A population targeting method based on big data analysis

Abstract

This invention discloses a user targeting method based on big data analysis, belonging to the field of user targeting technology. It addresses the problems of reduced shopping cart conversion efficiency and increased resource waste in recommendation systems. By setting an analysis time, the method monitors the frequency of user visits to the shopping cart to determine whether the user enters the product analysis mechanism. When the product analysis mechanism is entered, the method statistically analyzes the access interval of various products, extracts the user's conversion cycle benchmark from the historical database, calculates the interaction decay characteristics based on the access interval, and analyzes the cooling-off ratio to determine whether the user is in the interest cooling-off stage. For the interest cooling-off stage, the method extracts the product dwell time and product source information, calculates the channel stickiness index of different product source channels, and comprehensively calculates the scheduling priority score by combining the channel stickiness index and product dwell time. This adjusts the display order of products in the shopping cart, increasing the display weight of high-potential products and improving shopping cart conversion efficiency and recommendation accuracy.

Description

Technical Field

[0001] This invention relates to the field of crowd targeting technology, and more specifically, to a crowd targeting method based on big data analysis. Background Technology

[0002] With the rapid development of internet e-commerce platforms and digital marketing systems, user behavior data on online shopping platforms is characterized by high frequency, diversity, and fragmentation. Merchants typically assess users' purchasing interests and potential needs by analyzing their browsing history, shopping cart activity records, and order conversion behavior.

[0003] The existing technology has the following shortcomings:

[0004] Currently, existing audience targeting methods only segment users based on static behavioral tags, lacking a dynamic analysis mechanism for the temporal characteristics of user access behavior and the law of interest decay. They cannot accurately identify the user's interest cooling stage and adjust the display strategy accordingly, making it difficult to achieve refined targeting and product priority scheduling based on real-time interest status. This leads to reduced shopping cart conversion efficiency and increased waste of recommendation system resources. Therefore, a audience targeting method based on big data analysis is proposed.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a user targeting method based on big data analysis, which solves the problems mentioned in the background art by employing user access behavior time-series analysis, interaction decay modeling, channel stickiness calculation, and product scheduling priority scoring mechanism.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a population targeting method based on big data analysis, comprising the following steps:

[0008] Step S1: Set the analysis time. During the analysis time, determine whether to enter the product analysis mechanism based on the number of times the user accesses the shopping cart. When entering the product analysis mechanism, count the access interval of various types of products.

[0009] Step S2: Access the historical database to obtain the user's conversion cycle benchmark, analyze the interaction decay characteristics using the access interval, and determine whether the user's conversion interest stage is in the interest cooling stage based on the conversion cycle benchmark.

[0010] Step S3: When the user is in the interest cooling stage, the product retention time and product source information of various products are obtained, and the channel stickiness index of the user to the product source information is evaluated according to the product source information;

[0011] Step S4: The scheduling priority score of various products is evaluated by combining the channel stickiness index and the product retention time, the various products in the shopping cart are sorted based on the scheduling priority score, and the arrangement order of the products in the shopping cart is adjusted according to the sorting result.

[0012] In a preferred embodiment, in step S1, a preset analysis time is set, the number of times of accessing the shopping cart by the user is monitored in real time within the preset analysis time, and the ratio result of the number of times of accessing the shopping cart by the user to the preset analysis time is taken as the shopping cart access frequency;

[0013] If the shopping cart access frequency is greater than the preset access frequency threshold, it is judged to enter the product analysis mechanism;

[0014] Otherwise, it is judged not to enter the product analysis mechanism.

[0015] In a preferred embodiment, in step S1, when entering the product analysis mechanism, the access events of various products are called through a log database, and the time stamp of the access event is taken as the product access time;

[0016] The product access times of the same type of products are sorted in time sequence and combined into an access time sequence;

[0017] The access time sequence is analyzed, and the adjacent product access times are processed by difference to obtain an access interval.

