Customer marketing strategy recommendation method and system based on artificial intelligence, and medium

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a customer marketing strategy recommendation method and system based on artificial intelligence and a medium, and the method comprises the steps: obtaining a customer data set, calculating customer correlation factors between customers in the customer data set, carrying out the missing item supplementation of the customer data set according to the customer correlation factors, and obtaining a customer marketing strategy recommendation result; obtaining a target data set; performing customer project score prediction on the target data set to obtain a project prediction score; constructing a customer interest matrix according to the project prediction score, and performing customer classification according to the customer interest matrix to obtain a customer category set; calculating a project association score between the clients according to the project prediction score, and calculating a path association score according to the target data set; and calculating a recommendation list through the project association score and the path association score, and generating a customer marketing strategy based on the recommendation list. According to the invention, the accuracy of customer marketing recommendation can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based customer marketing strategy recommendation method, system and medium. Background Art

[0002] With the rapid development of the new generation of information technology, artificial intelligence (AI) is being used more and more widely in various fields, especially in customer lifecycle management and supply chain marketing.

[0003] By analyzing customer behavior data at different stages of the life cycle, artificial intelligence can provide targeted marketing and service strategies. For example, in the customer acquisition stage, artificial intelligence can help companies identify potential customers and improve the accuracy and conversion rate of marketing activities; in the customer conversion stage, artificial intelligence can provide personalized recommendations and services to enhance customer experience; in the customer retention stage, artificial intelligence can analyze customer satisfaction data, provide improvement suggestions, and reduce customer churn. Therefore, how to use artificial intelligence to improve the accuracy of customer marketing strategy recommendations has become an urgent problem to be solved.

[0004] This problem is also prominent in supply chain marketing. The supply chain involves multiple links, including suppliers, manufacturers, distributors, retailers, and end customers, and each link may generate a large amount of customer data. However, the existing marketing recommendation methods mainly rely on mining historical data to find similar users and recommend similar items to target users based on user preferences. Although this method improves the accuracy of recommendations to a certain extent, there are still many uncertainties in actual operations. For example, the integrity and quality of data are key factors affecting the recommendation effect. If the missing data cannot be properly and reasonably filled, the sample data will eventually become distorted, thereby affecting the accuracy of the recommendation. At the same time, due to the diversity and complexity of the customer base, a single recommendation algorithm may not meet the needs of all customers, resulting in insufficient accuracy and relevance of the recommendation results.

[0005] At the same time, since customers in the supply chain include not only end consumers but also participants in various intermediate links, their needs and preferences vary greatly. For example, retailers may pay more attention to inventory management, logistics distribution efficiency and cost control, while manufacturers may pay more attention to the stability and quality of raw material supply. Therefore, it is difficult to meet the diverse needs of different customer groups in the supply chain by relying solely on recommendation methods based on historical data mining and similarity matching, which in turn leads to poor accuracy in customer marketing recommendations.

[0006] Therefore, how to improve the accuracy of customer marketing recommendations becomes an urgent problem to be solved. Summary of the invention

[0007] The present invention provides a customer marketing strategy recommendation method, system and medium based on artificial intelligence, the main purpose of which is to solve the problem of poor accuracy of customer marketing recommendations.

[0008] To achieve the above purpose, the present invention provides a customer marketing strategy recommendation method based on artificial intelligence, comprising: Acquire a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; Predicting customer project scores for the target data set to obtain project prediction scores; Constructing a customer interest matrix according to the project prediction scores, and classifying customers in the customer data set according to the customer interest matrix to obtain a customer category set; Calculating the project association scores between customers in the customer category set according to the project prediction scores, and calculating the path association scores according to the target data set; A recommendation list is calculated by using the item association score and the path association score, and a customer marketing strategy is generated based on the recommendation list.

[0009] Optionally, calculating the customer correlation factor between each customer in the customer data set includes: Calculating item data for each customer in the customer data set; Counting the total number of identical projects among the customers according to the project data; Calculating the customer correlation factor between the customers according to the total number of the same items; The customer correlation factor between the customers is calculated using the following formula: in, represents the customer-related factor, Represents the preset weight coefficient, Indicates the total number of identical items.

