A method, apparatus and device for determining a target user

Abstract

The application discloses a kind of method for determining target user, device and equipment, the method includes, obtaining at least one user to be handled in at least two years corresponding traffic data;To each user to be handled, the traffic of current user to be handled each year is sorted, and at least two groups of traffic arrangement information of current user to be handled are obtained;For each group of traffic arrangement information, according to current traffic arrangement information, determine the cumulative traffic proportion of each month, according to cumulative traffic proportion and preset proportion threshold, determine the list of months to be used of the year to which current traffic arrangement information belongs;According to at least two lists of months to be used of current user to be handled, determine user attribute;Based on the user attribute of each user to be handled and preset attribute threshold, determine at least one target user.The technical scheme of the embodiment of the application realizes the quick and accurate identification of target user by analyzing and processing user traffic data, and saves the identification cost.

Description

Technical Field

[0001] This invention relates to the field of user data analysis technology, and in particular to a method, apparatus, and device for identifying target users. Background Technology

[0002] With the development of big data on the Internet, various industries and platforms are investing a lot of resources in qualitative and quantitative research on user data in order to identify target users and retain and convert them.

[0003] Traditional target user identification methods mainly rely on manually observing users' business behavior to determine whether a user is a target user, and / or filtering each user's monthly business volume for at least two years by subjectively setting a business volume threshold, obtaining a set of months in at least two years where the monthly business volume exceeds the business volume threshold, and then roughly determining whether the user is a target user.

[0004] The above-mentioned technical solutions are costly, inefficient, and have limited data processing capacity due to the high cost of manually observing and identifying target users. They also lack universality. The manually set thresholds are subjective, and using the same threshold for all users makes it impossible to differentiate users based on their characteristics. Furthermore, the peak business volume of users varies from year to year, leading to a decrease in the accuracy of target user identification. Summary of the Invention

[0005] This invention provides a method, apparatus, and device for identifying target users, enabling targeted analysis of user data, thereby improving the efficiency and accuracy of target user identification while saving costs.

[0006] In a first aspect, embodiments of the present invention provide a method for determining a target user, the method comprising:

[0007] Obtain historical business volume data for at least one user to be processed over at least two years; wherein, the historical business volume data includes the historical business volume for each month of each year;

[0008] For each user to be processed, the historical business volume of the current user to be processed in each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user to be processed; wherein, the number of sets of business volume distribution information is consistent with the number of years.

[0009] For each group of business volume distribution information of the current pending users, determine the cumulative business volume percentage of each month based on the current business volume distribution information, and determine the list of pending months of the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and the preset percentage threshold.

[0010] Determine the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed.

[0011] Based on the user attributes and preset attribute thresholds of each user to be processed, at least one target user is identified.

[0012] Secondly, embodiments of the present invention also provide a data processing apparatus, the apparatus comprising:

[0013] The data acquisition module is used to acquire historical business volume data for at least one user to be processed over at least two years; wherein, the historical business volume data includes the historical business volume for each month in each year;

[0014] The business volume arrangement processing module is used to sort and process the historical business volume of each user to be processed in each year, and obtain at least two sets of business volume arrangement information associated with the current user to be processed; wherein, the number of sets of business volume arrangement information is consistent with the number of years.

[0015] The monthly table generation module is used to determine the cumulative business volume percentage of each month based on the current business volume distribution information of each group of users to be processed, and to determine the list of months to be used in the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and the preset percentage threshold.

[0016] The user attribute determination module is used to determine the user attributes of the current user based on the list of at least two months to be used corresponding to the current user.

[0017] The target user module is used to determine at least one target user based on the user attributes of each user to be processed and preset attribute thresholds.

[0018] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0019] At least one processor; and

[0020] A memory that is communicatively connected to at least one processor; wherein,

[0021] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the method for determining a target user according to any embodiment of the present invention.

[0022] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years. This historical business volume data includes the historical business volume for each month within each year. For each user to be processed, the historical business volume for each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user. The number of sets of business volume distribution information corresponds to the number of years. For each set of business volume distribution information for the current user to be processed, the cumulative business volume percentage for each month is determined based on the current business volume distribution information. Based on the cumulative business volume percentage and a preset percentage threshold, a list of months to be used for the year to which the current business volume distribution information belongs is determined. Based on the list of at least two months to be used for the current user to be processed, the user attributes of the current user to be processed are determined. Based on the user attributes of each user to be processed and a preset attribute threshold, at least one target user is identified. This solution addresses the problems of high cost, low efficiency, limited data processing, lack of universality, and low accuracy in identifying target users. It achieves targeted analysis of user data, improves the efficiency and accuracy of target user identification, and saves costs.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a method for identifying a target user according to Embodiment 1 of the present invention;

[0026] Figure 2 This is an annual business volume distribution information diagram provided according to an embodiment of the present invention;

[0027] Figure 3 This is a chart showing the percentage of annual cumulative business volume provided according to an embodiment of the present invention;

