Product pushing method and device
By obtaining user transaction records to generate multi-dimensional graphs, and clustering analysis with user multi-dimensional graphs based on product attributes to match target users in real time, solving the problem of long generation cycle and poor timeliness in the existing technology, achieving efficient and non-existence Accurate marketing of customer groups.
Patent Information
- Application Number
- CN202411006842.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-08
AI Technical Summary
The existing product push method generates customer groups with a long cycle, poor timeliness and low accuracy, resulting in waste of resources and insufficient marketing accuracy.
By obtaining user transaction records, generating multi-dimensional graphs, and clustering analysis with user multi-dimensional graphs based on product attributes, matching target users in real time, pushing products, avoiding pre-generating user groups, and improving data source utilization and system performance.
It realizes efficient precise product marketing of entities without customer groups, reduces generation cycles, improves timeliness, saves resources, and improves user data source utilization.
Smart Images

Figure CN118917916A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer technology, in particular to the field of artificial intelligence technology, and more particularly to a product push method and device. Background Art
[0002] Currently, product push is based on the target customer groups that have been generated. The customer group function currently exists in different systems in multiple fields. In related technologies, customer groups are usually generated by setting certain restrictions through page transactions or directly uploading customer groups lists. Customer groups between multiple systems can share customer group details by mutually authorizing the tables of their respective systems. However, this method has a long generation cycle and poor timeliness. The data sources for different restrictions often come from different systems, and the data update time is not uniform. The accuracy and matching degree of generated customer groups are low, and the utilization rate of customer sources is insufficient, resulting in waste of resources, which leads to low product marketing accuracy. Summary of the invention
[0003] One object of the present invention is to provide a product push method, which improves the utilization rate of user data sources, saves resources, does not need to pre-generate user group entities, improves system performance, can match target users in real time, reduces generation cycles, improves timeliness, and thus achieves efficient precision product marketing without customer group entities. Another object of the present invention is to provide a product push device. Another object of the present invention is to provide a computer-readable medium. Still another object of the present invention is to provide a computer device.
[0004] In order to achieve the above objectives, the present invention discloses a product push method, comprising:
[0005] Get the user's transaction records;
[0006] Build multi-dimensional data based on transaction records to generate a multi-dimensional user graph;
[0007] Perform cluster analysis based on product attributes and user multi-dimensional graphs to generate target users for the products to be pushed, and then push the products to be pushed to the target users.
[0008] Preferably, multi-dimensional data is constructed based on transaction records to generate a multi-dimensional graph of users, including:
[0009] Build basic data based on transaction records and generate a basic data base;
[0010] Perform multi-dimensional data statistics based on the basic data base to generate a multi-dimensional user graph.
[0011] Preferably, basic data is constructed based on transaction records to generate a basic data base, including:
[0012] Extract the latest transaction time, transaction frequency and transaction amount from the transaction records;
[0013] By comparing the latest transaction time, transaction frequency and transaction amount corresponding to each user with the preset latest transaction time threshold, transaction frequency threshold and transaction amount threshold, a user tag corresponding to the user is generated;
[0014] Generate a basic data base based on the user tags and transaction records corresponding to the user.
[0015] Preferably, multi-dimensional data statistics are performed based on the basic data base to generate a multi-dimensional user graph, including:
[0016] According to the preset multiple dimensions and transaction records, multi-dimensional product transaction information is calculated, including the time difference between the specified time point and the most recent transaction time of each type of product, the total number of transactions in the specified time period, the total transaction amount in the specified time period, the time difference between the current time point and the most recent transaction time of each type of product, the number of transactions of each type of product, the transaction amount of each type of product, and the transaction proportion of each type of product during the discount period;
[0017] A user multi-dimensional graph is generated based on the multi-dimensional product transaction information corresponding to the user.
[0018] Preferably, cluster analysis is performed based on the product attributes and the user multi-dimensional graph to generate target users corresponding to the product to be pushed, including:
[0019] According to the user multi-dimensional graph, users are sorted according to their multi-dimensional product transaction information to generate candidate user groups;
[0020] According to product attributes, users in the candidate user group are matched to filter out target users.
