Financial product recommendation method and device based on public account, and electronic equipment

Abstract

The invention discloses a financial product recommendation method and device based on a public account and electronic equipment, and relates to the field of artificial intelligence and the field of financial science and technology. The method comprises the following steps: obtaining business exchange data between L public accounts, L being an integer greater than 2; according to the business exchange data, M partner accounts with fund association are screened out from the L partner accounts to form an account set, and M is an integer larger than 2 and smaller than or equal to L; selecting a public account from the account set as a target account; according to the financial products purchased by the target account and the financial products purchased by other accounts except the target account in the account set, the target financial product recommended to the target account is obtained through screening from the N financial products, and N is an integer larger than 1. The technical problem that in the prior art, the recommendation accuracy of financial products is low due to the fact that the recommended products are determined only for account features of a single account is solved.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and financial technology, and specifically to a method, device, and electronic device for recommending financial products based on corporate accounts. Background Art

[0002] With the continuous development and innovation of the financial market, various financial institutions are actively exploring how to provide customers with more accurate and personalized financial services, especially financial product recommendation services for corporate accounts.

[0003] Currently, major banks and financial institutions generally use data analysis methods to assess customer needs and risk preferences, thereby recommending appropriate financial products. However, existing technologies only determine recommended products based on the characteristics of a single account. While this method can provide preliminary recommendations based on factors such as account balance, transaction frequency, and historical product purchase history, it ignores the complex network of capital flows and interdependent business relationships between corporate accounts, significantly reducing the accuracy and relevance of financial product recommendations.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a method, device, and electronic device for recommending financial products based on corporate accounts, so as to at least solve the technical problem in the prior art of determining recommended products based only on the account characteristics of a single account, resulting in low accuracy in financial product recommendations.

[0006] According to one aspect of an embodiment of the present application, a method for recommending financial products based on corporate accounts is provided, comprising: with user authorization, obtaining business transaction data between L corporate accounts, where L is an integer greater than 2; based on the business transaction data, screening out M corporate accounts with fund association from the L corporate accounts to form an account set, where M is an integer greater than 2 and less than or equal to L; selecting a corporate account from the account set as a target account; and screening out a target financial product recommended to the target account from N financial products based on financial products purchased by the target account and financial products purchased by other accounts in the account set except the target account, where N is an integer greater than 1.

[0007] Optionally, based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from N financial products, including: using the product characteristics of the financial products purchased by the target account as the first product characteristics; using the product characteristics of the financial products purchased by other accounts as the second product characteristics; detecting the amount of funds transferred between the other accounts and the target account and the frequency of funds transactions; setting a corresponding weight for the second product characteristic based on the amount of funds transferred between the other accounts and the target account and the frequency of funds transactions; generating a feature matrix based on the first product characteristics, the second product characteristics and the weights corresponding to the second product characteristics; and screening the target financial product recommended to the target account from the N financial products based on the feature matrix.

[0008] Optionally, the amount of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account; the frequency of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account.

[0009] Optionally, target financial products recommended to a target account are screened from N financial products according to a feature matrix, including: detecting similarity between the feature matrix and product feature vectors of the N financial products to obtain a similarity matrix; wherein each element in the similarity matrix represents similarity between the feature matrix and the product feature vector of a financial product; determining, according to the similarity matrix, financial products having a similarity with the feature matrix greater than or equal to a similarity threshold as a set of candidate financial products; and selecting, from the set of candidate financial products, a preset number of financial products as target financial products in descending order of similarity with the feature matrix.

[0010] Optionally, after selecting a preset number of financial products as target financial products from the set of candidate financial products in descending order of similarity to the feature matrix, the liquidity characteristics of the target account are obtained; and based on the liquidity characteristics of the target account, the preset number of target financial products are recommended and ranked, wherein the more similar the liquidity characteristics of the target financial product are to the liquidity characteristics of the target account, the higher the recommended ranking of the target financial product.