[0028] Figure 4 This is a flowchart of a method for identifying a target user according to Embodiment 2 of the present invention;

[0029] Figure 5 This is a flowchart of a method for identifying a target user according to Embodiment 3 of the present invention;

[0030] Figure 6 This is a flowchart of a method for identifying a target user according to Embodiment 4 of the present invention;

[0031] Figure 7 This is a schematic diagram of the structure of an apparatus for identifying a target user according to Embodiment 5 of the present invention;

[0032] Figure 8 This is a schematic diagram of the structure of an electronic device that implements a method for identifying a target user according to an embodiment of the present invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] Example 1

[0036] Figure 1 This is a flowchart of a method for determining a target user according to Embodiment 1 of the present invention. This embodiment can be applied to situations where a user is identified as a target user by analyzing the user's historical business volume data. The method can be executed by a device for determining the target user, which can be implemented in hardware and / or software and can be configured in a computer.

[0037] like Figure 1 As shown, the method includes:

[0038] S110. Obtain historical business volume data for at least one user to be processed over at least two years.

[0039] The historical business volume data includes the historical business volume corresponding to each month of each year.

[0040] In this context, "users awaiting processing" refers to those whose business volume needs to be analyzed to determine if they are target users. Specifically, these users can be e-commerce, brick-and-mortar, and online customers. Historical business volume data refers to the business data generated when providing product services to these users or when they place orders, such as order volume, shipment volume, and sales volume. Furthermore, determining whether a user is a target user requires comparing and analyzing historical business volume data from two or more years; therefore, at least two years' worth of historical business volume data for these users is necessary.

[0041] Understandably, in order to improve the accuracy of identifying target users, it is advisable to obtain as much historical business volume data as possible from multiple years of the users to be processed, and then analyze it to improve the efficiency of identifying target users.

[0042] Since there can be multiple users to be processed, the method for obtaining historical business volume data for each user to be processed is the same. In order to clearly explain how to obtain the historical business volume data for each user to be processed, we will take obtaining at least two years of historical business volume data for a user to be processed as an example.

[0043] Specifically, the user data management platform obtains historical business volume data for at least two years for the users to be processed.

[0044] For example, let's take obtaining historical business volume data for user A over two years as an example. User A is an e-commerce platform, and the historical business volume data can be the express delivery order volume of product a for each month of 2020 and 2021 for user A. We then filter the express delivery order volume data for user A to extract the historical business volume data for product a for each month of 2020 and 2021.

[0045] S120. For each user to be processed, sort and process the historical business volume of the current user to be processed in each year to obtain at least two sets of business volume arrangement information associated with the current user to be processed.

[0046] The number of groups for business volume distribution information is consistent with the number for the year.

[0047] Here, "sorting" refers to sorting the historical business volume of each month within each year in descending order of volume. The business volume distribution information is obtained by arranging the historical business volume of each month in descending order. See also... Figure 2In the business volume distribution information, the horizontal axis represents monthly information, and the vertical axis represents the historical business volume for each month. The business volume distribution information clearly shows the historical business volume for each month, arranged in descending order. Furthermore, a year corresponds to a set of business volume distribution information.

[0048] Specifically, since the method for obtaining the business volume distribution information for each year is the same, we will take the processing of a set of business volume distribution information corresponding to the historical business volume of a year as an example for explanation. The historical business volumes of the current user to be processed for January to December of the current year are 700, 100, 800, 900, 1000, 300, 200, 500, 600, 99, 320, and 110. Sort the historical business volumes of each month of the current year from largest to smallest to obtain the historical business volume ranking: 1000, 900, 800, 700, 600, 500, 320, 300, 200, 110, 100, and 99. Then, sort the months according to the business volume of each month to obtain the month ranking information: 5, 4, 3, 1, 9, 8, 11, 6, 7, 12, 2, and 10. Therefore, the business volume distribution information for the current user to be processed in the current year is as follows: Figure 2 As shown.

[0049] S130. For each group of business volume arrangement information of the current pending users, determine the cumulative business volume percentage corresponding to each month based on the current business volume arrangement information, and determine the list of pending months of the year to which the current business volume arrangement information belongs based on the cumulative business volume percentage and the preset percentage threshold.

[0050] The cumulative business volume percentage for each month refers to the proportion of the current month's business volume to the sum of the business volumes of all months preceding the current month in the total annual business volume. The preset percentage threshold is a pre-defined threshold for the cumulative business volume percentage; the value of this threshold can be set according to actual circumstances, and this embodiment does not impose any restrictions. The list of months to be used refers to the set of all months whose cumulative business volume percentage meets the preset conditions compared to the preset percentage threshold.

[0051] Specifically, since the same analysis and processing are performed on each group of business volume distribution information for the current users to be processed, we will now take the analysis and processing of one group of business volume distribution information as an example. For example... Figure 3 As shown, for the current business volume distribution information, the cumulative business volume percentage of each month is calculated, and the cumulative business volume percentage of each month is compared with the preset percentage threshold. If the preset condition is met, the month corresponding to the cumulative business volume percentage is stored in the month list.

