Financial product scheme analysis method and device, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a financial product scheme analysis method, device and equipment and a storage medium. Matching a preset target financial product scheme by using the regional features and the historical transaction data to obtain an initial target financial product scheme, sending the initial target financial product scheme to a preset target customer, and monitoring the sent initial target financial product scheme in real time to obtain a target financial product scheme. And adjusting a preset initial pushing strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated pushing strategy, and adjusting the initial target financial product scheme by using the updated pushing strategy to obtain a final target financial product scheme. According to the invention, the efficiency of generating personalized financial products and the efficiency of adjusting financial product schemes according to customer demands can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the fields of artificial intelligence technology and financial technology, and in particular to financial product solution analysis methods, devices, electronic devices and computer-readable storage media. Background Art

[0002] The current unified solution strategy of financial products such as insurance products and wealth management products has limitations and lacks data support and personalized design, which makes it difficult to meet the diverse market needs. They can only rely on experience and conjecture to make fine adjustments based on the original products. Due to the lack of data support, the final result cannot be predicted, differentiation is not fully utilized to create value, and it is difficult to determine the factors that are truly effective or the reasons why they are not effective. Therefore, this method is labor-intensive, cannot obtain value, and may even affect the original premiums.

[0003] The existing technologies currently have the problem of low efficiency in generating personalized financial products and low efficiency in adjusting financial product solutions according to customer needs. Summary of the invention

[0004] The present invention provides a financial product solution analysis method, device, electronic device and computer-readable storage medium, the main purpose of which is to solve the problem of low efficiency in generating personalized financial products and low efficiency in adjusting financial product solutions according to customer needs.

[0005] In a first aspect, to achieve the above-mentioned purpose, the present invention provides a financial product solution analysis method, comprising:

[0006] Obtain regional characteristics and historical transaction data of historical financial products;

[0007] Matching a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution;

[0008] Sending the initial target financial product solution to a preset target customer, monitoring the sent initial target financial product solution in real time, and adjusting the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy;

[0009] The initial target financial product solution is adjusted using the update push strategy to obtain a final target financial product solution.

[0010] In a second aspect, the present invention also provides a financial product solution analysis device, the device comprising:

[0011] Data acquisition module, used to obtain regional characteristics and historical transaction data of historical financial products;

[0012] A solution matching module, used to match a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution;

[0013] A strategy update module, used to send the initial target financial product solution to a preset target customer, monitor the initial target financial product solution in real time after sending, and adjust the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy;

[0014] A solution adjustment module is used to adjust the initial target financial product solution using the update push strategy to obtain a final target financial product solution.

[0015] In a third aspect, the present invention further provides an electronic device, the electronic device comprising:

[0016] at least one processor; and,

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial product solution analysis method described above.

[0019] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the above-mentioned financial product solution analysis method.

[0020] The present invention obtains regional characteristics and historical transaction data of historical financial products, uses the regional characteristics and the historical transaction data to match preset target financial product solutions, obtains an initial target financial product solution, sends the initial target financial product solution to a preset target customer, monitors the initial target financial product solution after sending in real time, adjusts the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring, calculates the covariance, standard deviation and Pearson correlation coefficient in combination with the historical customer behavior data, thereby deeply understanding the driving factors behind customer behavior, facilitating accurate decision-making based on data, screening out behaviors closely related to customer satisfaction, and then formulating targeted adjustment strategies, thereby improving the efficiency of adjusting financial product solutions according to customer needs, and using the update push strategy to adjust the initial target financial product solution to obtain a final target financial product solution, thereby improving the efficiency of generating personalized financial products. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0022] Figure 1 is a schematic diagram of an application environment of a financial product solution analysis method in one embodiment of the present invention;

[0023] Figure 2 A schematic diagram of a flow chart of a financial product solution analysis method provided by an embodiment of the present invention;

[0024] Figure 3 A schematic diagram of modules of a financial product solution analysis device provided by an embodiment of the present invention;

[0025] Figure 4 A schematic diagram of the structure of an electronic device of a financial product solution analysis device provided by an embodiment of the present invention;

[0026] Figure 5 It is another structural schematic diagram of an electronic device of a financial product solution analysis device provided by an embodiment of the present invention.