[0011] Optionally, based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from N financial products, including: determining the transaction behavior preference characteristics of the target account based on the transaction behavior data of the target account; based on the transaction behavior preference characteristics of the target account, screening a first category of accounts from the account set, wherein the similarity between the transaction behavior preference characteristics of the first category of accounts and the transaction behavior preference characteristics of the target account is greater than a preset similarity; based on the financial products purchased by the target account and the financial products purchased by the first category of accounts, a target financial product recommended to the target account is screened from N financial products.

[0012] Optionally, the transaction behavior preference characteristics of the target account are determined based on the transaction behavior data of the target account, including: performing time series analysis on the financial management behavior data of the target account to obtain the time characteristics, transaction frequency characteristics and transaction amount characteristics corresponding to when the target account completes the financial management behavior; and using the time characteristics, transaction frequency characteristics and transaction amount characteristics as the transaction behavior preference characteristics of the target account.

[0013] According to another aspect of an embodiment of the present application, a financial product recommendation device based on corporate accounts is also provided, wherein the device includes: an acquisition unit for acquiring business transaction data between L corporate accounts with user authorization, wherein L is an integer greater than 2; a screening unit for screening out M corporate accounts with capital association from the L corporate accounts to form an account set based on the business transaction data, wherein M is an integer greater than 2 and less than or equal to L; a selection unit for selecting a corporate account from the account set as a target account; a processing unit for screening a target financial product recommended to the target account from N financial products based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, wherein N is an integer greater than 1.

[0014] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is run, the device where the computer-readable storage medium is located executes the above-mentioned financial product recommendation method based on corporate accounts.

[0015] According to another aspect of an embodiment of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned financial product recommendation method based on corporate accounts.

[0016] According to another aspect of an embodiment of the present application, a computer program product is also provided, wherein the computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the computer program or instructions implements the above-mentioned financial product recommendation method based on corporate accounts.

[0017] In this application, with user authorization, business transaction data between L public accounts is obtained, where L is an integer greater than 2. Based on the business transaction data, M public accounts with fund associations are screened from the L public accounts to form an account set, where M is an integer greater than 2 and less than or equal to L. A public account is selected from the account set as the target account, and based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set other than the target account, a target financial product is screened from N financial products to obtain a recommendation for the target account, where N is an integer greater than 1.

[0018] From the above, it can be seen that compared with the traditional method that only focuses on the static data of a single account, this application captures the dynamic correlation between accounts by analyzing the business transaction data of L accounts, which is equivalent to building a network model of capital flow. This method can more comprehensively understand the business ecology and capital flow of each public account, thereby providing each target account with in-depth insights based on the entire network. Secondly, this application also intelligently selects M public accounts with direct or indirect capital connections from L accounts to form an account set. This process greatly improves the pertinence of subsequent recommendations. By focusing on the account group that has actual business transactions with the target account, the interference of irrelevant account data is avoided, ensuring that the recommendation results are more in line with the actual needs of the target account.

[0019] Based on an account pool, this application not only considers the target account's own historical financial product purchase history but also incorporates purchase information from other accounts within the pool, enabling collaborative multi-account recommendations. This approach can uncover shared needs among similar businesses or partners, as well as product preference patterns that might be overlooked from a single account perspective, thereby improving the overall quality and success rate of recommendations.

[0020] In summary, the technical solution of this application effectively compensates for the limitations of the single account perspective in the existing technology by introducing the concept of multi-account correlation analysis and collaborative recommendation, and overcomes the problem of low accuracy in financial product recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 This is a flowchart of an optional method for recommending financial products based on public accounts according to an embodiment of the present application;

[0023] Figure 2 is an optional flow chart for determining a target financial product according to an embodiment of the present application;

[0024] Figure 3 This is a schematic diagram of an optional financial product recommendation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising 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 devices.

[0027] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) collected by this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or institution through the interface, and obtain relevant information after receiving the consent information fed back by the aforementioned user or institution.