[0052] For example, the preset percentage threshold is set to 80%, and the preset condition is that the cumulative business volume percentage is less than the preset percentage threshold. Figure 2The following is the business volume distribution information for user company A in 2020. The calculated total annual business volume is 5629. The corresponding cumulative business volume percentage is obtained based on the historical business volume of each month and the total annual business volume. Figure 3 As shown. The cumulative business volume in August accounted for 79.94%, and the cumulative business volume in November accounted for 85.63%. Therefore, the months with a cumulative business volume of less than 80% are stored in the list of months to be used in 2020 for the current pending user company A. The resulting list of months to be used is [5,4,3,1,9,8].

[0053] S140. Determine the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed.

[0054] Among them, user attributes refer to the degree of consistency between the current user's list of months for at least two years.

[0055] Specifically, since an annual business volume information distribution table corresponds to a monthly list, at least two annual monthly lists can be obtained. By comparing the similarity of the months in the pending monthly lists of at least two years, it is determined whether the current user to be processed is the target user.

[0056] S150. Based on the user attributes and preset attribute thresholds of each user to be processed, determine at least one target user.

[0057] The preset attribute threshold is a pre-set threshold. Target users are users whose attributes meet the preset attribute threshold. After identifying target users, services such as maintenance or message push can be provided to them.

[0058] Specifically, user attributes are compared with preset attribute thresholds to determine whether the current user to be processed is the target user. Since historical business volume data of all users is processed in batches, the identified target user can be one or more.

[0059] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years. This historical business volume data includes the historical business volume for each month within each year. For each user to be processed, the historical business volume for each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user. The number of sets of business volume distribution information corresponds to the number of years. For each set of business volume distribution information for the current user to be processed, the cumulative business volume percentage for each month is determined based on the current business volume distribution information. Based on the cumulative business volume percentage and a preset percentage threshold, a list of months to be used for the year to which the current business volume distribution information belongs is determined. Based on the list of at least two months to be used for the current user to be processed, the user attributes of the current user to be processed are determined. Based on the user attributes of each user to be processed and a preset attribute threshold, at least one target user is identified. This solution addresses the problems of high cost, low efficiency, limited data processing, lack of universality, and low accuracy in identifying target users. It achieves targeted analysis of user data, improves the efficiency and accuracy of target user identification, and saves costs.

[0060] Example 2

[0061] Figure 4 This is a flowchart of a method for determining a target user provided in Embodiment 2 of the present invention. Based on the foregoing embodiments, the cumulative business volume percentage corresponding to each month can be determined according to the current business volume arrangement information, and the list of months to be used in the year to which the current business volume arrangement information belongs can be refined according to the cumulative business volume percentage and the preset percentage threshold. For specific implementation methods, please refer to the detailed description of the embodiments of the present invention. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0062] like Figure 4 As shown, the method includes:

[0063] S210. Obtain historical business volume data for at least one user to be processed over at least two years.

[0064] The historical business volume data includes the historical business volume corresponding to each month of each year.

[0065] Optionally, the historical business volume of at least one user to be processed in each month of at least two years can be retrieved from the database in batches and used as the historical business volume data for each year.

[0066] The database refers to a summary of the historical business volume of each user across all years and months, compiled by the enterprise. Furthermore, the database can be used to batch retrieve historical business volume data for each user by filtering by user name, year, and month. This allows for the analysis and processing of massive amounts of data, improving the efficiency of identifying target users while saving labor costs.

[0067] S220. For each user to be processed, sort the historical business volume of the current user in each year to obtain at least two sets of business volume arrangement information associated with the current user.

[0068] The number of groups for business volume distribution information is consistent with the number for the year.

[0069] Optionally, the historical business volume of the current user to be processed in each year can be arranged in descending order to obtain at least two sets of business volume arrangement information.

[0070] For example, since the same operation is performed on the historical business volume of each year, let's take a set of business volume distribution information corresponding to the historical business volume of one year as an example, such as... Figure 2 As shown, the business volume of user A in each month of 2020 is sorted in descending order to obtain the corresponding business volume ranking chart.

[0071] S230. For each month in the current business volume distribution information, based on the current historical business volume of the current month and the historical business volume to be accumulated in the current business volume distribution information that is higher than the current historical business volume, the historical business volume to be accumulated is added to the current historical business volume to obtain the cumulative business volume of the current month.

[0072] The historical business volume to be accumulated refers to the historical business volume of each month whose current historical business volume is higher than that of the current month. The cumulative business volume of the current month is the sum of the current historical business volume and the historical business volume to be accumulated.