[0010] Optionally, supplementing the missing items of the customer dataset according to the customer-related factors to obtain a target dataset includes: Determine a related customer set for each customer according to the customer related factors, calculate user similarity of the related customer set, and calculate a similar customer set according to the user similarity; Find the missing items of the customer according to the similar customer set and calculate the item score corresponding to the missing item; Calculate the missing item data corresponding to the missing item according to the item score; The project data corresponding to the missing items are calculated using the following formula: in, Indicates missing items The corresponding project data, Indicates the customer The corresponding mean score of the rated items, Indicates the customer The corresponding set of similar customers, Indicates the customer The corresponding similar customers are concentrated in Similar customers for missing items The project ratings, Indicates The average rating of the rated items corresponding to similar customers, Indicates the customer With The user similarity between similar customers, Indicates the customer With Customer correlation factors between similar customers; The missing item data are used to supplement the missing items to obtain the target data set.

[0011] Optionally, performing customer project score prediction on the target data set to obtain project prediction scores includes: Extracting the project rating of each customer from the target data set, and calculating the customer rating similarity based on the project rating; Selecting customers with similar ratings based on the customer rating similarity; Calculate the predicted project score for each customer based on customers with similar scores; The project prediction score is calculated using the following formula: in, Indicates Clients on projects The project prediction score, Indicates The average rating of the rated items by customers. Indicates The set of customers with similar ratings to the customer. represents the set of customers who have rated the item, Indicates Customers and The similarity of customer ratings between customers, Indicates Clients on projects The project ratings, Indicates The mean item rating of the rated items by customers.

[0012] Optionally, constructing a customer interest matrix according to the project prediction scores includes: Calculate the time decay coefficient corresponding to the predicted score of the project; Calculate the project interest according to the time decay coefficient and the project prediction score; A customer interest matrix is ​​constructed based on the project interest levels.

[0013] Optionally, classifying the customers in the customer data set according to the customer interest matrix to obtain a customer category set includes: Performing principal component dimensionality reduction on the customer interest matrix to obtain a dimensionality reduction matrix; Pre-clustering the dimension reduction matrix to obtain pre-clustering clusters, and determining the number of cluster centers according to the pre-clustering clusters; The customers in the customer data set are clustered according to the number of cluster centers to obtain a customer category set.

[0014] Optionally, calculating the project association scores between customers in the customer category set according to the project prediction scores includes: Calculate the difference in project scores between customers in each customer category set according to the project prediction scores; Calculating the item difference entropy between the customers of the category according to the item score differences; The project difference entropy is calculated using the following formula: in, represents the item difference entropy, Expressing the The difference in project scores for each project, represents the frequency of occurrence of item score differences, Indicates the total number of items corresponding to the difference in item scores; The item differences are used to determine item association scores between the categories of customers.

[0015] Optionally, the calculating the recommendation list by using the item association score and the path association score includes: Determine project-associated customers according to the project-associated scores, and extract a list of associated projects from the associated users; Determine path-associated customers according to the path-associated scores, extract path categories of the path-associated customers and convert them into feature vectors; Calculate the path similarity according to the feature vector, and calculate the path item list according to the path similarity; A recommendation list is generated according to the associated item list and the path item list.

[0016] In order to solve the above problems, the present invention also provides a customer marketing strategy recommendation system based on artificial intelligence, the system comprising: A missing item supplementation module is used to obtain a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; A rating prediction module is used to predict customer project ratings for the target data set to obtain project prediction ratings; A customer classification module, used to construct a customer interest matrix according to the project prediction score, and classify the customers in the customer data set according to the customer interest matrix to obtain a customer category set; A correlation score calculation module, used to calculate the project correlation scores between customers in the customer category set according to the project prediction scores, and calculate the path correlation scores according to the target data set; The customer marketing strategy generation module is used to calculate a recommendation list through the item association score and the path association score, and generate a customer marketing strategy based on the recommendation list.

[0017] In order to solve the above problems, the present invention also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the customer marketing strategy recommendation method based on artificial intelligence as described above is implemented.

