Method, device, storage medium and electronic equipment for recommending financial products

Abstract

The application discloses a financial product recommendation method and device, a storage medium and an electronic device. It relates to the field of artificial intelligence. The method comprises the following steps: obtaining a consumption record set of all customers in a target database, and dividing all customers into a plurality of customer groups based on the consumption record set; obtaining target interest feature information and target consumption records of a current customer, and determining a target customer group to which the current customer belongs according to the target consumption records of the current customer; calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, and obtaining a set of interest feature similarities; determining a target interest feature group of the current customer based on the set of interest feature similarities; determining a target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer. Through the application, the problem of low success rate of recommending financial products in the related art is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence, in particular to a financial product recommendation method and device, a storage medium and an electronic device. BACKGROUND

[0002] In related technologies, various financial institutions constantly innovate to find new credit card users, and recommending credit cards to users is an important task for business personnel. However, business personnel basically recommend products by asking customers and publishing relevant information on social software, and the success rate of recommendation is low.

[0003] In view of the low success rate of recommending financial products in related technologies, an effective solution has not yet been proposed. SUMMARY

[0004] The main purpose of the present application is to provide a financial product recommendation method, device, storage medium and electronic device to solve the problem of low success rate of recommending financial products in related technologies.

[0005] In order to achieve the above purpose, according to one aspect of the present application, a financial product recommendation method is provided. The method comprises: obtaining a consumption record set of all customers in a target database, and dividing all customers into a plurality of customer groups based on the consumption record set; obtaining target interest feature information and target consumption records of a current customer, and determining a target customer group to which the current customer belongs according to the target consumption records of the current customer; calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, to obtain a set of interest feature similarities; determining a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group; determining a target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer.

[0006] Optionally, dividing all customers into a plurality of customer groups based on the consumption record set comprises: determining the number of consumptions in a preset time period in the consumption records of each customer; determining whether the number of consumptions is greater than or equal to a first preset number of consumptions, and in the case that the number of consumptions is less than the first preset number of consumptions, dividing the customer into a first customer group; in the case that the number of consumptions is greater than or equal to the first preset number of consumptions, determining whether the number of consumptions is greater than or equal to a second preset number of consumptions, wherein the second preset number of consumptions is greater than or equal to the first preset number of consumptions; in the case that the number of consumptions is less than the second preset number of consumptions, dividing the customer into a second customer group; in the case that the number of consumptions is greater than or equal to the second preset number of consumptions, dividing the customer into a third customer group.

[0007] Optionally, before calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, the method further comprises: receiving a questionnaire result of each target customer in the target customer group, and obtaining the interest feature information of each target customer based on the questionnaire result.

[0008] Optionally, calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information comprises: determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target customer to obtain a second interest feature set; determining the number of interest features in the intersection of the first interest feature set and the second interest feature set to obtain a first interest feature number; determining the number of interest features in the union of the first interest feature set and the second interest feature set to obtain a second interest feature number; and calculating the ratio of the first interest feature number and the second interest feature number to obtain the interest feature similarity between the current customer and the target customer.

[0009] Optionally, determining the target interest feature group of the current customer based on the group of interest feature similarities comprises: determining a plurality of interest feature groups in the target customer group, and determining a group of target feature customers contained in each interest feature group; calculating the sum of the interest feature similarities between the current customer and all target feature customers in each interest feature group to obtain a similarity accumulation value of each interest feature group; calculating the sum of the interest feature similarities between the current customer and all customers in the target customer group to obtain a total interest feature similarity accumulation value of the target customer group; calculating the ratio of the similarity accumulation value of each interest feature group and the total interest feature similarity accumulation value to obtain a group of target probabilities that the current customer belongs to each interest feature group; determining the maximum target probability value in the group of target probabilities, and determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0010] Optionally, before determining the interest feature group corresponding to the maximum target probability value as the target interest feature group, the method further comprises: calculating the sum of all target probability values in the group of target probabilities to obtain a total probability value; determining whether the total probability value is greater than or equal to a preset probability value; in the case that the total probability value is less than the preset probability value, establishing a new interest feature group and determining the new interest feature group as the target interest feature group; in the case that the total probability value is greater than or equal to the preset probability value, performing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0011] Optionally, determining the target financial product according to the target interest feature group and the target customer group comprises: determining a type of financial products corresponding to the target interest feature group; determining a consumption frequency range of the target customer group, and screening the target financial product from the type of financial products based on the consumption frequency range.