[0027] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. 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 necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0030] The embodiment of the present application provides a financial product solution analysis method, and the execution subject of the financial product solution analysis method includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the device provided by the embodiment of the present application. In other words, the financial product solution analysis method can be executed by software or hardware installed in a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0031] The financial product solution analysis method according to the embodiment of the present invention can be applied in the following aspects: Figure 1In the application environment of . Among them, the client communicates with the server through the network. The server can obtain the regional characteristics and historical transaction data of historical financial products through the client, use the regional characteristics and the historical transaction data to match the preset target financial product plan, obtain the initial target financial product plan, send the initial target financial product plan to the preset target customer, monitor the initial target financial product plan after sending in real time, adjust the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring, and calculate the covariance, standard deviation and Pearson correlation coefficient in combination with the historical customer behavior data, so as to deeply understand the driving factors behind the customer behavior, which is conducive to making accurate decisions based on data, screening out behaviors closely related to customer satisfaction, and then formulating targeted adjustment strategies, improving the efficiency of adjusting the financial product plan according to customer needs, using the update push strategy to adjust the initial target financial product plan, obtain the final target financial product plan, and feed the final target financial product plan back to the client. Among them, the client can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0032] Reference Figure 2 FIG. 1 is a flow chart of a method for analyzing a financial product solution according to an embodiment of the present invention. In this embodiment, the method for analyzing a financial product solution includes:

[0033] S1. Obtain regional characteristics and historical transaction data of historical financial products.

[0034] In an embodiment of the present invention, the region where the historical financial product is located is divided, and the regional characteristics of the divided region are collected, including: geographical attributes and cultural attributes, and the transaction data of the historical financial products are collected, including: historical financial product sales records, customer purchase behavior, claims data, customer feedback, etc., to provide data support for the subsequent use of the regional characteristics and the historical transaction data to match the preset target financial products, thereby improving the matching efficiency and accuracy.

[0035] S2. Matching a preset target financial product solution with the regional features and the historical transaction data to obtain an initial target financial product solution.

[0036] In an embodiment of the present invention, the content of the target financial product is analyzed, the time dependency is captured through a long short-term memory network, and an initial target financial product solution is generated by matching.

[0037] In the embodiment of the present invention, the method of matching a preset target financial product with a solution by using the regional features and the historical transaction data to obtain an initial target financial product solution includes:

[0038] Removing outliers from the regional features to obtain target features;

[0039] Arrange the historical transaction data in chronological order from the beginning to the end to obtain standard transaction data;

[0040] Using a generative adversarial network to synthesize the target features and the standard transaction data to obtain standard solution data;

[0041] Converting the standard scheme data into a three-dimensional vector using a preset embedding layer;

[0042] Performing time series analysis on the three-dimensional vector using a preset stacked LSTM layer to obtain a time series vector;

[0043] Performing full connection on the time series vector to obtain a fully connected vector;

[0044] Converting the data of the target financial product solution into a target financial product solution vector;

[0045] Calculating the cosine similarity between the target financial product solution vector and the fully connected vector one by one;

[0046] Filter out the fully connected vectors whose cosine similarity is greater than a preset cosine similarity threshold;

[0047] The screened fully connected vector is used as the initial target financial product solution.

[0048] In detail, the target feature and the standard transaction data are synthesized by using a generative adversarial network to obtain standard solution data, including:

[0049] Extracting a random noise vector from the standard transaction data using normal distribution;

[0050] Using a preset generator to convolve the target feature and the random noise vector to obtain initial solution data;

[0051] Convolving the initial scheme data using a preset discriminator to obtain the probability that the initial scheme data is true data;

[0052] If the probability that the initial scheme data is true data is less than or equal to a preset probability threshold, returning to convolve the target feature and the random noise vector using a preset generator;

[0053] If the probability that the initial solution data is true data is greater than the probability threshold, the standard solution data is obtained.

