Business data processing method and system based on multiple channels

Abstract

The invention discloses a business data processing method and system based on multiple channels, and the method comprises the steps: obtaining the basic information of a to-be-sold commodity and a preset advertisement putting amount, calculating the average re-purchase period of the commodity through analyzing the historical business data of each channel, comparing the remaining re-purchase time of a user with the average re-purchase period, and determining a first intention user. If the number of the first intention users meets the advertisement putting demand, allocating the advertisement putting amount and screening the advertisement putting users based on the remaining re-purchase time and a preset advertisement putting preference prediction algorithm; otherwise, the second intention users who have purchased the commodities recently are found out by analyzing the commodity set with high relevance, and the final advertisement putting object is determined by combining the conditions of the two types of intention users. According to the invention, by analyzing the multi-channel business data and the user re-purchase cycle, the intentional user is accurately positioned, the advertisement putting is optimized, and the advertisement conversion rate and the resource utilization rate are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision detection, and in particular to a multi-channel-based business data processing method and system. Background Art

[0002] The current e-commerce field shows a trend of channel diversification. Major e-commerce platforms, social media, mobile applications and traditional retail industries have transformed or integrated online sales models, forming a multi-channel competition landscape. However, in this context, how to effectively place advertisements has become a major challenge for merchants. Although advertising platforms and technical means are becoming increasingly abundant, due to the lack of effective user behavior analysis and product correlation research, advertising is often not accurate enough, resulting in a waste of advertising resources and low conversion rates.

[0003] Especially for products that are purchased periodically, such as daily consumer goods and seasonal goods, the purchasing habits of consumers have obvious cyclical characteristics. The characteristic of such products is that users will make repeated purchases within a certain period. Therefore, if relevant advertisements can be accurately pushed when users are approaching their next purchase cycle, the effectiveness and conversion rate of advertisements will be greatly improved. However, the existing advertising delivery mechanism often cannot accurately grasp the user's repurchase cycle, nor can it effectively distinguish which users are about to enter the repurchase period, thus missing the best time to push advertisements. Summary of the invention

[0004] In order to solve at least one of the technical problems mentioned above, the present invention provides a multi-channel-based business data processing method and system.

[0005] In a first aspect, the present invention provides a multi-channel-based business data processing method, the method comprising:

[0006] Obtain basic product information and preset advertising volume of the products for sale;

[0007] Based on the basic information of the goods, the historical business data of the current product category in different channels is analyzed to calculate the average repurchase period of the corresponding goods, and the remaining repurchase time of users in each channel is compared with the calculated average repurchase period. If the difference between the two is less than the preset time difference, the corresponding user is determined as the first intended user;

[0008] If the total number of first-intent users is greater than or equal to the advertising delivery volume, the advertising delivery volumes of multiple channels are obtained based on the first-intent users and according to a preset advertising delivery preference prediction algorithm, and the advertising delivery users are screened out based on the channel advertising delivery volumes and the remaining repurchase time of the first-intent users of the corresponding channels;

[0009] If the total number of first-intention users is less than the amount of advertisement delivery, then based on the historical business data and according to the basic information of the products, a set of related products with high to low relevance is obtained, and second-intention users who have purchased related products within a preset time period are screened from the historical business data according to the set of related products, and the advertisement delivery users are obtained according to the distribution of the first-intention users and the second-intention users;

[0010] Push advertisements to users who place advertisements.

[0011] Preferably, the advertisement delivery preference prediction algorithm is expressed as follows:

[0012]

[0013] In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

[0014] Preferably, the method of obtaining a set of related products with descending relevance based on the historical business data and the basic information of the products, filtering out the second potential users who have purchased the related products within a preset time period from the historical business data according to the set of related products, and obtaining the advertisement delivery users according to the distribution of the first potential users and the second potential users, includes:

[0015] Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met:

[0016]

[0017] In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels. represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users;

[0018] Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products;

[0019] The first potential user and the second potential user are determined as advertisement delivery users.

[0020] Preferably, the correlation is obtained based on historical business data and analyzed according to an Apriori algorithm.

