Transaction item recommendation method and device, equipment and storage medium

Abstract

The invention provides a transaction item recommendation method and device, equipment and a storage medium. Relates to the technical field of data processing. The method comprises the following steps: acquiring historical transaction information of each user, determining a user label of each user according to the historical transaction information of each user, determining at least one user group according to each historical transaction information, and respectively determining item groups corresponding to each user group according to the historical transaction information of each user in each user group, and establishing a project recommendation model according to each piece of historical transaction information, each user tag and each project group, and in response to a received project transaction application, inputting the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model. According to the method provided by the invention, the problems of low matching degree between a transaction item recommendation result and a user demand and relatively low recommendation success rate in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a transaction item recommendation method, device, equipment and storage medium. Background Art

[0002] Project recommendation (such as trading project recommendation, entertainment project recommendation, etc.) refers to identifying projects that match the user profile and recommending them to the user based on pre-authorized historical data through data mining and analysis.

[0003] Among them, the existing transaction item recommendation method is mainly based on the user's historical transaction data, analyzing and determining the transaction items with a higher number of successful transactions, and recommending them to the user.

[0004] However, the transaction item recommendation results of the above method do not match the user's needs, resulting in a low recommendation success rate, thereby failing to increase the transaction volume of the transaction items. Summary of the invention

[0005] The present application provides a transaction item recommendation method, device, equipment and storage medium, which are used to solve the problem in the prior art that the transaction item recommendation results are not well matched with user needs, resulting in a low recommendation success rate.

[0006] In a first aspect, the present application provides a transaction item recommendation method, comprising:

[0007] Acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user;

[0008] Determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area;

[0009] According to the historical transaction information of each user in each user group, respectively determine the project group corresponding to each user group; wherein the project group includes a plurality of related transaction projects;

[0010] Establishing a project recommendation model according to each of the historical transaction information, each of the user tags, and each of the project groups;

[0011] In response to receiving a project transaction application, the project transaction application is input into the project recommendation model to obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

[0012] In one possible design, the historical transaction information includes at least one historical transaction item;

[0013] Determining the project groups corresponding to the user groups according to the historical transaction information of each user in the user groups includes:

[0014] respectively determining the correlation between every two of the historical transaction items in each of the user groups;

[0015] For each of the user groups, a correlation greater than or equal to a first threshold is determined as a target correlation, and each historical transaction item corresponding to the target correlation is used as an associated transaction item corresponding to the user group, to obtain an item group for each of the user groups;

[0016] A corresponding group tag is added to each related transaction item in the item group of each user group, and a corresponding group tag is added to each user in each user group.

[0017] In a possible design, establishing a project recommendation model according to each of the historical transaction information, each of the user tags, and each of the project groups includes:

[0018] According to the user tags and historical transaction records of each user corresponding to each project group, respectively establish the user and transaction project joint relationship corresponding to each project group;

[0019] The joint relationship between users and transaction items corresponding to each of the item groups is processed by an analysis algorithm to obtain an item recommendation model; wherein the analysis algorithm includes a collaborative filtering algorithm or a regression analysis algorithm.

[0020] In a possible design, the project transaction application includes a target user ID;

[0021] In response to receiving the project transaction application, inputting the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model, including:

[0022] In response to receiving the project transaction application, determining a group label of the target user according to the target user ID carried in the project transaction application;

[0023] Determine a target project group according to the group label of the target user, and determine each related transaction project in the target project group;

[0024] The project transaction application and each associated transaction project in the target project group are input into the project recommendation model to obtain a project recommendation list output by the project recommendation model.

[0025] In a possible design, the historical transaction information includes at least one historical transaction item and at least one of the cities to which each historical transaction item belongs;

[0026] The determining at least one user group according to each of the historical transaction information includes:

[0027] Determine a city label for each user according to the city to which each historical transaction item in the historical transaction information of each user belongs;

[0028] It is determined that users with the same city tag belong to the same user group.

[0029] In a possible design, determining the city label of each user according to the city to which each historical transaction item in the historical transaction information of each user belongs includes:

[0030] Performing continuous processing on the cities to which each of the historical transaction items in the historical transaction information of each of the users belongs, to obtain continuous city information data of each of the users;

[0031] Based on a linear optimization algorithm, linear optimization is performed on the continuous city information data of each user to obtain a city label for each user; wherein the linear optimization algorithm includes a logistic regression model.

[0032] In a possible design, the acquiring historical transaction information of each user and determining a user tag of each user according to the historical transaction information of each user includes:

[0033] Obtaining historical transaction information of each of the users;

[0034] Processing the historical transaction information of each user based on the refined operation model to obtain a user level of each user; wherein the user level includes a first category of users and a second category of users;

[0035] A corresponding user tag is added to each user according to the user level of each user; wherein the user tag includes a first user tag and a second user tag.

[0036] In a possible design, in response to receiving a project transaction application, inputting the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model, further comprising:

[0037] In response to receiving the project transaction application, determining a target user tag according to the target user ID carried in the project transaction application;

[0038] When the target user tag is the first user tag, determining the target project group corresponding to the target user according to the target user ID, and determining each associated transaction project in the target project group;

[0039] The target user ID, the target user tag, and each associated transaction item in the target item group are input into the item recommendation model to obtain an item recommendation list output by the item recommendation model.