[0028] According to an embodiment of the present application, an embodiment of a method for recommending financial products based on corporate accounts is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Optionally, according to an embodiment of the present application, a financial product recommendation system is provided as the execution subject of the financial product recommendation method of the embodiment of the present application, wherein the system can be a software system or an embedded system combining software and hardware. Of course, the method execution subject in the embodiment of the present application can also be other forms of execution subjects, such as devices, equipment, etc. Those skilled in the art should know that this application does not specifically limit the specific form of expression of the method execution subject.

[0030] Figure 1 This is a flowchart of an optional method for recommending financial products based on public accounts according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0031] Step S101: With user authorization, obtain business transaction data between L public accounts.

[0032] In step S101 , L is an integer greater than 2.

[0033] It's important to note that before data collection and analysis can begin, it's necessary to first ensure legitimate data use authorization is obtained from the target user. This step is crucial and demonstrates respect for and protection of user privacy and data security. Authorization can be obtained in a variety of ways, such as by users actively selecting the privacy policy when using the service, or by explicitly consenting to data collection within specific functional modules. The authorization should clearly inform users of the scope of data collection, purpose of use, storage methods, and protection measures, ensuring that users have full knowledge and choice regarding data usage.

[0034] Transaction data may include, but is not limited to, transfer records, payment instructions, receipt information, transaction amounts, transaction frequency, transaction time, and counterparty account information. Each transaction may reflect a company's operating status, funding needs, creditworthiness, and partnerships with other businesses. Transaction data for public accounts can be obtained directly through the bank's transaction system, imported through the client's financial software interface, or even supplemented and integrated using third-party data platforms.

[0035] It's important to reiterate that obtaining explicit authorization from the target individual involves informing the target individual of the purpose of data collection, how it will be used, and how their privacy will be protected. The target individual is also clearly informed of the privacy policy, including policies for data collection, use, storage, and deletion, as well as how the target individual can exercise their rights, such as accessing, correcting, or deleting their data. The target individual has the right to choose whether to consent to the collection and use of their data. Furthermore, when collecting the target individual's data, the system uses encryption technology to ensure data security during transmission and storage. The use of the target individual's data will strictly comply with relevant laws and regulations and the scope of the target individual's authorization. The target individual's data will be stored in a secure database and undergo regular security audits to ensure data security and the effectiveness of privacy protection measures. When the target individual's data is no longer needed, the system securely deletes it according to the target individual's request and legal requirements to ensure it cannot be recovered.

[0036] The acquired data often contains noise, including erroneous records, duplicate transactions, and non-transactional fund transfers (such as interest income and fees). Therefore, preprocessing requires removing non-business transactions, denoising the data, and standardizing the data format to ensure the accuracy of subsequent analysis. The financial product recommendation system can transform the cleaned transaction data into a graph, where nodes represent public accounts and edges represent the direction and amount of fund flows, thereby forming a detailed public account fund flow network. This visual graph helps intuitively understand the strength of relationships between accounts and fund flow patterns.

[0037] Optionally, by applying various data processing technologies such as statistics, machine learning, and social network analysis, the financial product recommendation system can extract valuable information from business transaction data, including but not limited to trading habits between accounts, periodicity of capital flows, and distribution of transaction sizes.

[0038] Step S102: Based on the business transaction data, M public accounts with fund association are selected from the L public accounts to form an account set.

[0039] In step S102 , M is an integer greater than 2 and less than or equal to L.

[0040] Step S103: Select a public account from the account set as the target account.

[0041] Step S104 , based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from the N financial products.

[0042] Wherein, N is an integer greater than 1.

[0043] Optionally, the financial product recommendation system can first select a single public account as the target account from a set of M public accounts, identified through fund linkage screening. This selection can be random or based on criteria such as account activity, fund flow volume, or the time of the most recent transaction. The selection of the target account forms the foundation for subsequent recommendation strategies, serving as a focal point for data comparison and analysis. Subsequently, the financial product recommendation system can gain in-depth insights into the target account's past purchases, including the type, amount, maturity, and yield of financial products. Simultaneously, the system considers the financial product purchase information of the other M-1 public accounts in the set. The fact that these accounts are financially linked to the target account suggests that they may share similar business models, industry attributes, or financial management needs. By comparing and analyzing their purchasing behavior, potential financial trends or shared preferences can be identified, providing valuable insights for target account recommendations.