[0073] For example, since the same analysis and processing are performed on each group of service volume distribution information for the current user to be processed, we will now take the analysis and processing of one group of service volume distribution information as an example. Figure 3For the current business volume distribution information corresponding to user A in 2020, if the current month is April, then the current historical business volume for the current month is 900. The historical business volume to be accumulated is the business volume higher than 900, namely the historical business volume of May (1000), so the cumulative business volume for April is 1900. Furthermore, if the current month is March, then the current historical business volume for the current month is 800. The historical business volume to be accumulated is the historical business volume higher than 900, namely the historical business volume of May (1000) and the historical business volume of April (900), so the cumulative business volume for March is 2700.

[0074] S240. Given the cumulative business volume for each month and the sum of the historical business volume for each month in the current business volume distribution information, obtain the percentage of the cumulative business volume for each month.

[0075] The cumulative business volume percentage is inversely proportional to the cumulative business volume for each month.

[0076] Specifically, such as Figure 3 As shown, the cumulative business volume percentages for May, April, and March were 17.77%, 33.75%, and 47.97%, respectively, with corresponding cumulative business volumes of 1000, 900, and 800.

[0077] For example, the current business volume distribution information for user A in 2020 is as follows: Figure 2 As shown. The total historical business volume for each month can be calculated to be 5629. Based on the cumulative business volume for each month and the total annual business volume, the corresponding cumulative business volume percentage can be obtained, as follows. Figure 3 As shown in the line chart, the cumulative business volume in May was 1000, accounting for 17.77% of the total; the cumulative business volume in April was 1900, accounting for 33.75%; and the cumulative business volume in March was 2700, accounting for 47.97%.

[0078] S250. Based on the cumulative business volume percentage of each month in the current year and the preset percentage threshold, determine the list of months to be used in the current year to which the current business volume arrangement information belongs.

[0079] Specifically, the cumulative business volume percentage of the current month is compared with a preset percentage threshold, and months with a cumulative business volume percentage greater than or less than the preset percentage threshold are stored in the month list.

[0080] For example, the preset percentage threshold is set to 80%, and months with a cumulative business volume percentage less than the preset percentage threshold are stored in the month list as needed. Figure 2The following is the business volume distribution information for user company A in 2020. The calculated total annual business volume is 5629. The corresponding cumulative business volume percentage is obtained based on the historical business volume of each month and the total annual business volume. Figure 3 As shown. The cumulative business volume in August accounted for 79.94%, and the cumulative business volume in November accounted for 85.63%. Therefore, the months with a cumulative business volume of less than 80% are stored in the list of months to be used in 2020 of Company A, and the list of months to be used is [5,4,3,1,9,8].

[0081] S260. Determine the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed.

[0082] S270. Based on the user attributes and preset attribute thresholds of each user to be processed, determine at least one target user.

[0083] Optionally, if the user attributes of the user to be processed are higher than the preset attribute threshold, then the user to be processed is determined to be the target user.

[0084] Specifically, if the attributes of the user to be processed are higher than the preset attribute threshold, it means that the business volume of the user to be processed is concentrated in a few months over at least two years, and the user to be processed is determined to be the target user.

[0085] S280. Based on the list of months to be used by the target user in at least two years, determine the target quarter corresponding to the target user, and determine the corresponding response measures for the target quarter.

[0086] The target quarter refers to one or more months in which the user has generated a significant historical volume of business over at least two years. Furthermore, users are more likely to have greater demand for related products, services, or businesses during the target quarter.

[0087] For example, if the list of months to be used is [2,5,8,3,7] and [3,6,5,8,9], then the target quarters are March, May, and August. After determining the target quarter for the target users, users can be visited, user care activities can be conducted, and relevant offers can be distributed before and / or during the target quarter.

[0088] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years; for each user to be processed, sorting the historical business volume of the current user in each year to obtain at least two sets of business volume distribution information associated with the current user; for each month in the current business volume distribution information, based on the current historical business volume of the current month and the historical business volume to be accumulated in the current business volume distribution information that is higher than the current historical business volume, and adding the historical business volume to be accumulated with the current historical business volume to obtain the cumulative business volume of the current month; and then, for each month's cumulative business volume and the current business volume... The historical business volume of each month in the volume distribution information is summed to obtain the cumulative business volume percentage of each month; based on the cumulative business volume percentage of the months in the current year and the preset percentage threshold, the list of months to be used in the current year to which the current business volume distribution information belongs is determined; based on the list of at least two months to be used corresponding to the current user to be processed, the user attributes of the current user to be processed are determined; based on the user attributes of each user to be processed and the preset attribute threshold, at least one target user is determined; by obtaining the list of months corresponding to the months with large historical business volume of the user through the cumulative business volume percentage of each month, a scientific data reference is provided for subsequent determination of target users and target seasons.

[0089] Example 3

[0090] Figure 5 The flowchart below shows a method for determining a target user according to Embodiment 3 of the present invention. Based on the foregoing embodiments, the user attributes of the current user to be processed can be further refined by determining the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed. For the specific implementation method, please refer to the detailed description of the embodiments of the present invention. The technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0091] like Figure 5 As shown, the method includes:

[0092] S310. Obtain historical business volume data for at least one user to be processed over at least two years.