[0040] In one possible design, the method further includes:

[0041] Sort the related transaction items in the project recommendation list according to the matching degree between the related transaction items in the project recommendation list and the project transaction application, and display the project recommendation list;

[0042] receiving a request corresponding to the project recommendation list;

[0043] The project recommendation model is optimized and trained based on the request corresponding to the project recommendation list to obtain an optimized and trained project recommendation model.

[0044] In a second aspect, the present application provides a transaction item recommendation device, comprising:

[0045] An acquisition module, used to acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user;

[0046] A user group determination module, configured to determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area;

[0047] A project group determination module, used to determine the project group corresponding to each user group according to the historical transaction information of each user in each user group; wherein the project group includes a plurality of related transaction projects;

[0048] A model building module, used to build a project recommendation model according to each of the historical transaction information, each of the user tags and each of the project groups;

[0049] The project recommendation module is used to respond to receiving a project transaction application, input the project transaction application into the project recommendation model, and obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

[0050] In a third aspect, an embodiment of the present application provides an electronic device comprising: at least one processor and a memory; the memory stores computer execution instructions; the at least one processor executes the computer execution instructions stored in the memory, so that the at least one processor executes the transaction item recommendation method described in the first aspect and various possible designs of the first aspect.

[0051] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the transaction item recommendation method described in the first aspect and various possible designs of the first aspect is implemented.

[0052] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the transaction item recommendation method described in the first aspect and various possible designs of the first aspect.

[0053] The transaction project recommendation method, device, equipment and storage medium provided by the present application obtain the historical transaction information of each user, determine the user tag of each user according to the historical transaction information of each user, determine at least one user group according to each historical transaction information, determine the project group corresponding to each user group according to the historical transaction information of each user in each user group, and establish a project recommendation model according to each historical transaction information, each user tag and each project group. In response to receiving the project transaction application, the project transaction application is input into the project recommendation model, and the project recommendation list output by the project recommendation model is obtained, and one or more related transaction projects matching the project transaction application in the project group to which the target user corresponding to the project transaction application belongs are obtained. In other words, the project recommendation model can be used to determine the related transaction projects matching the project transaction application at the current moment in the project group corresponding to the same user group with the same city tag, thereby improving the matching degree between the project recommendation list and the project transaction application at the current moment. Therefore, it can solve the problem that the matching degree between the transaction project recommendation result and the user demand is not high and the recommendation success rate is low in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0055] Figure 1 Recommended application scenario diagram for existing technology trading projects;

[0056] Figure 2 A flowchart of a transaction item recommendation method provided in an embodiment of the present application;

[0057] Figure 3 A flowchart of step S103 of the transaction item recommendation method provided in an embodiment of the present application;

[0058] Figure 4 A flowchart of step S104 of the transaction item recommendation method provided in an embodiment of the present application;

[0059] Figure 5 A flowchart of step S105 of the transaction item recommendation method provided in an embodiment of the present application;

[0060] Figure 6 A flowchart of step S101 of the transaction item recommendation method provided in an embodiment of the present application;

[0061] Figure 7 An application flow chart of the transaction item recommendation method provided in the embodiment of the present application;

[0062] Figure 8 An application interface diagram of the transaction item recommendation method provided in an embodiment of the present application;

[0063] Fig. 9 A schematic diagram of the structure of a transaction item recommendation device provided in an embodiment of the present application;

[0064] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0065] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0066] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0067] In the technical solution of this application, the collection, storage, use, processing, transmission, provision and disclosure of information such as financial data or user data involved shall comply with the provisions of relevant laws and regulations and shall not violate public order and good morals.

[0068] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0069] Terminology explanation:

[0070] Project recommendation (such as trading project recommendation, entertainment project recommendation, etc.) refers to identifying projects that match the user profile and recommending them to the user based on pre-authorized historical data through data mining and analysis.

[0071] A user tag refers to a unique identity tag used to distinguish users, which includes identity information, behavioral characteristics, customer characteristics, and other information used to indicate user portraits.

[0072] A user group is used to indicate one or more users located in the same area.

[0073] Item group is used to indicate charging items that are strongly related to the user group (also called related transaction items).

[0074] Existing transaction item recommendation methods are mainly based on user historical transaction data, analyzing and determining transaction items with a higher number of successful transactions to recommend to users.

[0075] See also Figure 1 The user's historical transaction information data includes 3 transactions for item 3, 2 transactions for item 1, 1 transaction for item 6 and 1 transaction for item 7. Through analysis, it is determined that the transaction items with a higher number of successful transactions include transaction item 1 and transaction item 3, and transaction item 1 and transaction item 3 are recommended to the user accordingly.

[0076] However, the transaction item recommendation results generated by this method do not match the user well, resulting in a low success rate of transaction item recommendation and an inability to increase the transaction volume of the transaction items.