[0012] To achieve the above object, according to another aspect of the present application, a financial product recommendation device is provided. The device comprises: a first acquisition unit configured to acquire a consumption record set of all customers in a target database, and divide all customers into a plurality of customer groups based on the consumption record set; a second acquisition unit configured to acquire target interest feature information and target consumption record of a current customer, and determine a target customer group to which the current customer belongs according to the target consumption record of the current customer; a calculation unit configured to calculate interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, and obtain a set of interest feature similarities; a first determination unit configured to determine a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group; and a second determination unit configured to determine a target financial product according to the target interest feature group and the target customer group, and recommend the target financial product to the current customer.

[0013] By the present application, the following steps are adopted: acquiring a consumption record set of all customers in a target database, and dividing all customers into a plurality of customer groups based on the consumption record set; acquiring target interest feature information and target consumption record of a current customer, and determining a target customer group to which the current customer belongs according to the target consumption record of the current customer; calculating interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, and obtaining a set of interest feature similarities; determining a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group; and determining a target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer. The problem of low success rate of recommending financial products in the related art is solved. By calculating interest feature similarity between the current customer and customers in different interest feature groups, the interest feature group to which the current customer belongs is determined, and a financial product is recommended to the current customer based on the target interest feature group to which the current customer belongs and the target customer group, thereby achieving the effect of improving the success rate of product recommendation. BRIEF DESCRIPTION OF DRAWINGS

[0014] The accompanying drawings, which form a part of the present application, are intended to provide further understanding of the present application, and are used to interpret the illustrative embodiments of the present application and their descriptions, and are not intended to be an improper limitation of the present application. In the drawings:

[0015] Figure 1 is a flowchart of a financial product recommendation method provided according to an embodiment of the present application;

[0016] Figure 2is a flowchart of a method for calculating interest feature similarity according to an embodiment of the present application;

[0017] Figure 3 is a schematic diagram of a device for recommending a financial product according to an embodiment of the present application;

[0018] Figure 4 is a schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0019] It should be noted that the embodiments and features of the present application can be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0020] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0021] 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 do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0022] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for display, analyzed data, etc.) involved in the present disclosure are all information and data authorized by the user or authorized by all parties.

[0023] The present application will be described below in combination with preferred implementation steps, Figure 1 is a flowchart of a method for recommending a financial product according to an embodiment of the present application, as Figure 1 shown, the method comprises the following steps:

[0024] Step S101, obtain a consumption record set of all customers in the target database, and divide all customers into a plurality of customer groups based on the consumption record set.

[0025] Specifically, the target database can be a database of a financial institution, and the consumption records of customers are derived from the target database, and all customers are divided into three customer groups of "frequent consumption", "normal consumption" and "low-frequency consumption" according to the consumption records.

[0026] Step S102, obtaining target interest feature information and target consumption record of the current customer, and determining the target customer group to which the current customer belongs according to the target consumption record of the current customer.

[0027] Specifically, the interest feature information can be obtained according to the survey questionnaire, and the questionnaire can be designed for the type of financial product to be recommended, such as a credit card, and the unique selling points of the credit card are extracted, for example, when a star credit card, a car credit card, and an ancient architecture credit card are needed, the questions in the questionnaire can be set as "whether interested in star", "whether have a car", "whether interested in ancient architecture", etc. In this way, the interest feature information is obtained by the user to handle the relevant questionnaire survey, and the target consumption record of the current customer is obtained, and the number of consumptions in the preset time period in the target consumption record is used to determine which target customer group the current customer belongs to among "frequent consumption", "normal consumption" and "low-frequency consumption".

[0028] Step S103, calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, to obtain a set of interest feature similarities.

[0029] Specifically, the interest feature similarity is calculated by the number of interest features in the intersection and union of the interest features of the current customer and the target customer, so as to obtain a set of interest feature similarities between the current customer and each target customer in the target customer group.

