CN116542747A - Product recommendation method and device, storage medium and electronic equipment - Google Patents
Product recommendation method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116542747A CN116542747A CN202310644139.9A CN202310644139A CN116542747A CN 116542747 A CN116542747 A CN 116542747A CN 202310644139 A CN202310644139 A CN 202310644139A CN 116542747 A CN116542747 A CN 116542747A
- Authority
- CN
- China
- Prior art keywords
- product
- preference
- products
- evaluation value
- financial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000011156 evaluation Methods 0.000 claims abstract description 300
- 230000006399 behavior Effects 0.000 claims description 62
- 238000013507 mapping Methods 0.000 claims description 30
- 238000005516 engineering process Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 12
- 238000004590 computer program Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a product recommendation method, a product recommendation device, a storage medium and electronic equipment. Relates to the field of financial science and technology and other related technical fields, and the method comprises the following steps: acquiring a preference product of a target user, preference evaluation values of the preference product and M financial products to be recommended; determining a preference evaluation value list, and calculating the similarity between the preference product and the financial product to obtain a group of similarity; determining products to be recommended corresponding to the first quantity of similarity to obtain a first product set; acquiring a financial product transaction record of a target user in a preset period, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set; a first number of a set of target products is determined from the set of target products and the set of target products is recommended to the target user. According to the method and the device, the problem that the matching degree of the recommended product and the user requirement in the related technology is low is solved.
Description
Technical Field
The present disclosure relates to the field of financial science and technology and other related technical fields, and in particular, to a product recommendation method, device, storage medium and electronic equipment.
Background
In the related art, when a financial institution recommends a financial product to a user, it is necessary to consider the intention of the customer. Recommending proper financial products for the client in the application scene required by the client is an important subject. The off-line channel recommends financial products to the clients in a manual recommending mode, namely, a client manager recommends financial products for the clients, the client manager manually screens financial products suitable for the clients based on the mastered client information, and recommends the clients in a mode of off-line contact such as telephone.
However, online and offline channels recommend financial products, the online and offline channels are mainly recommended to clients through client managers, and the recommendation is generally judged manually, and the manual recommendation easily causes deviation between the recommended financial products and the demands of users, so that accurate and personalized recommendation of the products to the clients cannot be realized.
Aiming at the problem of low matching degree between the recommended product and the user requirement in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The main objective of the present application is to provide a product recommendation method, device, storage medium and electronic apparatus, so as to solve the problem of low matching degree between a recommended product and a user's requirement in the related art.
In order to achieve the above object, according to one aspect of the present application, there is provided a product recommendation method. The method comprises the following steps: acquiring a preference product of a target user, preference evaluation values of the preference product and M financial products to be recommended; determining a preference evaluation value list of M financial products, and calculating the similarity between the preferred products and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation values of each user for each financial product; determining products to be recommended corresponding to a first quantity of similarity from a group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set; acquiring a financial product transaction record of a target user in a preset period, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set; a first number of a set of target products is determined from the set of target products based on the order of the transaction amount from the greater to the lesser and the set of target products is recommended to the target user, wherein the transaction amount is an amount required by the target user to purchase the financial products in the set of target products.
Optionally, obtaining the preference product of the target user includes: judging whether behavior data of the target user on M financial products is acquired or not, wherein the behavior data at least comprises one of the following steps: purchase times, browsing times and collection times; under the condition that the behavior data is acquired, calculating preference evaluation values of a target user on each financial product based on the behavior data to obtain a group of preference evaluation values; determining a maximum preference rating value from a set of preference ratings, determining a target financial product associated with the maximum preference rating value, and determining the target financial product as a preferred product.
Optionally, after determining whether behavior data of the target user on the M financial products is acquired, the method further includes: acquiring a user tag of a target user and determining a plurality of other users in the case that the behavior data is not acquired, wherein the other users are users which have the same user tag as the target user and have acquired the behavior data; determining preference products of each other user to obtain a preference product set; and determining the most preferred products in the preferred product set as the preferred products of the target user.
Optionally, in the case where the behavior data includes the purchase number, the browse number, and the collection number, calculating the preference evaluation value of the target user for each financial product based on the behavior data includes: determining a first weight of the purchase times, a second weight of the browsing times and a third weight of the collection times; determining the historical purchase times, the historical browsing times and the historical collection times of the target user on the current financial product; determining a first evaluation value corresponding to historical purchase times from an evaluation value mapping relation table based on the purchase times, determining a second evaluation value corresponding to historical browse times from the evaluation value mapping relation table based on the browse times, and determining a third evaluation value corresponding to historical collection times from the evaluation value mapping relation table based on the collection times, wherein the evaluation value mapping relation table comprises a first mapping relation between the purchase times and the evaluation values, a second mapping relation between the browse times and the evaluation values and a third mapping relation between the collection times and the evaluation values; calculating the product of the first weight and the first evaluation value to obtain a purchase number evaluation value, calculating the product of the second weight and the second evaluation value to obtain a browsing number evaluation value, and calculating the product of the third weight and the third evaluation value to obtain a collection number evaluation value; and calculating the sum of the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value to obtain a preference evaluation value.