[0054] By extracting random noise vectors from normal distribution, we can more accurately simulate the uncertainty and randomness in the real world, thereby improving the diversity and authenticity of the generated data. By using the generator to convolve the target features and random noise vectors, we can create a variety of initial solution data. The authenticity of the initial solution data is evaluated by the discriminator to ensure that the generated data meets the characteristics of real data, thereby improving the quality and reliability of the generated solution. If the generated data does not reach the preset probability threshold, the system can automatically return and regenerate the data. This cyclic optimization mechanism can continuously improve the quality of the solution, ensure that the final output standard solution data meets the expected requirements, and improve the quality and applicability of the generated data.

[0055] In detail, the step of calculating the cosine similarity between the target financial product solution vector and the fully connected vector one by one includes:

[0056] Calculating the dot product of the target financial product solution vector and the fully connected vector;

[0057] Calculating the modulus of the target financial product solution vector and the modulus of the fully connected vector;

[0058] Calculating the module product of the target financial product solution vector and the fully connected vector using the module of the target financial product solution vector and the module of the fully connected vector;

[0059] The dot product is divided by the modular product to obtain the cosine similarity between the target financial product solution vector and the fully connected vector.

[0060] Specifically, the target financial product solution vector A is defined as [a1, a2, ..., a n ], the fully connected vector B = [b1, b2, ..., b n ].

[0061] Calculate the dot product of the target financial product solution vector and the fully connected vector:

[0062] dot(A,B)=a1×b1+a2×b2+…+a n ×b n

[0063] Among them, dot(A,B) is the dot product of the target financial product solution vector and the fully connected vector, a1, a2, …, a n is the target financial product solution vector, b1, b2, …, b n is a fully connected vector.

[0064] Calculate the modulus of the target financial product solution vector and the modulus of the fully connected vector:

[0065] ||A||=a 12 +a 22 +…+a n2

[0066] ||B||=b 12 +b 22 +…+b n2 Among them, ||A|| is the modulus of the target financial product solution vector, and ||B|| is the modulus of the fully connected vector.

[0067] The cosine similarity is calculated using the following formula:

[0068]

[0069] Among them, dot(A,B) is the dot product of the target financial product solution vector and the fully connected vector, ||A|| is the modulus of the target financial product solution vector, and ||B|| is the modulus of the fully connected vector.

[0070] In the insurance industry, cosine similarity can be used to recommend similar financial products to customers based on their historical choices or preferences. It is beneficial to evaluate the similarity between different documents, help extract relevant information and optimize document content, and help improve customer satisfaction and conversion rates.

[0071] By using the generative adversarial network to synthesize target features and standard transaction data, we can generate richer and more diverse samples, improve the training effect and accuracy of the model; by embedding layers and stacking LSTM layers, the data is converted into three-dimensional vectors and time series analysis is performed, which can effectively capture the complex patterns and dependencies in the time series; by calculating the cosine similarity, we can accurately find solutions similar to the target financial product solution, thereby improving the relevance and effectiveness of the recommendation. The fully connected vector finally selected as the initial target financial product solution can better meet customer needs and improve customer satisfaction. It not only improves the efficiency of data processing and analysis, but also provides a scientific basis for personalized recommendations of financial products and helps business decision-making.

[0072] S3. Send the initial target financial product solution to the preset target customer, monitor the sent initial target financial product solution in real time, adjust the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring, and obtain an updated push strategy.

[0073] In an embodiment of the present invention, the initial target financial product plan is divided into three parts, namely, the initial target financial product itself, the initial target financial product copy, and the initial target financial product channel. Among them, the initial target financial product itself is divided into the initial target financial product type, the initial target financial product service, and the initial target financial product content. The adjustment of the initial target financial product plan is a real-time monitoring adjustment of the above five parts.