[0018] The embodiment of the present invention calculates the customer correlation factors between customers in the customer data set, supplements the missing items in the customer data set, and can supplement the project rating data with insufficient information to obtain a more comprehensive and accurate target data set; predicts the customer project ratings of the target data set, and can predict the subsequent rating trends to obtain project prediction ratings; constructs a customer interest matrix, and classifies customers according to the customer interest matrix, and can classify customers with similar interests into the same customer category set; then calculates the project association ratings between customers in the customer category set according to the project prediction ratings, and calculates the path association ratings, project associations, and project transformation associations to analyze changes in customer interests, which is conducive to improving the accuracy of the subsequent recommendation list calculated by the project association ratings and path association ratings, and generating customer marketing strategies with higher accuracy and relevance based on the recommendation list. Therefore, the customer marketing strategy recommendation method, system, and medium based on artificial intelligence proposed by the present invention can solve the problem of poor accuracy of customer marketing recommendations. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1A flowchart of a customer marketing strategy recommendation method based on artificial intelligence provided by an embodiment of the present invention; Figure 2 A schematic diagram of a process for predicting customer project ratings for a target data set provided by an embodiment of the present invention; Figure 3 A schematic diagram of a process for constructing a customer interest matrix based on project prediction scores provided by an embodiment of the present invention; Figure 4 A functional module diagram of a customer marketing strategy recommendation system based on artificial intelligence provided by an embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0020] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0021] The embodiment of the present application provides a method for recommending customer marketing strategies based on artificial intelligence. The execution subject of the method for recommending customer marketing strategies based on artificial intelligence includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for recommending customer marketing strategies based on artificial intelligence can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms.

[0022] Reference Figure 1 FIG. 1 is a flow chart of a method for recommending customer marketing strategies based on artificial intelligence according to an embodiment of the present invention. In this embodiment, the method for recommending customer marketing strategies based on artificial intelligence includes: S1. Obtain a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set.

[0023] In the enterprise of the embodiment of the present invention, the customer data set is the multi-channel data of the target customers sorted by the enterprise, which can be project data such as customer consumption of enterprise products and services, marketing data, web browsing and other different projects' ratings, but there may be insufficient category information of the customer for a certain project, resulting in a low matching degree of marketing recommendations. Therefore, it is necessary to supplement the missing values ​​of the data in the customer data set to obtain a more comprehensive and complete target data set.

[0024] In detail, the calculating of the customer correlation factor between each customer in the customer data set includes: Calculating item data for each customer in the customer data set; Counting the total number of identical projects among the customers according to the project data; A customer correlation factor between the customers is calculated based on the total number of the same items.

[0025] In an embodiment of the present invention, project data refers to the number of times each customer in the customer data set pays attention to each project, wherein the data categories existing in the customer data set can be used as customer projects, for example, customers, web pages browsed each time, information projects, projects in which customers and enterprises have related exchanges, and basic information about customers, etc., and then data with the same projects among different customers are counted to obtain the total number of the same projects.

[0026] Specifically, the customer correlation factor between the customers is calculated using the following formula: in, represents the customer-related factor, Represents the preset weight coefficient, Indicates the total number of identical items.

[0027] In the embodiment of the present invention, the weight coefficient is related to the total number of identical items. The larger the total number of identical items is, the larger the corresponding weight coefficient is. Therefore, the correlation between customers can be analyzed through customer correlation factors.

[0028] Furthermore, the step of supplementing the missing items of the customer dataset according to the customer-related factors to obtain the target dataset includes: Determine a related customer set for each customer according to the customer related factors, calculate user similarity of the related customer set, and calculate a similar customer set according to the user similarity; Find the missing items of the customer according to the similar customer set and calculate the item score corresponding to the missing item; Calculate the missing item data corresponding to the missing item according to the item score; The missing item data are used to supplement the missing items to obtain the target data set.

[0029] In an embodiment of the present invention, customers whose customer correlation factors are greater than a preset correlation factor threshold are selected as related customers of each customer, and a related customer set of the customer is obtained. The similarity between the customers in the related customer set and the customer is calculated to obtain user similarity, wherein the feature similarity can be calculated based on the feature vector of the customer's basic information such as gender, age, occupation, etc. to obtain user similarity.