[0030] Step S104, determining a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group.

[0031] Specifically, the probability of the current customer belonging to each interest feature group is calculated according to the set of interest feature similarities, and the interest feature group with the maximum probability is determined as the target interest feature group.

[0032] Step S105, determining the target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer.

[0033] Specifically, after determining the target customer group and the target interest feature group of the current customer, a product recommendation group of the current customer is determined, for example, the generated product recommendation group can include: a "frequent consumption, interested in constellations" group, a "frequent consumption, interested in ancient buildings" group, a "frequent consumption, with a car" group, a "normal consumption, interested in constellations" group, a "normal consumption, interested in ancient buildings" group, a "normal consumption, with a car" group, a "low-frequency consumption, interested in constellations" group, a "low-frequency consumption, interested in ancient buildings" group, a "low-frequency consumption, with a car" group, and the like. Different product recommendation scripts are adopted for the product recommendation groups with different labels for recommendation, and a target financial product corresponding to the product recommendation group is selected for recommendation, so as to improve the success rate of product recommendation.

[0034] The method for recommending a financial product provided in the embodiments of the present application comprises the following steps: obtaining a consumption record set of all customers in a target database, and dividing all customers into a plurality of customer groups based on the consumption record set; obtaining target interest feature information and target consumption records of a current customer, and determining a target customer group to which the current customer belongs according to the target consumption records of the current customer; calculating interest feature similarities between the current customer and each target customer in the target customer group based on the target interest feature information, to obtain a set of interest feature similarities; determining a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group; determining a target financial product according to the target interest feature group and the target customer group, and recommending the target financial product to the current customer, thereby solving the problem of low success rate of recommending a financial product in the related art. The interest feature similarities between the current customer and customers with different interest feature groups are calculated to determine the interest feature group to which the current customer belongs, and a financial product is recommended to the current customer based on the target interest feature group and the target customer group to which the current customer belongs, thereby achieving the effect of improving the success rate of product recommendation.

[0035] Before product recommendation, it is necessary to determine the target customer group to which the current customer belongs. In the method for recommending a financial product provided in the embodiments of the present application, dividing all customers into a plurality of customer groups based on the consumption record set comprises the following steps: determining the number of consumptions in a preset time period in the consumption records of each customer; determining whether the number of consumptions is greater than or equal to a first preset number of consumptions, and in the case that the number of consumptions is less than the first preset number of consumptions, dividing the customer into a first customer group; in the case that the number of consumptions is greater than or equal to the first preset number of consumptions, determining whether the number of consumptions is greater than or equal to a second preset number of consumptions, wherein the second preset number of consumptions is greater than or equal to the first preset number of consumptions; in the case that the number of consumptions is less than the second preset number of consumptions, dividing the customer into a second customer group; and in the case that the number of consumptions is greater than or equal to the second preset number of consumptions, dividing the customer into a third customer group.

[0036] Specifically, the preset time period can be one month, the consumption frequency refers to the number of times that the customer purchases products at the financial institution, the first preset consumption frequency can be ten times, and the second preset consumption frequency can be twenty times. If the number of times of consumption of the current customer in the consumption record in one month is less than ten times, the target customer group to which the current customer belongs is low-frequency consumption. If the number of times of consumption of the current customer in the consumption record in one month is greater than or equal to ten times and less than or equal to twenty times, the target customer group to which the current customer belongs is normal consumption. If the number of times of consumption of the current customer in the consumption record in one month is greater than or equal to twenty times, the target customer group to which the current customer belongs is high-frequency consumption. By determining the target customer group to which the current customer belongs, initial data for determining the product recommendation group of the current customer is obtained.

[0037] To determine the target interest feature group of the target customer, interest feature information of the target customer needs to be obtained. Optionally, in the method for recommending a financial product provided in the embodiments of the present application, before calculating the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, the method further includes: receiving a questionnaire result of each target customer in the target customer group, and obtaining the interest feature information of each target customer based on the questionnaire result.