[0044] Building on this foundation, the financial product recommendation system can comprehensively analyze the target account's historical purchase data with the purchase information of other accounts within the same set. For example, it can employ various data analysis and machine learning algorithms, such as cluster analysis, association rule mining, and predictive modeling, to uncover the connections and patterns hidden in the data. This comprehensive, data-driven approach helps form more accurate customer profiles and provides a basis for financial product recommendations.

[0045] Finally, based on the above analysis results, N financial products (N is an integer greater than 1, meaning there are multiple candidate products to choose from) are screened to find the financial product that best suits the target account.

[0046] In an optional embodiment, Figure 2 This is an optional flow chart for determining a target financial product according to an embodiment of the present application. Figure 2 As shown, the following steps are included:

[0047] Step S201: Using the product feature of the financial product purchased by the target account as the first product feature;

[0048] Step S202: Using the product characteristics of the financial product purchased by the other account as the second product characteristics;

[0049] Step S203: Detect the amount of funds transferred between the target account and the other accounts and the frequency of fund transactions;

[0050] Step S204: setting a corresponding weight for the second product feature based on the amount of funds transferred between the target account and the other accounts and the frequency of fund transactions;

[0051] Step S205, generating a feature matrix based on the first product feature, the second product feature, and the weight corresponding to the second product feature;

[0052] Step S206 , screening the N financial products according to the feature matrix to obtain a target financial product recommended to the target account.

[0053] Optionally, the amount of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account; the frequency of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account.

[0054] Optionally, the first product characteristics refer to the specific characteristics of financial products purchased in the past by the target account (i.e., the corporate account for which financial product recommendations are currently being made), including but not limited to product type (e.g., bonds, funds, insurance), investment period, rate of return, risk level, etc. The second product characteristics are derived from other accounts with which the target account has financial transactions (these accounts form part of a financial network). From the purchase history of other accounts, the same set of characteristics related to the financial products purchased by the target account is extracted, i.e., the second product characteristics.

[0055] Optionally, in order to better integrate the first product feature with the second product feature, the present application introduces the concept of weight. The setting of weights mainly refers to two aspects of information: one is the amount of funds transferred between other accounts and the target account, and the other is the frequency of fund transactions. Among them, large transactions often reflect the importance and trust between the two accounts better than small transactions. Therefore, for transactions with large amounts of funds transferred between other accounts, the characteristics of the financial products purchased by the corresponding accounts will be given higher weights when generating the feature matrix. High-frequency trading means that there is a stable or close business relationship between the two accounts. Frequent fund transactions can be regarded as a signal that the target account may learn from or be interested in the financial management strategies of other accounts. Therefore, the characteristics of financial products purchased by accounts with high transaction frequencies will also receive relatively high weights.

[0056] Optionally, a feature matrix is ​​a mathematical structure consisting of primary product features, secondary product features, and corresponding weights, used to systematically organize and represent various product features and their importance. In constructing the feature matrix, each column represents a product feature (such as product type, yield, risk level, etc.), and each row corresponds to an account (including the target account and other accounts). In the matrix, the row for the target account is populated with its primary product feature, while the rows for other accounts are populated with the secondary product feature, with different weights assigned based on the respective transaction amounts and transaction frequency.

[0057] In an optional embodiment, a target financial product recommended to a target account is selected from N financial products based on a feature matrix. The method includes: the financial product recommendation system may detect the similarity between the feature matrix and the product feature vectors of the N financial products to obtain a similarity matrix; each element in the similarity matrix represents the similarity between the feature matrix and the product feature vector of a financial product. Based on the similarity matrix, financial products whose similarity to the feature matrix is ​​greater than or equal to a similarity threshold are then identified as a set of candidate financial products. Finally, a preset number of financial products are selected from the set of candidate financial products in descending order of similarity to the feature matrix as target financial products.