[0030] Furthermore, relevant customers with greater user similarity are selected to obtain a similar customer set, the differences between the customer data and the customer data in the similar customer set are counted, the customer data missing from the customer is obtained, the customer's missing items are obtained, and then the frequency of occurrence of missing items in the customer data of similar customers is calculated to obtain the item frequency corresponding to the similar customer set, and the frequency corresponding to each item in the customer's customer data is calculated to obtain the item frequency corresponding to the customer.

[0031] Specifically, the project data corresponding to the missing items are calculated using the following formula: in, Indicates missing items The corresponding project data, Indicates the customer The corresponding mean score of the rated items, Indicates the customer The corresponding set of similar customers, Indicates the customer The corresponding similar customers are concentrated in Similar customers for missing items The project ratings, Indicates The average rating of the rated items corresponding to similar customers, Indicates the customer With The user similarity between similar customers, Indicates the customer With Customer correlation factors between similar customers.

[0032] In the embodiment of the present invention, the project data corresponding to the missing items are added to the customer data set of each customer, thereby supplementing the project scoring data with insufficient information in the customer data set to obtain a more comprehensive and accurate target data set.

[0033] S2. Predict customer project scores for the target data set to obtain project prediction scores.

[0034] In the embodiment of the present invention, the customer rating is to predict the customer's project rating based on the customer's previous historical rating of the project, wherein the customer project rating prediction is to predict the rating of the project experience, demand satisfaction and overall performance of the project, and is a quantitative evaluation of a certain project (such as a product, service, activity, etc.). This rating is usually presented in the form of numbers or grades, such as 1 to 5 stars, 1 to 10 points, etc.

[0035] In the embodiment of the present invention, refer to Figure 2 As shown, the step of predicting the customer project scores of the target data set to obtain the project prediction scores includes: S21, extracting the project score of each customer from the target data set, and calculating the customer score similarity based on the project score; S22, selecting customers with similar ratings according to the customer rating similarity; S23, calculating the predicted project score of each customer based on the customers with similar scores.

[0036] Specifically, the score similarity is calculated using the following formula: in, Indicates Customers and The similarity of customer ratings between customers, Indicates Clients on projects The project ratings, Indicates Clients on projects 's project rating.

[0037] Furthermore, customers with similar scores corresponding to a preset number of customers are selected according to the size of the score similarity, and then the project predicted scores of each customer for different projects are calculated based on the project scores of the customers with similar scores.

[0038] Specifically, the project prediction score is calculated using the following formula: in, Indicates Clients on projects The project prediction score, Indicates The average item rating of the rated items by customers, Indicates The set of customers with similar ratings to the customer. represents the set of customers who have rated the item, Indicates Customers and The similarity of customer ratings between customers, Indicates Clients on projects The project ratings, Indicates The mean item rating of the rated items by customers.

[0039] In the embodiment of the present invention, by predicting the customer project ratings through the target data set, subsequent rating trends can be predicted based on the customer's historical ratings, thereby improving the accuracy of customer project recommendations.

[0040] S3. Construct a customer interest matrix according to the project prediction scores, and classify the customers in the customer data set according to the customer interest matrix to obtain a customer category set.

[0041] In the embodiment of the present invention, the customer interest matrix is ​​a matrix constructed by the customer's interest in each project. The customer interest matrix uses a two-dimensional table structure to show the interest of different customers in different projects, so as to more intuitively analyze the degree of interest of customers in different projects.

[0042] Specifically, see Figure 3 As shown, the customer interest matrix is ​​constructed according to the project prediction score, including: S31, calculating the time decay coefficient corresponding to the project prediction score; S31, calculating the project interest level according to the time decay coefficient and the project prediction score; S31. Construct a customer interest matrix according to the project interest.

[0043] In the embodiment of the present invention, the time decay coefficient is the time interval for customers to rate items. The time decay coefficient is used to calculate the impact of changes in customer behavior and interests over time. For example, the longer the time interval between ratings, the less interest a customer has. Specifically, the time when a customer rates each item and the current time can be obtained to calculate the time decay coefficient.