[0038] Specifically, the interest feature information of the target customer is generally obtained through a questionnaire survey. According to the questionnaire result filled in by the target customer, the interest feature information of the target customer is obtained. For example, the questionnaire can be designed as questions such as “whether to have a vehicle”, “whether to like ancient buildings”, “whether to like constellations”, and the like, so as to obtain the specific interest features of the target user. By obtaining the interest feature information of the target customer, different interest feature groups are divided for the target customer.

[0039] After the interest feature group of the target customer is determined, the interest feature similarity between the current customer and each target customer in the target customer group needs to be calculated. Optionally, Figure 2 is a flowchart of the method for calculating the interest feature similarity according to the embodiments of the present application, as shown in Figure 2As shown, in the financial product recommendation method provided by the embodiments of the present application, the calculation of the interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information comprises: step S201, determining a plurality of interest features in the target interest feature information to obtain a first interest feature set, and determining a plurality of interest features in the interest feature information of each target customer to obtain a second interest feature set; step S202, determining the number of interest features in the intersection of the first interest feature set and the second interest feature set to obtain a first interest feature number; step S203, determining the number of interest features in the union of the first interest feature set and the second interest feature set to obtain a second interest feature number; and step S204, calculating the ratio of the first interest feature number to the second interest feature number to obtain the interest feature similarity between the current customer and the target customer.

[0040] Specifically, the target interest feature information refers to the interest feature information of the current customer. For example, the target customer group of the current customer is low-frequency consumption, and each interest feature group contained in the low-frequency consumption is determined, such as an interest feature group of liking cars, an interest feature group of liking ancient buildings, an interest feature group of liking constellations, etc. The interest features of the current customer include liking ancient buildings and loving sports, etc. The first interest feature set includes two interest features of liking ancient buildings and loving sports, target customer A likes constellations and cars, and target customer B likes ancient buildings and tourism. The interest feature similarity between each target customer and the current customer is calculated by the Jaccard similarity coefficient, for example, the first interest feature number of target customer A and the current customer is 0, and the second interest feature number is 4, so the interest feature similarity between target customer A and the current customer is 0 divided by 4, which is 0. Similarly, the interest feature similarity between target customer B and the current customer is 1 divided by 3, which is 0.3. The interest feature similarity between the current customer and each target customer in the target customer group is calculated, and then the target interest feature group to which the current customer belongs is determined.

[0041] It should be noted that the calculation method of the Jaccard similarity coefficient is that, assuming that there are n customers at present, the customer set is represented as U={u1,…,u i ,…,u n}, each customer has interest features, the interest features of customer u1 are defined as I u1 , the interest features of customer u2 are defined as I u2 , and the Jaccard similarity formula can be used to obtain the interest feature similarity between the two customers as follows:

[0042]

[0043] I(u1,u2)∈[0,1]

[0044] After calculating the similarity of interest features between each target customer in the target customer group and the current customer, the probability that the current customer belongs to each interest feature group is calculated. Optionally, in the recommendation method for financial products provided in this application embodiment, determining the target interest feature group of the current customer based on a set of interest feature similarities includes: determining multiple interest feature groups in the target customer group, and determining a set of target feature customers included in each interest feature group; calculating the sum of the interest feature similarities between the current customer and all target feature customers in each interest feature group to obtain the cumulative similarity value of each interest feature group; calculating the sum of the interest feature similarities between the current customer and all customers in the target customer group to obtain the cumulative total interest feature similarity value of the target customer group; calculating the ratio of the cumulative similarity value of each interest feature group to the cumulative total interest feature similarity value to obtain a set of target probabilities for the current customer to belong to each interest feature group; determining the maximum target probability value in a set of target probabilities, and determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0045] Specifically, multiple interest feature groups are represented as G = {g1, ..., g...} a ,…,g A The similarity of interest features among customers determines whether a current customer can join a corresponding interest feature group. It is unknown which interest feature group a current customer u1 can join. There are two possibilities for the current customer: the first possibility is that customer u1 will join an existing interest feature group, such as interest feature group g1, g2, g3, g4, g5, g6, g7, g8, g9, g1, g1, g1, g1, g1, g1, g1, g2 ... a The first possibility is that the current customer u1 forms a new interest feature group, because the interest features of the existing interest feature group are the same as those of the current customer. The second possibility is that the current customer u1 forms a new interest feature group. Since the other customers already in the interest feature group have different interest features from the current customer, the probability of the current customer joining an existing interest feature group or forming a new interest feature group is:

