concatenation to obtain a second concatenated vector set; Calculate the cosine similarity based on the first concatenated vector set and the second concatenated vector set, calculate the mutual correlation coefficient based on all matrices in the first feature matrix set and the second feature matrix set, perform linear weighted calculation on the cosine similarity and the mutual correlation coefficient to obtain a feature proximity value, sort based on the feature proximity value to obtain a maximum feature proximity value, classify the first customer group based on the maximum feature proximity value, and form a nearest customer link between the first customer group and the nearest customer in the corresponding second customer group; Step S3, based on the identity tags of the customers in the second customer group, encode the identity tags to obtain the input identity tag vector, perform the classification task on the input identity tag vector through the BP neural network model to obtain the optimal equity configuration, complete the equity delivery to the customer through the API platform interface based on the optimal equity configuration, and record the equity feedback.

Images