[0074] The initial target financial product channel refers to the way of reaching customers, including: APP messages, WeChat, SMS, phone calls, etc. The collected customer click data is used to determine the customer's preferred way of receiving information, and the initial target financial product is sent to the customer through the channel of the customer's preferred way of receiving information.

[0075] In a specific embodiment, the initial target financial product service can identify relevant holidays and push different services according to the holidays. For example, if it is identified that the holiday is Qingming Festival, according to historical data, customers may have the need for car washing on Qingming Festival, so the car washing service can be pushed to the customer; if it is identified that the holiday is Labor Day, according to historical data, customers may have the need for taxis on Labor Day, so the taxi voucher service can be pushed to the customer, etc.

[0076] In the embodiment of the present invention, the initial target financial product plan after sending is monitored in real time, and the monitoring data mainly includes customer click data, customer browsing data, climate change, etc. For example, by monitoring the customer click data, the customer contact method and marketing copy of the initial target financial product can be adjusted.

[0077] In detail, the preset initial push strategy is adjusted according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy, including:

[0078] Obtaining the target customer behavior data and customer satisfaction;

[0079] Normalizing the target customer behavior data to obtain normalized data;

[0080] Analyzing the normalized data using a preset polynomial regression model to obtain predicted satisfaction;

[0081] Determining whether the customer satisfaction is greater than or equal to the predicted satisfaction;

[0082] If the customer satisfaction is greater than or equal to the predicted satisfaction, continue to obtain the target customer behavior data;

[0083] If the customer satisfaction is less than the predicted satisfaction, extracting key behavior data based on the target customer behavior data;

[0084] An update push strategy is generated according to the key behavior data.

[0085] Further, generating an update push strategy according to the key behavior data includes:

[0086] Obtain historical customer behavior data;

[0087] Calculating the mean of the key behavior data and the mean of the historical customer behavior data;

[0088] Calculating the covariance and standard deviation of the key behavior data and the historical customer behavior data using the mean of the key behavior data and the mean of the historical customer behavior data;

[0089] Calculate the Pearson correlation coefficient between the key behavior data and the historical customer behavior data according to the covariance and the standard deviation;

[0090] Filter out the historical customer behavior data whose Pearson correlation coefficient is greater than a preset Pearson correlation coefficient threshold;

[0091] Extract purchase data from the filtered historical customer behavior data;

[0092] Merging the purchase data in the historical customer behavior data and the purchase data in the key behavior data according to preset key fields to obtain difference data;

[0093] The update push strategy is formulated using the difference data.

[0094] Specifically, the difference data can be used to design specific update push strategies, such as coupons, limited-time discounts, product recommendations, etc., to encourage the target customers to complete the purchase. Regularly compare the changes in user behavior before and after the implementation of the update push strategy, such as purchase rate, click-through rate, user activity, etc.

[0095] Through in-depth analysis of target customer behavior data and customer satisfaction, accurate customer satisfaction prediction and targeted adjustment strategy formulation can be achieved. Through normalization processing and the application of polynomial regression models, customer satisfaction can be accurately predicted, which helps to monitor changes in customer needs in real time. When actual customer satisfaction is lower than the predicted satisfaction, the system can promptly identify key behavior data, and calculate covariance, standard deviation and Pearson correlation coefficient in combination with historical customer behavior data, so as to deeply understand the driving factors behind customer behavior, which is conducive to making accurate decisions based on data, screening out behaviors that are closely related to customer satisfaction, and then formulating targeted adjustment strategies, optimizing products and services, improving customer satisfaction and loyalty, effectively reducing corporate risks, and improving the scientificity and effectiveness of decision-making, thereby enhancing market competitiveness.