[0046]

[0047] Where P(u1,α) represents the probability that the current customer belongs to a set of target groups for each interest feature group. This represents the cumulative similarity of the total interest characteristics between the current customer u1 and all target customers in the target customer group. This represents the cumulative similarity between the current customer u1 and all target customers in the interest feature group ga. α is a parameter of this algorithm, which determines the dispersion of the interest feature group formation. By calculating the probability that the current customer belongs to each interest feature group, the interest feature group with the highest probability is selected as the target interest feature group.

[0048] Optionally, in the method for recommending a financial product provided in the embodiments of the present application, before the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group, the method further comprises: calculating the sum of all target probability values in the group of target probabilities to obtain a total probability value; determining whether the total probability value is greater than or equal to a preset probability value; in the case that the total probability value is less than the preset probability value, establishing a new interest feature group and determining the new interest feature group as the target interest feature group; and in the case that the total probability value is greater than or equal to the preset probability value, performing the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0049] Specifically, the preset probability value can be 0.5, and in the case that the sum of the probabilities of the current customer belonging to each existing interest feature group, i.e., the total probability value, is less than 0.5, it is indicated that the current customer does not belong to any of the existing interest feature groups, and the target interest feature group is a new interest feature group. By determining the target interest feature group of the current customer as a new feature group when the total probability value is less than the preset probability value, the division of the target interest feature group is ensured to be more accurate.

[0050] Optionally, in the method for recommending a financial product provided in the embodiments of the present application, determining the target financial product according to the target interest feature group and the target customer group comprises: determining a type of financial products corresponding to the target interest feature group; determining the consumption frequency range of the target customer group, and screening the target financial product from the type of financial products based on the consumption frequency range.

[0051] For example, the target interest feature group is an interest feature group of liking constellations, a type of financial products is determined from a plurality of financial products, the type of financial products can be credit cards of different amounts associated with constellations, and then the final recommended target financial product is determined based on the consumption frequency range of the target customer group, for example, the target customer group is a low-frequency consumer, and a credit card with a smaller amount is selected as the target financial product from the type of credit cards associated with constellations. By screening the target financial product from the type of financial products, the target financial product is matched with the current customer, and thus the success rate of product recommendation is improved.

[0052] 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 group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0053] The embodiments of the present application also provide a device for recommending a financial product. It should be noted that the device for recommending a financial product provided in the embodiments of the present application can be used to execute the method for recommending a financial product provided in the embodiments of the present application. The device for recommending a financial product provided in the embodiments of the present application is introduced as follows.

[0054] Figure 3 is a schematic diagram of a device for recommending a financial product according to an embodiment of the present application. As shown in the figure, the device comprises: Figure 3

[0055] a first obtaining unit 10, configured to obtain a consumption record set of all customers in a target database, and divide all customers into a plurality of customer groups based on the consumption record set;

[0056] a second obtaining unit 20, configured to obtain target interest feature information and target consumption records of a current customer, and determine a target customer group to which the current customer belongs according to the target consumption records of the current customer;

[0057] a calculating unit 30, configured to calculate interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, and obtain a set of interest feature similarities;

[0058] a first determining unit 40, configured to determine a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group;

[0059] a second determining unit 50, configured to determine a target financial product according to the target interest feature group and the target customer group, and recommend the target financial product to the current customer.

[0060] ​The financial product recommendation device provided in the embodiments of the present application comprises: a first obtaining unit 10, configured to obtain a consumption record set of all customers in a target database, and divide all customers into a plurality of customer groups based on the consumption record set; a second obtaining unit 20, configured to obtain target interest feature information and target consumption records of a current customer, and determine a target customer group to which the current customer belongs according to the target consumption records of the current customer; a calculation unit 30, configured to calculate interest feature similarity between the current customer and each target customer in the target customer group based on the target interest feature information, and obtain a set of interest feature similarities; a first determination unit 40, configured to determine a target interest feature group of the current customer based on the set of interest feature similarities, wherein the target interest feature group is an interest feature group in the target customer group; and a second determination unit 50, configured to determine a target financial product according to the target interest feature group and the target customer group, and recommend the target financial product to the current customer, thereby solving the problem of low success rate of recommending financial products in the related art, calculating interest feature similarity between the current customer and customers with different interest feature groups, determining an interest feature group to which the current customer belongs, and recommending a financial product to the current customer based on the target interest feature group to which the current customer belongs and the target customer group, thereby achieving the effect of improving the success rate of product recommendation.

