Merchant portrait generation method and device based on artificial intelligence, equipment and medium

Abstract

The application provides a merchant portrait generation method and device based on artificial intelligence, an electronic device and a storage medium. The merchant portrait generation method based on artificial intelligence comprises the following steps: screening registered merchants of a transaction platform to obtain an active merchant set; collecting transaction data of the merchants in the active merchant set to obtain a merchant transaction data set; counting transaction frequencies of the merchants in the merchant transaction data set to obtain a transaction frequency mean value; dividing the transaction frequencies based on the transaction frequency mean value to obtain a high-frequency transaction time period; counting different categories of payment methods and payment limits in the merchant transaction data set to obtain a channel transaction limit; and constructing a merchant portrait based on the high-frequency transaction time period and the channel transaction limit to formulate different merchant portrait strategies. The application can effectively improve the service efficiency for merchants by obtaining the high-frequency transaction time period of the merchants and combining the obtained channel transaction limit to generate the merchant portrait.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, electronic device and storage medium for generating merchant profiles based on artificial intelligence. Background Technology

[0002] User profiles generally refer to a labeled user model abstracted from a large amount of information collected based on user demographic characteristics, such as online browsing content, online social activities, and various consumption behaviors in daily life. This information is then standardized, categorized, and subjected to precise model calculations.

[0003] Existing user profiles generally describe consumers, with very few merchant profiles. However, merchants possess a large amount of real transaction data. Therefore, in the daily maintenance and operation of the transaction platform, if merchant profiles can be generated based on transaction data, different operation and marketing strategies can be effectively formulated for different merchant profiles, thereby improving the efficiency of services to merchants. Summary of the Invention

[0004] In view of the above, it is necessary to propose a merchant profile generation method, device, electronic device and storage medium based on artificial intelligence to solve the technical problem of how to improve the efficiency of service to users.

[0005] This application provides a method for generating merchant profiles based on artificial intelligence, the method comprising:

[0006] Filter registered merchants on the trading platform to obtain a set of active merchants;

[0007] Collect transaction data from the active merchants in the centralized merchant database to obtain a merchant transaction dataset;

[0008] The transaction frequency of merchants in the merchant transaction dataset is statistically analyzed to obtain the average transaction frequency.

[0009] The transaction frequency is divided based on the average transaction frequency to obtain high-frequency transaction time periods;

[0010] The channel transaction limit is obtained by statistically analyzing the different categories of payment methods and payment amounts in the merchant transaction dataset.

[0011] Merchant profiles are constructed based on the high-frequency trading time periods and the channel transaction amounts to formulate different merchant profile strategies.

[0012] In some embodiments, the process of filtering registered merchants on the trading platform to obtain an active merchant set includes:

[0013] Statistical analysis of transaction volume of registered merchants on the trading platform;

[0014] Based on their transaction volume, the registered merchants are divided into a high-activity merchant group and a low-activity merchant group;

[0015] The merchants in the low-activity merchant cluster are filtered to obtain a low-activity effective merchant cluster;

[0016] The set of highly active merchants and the set of inactive but valid merchants are defined as the active merchant set.

[0017] In some embodiments, filtering the merchants in the inactive merchant set to obtain a set of inactive valid merchants includes:

[0018] Push inspection and verification information to the merchants where inactive merchants are concentrated;

[0019] If the merchants in the low-activity merchant cluster perform verification according to the instructions of the inspection verification information, the verification is successful;

[0020] If the merchants in the low-activity merchant cluster do not perform the verification according to the instructions of the inspection verification information, the verification will fail.

[0021] All verified merchants are grouped into a low-activity, active merchant set.

[0022] In some embodiments, obtaining a merchant transaction dataset by collecting transaction data from the active merchant pool includes:

[0023] A transaction log dataset is obtained by collecting log data from the active merchants in the transaction platform.

[0024] The transaction log dataset is preprocessed to obtain a structured dataset;

[0025] The structured dataset is anonymized to obtain the merchant transaction dataset.