[0077] In view of the above technical problems, the present application proposes a transaction project recommendation method, device, equipment and storage medium, the method comprising: obtaining historical transaction information of each user, determining a user tag of each user according to the historical transaction information of each user, determining at least one user group according to each historical transaction information, determining a project group corresponding to each user group according to the historical transaction information of each user in each user group, and establishing a project recommendation model according to each historical transaction information, each user tag and each project group. In response to receiving a project transaction application, the project transaction application is input into the project recommendation model, a project recommendation list output by the project recommendation model is obtained, and one or more associated transaction projects matching the project transaction application in the project group to which the target user corresponding to the project transaction application belongs are obtained. That is, the above method determines the associated transaction projects matching the project transaction application at the current moment in the project group corresponding to the same user group with the same city tag through the project recommendation model, thereby improving the matching degree between the project recommendation list and the project transaction application at the current moment, that is, improving the matching degree between the project recommendation list and the user demand, thereby improving the success rate of transaction project recommendation, and then increasing the transaction volume of the transaction project.

[0078] The above method is applied to electronic devices, including tablets, mobile phones, PCs and other devices, which are not specifically limited here.

[0079] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0080] Figure 2 Flow chart of the transaction item recommendation method provided in the embodiment of the present application. Figure 2 As shown, the transaction project recommendation method includes:

[0081] S101. Acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user.

[0082] Specifically, historical transaction information of each user is obtained, and a user tag of each user is determined based on the historical transaction information of each user. The historical transaction information refers to transaction data of successful transactions within a preset time period before the current moment. The preset time period can be specifically set according to actual conditions. For example, the preset time period is set to one month, or the preset time period is set to 6 months. User tags include but are not limited to user identity information, behavioral characteristics, and customer characteristics. User identity information includes but is not limited to user ID, user gender, and user age. User behavioral characteristics include but are not limited to user transaction preferences, wherein user transaction preferences are used to indicate transaction items with a higher number of successful transactions in the user's historical transaction information. The user's customer characteristics are used to indicate the user value of the user and the user's activity. The user value of the user includes but is not limited to important and general. The user's activity includes but is not limited to active or inactive.

[0083] S102: Determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area.

[0084] Specifically, one or more users located in the same area are determined according to the historical transaction information of each user, and each user located in the same area is determined as a user group, thereby obtaining at least one user group.

[0085] S103 . Determine a project group corresponding to each user group according to historical transaction information of each user in each user group; wherein the project group includes a plurality of related transaction projects.

[0086] Specifically, according to the historical transaction information of each user in each user group, a plurality of associated transaction items with a correlation greater than a first threshold with each user group are determined respectively, so as to obtain an item group corresponding to each user group.

[0087] S104: Establish a project recommendation model according to each of the historical transaction information, each of the user tags, and each of the project groups.

[0088] Specifically, a project recommendation model is constructed based on the historical transaction information of each user, the user tag of each user, and each project group. The project recommendation model is used to determine a corresponding project recommendation list according to a project transaction application.

[0089] S105. In response to receiving a project transaction application, input the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

[0090] Specifically, in response to receiving a project transaction application, the project transaction application is input into a project recommendation model, a target user corresponding to the project transaction application and a project group corresponding to the target user are determined through the project recommendation model, one or more associated transaction projects matching the project transaction application are determined in the project group corresponding to the target user, and a project recommendation list output by the project recommendation model is obtained. The target user is used to indicate the user who initiated the project transaction application.

[0091] The project transaction application includes but is not limited to the user ID of the target user, the target transaction project, the transaction amount of the target transaction project, etc.

[0092] It is understandable that the associated transaction project that matches the project transaction application can also be referred to as the associated transaction project that matches the target transaction project.

[0093] In some embodiments, historical transaction information includes but is not limited to user ID, at least one historical transaction item, the transaction date of each of the historical transaction items, the number of transactions of each of the historical transaction items, the transaction amount of each of the historical transaction items, and at least one of the cities to which each of the historical transaction items belongs.

[0094] In some embodiments, the step S102 includes:

[0095] S1021, determining a city label for each user according to the city to which each historical transaction item in the historical transaction information of each user belongs;

[0096] S1022: Determine whether users with the same city tag belong to the same user group.

[0097] Specifically, the cities to which the historical transaction items of each user belong are determined from the historical transaction information of each user, and the city tag of each user is determined. It is determined that users with the same city tag belong to the same user group, and at least one user group is obtained accordingly.

[0098] For example, if the city tag of user A is city C001, the city tag of user B is C002, and the city tag of user C is C001, it is determined that user A and user C belong to the same user group.

[0099] It is understandable that the embodiments of the present application mainly divide users in the same area by being located in the same city. In some possible embodiments, users in the same area may also be determined in other ways. For example, users in an area with a diameter of 100 km with position s as the center are users in the same area.

[0100] In some embodiments, the step S1021 includes:

[0101] Performing continuous processing on the cities to which each of the historical transaction items in the historical transaction information of each of the users belongs, to obtain continuous city information data of each of the users;

[0102] Based on a linear optimization algorithm, linear optimization is performed on the continuous city information data of each user to obtain a city label for each user; wherein the linear optimization algorithm includes a logistic regression model.