[0061] Optionally, in the financial product recommendation device provided in the embodiments of the present application, the first obtaining unit 10 comprises: a first determination module, configured to determine a consumption frequency of each customer in a preset time period in the consumption records of the customer; a first judgment module, configured to judge whether the consumption frequency is greater than or equal to a first preset consumption frequency, and divide the customer into a first customer group in a case where the consumption frequency is less than the first preset consumption frequency; a second judgment module, configured to judge whether the consumption frequency is greater than or equal to a second preset consumption frequency in a case where the consumption frequency is greater than or equal to the first preset consumption frequency, wherein the second preset consumption frequency is greater than or equal to the first preset consumption frequency; a first division module, configured to divide the customer into a second customer group in a case where the consumption frequency is less than the second preset consumption frequency; and a second division module, configured to divide the customer into a third customer group in a case where the consumption frequency is greater than or equal to the second preset consumption frequency.

[0062] Optionally, in the financial product recommendation device provided in the embodiments of the present application, the device further comprises a receiving unit, configured to receive a questionnaire result of each target customer in the target customer group, and obtain interest feature information of each target customer based on the questionnaire result.

[0063] Optionally, in the financial product recommendation apparatus provided by the embodiment of the present application, the calculation unit 30 comprises: a second determination module, configured to determine a plurality of interest features in the target interest feature information, to obtain a first interest feature set, and to determine a plurality of interest features in the interest feature information of each target customer, to obtain a second interest feature set; a third determination module, configured to determine the number of interest features in the intersection of the first interest feature set and the second interest feature set, to obtain a first interest feature number; a fourth determination module, configured to determine the number of interest features in the union of the first interest feature set and the second interest feature set, to obtain a second interest feature number; and a first calculation module, configured to calculate the ratio of the first interest feature number and the second interest feature number, to obtain the interest feature similarity between the current customer and the target customer.

[0064] Optionally, in the financial product recommendation apparatus provided by the embodiment of the present application, the first determination unit 40 comprises: a fifth determination module, configured to determine a plurality of interest feature groups in the target customer group, and to determine a group of target feature customers contained in each interest feature group; a second calculation module, configured to calculate the sum of the interest feature similarities between the current customer and all target feature customers in each interest feature group, to obtain a similarity accumulation value of each interest feature group; a third calculation module, configured to calculate the sum of the interest feature similarities between the current customer and all customers in the target customer group, to obtain a total interest feature similarity accumulation value of the target customer group; a fourth calculation module, configured to calculate the ratio of the similarity accumulation value of each interest feature group and the total interest feature similarity accumulation value, to obtain a group of target probabilities that the current customer belongs to each interest feature group; and a sixth determination module, configured to determine the maximum target probability value in the group of target probabilities, and to determine the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0065] Optionally, in the financial product recommendation apparatus provided by the embodiment of the present application, the apparatus further comprises: a probability value calculation unit, configured to calculate the sum of all target probability values in the group of target probabilities, to obtain a total probability value; a judgment unit, configured to judge whether the total probability value is greater than or equal to a preset probability value; a establishing unit, configured to, in the case that the total probability value is less than the preset probability value, establish a new interest feature group, and to determine the new interest feature group as the target interest feature group; and an execution unit, configured to, in the case that the total probability value is greater than or equal to the preset probability value, execute the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group.

[0066] Optionally, in the financial product recommendation apparatus provided by the embodiment of the present application, the second determination unit 50 comprises: a seventh determination module, configured to determine a type of financial products corresponding to the target interest feature group; and an eighth determination module, configured to determine the consumption frequency range of the target customer group, and to filter target financial products from the type of financial products based on the consumption frequency range.