[0021] Preferably, pushing the product to be pushed to the target user includes:
[0022] Query the user tag corresponding to the target user;
[0023] Match the corresponding target push strategy according to user tags;
[0024] According to the target push strategy, push the products to be pushed to the target users.
[0025] The present invention also discloses a product pushing device, comprising:
[0026] An acquisition unit, used to acquire a user's transaction records;
[0027] A multi-dimensional graph generation unit, used to construct multi-dimensional data based on transaction records and generate a user multi-dimensional graph;
[0028] The product push unit is used to perform cluster analysis based on the product attributes and user multi-dimensional graph, generate target users corresponding to the products to be pushed, and push the products to be pushed to the target users.
[0029] The present invention also discloses a computer-readable medium on which a computer program is stored. When the program is executed by a processor, the method described above is implemented.
[0030] The present invention also discloses a computer device, including a memory and a processor, wherein the memory is used to store information including program instructions, the processor is used to control the execution of program instructions, and the processor implements the above method when executing the program.
[0031] The present invention also discloses a computer program product, including a computer program / instruction, and the method described above is implemented when the computer program / instruction is executed by a processor.
[0032] The present invention obtains the transaction records of users; constructs multidimensional data according to the transaction records to generate a multidimensional graph of users; performs cluster analysis according to the product attributes of the products and the multidimensional graph of users to generate target users corresponding to the products to be pushed, and pushes the products to be pushed to the target users, performs adhesion cluster analysis with the multidimensional graph of all users and the products to be pushed, thereby improving the utilization rate of user data sources, saving resources, and eliminating the need to pre-generate user group entities, improving system performance, being able to match target users in real time, reducing generation cycles, and improving timeliness, thereby achieving efficient precision product marketing without customer group entities. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0034] Figure 1 A flowchart of a product push method provided by an embodiment of the present invention;
[0035] Figure 2 A flowchart of another product push method provided by an embodiment of the present invention;
[0036] Figure 3 A schematic diagram of the structure of a product pushing device provided by an embodiment of the present invention;
[0037] Figure 4A schematic diagram of the structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0039] It should be noted that the product push method and device disclosed in the present application can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology. The application field of the product push method and device disclosed in the present application is not limited.
[0040] In order to facilitate the understanding of the technical solution provided by the present application, the relevant contents of the technical solution of the present application are first explained below. Customer group, that is, a collection of customers. It is to aggregate customers with certain common characteristics or attributes into a group. The customers in this group can be collected at a time point according to certain conditions, or they can be set in a time period and enter the group only when the conditions are met according to certain conditions.
[0041] The following takes the product push device as an example to illustrate the implementation process of the product push method provided by the embodiment of the present invention. It is understandable that the execution subject of the product push method provided by the embodiment of the present invention includes but is not limited to the product push device.
[0042] Figure 1 A flowchart of a product push method provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes:
[0043] Step 101: Obtain the user's transaction records.
[0044] Step 102: Build multi-dimensional data based on transaction records to generate a multi-dimensional graph of users.
[0045] Step 103: Perform cluster analysis based on the product attributes and the user multi-dimensional graph to generate target users corresponding to the products to be pushed, and push the products to be pushed to the target users.
[0046] In the technical solution provided by the embodiment of the present invention, the transaction records of users are obtained; multi-dimensional data is constructed according to the transaction records to generate a multi-dimensional graph of users; cluster analysis is performed according to the product attributes of the products and the multi-dimensional graph of users to generate target users corresponding to the products to be pushed, and the products to be pushed are pushed to the target users. The adhesion cluster analysis is performed with the multi-dimensional graph of all users and the products to be pushed, so as to improve the utilization rate of the user data source, save resources, and do not need to generate user group entities in advance, so as to improve the system performance, be able to match target users in real time, improve the system performance, reduce the generation cycle, and improve the timeliness, thereby realizing efficient and precise product marketing without customer group entities.
[0047] Figure 2 A flowchart of another product push method provided by an embodiment of the present invention, such as Figure 2 As shown, the method includes:
[0048] Step 201: Obtain the user's transaction records.