[0096] In a specific embodiment, suppose that an insurance company launches a new health financial product, and monitors the behavior data and customer satisfaction of customers who purchase health financial products in real time through a preset polynomial regression model. First, the target customer behavior data is obtained, including: basic information: age, gender, region, insurance type (such as personal health insurance, family health insurance, etc.), purchase history: policy purchase time, policy amount, additional insurance types (such as hospitalization medical insurance, outpatient insurance, etc.), claim history: number of claims, claim amount, claim processing time, claim result (successful or rejected), etc., and then obtain customer scores (1-10 points), opinions and suggestions through regular customer satisfaction surveys.

[0097] When it is found that the target customer's satisfaction is lower than the predicted satisfaction analyzed based on the target customer's behavior data, a similarity comparison is performed between the target customer's behavior data and the historical customer behavior data to find out the historical customer purchase data with a similarity greater than a preset similarity, and the push strategy is adjusted for the target customer based on the historical customer purchase data.

[0098] S4. Using the update push strategy, adjust the initial target financial product solution to obtain a final target financial product solution.

[0099] In the embodiment of the present invention, the use of the update push strategy to adjust the initial target financial product solution to obtain the final target financial product solution includes:

[0100] Extracting the adjustment factor in the update push strategy;

[0101] Adding the adjustment factor to the initial target financial product solution to obtain an updated target financial product solution;

[0102] Extracting the target customer click rate from the target customer behavior data;

[0103] Filter out the push channels whose click-through rates of the target customers are greater than a preset click-through rate threshold;

[0104] Sending the updated target financial product solution to the target customer using the selected push channel;

[0105] Collect the target customers' satisfaction after sending;

[0106] If the target customer's satisfaction after sending is less than the satisfaction threshold, the updated target financial product solution is monitored in real time, and the update push strategy is adjusted according to the target customer behavior data obtained by real-time monitoring;

[0107] If the target customer's satisfaction after sending is greater than or equal to the satisfaction threshold, the final target financial product solution is obtained.

[0108] In detail, the adjustment factors related to the push process are extracted from the update push strategy, including customer preferences, historical click-through rates, product features, market dynamics, etc. According to the historical click-through rates of target customers, the push channels with click-through rates greater than the preset threshold are screened out. The push channels may include emails, SMS, social media, APP push notifications, etc., to ensure that the selected channels can effectively reach the target customers.

[0109] By extracting adjustment factors, financial product solutions can be accurately optimized to better meet the needs of target customers. High click-through rate push channels can be screened to ensure that information can effectively reach customers, thereby increasing participation and conversion rates. By collecting customer satisfaction feedback, potential problems can be identified and resolved in a timely manner, and real-time monitoring and strategy adjustments can be achieved, which not only enhances customer experience, but also helps insurance companies better meet market demand and improve competitiveness.

[0110] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0111] like Figure 3 , which is a functional module diagram of a financial product solution analysis method provided by an embodiment of the present invention.

[0112] In the embodiment of the present disclosure, a financial product solution analysis device is provided, and the financial product solution analysis device corresponds one-to-one to the financial product solution analysis method in the above embodiment. Figure 3 As shown, the financial product solution analysis device 100 can be installed in an electronic device. According to the functions to be implemented, the financial product solution analysis device 100 includes a data acquisition module 101, a solution matching module 102, a strategy update module 103 and a solution adjustment module 104. The functional modules are described in detail as follows:

[0113] Data acquisition module 101, used to acquire regional characteristics and historical transaction data of historical financial products;

[0114] A solution matching module 102 is used to match a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution;

[0115] The strategy updating module 103 is used to send the initial target financial product solution to the preset target customer, monitor the initial target financial product solution in real time after sending, and adjust the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy;

[0116] The solution adjustment module 104 is used to adjust the initial target financial product solution by using the update push strategy to obtain a final target financial product solution.