[0103] Specifically, the city information of the historical transaction items in the historical transaction information may be discontinuous data. Based on this, the city information of each historical transaction item in the historical transaction information of each user is processed continuously to obtain the continuous city information data of each user. The continuous city information data of each user is linearly optimized based on the linear optimization algorithm to obtain the city label of each user. The linear optimization algorithm includes but is not limited to the logistic regression model.

[0104] Figure 3 This is a flow chart of step S103 of the transaction item recommendation method provided in the embodiment of the present application. Figure 3 As shown, step S103 of the transaction item recommendation method includes the following steps:

[0105] S1031. Determine the correlation between every two historical transaction items in each user group.

[0106] Specifically, for each user group, the correlation between every two historical transaction items in the user group is calculated based on the historical transaction information of each user in the user group.

[0107] Exemplarily, the correlation between every two historical transaction items may be calculated by an association rule mining algorithm (Apriori) or an association analysis algorithm (FP-growth).

[0108] S1032: for each user group, determine a correlation greater than or equal to a first threshold as a target correlation, and use each historical transaction item corresponding to the target correlation as an associated transaction item corresponding to the user group, to obtain an item group for each user group;

[0109] S1033: adding a corresponding group tag to each related transaction item in the project group of each user group, and adding a corresponding group tag to each user in each user group.

[0110] Specifically, for each user group, among the correlations between the historical transaction items of the user group, a correlation greater than a first threshold is determined, and each historical transaction item corresponding to the correlation greater than the first threshold is used as an associated transaction item of the user group, thereby obtaining an item group of each user group. A corresponding group label is added to each associated transaction item in the item group of each user group. The first threshold can be specifically set according to actual conditions, for example, the first threshold is set to 0.8 or 0.9.

[0111] Specifically, when determining the project group of each user group, a corresponding group tag may be added to each user in each user group as a user tag of each user.

[0112] As an example but not a limitation, when adding a corresponding group tag to each user in each user group, an association relationship between the group tag and the user ID is established to facilitate determining the project group corresponding to the user based on the user ID.

[0113] As an example but not a limitation, after determining the city tag of each user, the city tag of each user is used as the user tag of each user.

[0114] As an example but not a limitation, the information in the user tag is divided into multiple levels according to the importance of different information in the user tag. For example, the user tag can be represented by Table 1:

[0115] Table 1 User tag table

[0116]

[0117]

[0118] In Table 1, user tags are divided into three levels, among which the first-level tags include the user's identity information, behavioral characteristics and customer characteristics. The second-level tags under the identity information include basic characteristics, and the third-level tags under the basic characteristics include the user's gender, age, city, and group tags. The second-level tags under the behavioral characteristics include the user's transaction preferences. The third-level tags under the transaction preferences include the historical transaction items preferred by the user. The second-level tags under the customer characteristics include user value and user activity. The third-level tags under the user value include important / general, and the third-level tags under the active situation include active / inactive.

[0119] Figure 4 This is a flow chart of step S104 of the transaction item recommendation method provided in the embodiment of the present application. Figure 4 As shown, step S104 of the transaction item recommendation method includes the following steps:

[0120] S1041. According to the user tags and historical transaction records of each user corresponding to each project group, respectively establish a user-transaction project joint relationship corresponding to each project group.

[0121] Specifically, each user corresponding to each project group is determined, and according to the user tags and historical transaction records of each user corresponding to each project group, a user-transaction project joint relationship corresponding to each project group is constructed according to each project group. For the sake of convenience, the above user-transaction project joint relationship can also be called a user-transaction project joint matrix.

[0122] S1042. Process the joint relationship between users and transaction items corresponding to each of the item groups through an analysis algorithm to obtain an item recommendation model; wherein the analysis algorithm includes a collaborative filtering algorithm or a regression analysis algorithm.

[0123] Specifically, the joint relationship between users and transaction items corresponding to each project group is processed by an analysis algorithm to construct a project recommendation model. The above analysis algorithm includes but is not limited to a collaborative filtering algorithm (CF) or a logistic regression analysis algorithm (LR).

[0124] Exemplarily, the user tags and group tags of each user corresponding to each project group and the related transaction items under each project group can be represented by Table 2:

[0125] Table 2 Project group table

[0126]

[0127]

[0128] According to Table 2, among the user groups with the same city tag C001, the group tag of the project group corresponding to user A, user B and user C is Q001, and the associated transaction items under the project group Q001 include transaction item 1 and transaction item 6. User A's historical transaction information includes successful transaction items 1 and 6, user B's historical transaction information includes successful transaction item 1, and user C's historical transaction items include successful transaction item 6. The user tag of each user includes the user identity information and the corresponding city tag.

[0129] In some embodiments, the project transaction application includes a target user ID.

[0130] Figure 5 This is a flow chart of step S105 of the transaction item recommendation method provided in the embodiment of the present application. Figure 5 As shown, step S105 of the transaction item recommendation method includes the following steps:

[0131] S1051, in response to receiving the project transaction application, determining a group label of the target user according to the target user ID carried in the project transaction application;

[0132] S1052: Determine a target project group according to the group tag of the target user, and determine each related transaction project in the target project group.