[0049] In the embodiment of the present invention, each step is executed by a product pushing device.
[0050] In the embodiment of the present invention, the database stores transaction records of all users, and the transaction records of all users can be obtained from the database. The transaction record is all data in the user's transaction process, and the data in the transaction record includes but is not limited to user identification, transaction time, transaction amount, transaction product identification, transaction product type and transaction preferential activities.
[0051] Step 202: Build basic data based on transaction records to generate a basic data base.
[0052] In the embodiment of the present invention, step 202 specifically includes:
[0053] Step 2021: extract the most recent transaction time, transaction frequency and transaction amount from the transaction records.
[0054] In the embodiment of the present invention, according to the RFM model, namely: the last purchase time (Recency, R), transaction frequency (F) and transaction amount (Monetary, M), the last transaction time, transaction frequency and transaction amount are extracted from the transaction records according to different transaction product types. Among them, the R value is to calculate the interval between the last transaction date of the user and the current date; the F value is to count the number of transactions of the user within a certain period of time; the M value is to calculate the total transaction amount or average transaction amount of the user within a certain period of time.
[0055] Step 2022: Compare the latest transaction time, transaction frequency and transaction amount corresponding to each user with the preset latest transaction time threshold, transaction frequency threshold and transaction amount threshold to generate a user tag corresponding to the user.
[0056] In the embodiment of the present invention, the most recent transaction time threshold, the transaction frequency threshold, and the transaction amount threshold can be set according to actual needs, and the embodiment of the present invention does not limit this.
[0057] Specifically, it is determined whether the most recent transaction time of each user is greater than the most recent transaction time threshold. If so, it indicates that the user has a recent transaction, and the user's most recent purchase time (Recency, R) level is set to high; if not, it indicates that the user has no recent transaction, and the user's most recent purchase time (Recency, R) level is set to low.
[0058] Specifically, it is determined whether the transaction frequency of each user is greater than the transaction frequency threshold. If so, it indicates that the transaction frequency of the user is high, and the transaction frequency (Frequency, F) level of the user is set to high; if not, it indicates that the transaction frequency of the user is low, and the transaction frequency (Frequency, F) level of the user is set to low.
[0059] Specifically, it is determined whether the transaction amount of each user is greater than the transaction amount threshold. If so, it indicates that the transaction amount of the user is high, and the transaction amount (Monetary, M) level of the user is set to high; if not, it indicates that the transaction amount of the user is low, and the transaction amount (Monetary, M) level of the user is set to low.
[0060] In the embodiment of the present invention, user tags include but are not limited to high-value users, key retention users, key development users, key retention users, general value users, general retention users, general development users and potential users. As an optional solution, the mapping relationship between the user's corresponding latest transaction time, transaction frequency and transaction amount and the user tag is shown in Table 1:
[0061] Table 1
[0062] R F M User Tags high high high High value users Low high high Focus on retaining users high Low high Focus on developing users Low Low high Focus on retaining users high high Low General value users Low high Low Generally keep users high Low Low General development users Low Low Low Potential Users
[0063] According to the user's RFM level, the corresponding user tag is matched.
[0064] Step 2023: Generate a basic data base based on the user tags and transaction records corresponding to the user.
[0065] Specifically, based on the RFM model, a basic data base is generated according to user identification and corresponding user tags and transaction records for subsequent multi-dimensional graph generation.
[0066] Furthermore, the basic data base is updated according to a preset cycle to ensure the reliability of the data in the basic data base, thereby ensuring the accuracy of subsequent determination of target users and product push.
[0067] It is worth noting that the preset period can be set according to actual needs, and the embodiment of the present invention does not limit this. As an optional solution, the preset period is one day, that is, the basic data base is updated once a day.
[0068] Step 203: Perform multi-dimensional data statistics based on the basic data base to generate a user multi-dimensional graph.
[0069] In the embodiment of the present invention, step 203 specifically includes:
[0070] Step 2031: Calculate multi-dimensional product transaction information based on transaction records according to preset multiple dimensions.