[0117] In one embodiment, the solution matching module 102 is used to:

[0118] Removing outliers from the regional features to obtain target features;

[0119] Arrange the historical transaction data in chronological order from the beginning to the end to obtain standard transaction data;

[0120] Using a generative adversarial network to synthesize the target features and the standard transaction data to obtain standard solution data;

[0121] Converting the standard scheme data into a three-dimensional vector using a preset embedding layer;

[0122] Performing time series analysis on the three-dimensional vector using a preset stacked LSTM layer to obtain a time series vector;

[0123] Performing full connection on the time series vector to obtain a fully connected vector;

[0124] Converting the data of the target financial product solution into a target financial product solution vector;

[0125] Calculating the cosine similarity between the target financial product solution vector and the fully connected vector one by one;

[0126] Filter out the fully connected vectors whose cosine similarity is greater than a preset cosine similarity threshold;

[0127] The screened fully connected vector is used as the initial target financial product solution.

[0128] In one embodiment, the solution matching module 102 is used to:

[0129] Extracting a random noise vector from the standard transaction data using normal distribution;

[0130] Using a preset generator to convolve the target feature and the random noise vector to obtain initial solution data;

[0131] Convolving the initial scheme data using a preset discriminator to obtain the probability that the initial scheme data is true data;

[0132] If the probability that the initial scheme data is true data is less than or equal to a preset probability threshold, returning to convolve the target feature and the random noise vector using a preset generator;

[0133] If the probability that the initial solution data is true data is greater than the probability threshold, the standard solution data is obtained.

[0134] In one embodiment, the solution matching module 102 is used to:

[0135] Calculating the dot product of the target financial product solution vector and the fully connected vector;

[0136] Calculating the modulus of the target financial product solution vector and the modulus of the fully connected vector;

[0137] Calculating the module product of the target financial product solution vector and the fully connected vector using the module of the target financial product solution vector and the module of the fully connected vector;

[0138] The dot product is divided by the modular product to obtain the cosine similarity between the target financial product solution vector and the fully connected vector.

[0139] In one embodiment, the policy update module 103 is used to:

[0140] Obtaining the target customer behavior data and customer satisfaction;

[0141] Normalizing the target customer behavior data to obtain normalized data;

[0142] Analyzing the normalized data using a preset polynomial regression model to obtain predicted satisfaction;

[0143] Determining whether the customer satisfaction is greater than or equal to the predicted satisfaction;

[0144] If the customer satisfaction is greater than or equal to the predicted satisfaction, continue to obtain the target customer behavior data;

[0145] If the customer satisfaction is less than the predicted satisfaction, extracting key behavior data based on the target customer behavior data;

[0146] An update push strategy is generated according to the key behavior data.

[0147] In one embodiment, the policy update module 103 is used to:

[0148] Obtain historical customer behavior data;

[0149] Calculating the mean of the key behavior data and the mean of the historical customer behavior data;

[0150] Calculating the covariance and standard deviation of the key behavior data and the historical customer behavior data using the mean of the key behavior data and the mean of the historical customer behavior data;

[0151] Calculate the Pearson correlation coefficient between the key behavior data and the historical customer behavior data according to the covariance and the standard deviation;

[0152] Filter out the historical customer behavior data whose Pearson correlation coefficient is greater than a preset Pearson correlation coefficient threshold;

[0153] Extract purchase data from the filtered historical customer behavior data;

[0154] Merging the purchase data in the historical customer behavior data and the purchase data in the key behavior data according to preset key fields to obtain difference data;

[0155] The update push strategy is formulated using the difference data.

[0156] In one embodiment, the scheme adjustment module 104 is used to:

[0157] Extracting the adjustment factor in the update push strategy;

[0158] Adding the adjustment factor to the initial target financial product solution to obtain an updated target financial product solution;

[0159] Extracting the target customer click rate from the target customer behavior data;

[0160] Filter out the push channels whose click-through rates of the target customers are greater than a preset click-through rate threshold;

[0161] Sending the updated target financial product solution to the target customer using the selected push channel;

[0162] Collect the target customers' satisfaction after sending;

[0163] If the target customer's satisfaction after sending is less than the satisfaction threshold, the updated target financial product solution is monitored in real time, and the update push strategy is adjusted according to the target customer behavior data obtained by real-time monitoring;

[0164] If the target customer's satisfaction after sending is greater than or equal to the satisfaction threshold, the final target financial product solution is obtained.