[0093] The historical business volume data includes the historical business volume corresponding to each month of each year.

[0094] S320. For each user to be processed, sort and process the historical business volume of the current user to be processed in each year to obtain at least two sets of business volume arrangement information associated with the current user to be processed.

[0095] The number of groups for business volume distribution information is consistent with the number for the year.

[0096] S330. For each group of business volume arrangement information of the current pending users, determine the cumulative business volume percentage corresponding to each month based on the current business volume arrangement information, and determine the list of pending months of the year to which the current business volume arrangement information belongs based on the cumulative business volume percentage and the preset percentage threshold.

[0097] S340. For each list of months to be used, based on the preset month adjustment step size and the information of the months to be used in the current list of months to be used, obtain a subset of months corresponding to the information of each month to be used.

[0098] The month adjustment step size refers to the range by which each month in the month list is adjusted forward and / or backward. Furthermore, since different activity rules may cause user requests to be made earlier and / or later, introducing a month adjustment step size can improve the accuracy of target user identification. Typically, the month adjustment step size is set to 1. The month information to be used refers to the months in the month list to be used. The month subset is obtained by adjusting each month in the month list by one month step size, resulting in a subset of months corresponding to each month information to be used.

[0099] Specifically, since the same processing is applied to each month information in the list of months to be used, we will take the processing of one month information as an example. If the month information to be used is 5 and the adjustment step size is 1, then we extend forward and / or backward by one adjustment step size based on 5 to obtain the month subset [4,5,6] corresponding to the month information 5.

[0100] For example, if the monthly adjustment step size is preset to 1, the monthly step size of the three months to be used in the list of months to be used [3,4,5] is adjusted, resulting in the monthly subsets corresponding to the months to be used as [2,3,4], [3,4,5], and [4,5,6]. If the monthly adjustment step size is 2, the monthly step size of the three months to be used in the list of months to be used [3,4,5] is adjusted, resulting in the monthly subsets corresponding to the months to be used as [1,3,5], [2,4,6], and [3,5,7].

[0101] It should be noted that since adjusting month information 1 will result in 0, and delaying 12 will result in 13, the elements in the month subset need to be limited, that is, the minimum value is 1 and the maximum value is 12. For example, if the month adjustment step size is 1, adjusting month information 1 will result in the corresponding month subset [1,2], and adjusting month information 12 will result in the corresponding month subset [11,12].

[0102] S350. For each list of months to be used, determine the target month set corresponding to the current list of months to be used based on the subset of months in the current list of months to be used.

[0103] The target month set refers to the union of the subsets of months corresponding to the list of months to be used by the users to be processed.

[0104] Based on the above embodiment, the union of the month subsets [2,3,4], [3,4,5], and [4,5,6] corresponding to the list of months to be used [3,4,5] is used to obtain the target month set [2,3,4,5,6] of the list of months to be used. Since the target month set is obtained by analyzing the user's annual historical data, the number of target months should be consistent with the number of users in the year, which should be at least two, and the two should have a one-to-one correspondence.

[0105] S360. Determine the user attributes of the current user based on at least two target month sets corresponding to the current user to be processed.

[0106] Optionally, obtain the target month set of two adjacent years to get at least one set of adjacent year data; for each set of adjacent year data, determine the first month set and the second month set based on the intersection and union of the two target month sets; determine the first attribute based on the number of elements in the first month set and the second month set; process the mean of the first attribute of each adjacent year data to obtain the user attribute.

[0107] The adjacent year data includes the target month sets for two adjacent years. The first month set is the intersection of the two target sets corresponding to two adjacent years, and the second month set is the union of the two target sets corresponding to two adjacent years. Furthermore, if only the target month sets for two years are obtained, the first attribute is used as the user attribute.

[0108] For example, obtain the target month sets for user A across three years: [1,2,3,4,5,6] for 2020; [3,4,6,8,9] for 2021; and [3,4,11,9,6] for 2022. Based on these three target month sets, two sets of data for adjacent years can be obtained. [1,2,3,4,5,6] and [3,4,6,8,9] represent adjacent year data 'a'.

[0109] [3,4,6,8,9] and [3,4,11,9,6] are adjacent year data b. Therefore, the first month set corresponding to the adjacent year data a is the intersection of the two sets [3,4,6], and the second month set is the union of the two sets [1,2,3,4,5,6,8,9]. Based on the number of elements (3 and 8) in the first and second month sets, the first attribute of the adjacent year data a is... Similarly, the first attribute of adjacent year data b is User attributes are

[0110] S370. Based on the user attributes and preset attribute thresholds of each user to be processed, determine at least one target user.