Optionally, before calculating the similarity of the preferred product to each of the financial products based on the preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product, the method further includes: acquiring behavior data of all users in a target database, and determining preference evaluation values of each user on each financial product based on the behavior data; a preference evaluation value list is constructed based on the preference evaluation values of each user for each financial product.
Optionally, calculating the similarity of the preferred product to each of the financial products based on the preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product includes: calculating the average value of preference evaluation values of all users on the preference products to obtain the preference evaluation average value of the preference products; calculating the average value of preference evaluation values of all users on the financial products based on the preference evaluation value list to obtain the preference evaluation average value of the financial products; and calculating a cosine similarity coefficient based on the preference evaluation average value of the preference products, the preference evaluation average value of the financial products, the preference evaluation value of each user on the preference products and the preference evaluation value of each user on the financial products to obtain the similarity of the preference products and the financial products.
Optionally, extracting the second quantity of the historical transaction product from the financial product transaction record includes: determining N financial products contained in a financial product transaction record, and determining the transaction frequency and transaction amount of a target user for each financial product, wherein N is a positive integer; calculating the product of the transaction frequency and the fourth weight to obtain a transaction frequency evaluation value, and calculating the product of the transaction amount and the fifth weight to obtain a transaction amount evaluation value; calculating the sum of the transaction frequency evaluation value and the transaction amount evaluation value to obtain a transaction record evaluation value; and determining a second number of products from the N financial products according to the order of the transaction record evaluation values from large to small, and obtaining a second product set.
In order to achieve the above object, according to another aspect of the present application, there is provided a product recommendation device. The device comprises: a first acquiring unit configured to acquire a preference product of a target user, a preference evaluation value of the preference product, and M financial products to be recommended; the first determining unit is used for determining a preference evaluation value list of M financial products, and calculating the similarity between the preferred product and each financial product based on the preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation value of each user for each financial product; the second determining unit is used for determining products to be recommended corresponding to the first quantity of similarity from a group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set; the second acquisition unit is used for acquiring financial product transaction records in a preset period of a target user, extracting a second number of historical transaction products from the financial product transaction records to obtain a second product set, and combining the first product set and the second product set to obtain a target product set; and a third determining unit for determining a first number of a group of target products from the target product set based on the order of the transaction amount from the large to the small, and recommending the group of target products to the target user, wherein the transaction amount is an amount required by the target user to purchase the financial products in the target product set.
Through the application, the following steps are adopted: acquiring a preference product of a target user, preference evaluation values of the preference product and M financial products to be recommended; determining a preference evaluation value list of M financial products, and calculating the similarity between the preferred products and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation values of each user for each financial product; determining products to be recommended corresponding to a first quantity of similarity from a group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set; acquiring a financial product transaction record of a target user in a preset period, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set; and determining a first number of a group of target products from the target product set based on the order of the transaction amount from large to small, and recommending the group of target products to the target user, wherein the transaction amount is the amount required by the target user to purchase the financial products in the target product set, and the problem of low matching degree between the recommended products and the user requirements in the related technology is solved. A group of first product sets with higher similarity are screened out by calculating the similarity between the preferred products of the target user and the financial products to be recommended, the target product sets are comprehensively evaluated based on historical financial product transaction records of the target user, and the target user is recommended, so that the differentiated requirements of the user on the financial products are met. Thereby achieving the effect of improving the matching degree of the recommended product and the user requirement.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a product recommendation method provided according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a product recommendation system provided in accordance with an embodiment of the present application;
FIG. 3 is a flow chart of an alternative product recommendation method provided in accordance with an embodiment of the present application;
FIG. 4 is a schematic diagram of a product recommendation device provided according to an embodiment of the present application;
fig. 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
The invention will be described with reference to preferred implementation steps, and fig. 1 is a flowchart of a product recommendation method according to an embodiment of the present application, as shown in fig. 1, and the method includes the following steps:
Step S101, obtaining a preference product of a target user, preference evaluation values of the preference products, and M financial products to be recommended.
Specifically, the target user may be a user transacting with a financial institution, and the preferred product is a product that is preferable to the target user and is predicted after the behavior data of the target user is analyzed by acquiring the behavior data of the target user on the financial product. The preference evaluation value is an evaluation value for quantitatively evaluating the preference degree of the user for the financial products, for example, the preference evaluation value is quantized into an evaluation value based on the behavior data of the target user such as collection, purchase, browsing and the like of the financial products, and finally, the product with the highest evaluation value is screened out as the preference product of the target user, and M financial products to be recommended can be selected from the financial products currently sold by the financial institutions and are ready to be recommended to the target user.
For example, by collecting user behavior data of online channels and offline channels (after consent of the user is obtained), the transaction data of the total amount of the customer financial products stored in the database is obtained, including customer information, names of purchase financial products, codes, product deadlines, risk levels, transaction time, transaction amount, and the like. And sending the financial product transaction data and the user behavior data to a product recommendation analysis system module to screen M financial products to be recommended.
Step S102, determining a preference evaluation value list of M financial products, and calculating the similarity between the preferred product and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation values of each user on each financial product.