[0165] In the present invention, for the analysis of financial product solutions, first, the regional characteristics and historical transaction data of historical financial products are obtained, and then the regional characteristics and the historical transaction data are used to match the preset target financial product solutions to obtain the initial target financial product solutions, and then the initial target financial product solutions are sent to the preset target customers, and the initial target financial product solutions after sending are monitored in real time. The preset initial push strategy is adjusted according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy, and accurate decisions are made based on the data to screen out behaviors that are closely related to customer satisfaction, and then targeted adjustment strategies are formulated to improve the efficiency of adjusting financial product solutions according to customer needs. Finally, the initial target financial product solution is adjusted using the updated push strategy to obtain the final target financial product solution, thereby improving the efficiency of generating personalized financial products. The specific definition of the financial product solution analysis device can be found in the definition of the financial product solution analysis method above, which will not be repeated here. Each module in the above-mentioned financial product solution analysis device can be implemented in whole or in part by software, hardware and a combination thereof. The above modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0166] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps on the service side of the financial product solution analysis method are implemented.

[0167] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server through a network connection. When the computer program is executed by the processor, the functions or steps on the client side of the financial product solution analysis method are implemented.

[0168] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0169] Obtain regional characteristics and historical transaction data of historical financial products;

[0170] Matching a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution;

[0171] Sending the initial target financial product solution to a preset target customer, monitoring the sent initial target financial product solution in real time, and adjusting the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy;

[0172] The initial target financial product solution is adjusted using the update push strategy to obtain a final target financial product solution.

[0173] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and apparatuses can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0174] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0175] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0176] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0177] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the steps of the method described in the above embodiment are implemented.

[0178] The readable storage medium of the present invention stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can achieve:

[0179] Obtain regional characteristics and historical transaction data of historical financial products;

[0180] Matching a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution;

[0181] Sending the initial target financial product solution to a preset target customer, monitoring the sent initial target financial product solution in real time, and adjusting the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy;

[0182] The initial target financial product solution is adjusted using the update push strategy to obtain a final target financial product solution.

[0183] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0184] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0185] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0186] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0187] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0189] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0190] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0191] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article 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, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0192] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

[0193] It should be noted that if software tools or components other than those of our company appear in the embodiments of the present application, they are only used for illustrative purposes and do not represent actual use.

Claims

1. A financial product solution analysis method, characterized in that: The method comprises: Obtain regional characteristics and historical transaction data of historical financial products; Matching a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution; Sending the initial target financial product solution to a preset target customer, monitoring the sent initial target financial product solution in real time, and adjusting the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy; The initial target financial product solution is adjusted using the update push strategy to obtain a final target financial product solution.

2. The financial product solution analysis method according to claim 1, characterized in that: The using the regional features and the historical transaction data to match the preset target financial product solutions to obtain an initial target financial product solution includes: Removing outliers from the regional features to obtain target features; Arrange the historical transaction data in chronological order from the beginning to the end to obtain standard transaction data; Using a generative adversarial network to synthesize the target features and the standard transaction data to obtain standard solution data; Converting the standard scheme data into a three-dimensional vector using a preset embedding layer; Performing time series analysis on the three-dimensional vector using a preset stacked LSTM layer to obtain a time series vector; Performing full connection on the time series vector to obtain a fully connected vector; Converting the data of the target financial product solution into a target financial product solution vector; Calculating the cosine similarity between the target financial product solution vector and the fully connected vector one by one; Filter out the fully connected vectors whose cosine similarity is greater than a preset cosine similarity threshold; The screened fully connected vector is used as the initial target financial product solution.

3. The financial product solution analysis method according to claim 2, characterized in that: The method of synthesizing the target feature and the standard transaction data using a generative adversarial network to obtain standard solution data includes: Extracting a random noise vector from the standard transaction data using normal distribution; Using a preset generator to convolve the target feature and the random noise vector to obtain initial solution data; Convolving the initial scheme data using a preset discriminator to obtain a probability that the initial scheme data is true data; If the probability that the initial scheme data is true data is less than or equal to a preset probability threshold, returning to convolve the target feature and the random noise vector using a preset generator; If the probability that the initial solution data is true data is greater than the probability threshold, the standard solution data is obtained.