[0071] In the embodiment of the present invention, the multi-dimensional product transaction information includes but is not limited to the time difference between the specified time point and the last transaction time of each type of product, the total number of transactions in the specified time period, the total transaction amount in the specified time period, the time difference between the current time point and the last transaction time of each type of product, the number of transactions of each type of product, the transaction amount of each type of product, and the transaction ratio of each type of product during the preferential period. Among them, the transaction ratio of each type of product during the preferential period is the ratio between the number of transactions of each type of product using the transaction preferential activities during the preferential period and the total number of transactions.
[0072] It is worth noting that the specified time point is the time point that needs to be counted, which can be set according to actual needs, and the embodiment of the present invention does not limit this; the specified time period is the time period from the time point of statistics to the current time point;
[0073] It is worth noting that multiple dimensions can be set according to actual needs, and the embodiment of the present invention does not limit this. As an optional solution, the embodiment of the present invention takes the seven-dimensional attributes of the user as an example to count and generate the seven-dimensional graph of the user.
[0074] Step 2032: Generate a user multi-dimensional graph based on the multi-dimensional product transaction information corresponding to the user.
[0075] In the embodiment of the present invention, the user multi-dimensional graph includes a user identification and a corresponding user tag as well as multi-dimensional product transaction information.
[0076] Step 204: sort the users according to their multi-dimensional product transaction information based on the user multi-dimensional graph to generate a candidate user group.
[0077] In an embodiment of the present invention, the user multi-dimensional graph includes but is not limited to the time difference between each type of product at a specified time point and the most recent transaction time, the total number of transactions within a specified time period, the total transaction amount within a specified time period, the time difference between each type of product at the current time point and the most recent transaction time, the number of transactions of each type of product, the transaction amount of each type of product, and the transaction proportion of each type of product during the discount period.
[0078] Specifically, the time difference between the current time point and the most recent transaction time for each type of product corresponding to each user tag is sorted from low to high to generate a recent transaction candidate user group corresponding to each type of product. There is a higher degree of adhesion between the users ranked first and the product of this type, and the users ranked first have a priority push level.
[0079] Specifically, the transaction times of each type of product corresponding to each user tag are sorted from high to low to generate a candidate user group of transaction times corresponding to each type of product. There is a higher degree of adhesion between the users ranked first and the products of this type, and the users ranked first have a priority push level.
[0080] Specifically, the transaction amounts of various types of products corresponding to each user tag are sorted from high to low to generate candidate user groups of transaction amounts corresponding to various types of products. Users ranked at the front have a higher degree of adhesion with the products of this type, and users ranked at the front have a priority push level.
[0081] Specifically, the transaction proportions during the discount period for each type of product corresponding to each user tag are sorted from high to low to generate a candidate user group for the transaction amount corresponding to each type of product. There is a higher degree of adhesion between the users ranked first and the product of this type, and the users ranked first have a priority push level.
[0082] Step 205: Match the users in the candidate user group according to product attributes to screen out target users.
[0083] In the embodiment of the present invention, the product attributes of the product are matched with the types of each candidate user group, and users with high priority push levels are selected, that is, users ranked first are selected, and the selected users are determined as target users. Product attributes include but are not limited to product type, product amount and product discount activities.
[0084] Furthermore, the target users that meet the derived rules can also be determined through preset derived rules. The derived rules can be set by the marketing personnel according to actual needs, and the embodiments of the present invention do not limit this. The derived rules include but are not limited to time periods, amount intervals, frequency intervals, product types, and user tags.
[0085] Step 206: Query the user tag corresponding to the target user.
[0086] Specifically, according to the user identification of the target user, the corresponding user tag is matched based on the basic data base or the user multi-dimensional graph.
[0087] Step 207: Match the corresponding target push strategy according to the user tag.
[0088] In the embodiment of the present invention, the target push strategy can be set according to actual needs, and the embodiment of the present invention does not limit this.
[0089] As an optional solution, the mapping relationship between user tags and push strategies is shown in Table 2:
[0090] Table 2
[0091]
[0092] Step 208: Push the product to be pushed to the target user according to the target push strategy.