Specifically, the preference evaluation value list may be a list recording preference evaluation values of M financial products of all users in a database of a financial institution, and after vectorizing each list of preference evaluation values by regarding each list of preference evaluation value lists of users and products as evaluation of one financial product of all users, a similarity between any two vectors, that is, a similarity between two financial products is calculated. A set of similarities is obtained by calculating the similarities between the preferred product and each of the M financial products.
Step S103, determining products to be recommended corresponding to the first quantity of similarity from a group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set.
Specifically, the higher the similarity is, the more similar the financial products to be recommended are to the preferred products, namely, the higher the possibility that the target user likes the financial products to be recommended is, so that the first quantity of the products to be recommended corresponding to the similarity is determined from a group of similarities in the order of the similarities from high to low, the first quantity is set by oneself according to needs, for example, the first quantity can be 10, the 10 financial products to be recommended are taken as a first product set, and when the target user does not have a history record of purchasing the financial products, namely, the financial product transaction record in the preset period of the target user cannot be obtained, the first product set is directly recommended to the target user.
Step S104, obtaining a financial product transaction record of a target user in a preset period, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set.
Specifically, the preset period can be set to one month, the second number can be manually adjusted according to the needs, for example, the second number can be set to 5, historical transaction records of financial products in the last 30 days of a target user are queried, namely financial product transaction records in the preset period, products in the financial product transaction records are ordered according to the comprehensive transaction frequency and transaction amount, the first 5 products are discharged, and the 5 products are combined with the first product set to obtain a target product set.
Step S105, determining a first number of a group of target products from the target product set based on the order of the transaction amount from the large to the small, and recommending the group of target products to the target user, wherein the transaction amount is an amount required for the target user to purchase the financial products in the target product set.
Specifically, financial products in the target product set are compared, sorting is performed according to transaction amounts, and the first 10 financial products are found and recommended to target users as a group of target products.
According to the product recommendation method, the preference products of the target user, the preference evaluation values of the preference products and M financial products to be recommended are obtained; determining a preference evaluation value list of M financial products, and calculating the similarity between the preferred products and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation values of each user for each financial product; determining products to be recommended corresponding to a first quantity of similarity from a group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set; acquiring a financial product transaction record of a target user in a preset period, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set; and determining a first number of a group of target products from the target product set based on the order of the transaction amount from large to small, and recommending the group of target products to the target user, wherein the transaction amount is the amount required by the target user to purchase the financial products in the target product set, and the problem of low matching degree between the recommended products and the user requirements in the related technology is solved. A group of first product sets with higher similarity are screened out by calculating the similarity between the preferred products of the target user and the financial products to be recommended, the target product sets are comprehensively evaluated based on historical financial product transaction records of the target user, and the target user is recommended, so that the differentiated requirements of the user on the financial products are met. Thereby achieving the effect of improving the matching degree of the recommended product and the user requirement.
Optionally, in the product recommendation method provided by the embodiment of the present application, the obtaining the preferred product of the target user includes: judging whether behavior data of the target user on M financial products is acquired or not, wherein the behavior data at least comprises one of the following steps: purchase times, browsing times and collection times; under the condition that the behavior data is acquired, calculating preference evaluation values of a target user on each financial product based on the behavior data to obtain a group of preference evaluation values; determining a maximum preference rating value from a set of preference ratings, determining a target financial product associated with the maximum preference rating value, and determining the target financial product as a preferred product.
Specifically, the preferred product may be a product in M financial products, so it is first determined whether behavior data of the target user on the M financial products is obtained, where the behavior data may include a purchase number, a browse number, a collection number, and the like, and these behavior data reflect, to a certain extent, a preference degree of the target user on the financial products, for example, the target user collects the a product too many times, which indicates that the target user prefers the a product. Under the condition that the behavior data is obtained, quantitative evaluation is carried out on the behavior data of each financial product based on the target user, the preference evaluation value of the target user on each financial product is calculated, a group of preference evaluation values are obtained, and the target financial product associated with the maximum preference evaluation value is selected from M financial products to serve as a preference product. And recommending financial products to be recommended which are similar to the preferred products based on the preferred products by screening the preferred products.
In the product recommendation method provided in the embodiment of the present application, after determining whether the behavior data of the target user on M financial products is acquired, the method further includes: acquiring a user tag of a target user and determining a plurality of other users in the case that the behavior data is not acquired, wherein the other users are users which have the same user tag as the target user and have acquired the behavior data; determining preference products of each other user to obtain a preference product set; and determining the most preferred products in the preferred product set as the preferred products of the target user.
Specifically, when the behavior data of the target user cannot be acquired, the preference products of the target user are comprehensively screened out based on the preference products of other users by determining the other users similar to the client information of the target user. For example, in a financial institution, users having similar customer information to the target user belong to one user tag, and thus by determining other users having acquired behavior data of the same user tag as the target user. And determining the preference products of each other user to obtain a preference product set, wherein the most number of preference products in the preference product set are used as preference products of the target user, and if the preference products in the preference product set are different or the most number of preference products is more than one, randomly selecting one preference product from the preference products as the preference product of the target user. By determining the preference products of the target user under the condition that the behavior data of the target user are not acquired, the matching degree of the financial products to be recommended and the requirements of the target user is ensured to be higher.