[0044] Specifically, the time attenuation coefficient is calculated using the following formula: in, Indicates the customer About Project The time decay coefficient, represents a natural constant, Represents the preset attenuation parameter, Indicates the customer About Project The scoring time, Indicates the current time. Indicates the customer Minimum scoring time for conducting the project, Indicates the customer The maximum scoring time for the project.

[0045] Furthermore, the time decay coefficient is multiplied by the corresponding project prediction score to obtain the project interest of each project, and the customer is used as the vertical coordinate and each project is used as the horizontal coordinate. Then, the project interest of each project can be used as a matrix element to construct a customer interest matrix.

[0046] In the embodiment of the present invention, the classifying the customers in the customer data set according to the customer interest matrix to obtain a customer category set includes: Performing principal component dimensionality reduction on the customer interest matrix to obtain a dimensionality reduction matrix; Pre-clustering the dimension reduction matrix to obtain pre-clustering clusters, and determining the number of cluster centers according to the pre-clustering clusters; The customers in the customer data set are clustered according to the number of cluster centers to obtain a customer category set.

[0047] In detail, principal component dimensionality reduction is to reduce the dimension of the customer interest matrix by calculating the eigenvalues ​​and corresponding eigenvectors of the covariance matrix constructed by the mean of each row in the customer interest matrix, sorting the eigenvectors from top to bottom according to the eigenvalues, taking a preset number of the first eigenvectors to form a feature matrix, and multiplying the feature matrix by the matrix formed by the eigenvectors to obtain a reduced dimension matrix.

[0048] Furthermore, pre-clustering uses the Canopy algorithm to divide the elements in the dimensionality reduction matrix to form several Canopies (covering areas), namely pre-clustering clusters. The data points within each Canopy have high similarity. The number of pre-clustering clusters is used as the number of customer classification categories, and then K-means clustering is performed on the customers to obtain multiple customer category sets.

[0049] Specifically, customers are selected as cluster centers according to the number of clusters, and the distances between customers are calculated according to the above steps of calculating the similarity of customer ratings, so as to cluster the customers and obtain a set of customer categories.

[0050] In the embodiment of the present invention, customers with similar interests can be classified into the same customer category set through the customer category set, which can improve the accuracy and efficiency of subsequent recommendation list calculation.

[0051] S4. Calculate the project association scores between customers in the customer category set according to the project prediction scores, and calculate the path association scores according to the target data set.

[0052] In the embodiment of the present invention, the project association score is the probability score of customers in the customer category set being interested in the same project, and the path association is the score between the project paths through which customers score projects, to reflect changes in customer project scores over time.

[0053] Specifically, calculating the project association scores between customers in the customer category set according to the project prediction scores includes: Calculate the difference in project scores between customers in each customer category set according to the project prediction scores; Calculating the item difference entropy between the customers of the category according to the item score differences; The item differences are used to determine item association scores between the categories of customers.

[0054] In detail, the difference of the item scores of each customer in the customer category set for the same item is calculated according to the item prediction score, and then the item difference entropy is calculated.

[0055] Specifically, the following formula is used to calculate the item difference entropy: in, represents the item difference entropy, Indicates The difference in project scores for each project, represents the frequency of occurrence of item score differences, Indicates the total number of items corresponding to the difference in item scores.

[0056] In the embodiment of the present invention, the larger the item difference entropy is, the smaller the possibility that customers are interested in the same item is, that is, the smaller the item association score is. Therefore, the inverse of the item difference entropy can be used as the item association score. In particular, when the item difference entropy is zero, it indicates that customers within the customer category set may be interested in the same item.

[0057] In the embodiment of the present invention, the step of calculating the path association score according to the target data set includes: Constructing a project scoring path for each customer in the customer category set according to the target data set; Convert the scoring path into a vector to obtain a feature vector corresponding to the project scoring path; The feature differences between the feature vectors are calculated to obtain a path association score.

[0058] Specifically, the project scoring path is to sort the project scoring behavior of each customer in the customer category set by time to obtain the project scoring path. The project scoring path is in text format. The project scoring path is formatted and the feature vector corresponding to the project scoring path is obtained. The feature similarity is then calculated as the feature difference to obtain the path association score.