[0058] Optionally, for each row in the feature matrix (representing an account's financial product preferences), the system calculates similarity with the feature vectors of N financial products. This calculation can employ various mathematical tools, such as cosine similarity, Euclidean distance, and Jaccard similarity coefficient, to measure the similarity between features. All calculated similarity values ​​are arranged into a matrix, the similarity matrix, based on the correspondence between accounts and financial products. Each element in the matrix represents a similarity score between an account in the feature matrix and one of the N financial products. These scores reflect the degree of match between the product and the account's historical investment behavior.

[0059] Next, the system applies a pre-set similarity threshold to filter the similarity matrix. This threshold is determined based on an analysis of historical recommendation performance and an understanding of the target account's risk appetite. Any financial product with a score above or equal to this threshold is considered a match for the target account's preferences and is added to the candidate financial product pool.

[0060] Finally, the system selects a preset number of financial products from the candidate set, sorting them by similarity score from high to low, as the final target financial products to recommend to the target account. This preset number can be adjusted based on the flexibility of the recommendation strategy, market conditions, or client preferences, aiming to provide clients with a curated list of high-quality financial products. Financial products with higher similarity scores are considered more compatible with the target account's investment preferences and therefore receive higher priority, becoming the primary recommendation targets.

[0061] In summary, through the construction and analysis of the similarity matrix, combined with the screening and final sorting of the candidate set, the financial product recommendation system of this application can intelligently and accurately select financial products that meet the needs of the target account from a large number of financial products, which not only improves the accuracy and practicality of the recommendations, but also strengthens the interaction and trust between financial institutions and customers.

[0062] In an optional embodiment, after selecting a preset number of financial products as target financial products from a set of candidate financial products in descending order of similarity to the feature matrix, the financial product recommendation system may obtain the liquidity characteristics of the target account, and then recommend and rank the preset number of target financial products based on the liquidity characteristics of the target account, wherein the more similar the liquidity characteristics of the target financial product are to the liquidity characteristics of the target account, the higher the recommendation ranking of the target financial product.

[0063] Optionally, liquidity characteristics refer to the inflow and outflow of funds in a public account within a specific timeframe, including the stability of funds, the cyclical nature of fund demand, the size and frequency of fund flows, etc. After obtaining the target account's liquidity characteristics, the system can perform a personalized ranking of the initially selected target financial products (i.e., a preset number of financial products). The ranking is based on the degree of match between the product's liquidity characteristics and the actual needs of the target account.

[0064] For example, short-term products offer higher liquidity and are more suitable for accounts with short funding cycles; flexible financial products allow early redemption when necessary and are more attractive to accounts with higher liquidity requirements; certain investment products can be bought and sold quickly in the market, and their liquidity is particularly important for accounts that need to frequently transfer funds.

[0065] By ranking recommendations based on liquidity characteristics, the technical solution of this application makes financial product recommendations more aligned with the actual needs of corporate accounts, improving the practicality and effectiveness of recommendations. This strategy not only enhances the customer experience but also helps financial institutions connect more precisely with the market, improving the quality of their financial services and customer satisfaction.

[0066] In an optional embodiment, a target financial product recommended to the target account is screened from N financial products based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set other than the target account. This includes: the financial product recommendation system may determine the target account's transaction behavior preference characteristics based on the target account's transaction behavior data, and then screen a first category of accounts from the account set based on the target account's transaction behavior preference characteristics, wherein the similarity between the transaction behavior preference characteristics of the first category of accounts and the transaction behavior preference characteristics of the target account is greater than a preset similarity. Finally, based on the financial products purchased by the target account and the financial products purchased by the first category of accounts, the target financial product recommended to the target account is screened from N financial products.