Optionally, in the product recommendation method provided in the embodiment of the present application, when the behavior data includes the purchase number, the browse number, and the collection number, calculating the preference evaluation value of the target user for each financial product based on the behavior data includes: determining a first weight of the purchase times, a second weight of the browsing times and a third weight of the collection times; determining the historical purchase times, the historical browsing times and the historical collection times of the target user on the current financial product; determining a first evaluation value corresponding to historical purchase times from an evaluation value mapping relation table based on the purchase times, determining a second evaluation value corresponding to historical browse times from the evaluation value mapping relation table based on the browse times, and determining a third evaluation value corresponding to historical collection times from the evaluation value mapping relation table based on the collection times, wherein the evaluation value mapping relation table comprises a first mapping relation between the purchase times and the evaluation values, a second mapping relation between the browse times and the evaluation values and a third mapping relation between the collection times and the evaluation values; calculating the product of the first weight and the first evaluation value to obtain a purchase number evaluation value, calculating the product of the second weight and the second evaluation value to obtain a browsing number evaluation value, and calculating the product of the third weight and the third evaluation value to obtain a collection number evaluation value; and calculating the sum of the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value to obtain a preference evaluation value.
Specifically, different weights can be set manually based on different types of behavior data, and the influence degree of the different types of behavior data on the preference of the user is distinguished through the weights. For example, the first weight of the purchase number is set to 0.5, the second weight of the browsing number is set to 0.2, and the third weight of the collection number is set to 0.3. The evaluation value mapping relation table may be an artificially set evaluation value of behavior data quantification of different times, for example, an evaluation value corresponding to one purchase is 2 points, and an evaluation value corresponding to five purchases is 10 points. After the historical purchase times, the historical browsing times and the historical collection times of the current financial product by the target user are determined, a first evaluation value, a second evaluation value and a third evaluation value are determined by querying an evaluation value mapping relation table. And calculating the product of each weight and the corresponding evaluation value to obtain the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value. And the sum of the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value is used as a preference evaluation value of the financial product. And weight distribution is carried out according to indexes such as purchase times, browsing or collection operation times and the like, and scoring is carried out, so that the preference degree of the target user on different financial products is obtained, and the preference evaluation value is calculated.
In the product recommendation method provided in the embodiment of the present application, before calculating the similarity between the preferred product and each financial product, optionally, before calculating the similarity between the preferred product and each financial product based on the preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product, the method further includes: acquiring behavior data of all users in a target database, and determining preference evaluation values of each user on each financial product based on the behavior data; a preference evaluation value list is constructed based on the preference evaluation values of each user for each financial product.
Specifically, weight distribution is carried out according to indexes such as purchase times, browsing or collection operation times and the like, scoring is carried out, the preference degree of different customers on different products is obtained, and a preference evaluation value list is constructed. For example, a user purchases a product once, browses twice, and collects once, and a user's preference evaluation value for a product is calculated as 2+1×2+2=6 points. And b, purchasing the product A twice, browsing five times and collecting once by the user, and calculating the preference evaluation value of the user B for the product A as 2 x 2+1 x 5+2=11 points. And recording preference evaluation values of different users on different financial products in a table to obtain a preference evaluation value list. Data is provided for calculating the similarity between the preferred product and the financial product by constructing a list of preferred estimates.
Optionally, in the product recommendation method provided in the embodiment of the present application, calculating the similarity between the preferred product and each of the financial products based on the preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product includes: calculating the average value of preference evaluation values of all users on the preference products to obtain the preference evaluation average value of the preference products; calculating the average value of preference evaluation values of all users on the financial products based on the preference evaluation value list to obtain the preference evaluation average value of the financial products; and calculating a cosine similarity coefficient based on the preference evaluation average value of the preference products, the preference evaluation average value of the financial products, the preference evaluation value of each user on the preference products and the preference evaluation value of each user on the financial products to obtain the similarity of the preference products and the financial products.
For example, a the preference evaluation value of the user for the preference product X is 10 points, and the preference evaluation value of the financial product a to be recommended is 20 points; b, the preference evaluation value of the user on the preference product X is 30 points, and the preference evaluation value of the financial product A to be recommended is 10 points; and c, the preference evaluation value of the user on the preference product X is 20 points, the preference evaluation value of the financial product A to be recommended is 12 points, the preference evaluation mean value of the preference product is (10+30+20)/3=20, and the preference evaluation mean value of the financial product A to be recommended is (20+10+12)/3=14. The cosine similarity coefficient = ((10-20) × (20-14) + (30-20) × (10-14) + (20-20) × (12-14))/(10-20) of the preferred product X and the financial product a to be recommended is calculated 2 +(30-20) 2 +(20-20) 2 ) 1/2 ×((20-14) 2 +(10-14) 2 +(12-14) 2 ) 1/2 =0.19. Similarity of preference product X and financial product A to be recommendedI.e. 0.19. And (3) screening out target products finally recommended to target users by calculating the similarity between the preference products and each financial product.
