Generation method and device of promotion strategy, storage medium and electronic equipment

Abstract

The invention provides a promotion strategy generation method and device, a storage medium and electronic equipment. The method can be applied to the field of financial science and technology. The method comprises the following steps: acquiring promotion behavior data of a plurality of customer managers, and determining a promotion to-do behavior set of a target customer manager according to the promotion behavior data; acquiring behavior data authorized by a plurality of clients, and determining a similar client set of a target client according to the behavior data, the target client being a client that has been reached by a target client manager; according to the promotion to-do behavior set and the similar customer set, performing preference matching on each promotion content in the promotion to-do behavior set and the similar customer set so as to determine at least one final promotion content from the promotion to-do behavior set, and obtaining a matching relationship between the final promotion content and each customer in the similar customer set; and generating a promotion strategy at least according to the final promotion content, the similar customer set and the matching relationship. The popularization efficiency and effect can be improved.

Description

Technical Field

[0001] This application relates to the field of marketing technology, and more specifically, to a method, apparatus, computer-readable storage medium, and electronic device for generating a marketing strategy. Background Technology

[0002] With the accelerating pace of digital transformation in the banking industry, account managers face unprecedented challenges and opportunities. On the one hand, customers' demand for personalized, high-value financial services is growing; on the other hand, banks offer a wide variety of products, information, and activities that are rapidly updated, making it crucial to accurately match customer needs with bank services. Traditional promotional strategies rely heavily on account managers' experience and intuition, but this manual decision-making approach falls short in the face of massive amounts of data, failing to capture the subtle differences in each customer's needs. Therefore, there is an urgent need for a promotional method that improves efficiency and effectiveness. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, computer-readable storage medium, and electronic device for generating promotional strategies, so as to at least solve the problem of low effectiveness and efficiency in the promotion of products, information, and activities in the prior art.

[0004] To achieve the above objectives, according to one aspect of this application, a method for generating a promotion strategy is provided, comprising: acquiring promotion behavior data of multiple account managers, and determining a set of promotional pending actions for a target account manager based on the promotion behavior data, the set of promotional pending actions including promotional content that the target account manager has not yet promoted but that has been promoted by similar account managers, the similar account managers being account managers whose promotional behavior data is similar to that of the target account manager to a first threshold; acquiring authorized behavior data of multiple customers, and determining a set of similar customers for a target customer based on the behavior data, the target customer being a customer already reached by the target account manager, the set of similar customers being a set of customers whose behavior data is similar to that of the target customer to a second threshold; performing preference matching on each promotional content in the set of promotional pending actions and the set of similar customers based on the set of promotional pending actions and the set of similar customers, to determine at least one final promotional content from the set of promotional pending actions, and obtaining a matching relationship between the final promotional content and each customer in the set of similar customers; and generating a promotion strategy based at least on the final promotional content, the set of similar customers, and the matching relationship.

[0005] Optionally, determining the set of promotional tasks for the target account manager based on the promotional behavior data includes: determining the set of similar account managers based on the promotional behavior data; determining the union of the promoted content of each similar account manager based on the promotional behavior data; and calculating the complement of the set of promoted content of the target account manager relative to the union to obtain the set of promotional tasks.

[0006] Optionally, the promotion behavior data includes promotion learning behavior, promotion triggering behavior, promotion completion behavior, and promotion tracking behavior. Based on the promotion behavior data, determining the set of similar account managers includes: constructing a vector for each account manager, where each vector element includes at least two of the promotion learning behavior, promotion triggering behavior, promotion completion behavior, and promotion tracking behavior; calculating the cosine similarity between the target account manager's vector and the vectors of all other account managers using a cosine similarity calculation formula, obtaining multiple first cosine similarities; and selecting the first n account managers corresponding to the first cosine similarities in descending order as the set of similar account managers, where n is an integer greater than 0.

[0007] Optionally, determining a set of similar customers for the target customer based on the behavioral data includes: determining behavioral preference data for each customer based on the behavioral data, wherein the behavioral preference data characterizes the degree of interest of the customer in each of the promotional contents; calculating the cosine similarity between the target customer and all other customers regarding the behavioral preference data of each of the promotional contents using a cosine similarity calculation formula to obtain a second cosine similarity; and selecting the first m customers corresponding to the second cosine similarities from all the second cosine similarities in descending order to form the set of similar customers, where m is an integer greater than 0.

[0008] Optionally, determining the behavioral preference data of each customer based on the behavioral data includes: initializing the preference score of each customer regarding the promotional content; when the behavioral data indicates that the customer has completed the promotional content, adding a first score to the preference score to obtain the customer's behavioral preference data regarding the promotional content; when the behavioral data indicates that the customer has not viewed the promotional content, adding a second score to the preference score to obtain the customer's behavioral preference data regarding the promotional content; when the behavioral data indicates that the customer has not completed the promotional content but has viewed the promotional content, normalizing the customer's browsing time using a standard score, converting the normalized time into a corresponding score to obtain a third score, and adding the third score to the preference score to obtain the customer's behavioral preference data regarding the promotional content, wherein the first score, the third score, and the second score decrease sequentially.

[0009] Optionally, based on the set of promotional tasks and the set of similar customers, preference matching is performed on each promotional content in the set of promotional tasks and the set of similar customers to determine at least one final promotional content from the set of promotional tasks. This includes: determining the behavioral preference data of each similar customer for each promotional content in the set of promotional tasks based on the behavioral preference data of each customer, to obtain initial behavioral preference data; and removing the promotional content corresponding to the initial behavioral preference data that is less than or equal to a third threshold to obtain the final promotional content.