[0067] Optionally, trading behavior preference characteristics refer to characteristics of the target account's trading habits, preferences, risk tolerance, and other aspects, summarized and summarized through analysis of the target account's transaction data. These characteristics may include trading time preferences (e.g., frequent large-value transactions on weekdays), trading size preferences (preference for small or large transactions), trading frequency (daily, weekly, monthly, etc.), transaction type preferences (investments, transfers, loans, etc.), and preferences for specific financial products (e.g., a preference for bonds over stocks).

[0068] After determining the target account's trading behavior preferences, the financial product recommendation system will filter out accounts from a larger set of accounts, selecting the first category whose similarity with the target account's trading behavior preferences exceeds a preset similarity threshold. This threshold serves as a threshold for distinguishing "sufficiently similar" accounts from those considered "similar enough" and can be adjusted dynamically based on factors such as the accuracy of the recommendation algorithm and market volatility.

[0069] Finally, the financial product recommendation system combines the financial products purchased by the target account with those purchased by the first category of accounts (i.e., accounts with similar trading preferences) to further filter the N available financial products and recommend the target financial product to the target account. This recommendation process is based on a core assumption: accounts with similar trading preferences are likely to share similar financial needs and product preferences.

[0070] By deeply analyzing the target account's transaction behavior preferences and combining it with information about Category 1 accounts with similar behavior patterns, the financial product recommendation system in this application can more accurately capture the target account's financial needs and provide highly personalized financial product recommendation services. This approach not only improves the customer experience but also helps financial institutions precisely meet market demand and enhance customer retention.

[0071] In an optional embodiment, the transaction behavior preference characteristics of the target account are determined based on the transaction behavior data of the target account, including: performing a time series analysis on the financial management behavior data of the target account to obtain the time characteristics, transaction frequency characteristics, and transaction amount characteristics corresponding to when the target account completes the financial management behavior; and using the time characteristics, transaction frequency characteristics, and transaction amount characteristics as the transaction behavior preference characteristics of the target account.

[0072] Alternatively, time series analysis is a statistical analysis method specifically designed to process chronologically ordered data sequences to reveal trends, cyclical characteristics, seasonal fluctuations, and other characteristics. In finance, particularly in analyzing financial management behavior of corporate accounts, time series analysis can help understand a company's financial decision-making and capital management patterns at different points in time.

[0073] Based on time series analysis, we can extract the following three key features, which together constitute the trading behavior preference characteristics of the target account:

[0074] Temporal characteristics: These relate to the timing of account financial management activities, including but not limited to trading preferences on weekdays versus non-weekdays, monthly or quarterly peak trading periods, and preferences for specific months within an annual cycle. Temporal characteristics are crucial for capturing an account's cyclical funding needs and financial planning habits.

[0075] Transaction frequency: This describes the number of times an account completes financial activities (such as purchasing financial products and transferring funds) within a specific period. A high transaction frequency may indicate strong liquidity and market sensitivity, while a low transaction frequency may indicate a long-term holding trend or less market participation.

[0076] Transaction amount characteristics: Analyze the average transaction size, maximum transaction amount, minimum transaction amount, etc. of the account when conducting financial management activities, so as to determine the account's risk appetite, capital adequacy, and demand for high-yield or high-risk products.

[0077] According to another aspect of the embodiment of the present application, a financial product recommendation device based on a public account is also provided, wherein: Figure 3 is a schematic diagram of an optional financial product recommendation device according to an embodiment of the present application, such as Figure 3 As shown, the device includes: an acquisition unit 301, a screening unit 302, a selection unit 303, and a processing unit 304.

[0078] Optionally, the acquisition unit 301 is used to obtain business transaction data between L corporate accounts with user authorization, where L is an integer greater than 2; the screening unit 302 is used to screen out M corporate accounts with financial association from the L corporate accounts to form an account set based on the business transaction data, where M is an integer greater than 2 and less than or equal to L; the selection unit 303 is used to select a corporate account from the account set as a target account; the processing unit 304 is used to screen N financial products to obtain a target financial product recommended to the target account based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, where N is an integer greater than 1.