[0111] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years; for each user to be processed, sorting and processing the historical business volume of the current user in each year to obtain at least two sets of business volume distribution information associated with the current user; for each set of business volume distribution information for the current user to be processed, determining the cumulative business volume percentage corresponding to each month based on the current business volume distribution information, and determining the list of months to be used for the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and a preset percentage threshold; for each list of months to be used, adjusting the monthly step size according to a preset monthly step size and the current list of months to be used. The system retrieves the information of months to be used from the available data, obtaining a subset of months corresponding to each month. For each list of months to be used, based on the subset of months in the current list, it determines the set of target months corresponding to the current list. Based on at least two sets of target months corresponding to the current user to be processed, it determines the user attributes of the current user to be processed. Based on the user attributes of each user to be processed and preset attribute thresholds, it determines at least one target user, adjusts the month list by a step size, and obtains the set of target months. This solves the problem of inaccurate target user identification caused by the time effect of the advance and / or delay of the annual activity time on the target user's business volume data. The method for determining target users is more flexible and comprehensive, improving the accuracy of user identification.

[0112] Example 4

[0113] Figure 6 This is a flowchart of a method for determining a target user provided in Embodiment 4 of the present invention. Based on the foregoing embodiments, the method for determining a target user can be further described. For specific implementation methods, please refer to the detailed description of the embodiments of the present invention. Technical terms that are the same as or corresponding to those in the above embodiments will not be repeated here.

[0114] like Figure 6 As shown, the method includes:

[0115] S410. Obtain historical business volume data for each month of at least two years for at least one user to be processed.

[0116] For example, obtain the express delivery order volume data of user A in each month of 2020 and 2021.

[0117] S420. Sort the historical business volume corresponding to each month in at least two years from high to low to obtain at least two sets of business volume distribution information.

[0118] Since the historical transaction volume is processed in the same way for each year, we will use the historical transaction volume of one year as an example. We will sort the historical transaction volume of each month in 2020 for user A, as shown below. Figure 2 The image shows a set of business volume distribution information.

[0119] S430. Calculate the total annual business volume for each year and the corresponding cumulative business volume percentage for each month.

[0120] For example, the historical business volume of all months corresponding to the current year is summed up to obtain the total business volume for the current year. For each month, the historical business volume of the current month is summed up with the business volume to be accumulated to obtain the cumulative business volume percentage for each month. See [link to relevant documentation]. Figure 3 .

[0121] S440. Generate a list of months for at least two years based on the cumulative business volume percentage of each month in at least two years and a preset percentage threshold.

[0122] For example, if the preset percentage threshold is 80%, then months with a cumulative business percentage of less than 80% will be stored in the month list to obtain the month list for each year. Furthermore, since the business volume of target users will be concentrated in a few months, if the historical business volume distribution of each month is relatively even, it means that the business volume of the user is not significantly different from month to month and there is no target season, so it will not be included in the target users.

[0123] S450. Complete the month list by offsetting the months in at least two month lists, and obtain the target month list by dimensionality reduction and deduplication.

[0124] For example, the month list [1,5,6] is padded with misalignment to obtain the corresponding month subsets [1,2], [4,5,6], and [5,6,7]. The union of all month subsets is then used to obtain the target month list [1,2,4,5,6,7].

[0125] Furthermore, since adjusting month information 1 will result in 0, and delaying 12 will result in 13, the elements in the month subset need to be limited, i.e., the minimum value is 1 and the maximum value is 12. For example, if the month adjustment step size is 1, adjusting month information 1 will result in the corresponding month subset [1,2], and adjusting month information 12 will result in the corresponding month subset [11,12].

[0126] S460. Calculate the similarity between at least two lists of target months for each year.

[0127] For example, if two lists of target months for a given year are [1,5,7,8,9] and [2,4,5,8,9], and the number of identical elements in the two lists is 3, and the two lists have a total of 7 different elements, then the similarity between the two lists is 3 / 7.

[0128] S470. Determine whether a user is a target user by comparing the similarity of at least two lists of months in different years with a set similarity threshold.

[0129] Based on the above example, the preset similarity threshold is 5 / 7. If the similarity between two lists is less than the similarity threshold, then the target user to be processed is not the target user; otherwise, it is the target user.

[0130] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years. This historical business volume data includes the historical business volume for each month within each year. For each user to be processed, the historical business volume for each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user. The number of sets of business volume distribution information corresponds to the number of years. For each set of business volume distribution information for the current user to be processed, the cumulative business volume percentage for each month is determined based on the current business volume distribution information. Based on the cumulative business volume percentage and a preset percentage threshold, a list of months to be used for the year to which the current business volume distribution information belongs is determined. Based on the list of at least two months to be used for the current user to be processed, the user attributes of the current user to be processed are determined. Based on the user attributes of each user to be processed and a preset attribute threshold, at least one target user is identified. This solution addresses the problems of high cost, low efficiency, limited data processing, lack of universality, and low accuracy in identifying target users. It achieves targeted analysis of user data, improves the efficiency and accuracy of target user identification, and saves costs.

[0131] Example 5

[0132] Figure 7 This is a schematic diagram of a device for determining a target user according to Embodiment 5 of the present invention.