[0010] Optionally, before generating a promotion strategy based at least on the final promotional content, the similar customer set, and the matching relationship, the method further includes: calculating the similarity between each of the promotional contents based at least on the attribute information of each of the promotional contents and the collected information of the customers interested in each of the promotional contents; determining the promotional contents with a similarity greater than a fourth threshold to the final promotional content as relevant promotional contents based on the similarity; calculating the matching relationship between the relevant promotional contents and each of the customers in the similar customer set to obtain a second relationship; the matching relationship between the final promotional content and each of the customers in the similar customer set is a first relationship; generating a promotion strategy based at least on the final promotional content, the similar customer set, and the matching relationship includes: sending the final promotional content, the similar customer set, the first relationship, and the second relationship to the terminal of the target account manager.

[0011] According to another aspect of this application, an apparatus for generating a promotion strategy is provided, comprising: a first acquisition unit, configured to acquire promotion behavior data of multiple account managers, and determine a set of promotion pending actions for a target account manager based on the promotion behavior data, the set of promotion pending actions including promotional content that the target account manager has not yet promoted but that has been promoted by similar account managers, the similar account managers being account managers whose promotion behavior data is similar to that of the target account manager to a first threshold; a second acquisition unit, configured to acquire authorized behavior data of multiple customers, and determine a set of similar customers for a target customer based on the behavior data, the target customer being a customer already reached by the target account manager, the set of similar customers being a set of customers whose behavior data is similar to that of the target customer to a second threshold; a matching unit, configured to perform preference matching on each promotional content in the set of promotion pending actions and the set of similar customers based on the set of promotion pending actions and the set of similar customers, to determine at least one final promotional content from the set of promotion pending actions, and to obtain a matching relationship between the final promotional content and each customer in the set of similar customers; and a generation unit, configured to generate a promotion strategy based at least on the final promotional content, the set of similar customers, and the matching relationship.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0013] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0014] By applying the technical solution of this application, firstly, by acquiring promotional behavior data from multiple account managers, data similarity analysis is used to determine the set of promotional tasks for the target account manager. This set includes promotional content that the target account manager has not yet promoted but that has been promoted by their similar account managers, thereby ensuring that the promotional content matches the account manager's promotional behavior preferences and improving the targeting and success rate of the promotion. Furthermore, by acquiring customer-authorized behavior data, a set of similar customers for the target customer is determined, enhancing the understanding of the target customer's personalized needs. After determining the set of promotional tasks and the set of similar customers, this application further uses preference matching to filter at least one final promotional content from the set of promotional tasks that matches each customer in the set of similar customers, and clarifies its matching relationship with each customer in the set of similar customers. This process not only improves the matching accuracy of the promotional content but also optimizes the efficiency of generating promotional strategies. Finally, the promotional strategies generated based on these analysis results are conducive to effectively reaching customers in the set of similar customers, improving customer response rate and satisfaction, and enhancing the promotional effect and resource utilization efficiency of the promotional content. Attached Figure Description

[0015] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for generating a promotion strategy according to an embodiment of this application is shown.

[0017] Figure 2 A flowchart illustrating a method for generating a promotion strategy according to an embodiment of this application is shown.

[0018] Figure 3 A structural block diagram of a device for generating a first promotion strategy according to an embodiment of this application is shown;

[0019] Figure 4 A structural block diagram of a generation apparatus for a second promotion strategy provided according to an embodiment of this application is shown.

[0020] The accompanying drawings include the following reference numerals:

[0021] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0022] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0024] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application 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 used interchangeably where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover 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.

[0025] As described in the background section, the effectiveness and efficiency of product, information, and activity promotion in the prior art are relatively poor. To solve this technical problem, embodiments of this application provide a method, apparatus, computer-readable storage medium, and electronic device for generating promotion strategies.

[0026] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0027] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of generating a promotion strategy according to an embodiment of this application. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include components that are larger than... Figure 1 The more or fewer components shown, or having the same Figure 1The different configurations shown.

[0028] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the promotion strategy generation method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, i.e., implementing the method described. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of such networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0029] This embodiment provides a method for generating a promotional strategy that runs on a mobile terminal, computer terminal, or similar computing device, and this method can be applied to the fintech field. It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowcharts, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] Figure 2 This is a flowchart illustrating a method for generating a promotion strategy according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0031] Step S201: Obtain promotion behavior data of multiple account managers, and determine the set of promotion pending actions of the target account manager based on the promotion behavior data. The set of promotion pending actions includes promotion content that the target account manager has not yet promoted but that similar account managers have promoted. The similar account managers are account managers whose promotion behavior data is more similar to that of the target account manager than a first threshold.

[0032] Specifically, the promotional behavior data refers to the recorded information of various promotional activities executed by the account manager during the interaction between the account manager and the customer. These promotional activities include, but are not limited to, products, information, and events. Specifically, the target account manager is one of multiple account managers.

[0033] Step S202: Obtain multiple customer-authorized behavioral data, and determine a set of similar customers to the target customer based on the behavioral data. The target customer is the customer that the target customer manager has reached, and the set of similar customers is the set of customers whose behavioral data is more similar to the target customer than a second threshold.

[0034] Optionally, the behavioral data refers to data related to customer behavior collected and used by the organization with the customer's explicit consent or authorization. This behavioral data includes, but is not limited to, the customer's transaction history, usage of promotional content, preference settings, and interaction records with account managers. Specifically, the similar customer set includes at least one similar customer of the target customer.

[0035] Step S203: Based on the set of promotional tasks and the set of similar customers, perform preference matching on each promotional content in the set of promotional tasks and the set of similar customers to determine at least one final promotional content from the set of promotional tasks and obtain the matching relationship between the final promotional content and each customer in the set of similar customers.