[0067] The recommendation device of the financial product comprises a processor and a memory, the first acquisition unit 10, the second acquisition unit 20, the calculation unit 30, the first determination unit 40 and the second determination unit 50 are stored in the memory as program units, and the corresponding functions are realized by executing the program units stored in the memory by the processor.

[0068] The processor comprises a core, and the core calls the corresponding program units in the memory. The core can be one or more, and the product recommendation success rate can be improved by adjusting the core parameters.

[0069] The memory can comprise a non-permanent memory in a computer readable medium, a random access memory (RAM) and / or a non-volatile memory such as a read-only memory (ROM) or a flash memory (flash RAM), and the memory comprises at least one memory chip.

[0070] The embodiment of the application provides a computer readable storage medium, which stores a program, and the program is executed by a processor to realize the recommendation method of the financial product.

[0071] The embodiment of the application provides a processor, which is used for running a program, and the program is executed to realize the recommendation method of the financial product.

[0072] Figure 4 It is a schematic diagram of an electronic device provided by the embodiment of the application. As shown in the figure, Figure 4 The device 401 comprises a processor, a memory and a program stored in the memory and capable of running on the processor, and the processor realizes the following steps when executing the program: the recommendation method of the financial product. The device in the present application can be a server, a PC, a PAD, a mobile phone and the like.

[0073] The application further provides a computer program product, which is suitable for executing the program of the following method steps: the recommendation method of the financial product when executed on a data processing device.

[0074] Those skilled in the art should understand that the embodiments of the application can be provided as a method, a system or a computer program product. Therefore, the application can be in the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the application can be in the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program codes.

[0075] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0076] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0077] The computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 one or more flow or blocks Figure 1 means for functionally implementing the steps listed in the flowchart block or blocks.

[0078] In one typical configuration, the computing device includes one or more processors (CPU's), input / output interfaces, network interfaces, and memory.

[0079] The memory can include non-persistent memory and / or persistent memory, for example, read only memory (ROM) and / or flash memory, for example, in the form of a computer readable storage medium. The memory is an example of computer readable media.

[0080] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0081] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover non-exclusive inclusions, such that a process, method, article or apparatus that comprises a list of elements does not only include those elements, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, the element defined by the phrase "comprising a" does not exclude the presence of additional identical elements in the process, method, article or apparatus that includes the element.

[0082] Those skilled in the art will appreciate that embodiments of the present application can be provided as a method, system or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) containing computer usable program code.

[0083] The above merely provides embodiments of the present application and is not intended to limit the present application. Various modifications and changes can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the scope of the claims of the present application.

Claims

1. A method for recommending financial products, characterized in that, include: Obtain the set of consumption records for all customers in the target database, and divide all customers into multiple customer groups based on the set of consumption records; Obtain the target interest characteristics and target consumption records of the current customer, and determine the target customer group to which the current customer belongs based on the target consumption records of the current customer; Based on the target interest feature information, the similarity of the interest features between the current customer and each target customer in the target customer group is calculated to obtain a set of interest feature similarities; The target interest feature group of the current customer is determined based on the similarity of the set of interest features, wherein the target interest feature group is the interest feature group in the target customer group; Based on the target interest feature group and the target customer group, a target financial product is determined, and the target financial product is recommended to the current customer. Based on the aforementioned collection of purchase records, all customers are divided into multiple customer groups, including: Determine the number of transactions within a preset time period in each customer's consumption records, wherein the number of transactions refers to the number of times the customer purchases products from the financial institution; Determine whether the number of transactions is greater than or equal to a first preset number of transactions. If the number of transactions is less than the first preset number of transactions, classify the customer into a first customer group. If the number of transactions is greater than or equal to the first preset number of transactions, it is determined whether the number of transactions is greater than or equal to the second preset number of transactions, wherein the second preset number of transactions is greater than or equal to the first preset number of transactions; If the number of transactions is less than the second preset number of transactions, the customer is classified into a second customer group. If the number of transactions is greater than or equal to the second preset number of transactions, the customer will be classified into a third customer group.

2. The method according to claim 1, characterized in that, Before calculating the similarity of interest features between the current customer and each target customer in the target customer group based on the target interest feature information, the method further includes: Receive the questionnaire results of each target customer in the target customer group, and obtain the interest characteristic information of each target customer based on the questionnaire results.