[0093] In the embodiment of the present invention, products to be pushed are selected according to the target push strategy; target users are grouped separately, and relevant information of the products to be pushed is pushed to the user terminals of the target users at a specified time point or in a specified time period for the target users to view and purchase, thereby achieving precision marketing without generating customer group entities, and no entity details of each customer group are stored in the database, saving storage resources.
[0094] It is worth noting that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of laws and regulations. The user information in the embodiments of this application is obtained through legal and compliant channels, and the acquisition, storage, use, and processing of user information are authorized and agreed by the customer.
[0095] It is worth noting that the information collected in this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.
[0096] It is worth noting that the technical solution provided in this application provides users with corresponding operation entrances for them to choose to agree or reject the automated decision-making results; if the user chooses to reject, the expert decision-making process will be entered.
[0097] In the technical solution of the product push method provided by the embodiment of the present invention, the user's transaction record is obtained; multi-dimensional data is constructed according to the transaction record to generate a user multi-dimensional graph; cluster analysis is performed according to the product attributes of the product and the user multi-dimensional graph to generate the target user corresponding to the product to be pushed, and the product to be pushed is pushed to the target user, and the adhesion cluster analysis is performed with the multi-dimensional graph of all users and the product to be pushed, so as to improve the utilization rate of the user data source, save resources, do not need to generate user group entities in advance, improve system performance, be able to match target users in real time, reduce the generation cycle, and improve timeliness, thereby realizing efficient precision product marketing without customer group entities.
[0098] Figure 3 A schematic diagram of the structure of a product pushing device provided in an embodiment of the present invention, wherein the device is used to execute the above-mentioned product pushing method, such as Figure 3 As shown, the device includes: an acquisition unit 11, a multi-dimensional graph generation unit 12 and a product push unit 13.
[0099] The acquisition unit 11 is used to acquire the transaction records of the user.
[0100] The multi-dimensional graph generation unit 12 is used to construct multi-dimensional data according to the transaction records to generate a multi-dimensional graph of the user.
[0101] The product push unit 13 is used to perform cluster analysis according to the product attributes of the product and the user multi-dimensional graph, generate target users corresponding to the products to be pushed, and push the products to be pushed to the target users.
[0102] In the embodiment of the present invention, the multi-dimensional graph generation unit 12 is specifically used to build basic data according to transaction records to generate a basic data base; perform multi-dimensional data statistics according to the basic data base to generate a user multi-dimensional graph.
[0103] In an embodiment of the present invention, the multi-dimensional graph generation unit 12 is specifically used to extract the most recent transaction time, transaction frequency and transaction amount from the transaction records; compare the most recent transaction time, transaction frequency and transaction amount corresponding to each user through the preset most recent transaction time threshold, transaction frequency threshold and transaction amount threshold, and generate a user tag corresponding to the user; generate a basic data base based on the user tag and transaction record corresponding to the user.
[0104] In an embodiment of the present invention, the multi-dimensional graph generating unit 12 is specifically used to count multi-dimensional product transaction information according to transaction records in accordance with preset multiple dimensions, the multi-dimensional product transaction information including the time difference between a specified time point and the most recent transaction time for each type of product, the total number of transactions within a specified time period, the total transaction amount within a specified time period, the time difference between the current time point and the most recent transaction time for each type of product, the number of transactions for each type of product, the transaction amount for each type of product, and the transaction proportion of each type of product during the discount period; a user multi-dimensional graph is generated according to the multi-dimensional product transaction information corresponding to the user.
[0105] In the embodiment of the present invention, the product push unit 13 is specifically used to sort users according to the user multi-dimensional graph and the multi-dimensional product transaction information of the users to generate a candidate user group; and to match the users in the candidate user group according to the product attributes to screen out the target users.
[0106] In the embodiment of the present invention, the product push unit 13 is specifically used to query the user tag corresponding to the target user; match the corresponding target push strategy according to the user tag; and push the product to be pushed to the target user according to the target push strategy.