[0036] Specifically, deep preference matching is performed between the promotional content in these to-do sets and similar customer sets to determine which promotional content is most likely to generate interest and response from the target customer's similar customer group. If the similar customer set includes only one customer, the final promotional content can be only one or include multiple similar customers. If the similar customer set includes multiple similar customers, promotional content matching each similar customer is determined from the promotional to-do set as the final promotional content.

[0037] Step S204: Generate a promotion strategy based at least on the final promotion content, the set of similar customers, and the matching relationship.

[0038] Specifically, the promotion strategy includes at least one final promotional content and similar customers matching each final promotional content. The promotion strategy may also include personalized promotional messages for each similar customer.

[0039] This embodiment first obtains promotional behavior data from multiple account managers and uses data similarity analysis to determine the target account manager's promotional task set. This set includes promotional content that the target account manager has not yet promoted but that has been promoted by similar account managers, thus ensuring that the promotional content matches the account manager's promotional behavior preferences and improving the targeting and success rate of the promotion. Furthermore, by obtaining customer-authorized behavior data, a set of similar customers for the target customer is determined, enhancing the understanding of the target customer's personalized needs. After determining the promotional task set and the similar customer set, this application further uses preference matching to filter at least one final promotional content from the promotional task set that matches each customer in the similar customer set, and clarifies its matching relationship with each customer in the similar customer set. This process not only improves the matching accuracy of the promotional content but also optimizes the efficiency of generating the promotional strategy. Finally, the promotional strategy generated based on these analysis results is conducive to effectively reaching customers in the similar customer set, improving customer response rate and satisfaction, and enhancing the promotional effect and resource utilization efficiency of the promotional content.

[0040] Optionally, the promotional behavior data includes, but is not limited to, promotional records of promotional content, interaction data with customers, promotional effectiveness data, learning and training records, and customer feedback data.

[0041] For example, promotional records may include a history of account managers introducing and promoting different products to customers, records of bank information shared by account managers, and records of various activities invited by account managers to customers. Customer interaction data includes communication records between account managers and customers, such as call logs, email exchanges, and social media interactions. Promotional effectiveness data refers to the results of each promotional activity, such as customer conversion rate, sales volume, and customer satisfaction rating. Customer feedback data refers to customer reactions to the promotional activities, such as whether they are interested, whether they purchase, whether they participate in the activity, and whether they accept, reject, or inquire about details. Learning and training records include records of account managers researching and learning about products, information, and activities.

[0042] In some embodiments, determining the set of promotional tasks for a target account manager based on the promotional behavior data includes: determining a set of similar account managers based on the promotional behavior data; determining the union of the promoted content of each of the similar account managers based on the promotional behavior data; and calculating the complement of the set of promoted content of the target account manager relative to the union to obtain the set of promotional tasks. This embodiment, based on account manager behavior patterns and existing promotional history, intelligently identifies bank products, information, or activities that the target account manager has not yet covered but has the potential to promote, thereby helping account managers supplement and improve their promotional strategies and effectively enhance the comprehensiveness of promotions and customer satisfaction.

[0043] In other embodiments not shown, the set of similar account managers or the set of pending behaviors can also be dynamically adjusted according to specific business needs or changes in customer preferences to further optimize recommendation results and meet more complex and ever-changing promotion scenarios.

[0044] According to some alternative embodiments of this application, the promotion behavior data includes promotion learning behavior, promotion triggering behavior, promotion completion behavior, and promotion tracking behavior. Determining the set of similar account managers based on the promotion behavior data includes: constructing a vector for each account manager, where each vector element includes at least two of the promotion learning behavior, promotion triggering behavior, promotion completion behavior, and promotion tracking behavior; calculating the cosine similarity between the target account manager's vector and the vectors of all other account managers using a cosine similarity calculation formula, obtaining multiple first cosine similarities; and selecting the first n account managers corresponding to the first cosine similarities in descending order as the set of similar account managers, where n is an integer greater than 0. This technical solution quantifies the behavioral preferences of account managers to calculate the similarity between them, thereby identifying the group of account managers whose behavioral patterns are closest to those of the target account managers. The use of cosine similarity can accurately measure the degree of similarity between the behavioral vectors of account managers, ensuring that the selected set of account managers is highly consistent with the target account managers in terms of promotional behavior, thus providing strong data support for subsequent personalized recommendations. In this way, this application can achieve in-depth analysis of account manager promotional behavior, improve the accuracy of recommendations, and increase the success rate of promotional activities.

[0045] Furthermore, 'n', as an adjustable parameter, allows for adjustments to the size of the similar customer set based on actual needs, ensuring a high degree of relevance in recommended content. In addition, by dynamically updating behavioral preference data and adjusting the value of 'n', it is possible to respond promptly to changing market environments, continuously optimize recommendation results, and meet the personalized needs of different account managers and customer groups.

[0046] In other embodiments not shown, other similarity calculation methods or adjustments to the value of n can be used to adapt to specific needs in different scenarios and further optimize the recommendation results.

[0047] In some exemplary solutions, determining a set of similar customers for the target customer based on the behavioral data includes: determining behavioral preference data for each customer based on the behavioral data, wherein the behavioral preference data characterizes the degree of interest of the customer in each of the promotional contents; calculating the cosine similarity between the target customer and all other customers regarding the behavioral preference data of each of the promotional contents using a cosine similarity calculation formula to obtain a second cosine similarity; and selecting the first m customers corresponding to the second cosine similarities in descending order to form the set of similar customers, where m is an integer greater than 0. In this embodiment, by quantifying the behavioral preference data of the target customer and other customers regarding promotional content, and using the cosine similarity calculation formula, the similarity between the target customer and all customers in terms of promotional content can be accurately assessed, thereby obtaining a series of second cosine similarities. This method not only considers the degree of interest of individual customers in different content, but also discovers customers with similar behavioral patterns to the target customer through comparative analysis, and then constructs a set containing m highly similar customers. As a result, account managers can recommend products, information or activities to their target customers more effectively based on the behavioral preferences of this set of similar customers, thereby improving the accuracy and effectiveness of recommendations and promoting the improvement of promotional results.