[0018] In a preferred embodiment, in step S2, the conversion cycle benchmark of the user is obtained from the access history database;

[0019] The reciprocal of the conversion cycle benchmark is taken as the interest decay rate;

[0020] The access intervals of the same type of products are sorted in time sequence, and the change amplitude between adjacent access intervals is analyzed;

[0021] The current access interval is processed by difference with the previous access interval to obtain an interval change amplitude, and the access interval growth rate is obtained by dividing the interval change amplitude by the previous access interval;

[0022] The average value of the access interval growth rate is taken as the interaction decay feature of various products.

[0023] In a preferred embodiment, in step S2, after the interaction decay feature is standardized by the Max-min standardization method, the category interest deviation value is calculated by combining the interest decay rate.

[0024] The number of product categories with a category interest offset value greater than 1 is counted as the total number of declining categories, and the ratio of the total number of declining categories to the total number of product categories in the shopping cart is used as the cooling ratio.

[0025] If the cooling ratio is greater than the preset cooling ratio threshold, the user's conversion interest stage is determined to be the interest cooling stage.

[0026] Conversely, if the user's conversion interest stage is determined to be the active interest stage.

[0027] In a preferred embodiment, in step S3, when the user is in the interest cooling phase, the dwell time and product source information of the items in the shopping cart are obtained through the log database;

[0028] Product source information refers to the source channel identifier when a user adds a product to their shopping cart;

[0029] The average residence time of similar products is taken to obtain the residence time of similar products.

[0030] In a preferred embodiment, in step S3, historical conversion data corresponding to each source channel identifier is retrieved from the conversion statistics database, including the number of product purchases corresponding to different source channel identifiers;

[0031] The cumulative number of purchases is calculated by summing the purchase counts corresponding to products from different source channels.

[0032] The ratio of the number of times a product is purchased to the total number of purchases corresponding to the source channel identifier is used as the channel stickiness index of the product source information.

[0033] In a preferred embodiment, in step S4, the average channel stickiness index of similar products is obtained by averaging the channel stickiness index in the product source information of similar products.

[0034] The channel stickiness index mean and product dwell time were standardized to obtain the channel stickiness coefficient and dwell time coefficient.

[0035] In a preferred embodiment, in step S4, the scheduling priority score of various commodities is evaluated using the channel stickiness coefficient and the residence time coefficient: ,in, Prioritize scheduling and score. Channel stickiness coefficient, This is the dwell time coefficient. The preset time decay factor, It is a natural constant;

[0036] According to the scheduling priority score of various types of goods, the various types of goods are sorted in descending order, and the arrangement order of the various types of goods in the shopping cart is adjusted according to the sorting result.

[0037] Technical effects and advantages of the present application:

[0038] The present application sets the analysis time, monitors the user access frequency of the shopping cart, judges whether to enter the commodity analysis mechanism, when entering the commodity analysis mechanism, the access interval of various types of goods is counted, the conversion cycle benchmark of the user is extracted from the access history database, the interaction attenuation feature is calculated in combination with the access interval, and then the cooling ratio is analyzed to judge whether the user is in the interest cooling stage, for the interest cooling stage, the commodity retention time and the commodity source information are extracted, the channel stickiness index of different commodity source channels is calculated, the channel stickiness index and the commodity retention time are comprehensively calculated to obtain the scheduling priority score, and the display order of the shopping cart goods is adjusted accordingly, realizing the closed-loop control from the stage recognition of user conversion interest to dynamic display optimization, improving the display weight of high-potential goods, and improving the shopping cart conversion efficiency and recommendation accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0039] Fig. 1 The present application is a flowchart for realizing a population targeting method based on big data analysis.