[0133] Specifically, in response to receiving a project transaction application, the project transaction application is parsed to determine that the user ID carried in the project transaction application is the target user ID. The group tag of the target user is determined according to the target user ID, and the project group corresponding to the target user is determined according to the group tag of the target user as the target project group, and each associated transaction project in the target project group is determined.

[0134] S1053: Input the project transaction application and each related transaction project in the target project group into the project recommendation model to obtain a project recommendation list output by the project recommendation model.

[0135] Specifically, the project transaction application and each historical transaction project included in the above-mentioned target project group are input into the project recommendation model. The project recommendation model is used to determine one or more related transaction projects that match the target transaction project carried by the project transaction application from among the related transaction projects included in the target project group, and obtain a project recommendation list output by the project recommendation model.

[0136] The user group is determined by users in the same area, and the correlation between the transaction items corresponding to the user group is mined to determine the project group. The transaction items that match the project transaction request of the target user in the project group corresponding to the user group in the same area are recommended to the target user through group tags and user tags, which improves the matching degree between the associated transaction items in the project recommendation list and the project transaction request of the target user, thereby improving the success rate of transaction item recommendation and further increasing the transaction volume of the transaction items.

[0137] Figure 6 This is a flow chart of step S101 of the transaction item recommendation method provided in the embodiment of the present application. Figure 6 As shown, the transaction item recommendation method step S101 includes the following steps:

[0138] S1011, obtaining historical transaction information of each user;

[0139] S1012: Process the historical transaction information of each user based on the refined operation model to obtain a user level of each user; wherein the user level includes a first type of user and a second type of user.

[0140] Specifically, historical transaction information of each user is obtained, and the historical transaction information includes but is not limited to user ID, at least one historical transaction item, transaction date of each historical transaction item, transaction number of each historical transaction item, and transaction amount of each historical transaction item. The historical transaction information is processed through a refined operation model to obtain the user level of each user. Among them, the user level includes a first type of user and a second type of user. Among them, the first type of user is used to indicate users with important user value and / or active user status. The second type of user is used to indicate users with average user value and / or inactive user status. The refined operation model is: RMF model, which is specifically used to determine the user level according to the user's most recent payment interval recency, payment frequency, and payment amount monetary.

[0141] As an example but not a limitation, the user value of each user can be determined by the RMF model. Correspondingly, the user value may include multiple levels, such as: important type A customers, important type B customers, important type C customers, important type D customers, general type A customers, general type B customers, general type C customers, and general type D customers. The user value table can be represented by Table 3:

[0142] Table 3 User value table

[0143]

[0144] In Table 3, R is used to indicate the interval time of the user's historical transaction items. A high R indicates that the interval time is greater than the preset interval time, and a low R indicates that the interval time is less than the preset interval time. F is used to indicate the number of transactions of the user's historical transaction items. A high F indicates that the number of transactions is greater than the preset number of transactions, and a low F indicates that the number of transactions is less than the preset number of transactions. M is used to indicate the transaction amount of the user's historical transaction items. A high M indicates that the transaction amount is greater than the preset transaction amount, and a low M indicates that the transaction amount is less than the preset transaction amount. Among them, the preset interval time, the preset number of transactions, and the preset transaction amount can be specifically set according to the actual situation. For example, the preset interval time is set to 10 days or 30 days, the preset number of transactions is set to 5 times or 15 times, and the preset transaction amount is set to 100 yuan or 500 yuan.

[0145] As an example but not limitation, the above-mentioned important class A users, important class B users, important class C users, and important class D users are regarded as first class users, and general class A users, general class B users, general class C users, and general class D users are regarded as second class users.

[0146] S1013. Add a corresponding user tag to each of the users according to the user level of each of the users; wherein the user tag includes a first user tag and a second user tag.

[0147] Specifically, a corresponding user tag is added to each user according to the user level of each user. The user tags include but are not limited to a first user tag and a second user tag.

[0148] It can be understood that the user tag added for the first type of users is the first user tag, and the user tag added for the second type of users is the second user tag.

[0149] In some embodiments, step S101 further includes:

[0150] In response to receiving the project transaction application, determining a target user tag according to the target user ID carried in the project transaction application;

[0151] When the target user tag is the first user tag, determining the target project group corresponding to the target user according to the target user ID, and determining each associated transaction project in the target project group;

[0152] The target user ID, the target user tag, and each associated transaction item in the target item group are input into the item recommendation model to obtain an item recommendation list output by the item recommendation model.

[0153] Specifically, in response to receiving a project transaction application, the project transaction application is parsed to determine that the user ID carried by the project transaction application is the target user ID, and the target user tag of the target user is determined according to the target user ID. When the target user tag is the first user tag, the user's group tag is determined according to the target user ID to determine that the project group corresponding to the target user is the target user group, and each associated transaction project in the target project group is determined. The target user ID, the target user tag and each associated transaction project in the target project group carried by the project transaction application are input into the project recommendation model to obtain a project recommendation list output by the target project recommendation model.