[0048] Furthermore, 'm', as an adjustable parameter, allows for adjustments to the size of the similar customer set based on actual needs, ensuring a high degree of relevance in recommended content. In addition, by dynamically updating behavioral preference data and adjusting the value of 'm', it is possible to respond promptly to changing market environments, continuously optimize recommendation results, and meet the personalized needs of different account managers and customer groups.

[0049] In other embodiments not shown, other similarity calculation methods or adjustments to the value of m can be used to adapt to specific needs in different scenarios and further optimize the recommendation results.

[0050] Optionally, determining the behavioral preference data of each customer based on the behavioral data includes: initializing the preference score of each customer regarding the promotional content; when the behavioral data indicates that the customer has completed the promotional content, adding a first score to the preference score to obtain the customer's behavioral preference data regarding the promotional content; when the behavioral data indicates that the customer has not viewed the promotional content, adding a second score to the preference score to obtain the customer's behavioral preference data regarding the promotional content; when the behavioral data indicates that the customer has not completed the promotional content but has viewed the promotional content, normalizing the customer's browsing time using a standard score, converting the normalized time into a corresponding score to obtain a third score, and adding the third score to the preference score to obtain the customer's behavioral preference data regarding the promotional content, wherein the first score, the third score, and the second score decrease sequentially.

[0051] In the aforementioned embodiment, the process of determining each customer's behavioral preference data based on behavioral data employs a multi-level scoring mechanism. This mechanism initializes each customer's preference score for the promoted content. When behavioral data indicates that the customer has completed the promoted content, such as purchasing a specific financial product or participating in a bank activity, a first score is added to the preference score to reflect the customer's high interest in this type of promotional content. If the customer has not viewed the promoted content, a smaller second score is added to the preference score, reflecting that even without direct interaction, the customer may still have some potential interest in the promoted content. For customers who did not complete the promoted content but left traces during browsing, a standard Z-score is used to normalize the customer's browsing time, and the processed time is converted into a corresponding third score. This third score is then added to the preference score to quantify the customer's level of interest in the promoted content. The third score lies between the first and second scores, reflecting the importance assessment of customer behavior to the recommended content. This multi-layered scoring mechanism allows for the precise differentiation of different customer behavior patterns, more accurately capturing customers' true needs and preferences. This enables highly relevant bank products, information, or activities to be recommended in subsequent processes, enhancing customer experience and satisfaction. It also improves the efficiency and accuracy of account managers' promotional efforts. Furthermore, the introduction of this scoring mechanism makes the recommendation algorithm more flexible and personalized, adapting to the diverse needs of different customer groups. This optimizes the matching quality of banking financial services, strengthens the emotional connection between banks and customers, and promotes innovation and development in bank promotional strategies.

[0052] For example, the first score can be 1, the second score can be 0, and the third score can be any value between 0 and 1. Of course, in addition to the example described, the specific values ​​of the first score, the second score, and the third score can be flexibly set according to actual needs or design.

[0053] In other embodiments not shown, the scoring mechanism can be further optimized by adjusting the score weights or introducing more complex machine learning models to adapt to a wider range of customer behavior patterns and predict future customer demand trends.

[0054] According to some embodiments of this application, based on the set of promotional tasks and the set of similar customers, preference matching is performed on each promotional content in the set of promotional tasks and the set of similar customers to determine at least one final promotional content from the set of promotional tasks. This includes: determining the behavioral preference data of each similar customer for each promotional content in the set of promotional tasks based on the behavioral preference data of each customer, obtaining initial behavioral preference data; and removing the promotional content corresponding to the initial behavioral preference data that is less than or equal to a third threshold to obtain the final promotional content. In this embodiment, the behavioral preference data of each similar customer for each promotional content in the set of promotional tasks is determined based on the behavioral preference data of each customer, obtaining initial behavioral preference data. Then, the promotional content corresponding to the initial behavioral preference data that is less than or equal to a third threshold is removed to obtain the final promotional content. This enables accurate matching of customer preferences, ensuring that recommended products, information, and activities better meet the actual needs and preferences of target customers, thereby improving the success rate of promotion and customer satisfaction. By eliminating promotional content with low relevance, ineffective promotion can be avoided, the allocation of promotional resources can be optimized, and the overall promotional efficiency can be improved.

[0055] In other embodiments not shown, the matching and filtering logic of promotional content can be adjusted according to specific business scenarios, such as adjusting the threshold or using different similarity calculation methods, to adapt to different promotional strategies and customer needs.

[0056] Optionally, before generating a promotion strategy based at least on the final promotional content, the set of similar customers, and the matching relationship, the method further includes: calculating the similarity between each of the promotional contents based at least on the attribute information of each of the promotional contents and the collected information of the customers interested in each of the promotional contents; determining the promotional contents with a similarity greater than a fourth threshold to the final promotional content as relevant promotional content based on the similarity; and calculating the matching relationship between the relevant promotional content and each of the customers in the set of similar customers to obtain a second relationship. In the process of generating a promotion strategy, this application identifies the inherent connections and structural similarities between content, and then calculates the similarity between them, determining the promotional content with a similarity exceeding a fourth threshold to be relevant promotional content. Essentially, this introduces the concept of approximation on the basis of the original recommendation, enabling the promotion strategy to cover a wider range of potentially relevant products, information, or activities. This not only enriches the recommendation options for account managers but also provides customers with a more comprehensive service perspective, increasing the opportunity for customers to discover other potentially valuable products or services. The matching relationship between relevant promotional content and each customer in the similar customer set is calculated to form a second relationship. Through such matching, a coherent and rich recommendation sequence can be provided to customers. Each recommendation has a certain internal connection, which can guide customers to gradually explore service areas that they may be interested in, thereby improving customer experience and satisfaction.