[0107] In the scheme of the embodiment of the present invention, the transaction records of users are obtained; multi-dimensional data is constructed based on the transaction records to generate a multi-dimensional graph of users; cluster analysis is performed based on the product attributes of the products and the multi-dimensional graph of users to generate target users corresponding to the products to be pushed, and the products to be pushed are pushed to the target users. The adhesion cluster analysis is performed with the multi-dimensional graph of all users and the products to be pushed, thereby improving the utilization rate of the user data source and saving resources. There is no need to generate user group entities in advance, which improves system performance, can match target users in real time, reduces the generation cycle, and improves timeliness, thereby realizing efficient and precise product marketing without customer group entities.
[0108] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0109] An embodiment of the present invention provides a computer device, including a memory and a processor, the memory is used to store information including program instructions, the processor is used to control the execution of the program instructions, and when the program instructions are loaded and executed by the processor, the steps of the embodiment of the above-mentioned product push method are implemented. For a specific description, please refer to the embodiment of the above-mentioned product push method.
[0110] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.
[0111] like Figure 4 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate operations and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer device 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0112] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.
[0113] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from the removable medium 611.
[0114] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0115] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0116] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0117] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0118] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0119] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0120] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.
[0121] 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.
[0122] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0123] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0124] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0125] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A product push method, It is characterized in that The method comprises: Get the user's transaction records; Construct multi-dimensional data based on the transaction records to generate a multi-dimensional graph of users; Cluster analysis is performed based on the product attributes of the product and the user multi-dimensional graph to generate target users corresponding to the product to be pushed, and the product to be pushed is pushed to the target user.
2. The product push method according to claim 1, It is characterized in that The step of constructing multi-dimensional data according to the transaction records to generate a multi-dimensional graph of users includes: Build basic data according to the transaction records to generate a basic data base; Multi-dimensional data statistics are performed based on the basic data base to generate the user multi-dimensional graph.
3. The product push method according to claim 2, It is characterized in that The step of constructing basic data according to the transaction records to generate a basic data base includes: Extracting the most recent transaction time, transaction frequency and transaction amount from the transaction records; By comparing the latest transaction time, transaction frequency and transaction amount corresponding to each user with the preset latest transaction time threshold, transaction frequency threshold and transaction amount threshold, a user tag corresponding to the user is generated; The basic data base is generated according to the user tag corresponding to the user and the transaction record.
4. The product push method according to claim 2, It is characterized in that The performing multi-dimensional data statistics according to the basic data base to generate the user multi-dimensional graph includes: According to the preset multiple dimensions, based on the transaction records, multi-dimensional product transaction information is counted, and the multi-dimensional product transaction information includes the time difference between the specified time point and the most recent transaction time of each type of product, the total number of transactions in the specified time period, the total transaction amount in the specified time period, the time difference between the current time point and the most recent transaction time of each type of product, the number of transactions of each type of product, the transaction amount of each type of product, and the transaction proportion of each type of product during the discount period; The user multi-dimensional graph is generated according to the multi-dimensional product transaction information corresponding to the user.
5. The product push method according to claim 1, It is characterized in that The cluster analysis is performed according to the product attributes of the product and the user multi-dimensional graph to generate target users corresponding to the product to be pushed, including: According to the user multi-dimensional graph, the users are sorted according to their multi-dimensional product transaction information to generate a candidate user group; According to the product attributes, users in the candidate user group are matched to screen out the target users.
6. The product push method according to claim 1, It is characterized in that The step of pushing the product to be pushed to the target user includes: Querying a user tag corresponding to the target user; Matching a corresponding target push strategy according to the user tag; According to the target push strategy, the product to be pushed is pushed to the target user.
7. A product pushing device, It is characterized in that The device comprises: An acquisition unit, used to acquire a user's transaction records; A multi-dimensional graph generating unit, used to construct multi-dimensional data according to the transaction records to generate a multi-dimensional graph of the user; The product push unit is used to perform cluster analysis according to the product attributes of the product and the user multi-dimensional graph, generate target users corresponding to the products to be pushed, and push the products to be pushed to the target users.
8. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the product push method described in any one of claims 1 to 6 is implemented.
9. A computer device comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions. It is characterized in that When the program instructions are loaded and executed by the processor, the product push method according to any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program / instructions, It is characterized in that When the computer program / instructions are executed by a processor, the product push method according to any one of claims 1 to 6 is implemented.