[0079] Optionally, the processing unit 304 includes: a first processing sub-unit, used to use the product characteristics of the financial products purchased by the target account as the first product characteristics; a second processing sub-unit, used to use the product characteristics of the financial products purchased by other accounts as the second product characteristics; a detection sub-unit, used to detect the amount of funds transferred between the other accounts and the target account and the frequency of funds transactions; a third processing sub-unit, used to set a corresponding weight for the second product characteristics according to the amount of funds transferred between the other accounts and the target account and the frequency of funds transactions; a fourth processing sub-unit, used to generate a feature matrix according to the first product characteristics, the second product characteristics and the weights corresponding to the second product characteristics; and a screening sub-unit, used to screen the target financial product recommended to the target account from N financial products according to the feature matrix.

[0080] Optionally, the amount of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account; the frequency of fund transactions between any account in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account.

[0081] Optionally, the screening subunit includes: a detection module, configured to detect the similarity between the feature matrix and the product feature vectors of N financial products to obtain a similarity matrix; wherein each element in the similarity matrix represents the similarity between the feature matrix and the product feature vector of a financial product; a first processing module, configured to determine, based on the similarity matrix, financial products whose similarity to the feature matrix is ​​greater than or equal to a similarity threshold, as a set of candidate financial products; and a second processing module, configured to select a preset number of financial products from the set of candidate financial products as target financial products in descending order of similarity to the feature matrix.

[0082] Optionally, the financial product recommendation device also includes: a first acquisition unit, used to obtain the liquidity characteristics of the target account; a sorting unit, used to recommend and sort a preset number of target financial products based on the liquidity characteristics of the target account, wherein the more similar the liquidity characteristics of the target financial product are to the liquidity characteristics of the target account, the higher the recommendation ranking of the target financial product.

[0083] Optionally, the processing unit 304 includes: a first determination subunit, used to determine the transaction behavior preference characteristics of the target account based on the transaction behavior data of the target account; a second determination subunit, used to screen out a first type of account from the account set based on the transaction behavior preference characteristics of the target account, wherein the similarity between the transaction behavior preference characteristics of the first type of account and the transaction behavior preference characteristics of the target account is greater than a preset similarity; and a third determination subunit, used to screen out a target financial product recommended to the target account from N financial products based on the financial products purchased by the target account and the financial products purchased by the first type of account.

[0084] Optionally, the first determination sub-unit includes: an analysis module for performing time series analysis on the financial management behavior data of the target account to obtain the time characteristics, transaction frequency characteristics and transaction amount characteristics corresponding to when the target account completes the financial management behavior; a third processing module for using the time characteristics, transaction frequency characteristics and transaction amount characteristics as the transaction behavior preference characteristics of the target account.

[0085] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium. When the computer program is run, the device where the computer-readable storage medium is located executes the above-mentioned financial product recommendation method based on corporate accounts.

[0086] According to another aspect of an embodiment of the present application, an electronic device is also provided, wherein the electronic device includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors execute the above-mentioned financial product recommendation method based on corporate accounts.

[0087] According to another aspect of an embodiment of the present application, a computer program product is also provided, wherein the computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the computer program or instructions implements the above-mentioned financial product recommendation method based on corporate accounts.

[0088] The above-mentioned embodiments or examples disclosed in this application are not exhaustive, but are only illustrations of some embodiments or examples, and are not intended to be specific limitations on the scope of protection disclosed in this application. In the absence of contradiction, each step in a certain embodiment or example in this application can be implemented as an independent example, and the steps can be arbitrarily combined. For example, the solution after removing some steps in a certain embodiment or example can also be implemented as an independent example, and the order of the steps in a certain embodiment or example can be arbitrarily exchanged. In addition, the optional methods or optional examples in a certain embodiment or example can be arbitrarily combined; in addition, the various embodiments or examples can be arbitrarily combined. For example, some or all of the steps in different embodiments or examples can be arbitrarily combined, and a certain embodiment or example can be arbitrarily combined with the optional methods or optional examples of other embodiments or examples.