Optionally, in the product recommendation method provided in the embodiment of the present application, extracting the second number of historical transaction products from the financial product transaction record includes: determining N financial products contained in a financial product transaction record, and determining the transaction frequency and transaction amount of a target user for each financial product, wherein N is a positive integer; calculating the product of the transaction frequency and the fourth weight to obtain a transaction frequency evaluation value, and calculating the product of the transaction amount and the fifth weight to obtain a transaction amount evaluation value; calculating the sum of the transaction frequency evaluation value and the transaction amount evaluation value to obtain a transaction record evaluation value; and determining a second number of products from the N financial products according to the order of the transaction record evaluation values from large to small, and obtaining a second product set.
Specifically, the transaction frequency and the transaction amount are comprehensively considered, a second number of historical transaction products are extracted from a transaction record of the financial products, first, a fourth weight of the transaction frequency and a fifth weight of the transaction amount are determined, a plurality of financial products which are most likely to be purchased by a target user are screened out based on the sum of the transaction frequency evaluation value and the transaction amount evaluation value, namely, the transaction record evaluation value, and the greater the transaction record evaluation value, the higher the probability that the target client purchases the corresponding financial products. And thus the second product set is selected from the N kinds of financial products in order of the transaction record evaluation value from the large to the small. The user's repurchase needs are also taken into account when recommending financial products to the target user by determining the second product set guarantee.
According to another embodiment of the present application, there is further provided a product recommendation system, and fig. 2 is a schematic diagram of the product recommendation system provided according to an embodiment of the present application. As shown in fig. 2, the system includes:
the data collection module 201 is configured to collect user behavior data and customer financial product transaction data.
Specifically, user behavior data (after consent of a user is obtained) of an online channel and an offline channel is collected, and total customer financial product transaction data including customer information, names, codes, product deadlines, risk levels, transaction time, transaction amount and the like of purchase financial products are collected. To the product recommendation analysis module 202 for product recommendation analysis.
The product recommendation analysis module 202 is configured to analyze a first product set to be recommended, which has high similarity with a product with high user evaluation, based on user behavior data and customer financial product transaction data.
Specifically, based on input financial product historical transaction data of the full-quantity clients, a preference matrix of the user for different financial products is constructed through a collaborative filtering algorithm based on the articles. If the weight distribution is carried out according to the indexes such as the purchase times, the browsing or collecting operation times and the like, the preference degree (evaluation) of different customers on different products is obtained, and a preference matrix is constructed. And regarding a certain column in the preference matrix as the evaluation of all users on the product, vectorizing the product, and calculating the similarity among financial products according to the evaluation of the users on the product. For the products with high evaluation by the current user, the 10 products with the highest similarity are found out to be used as the first product set.
And the recommendation result output module 203 outputs a target product set finally recommended to the user.
Specifically, the historical transaction record of the financial product of the customer in the last 30 days is queried, and if not, the first product set is directly adopted as the target product set. If so, sorting according to the transaction frequency and the transaction amount, discharging the first 5 products, comparing the 5 products with the first product set, sorting according to the transaction amount, and finding out the first 10 products as the target product set.
Fig. 3 is a flow chart of an alternative product recommendation method provided in accordance with an embodiment of the present application. As shown in fig. 3, the method includes: step S301, collecting user behavior data; step S302, a preference matrix between a user and a product is constructed; step S303, calculating the similarity of products; step S304, finding 10 products with highest similarity with the products with high evaluation of the current user; step S305, performing secondary correction according to the historical behavior of the client; step S306, outputting a recommendation result.
According to the selectable product recommending method provided by the embodiment of the application, the similarity between the preference product of the target user and the financial product to be recommended is calculated based on the collaborative filtering algorithm, a group of first product sets with higher similarity are screened out, the target product sets are comprehensively evaluated based on historical financial product transaction records of the target user, the target user is recommended, and the target product sets are output to a bank staff for off-line accurate recommendation to customers. The service efficiency and quality are greatly improved, and the differentiated requirements of users on financial products are met.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides a product recommendation device, and the product recommendation device can be used for executing the product recommendation method provided by the embodiment of the application. The following describes a product recommendation device provided in the embodiment of the present application.
Fig. 4 is a schematic diagram of a product recommendation device provided according to an embodiment of the present application. As shown in fig. 4, the apparatus includes:
a first acquiring unit 10 for acquiring a preference product of a target user, a preference evaluation value of the preference product, and M kinds of financial products to be recommended;
a first determining unit 20, configured to determine a preference evaluation value list of M financial products, and calculate a similarity between the preferred product and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products, to obtain a set of similarity, where M is a positive integer, and the preference evaluation value list includes preference evaluation values of each user for each financial product;
A second determining unit 30, configured to determine products to be recommended corresponding to the first number of similarities from a group of similarities in order of high-to-low similarities, to obtain a first product set;
a second obtaining unit 40, configured to obtain a transaction record of a financial product within a preset period of the target user, extract a second number of historical transaction products from the transaction record of the financial product, obtain a second product set, and combine the first product set and the second product set to obtain a target product set;
a third determining unit 50 for determining a first number of a group of target products from the target product set based on the order of the transaction amount, which is an amount required for the target user to purchase the financial products in the target product set, from the large to the small, and recommending the group of target products to the target user.