3. The method according to claim 1, characterized in that, Calculating the similarity of interest features between the current customer and each target customer in the target customer group based on the target interest feature information includes: Multiple interest features are determined in the target interest feature information to obtain a first interest feature set, and multiple interest features are determined in the interest feature information of each target customer to obtain a second interest feature set; The number of interest features in the intersection of the first interest feature set and the second interest feature set is determined to obtain the number of the first interest features; The number of interest features in the union of the first interest feature set and the second interest feature set is determined to obtain the number of second interest features; The ratio of the number of the first interest features to the number of the second interest features is calculated to obtain the similarity of interest features between the current customer and the target customer.

4. The method according to claim 1, characterized in that, Determining the target interest feature group of the current customer based on the aforementioned set of interest feature similarities includes: Identify multiple interest feature groups within the target customer group, and determine a set of target feature customers included in each interest feature group; Calculate the sum of the similarity of the current customer with the interest features of all target customers in each interest feature group to obtain the cumulative similarity value of each interest feature group; Calculate the sum of the similarity of the interest features between the current customer and all customers in the target customer group to obtain the total cumulative value of the similarity of the interest features of the target customer group; Calculate the ratio of the cumulative similarity value of each interest feature group to the cumulative similarity value of the total interest features, and obtain the target probability that the current customer belongs to each interest feature group. Determine the maximum target probability value in the set of target probabilities, and determine the interest feature group corresponding to the maximum target probability value as the target interest feature group.

5. The method according to claim 4, characterized in that, Before determining the interest feature group corresponding to the maximum target probability value as the target interest feature group, the method further includes: Calculate the sum of all target probability values ​​in the set of target probabilities to obtain the total probability value; Determine whether the total probability value is greater than or equal to a preset probability value; If the total probability value is less than the preset probability value, a new interest feature group is established, and the new interest feature group is determined as the target interest feature group. If the total probability value is greater than or equal to the preset probability value, the step of determining the interest feature group corresponding to the maximum target probability value as the target interest feature group is executed.

6. The method according to claim 1, characterized in that, Determining target financial products based on the target interest feature groups and the target customer groups includes: Identify a type of financial product that corresponds to the target interest feature group; Determine the consumption frequency range of the target customer group, and select the target financial products from the category of financial products based on the consumption frequency range.

7. A device for recommending financial products, characterized in that, include: The first acquisition unit is used to acquire a set of consumption records of all customers in the target database, and to divide all customers into multiple customer groups based on the set of consumption records; The second acquisition unit is used to acquire the target interest characteristics information and target consumption records of the current customer, and determine the target customer group to which the current customer belongs based on the target consumption records of the current customer; The calculation unit is used to calculate the similarity of the interest features between the current customer and each target customer in the target customer group based on the target interest feature information, so as to obtain a set of interest feature similarities; The first determining unit is configured to determine the target interest feature group of the current customer based on the similarity of the set of interest features, wherein the target interest feature group is the interest feature group in the target customer group; The second determining unit is used to determine the target financial product based on the target interest feature group and the target customer group, and recommend the target financial product to the current customer. The first acquisition unit includes: a first determining module, used to determine the number of transactions within a preset time period in each customer's consumption records, wherein the number of transactions is the number of times the customer purchases products from a financial institution; a first judging module, used to judge whether the number of transactions is greater than or equal to a first preset number of transactions, and if the number of transactions is less than the first preset number of transactions, classifying the customer into a first customer group; a second judging module, used to judge whether the number of transactions is greater than or equal to a second preset number of transactions if the number of transactions is greater than or equal to the first preset number of transactions, wherein the second preset number of transactions is greater than or equal to the first preset number of transactions; a first dividing module, used to classify the customer into a second customer group if the number of transactions is less than the second preset number of transactions; and a second dividing module, used to classify the customer into a third customer group if the number of transactions is greater than or equal to the second preset number of transactions.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the non-volatile storage medium resides to perform the method for recommending the financial product as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, It 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 the one or more processors, the one or more processors cause the one or more processors to implement the method of recommending the financial product according to any one of claims 1 to 6.

Images