[0133] like Figure 7 As shown, the device includes:

[0134] The data acquisition module 510 is used to acquire historical business volume data corresponding to at least one user to be processed in at least two years; wherein, the historical business volume data includes the historical business volume corresponding to each month in each year; the business volume arrangement processing module 520 is used to sort and process the historical business volume of the current user to be processed in each year for each user to be processed, and obtain at least two sets of business volume arrangement information associated with the current user to be processed; wherein, the number of sets of business volume arrangement information is consistent with the number of years; the month table generation module 530 is used to determine the cumulative business volume percentage corresponding to each month for each set of business volume arrangement information of the current user to be processed, and determine the list of months to be used in the year to which the current business volume arrangement information belongs based on the current business volume arrangement information, and determine the list of months to be used in the year to which the current business volume arrangement information belongs based on the cumulative business volume percentage and a preset percentage threshold; the user attribute determination module 540 is used to determine the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed; the target user module 550 is used to determine at least one target user based on the user attributes of each user to be processed and a preset attribute threshold.

[0135] Based on the above technical solutions, the data acquisition module is also used for,

[0136] The system retrieves the historical business volume of at least one user in at least two years from the database for each month, and uses this data as the historical business volume data for each year.

[0137] Based on the above technical solutions, the traffic allocation processing module is also used for,

[0138] Arrange the historical business volume of the current users to be processed in each year in descending order to obtain at least two sets of business volume arrangement information.

[0139] Based on the above technical solutions, the monthly table generation module also includes,

[0140] The cumulative business volume calculation unit is used to calculate the cumulative business volume of each month in the current business volume distribution information by adding the current historical business volume of the current month to the current historical business volume in the current business volume distribution information, based on the current historical business volume of the current month and the historical business volume to be accumulated in the current business volume distribution information. The cumulative business volume percentage calculation unit is used to calculate the cumulative business volume percentage of each month by adding the cumulative business volume of each month to the historical business volume of each month in the current business volume distribution information. The cumulative business volume percentage is inversely proportional to the cumulative business volume of each month. The month list determination unit is used to determine the list of months to be used in the current business volume distribution information based on the cumulative business volume percentage of the months in the current year and a preset percentage threshold.

[0141] Based on the above technical solutions, the user attribute determination module also includes,

[0142] The month subset generation unit is used to obtain a month subset corresponding to each month to be used based on a pre-set month adjustment step size and the month information in the current month to be used list. The target month set generation unit is used to determine the target month set corresponding to the current month to be used list based on the month subset of the current month to be used list. The user attribute determination unit determines the user attributes of the current user to be processed based on at least two target month sets corresponding to the current user to be processed.

[0143] Based on the above technical solutions, the user attribute determination unit is also used for,

[0144] Obtain the target month sets for two adjacent years to get at least one set of adjacent year data; for each set of adjacent year data, determine the first month set and the second month set based on the intersection and union of the two target month sets; determine the first attribute based on the number of elements in the first month set and the second month set; process the mean of the first attribute of each adjacent year data to obtain the user attribute.

[0145] Based on the above technical solutions, the device for determining the target user also includes,

[0146] The target user determination module is used to determine the user to be processed as the target user if the user attributes of the user to be processed are higher than the preset attribute threshold.

[0147] Based on the above technical solutions, the device for determining the target user also includes,

[0148] The hardness measure determination module is used to determine the target quarter corresponding to the target user based on the list of months to be used by the target user in at least two years, and to determine the corresponding response measures for the target quarter.

[0149] The technical solution of this invention involves acquiring historical business volume data for at least one user to be processed over at least two years. This historical business volume data includes the historical business volume for each month within each year. For each user to be processed, the historical business volume for each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user. The number of sets of business volume distribution information corresponds to the number of years. For each set of business volume distribution information for the current user to be processed, the cumulative business volume percentage for each month is determined based on the current business volume distribution information. Based on the cumulative business volume percentage and a preset percentage threshold, a list of months to be used for the year to which the current business volume distribution information belongs is determined. Based on the list of at least two months to be used for the current user to be processed, the user attributes of the current user to be processed are determined. Based on the user attributes of each user to be processed and a preset attribute threshold, at least one target user is identified. This solution addresses the problems of high cost, low efficiency, limited data processing, lack of universality, and low accuracy in identifying target users. It achieves targeted analysis of user data, improves the efficiency and accuracy of target user identification, and saves costs.

[0150] The apparatus for determining a target user provided in the embodiments of the present invention can execute the method for determining a target user provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0151] Example 6

[0152] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments 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 can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0153] like Figure 8As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0154] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0155] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as methods for identifying target users.

[0156] In some embodiments, the method for determining a target user may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining a target user described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining a target user by any other suitable means (e.g., by means of firmware).