[0021] In a second aspect, the present invention further provides a multi-channel-based business data processing system, the system comprising:

[0022] The data acquisition module is used to obtain basic information of the goods for sale and the preset advertising volume;

[0023] The potential user analysis module is used to analyze the historical business data of the current product category in different channels based on the basic information of the product to calculate the average repurchase cycle of the corresponding product, and compare the remaining repurchase time of users in each channel with the calculated average repurchase cycle. If the difference between the two is less than the preset time difference, the corresponding user is determined as the first potential user;

[0024] A first advertisement delivery user determination module is used to obtain advertisement delivery amounts of multiple channels based on the first intended users and according to a preset advertisement delivery preference prediction algorithm if the total number of first intended users is greater than or equal to the advertisement delivery amount, and screen out advertisement delivery users based on the channel advertisement delivery amount and according to the remaining repurchase time of the first intended users of the corresponding channel;

[0025] A second advertisement delivery user determination module is used for, if the total number of first intention users is less than the advertisement delivery amount, obtaining a set of related products with a high to low relevance based on historical business data and basic product information, filtering out second intention users who have purchased related products within a preset time period from historical business data based on the set of related products, and obtaining advertisement delivery users based on the distribution of first intention users and second intention users;

[0026] The advertisement delivery module is used to push advertisements to advertisement delivery users.

[0027] Preferably, the advertisement delivery preference prediction algorithm is expressed as follows:

[0028]

[0029] In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

[0030] Preferably, the method of obtaining a set of related products with descending relevance based on the historical business data and the basic information of the products, filtering out the second potential users who have purchased the related products within a preset time period from the historical business data according to the set of related products, and obtaining the advertisement delivery users according to the distribution of the first potential users and the second potential users, includes:

[0031] Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met:

[0032]

[0033] In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels. represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users;

[0034] Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products;

[0035] The first potential user and the second potential user are determined as advertisement delivery users.

[0036] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory is used to store computer program code, and the computer program code comprises computer instructions. When the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] 1) The present invention realizes the effective allocation of advertising resources through in-depth mining of historical business data, and reduces advertising waste and improves advertising efficiency by accurately positioning potential customers, thereby ultimately improving the marketing benefits of the enterprise. Furthermore, more potential customers are introduced through the analysis of related products, which increases the advertising coverage while maintaining the targeting of the advertising.

[0040] 2) The present invention realizes the effective allocation of advertising resources by accurately analyzing the distribution of first-intention users in different channels, which not only improves the accuracy and conversion rate of advertising delivery, but also enhances the user experience, reduces invalid advertising expenditures, and thus improves marketing efficiency.

[0041] 3) The present invention effectively mines the correlation between commodities through the application of Apriori algorithm, provides a scientific basis for advertising, reduces operating costs by reducing the placement of invalid advertisements, and thus improves the return on investment of the overall marketing activities. At the same time, through personalized recommendations, it can also improve user experience, enhance user satisfaction and loyalty, and bring positive impacts to the long-term development of the enterprise.

[0042] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0044] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0045] Figure 1 A flowchart of a multi-channel business data processing method provided by an embodiment of the present invention;

[0046] Figure 2 A schematic diagram of the structure of a multi-channel business data processing system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] 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 are within the scope of protection of the present invention.

[0048] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0049] The existing advertising delivery mechanism is often unable to accurately grasp the intended users and often uses a full-scale delivery strategy. The advertising delivery is often not accurate enough, resulting in a waste of advertising resources and low conversion rates.

[0050] See also Figure 1 , Figure 1 The following is a flow chart of a multi-channel business data processing method provided by an embodiment of the present invention. Figure 1 As shown, the method includes:

[0051] S100, obtaining basic information of the goods for sale and a preset advertising quantity;

[0052] The basic information of the goods for sale is obtained from the e-commerce platform through interfaces or API calls of different channels. The basic information includes but is not limited to the attributes such as product ID, name, category, price, etc. At the same time, the threshold of advertising delivery set according to the marketing strategy is used as the preset advertising delivery volume. The "preset advertising delivery volume" refers to the number of advertising exposures expected to be achieved within a period of time determined by the product promotion plan.