[0089] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0090] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0092] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0093] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0094] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0095] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A financial product recommendation method based on public accounts, characterized in that: include: With user authorization, obtain business transaction data between L public accounts, where L is an integer greater than 2; Based on the business transaction data, M public accounts with fund association are selected from the L public accounts to form an account set, where M is an integer greater than 2 and less than or equal to L; Selecting a public account from the account set as the target account; Based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from N financial products, where N is an integer greater than 1.

2. The method according to claim 1, characterized in that According to the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from N financial products, including: Using the product feature of the financial product purchased by the target account as the first product feature; Using the product characteristics of the financial product purchased by the other account as the second product characteristics; Detecting the amount of funds transferred between the other accounts and the target account and the frequency of fund transactions; Setting a corresponding weight for the second product feature based on the amount of funds transferred between the other account and the target account and the frequency of fund transactions; generating a feature matrix according to the first product feature, the second product feature, and the weights corresponding to the second product feature; A target financial product recommended to the target account is obtained by screening N financial products according to the feature matrix.

3. The method according to claim 2, characterized in that The amount of fund transactions between any one of the accounts in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account; the frequency of fund transactions between any one of the accounts in the account set and the target account is positively correlated with the weight corresponding to the product feature of the account.

4. The method according to claim 2, characterized in that A target financial product recommended to the target account is obtained by screening N financial products according to the feature matrix, including: Detecting the similarity between the feature matrix and the product feature vectors of the N financial products to obtain a similarity matrix; wherein each element in the similarity matrix represents the similarity between the feature matrix and the product feature vector of a financial product; Determining, based on the similarity matrix, financial products whose similarity to the feature matrix is ​​greater than or equal to a similarity threshold as a set of candidate financial products; A preset number of financial products are selected from the candidate financial product set in descending order of similarity to the feature matrix as the target financial products.

5. The method according to claim 4, characterized in that After selecting a preset number of financial products from the candidate financial product set as the target financial products in descending order of similarity to the feature matrix, the method further includes: Obtaining the liquidity characteristics of the target account; The preset number of target financial products are recommended and ranked according to the liquidity characteristics of the target account, wherein the more similar the liquidity characteristics of the target financial product are to the liquidity characteristics of the target account, the higher the recommended ranking of the target financial product.

6. The method according to claim 1, wherein According to the financial products purchased by the target account and the financial products purchased by other accounts in the account set except the target account, a target financial product recommended to the target account is screened from N financial products, including: determining the transaction behavior preference characteristics of the target account based on the transaction behavior data of the target account; Screening out a first category of accounts from the account set based on the transaction behavior preference characteristics of the target account, wherein the transaction behavior preference characteristics of the first category of accounts and the transaction behavior preference characteristics of the target account have a similarity greater than a preset similarity; According to the financial products purchased by the target account and the financial products purchased by the first category of accounts, a target financial product recommended to the target account is screened from N financial products.

7. The method according to claim 6, characterized in that Determining the transaction behavior preference characteristics of the target account based on the transaction behavior data of the target account includes: Performing time series analysis on the target account's financial management behavior data to obtain the time characteristics, transaction frequency characteristics, and transaction amount characteristics corresponding to when the target account completes the financial management behavior; The time feature, transaction frequency feature, and transaction amount feature are used as the transaction behavior preference features of the target account.

8. A financial product recommendation device based on public accounts, characterized in that: include: An acquisition unit, configured to acquire business transaction data between L public accounts with user authorization, where L is an integer greater than 2; a screening unit, configured to screen, based on the business transaction data, M public accounts with fund association from the L public accounts to form an account set, where M is an integer greater than 2 and less than or equal to L; a selection unit, configured to select a public account from the account set as a target account; a processing unit, configured to filter, based on the financial products purchased by the target account and the financial products purchased by other accounts in the account set other than the target account, a target financial product recommended to the target account from N financial products, where N is an integer greater than 1.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the financial product recommendation method based on the corporate account according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the financial product recommendation method based on corporate accounts as described in any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the financial product recommendation method based on a public account according to any one of claims 1 to 7.

Images