[0154] By determining a project recommendation list that matches the project transaction application through the project recommendation model only when the target user tag is determined to be the first user tag, the transaction project recommendation function for some customers is realized, reducing the amount of calculation while specifically increasing the transaction volume of some customers' transaction projects.

[0155] In some embodiments, the method further comprises:

[0156] Sort the related transaction items in the project recommendation list according to the matching degree between the related transaction items in the project recommendation list and the project transaction application, and display the project recommendation list;

[0157] receiving a request corresponding to the project recommendation list;

[0158] The project recommendation model is optimized and trained based on the request corresponding to the project recommendation list to obtain an optimized and trained project recommendation model.

[0159] Specifically, according to the matching degree between each related transaction item in the project recommendation list and the project transaction application, each related transaction item in the project recommendation list is sorted, and the project recommendation list is displayed. The sorting method includes an ascending sorting method or a descending sorting method.

[0160] It can be understood that the matching degree between each related transaction project in the project recommendation list and the project transaction application can also be referred to as the matching degree between each related transaction project in the project recommendation list and the target transaction project carried by the project transaction application.

[0161] Specifically, a request corresponding to the project recommendation list is received, for example: a transaction request corresponding to an associated transaction item in the project recommendation list; for example: a deletion request corresponding to an associated transaction item in the project recommendation list, a switching request corresponding to the project recommendation list, etc.

[0162] Specifically, the project recommendation model is optimized and trained based on the request corresponding to the project recommendation list to obtain the optimized and trained project recommendation model.

[0163] Exemplarily, transaction requests corresponding to associated transaction items in the project recommendation list are used as positive feedback data of the project recommendation list, such as deletion requests corresponding to associated transaction items in the project recommendation list and switching requests corresponding to the project recommendation list are used as negative feedback data of the project recommendation list. Based on the positive feedback data and / or negative feedback data, the project recommendation model is optimized and trained to obtain the optimized and trained project recommendation model.

[0164] It is understandable that by continuously optimizing the project recommendation model, while improving the matching degree between each related transaction project and the project transaction request in the project recommendation list, various transaction projects are fully covered, the recommendation frequency of each transaction project is increased, and the transaction volume of the transaction project is comprehensively increased. Similarly, it is convenient for users to determine the change information of the transaction success rate and the change information of the transaction volume of the transaction project based on the new transaction information, as well as the positive feedback of each related transaction project in the project recommendation model.

[0165] Figure 7 An application flow chart of a transaction item recommendation method is shown exemplarily.

[0166] See also Figure 7 , determine the user label of each user based on the historical transaction information of each user, and determine the user group and the project group corresponding to each user group based on the historical transaction information and each historical transaction project. Determine the joint relationship between the user and the transaction project based on the historical transaction information, the user group and the corresponding project group, and build a project recommendation model based on the joint relationship between the user and the transaction project. When a user performs touch, slide or click operations on an electronic device to initiate a project transaction application, the project transaction application is processed by the project recommendation model to obtain a project recommendation list corresponding to the target transaction project in the project transaction application. Sort the related transaction items in the project recommendation list and display the above project recommendation list. Receive relevant requests from users for the project recommendation list, optimize and train the project recommendation model based on the transaction results of the project transaction application and the relevant requests from users for the project recommendation list, and obtain the optimized and trained project recommendation model.

[0167] Figure 8 An application interface diagram of a transaction item recommendation method is exemplarily shown.

[0168] See also Figure 8, the project recommendation list is displayed through the "Guess the transaction project you need" window. Among them, the project recommendation list includes the transaction object of each related transaction project, such as xx transportation, xx swimming, xx drinking water, etc.) and the recommendation reason of each related transaction project, such as commonly used transaction projects for users in the same city, recommended based on historical transaction projects, popular transaction projects in the same city, etc. Among them, commonly used transaction projects for users in the same city can be used to indicate transaction projects with a number of successful transactions greater than the transaction number threshold in the corresponding project group for users with the same city tag as the current user. Recommended based on historical transaction projects can be used to indicate transaction projects with a number of successful transactions greater than the transaction number threshold in the historical transaction projects of the current user. Popular transaction projects in the same city can be used to indicate transaction projects with a number of successful transactions greater than the transaction number threshold in the historical transaction projects of users with the same city tag as the current user. Among them, the transaction number threshold can be specifically set according to actual conditions. For example, the number of historical transactions is set to 5 times, or the number of historical transaction projects is set to 8 times.

[0169] Fig. 9 This is a schematic diagram of the structure of the transaction item recommendation device provided in the embodiment of the present application. Fig. 9 As shown, the transaction item recommendation device includes:

[0170] An acquisition module 901 is used to acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user;

[0171] A user group determination module 902, configured to determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area;

[0172] The project group determination module 903 is used to determine the project group corresponding to each user group according to the historical transaction information of each user in each user group; wherein the project group includes a plurality of related transaction projects;

[0173] A model building module 904, for building a project recommendation model according to each of the historical transaction information, each of the user tags and each of the project groups;

[0174] The project recommendation module 905 is used to respond to receiving a project transaction application, input the project transaction application into the project recommendation model, and obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

[0175] In some embodiments, the historical transaction information includes at least one historical transaction item;

[0176] The project group determination module includes:

[0177] A first determining unit, configured to respectively determine the correlation between every two historical transaction items in each user group;

[0178] A second determining unit is used to determine, for each of the user groups, a correlation greater than or equal to a first threshold as a target correlation, and use each historical transaction item corresponding to the target correlation as an associated transaction item corresponding to the user group, to obtain an item group for each of the user groups;

[0179] The first label construction unit is used to add a corresponding group label to each related transaction item in the project group of each user group, and to add a corresponding group label to each user in each user group.