[0057] Based on this, the matching relationship between the final promotional content and each customer in the similar customer set is a first relationship. A promotional strategy is generated based on at least the final promotional content, the similar customer set, and the matching relationship. This includes sending the final promotional content, the similar customer set, the first relationship, and the second relationship to the target account manager's terminal, so that the target account manager executes the promotion according to the promotional strategy. In this embodiment, information based on the final promotional content, the similar customer set, the first relationship, and the second relationship is sent to the target account manager's terminal, thereby achieving a more accurate and comprehensive promotional strategy generation. This strategy generation method not only considers the promotional content itself but also deeply analyzes the interaction between the promotional content and customers, which helps improve the targeting and effectiveness of recommendations, optimize account managers' promotional decisions, and enhance the connection between customers and bank products.

[0058] Each of the first threshold, the second threshold, the third threshold, and the fourth threshold in this application may be determined based on empirical values ​​or obtained through multiple experimental verifications.

[0059] It should be noted that the customer-related information collected in this application is information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, and necessary confidentiality measures have been taken. The information does not violate public order and good morals, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0060] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the promotion strategy generation method of this application will be described in detail below with reference to specific embodiments.

[0061] This embodiment relates to a specific method for generating a promotion strategy, including the following steps:

[0062] Step S1: Obtain promotional behavior data for each account manager. Specifically, browsing relevant product, information, and event information during daily work is considered pre-promotion learning behavior; initial communication between account managers and customers via SMS, phone, mobile banking, or QR code scanning is considered promotional outreach behavior; successful transactions for customers through WeChat, tablets, or mobile banking are considered successful promotional activities; and communication between account managers and already reached customers via SMS, phone, mobile banking, or QR code scanning is considered promotional follow-up behavior. All of the above-mentioned learning, outreach, completion, and follow-up data constitute account manager promotional behavior data.

[0063] Step S2: Based on the promotional behavior data of each account manager, determine the similar account managers for each account manager, and the similarity value between the target account manager and each similar account manager; the specific steps are as follows:

[0064] The set of promotion behaviors of the account manager in step S1 mainly includes promotion learning behavior, promotion reach behavior, promotion completion behavior, and promotion tracking behavior. The set of behaviors of each account manager consists of the above three behaviors forming a vector group beh{b1,b2,b3}.

[0065] Obtain the vector set BEH{B1,B2,B3,.....} of all account managers in the entire bank;

[0066] Based on the cosine similarity formula, the cosine similarity of the set of customer manager vectors is calculated and sorted to form a customer manager similarity map table with customer manager ID as the primary key. The key value represents the customer manager ID, and the value is a list that records the similarity between the customer manager and other customer managers, denoted as Bmap1.

[0067] Step S3: Based on the promotion learning behavior, promotion outreach behavior, promotion completion behavior, and promotion tracking behavior of each account manager's similar account managers, determine the promotion pending behaviors that the account manager may not have completed but that similar account managers have completed.

[0068] Filter Bmap1 obtained in step S2, retaining the values ​​of the 100 account managers most similar to each account manager, to obtain Bmap2. In Bmap2, each account manager has 100 account managers with similarity to them. For each account manager ID in Bmap2, obtain their behavior set B_id0, and obtain the 100 account managers B_id1-B_id101 that are similar to them. Take the union of B_id1-B_id101 and then take the complement of B_id0. Finally, the complement of B_id0 represents the promotional tasks that the account manager still needs to complete.

[0069] Step S4: Based on the similar promotional to-do behaviors of customer managers obtained in step S3, form a set of to-do behaviors a.

[0070] Step S5: Obtain authorized behavioral data for each customer, including:

[0071] Customer-authorized transaction behavior information, browsing behavior information, click behavior information, etc., for activities, products, and information. Among them, activity behavior information is denoted as act, product behavior information is denoted as prod, and browsing behavior information is denoted as brow.

[0072] The `act` function uses the account manager ID as the primary key and records the activity behavior IDs of each account manager as `act1`, `act2`, ...;

[0073] The `prod` key uses the account manager's ID as the primary key to record each account manager's product behavior ID, such as `prod1`, `prod2`, ...; `brow` records the account manager's browsing behavior information, with each account manager's browsing behavior ID denoted as `brow1`, `brow2`, ...;

[0074] The above customer and account manager data are normalized and encrypted to describe the customer's preference for each behavioral item;

[0075] For product behavior information, if the product is sold, 1 point is awarded; if the product is not sold and the customer has not viewed the product, 0 points are awarded. If the customer has a browsing record but the product is not sold, the browsing time data is normalized according to the Z-score method to make the data follow a normal distribution.

[0076] For activity behavior information, if the customer completes the activity, 1 point is awarded; if the customer does not participate and does not browse the activity, 0 points are awarded; if the customer participates in the activity but has browsing records, the customer's browsing time data is normalized.

[0077] For information behavior data, data normalization is performed based on the duration of customer browsing information using the Z-score method;

[0078] The data from the prod, act, and brow tables are linked together using the customer ID into a single wide table, forming a preference score table for each customer's different behaviors. Each row of data is {id, prod, act, brow}.