[0053] S200, based on the basic information of the product, analyzing the historical business data of the current product category in different channels to calculate the average repurchase period of the corresponding product, comparing the remaining repurchase time of users of each channel with the calculated average repurchase period, and if the difference between the two is less than a preset time difference, determining the corresponding user as the first intended user;

[0054] Use big data analysis tools (Hadoop or Spark) to conduct in-depth mining of historical sales records in different sales channels to identify the purchasing behavior patterns of the current product category. Through statistical analysis, calculate the average repurchase cycle of specific products, that is, how long it takes for consumers to usually buy the same type of product again. Then, add the last purchase date of users in each channel to the average repurchase cycle to obtain each user's expected next purchase date, and compare it with the current time. If the time difference between the two is less than the preset time difference threshold, the user is marked as a potential repurchaser, that is, the first intention user. The "preset time difference" refers to the maximum time deviation allowed, which is used to determine whether the user is close to his or her repurchase time. It should be noted that the preset time difference is different for different products. For example, female users need to repurchase sanitary napkins every month or so, so the preset time difference can be set to one week or less, so that users who have been away from their last purchase for more than three weeks can be identified and marked as first intention users.

[0055] S300, if the total number of first potential users is greater than or equal to the advertising delivery amount, based on the first potential users and according to a preset advertising delivery preference prediction algorithm, multiple channel advertising delivery amounts are obtained, and based on the channel advertising delivery amounts and according to the remaining repurchase time of the first potential users of the corresponding channel, advertising delivery users are screened out;

[0056] In order to determine the amount of advertising on different channels, we first need to collect the data of all first-intention users and classify them according to the different channels where the users are located. For each channel, calculate the proportion of first-intention users in the channel to the total first-intention users. A distributed data processing framework is used here, such as Apache Hadoop or Spark, to efficiently process massive data and parallelize data from multiple channels to speed up data processing.

[0057] In a possible embodiment, other influencing factors are considered, such as historical conversion rate of a channel, user activity and other indicators. These indicators can be quantified in the following ways:

[0058] User activity can be measured by data such as user visit frequency, dwell time, and click-through rate on the channel;

[0059] The historical conversion rate can be calculated based on the actual conversions after the advertising on the channel was launched over a period of time. A weighted sum method is used to comprehensively consider these influencing factors. The formula is as follows:

[0060] W i =α·P i +β·C i +γ·A i

[0061] Among them, W i represents the comprehensive weight of the ith channel, P i represents the proportion of first-intention users in the i-th channel, C i represents the historical conversion rate of the ith channel, A i represents the user activity of the ith channel, α, β, and γ represent the weight coefficients of proportion, conversion rate, and activity, respectively.

[0062] After determining the comprehensive weight of each channel, the advertising volume is allocated according to the weight ratio. Specifically, the total advertising volume is multiplied by the comprehensive weight ratio of each channel, that is:

[0063]

[0064] Among them, Q i It represents the advertising volume allocated to the ith channel, and N is the total advertising volume.

[0065] The above allocation method not only takes into account the distribution of first-intention users, but also takes into account historical performance and user behavior characteristics, so that advertising resources can be more accurately allocated to channels that are more likely to bring conversions, thereby improving the effectiveness of the overall advertising campaign.

[0066] S400, if the total number of first potential users is less than the amount of advertisement delivery, then based on the historical business data and according to the basic information of the products, a set of related products with high to low relevance is obtained, and second potential users who have purchased related products within a preset time period are screened from the historical business data according to the set of related products, and advertisement delivery users are obtained according to the distribution of the first potential users and the second potential users;

[0067] If it is found in step S300 that the number of first potential users is insufficient, a clustering algorithm is used to find a combination of products that are highly correlated with the target product, forming a set of related products, and finding users who have purchased these related products within a preset time period, and defining these users as second potential users. Combined with the distribution of the first and second potential users, a comprehensive evaluation is performed to determine the optimal user group for advertising.

[0068] S500: Push advertisements to advertisement delivery users.

[0069] Personalized advertising content is accurately pushed to advertising users through multiple channels such as email, SMS, social media, etc.

[0070] In this embodiment, effective allocation of advertising resources is achieved through in-depth mining of historical business data, and by accurately positioning potential customers, advertising waste is reduced, advertising efficiency is improved, and ultimately the company's marketing benefits are improved. Furthermore, more potential customers are introduced through analysis of related products, increasing advertising coverage while maintaining advertising targeting.

[0071] Preferably, the advertisement delivery preference prediction algorithm is expressed as follows:

[0072]

[0073] In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

[0074] In this embodiment, by accurately analyzing the distribution of first-intention users in different channels, effective allocation of advertising resources is achieved, which not only improves the accuracy and conversion rate of advertising delivery, but also enhances user experience, reduces invalid advertising expenditures, and thus improves marketing efficiency.

[0075] Preferably, the method of obtaining a set of related products with descending relevance based on the historical business data and the basic information of the products, filtering out the second potential users who have purchased the related products within a preset time period from the historical business data according to the set of related products, and obtaining the advertisement delivery users according to the distribution of the first potential users and the second potential users, includes:

[0076] Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met:

[0077]

[0078] In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels. represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users;

[0079] Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products;

[0080] The first potential user and the second potential user are determined as advertisement delivery users.

[0081] In this embodiment, an empty associated product set K is created to store products that are highly associated with the target product. In this step, "associated products" refer to products that are related to the target product in some way, which may be complementary products, substitutes, or other related products. The association can be obtained through data analysis, for example, by analyzing the user's shopping basket data to find out products that are often purchased together. According to the association between the products, the associated product k is added to the associated product set K in descending order. i , until the condition is met: When solving the smallest set of associated products, the idea of ​​greedy algorithm is used. Each time, the product with the highest correlation is selected to join the set until the conditions are met. The advantage of this is that an approximate optimal solution can be quickly obtained, and the computational complexity is low, which is suitable for large-scale data processing. The key to this step is to select appropriate associated products to meet the advertising needs to the greatest extent, and to continuously try to add associated products until the predetermined advertising volume N is reached. Based on the associated product set, the second intention users who have purchased the associated products within a preset time period are screened out from the historical business data. The process of screening the second intention users depends on the historical business data. The historical business data contains user behavior information, such as purchase records, browsing records, etc. The user records that meet the conditions are quickly retrieved through SQL query statements, and summarized and counted. Users who have purchased associated products in the past period of time can be found. They are regarded as second intention users, and the first intention users and second intention users are determined as advertising users.

[0082] In this embodiment, through related product analysis and user segmentation, effective allocation of advertising resources is achieved, the accuracy and conversion rate of advertising delivery are improved, invalid advertising expenditures are reduced, and user experience is improved, thereby achieving significant beneficial effects in improving advertising delivery effectiveness.

[0083] Preferably, the correlation is obtained based on historical business data and analyzed according to an Apriori algorithm.

[0084] The core idea of ​​the Apriori algorithm is to use the a priori property of frequent itemsets, that is, if an itemset is frequent, then all its subsets are also frequent. Based on this principle, the algorithm first scans the data set to find frequently occurring single items, then gradually combines them into larger itemsets, and continues to scan the data set to verify whether these combinations are frequent enough. This cycle is repeated until no new frequent itemsets are found. In this process, the algorithm needs to calculate the support of each itemset, that is, the frequency of occurrence of the itemset, and the confidence, that is, the probability that another item is also included in a transaction containing a certain item. Only when both the support and confidence are higher than the preset threshold, the corresponding association rule is considered valid. After obtaining a series of association rules, the products are sorted according to the support and confidence of the rules to form a set of associated products with high to low relevance. Products with high relevance mean that there is a high probability of co-occurrence between them. Therefore, when advertising, pushing advertisements of target products to users who have purchased these associated products can significantly improve the click-through rate and conversion rate of the advertisements.

[0085] When the associated product set is built, the second potential users are screened out based on the user records who have purchased the associated products within the preset time period. The "preset time period" usually refers to a period of time calculated from the current time. The selection of this period needs to be based on the characteristics of the product and the market strategy. The purpose is to ensure that the screened users are still active and have a high probability of responding to the advertisement.

[0086] This embodiment uses the Apriori algorithm to effectively mine the correlation between products, provide a scientific basis for advertising, reduce operating costs by reducing the delivery of invalid advertisements, and thus improve the return on investment of the overall marketing activities. At the same time, through personalized recommendations, it can also improve user experience, enhance user satisfaction and loyalty, and have a positive impact on the long-term development of the enterprise.

[0087] In summary, the method provided in this embodiment can at least achieve the following effects:

[0088] 1) The present invention realizes the effective allocation of advertising resources through in-depth mining of historical business data, and reduces advertising waste and improves advertising efficiency by accurately positioning potential customers, thereby ultimately improving the marketing benefits of the enterprise. Furthermore, more potential customers are introduced through the analysis of related products, which increases the advertising coverage while maintaining the targeting of the advertising.

[0089] 2) The present invention realizes the effective allocation of advertising resources by accurately analyzing the distribution of first-intention users in different channels, which not only improves the accuracy and conversion rate of advertising delivery, but also enhances the user experience, reduces invalid advertising expenditures, and thus improves marketing efficiency.

[0090] 3) The present invention effectively mines the correlation between commodities through the application of Apriori algorithm, provides a scientific basis for advertising, reduces operating costs by reducing the placement of invalid advertisements, and thus improves the return on investment of the overall marketing activities. At the same time, through personalized recommendations, it can also improve user experience, enhance user satisfaction and loyalty, and bring positive impacts to the long-term development of the enterprise.

[0091] See also Figure 2 In one embodiment, a multi-channel-based business data processing system is also provided, the system comprising:

[0092] The data acquisition module 100 is used to acquire basic information of the goods for sale and a preset advertising volume;

[0093] The potential user analysis module 200 is used to analyze the historical business data of the current commodity category in different channels based on the basic information of the commodity, so as to calculate the average repurchase period of the corresponding commodity, and compare the remaining repurchase time of the users of each channel with the calculated average repurchase period. If the difference between the two is less than the preset time difference, the corresponding user is determined as the first potential user;

[0094] The first advertisement delivery user determination module 300 is used to obtain the advertisement delivery amounts of multiple channels based on the first intended users and according to a preset advertisement delivery preference prediction algorithm if the total number of first intended users is greater than or equal to the advertisement delivery amount, and screen out advertisement delivery users based on the channel advertisement delivery amounts and the remaining repurchase time of the first intended users of the corresponding channels;

[0095] The second advertisement delivery user determination module 400 is used to obtain a set of related products with a high to low relevance based on historical business data and basic product information if the total number of first potential users is less than the advertisement delivery amount, filter out second potential users who have purchased related products within a preset time period from historical business data based on the set of related products, and obtain advertisement delivery users based on the distribution of first potential users and second potential users;

[0096] The advertisement delivery module 500 is used to push advertisements to advertisement delivery users.

[0097] In one embodiment, the advertisement delivery preference prediction algorithm is expressed as follows:

[0098]

[0099] In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

[0100] In one embodiment, the method of obtaining a set of related products with a descending relevance based on the historical business data and the basic information of the products, filtering out the second potential users who have purchased the related products within a preset time period from the historical business data according to the set of related products, and obtaining the advertisement delivery users according to the distribution of the first potential users and the second potential users, includes:

[0101] Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met:

[0102]

[0103] In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels. represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users;

[0104] Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products;

[0105] The first potential user and the second potential user are determined as advertisement delivery users.