[0040] Fig. 2 The present application is a flowchart for realizing a population targeting method based on big data analysis. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0042] The present application sets the analysis time, monitors the user access frequency of the shopping cart, judges whether to enter the commodity analysis mechanism, when entering the commodity analysis mechanism, the access interval of various types of goods is counted, the conversion cycle benchmark of the user is extracted from the access history database, the interaction attenuation feature is calculated in combination with the access interval, and then the cooling ratio is analyzed to judge whether the user is in the interest cooling stage, for the interest cooling stage, the commodity retention time and the commodity source information are extracted, the channel stickiness index of different commodity source channels is calculated, the channel stickiness index and the commodity retention time are comprehensively calculated to obtain the scheduling priority score, and the display order of the shopping cart goods is adjusted accordingly, realizing the closed-loop control from the stage recognition of user conversion interest to dynamic display optimization, improving the display weight of high-potential goods.

[0043] Example 1, asFigs. 1-2 As shown in the figure, a crowd-oriented method based on big data analysis includes the following steps:

[0044] Step S1: Set the analysis time, and determine whether to enter the product analysis mechanism according to the number of times the user accesses the shopping cart within the analysis time. When entering the product analysis mechanism, the access interval of each type of product is counted.

[0045] Step S2: Obtain the conversion cycle benchmark of the user from the access history database, analyze the interaction decay characteristics using the access interval, and determine whether the user's conversion interest stage is the interest cooling stage in combination with the conversion cycle benchmark.

[0046] Step S3: When the user is in the interest cooling stage, obtain the product retention time and product source information of each type of product, and evaluate the channel stickiness index of the user to the product source information according to the product source information.

[0047] Step S4: Evaluate the scheduling priority score of each type of product by combining the channel stickiness index and the product retention time, sort the types of products in the shopping cart based on the scheduling priority score, and adjust the arrangement order of the products in the shopping cart according to the sorting result.

[0048] The specific implementation is as follows:

[0049] In step S1, the preset analysis time is set, and the number of times the user accesses the shopping cart is monitored in real time within the preset analysis time. The ratio of the number of times the user accesses the shopping cart to the preset analysis time is taken as the shopping cart access frequency.

[0050] The preset access frequency threshold is compared with the shopping cart access frequency to determine whether to enter the product analysis mechanism.

[0051] If the shopping cart access frequency is greater than the preset access frequency threshold, it is determined that the product analysis mechanism is entered.

[0052] Conversely, it is determined that the product analysis mechanism is not entered.

[0053] When the shopping cart access frequency is greater than the preset access frequency threshold, it indicates that the user's product attention frequency to the shopping cart is high within the preset analysis time. After entering the product analysis mechanism, the user's conversion interest stage is further analyzed.

[0054] When entering the product analysis mechanism, the access events of each type of product are retrieved from the log database, and the timestamp of the access event is taken as the product access time.

[0055] Among them, each type of product refers to the division of products into different categories according to the category of the product. Within the preset statistical time, for example, it includes digital accessory products, shoe single product, and instant food products, etc.

[0056] The commodity access time of the same kind of commodities is sorted in time sequence and combined into an access time sequence, and the access time sequence is analyzed to obtain an access interval by differencing adjacent commodity access times, which is used to reflect the continuous access trend of the user to the same kind of commodities.

[0057] It should be explained that the preset analysis time refers to a time window for counting the user's access to the shopping cart behavior, which can be set according to the platform activity and the commodity cycle; the preset access frequency threshold is a behavior trigger threshold for judging whether the user enters the commodity analysis mechanism, which can be set according to the activity level of different user groups, for example, the group label of the user is retrieved, and for daily active users, the average value of the shopping cart access frequency of the daily active users is taken as the preset access frequency threshold; the log database is a data storage module for recording the behavior event information of the user, and records the behavior logs of the user access, adding to the shopping cart and the commodity source channel in time sequence, which is used to generate the time sequence and source record of the commodities in the shopping cart.

[0058] This step can analyze the user behavior characteristics from the time dimension by monitoring and counting the user's access to the shopping cart behavior, and can realize the preliminary layering of the user interest cycle, and provide high timeliness and comparable data basis for the subsequent conversion interest evaluation stage.

[0059] In step S2, the access history database obtains the conversion cycle benchmark of the user, and the conversion cycle benchmark refers to the average time cycle experienced by the user from accessing the shopping cart to completing the purchase of the commodity in the past shopping behavior.