[0026] In some embodiments, the step of calculating the transaction frequency of merchants in the merchant transaction dataset to obtain the average transaction frequency includes:

[0027] The transaction frequency set of each merchant in the transaction dataset is obtained by statistically analyzing the transaction frequency of each merchant within a preset time interval.

[0028] The unit transaction frequencies in the unit transaction frequency set are sorted in descending order to obtain a transaction frequency sequence;

[0029] A stable transaction frequency sequence is obtained by truncating the transaction frequency sequence according to a preset threshold range;

[0030] The average value of each unit transaction frequency in the stable transaction frequency sequence is calculated as the transaction frequency mean.

[0031] In some embodiments, dividing the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods includes:

[0032] The unit transaction frequency is divided into multiple time period frequency datasets according to a preset time period;

[0033] The average of all unit transaction frequencies in the time period frequency dataset is calculated as the time period frequency mean.

[0034] The average frequency of the time period is compared with the average frequency of the transaction, and the time periods corresponding to all time periods with a frequency greater than the average frequency of the transaction are defined as high-frequency trading time periods.

[0035] In some embodiments, obtaining the channel transaction limit by statistically analyzing different categories of payment methods and payment amounts in the merchant transaction dataset includes:

[0036] The different categories of payment methods in the merchant transaction dataset are statistically analyzed;

[0037] Statistics on the number of merchants and total payment amount for each payment method;

[0038] The ratio of the total payment amount to the number of merchants is used as the channel transaction limit for the corresponding payment method category.

[0039] This application also provides an artificial intelligence-based merchant profile generation device, which includes a filtering module, a collection module, a statistics module, a clustering module, an acquisition module, and a construction module.

[0040] The filtering module is used to filter registered merchants on the trading platform to obtain a set of active merchants;

[0041] The acquisition module is used to collect transaction data from the active merchants in the merchant cluster to obtain a merchant transaction dataset.

[0042] The statistics module is used to calculate the transaction frequency of merchants in the merchant transaction data to obtain the average transaction frequency.

[0043] The clustering module is used to divide the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods;

[0044] The acquisition module is used to statistically analyze the different types of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction amount;

[0045] The construction module is used to build merchant profiles based on the high-frequency trading period and the channel transaction amount in order to formulate different merchant profile strategies.

[0046] This application embodiment also provides an electronic device, the electronic device comprising:

[0047] Memory, storing at least one instruction;

[0048] The processor executes the instructions stored in the memory to implement the artificial intelligence-based merchant profile generation method.

[0049] This application also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the artificial intelligence-based merchant profile generation method.

[0050] This application obtains merchants' high-frequency transaction periods by collecting transaction frequency data at different times, and combines this with the obtained channel transaction amount to generate merchant profiles. This allows for the development of different operation and marketing strategies for different merchant profiles, thereby improving service efficiency for merchants. Attached Figure Description

[0051] Figure 1 This is a flowchart of a preferred embodiment of the merchant profile generation method based on artificial intelligence involved in this application.

[0052] Figure 2 This is a functional block diagram of a preferred embodiment of the merchant profile generation device based on artificial intelligence involved in this application.

[0053] Figure 3 This is a schematic diagram of the structure of an electronic device that is a preferred embodiment of the merchant profile generation method based on artificial intelligence involved in this application. Detailed Implementation

[0054] To better understand the purpose, features, and advantages of this application, a detailed description of the application is provided below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other. Numerous specific details are set forth in the following description to provide a thorough understanding of this application; the described embodiments are only a part of the embodiments of this application, and not all of them.

[0055] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0056] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0057] This application provides a merchant profile generation method based on artificial intelligence, which can be applied to one or more electronic devices. An electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0058] Electronic devices can be any electronic product that allows human-computer interaction with a customer, such as personal computers, tablets, smartphones, personal digital assistants (PDAs), game consoles, interactive network television (IPTV), smart wearable devices, etc.

[0059] Electronic devices may also include network devices and / or client devices. The network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0060] The networks in which electronic devices are located include, but are not limited to, the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0061] like Figure 1 The diagram shown is a flowchart of a preferred embodiment of the merchant profile generation method based on artificial intelligence according to this application. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different needs.