According to the product recommending device provided by the embodiment of the application, the preferred products of the target user, the preference evaluation values of the preferred products and M financial products to be recommended are acquired through the first acquiring unit 10; the first determining unit 20 determines a preference evaluation value list of M financial products, and calculates a similarity between the preferred product and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preferred products, so as to obtain a set of similarity, wherein M is a positive integer, and the preference evaluation value list includes preference evaluation values of each user for each financial product; the second determining unit 30 determines products to be recommended corresponding to the first number of similarities from the group of similarities in the order of high-to-low similarities, so as to obtain a first product set; a second obtaining unit 40, configured to obtain a financial product transaction record within a preset period of the target user, extract a second number of historical transaction products from the financial product transaction record, obtain a second product set, and combine the first product set and the second product set to obtain a target product set; the third determining unit 50 determines a first number of a group of target products from the target product sets based on the order of the transaction amount from large to small, and recommends a group of target products to the target user, wherein the transaction amount is the amount required by the target user to purchase the financial products in the target product sets, the problem of low matching degree between the recommended products and the user demands in the related art is solved, a group of first product sets with high similarity are screened out by calculating the similarity between the preferred products of the target user and the financial products to be recommended, and the target product sets are comprehensively evaluated and recommended based on historical financial product transaction records of the target user, so that the differentiated demands of the user on the financial products are met. Thereby achieving the effect of improving the matching degree of the recommended product and the user requirement.
Optionally, in the product recommendation device provided in the embodiment of the present application, the first obtaining unit 10 includes: the judging module is used for judging whether behavior data of the target user on M financial products is acquired or not, wherein the behavior data at least comprises one of the following: purchase times, browsing times and collection times; the first calculation module is used for calculating preference evaluation values of the target user on each financial product based on the behavior data under the condition that the behavior data are acquired, so as to obtain a group of preference evaluation values; the first determining module is used for determining a maximum preference evaluation value from a group of preference evaluation values, determining a target financial product associated with the maximum preference evaluation value, and determining the target financial product as a preference product.
Optionally, in the product recommendation device provided in the embodiment of the present application, the device further includes: a third acquisition unit configured to acquire a user tag of a target user and determine a plurality of other users, which are users having the same user tag as the target user and having acquired behavior data, in a case where the behavior data is not acquired; a fourth determining unit, configured to determine a preference product of each other user, to obtain a preference product set; and a fifth determining unit for determining the most number of preferred products in the preferred product set as preferred products of the target user.
Optionally, in the product recommendation device provided in the embodiment of the present application, the first calculation module includes: the first determining submodule is used for determining a first weight of the purchase times, a second weight of the browsing times and a third weight of the collection times; the second determining submodule is used for determining the historical purchase times, the historical browsing times and the historical collection times of the target user on the current financial product; a third determining sub-module, configured to determine a first evaluation value corresponding to the historical purchase number from an evaluation value mapping relationship table based on the purchase number, determine a second evaluation value corresponding to the historical browse number from the evaluation value mapping relationship table based on the browse number, and determine a third evaluation value corresponding to the historical collection number from the evaluation value mapping relationship table based on the collection number, where the evaluation value mapping relationship table includes a first mapping relationship between the purchase number and the evaluation value, a second mapping relationship between the browse number and the evaluation value, and a third mapping relationship between the collection number and the evaluation value; the first computing sub-module is used for computing the product of the first weight and the first evaluation value to obtain a purchase number evaluation value, computing the product of the second weight and the second evaluation value to obtain a browsing number evaluation value, and computing the product of the third weight and the third evaluation value to obtain a collection number evaluation value; and the second calculating sub-module is used for calculating the sum of the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value to obtain a preference evaluation value.
Optionally, in the product recommendation device provided in the embodiment of the present application, the device further includes: a fourth acquisition unit configured to acquire behavior data of all users in the target database, and determine preference evaluation values of each user for each financial product based on the behavior data; and a construction unit for constructing a preference evaluation value list based on the preference evaluation values of each user for each financial product.
Optionally, in the product recommendation device provided in the embodiment of the present application, the first determining unit 20 includes: the second calculation module is used for calculating the average value of preference evaluation values of all users on the preference products to obtain the preference evaluation average value of the preference products; the third calculation module is used for calculating the average value of preference evaluation values of all users on the financial products based on the preference evaluation value list to obtain the preference evaluation average value of the financial products; and the fourth calculation module is used for calculating a cosine similarity coefficient based on the preference evaluation average value of the preference products, the preference evaluation average value of the financial products, the preference evaluation value of each user on the preference products and the preference evaluation value of each user on the financial products, so as to obtain the similarity of the preference products and the financial products.
Optionally, in the product recommendation device provided in the embodiment of the present application, the second obtaining unit 40 includes: the second determining module is used for determining N financial products contained in the financial product transaction records and determining the transaction frequency and the transaction amount of a target user on each financial product, wherein N is a positive integer; a fifth calculation module, configured to calculate a product of the transaction frequency and the fourth weight to obtain a transaction frequency evaluation value, and calculate a product of the transaction amount and the fifth weight to obtain a transaction amount evaluation value; a sixth calculation module, configured to calculate a sum of the transaction frequency evaluation value and the transaction amount evaluation value, to obtain a transaction record evaluation value; and the third determining module is used for determining a second number of products from the N financial products according to the order of the transaction record evaluation values from large to small to obtain a second product set.