[0060] It should be explained that the history database refers to the continuous archiving and counting of the historical data of the user and different categories of commodities, and in this embodiment, it is used to extract the conversion cycle benchmark of the user.

[0061] The access intervals of the same kind of commodities are sorted in time sequence, and the change amplitude between adjacent access intervals is analyzed, and the interval change amplitude is obtained by differencing the current access interval and the previous access interval, and the access interval growth rate is obtained by dividing the previous access interval, which reflects the change trend of the access interval.

[0062] The average value of the access interval growth rate is taken as the interaction decay feature of each kind of commodity.

[0063] The greater the interaction decay feature, the more obvious the interest decay of the commodity, and the smaller the interaction decay feature, the shorter or stable the access interval, and the interest in the commodity is maintained or enhanced.

[0064] The reciprocal of the conversion period reference is taken as the interest decay rate, reflecting the average rate at which the user completes a purchase decision in a unit of time;

[0065] The interaction decay feature is standardized using the Max-min standardization method: , is the interaction decay feature of each type of commodity, is the minimum value of the interaction decay feature of each type of commodity, is the maximum value of the interaction decay feature of each type of commodity, is the standardized result corresponding to the interaction decay feature.

[0066] The product of the interest decay rate and the preset adjustment coefficient is taken as the adjusted decay rate;

[0067] The ratio of the standardized result of the interaction decay feature to the adjusted decay rate is taken as the category interest offset value;

[0068] For example, the interest decay rate is set to 0.25, the result of the Max-min standardization processing of the interaction decay feature of the earphone type commodity is 0.39, and the preset adjustment coefficient is 0.8. Then the adjusted decay rate is 0.2. The ratio of the standardized result of the interaction decay feature of the earphone type commodity to the adjusted decay rate is calculated to obtain the category interest offset value of the earphone type commodity, which is 1.95.

[0069] When the category interest offset value is greater than 1, it means that the user's interest in the commodity decreases faster than the interest decay rate, and the user is in the interest cooling stage. When the category interest offset value is less than or equal to 1, it means that the user's interest in the commodity is maintained or enhanced, and the user is in the interest active stage.

[0070] The category interest offset values are analyzed to determine whether the user's conversion interest stage is in the interest cooling stage. The number of commodity categories with a category interest offset value greater than 1 is counted as the total number of decreasing categories. The ratio of the total number of decreasing categories to the total number of commodity categories in the shopping cart is taken as the cooling ratio.

[0071] The preset cooling ratio threshold is compared with the cooling ratio to determine whether the user's conversion interest stage is in the interest cooling stage:

[0072] If the cooling ratio is greater than the preset cooling ratio threshold, it is determined that the user's conversion interest stage is in the interest cooling stage;

[0073] Otherwise, it is determined that the user's conversion interest stage is in the interest active stage.

[0074] The interest cooling stage refers to the weakening of the user's attention to the commodities in the shopping cart and the delay of the purchase decision. The interest active stage refers to the high level of interaction between the user and the commodities in the shopping cart.

[0075] It needs to be explained that the Max-min normalization method is a data normalization method that maps the original data to the interval [0, 1] through linear transformation; the preset adjustment coefficient refers to the coefficient parameter for adjusting the influence weight of the interest decay rate in the category interest offset value calculation, the value range is 0 to 1 interval, which can be set according to the historical data distribution characteristics; the preset cooling rate threshold can be calculated according to the user historical behavior sample, for example, by analyzing the cooling rate of the historical user in the shopping cart access stage and the actual conversion result for linear fitting, selecting the cooling rate corresponding to the turning point of the actual conversion result as the preset cooling rate threshold.

[0076] This step is used to identify the conversion interest stage of the user, through dynamic analysis of the interaction decay feature, quantifying the change of user attention to different goods, and taking the cooling rate as a measurement index, the conversion interest stage of the user is converted into a quantifiable index, realizing the identification of the interest cooling stage, and providing behavior basis for the subsequent priority display strategy.

[0077] In step S3, when the user is in the interest cooling stage, further analyze the conversion potential of various goods, and prioritize the goods with high conversion potential;

[0078] Obtain the retention time and source information of the goods in the shopping cart through the log database;

[0079] Take the average of the retention time of the same kind of goods to obtain the retention time of the same kind of goods;

[0080] The retention time of the goods refers to the cumulative residence time of the user from the first time the goods are added to the shopping cart to the current analysis time; the source information of the goods refers to the source channel identifier when the user adds the goods to the shopping cart, for example, the source information of the goods includes homepage recommendation, search result page, activity page and different source channel identifiers.

[0081] Retrieving the historical conversion data corresponding to each source channel identifier through the conversion statistics database, the historical conversion data refers to the statistical sample information generated based on the historical shopping behavior of the current user under different source channels, including the number of goods purchased corresponding to different source channel identifiers;

[0082] The number of goods purchased corresponding to different source channel identifiers is accumulated and summed as the cumulative purchase times, and the ratio of the number of goods purchased corresponding to the source channel identifier to the cumulative purchase times is taken as the channel stickiness index of the source information of the goods, reflecting the attraction degree of different source information of goods to the user's purchase behavior;

[0083] For example, the purchase times of the home page recommendation channel is 30 times, the purchase times of the activity page channel is 15 times, and the purchase times of the search page channel is 5 times. The cumulative purchase times is 50 times after the purchase times of the three source channels are added. The ratio of the purchase times of each source channel to the cumulative purchase times is 0.6, 0.3, and 0.1 respectively. The corresponding values are used as the channel stickiness indexes of the source information of each product.

[0084] The greater the channel stickiness index is, the greater the proportion of the purchase frequency of the user in the source channel is, and the higher the purchase conversion rate of the user is. The smaller the channel stickiness index is, the smaller the proportion of the purchase frequency of the user in the source channel is, and the lower the purchase conversion rate of the user is.

[0085] It should be explained that the conversion statistics database refers to a database for storing and managing historical shopping behavior data of the user in different source information of products, and is used for retrieving historical conversion data corresponding to the source information of products.

[0086] This step evaluates the conversion potential of different categories of products when the user is in the interest cooling stage, calculates the channel stickiness index based on the source information of products, evaluates the attachment of the user to different channels, dynamically identifies the category products that still have conversion potential in the cooling stage, and preferentially displays the category products with high stickiness.

[0087] In step S4, the channel stickiness indexes in the source information of the same category of products are averaged to obtain the average channel stickiness index of the same category of products.

[0088] The channel stickiness coefficient and the retention time coefficient are obtained after the average channel stickiness index and the product retention time are standardized respectively.

[0089] The channel stickiness coefficient and the retention time coefficient are used to evaluate the scheduling priority score of each category of products. wherein, is the scheduling priority score, is the channel stickiness coefficient, is the retention time coefficient, is a preset time decay factor, is a natural constant.

[0090] It should be explained that the standardization processing method includes but is not limited to standard linear transformation based on interval scaling, Z-Score standardization method based on statistics, or normalization method based on nonlinear mapping function. The application method of standardization processing is not described here. The preset time decay factor is used to adjust the decay strength of the retention time coefficient in the scheduling priority score. The value range is 0 to 1 interval. The preset time decay factor can be mapped to the 0 to 1 interval based on the ratio of the average access interval of each category of products to the conversion period benchmark.

[0091] For example, the average of the channel stickiness index and the commodity retention time are standardized respectively to obtain the channel stickiness coefficient and the retention time coefficient. Assuming that the standardized results of the earphone commodity are the channel stickiness coefficient 0.72 and the retention time coefficient 0.45, the preset time decay factor is set to 0.6, and the dispatch priority score calculation model is substituted to obtain the dispatch priority score of the earphone commodity as follows: wherein, is the dispatch priority score;

[0092] The longer the commodity retention time, the longer the time left in the shopping cart, and the user interest decays. The shorter the commodity retention time, the more new the user interest in the commodity. The greater the dispatch priority score, the greater the channel stickiness coefficient and the shorter the retention time coefficient, and the higher the user purchase potential of the commodity. The smaller the dispatch priority score, the smaller the channel stickiness coefficient and the longer the retention time coefficient, and the lower the user purchase potential of the commodity.

[0093] The various commodities are sorted in descending order according to the dispatch priority score, and the arrangement order of the various commodities in the shopping cart is adjusted according to the sorting result.

[0094] The display order of the various commodities in the shopping cart is adjusted by comparing the numerical values of the dispatch priority scores, so that the arrangement order of the commodities in the shopping cart interface can be updated when the user is in the interest cooling stage, thereby improving the conversion probability of the commodities.

[0095] This step dynamically adjusts the display order of the commodities in the shopping cart according to the dispatch priority score, sorts and rearranges the commodities in descending order, realizes real-time optimization of the shopping cart display layer, and can make the display order of the commodities in the user shopping cart interface consistent with the change of the conversion interest, thereby improving the exposure probability and the final conversion rate of the high-potential commodities, and forming a closed-loop optimization from interest recognition to commodity order display adjustment.

[0096] Finally, it should be noted that in this paper, relational terms such as first and second are used merely to distinguish one entity or action from another entity or action, and do not necessarily require or imply that there is any such actual relationship or order between these entities or actions.

[0097] Also, the use of "including," "comprising," or "having" and variations thereof herein is meant to encompass the items listed thereafter and equivalents thereof as well as additional items. Unless otherwise specified, "or" means "and / or." Unless otherwise noted, the use of the positive is meant to encompass the negative, e.g., the use of "a" is meant to encompass "not a," the use of "at least one" is meant to encompass "zero or more," etc.

[0098] In this document, the terms "a" or "an" are used, as is common in patent documents, to include one or more than one, independent of any other instances or usages of "at least one." In this document, the term "or" as used herein is used to mean "and / or," i.e., "A or B" means "A or B or both." Throughout this document, the term "comprising" or "comprises" means "including, but not limited to" or "containing, but not limited to," and the like. The term "consisting essentially of" means "including, but not limited to, integers which do not materially affect the essential characteristics of the subject matter." The term "consisting of" means "including, but not limited to," such that the only integers which can be present are those specifically named. As used herein, unless otherwise clear from context, the term "about" means ±10% of the value of that which follows, for example, about 90% means in the range of 81-99%, unless otherwise stated.

[0099] Embodiments of the present application will now be described, by way of example only, with reference to the accompanying drawings. These embodiments are provided so that this application will be thorough and complete, and will fully convey the scope of the application to those skilled in the art. Other embodiments can be derived from the teachings of this application by analogy with the described embodiments, and the skilled person will be able to devise other embodiments without departing from the scope of the application.

[0100] The above description of disclosed embodiments is not intended to be exhaustive or to be unduly limited by the embodiments described. While specific embodiments of, and examples for, the application are described herein for illustrative purposes, various equivalent modifications are possible within the scope of the application, as those skilled in the relevant art will recognize. The teachings of the application provided herein can be applied to other systems, not only for the systems described above. The elements and acts of which the application, alone or in other combinations can be arranged, combined, substituted, and designed in various different configurations, all of which have been contemplated to fall within the scope of the present application. Each publication, patent, or patent application cited in this specification is incorporated by reference in its entirety for the purpose of describing and disclosing, for example, the designs and functions of the various elements described in such publication, patent, or patent application.