[0062] S10 filters registered merchants on the trading platform to obtain an active merchant set.

[0063] In an optional embodiment, the process of filtering registered merchants on the trading platform to obtain an active merchant set includes:

[0064] Statistical analysis of transaction volume of registered merchants on the trading platform;

[0065] Based on their transaction volume, the registered merchants are divided into a high-activity merchant group and a low-activity merchant group;

[0066] The merchants in the low-activity merchant cluster are filtered to obtain a low-activity effective merchant cluster;

[0067] The set of highly active merchants and the set of inactive but valid merchants are defined as the active merchant set.

[0068] In this optional embodiment, the transaction volume published by each registered merchant on the trading platform within a preset time period can be statistically analyzed. The trading platform can be an e-commerce trading platform, and the preset time period can be one month.

[0069] In this optional embodiment, the acquired transaction volumes can be sorted in descending order, and all merchants corresponding to the bottom 30% of transaction volumes can be designated as the inactive merchant set, while all merchants corresponding to the top 70% of transaction volumes can be designated as the highly active merchant set. For example, if an e-commerce platform has 1000 merchants, after sorting them by transaction volume in descending order, all merchants corresponding to the top 700 of transaction volumes can be designated as the highly active merchant set, and all merchants corresponding to the bottom 300 of transaction volumes can be designated as the inactive merchant set.

[0070] In this optional embodiment, for the merchants in the low-activity merchant cluster, the low transaction volume may be caused by objective reasons such as the product store, or it may be caused by the merchants' own lack of initiative. Therefore, by pushing inspection and verification information to the merchants in the low-activity merchant cluster, the merchants who are not subjectively proactive can be screened, thereby retaining more active merchants, which is beneficial to obtaining more accurate merchant transaction information in the subsequent process.

[0071] In this optional embodiment, the inspection verification information can be internal inspection verification information pushed by the transaction platform, or inspection verification information sent to merchants via SMS or other means. The inspection verification information can be a unified URL verification link. For example, the inspection verification information can be: "Hello, please click the following URL link to complete the merchant inspection verification service. After verification, you will receive a red envelope reward sent by the platform. Thank you for your cooperation."

[0072] In this optional embodiment, if merchants in the low-activity merchant set perform verification according to the instructions of the inspection verification information, the verification passes; if merchants in the low-activity merchant set do not perform verification according to the instructions of the inspection verification information, the verification fails; all verified merchants are considered as the low-activity valid merchant set. In this scheme, the high-activity merchant set and the low-activity valid merchant set are considered as the active merchant set.

[0073] In this way, merchants with high activity levels can be identified through initial screening, which is beneficial for collecting more accurate merchant transaction information in subsequent processes.

[0074] S11, Collect transaction data of the active merchants in the centralized merchant pool to obtain a merchant transaction dataset.

[0075] In an optional embodiment, the step of collecting transaction data from the active merchant pool to obtain the merchant transaction dataset includes:

[0076] A transaction log dataset is obtained by collecting log data from the active merchants in the transaction platform.

[0077] The transaction log dataset is preprocessed to obtain a structured dataset;

[0078] The structured dataset is anonymized to obtain the merchant transaction dataset.

[0079] In this optional embodiment, the transaction log dataset can be obtained by collecting log data from the active merchants in the e-commerce transaction platform through the log collection system Flume. Flume is a distributed, reliable, and highly available system for collecting, aggregating, and transmitting massive log data. It is used to collect transaction data from data merchants in the log collection system. The transaction data may include information such as order volume, transaction amount, store type, merchant name, business address, and business content.

[0080] In this optional embodiment, the log data in the acquired transaction log dataset can be processed by the log analysis processor pre-built in the log collection system Flume to obtain two-dimensional table data carrying header information, i.e., structured data. In this solution, the obtained structured data is used as a structured dataset.