The product recommendation device includes a processor and a memory, the first acquiring unit 10, the first determining unit 20, the second determining unit 30, the second acquiring unit 40, the third determining unit 50, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one, and the effect of matching the recommended product with the user requirement is improved by adjusting the kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
The embodiment of the invention provides a computer readable storage medium, on which a program is stored, which when executed by a processor, implements a product recommendation method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute a product recommendation method.
Fig. 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application. As shown in fig. 5, the electronic device 501 includes a processor, a memory, and a program stored on the memory and executable on the processor, and when the processor executes the program, the following steps are implemented: product recommendation methods. The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: product recommendation methods.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may 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 flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of product recommendation, comprising:
acquiring a preference product of a target user, preference evaluation values of the preference products and M financial products to be recommended;
determining a preference evaluation value list of the M financial products, and calculating the similarity between the preference products and each financial product based on the preference evaluation values in the preference evaluation value list and the preference evaluation values of the preference products to obtain a group of similarity, wherein M is a positive integer, and the preference evaluation value list comprises the preference evaluation values of each user on each financial product;
Determining products to be recommended corresponding to a first number of similarities from the group of similarities according to the sequence of the similarities from high to low, and obtaining a first product set;
acquiring a financial product transaction record in a preset period of the target user, extracting a second number of historical transaction products from the financial product transaction record to obtain a second product set, and combining the first product set and the second product set to obtain a target product set;
determining a group of target products of the first quantity from the target product set based on the order of the transaction amount from the large to the small, and recommending the group of target products to the target user, wherein the transaction amount is an amount required by the target user to purchase the financial products in the target product set.
2. The method of claim 1, wherein obtaining the preference product of the target user comprises:
judging whether behavior data of the target user on the M financial products are acquired or not, wherein the behavior data at least comprise one of the following: purchase times, browsing times and collection times;
under the condition that the behavior data is acquired, calculating preference evaluation values of the target user on each financial product based on the behavior data to obtain a group of preference evaluation values;
Determining a maximum preference evaluation value from the set of preference evaluation values, determining a target financial product associated with the maximum preference evaluation value, and determining the target financial product as the preference product.
3. The method of claim 2, wherein after determining whether behavior data of the target user for the M financial products is acquired, the method further comprises:
acquiring a user tag of the target user and determining a plurality of other users, wherein the other users are users which have the same user tag as the target user and have acquired behavior data, in the case that the behavior data is not acquired;
determining preference products of each other user to obtain a preference product set;
and determining the most preferred products in the preferred product set as the preferred products of the target user.
4. The method of claim 2, wherein, in the case where the behavior data includes a purchase number, a browse number, and a collection number, calculating a preference evaluation value of the target user for each financial product based on the behavior data includes:
determining a first weight of the purchase times, a second weight of the browsing times and a third weight of the collection times;
Determining the historical purchase times, the historical browsing times and the historical collection times of the target user on the current financial product;
determining a first evaluation value corresponding to the historical purchase times from an evaluation value mapping relation table based on the purchase times, determining a second evaluation value corresponding to the historical browse times from the evaluation value mapping relation table based on the browse times, and determining a third evaluation value corresponding to the historical collection times from the evaluation value mapping relation table based on the collection times, wherein the evaluation value mapping relation table comprises a first mapping relation between the purchase times and the evaluation values, a second mapping relation between the browse times and the evaluation values and a third mapping relation between the collection times and the evaluation values;
calculating the product of the first weight and the first evaluation value to obtain a purchase number evaluation value, calculating the product of the second weight and the second evaluation value to obtain a browsing number evaluation value, and calculating the product of the third weight and the third evaluation value to obtain a collection number evaluation value;
and calculating the sum of the purchase number evaluation value, the browsing number evaluation value and the collection number evaluation value to obtain the preference evaluation value.
5. The method of claim 1, wherein prior to calculating the similarity of the preferred product to each financial product based on the preference rating value in the list of preference rating values and the preference rating value of the preferred product, the method further comprises:
Acquiring behavior data of all users in a target database, and determining preference evaluation values of each user on each financial product based on the behavior data;
and constructing the preference evaluation value list based on the preference evaluation value of each financial product of each user.
6. The method of claim 1, wherein calculating the similarity of the preferred product to each financial product based on the preference scores in the preference score list and the preference scores for the preferred product comprises:
calculating the average value of preference evaluation values of all users on the preference products to obtain the preference evaluation average value of the preference products;
calculating the average value of preference evaluation values of all users on the financial products based on the preference evaluation value list to obtain the preference evaluation average value of the financial products;
and calculating a cosine similarity coefficient based on the preference evaluation average value of the preference products, the preference evaluation average value of the financial products, the preference evaluation value of each user on the preference products and the preference evaluation value of each user on the financial products, so as to obtain the similarity of the preference products and the financial products.