Claims

1. A crowd targeting method based on big data analysis, characterized in that: Comprise the following steps: Step S1: set the analysis time, in the analysis time according to the number of times the user accesses the shopping cart to determine whether to enter the product analysis mechanism, when entering the product analysis mechanism, the access interval of each type of product is counted; Step S2: access history database to obtain the conversion period reference of the user, analyze the interaction attenuation characteristics by using the access interval, and judge whether the conversion interest stage of the user is the interest cooling stage by combining the conversion period reference; In step S2, the access history database obtains the conversion period reference of the user, and the conversion period reference refers to the average time period experienced by the user from accessing the shopping cart to completing the purchase of the product in the past shopping behavior; The reciprocal of the conversion period reference is taken as the interest decay rate; After sorting the access intervals of the same type of product in time sequence, the change amplitude between adjacent access intervals is analyzed; The interval change amplitude is obtained by subtracting the previous access interval from the current access interval, and the access interval growth rate is obtained by dividing the interval change amplitude by the previous access interval; The average value of the access interval growth rate is taken as the interaction attenuation characteristics of each type of product; Step S3: when the user is in the interest cooling stage, the product retention time and product source information of each type of product are obtained, and the channel stickiness index of the user to the product source information is evaluated according to the product source information; In step S3, the historical conversion data corresponding to each source channel identifier is retrieved through the conversion statistical database, including the number of product purchases corresponding to different source channel identifiers; The number of product purchases corresponding to different source channel identifiers is accumulated and summed as the cumulative purchase times; The ratio of the number of product purchases corresponding to the source channel identifier to the cumulative purchase times is taken as the channel stickiness index of the product source information; Step S4: the scheduling priority score of each type of product is evaluated by combining the channel stickiness index and the product retention time, the types of products in the shopping cart are sorted based on the scheduling priority score, and the arrangement order of the products in the shopping cart is adjusted according to the sorting result; In step S4, in the product source information of the same type of product, the average value of the channel stickiness index is obtained as the average channel stickiness index of the same type of product; The channel stickiness coefficient and the retention time coefficient are obtained by standardizing the average channel stickiness index and the product retention time respectively; In step S4, the dispatch priority score of each type of commodity is evaluated by using the channel stickiness coefficient and the retention time coefficient: wherein, is the dispatch priority score, is the channel stickiness coefficient, is the retention time coefficient, is a preset time decay factor, is a natural constant; According to the descending order of the scheduling priority score of each type of product, the arrangement order of each type of product in the shopping cart is adjusted according to the sorting result.

2. The method according to claim 1, wherein: In step S1, a preset analysis time is set, and the number of times the user accesses the shopping cart is monitored in real time within the preset analysis time, and the ratio of the number of times the user accesses the shopping cart to the preset analysis time is taken as the shopping cart access frequency; If the shopping cart access frequency is greater than the preset access frequency threshold, it is judged to enter the product analysis mechanism; Otherwise, it is judged not to enter the product analysis mechanism.

3. The method according to claim 2, wherein: In step S1, when entering the commodity analysis mechanism, access events of various commodities are retrieved through a log database, and the timestamp of the access event is taken as the commodity access time; The commodity access times of the same type of commodity are sorted in time sequence and combined into an access time sequence; The access time sequence is analyzed, and the adjacent commodity access times are processed by difference to obtain the access interval.

4. The population targeting method based on big data analysis according to claim 1, characterized in that: In step S2, after the interaction attenuation feature is standardized by the Max-min standardization method, the category interest offset value is calculated by combining the interest attenuation rate; The number of commodity categories with a category interest offset value greater than 1 is counted as the total number of declining categories, and the ratio of the total number of declining categories to the total number of commodity categories in the shopping cart is taken as the cooling rate; If the cooling rate is greater than the preset cooling rate threshold, it is judged that the user's conversion interest stage is the interest cooling stage; Otherwise, it is judged that the user's conversion interest stage is the interest active stage.

5. The population targeting method based on big data analysis according to claim 1, characterized in that: In step S3, when the user is in the interest cooling stage, the retention time and the commodity source information of the commodities in the shopping cart are obtained through the log database; The commodity source information is the source channel identifier when the user adds the commodity to the shopping cart; The retention time of the same type of commodity is averaged to obtain the commodity retention time of the same type of commodity.

Images