[0081] In this optional embodiment, the structured data in the structured dataset can be anonymized. The structured data consists of data columns with different data attributes. These data columns can be divided into identifiable columns, semi-identifiable columns, columns containing sensitive merchant information, and other columns that do not contain sensitive merchant information. Identifiable columns are those that can accurately locate a specific merchant, such as ID card number, merchant address, and merchant name. Semi-identifiable columns are those that cannot locate a specific merchant on a single column, such as postal code, birthday, and gender. Columns containing sensitive merchant information include bank account number and profit / revenue. Anonymization of the structured data can be performed by removing identifiable columns, removing columns containing sensitive merchant information, etc. In this solution, the anonymized structured data is used as the structured dataset.

[0082] In this way, while acquiring transaction data from the active merchant pool, the privacy data of the merchants can be protected from being leaked, thus improving the security of merchant transaction data.

[0083] S12, Calculate the transaction frequency of merchants in the merchant transaction data to obtain the average transaction frequency.

[0084] In an optional embodiment, the step of calculating the transaction frequency of merchants in the merchant transaction dataset to obtain the average transaction frequency includes:

[0085] The transaction frequency set of each merchant in the transaction dataset is obtained by statistically analyzing the transaction frequency of each merchant within a preset time interval.

[0086] The unit transaction frequencies in the unit transaction frequency set are sorted in descending order to obtain a transaction frequency sequence;

[0087] A stable transaction frequency sequence is obtained by truncating the transaction frequency sequence according to a preset threshold range;

[0088] The average value of each unit transaction frequency in the stable transaction frequency sequence is calculated as the transaction frequency mean.

[0089] In this optional embodiment, the transaction frequency of each merchant in the transaction dataset can be statistically analyzed within a preset time interval. The preset time interval can be one minute, that is, the transaction volume of each merchant per minute is counted as the unit transaction frequency, and a unit transaction frequency set is obtained by collecting the unit transaction frequencies of all merchants within a certain time period. For example, the unit transaction frequency set can be constructed by collecting all unit transaction frequencies of all merchants within a month.

[0090] In this optional embodiment, the unit transaction frequencies in the unit transaction frequency set can be sorted in descending order to obtain a transaction frequency sequence. The transaction frequency sequence can be truncated by a preset threshold range to obtain a stable transaction frequency sequence. Finally, the average value of each unit transaction frequency in the stable transaction frequency sequence is calculated as the transaction frequency mean. The preset threshold range can be from 21% to 80%.

[0091] For example, the unit transaction frequency set contains 100 unit transaction frequency data. After sorting the unit transaction frequencies in descending order, a transaction frequency sequence is obtained. Then, the top 20 and bottom 20 transaction frequency data in the transaction frequency sequence are discarded, and the remaining 60 transaction frequency data are used as a stable transaction frequency sequence. That is, the unit transaction frequency data ranked from 21 to 80 in the transaction frequency sequence are used as a stable transaction frequency sequence through a preset threshold range. Finally, the average value of each unit transaction frequency in the stable transaction frequency sequence is used as the transaction frequency mean.

[0092] In this optional embodiment, since the data with the highest and lowest unit transaction frequency is prone to data distortion and cannot effectively represent the true unit transaction frequency of most merchants, obtaining the average transaction frequency can more accurately represent the true transaction frequency of most merchants.

[0093] Thus, by obtaining the average transaction frequency of the unit transaction frequency of the merchants in the merchant transaction dataset, the true transaction frequency of most merchants can be obtained more accurately and effectively, which is beneficial to improving the accuracy of transaction frequency classification in subsequent processes.

[0094] S13, the transaction frequency is divided based on the average transaction frequency to obtain high-frequency transaction time periods.

[0095] In an optional embodiment, dividing the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods includes:

[0096] The unit transaction frequency is divided into multiple time period frequency datasets according to a preset time period;

[0097] The average of all unit transaction frequencies in the time period frequency dataset is calculated as the time period frequency mean.

[0098] The average frequency of the time period is compared with the average frequency of the transaction, and the time periods corresponding to all time periods with a frequency greater than the average frequency of the transaction are defined as high-frequency trading time periods.