[0157] Various embodiments 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-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0158] Computer programs used to implement 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, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0159] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0160] To provide interaction with a user, the systems and techniques described herein can 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0161] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0162] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0163] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0164] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for identifying target users, characterized in that, include: Obtain historical transaction volume data for at least one user to be processed over at least two years; wherein, the historical transaction volume data includes the historical transaction volume for each month of each year; For each user to be processed, the historical business volume of the current user to be processed in each year is sorted and processed to obtain at least two sets of business volume distribution information associated with the current user to be processed; wherein, the number of sets of business volume distribution information is consistent with the number of years. For each group of business volume distribution information of the current pending users, determine the cumulative business volume percentage corresponding to each month based on the current business volume distribution information, and determine the list of pending months of the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and the preset percentage threshold. Based on the list of at least two months to be used corresponding to the current user to be processed, determine the user attributes of the current user to be processed; Based on the user attributes and preset attribute thresholds of each user to be processed, at least one target user is identified; The step of determining the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed includes: For each list of months to be used, a subset of months corresponding to the information of each month to be used is obtained based on the preset month adjustment step size and the information of the months to be used in the current list of months to be used. For each list of months to be used, determine the target month set corresponding to the current list of months to be used, based on the subset of months in the current list of months to be used. Based on at least two target month sets corresponding to the current user to be processed, the user attributes of the current user to be processed are determined; wherein, the user attributes are the degree of consistency between the current user's at least two annual month lists.

2. The method according to claim 1, characterized in that, The acquisition of historical business volume data for at least one user to be processed over at least two years includes: The system retrieves the historical business volume of at least one user in at least two years from the database for each month, and uses this data as the historical business volume data for each year.

3. The method according to claim 1, characterized in that, The process of sorting the historical business volume of the current user to be processed in each year to obtain at least one set of business volume distribution information associated with the current user to be processed includes: The historical business volume of the current user to be processed in each year is arranged in descending order to obtain at least two sets of business volume arrangement information.

4. The method according to claim 1, characterized in that, The step of determining the cumulative business volume percentage for each month based on the current business volume distribution information, and determining the list of months to be used for the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and a preset percentage threshold, includes: For each month in the current business volume distribution information, based on the current historical business volume of the current month and the historical business volume to be accumulated in the current business volume distribution information that is higher than the current historical business volume, the historical business volume to be accumulated is added to the current historical business volume to obtain the cumulative business volume of the current month. The cumulative business volume for each month and the sum of the historical business volume for each month in the current business volume distribution information are used to obtain the cumulative business volume percentage for each month; wherein, the cumulative business volume percentage is inversely proportional to the business volume to be accumulated for each month. Based on the cumulative business volume percentage of each month in the current year and a preset percentage threshold, a list of months to be used for the year to which the current business volume distribution information belongs is determined.

5. The method according to claim 1, characterized in that, The step of determining the user attributes of the current user to be processed based on at least two target month sets corresponding to the current user to be processed includes: Obtain the target month set for two adjacent years to get at least one set of data for adjacent years; For each set of adjacent annual data, the first month set and the second month set are determined based on the intersection and union of the two target month sets; The first attribute is determined based on the number of elements in the first month set and the second month set; The user attribute is obtained by processing the mean of the first attribute of the data from each adjacent year.

6. The method according to claim 1, characterized in that, The process of determining at least one target user based on the user attributes and preset attribute thresholds of each user to be processed includes: If the user attributes of the user to be processed are higher than the preset attribute threshold, then the user to be processed is determined to be the target user.

7. The method according to claim 1 or 6, characterized in that, Also includes: Based on the list of months to be used by the target user in at least two years, determine the target quarter corresponding to the target user, and determine the corresponding countermeasures for the target quarter.

8. A device for identifying a target user, characterized in that, include: The data acquisition module is used to acquire historical business volume data for at least one user to be processed over at least two years; wherein, the historical business volume data includes the historical business volume for each month of each year; The business volume arrangement processing module is used to sort and process the historical business volume of each user to be processed in each year to obtain at least two sets of business volume arrangement information associated with the current user to be processed; wherein the number of sets of business volume arrangement information is consistent with the number of years. The monthly table generation module is used to determine the cumulative business volume percentage of each month based on the current business volume distribution information of each group of users to be processed, and to determine the list of months to be used in the year to which the current business volume distribution information belongs based on the cumulative business volume percentage and the preset percentage threshold. The user attribute determination module is used to determine the user attributes of the current user to be processed based on the list of at least two months to be used corresponding to the current user to be processed. The target user module is used to determine at least one target user based on the user attributes of each user to be processed and preset attribute thresholds; The user attribute determination module also includes, The month subset generation unit is used to obtain a month subset corresponding to each month to be used based on a pre-set month adjustment step size and the month information in the current month to be used list. The target month set generation unit is used to determine the target month set corresponding to the current month to be used list based on the month subset of the current month to be used list. The user attribute determination unit determines the user attributes of the current user to be processed based on at least two target month sets corresponding to the current user to be processed. The user attributes are the degree of consistency between at least two annual month lists of the current user to be processed.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the method for determining a target user as described in any one of claims 1-7.

Images