[0180] In some embodiments, the model building module includes:

[0181] A relationship building unit, used to build a user-transaction project joint relationship corresponding to each project group according to the user tag and historical transaction record of each user corresponding to each project group;

[0182] The model building unit is used to process the joint relationship between users and transaction items corresponding to each of the project groups through an analysis algorithm to obtain a project recommendation model; wherein the analysis algorithm includes a collaborative filtering algorithm or a regression analysis algorithm.

[0183] In some embodiments, the project transaction application includes a target user ID;

[0184] The project recommendation module includes:

[0185] A third determining unit, configured to, in response to receiving the project transaction application, determine a group label of the target user according to the target user ID carried in the project transaction application;

[0186] A fourth determining unit, configured to determine a target project group according to the group label of the target user, and determine each associated transaction project in the target project group;

[0187] The first project recommendation unit is used to input the project transaction application and each related transaction project in the target project group into the project recommendation model to obtain a project recommendation list output by the project recommendation model.

[0188] In some embodiments, the historical transaction information includes at least one historical transaction item and at least one of the cities to which each of the historical transaction items belongs;

[0189] The user group determination module comprises:

[0190] A fifth determining unit, configured to determine a city label for each user according to the city to which each historical transaction item in the historical transaction information of each user belongs;

[0191] The sixth determining unit is used to determine that users with the same city tag belong to the same user group.

[0192] In some embodiments, the fifth determining unit includes:

[0193] A continuous processing subunit, used for performing continuous processing on the cities to which each of the historical transaction items in the historical transaction information of each of the users belongs, to obtain continuous city information data of each of the users;

[0194] The linear processing subunit is used to perform linear optimization on the continuous city information data of each user based on a linear optimization algorithm to obtain a city label for each user; wherein the linear optimization algorithm includes a logistic regression model.

[0195] In some embodiments, the acquisition module includes:

[0196] An acquisition unit, used to acquire historical transaction information of each user;

[0197] A level determination unit, configured to process the historical transaction information of each user based on a refined operation model to obtain a user level of each user; wherein the user level includes a first category of users and a second category of users;

[0198] The second label construction unit is used to add a corresponding user label to each user according to the user level of each user; wherein the user label includes a first user label and a second user label.

[0199] In some embodiments, the project recommendation module further includes:

[0200] A seventh determining unit, configured to, in response to receiving the project transaction application, determine a target user tag according to the target user ID carried in the project transaction application;

[0201] an eighth determining unit, configured to determine a target project group corresponding to the target user according to the target user ID when the target user tag is the first user tag, and determine each associated transaction project in the target project group;

[0202] The second project recommendation unit is used to input the target user ID, the target user tag and each related transaction project in the target project group into the project recommendation model to obtain a project recommendation list output by the project recommendation model.

[0203] In some embodiments, the device further comprises:

[0204] A sorting module, used to sort the related transaction items in the project recommendation list according to the matching degree between each related transaction item in the project recommendation list and the project transaction application, and display the project recommendation list;

[0205] A receiving module, configured to receive a request corresponding to the project recommendation list;

[0206] The model optimization module is used to optimize the project recommendation model based on the request corresponding to the project recommendation list to obtain the optimized project recommendation model.

[0207] The transaction item recommendation device provided in the embodiment of the present application can be used to implement the technical solution of the transaction item recommendation method in the above embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0208] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software called by processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. For example, the project recommendation module 905 can be a separately established processing element, or it can be integrated in a chip of the above device. In addition, it can also be stored in the memory of the above device in the form of program code, and called and executed by a processing element of the above device. The function of the above project recommendation module 905. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0209] Fig.10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.10 As shown, the electronic device may include: a transceiver 1001 , a processor 1002 and a memory 1003 .

[0210] The processor 1002 executes the computer execution instructions stored in the memory, so that the processor 1002 executes the scheme in the above embodiment. The processor 1002 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0211] The memory 1003 is connected to the processor 1002 via a system bus and completes communication between them. The memory 1003 is used to store computer program instructions.

[0212] The transceiver 1001 can be used to obtain historical transaction information and project transaction applications, etc.

[0213] The system bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries).

[0214] The memory may include a random access memory (RAM) and may also include a non-volatile memory (VNM).

[0215] The embodiment of the present application also provides a chip for running instructions, which is used to execute the technical solution of the transaction item recommendation method in the above embodiment.

[0216] The embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the technical solution of the transaction item recommendation method of the above embodiment.

[0217] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solution of the transaction item recommendation method in the above embodiment.