4. The financial product solution analysis method according to claim 2, characterized in that: The step of calculating the cosine similarity between the target financial product solution vector and the fully connected vector one by one includes: Calculating the dot product of the target financial product solution vector and the fully connected vector; Calculating the modulus of the target financial product solution vector and the modulus of the fully connected vector; Calculating the module product of the target financial product solution vector and the fully connected vector using the module of the target financial product solution vector and the module of the fully connected vector; The dot product is divided by the modular product to obtain the cosine similarity between the target financial product solution vector and the fully connected vector.

5. The financial product solution analysis method according to claim 1, characterized in that: The step of adjusting the preset initial push strategy according to the target customer behavior data obtained through real-time monitoring to obtain an updated push strategy includes: Obtaining the target customer behavior data and customer satisfaction; Normalizing the target customer behavior data to obtain normalized data; Analyzing the normalized data using a preset polynomial regression model to obtain predicted satisfaction; Determining whether the customer satisfaction is greater than or equal to the predicted satisfaction; If the customer satisfaction is greater than or equal to the predicted satisfaction, continue to obtain the target customer behavior data; If the customer satisfaction is less than the predicted satisfaction, extracting key behavior data based on the target customer behavior data; An update push strategy is generated according to the key behavior data.

6. The financial product solution analysis method according to claim 5, characterized in that: The step of generating an update push strategy according to the key behavior data includes: Obtain historical customer behavior data; Calculating the mean of the key behavior data and the mean of the historical customer behavior data; Calculating the covariance and standard deviation of the key behavior data and the historical customer behavior data using the mean of the key behavior data and the mean of the historical customer behavior data; Calculate the Pearson correlation coefficient between the key behavior data and the historical customer behavior data according to the covariance and the standard deviation; Filter out the historical customer behavior data whose Pearson correlation coefficient is greater than a preset Pearson correlation coefficient threshold; Extract purchase data from the filtered historical customer behavior data; Merging the purchase data in the historical customer behavior data and the purchase data in the key behavior data according to preset key fields to obtain difference data; The update push strategy is formulated using the difference data.

7. The financial product solution analysis method according to claim 1, characterized in that: The using the update push strategy to adjust the initial target financial product solution to obtain the final target financial product solution includes: Extracting the adjustment factor in the update push strategy; Adding the adjustment factor to the initial target financial product solution to obtain an updated target financial product solution; Extracting the target customer click rate from the target customer behavior data; Filter out the push channels whose click-through rates of the target customers are greater than a preset click-through rate threshold; Sending the updated target financial product solution to the target customer using the selected push channel; Collect the target customers' satisfaction after sending; If the target customer's satisfaction after sending is less than the satisfaction threshold, the updated target financial product solution is monitored in real time, and the update push strategy is adjusted according to the target customer behavior data obtained by real-time monitoring; If the target customer's satisfaction after sending is greater than or equal to the satisfaction threshold, the final target financial product solution is obtained.

8. A financial product solution analysis device, characterized in that: The device comprises: Data acquisition module, used to obtain regional characteristics and historical transaction data of historical financial products; A solution matching module, used to match a preset target financial product solution using the regional characteristics and the historical transaction data to obtain an initial target financial product solution; A strategy update module, used to send the initial target financial product solution to a preset target customer, monitor the initial target financial product solution in real time after sending, and adjust the preset initial push strategy according to the target customer behavior data obtained by real-time monitoring to obtain an updated push strategy; A solution adjustment module is used to adjust the initial target financial product solution using the update push strategy to obtain a final target financial product solution.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the financial product solution analysis method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the financial product solution analysis method according to any one of claims 1 to 7 is implemented.

Images