[0099] In this optional embodiment, all the obtained unit transaction frequencies are divided into time periods according to a preset time period, which can be an hour. That is, all the unit transaction frequencies are divided into time periods according to an hour, and all the unit transaction frequencies included in each hour are used as time period frequency datasets to obtain multiple time period frequency datasets.

[0100] In this optional embodiment, the average value of all unit transaction frequencies in each time period frequency dataset can be calculated as the time period frequency mean corresponding to that time period frequency dataset. By comparing the time period frequency mean with the transaction frequency mean, all time periods corresponding to the time period frequency mean greater than the transaction frequency mean are regarded as high-frequency transaction time periods for time cycles such as daily, weekly, or monthly, and these high-frequency transaction time periods are used as the profile tags of merchants.

[0101] In this way, the transaction frequency of the unit can be divided according to the preset time period, thereby obtaining the high-frequency transaction time period of the merchant.

[0102] S14, Calculate the different categories of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction amount.

[0103] In an optional embodiment, the step of statistically analyzing different categories of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction limit includes:

[0104] The different categories of payment methods in the merchant transaction dataset are statistically analyzed;

[0105] Statistics on the number of merchants and total payment amount for each payment method;

[0106] The ratio of the total payment amount to the number of merchants is used as the channel transaction limit for the corresponding payment method category.

[0107] In this optional embodiment, various payment methods of different categories in the merchant transaction dataset can be counted, including bank card payment, QR code payment, payment software payment, etc., and the number of merchants corresponding to each payment method and the total payment amount of each payment method in the merchant transaction dataset can be counted on a daily basis.

[0108] In this optional embodiment, the ratio of the total payment limit corresponding to each payment method to the number of merchants corresponding to that payment method can be used as the channel transaction limit for that payment method, and the channel transaction limit can be used as a merchant profile tag. For example, if there are 100 merchants making transactions through bank card payment, and the corresponding daily payment limit is 2 million, then the channel transaction limit for bank card payment is 20,000.

[0109] In this way, the channel transaction limit corresponding to each payment method in the merchant transaction dataset can be obtained quickly.

[0110] S15, Based on the high-frequency trading period and the channel transaction amount, construct a merchant profile to formulate different merchant profile strategies.

[0111] In this optional embodiment, the obtained high-frequency transaction time period and the channel transaction amount can be used as merchant profile tags to construct a merchant profile, and different merchant profile strategies can be formulated for merchants based on different merchant profile tags.

[0112] For example, for merchants tagged with high-frequency transaction periods, when the transaction platform needs to make code changes or perform system maintenance, these high-frequency transaction periods can be avoided, thereby reducing the impact on the merchant's normal transactions. For merchants tagged with channel transaction limits, when there are changes or maintenance to large-amount payment channels, the corresponding merchants can be notified first in descending order of the channel transaction limit.

[0113] In an optional embodiment, regions with high-frequency transactions and large channel transaction amounts can be identified by statistically summarizing the high-frequency transaction periods and transaction amounts. When promotional activities or payment rule changes are implemented for these regions, priority notifications can be given to those regions. For example, merchants in the Jiangsu, Zhejiang, and Shanghai regions typically experience high-frequency transactions and large channel transaction amounts between 9:00 AM and 11:00 PM daily. Therefore, corresponding promotional activities can be developed for merchants in these regions, such as providing greater platform subsidies for express delivery fees for higher transaction frequencies and larger channel payment transaction amounts.

[0114] In this way, the obtained high-frequency trading time period and the channel trading amount can be used as merchant profile tags, which can help the trading platform formulate different merchant profile strategies based on different profile tags, thereby improving the efficiency of services to merchants.

[0115] Please see Figure 2 , Figure 2 This is a functional block diagram of a preferred embodiment of the merchant profile generation device based on artificial intelligence according to this application. The merchant profile generation device 11 based on artificial intelligence includes a filtering module 110, a data acquisition module 111, a statistics module 112, a clustering module 113, an acquisition module 114, and a construction module 115. The unit / module referred to in this application refers to a series of computer-readable instruction segments that can be executed by the processor 13 and perform a fixed function, and are stored in the memory 12. In this embodiment, the functions of each unit / module will be described in detail in subsequent embodiments.

[0116] In an optional embodiment, the filtering module 110 is used to filter registered merchants on the trading platform to obtain an active merchant set.

[0117] In an optional embodiment, the process of filtering registered merchants on the trading platform to obtain an active merchant set includes:

[0118] Statistical analysis of transaction volume of registered merchants on the trading platform;

[0119] Based on their transaction volume, the registered merchants are divided into a high-activity merchant group and a low-activity merchant group;

[0120] The merchants in the low-activity merchant cluster are filtered to obtain a low-activity effective merchant cluster;

[0121] The set of highly active merchants and the set of inactive but valid merchants are defined as the active merchant set.

[0122] In an optional embodiment, the acquisition module 111 is used to acquire transaction data of merchants in the active merchant pool to obtain a merchant transaction dataset.

[0123] In an optional embodiment, the step of collecting transaction data from the active merchant pool to obtain the merchant transaction dataset includes:

[0124] A transaction log dataset is obtained by collecting log data from the active merchants in the transaction platform.

[0125] The transaction log dataset is preprocessed to obtain a structured dataset;

[0126] The structured dataset is anonymized to obtain the merchant transaction dataset.

[0127] In an optional embodiment, the statistics module 112 is used to count the transaction frequency of merchants in the merchant transaction data to obtain the average transaction frequency.

[0128] In an optional embodiment, the step of calculating the transaction frequency of merchants in the merchant transaction dataset to obtain the average transaction frequency includes:

[0129] The transaction frequency set of each merchant in the transaction dataset is obtained by statistically analyzing the transaction frequency of each merchant within a preset time interval.

[0130] The unit transaction frequencies in the unit transaction frequency set are sorted in descending order to obtain a transaction frequency sequence;

[0131] A stable transaction frequency sequence is obtained by truncating the transaction frequency sequence according to a preset threshold range;

[0132] The average value of each unit transaction frequency in the stable transaction frequency sequence is calculated as the transaction frequency mean.

[0133] In an optional embodiment, clustering module 113 is used to divide the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods.

[0134] In an optional embodiment, dividing the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods includes:

[0135] The unit transaction frequency is divided into multiple time period frequency datasets according to a preset time period;

[0136] The average of all unit transaction frequencies in the time period frequency dataset is calculated as the time period frequency mean.

[0137] The average frequency of the time period is compared with the average frequency of the transaction, and the time periods corresponding to all time periods with a frequency greater than the average frequency of the transaction are defined as high-frequency trading time periods.

[0138] In an optional embodiment, the acquisition module 114 is used to collect statistics on different categories of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction amount.

[0139] In an optional embodiment, the step of statistically analyzing different categories of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction limit includes:

[0140] The different categories of payment methods in the merchant transaction dataset are statistically analyzed;

[0141] Statistics on the number of merchants and total payment amount for each payment method;

[0142] The ratio of the total payment amount to the number of merchants is used as the channel transaction limit for the corresponding payment method category.

[0143] In an optional embodiment, the construction module 115 is used to construct merchant profiles based on the high-frequency trading period and the channel transaction amount in order to formulate different merchant profile strategies.

[0144] As can be seen from the above technical solutions, this application can obtain the high-frequency transaction time period of merchants by collecting the transaction frequency of merchants in different time periods, and combine it with the obtained channel transaction amount to generate a merchant profile. It can effectively formulate different operation and marketing strategies for different merchant profiles, thereby improving the service efficiency for merchants.

[0145] Please see Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 1 includes a memory 12 and a processor 13. The memory 12 is used to store computer-readable instructions, and the processor 13 executes the computer-readable instructions stored in the memory to implement the artificial intelligence-based merchant profile generation method described in any of the above embodiments.

[0146] In an optional embodiment, the electronic device 1 further includes a bus and a computer program stored in the memory 12 and executable on the processor 13, such as an AI-based merchant profile generation program.

[0147] Figure 3 Only electronic device 1 with memory 12 and processor 13 is shown. It will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0148] Combination Figure 1 The memory 12 in the electronic device 1 stores a plurality of computer-readable instructions to implement an artificial intelligence-based merchant profile generation method, and the processor 13 can execute the plurality of instructions to achieve the following:

[0149] Filter registered merchants on the trading platform to obtain a set of active merchants;

[0150] Collect transaction data from the active merchants in the centralized merchant database to obtain a merchant transaction dataset;

[0151] The transaction frequency of merchants in the merchant transaction dataset is statistically analyzed to obtain the average transaction frequency.

[0152] The transaction frequency is divided based on the average transaction frequency to obtain high-frequency transaction time periods;

[0153] The channel transaction limit is obtained by statistically analyzing the different categories of payment methods and payment amounts in the merchant transaction dataset.

[0154] Merchant profiles are constructed based on the high-frequency trading time periods and the channel transaction amounts to formulate different merchant profile strategies.

[0155] Specifically, the processor 13's implementation method for the above instructions can be found in [reference needed]. Figure 1 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0156] Those skilled in the art will understand that the schematic diagram is merely an example of electronic device 1 and does not constitute a limitation on electronic device 1. Electronic device 1 can be a bus-type structure or a star-type structure. Electronic device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, electronic device 1 may also include input / output devices, network access devices, etc.

[0157] It should be noted that electronic device 1 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0158] The memory 12 includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a portable hard drive of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 1. The memory 12 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of an AI-based merchant profile generation program, but also to temporarily store data that has been output or will be output.

[0159] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits packaged with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the electronic device 1, connecting various components of the electronic device 1 via various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing an AI-based merchant profile generation program) and calls data stored in the memory 12 to perform various functions and process data in the electronic device 1.

[0160] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes these applications to implement the steps in the various embodiments of the artificial intelligence-based merchant profile generation method described above, for example... Figure 1 The steps are shown.

[0161] For example, the computer program may be divided into one or more units / modules, which are stored in the memory 12 and executed by the processor 13 to complete this application. The one or more units / modules may be a series of computer-readable instruction segments capable of performing specific functions, which describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a filtering module 110, a collection module 111, a statistics module 112, a clustering module 113, an acquisition module 114, and a construction module 115.

[0162] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the artificial intelligence-based merchant profile generation method described in the various embodiments of this application.

[0163] If the unit / module integrated in electronic device 1 is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0164] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memory.

[0165] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0166] The blockchain referred to in this application is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains information about a batch of network transactions, used to verify the validity of the information (anti-counterfeiting) and generate the next block. A blockchain can include an underlying blockchain platform, a platform product service layer, and an application service layer.

[0167] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, in... Figure 3 The symbol is represented by only one arrow, but this does not indicate that there is only one bus or one type of bus. The bus is configured to enable communication between the memory 12 and at least one processor 13, etc.

[0168] This application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions. These computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based merchant profile generation method described in any of the above embodiments.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0170] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0171] Furthermore, the functional modules in the various embodiments of this 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 integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0172] Furthermore, the word "comprising" clearly does not exclude other modules or steps, and the singular does not exclude the plural. Multiple modules or devices described in the specification can also be implemented by a single module or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A method for generating merchant profiles based on artificial intelligence, characterized in that, The method includes: Filter registered merchants on the trading platform to obtain an active merchant set, including: counting the transaction volume of registered merchants on the trading platform; Based on the transaction volume, the registered merchants are divided into a high-activity merchant group and a low-activity merchant group; Inspection and verification information is pushed to merchants in the low-activity merchant group; if the merchants in the low-activity merchant group verify according to the instructions of the inspection and verification information, the verification is successful; if the merchants in the low-activity merchant group do not verify according to the instructions of the inspection and verification information, the verification fails; all merchants that have passed the verification are regarded as the low-activity valid merchant group. The set of highly active merchants and the set of inactive but valid merchants are defined as the active merchant set. Collect transaction data from the active merchants in the centralized merchant database to obtain a merchant transaction dataset; The transaction frequency of merchants in the merchant transaction dataset is statistically analyzed to obtain the average transaction frequency. The transaction frequency is divided based on the average transaction frequency to obtain high-frequency transaction time periods; The channel transaction limit is obtained by statistically analyzing the different categories of payment methods and payment amounts in the merchant transaction dataset. Merchant profiles are constructed based on the high-frequency trading time periods and the channel transaction amounts to formulate different merchant profile strategies.

2. The merchant profile generation method based on artificial intelligence as described in claim 1, characterized in that, The process of collecting transaction data from the active merchants in the centralized merchant database to obtain the merchant transaction dataset includes: A transaction log dataset is obtained by collecting log data from the active merchants in the transaction platform. The transaction log dataset is preprocessed to obtain a structured dataset; The structured dataset is anonymized to obtain the merchant transaction dataset.

3. The merchant profile generation method based on artificial intelligence as described in claim 1, characterized in that, The process of calculating the transaction frequency of merchants in the merchant transaction dataset to obtain the average transaction frequency includes: The transaction frequency set of each merchant in the transaction dataset is obtained by statistically analyzing the transaction frequency of each merchant within a preset time interval. The unit transaction frequencies in the unit transaction frequency set are sorted in descending order to obtain a transaction frequency sequence; A stable transaction frequency sequence is obtained by truncating the transaction frequency sequence according to a preset threshold range; The average value of each unit transaction frequency in the stable transaction frequency sequence is calculated as the transaction frequency mean.

4. The merchant profile generation method based on artificial intelligence as described in claim 3, characterized in that, The step of dividing the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods includes: The unit transaction frequency is divided into multiple time period frequency datasets according to a preset time period; The average of all unit transaction frequencies in the time period frequency dataset is calculated as the time period frequency mean. The average frequency of the time period is compared with the average frequency of the transaction, and the time periods corresponding to all time periods with a frequency greater than the average frequency of the transaction are defined as high-frequency trading time periods.

5. The merchant profile generation method based on artificial intelligence as described in claim 1, characterized in that, The process of statistically analyzing different categories of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction limit includes: The different categories of payment methods in the merchant transaction dataset are statistically analyzed; Statistics on the number of merchants and total payment amount for each payment method; The ratio of the total payment amount to the number of merchants is used as the channel transaction limit for the corresponding payment method category.

6. A merchant profile generation device based on artificial intelligence, characterized in that, The device includes a screening module, a data acquisition module, a statistics module, a clustering module, an acquisition module, and a construction module. The filtering module is used to filter registered merchants on the trading platform to obtain an active merchant set, including: counting the transaction volume of registered merchants on the trading platform; dividing the registered merchants into a high-activity merchant set and a low-activity merchant set based on the transaction volume; pushing inspection and verification information to merchants in the low-activity merchant set; if the merchants in the low-activity merchant set verify according to the instructions of the inspection and verification information, the verification is successful; if the merchants in the low-activity merchant set do not verify according to the instructions of the inspection and verification information, the verification fails; all verified merchants are included in the low-activity valid merchant set; and the high-activity merchant set and the low-activity valid merchant set are included in the active merchant set. The acquisition module is used to collect transaction data from the active merchants in the merchant cluster to obtain a merchant transaction dataset. The statistics module is used to calculate the transaction frequency of merchants in the merchant transaction data to obtain the average transaction frequency. The clustering module is used to divide the transaction frequency based on the average transaction frequency to obtain high-frequency transaction time periods; The acquisition module is used to statistically analyze the different types of payment methods and payment amounts in the merchant transaction dataset to obtain the channel transaction amount; The construction module is used to build merchant profiles based on the high-frequency trading period and the channel transaction amount in order to formulate different merchant profile strategies.

7. An electronic device, characterized in that, The electronic device includes: Memory, which stores computer-readable instructions; and The processor executes computer-readable instructions stored in the memory to implement the artificial intelligence-based merchant profile generation method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the artificial intelligence-based merchant profile generation method as described in any one of claims 1 to 5.

Images