[0218] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0219] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0220] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0221] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0222] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0223] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic control unit or a main control device.

[0224] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0225] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A transaction item recommendation method, characterized in that: include: Acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user; Determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area; According to the historical transaction information of each user in each user group, respectively determine the project group corresponding to each user group; wherein the project group includes a plurality of related transaction projects; Establishing a project recommendation model according to each of the historical transaction information, each of the user tags, and each of the project groups; In response to receiving a project transaction application, the project transaction application is input into the project recommendation model to obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

2. The method according to claim 1, characterized in that The historical transaction information includes at least one historical transaction item; Determining the project groups corresponding to the user groups according to the historical transaction information of each user in the user groups includes: respectively determining the correlation between every two of the historical transaction items in each of the user groups; For each of the user groups, a correlation greater than or equal to a first threshold is determined as a target correlation, and each historical transaction item corresponding to the target correlation is used as an associated transaction item corresponding to the user group, to obtain an item group for each of the user groups; A corresponding group tag is added to each related transaction item in the item group of each user group, and a corresponding group tag is added to each user in each user group.

3. The method according to claim 1 or 2, characterized in that: The establishing of a project recommendation model according to each of the historical transaction information, each of the user tags and each of the project groups includes: According to the user tags and historical transaction records of each user corresponding to each project group, respectively establish the user and transaction project joint relationship corresponding to each project group; The joint relationship between users and transaction items corresponding to each of the item groups is processed by an analysis algorithm to obtain an item recommendation model; wherein the analysis algorithm includes a collaborative filtering algorithm or a regression analysis algorithm.

4. The method according to any one of claims 1 to 3, characterized in that The project transaction application includes a target user ID; In response to receiving the project transaction application, inputting the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model, including: In response to receiving the project transaction application, determining a group label of the target user according to the target user ID carried in the project transaction application; Determine a target project group according to the group label of the target user, and determine each related transaction project in the target project group; The project transaction application and each associated transaction project in the target project group are input into the project recommendation model to obtain a project recommendation list output by the project recommendation model.

5. The method according to any one of claims 1 to 4, characterized in that The historical transaction information includes at least one historical transaction item and at least one of the cities to which each historical transaction item belongs; The determining at least one user group according to each of the historical transaction information includes: Determine a city label for each user according to the city to which each historical transaction item in the historical transaction information of each user belongs; It is determined that users with the same city tag belong to the same user group.

6. The method according to claim 5, characterized in that The determining of the city label of each user according to the city to which each historical transaction item in the historical transaction information of each user belongs includes: Performing continuous processing on the cities to which each of the historical transaction items in the historical transaction information of each of the users belongs, to obtain continuous city information data of each of the users; Based on a linear optimization algorithm, linear optimization is performed on the continuous city information data of each user to obtain a city label for each user; wherein the linear optimization algorithm includes a logistic regression model.

7. The method according to any one of claims 1 to 6, characterized in that The acquiring of historical transaction information of each user and determining a user tag of each user according to the historical transaction information of each user includes: Obtaining historical transaction information of each of the users; Processing the historical transaction information of each user based on the refined operation model to obtain a user level of each user; wherein the user level includes a first category of users and a second category of users; A corresponding user tag is added to each user according to the user level of each user; wherein the user tag includes a first user tag and a second user tag.

8. The method according to claim 7, characterized in that In response to receiving the project transaction application, inputting the project transaction application into the project recommendation model to obtain a project recommendation list output by the project recommendation model, further comprising: In response to receiving the project transaction application, determining a target user tag according to the target user ID carried in the project transaction application; When the target user tag is the first user tag, determining the target project group corresponding to the target user according to the target user ID, and determining each associated transaction project in the target project group; The target user ID, the target user tag, and each associated transaction item in the target item group are input into the item recommendation model to obtain an item recommendation list output by the item recommendation model.

9. The method according to any one of claims 1 to 8, characterized in that The method further comprises: Sort the related transaction items in the project recommendation list according to the matching degree between the related transaction items in the project recommendation list and the project transaction application, and display the project recommendation list; receiving a request corresponding to the project recommendation list; The project recommendation model is optimized and trained based on the request corresponding to the project recommendation list to obtain an optimized and trained project recommendation model.

10. A transaction item recommendation device, characterized in that: include: An acquisition module, used to acquire historical transaction information of each user, and determine a user tag of each user according to the historical transaction information of each user; A user group determination module, configured to determine at least one user group according to each of the historical transaction information; wherein the user group includes one or more users located in the same area; A project group determination module, used to determine the project group corresponding to each user group according to the historical transaction information of each user in each user group; wherein the project group includes a plurality of related transaction projects; A model building module, used to build a project recommendation model according to each of the historical transaction information, each of the user tags and each of the project groups; The project recommendation module is used to respond to receiving a project transaction application, input the project transaction application into the project recommendation model, and obtain a project recommendation list output by the project recommendation model; wherein the project recommendation list includes one or more related transaction projects that match the project transaction application in the project group corresponding to the target user.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 9 when executed by a processor.

13. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 9 when being executed by a processor.

Images