[0079] Step S7: Based on the behavioral preferences of the multiple similar customers, determine the potential behavioral preference set L of the target customer. The specific steps are as follows: calculate the cosine similarity of each pair of customer preference behavior table row data formed in step S6, and obtain the cosine similarity of each customer with other customers after sorting.

[0080] Step S8: Determine which customers purchase, browse, and participate in different banking financial services such as products, information, and activities; determine similar product data for each product, information, and activity, and determine the similarity of these similar products;

[0081] Product similarity is characterized by the similarity of the customer groups that purchase the products. First, the customer groups that hold each product are obtained. The union and intersection of the customer groups that hold the products are then used as the similarity between pairs of products (PRO_a∩PRO_b / PRO_a∪PRO_b).

[0082] Step S9: Obtain the similarity threshold.

[0083] Step S10: Obtain the set of pending behaviors a for each account manager, and finally form the set of pending behaviors A for account managers based on the calculated behaviors and behaviors in set a with a similarity greater than the similarity threshold.

[0084] This step matches the account manager's to-do activities with the customer groups the account manager is to reach, matching the account manager's to-do activities with the customer's preferred products, information, or activities. The account manager's to-do activities calculated in step S3 are then matched with the potential preferred behaviors of customer group L, ultimately determining the account manager's to-do behavior set A.

[0085] Step S11: Obtain the customers reached by each account manager and the customer groups whose similarity to each reached customer is greater than the similarity threshold to form a customer set C. Among them, the behavior set A is the set of key promotion behaviors that account managers need to focus on learning and tracking in the future, and the customer set C is the largest similar customer cluster C that account managers can promote.

[0086] This application analyzes customer transaction data, information browsing data, and activity participation to identify customer preferences and needs. Based on this data, the recommendation system can recommend the most relevant products, information, and activities to each customer, reducing resource waste and improving customer satisfaction because the recommendations better match the customer's actual needs. By providing products and services that meet customer needs, customers are more likely to continue using the bank's services, enhancing customer loyalty and reducing customer churn.

[0087] In traditional marketing processes, account managers typically spend a significant amount of time understanding products and customer needs. With an automated recommendation system, account managers can quickly access recommended content without manually sifting through large amounts of information. This saves time, improves efficiency, and allows account managers to focus on customer interaction, thereby enhancing service quality.

[0088] Each customer's transaction and behavioral data is unique, and recommendation systems can generate personalized recommendations based on this unique data. This provides customized services, enhances customer experience, and increases customer loyalty. Based on historical data and behavioral analysis, recommendation systems make recommended products, information, and activities more likely to be accepted by customers. This increases customer conversion rates and improves the return on investment for promotional activities. Through precise recommendations, banks can focus promotional resources on customers and products most likely to generate revenue. It also reduces ineffective promotion, optimizes budget usage, and improves overall promotional efficiency.

[0089] The system takes into account customers' online and offline reach, providing comprehensive promotional strategies. It covers more customer touchpoints, enhancing the comprehensiveness and effectiveness of promotions.

[0090] In summary, the advantages of this invention include precise recommendations, improved efficiency for account managers, personalized experience, increased promotion success rate, optimized resource allocation, integrated online and offline outreach, data-driven decision-making, and improved customer retention. These advantages work together to significantly enhance the bank's promotional effectiveness and customer satisfaction.

[0091] Furthermore, this application dynamically generates recommended content through data-driven methods (such as customer behavior data and similarity analysis), enabling more flexible adaptation to changes in customer needs and more accurate recommendation results. This application not only utilizes content features but also combines customer behavior data and related customer behavior data, allowing for a more comprehensive analysis of customer needs and more personalized recommendation results. This application incorporates the concept of collaborative filtering (recommending based on related customer behavior data) but further optimizes the recommendation logic. For example, by analyzing account manager promotional behavior data and multi-dimensional behavior data of target customers, it can more comprehensively cover customer needs.

[0092] This application also provides an apparatus for generating a promotion strategy. It should be noted that this apparatus can be used to execute the method for generating a promotion strategy provided in this application. This apparatus is used to implement the embodiments and preferred embodiments described herein, and will not be repeated hereafter. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0093] The following describes the apparatus for generating promotion strategies provided in the embodiments of this application.

[0094] Figure 3 This is a structural block diagram of an apparatus for generating a promotion strategy according to an embodiment of this application. Figure 3 As shown, the device includes:

[0095] The first acquisition unit 10 is used to acquire promotion behavior data of multiple account managers and determine the set of promotion pending behaviors of the target account manager based on the promotion behavior data. The set of promotion pending behaviors includes promotion content that the target account manager has not yet promoted but that similar account managers have promoted. The similar account managers are account managers whose similarity to the promotion behavior data of the target account manager is greater than a first threshold.

[0096] The second acquisition unit 11 is used to acquire multiple customer-authorized behavioral data and determine a set of similar customers to the target customer based on the behavioral data. The target customer is the customer that the target customer manager has reached, and the set of similar customers is a set of customers whose behavioral data is more similar to the target customer than a second threshold.

[0097] The matching unit 12 is configured to perform preference matching between each of the promotional content in the promotional to-do set and the similar customer set based on the promotional to-do set and the similar customer set, so as to determine at least one final promotional content from the promotional to-do set and obtain the matching relationship between the final promotional content and each of the customers in the similar customer set.

[0098] The generation unit 13 is used to generate a promotion strategy based at least on the final promotion content, the set of similar customers, and the matching relationship.