7. The method of claim 1, wherein extracting a second quantity of historical transaction products from the financial product transaction record comprises:
Determining N financial products contained in the financial product transaction records, and determining the transaction frequency and transaction amount of the target user for each financial product, wherein N is a positive integer;
calculating the product of the transaction frequency and the fourth weight to obtain a transaction frequency evaluation value, and calculating the product of the transaction amount and the fifth weight to obtain a transaction amount evaluation value;
calculating the sum of the transaction frequency evaluation value and the transaction amount evaluation value to obtain a transaction record evaluation value;
and determining the second number of products from the N financial products according to the order of the transaction record evaluation values from large to small, and obtaining the second product set.
8. A product recommendation device, comprising:
a first obtaining unit, configured to obtain a preference product of a target user, a preference evaluation value of the preference product, and M financial products to be recommended;
a first determining unit, configured to determine a preference evaluation value list of the M financial products, and calculate a similarity between the preferred product and each financial product based on a preference evaluation value in the preference evaluation value list and the preference evaluation value of the preferred product, to obtain a set of similarities, where M is a positive integer, and the preference evaluation value list includes preference evaluation values of each user for each financial product;
The second determining unit is used for determining products to be recommended corresponding to the first quantity of similarity from the group of similarity according to the sequence of the similarity from high to low, and obtaining a first product set;
the second acquisition unit is used for acquiring financial product transaction records in a preset period of the target user, extracting a second number of historical transaction products from the financial product transaction records to obtain a second product set, and combining the first product set and the second product set to obtain a target product set;
and a third determining unit configured to determine the first number of a group of target products from the target product set based on an order of a transaction amount from a large value to a small value, and recommend the group of target products to the target user, wherein the transaction amount is an amount required for the target user to purchase the financial products in the target product set.
9. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein the program, when run, controls a device in which the non-volatile storage medium is located to perform the product recommendation method of any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the product recommendation method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644139.9A CN116542747A (en) | 2023-06-01 | 2023-06-01 | Product recommendation method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310644139.9A CN116542747A (en) | 2023-06-01 | 2023-06-01 | Product recommendation method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116542747A true CN116542747A (en) | 2023-08-04 |
Family
ID=87452456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310644139.9A Pending CN116542747A (en) | 2023-06-01 | 2023-06-01 | Product recommendation method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116542747A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117492379A (en) * | 2023-12-25 | 2024-02-02 | 珠海格力电器股份有限公司 | Electrical equipment function recommendation method and device, electronic equipment and electrical equipment |
-
2023
- 2023-06-01 CN CN202310644139.9A patent/CN116542747A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117492379A (en) * | 2023-12-25 | 2024-02-02 | 珠海格力电器股份有限公司 | Electrical equipment function recommendation method and device, electronic equipment and electrical equipment |
| CN117492379B (en) * | 2023-12-25 | 2024-04-26 | 珠海格力电器股份有限公司 | Electrical equipment function recommendation method and device, electronic equipment and electrical equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3279806A1 (en) | Data processing method and apparatus | |
| Del Barrio et al. | A central limit theorem for Lp transportation cost on the real line with application to fairness assessment in machine learning | |
| CN110737859A (en) | UP main matching method and device | |
| CN107886241B (en) | Resource analysis method, device, medium, and electronic apparatus | |
| Banerjee et al. | Capital structure decisions and its impact on dividend payout ratio during the pre-and post-period of recession in Indian scenario: An empirical study | |
| CN116542747A (en) | Product recommendation method and device, storage medium and electronic equipment | |
| CN110866698A (en) | Device for assessing service score of service provider | |
| CN108268519B (en) | Method and device for recommending network object | |
| CN116450951A (en) | Service recommendation method and device, storage medium and electronic equipment | |
| CN114971891A (en) | Risk prediction method and device, processor and electronic equipment | |
| CN114896506A (en) | Product recommendation method, device, equipment and storage medium | |
| US20220261818A1 (en) | System and method for determining and managing reputation of entities and industries through use of media data | |
| CN114529400A (en) | Consumption loan preauthorization evaluation method, device and medium | |
| CN104871547A (en) | Method and system for efficiently compiling media content items for a media-on-demand platform | |
| CN116468273A (en) | Customer risk identification method and device | |
| CN114741592A (en) | Product recommendation method, device and medium based on multi-model fusion | |
| KR102172532B1 (en) | Method and system for calculating price influence based on disclosure and media | |
| CN110858214B (en) | Recommendation model training and further auditing program recommendation method, device and equipment | |
| CN114049202A (en) | Operation risk identification method and device, storage medium and electronic equipment | |
| CN115392992A (en) | Commodity recommendation method, terminal device and computer-readable storage medium | |
| CN116228371A (en) | Recommendation method and device for financial products, storage medium and electronic equipment | |
| CN116485446A (en) | Service data processing method and device, processor and electronic equipment | |
| CN117952688A (en) | Classification method and device for merchants and electronic equipment | |
| CN115062228A (en) | Product recommendation method and device, processor and electronic equipment | |
| CN116228370A (en) | Product recommendation method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |