Accurate flow distribution method, device, equipment and medium

Abstract

The invention discloses an accurate flow distribution method, device and equipment and a medium. The accurate flow distribution method comprises the following steps: acquiring user behavior data and merchant operation data on a public domain flow platform; determining consumer portrait data and merchant portrait data based on the user behavior data and the merchant operation data; based on the merchant portrait data and a first business rule, determining a target merchant pool, and according to the target time window exposure and a second business rule, estimating a today estimated flow of a current merchant in the target merchant pool; and adjusting the distribution flow of the current merchant according to the current day estimated flow of the current merchant, the merchant flow consumption data, the merchant flow lower limit threshold and the merchant flow upper limit threshold, and distributing the distribution flow of the current merchant to the target user group based on a recall algorithm and the consumer portrait data. According to the technical scheme of the embodiment of the invention, the traffic can be reasonably, accurately and efficiently distributed, and the satisfaction degree of buyers and sellers is improved.

Description

Technical Field

[0001] The present invention relates to the field of e-commerce technology, and in particular to a method, device, equipment and medium for accurate flow distribution. Background Art

[0002] With the development of Internet technology, new sales methods such as social media and e-commerce platforms have emerged like mushrooms after rain.

[0003] The current new sales method requires rapid response to changes in user behavior through traffic allocation to achieve real-time traffic optimization. However, there may often be a contradiction between considering both consumer satisfaction and ensuring the exposure value of products. In addition, for some niche or newly listed products, due to limited sales transaction data, it is impossible to effectively determine the appropriate product exposure, resulting in low efficiency and unreasonable traffic allocation. Summary of the invention

[0004] The present invention provides a method, device, equipment and medium for accurately distributing traffic, so as to solve the problems of unreasonable traffic distribution and low distribution efficiency in current online commodity sales.

[0005] According to one aspect of the present invention, a method for accurate flow distribution is provided, comprising:

[0006] Obtain user behavior data and merchant operation data on public traffic platforms;

[0007] Determine consumer portrait data and merchant portrait data based on user behavior data and merchant operation data;

[0008] Based on the merchant portrait data and the first business rule, determine the target merchant pool, and estimate today's estimated traffic of the current merchant in the target merchant pool according to the exposure in the target time window and the second business rule;

[0009] According to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, adjust the current merchant's allocated traffic, and allocate the current merchant's allocated traffic to the target user group based on the recall algorithm and consumer portrait data.

[0010] According to another aspect of the present invention, there is provided a flow rate accurate distribution device, comprising:

[0011] Data acquisition module, used to obtain user behavior data and merchant operation data on the public domain traffic platform;

[0012] User portrait module, used to determine consumer portrait data and merchant portrait data based on user behavior data and merchant operation data;

[0013] The traffic estimation module is used to determine the target merchant pool based on the merchant portrait data and the first business rule, and estimate the estimated traffic of the current merchant in the target merchant pool today according to the exposure in the target time window and the second business rule;

[0014] The traffic allocation module is used to adjust the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocate the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the traffic precision allocation method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for accurate flow distribution described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains user behavior data and merchant operation data on the public domain traffic platform, thereby determining consumer portrait data and merchant portrait data based on the user behavior data and merchant operation data, and then determining the target merchant pool based on the merchant portrait data and the first business rule, and estimating the estimated traffic of the current merchant in the target merchant pool today according to the target time window exposure and the second business rule, and further, adjusting the allocated traffic of the current merchant according to the estimated traffic of the current merchant today, the merchant traffic consumption data, the merchant traffic lower limit threshold and the merchant traffic upper limit threshold, and allocating the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data. In this solution, the commodity resources in the public domain traffic platform are automatically and accurately allocated to the target user group that is most likely to generate conversion behavior, thereby improving the exposure effect and conversion rate of the commodity, helping merchants to increase transaction volume, and building a win-win ecological structure for sales platforms, users and merchants, effectively avoiding the Matthew effect, and solving the problems of unreasonable traffic allocation and low allocation efficiency in the current online commodity sales, and being able to reasonably and accurately allocate traffic efficiently, improving the satisfaction of both buyers and sellers.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0023] Figure 1 A flow chart of a method for accurate flow distribution provided in Embodiment 1 of the present invention;

[0024] Figure 2 A flow chart of a method for accurate flow distribution provided in Embodiment 2 of the present invention;

[0025] Figure 3 A schematic diagram of the structure of a flow rate precision distribution device provided in Embodiment 3 of the present invention;

[0026] Figure 4 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] Embodiment 1

[0030] Figure 1 This is a flow chart of a method for accurately allocating traffic provided by the first embodiment of the present invention. This embodiment can be applied to reasonably and accurately allocating traffic for online sales merchants. The method can be executed by a device for accurately allocating traffic. The device for accurately allocating traffic can be implemented in the form of hardware and / or software. The device for accurately allocating traffic can be configured in an electronic device. Figure 1 As shown, the method includes:

[0031] Step 110: Obtain user behavior data and merchant operation data on the public domain traffic platform.

[0032] Among them, the public domain traffic platform can be a platform that carries public domain traffic. Exemplarily, the public domain traffic platform can include but is not limited to social media and e-commerce platforms. Public domain traffic refers to traffic that is publicly accessible on the Internet, that is, traffic obtained through channels such as search engines and social media.

[0033] Among them, user behavior data can be used to describe the online behavior of network users. Business operation data can be data describing the business content and status. For example, user behavior data can include but is not limited to the user's online clicks, browsing and search records.

[0034] It should be noted that in the technical solutions of the embodiments of the present invention, the acquisition, storage and application of user behavior data and merchant operation data involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0035] In an embodiment of the present invention, user behavior data and merchant operation data on a public domain traffic platform may be collected in real time based on an API (Application Programming Interface) or other data collection means (such as a web crawler, etc.).

[0036] Step 120: Determine consumer portrait data and merchant portrait data based on user behavior data and merchant operation data.

[0037] Among them, consumer portrait data can be attribute data describing the role of consumers. Merchant portrait data can be attribute data describing the role of merchants. Exemplarily, consumer portrait data can include but are not limited to the consumer's age, gender, hobbies and interests, and the geographical location corresponding to the user's IP (Internet Protocol). Merchant portrait data can include but are not limited to the product shipping address, sales category, and sales price range.

[0038] In an embodiment of the present invention, user behavior data can be analyzed based on a user portrait tool to obtain consumer portrait data, and merchant operation data can be analyzed to obtain merchant portrait data.

[0039] Optionally, user behavior data and merchant operation data can be preprocessed, such as data cleaning and filling, to reduce data sparsity. Anonymization processing technology and data encryption technology can also be combined to ensure data security and privacy. The preprocessed data can then be parsed based on user portrait tools to obtain consumer portrait data and merchant portrait data.

[0040] Step 130: determine the target merchant pool based on the merchant portrait data and the first business rule, and estimate today's estimated traffic of the current merchant in the target merchant pool according to the target time window exposure and the second business rule.

[0041] Among them, the first business rule may be a pre-set rule for dividing the merchant pool. The second business rule may be a rule for estimating the traffic that merchants need to allocate. The target merchant pool may be a merchant that sells a certain product of interest. Today's estimated traffic can be used to describe the estimated size of the traffic allocated to the merchant. The target time window exposure may be the exposure of the concerned product in a preset time window (such as yesterday, which can be set according to user needs). Exposure refers to the number of times a product or information is seen by customers within a period of time. For example, in the takeaway merchant version, the concept of exposure can be more accurately described as the number of exposures, that is, how many customers have seen the store within a period of time.

[0042] In an embodiment of the present invention, the first business rule can be used to divide the merchants corresponding to the merchant screen data to obtain multiple merchant pools, and a target merchant pool can be determined from the merchant pool based on the recall strategy of the intelligent algorithm model, and then based on the second business rule and the proportion of exposure of each merchant in the target merchant pool in the target time window, the estimated traffic of the current merchant in the target merchant pool for today is estimated.

[0043] Optionally, the second business rule can be the following logic: determine the traffic allocation weight of each merchant in the target merchant pool based on the proportion of the target time window exposure occupied by each merchant in the target merchant pool, thereby calculating the target time window exposure, and multiplying it by the traffic allocation weight of the current merchant in the target merchant pool to obtain the current merchant's estimated traffic for today in the target merchant pool.

[0044] Alternatively, the second business rule can also be the following logic: according to the exposure in the target time window and the moving average algorithm, determine the traffic moving average of each merchant in the target merchant pool, thereby determining the level interval into which the traffic moving average corresponding to the current merchant falls, and multiply the traffic allocation weight corresponding to the level interval by the exposure in the target time window as the current merchant in the target merchant pool. The level interval and the corresponding relationship between the level interval and the traffic allocation weight can be agreed upon in the second business rule.

[0045] In a specific example, model feature extraction is performed on the aforementioned preprocessed consumer portrait data and merchant portrait data, thereby converting the extracted features into numerical vectors, and the final converted numerical vectors are input into a machine learning model that has learned the first business rules and the second business rules, so as to estimate today's estimated traffic of the current merchant in the target merchant pool through the machine learning model.

[0046] Optionally, cross validation and / or regularization techniques may be used to prevent overfitting of the machine learning model. The embodiment of the present invention uses an interpretable machine learning model to support the explanation of the model decision process.

[0047] Step 140: adjust the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocate the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data.

[0048] The merchant traffic consumption data can be used to characterize the merchant's traffic consumption, that is, to indicate the total amount of merchant exposure traffic. The merchant traffic lower limit threshold can be a preset minimum traffic allocated to the merchant. The merchant traffic upper limit threshold can be a preset maximum traffic allocated to the merchant. The target user group can be users who are interested in the concerned product, that is, users who are more likely to pay for, click on, etc. the concerned product.

[0049] In an embodiment of the present invention, the current merchant's estimated traffic for today can be used as the current merchant's allocated traffic for the whole day, and the merchant's traffic consumption data can be calculated in real time to monitor the merchant's traffic consumption of the current merchant in real time, thereby integrating the merchant's traffic consumption data, the merchant's traffic lower limit threshold, and the merchant's traffic upper limit threshold multi-dimensional data of the current merchant, and adjusting the current merchant's allocated traffic according to a preset adjustment cycle, and then analyzing the consumer portrait data and the current user's real-time behavior data based on the deep learning model to obtain the target user group, and further allocating the adjusted allocated traffic corresponding to the current merchant to the target user group.

[0050] Optionally, when the merchant traffic consumption data of the current merchant is greater than the merchant traffic upper limit threshold, it is timely determined whether the current merchant has malicious traffic diversion. If malicious traffic diversion exists, the merchant will not continue to be allocated traffic. If the merchant traffic consumption data is less than the merchant traffic lower limit threshold, and the merchant traffic consumption data is much less than today's estimated traffic, the merchant's current allocated traffic can be increased for the purpose of product exposure. For example, the increased traffic can be allocated to consumers who have never paid attention to the current merchant. The embodiment of the present invention does not limit the specific type of consumers allocated.

[0051] The technical solution of the embodiment of the present invention obtains user behavior data and merchant operation data on a public domain traffic platform, thereby determining consumer portrait data and merchant portrait data based on the user behavior data and merchant operation data, and then determining a target merchant pool based on the merchant portrait data and a first business rule, and estimating today's estimated traffic of the current merchant in the target merchant pool according to the target time window exposure and a second business rule, and further adjusting the allocated traffic of the current merchant according to today's estimated traffic of the current merchant, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocating the allocated traffic of the current merchant to the target user group based on a recall algorithm and consumer portrait data. In this solution, the commodity resources in the public domain traffic platform are automatically and accurately allocated to the target user groups who are most likely to generate conversion behaviors, thereby improving the exposure effect and conversion rate of the commodities, helping merchants to increase their transaction volume, and building a win-win ecological structure for sales platforms, users and merchants. It effectively avoids the Matthew effect (that is, under the premise of considering the platform's rate of return, reasonable traffic allocation is made for head merchants and medium and long-tail merchants), solves the problems of unreasonable traffic distribution and low distribution efficiency in the current online commodity sales, and can reasonably, accurately and efficiently allocate traffic, thereby improving the satisfaction of both buyers and sellers.

[0052] Embodiment 2

[0053] Figure 2 This is a flow chart of a method for accurate traffic distribution provided in Example 2 of the present invention. This example is specific based on the above example and provides a specific optional implementation method for determining consumer portrait data and merchant portrait data based on user behavior data and merchant operation data. Figure 2 As shown, the method includes:

[0054] Step 210: Obtain user behavior data and merchant operation data on the public domain traffic platform.

[0055] Step 220: Based on the big data analysis tool, data mining is performed on the user behavior data and the merchant operation data to obtain user analysis data and merchant analysis data.

[0056] The user analysis data may be valid data extracted from the user behavior data, and the merchant analysis data may be valid data extracted from the merchant operation data.

[0057] In the embodiment of the present invention, big data analysis tools can be used to mine effective information in user behavior data and merchant operation data to obtain user analysis data and merchant analysis data.

[0058] Step 230: Determine consumer portrait data based on user analysis data, and determine merchant portrait data based on merchant analysis data.

[0059] In an embodiment of the present invention, user analysis data can be input into a user portrait tool to construct consumer portrait data through the user portrait tool. Similarly, merchant operation data can be input into the user portrait tool to construct merchant portrait data through the user portrait tool.

[0060] Step 240: determine the target merchant pool based on the merchant portrait data and the first business rule, and estimate today's estimated traffic of the current merchant in the target merchant pool based on the target time window exposure and the second business rule.

[0061] In an optional embodiment of the present invention, determining the target merchant pool based on the merchant portrait data and the first business rule may include: clustering the merchant portrait data according to the first business rule to obtain a clustered merchant pool; and determining the target merchant pool based on the clustered merchant pool and the target product type.

[0062] The clustered merchant pool may be a merchant pool obtained by clustering merchants corresponding to merchant portrait data. The target product type may be a product type of the concerned product.

[0063] In an embodiment of the present invention, the merchant portrait data can be clustered based on the first business rule to divide the merchants corresponding to the merchant portrait data under the same cluster into the same merchant pool, that is, merchants selling the same category of goods are divided into a merchant pool to obtain a clustered merchant pool.

[0064] In an optional embodiment of the present invention, estimating today's estimated traffic of the current merchant in the target merchant pool based on the target time window exposure and the second business rule may include: determining the traffic allocation weights of the merchants in the target merchant pool based on the second business rule; estimating today's estimated traffic of the current merchant in the target merchant pool based on the target time window exposure and the traffic allocation weights of the merchants in the target merchant pool.

[0065] In an embodiment of the present invention, the proportion of the exposure of the target time window occupied by each merchant in the target merchant pool can be scored based on the second business rule, so that the traffic allocation weight of each merchant in the target merchant pool can be determined based on the correspondence between the score and the weight specified in the second business rule. Further, the corresponding traffic allocation weight of the current merchant is determined from the traffic allocation weights of the merchants in the target merchant pool, so as to calculate the product of the exposure of the target time window and the corresponding traffic allocation weight of the current merchant, and obtain the estimated traffic of the current merchant in the target merchant pool today.

[0066] Step 250: adjust the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocate the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data.

[0067] In an optional embodiment of the present invention, adjusting the allocated traffic of the current merchant based on the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold, and merchant traffic upper limit threshold, can include: obtaining a traffic pre-allocation target time period; adjusting the allocated traffic of the current merchant according to the traffic pre-allocation target time period based on the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold, and merchant traffic upper limit threshold.

[0068] The traffic pre-allocation target period may be a period for allocating initial traffic to the current merchant. Exemplarily, the traffic pre-allocation target period may be configured as three periods: morning, noon, and evening, such as 8 a.m., 12 p.m., and 6 p.m. The embodiment of the present invention does not limit the specific time point of the traffic pre-allocation target period.

[0069] In an embodiment of the present invention, the traffic pre-allocation target period configured by the sales platform can be obtained, so that today's estimated traffic can be used as the all-day traffic and allocated within the traffic pre-allocation target period to initialize the initial traffic of the current merchant under the traffic pre-allocation target period, and further adjust the allocated traffic of the current merchant according to the preset adjustment period based on the merchant traffic consumption data, the merchant traffic lower limit threshold and the merchant traffic upper limit threshold.

[0070] In an optional embodiment of the present invention, after allocating the allocated traffic of the current merchant to the target user group, it may also include: obtaining the real-time exposure of the current merchant and the response behavior data of the traffic recommendation users; adjusting the allocated traffic according to the traffic optimization strategy based on the real-time exposure of the current merchant and the response behavior data of the traffic recommendation users.

[0071] The traffic recommendation user may be a recommended object of the current merchant's corresponding traffic. The response behavior data may be used to characterize the consumer's response behavior to the merchant's recommended traffic. The traffic optimization strategy may be a pre-configured strategy for adjusting traffic distribution.

[0072] In an embodiment of the present invention, the real-time exposure of the current merchant and the response behavior data of the traffic recommendation user can be obtained in real time, so as to determine the number of times the current merchant is viewed by customers based on the real-time exposure of the current merchant, and thus determine the number of consumers who actually pay based on the response behavior data of the traffic recommendation user, and then use the ratio of the aforementioned number of views to the number of consumers as the exposure conversion rate, so as to adjust the allocated traffic based on the traffic optimization strategy when the exposure conversion rate does not meet the lower limit threshold of the exposure conversion rate.

[0073] Optionally, the traffic allocation strategy can be continuously optimized for compliance based on the merchant's satisfaction with the exposure conversion rate.

[0074] In an optional embodiment of the present invention, before adjusting the allocated traffic according to the traffic optimization strategy, it can also include: determining a test control merchant that matches the current merchant; based on the traffic optimization test rules, conducting a comparative experiment on the current merchant and the test control merchant to obtain the traffic optimization strategy.

[0075] The test control merchant may be a merchant that is benchmarked against the current merchant, that is, a merchant that sells the same product category as the current merchant and whose sales volume is within a certain preset error. The traffic optimization test rule may be an experimental rule corresponding to any known control experiment. The traffic optimization test rule may include but is not limited to A / B test experimental rules.

[0076] In an embodiment of the present invention, a test control merchant matching the current merchant can be determined in the target merchant pool, so that a comparative experiment can be conducted on the current merchant and the test control merchant based on the traffic optimization test rules, and the traffic allocation strategy applied by the merchant with a high exposure conversion rate can be used as the traffic optimization strategy.

[0077] The technical solution of the embodiment of the present invention obtains user behavior data and merchant operation data on the public domain traffic platform, thereby determining consumer portrait data and merchant portrait data based on the user behavior data and merchant operation data, and then determining the target merchant pool based on the merchant portrait data and the first business rule, and estimating the estimated traffic of the current merchant in the target merchant pool today according to the target time window exposure and the second business rule, and further, adjusting the allocated traffic of the current merchant according to the estimated traffic of the current merchant today, the merchant traffic consumption data, the merchant traffic lower limit threshold and the merchant traffic upper limit threshold, and allocating the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data. In this solution, the commodity resources in the public domain traffic platform are automatically and accurately allocated to the target user group that is most likely to generate conversion behavior, thereby improving the exposure effect and conversion rate of the commodity, helping merchants to increase transaction volume, and building a win-win ecological structure for sales platforms, users and merchants, solving the problems of unreasonable traffic allocation and low allocation efficiency in the current online commodity sales, and being able to reasonably and accurately allocate traffic efficiently, improving the satisfaction of both buyers and sellers.

[0078] Embodiment 3

[0079] Figure 3 A schematic diagram of the structure of a flow precision distribution device provided in Embodiment 3 of the present invention.

[0080] like Figure 3 As shown, the device comprises:

[0081] The data acquisition module 310 is used to acquire user behavior data and merchant operation data on the public domain traffic platform;

[0082] User portrait module 320, for determining consumer portrait data and merchant portrait data based on user behavior data and merchant operation data;

[0083] The traffic estimation module 330 is used to determine the target merchant pool based on the merchant portrait data and the first business rule, and estimate the estimated traffic of the current merchant in the target merchant pool today according to the exposure in the target time window and the second business rule;

[0084] The traffic allocation module 340 is used to adjust the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocate the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data.

[0085] The technical solution of the embodiment of the present invention obtains user behavior data and merchant operation data on the public domain traffic platform, thereby determining consumer portrait data and merchant portrait data based on the user behavior data and merchant operation data, and then determining the target merchant pool based on the merchant portrait data and the first business rule, and estimating the estimated traffic of the current merchant in the target merchant pool today according to the target time window exposure and the second business rule, and further, adjusting the allocated traffic of the current merchant according to the estimated traffic of the current merchant today, the merchant traffic consumption data, the merchant traffic lower limit threshold and the merchant traffic upper limit threshold, and allocating the allocated traffic of the current merchant to the target user group based on the recall algorithm and consumer portrait data. In this solution, the commodity resources in the public domain traffic platform are automatically and accurately allocated to the target user group that is most likely to generate conversion behavior, thereby improving the exposure effect and conversion rate of the commodity, helping merchants to increase transaction volume, and building a win-win ecological structure for sales platforms, users and merchants, solving the problems of unreasonable traffic allocation and low allocation efficiency in the current online commodity sales, and being able to reasonably and accurately allocate traffic efficiently, improving the satisfaction of both buyers and sellers.

[0086] Optionally, the user portrait module 320 is used to perform data mining on the user behavior data and the merchant operation data based on big data analysis tools to obtain user analysis data and merchant analysis data; determine the consumer portrait data based on the user analysis data, and determine the merchant portrait data based on the merchant analysis data.

[0087] Optionally, the traffic estimation module 330 includes a target merchant pool determination unit and a traffic estimation unit. The target merchant pool determination unit is used to perform data clustering on the merchant portrait data according to the first business rule to obtain a clustered merchant pool; and determine the target merchant pool according to the clustered merchant pool and the target product type.

[0088] Optionally, a traffic estimation unit is used to determine the traffic allocation weights of merchants in the target merchant pool based on the second business rule; and estimate today's estimated traffic of the current merchant in the target merchant pool according to the exposure of the target time window and the traffic allocation weights of the merchants in the target merchant pool.

[0089] Optionally, the traffic allocation module 340 is used to obtain a traffic pre-allocation target time period; determine the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and according to the traffic pre-allocation target time period.

[0090] Optionally, the precise traffic allocation device also includes a traffic allocation adjustment module, which is used to obtain the real-time exposure of the current merchant and the response behavior data of the traffic recommendation user; according to the real-time exposure of the current merchant and the response behavior data of the traffic recommendation user, the allocated traffic is adjusted according to the traffic optimization strategy.

[0091] Optionally, the precise traffic allocation device also includes a traffic optimization strategy determination module, which is used to determine a test control merchant that matches the current merchant; based on the traffic optimization test rules, a comparative experiment is performed on the current merchant and the test control merchant to obtain the traffic optimization strategy.

[0092] The precise flow distribution device provided in the embodiment of the present invention can execute the precise flow distribution method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0093] Embodiment 4

[0094] Figure 4 A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0095] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0096] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0097] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the flow precision allocation method.

[0098] In some embodiments, the accurate flow distribution method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the accurate flow distribution method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the accurate flow distribution method in any other appropriate manner (e.g., by means of firmware).

[0099] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0101] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0104] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of traditional physical hosts and VPS servers, which are difficult to manage and have weak business scalability.

[0105] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0106] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for accurate flow distribution, characterized in that: include: Obtain user behavior data and merchant operation data on public traffic platforms; Determine consumer portrait data and merchant portrait data based on the user behavior data and the merchant operation data; Based on the merchant portrait data and the first business rule, determine the target merchant pool, and estimate today's estimated traffic of the current merchant in the target merchant pool according to the target time window exposure and the second business rule; According to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, the allocated traffic of the current merchant is adjusted, and based on the recall algorithm and the consumer portrait data, the allocated traffic of the current merchant is allocated to the target user group.

2. The method according to claim 1, characterized in that Determining consumer portrait data and merchant portrait data based on the user behavior data and the merchant operation data includes: Based on big data analysis tools, data mining is performed on the user behavior data and the merchant operation data to obtain user analysis data and merchant analysis data; The consumer portrait data is determined based on the user analysis data, and the merchant portrait data is determined based on the merchant analysis data.

3. The method according to claim 1, characterized in that The determining a target merchant pool based on the merchant portrait data and the first business rule includes: According to the first business rule, clustering is performed on the merchant portrait data to obtain a clustered merchant pool; The target merchant pool is determined according to the clustered merchant pool and the target commodity type.

4. The method according to claim 1, characterized in that: The estimating today's estimated traffic of the current merchant in the target merchant pool according to the exposure in the target time window and the second business rule includes: Based on the second business rule, determining the traffic allocation weights of merchants in the target merchant pool; According to the exposure amount in the target time window and the traffic allocation weights of the merchants in the target merchant pool, the estimated traffic for today of the current merchant in the target merchant pool is estimated.

5. The method according to claim 1, characterized in that The adjusting the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold, and merchant traffic upper limit threshold includes: Get the traffic pre-allocation target period; According to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and in accordance with the traffic pre-allocation target time period, the allocated traffic of the current merchant is adjusted.

6. The method according to claim 1, characterized in that After allocating the allocated traffic of the current merchant to the target user group, the method further includes: Obtaining the real-time exposure of the current merchant and the response behavior data of traffic recommendation users; According to the real-time exposure of the current merchant and the response behavior data of the traffic recommendation user, the allocated traffic is adjusted according to the traffic optimization strategy.

7. The method according to claim 6, characterized in that Before adjusting the allocated traffic according to the traffic optimization strategy, the method further includes: Determining a test control merchant that matches the current merchant; Based on the traffic optimization test rules, a comparative experiment is conducted on the current merchant and the test control merchant to obtain the traffic optimization strategy.

8. A flow rate precision distribution device, characterized in that: include: Data acquisition module, used to obtain user behavior data and merchant operation data on the public domain traffic platform; A user portrait module, used to determine consumer portrait data and merchant portrait data based on the user behavior data and the merchant operation data; A traffic estimation module, for determining a target merchant pool based on the merchant portrait data and the first business rule, and estimating today's estimated traffic of the current merchant in the target merchant pool according to the target time window exposure and the second business rule; The traffic allocation module is used to adjust the allocated traffic of the current merchant according to the current merchant's estimated traffic today, merchant traffic consumption data, merchant traffic lower limit threshold and merchant traffic upper limit threshold, and allocate the allocated traffic of the current merchant to the target user group based on the recall algorithm and the consumer portrait data.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for accurate flow distribution according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for accurate flow distribution according to any one of claims 1 to 7 when executed.

Images