[0099] Optionally, the first acquisition unit includes:

[0100] The first determining module is used to determine the set of similar account managers based on the promotion behavior data;

[0101] The second determining module is used to determine the union of the promoted content of each of the similar account managers based on the promotion behavior data;

[0102] The first calculation module is used to calculate the complement of the set of promoted content of the target account manager relative to the union of the set of content to be promoted, so as to obtain the set of promotion pending actions.

[0103] Optionally, the promotion behavior data includes promotion learning behavior, promotion triggering behavior, promotion completion behavior, and promotion tracking behavior, and the first determining module includes:

[0104] A construction submodule is used to construct vectors for each of the aforementioned account managers, wherein the elements of the vectors include at least two of the following: the promotion learning behavior, the promotion triggering behavior, the promotion completion behavior, and the promotion tracking behavior.

[0105] The calculation submodule is used to calculate the cosine similarity between the vector of the target account manager and the vectors of all other account managers using the cosine similarity calculation formula, and obtain multiple first cosine similarities.

[0106] The selection submodule is used to select the first n customer managers corresponding to the first cosine similarity from all the first cosine similarities in descending order, where n is an integer greater than 0.

[0107] Optionally, the second acquisition unit includes:

[0108] The third determining module is used to determine the behavioral preference data of each customer based on the behavioral data, wherein the behavioral preference data characterizes the degree of interest of the customer in each of the promotional contents;

[0109] The second calculation module is used to calculate the cosine similarity between the target customer and all other customers regarding the behavioral preference data of each promotional content using the cosine similarity calculation formula, and obtain the second cosine similarity.

[0110] The selection module is used to select the first m customers corresponding to the second cosine similarity from all the second cosine similarities in descending order to form the similar customer set, where m is an integer greater than 0.

[0111] Optionally, the third determining module includes:

[0112] An initialization submodule is used to initialize the preference scores of each customer regarding the promotional content;

[0113] The first addition submodule is used to add a first score to the preference score when the behavioral data indicates that the customer has completed the promotional content, so as to obtain the customer's behavioral preference data regarding the promotional content;

[0114] The second submodule is used to add a second score to the preference score when the behavioral data indicates that the customer has not viewed the promotional content, so as to obtain the customer's behavioral preference data regarding the promotional content.

[0115] The normalization submodule is used to normalize the customer's browsing time using a standard score when the behavioral data indicates that the customer has not completed the promotional content but has browsed the promotional content. The normalized time is then converted into a corresponding score to obtain a third score. The third score is added to the preference score to obtain the customer's behavioral preference data regarding the promotional content. The first score, the third score, and the second score decrease sequentially.

[0116] Optionally, the matching unit includes:

[0117] The fourth determining module is used to determine the behavioral preference data of each similar customer for each of the promotional contents in the set of promotional pending behaviors based on the behavioral preference data of each of the customers, so as to obtain the initial behavioral preference data;

[0118] The removal module is used to remove the promotional content corresponding to the initial behavioral preference data that is less than or equal to a third threshold, so as to obtain the final promotional content.

[0119] Optionally, the apparatus further includes: a first calculation unit, configured to calculate the similarity between each of the promotional contents based at least on the attribute information of each of the promotional contents and the collected information of the customers interested in each of the promotional contents before generating a promotional strategy based at least on the final promotional content, the similar customer set, and the matching relationship; a determination unit, configured to determine the promotional contents with a similarity greater than a fourth threshold as relevant promotional contents based on the similarity; and a second calculation unit, configured to calculate the matching relationship between the relevant promotional contents and each of the customers in the similar customer set to obtain a second relationship;

[0120] The matching relationship between the final promotional content and each customer in the similar customer set is a first relationship. The generation unit includes a generation module, which is used to send the final promotional content, the similar customer set, the first relationship and the second relationship to the terminal of the target customer manager.

[0121] like Figure 4 As shown, the promotion strategy generation device includes a processor 102 and a memory 104. The first acquisition unit, the second acquisition unit, the matching unit, and the generation unit are all stored as program units in the memory 104. The processor 102 executes the program units stored in the memory 104 to realize the corresponding functions.

[0122] For example, all the modules are located in the same processor; or, the modules are located in different processors in any combination.

[0123] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters can at least address the problem of low effectiveness and efficiency in product, information, and event promotion in existing technologies.

[0124] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0125] This application provides a computer-readable storage medium including a stored program, wherein the program controls the device where the computer-readable storage medium is located to execute a method for generating the promotion strategy when the program is running.

[0126] This application provides a processor for running a program, wherein the program executes the method for generating the promotion strategy during runtime.

[0127] This application provides an apparatus including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it implements at least the steps of a method for generating a promotion strategy. The apparatus described herein may be a server, PC, PAD, mobile phone, etc.

[0128] This application also provides a computer program product that, when executed on a data processing device, is adapted to perform a program that initializes a generation method step having at least a promotion strategy.

[0129] Obviously, those skilled in the art will understand that the modules or steps of this application can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0130] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0132] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0133] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0134] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0135] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0136] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0137] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0139] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for generating a promotion strategy, characterized by, The method comprises the following steps: obtaining promotion behavior data of a plurality of account managers, and determining a promotion to-be-done behavior set of a target account manager according to the promotion behavior data, the promotion to-be-done behavior set comprising promotion content that has not been promoted by the target account manager but has been promoted by a similar account manager, the similar account manager being an account manager whose similarity to the target account manager is greater than a first threshold value; obtaining behavior data of a plurality of authorized customers, and determining a similar customer set of a target customer according to the behavior data, the target customer being a customer reached by the target account manager, and the similar customer set being a set of customers whose similarity to the target customer is greater than a second threshold value; performing preference matching between each of the promotion content in the promotion to-be-done behavior set and the similar customer set according to the promotion to-be-done behavior set and the similar customer set, to determine at least one final promotion content from the promotion to-be-done behavior set, and obtain a matching relationship between the final promotion content and each of the customers in the similar customer set; generating a promotion strategy according to at least the final promotion content, the similar customer set and the matching relationship.