[0106] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0107] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0108] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0109] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0110] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

Claims

1. A multi-channel business data processing method, characterized in that: The method comprises: Obtain basic product information and preset advertising volume of the products for sale; Based on the basic information of the goods, the historical business data of the current product category in different channels is analyzed to calculate the average repurchase period of the corresponding goods, and the remaining repurchase time of users in each channel is compared with the calculated average repurchase period. If the difference between the two is less than the preset time difference, the corresponding user is determined as the first intended user; If the total number of first-intent users is greater than or equal to the advertising delivery volume, the advertising delivery volumes of multiple channels are obtained based on the first-intent users and according to a preset advertising delivery preference prediction algorithm, and the advertising delivery users are screened out based on the channel advertising delivery volumes and the remaining repurchase time of the first-intent users of the corresponding channels; If the total number of first-intention users is less than the amount of advertisement delivery, then based on the historical business data and according to the basic information of the products, a set of related products with high to low relevance is obtained, and second-intention users who have purchased related products within a preset time period are screened from the historical business data according to the set of related products, and the advertisement delivery users are obtained according to the distribution of the first-intention users and the second-intention users; Push advertisements to users who place advertisements.

2. The multi-channel business data processing method according to claim 1, characterized in that: The advertising placement preference prediction algorithm is expressed as follows: In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

3. The multi-channel business data processing method according to claim 1, characterized in that: The method is based on the historical business data and the basic information of the products to obtain a set of related products with a descending relevance, and according to the set of related products, to filter out the second potential users who have purchased the related products within a preset time period from the historical business data, and to obtain the users for advertisement delivery according to the distribution of the first potential users and the second potential users, including: Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met: In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels, represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users; Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products; The first potential user and the second potential user are determined as advertisement delivery users.

4. The multi-channel business data processing method according to claim 1, characterized in that: The correlation is obtained based on historical business data and analyzed according to the Apriori algorithm.

5. A multi-channel business data processing system, characterized in that: The system comprises: The data acquisition module is used to obtain basic information of the goods for sale and the preset advertising volume; The potential user analysis module is used to analyze the historical business data of the current product category in different channels based on the basic information of the product to calculate the average repurchase cycle of the corresponding product, and compare the remaining repurchase time of users in each channel with the calculated average repurchase cycle. If the difference between the two is less than the preset time difference, the corresponding user is determined as the first potential user; A first advertisement delivery user determination module is used to obtain advertisement delivery amounts of multiple channels based on the first intended users and according to a preset advertisement delivery preference prediction algorithm if the total number of first intended users is greater than or equal to the advertisement delivery amount, and screen out advertisement delivery users based on the channel advertisement delivery amount and according to the remaining repurchase time of the first intended users of the corresponding channel; A second advertisement delivery user determination module is used for, if the total number of first intention users is less than the advertisement delivery amount, obtaining a set of related products with a high to low relevance based on historical business data and basic product information, filtering out second intention users who have purchased related products within a preset time period from historical business data based on the set of related products, and obtaining advertisement delivery users based on the distribution of first intention users and second intention users; The advertisement delivery module is used to push advertisements to advertisement delivery users.

6. The multi-channel business data processing system according to claim 5, characterized in that: The advertising placement preference prediction algorithm is expressed as follows: In the formula, AD i represents the advertising volume of channel i, N represents the advertising volume, and A i represents the number of first-intention users in channel i, m represents the number of channels, Represents the total number of first intent users across all channels.

7. The multi-channel business data processing system according to claim 5, characterized in that: The method is based on the historical business data and the basic information of the products to obtain a set of related products with a descending relevance, and according to the set of related products, to filter out the second potential users who have purchased the related products within a preset time period from the historical business data, and to obtain the users for advertisement delivery according to the distribution of the first potential users and the second potential users, including: Initialize an empty set of related products, and add related product k to the related product set K in descending order of relevance. i , until the condition is met: In the formula, |K i | represents the size of the associated product set in channel i, m represents the number of channels, Represents the total number of first-intent users across all channels, represents the total number of second-intention users across all channels, B ik Indicates that the associated product K has been purchased within the preset time period k The number of second-intention users; Solve to obtain the smallest set of related products, and filter out the second potential users who have purchased related products within a preset time period from historical business data based on the set of related products; The first potential user and the second potential user are determined as advertisement delivery users.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program code, wherein the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes the multi-channel-based business data processing method as described in any one of claims 1 to 4.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the multi-channel-based business data processing method according to any one of claims 1 to 4.

Images