2. The method of claim 1, wherein, According to the promotion behavior data, the method comprises the following steps: determining a set of similar account managers according to the promotion behavior data; determining a union set of promoted content of each of the similar account managers according to the promotion behavior data; calculating a complement set of the promoted content set of the target account manager with respect to the union set to obtain the promotion to-be-done behavior set.

3. The method of claim 2, wherein, The promotion behavior data comprises promotion learning behavior, promotion triggering behavior, promotion completion behavior and promotion tracking behavior, and the method comprises the following steps according to the promotion behavior data to determine the set of similar account managers: constructing a vector of each of the account managers, the elements of the vector comprising at least two of the promotion learning behavior, the promotion triggering behavior, the promotion completion behavior and the promotion tracking behavior; calculating the cosine similarity between the vector of the target account manager and the vectors of all other account managers using a cosine similarity calculation formula to obtain a plurality of first cosine similarities; selecting the account managers corresponding to the first n cosine similarities from all the first cosine similarities in descending order to obtain the set of similar account managers, n being an integer greater than 0.

4. The method of claim 1, wherein, According to the behavior data, the method comprises the following steps to determine a similar customer set of a target customer: determining behavior preference data of each of the customers according to the behavior data, the behavior preference data representing the interest degree of the customer for each of the promotion content; calculating the cosine similarity between the behavior preference data of the target customer and the behavior preference data of all other customers with respect to each of the promotion content using a cosine similarity calculation formula to obtain second cosine similarities; selecting the customers corresponding to the second m cosine similarities from all the second cosine similarities in descending order to obtain the similar customer set, m being an integer greater than 0.

5. The method of claim 4, wherein, According to the behavior data, behavior preference data of each of the customers is determined, including: Initializing a preference score value of each of the customers on the promoted content; In a case where the behavior data represents that the customer completes the promoted content, a first score value is added to the preference score value to obtain the behavior preference data of the customer on the promoted content; In a case where the behavior data represents that the customer does not browse the promoted content, a second score value is added to the preference score value to obtain the behavior preference data of the customer on the promoted content; In a case where the behavior data represents that the customer does not complete the promoted content and browses the promoted content, a standard score is used to normalize the browsing time of the customer, and the normalized time is converted into a corresponding score value to obtain a third score value, and the third score value is added to the preference score value to obtain the behavior preference data of the customer on the promoted content, wherein the first score value, the third score value and the second score value decrease in turn.

6. The method of claim 4, wherein, According to the promoted to-be-completed behavior set and the similar customer set, each of the promoted content in the promoted to-be-completed behavior set is matched with the similar customer set in preference to determine at least one final promoted content from the promoted to-be-completed behavior set, including: According to the behavior preference data of each of the customers, the behavior preference data of each of the similar customers on each of the promoted content in the promoted to-be-completed behavior set is determined to obtain initial behavior preference data; The promoted content corresponding to the initial behavior preference data less than or equal to a third threshold value is removed to obtain the final promoted content.

7. The method of claim 1, wherein, Before generating a promotion strategy according to at least the final promoted content, the similar customer set and the matching relationship, the method further comprises: calculating the similarity between each of the promoted content according to at least the attribute information of each of the promoted content and the collection information of the customer interested in each of the promoted content; determining the promoted content with a similarity greater than a fourth threshold value to the final promoted content as a related promoted content according to the similarity; and calculating a matching relationship between the related promoted content and each of the customers in the similar customer set to obtain a second relationship; The matching relationship between the final promoted content and each of the customers in the similar customer set is a first relationship, and the generation of the promotion strategy according to at least the final promoted content, the similar customer set and the matching relationship comprises: sending the final promoted content, the similar customer set, the first relationship and the second relationship to a terminal of the target customer manager.

8. A promotion policy generation apparatus characterized by comprising: including: The first obtaining unit is configured to obtain promotion behavior data of a plurality of account managers, and determine a promotion to-be-done behavior set of a target account manager according to the promotion behavior data, the promotion to-be-done behavior set including promotion content that has not been promoted by the target account manager but has been promoted by a similar account manager, the similar account manager being an account manager whose similarity to the target account manager is greater than a first threshold value. The second obtaining unit is configured to obtain behavior data of a plurality of customers authorized, and determine a similar customer set of a target customer according to the behavior data, the target customer being a customer reached by the target account manager, the similar customer set being a set of customers whose similarity to the target customer is greater than a second threshold value. The matching unit is configured to perform preference matching between each of the promotion content in the promotion to-be-done behavior set and the similar customer set according to the promotion to-be-done behavior set and the similar customer set, to determine at least one final promotion content from the promotion to-be-done behavior set, and obtain a matching relationship between the final promotion content and each of the customers in the similar customer set. The generating unit is configured to generate a promotion strategy according to at least the final promotion content, the similar customer set, and the matching relationship.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program controls a device in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7 when the program is executed.

10. An electronic device, comprising: The computer-readable storage medium includes a stored program, wherein the program controls a device in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7 when the program is executed. The computer-readable storage medium includes a stored program, wherein the program controls a device in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7 when the program is executed. The computer-readable storage medium includes a stored program, wherein the program controls a device in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7 when the program is executed. The computer-readable storage medium includes a stored program, wherein the program controls a device in which the computer-readable storage medium is located to perform the method of any one of claims 1 to 7 when the program is executed.

Images