[0059] In the embodiment of the present invention, the project association scoring can utilize the project long-tail effect to expand the coverage of recommendations and further improve the accuracy of recommendations. At the same time, the path association scoring can analyze the customer's project interest trend and analyze the changes in customer interests from the association of project associations and project transformations, which is beneficial to improve the accuracy of subsequent recommendation list calculations.

[0060] S5. Calculate a recommendation list using the item association score and the path association score, and generate a customer marketing strategy based on the recommendation list.

[0061] In the embodiment of the present invention, the recommendation list is a list of items such as products, services or content that customers are most likely to be interested in, and the customer marketing strategy is a specific execution method of the recommendation list, through which the recommended items in the recommendation list are pushed to the corresponding customers.

[0062] Specifically, the calculating the recommendation list by using the item association score and the path association score includes: Determine project-associated customers according to the project-associated scores, and extract a list of associated projects from the associated users; Determine path-associated customers according to the path-associated scores, extract path categories of the path-associated customers and convert them into feature vectors; Calculate the path similarity according to the feature vector, and calculate the path item list according to the path similarity; A recommendation list is generated according to the associated item list and the path item list.

[0063] In the embodiment of the present invention, for each customer, a larger preset number of customers are selected as corresponding project-associated customers according to the project-associated scores, and the projects with the largest project scores among each project-associated customer form an associated project list.

[0064] Furthermore, path-associated customers whose number is consistent with that of project-associated customers are selected according to the path-associated scores, and the project paths of the target customers and the path-associated customers when scoring the projects are extracted, wherein two adjacent project scores are one path category, thereby obtaining the path category of the path-associated customers.

[0065] Next, based on the Euclidean distances between each path category of the target customer and each path category of the path-associated customer, the Euclidean distances are added to obtain the path similarity, and the sum of the path similarities for each path is counted. The larger the sum, the smaller the similarity of the path categories. Therefore, the latest path category of the customer associated with the smaller path can be selected to obtain a path item list. For example, the latest item score of customer 1 associated with the smaller path is selected to make up item 1 to item 2, then item 2 will be used as the item in the path item list.

[0066] Furthermore, the items in the associated item list and the path item list are sorted according to the customer's project prediction scores for the candidate items to obtain a recommendation list.

[0067] Among them, the project association score and path association score can be used to analyze the set of projects that the customer may be interested in based on the customer's project associations and project path changes, thereby expanding the scope of the customer's interested projects. The project prediction score can then be used to analyze the customer's quantitative rating of each candidate project, and the candidate projects can be further sorted, thereby improving the accuracy of the recommendation list calculation.

[0068] In the embodiment of the present invention, generating a customer marketing strategy based on the recommendation list includes: Determining a project recommendation order according to the recommendation list; Generate project recommendation information according to the project recommendation strategy; The project recommendation information is pushed according to the preset push rules to obtain the customer marketing strategy.

[0069] In the embodiment of the present invention, the order of project recommendation is the order in which the projects are promoted. The more valuable projects in the recommendation list are pushed earlier. The project recommendation information is the content that needs to be recommended for each project, for example, it can be specific content such as product improvements and services.

[0070] Furthermore, the preset push rules are pre-set information promotion rules, such as the push platform, frequency, method, etc. Corresponding rules can be set for different projects to improve the accuracy of customer marketing strategies.

[0071] like Figure 4 , which is a functional module diagram of an artificial intelligence-based customer marketing strategy recommendation system provided by one embodiment of the present invention.

[0072] The customer marketing strategy recommendation system 400 based on artificial intelligence of the present invention can be installed in an electronic device. According to the functions implemented, the customer marketing strategy recommendation system 400 based on artificial intelligence can include a missing item supplement module 401, a score prediction module 402, a customer classification module 403, an associated score calculation module 404 and a customer marketing strategy generation module 405. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0073] In this embodiment, the functions of each module / unit are as follows: The missing item supplementation module 401 is used to obtain a customer data set, calculate the customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; The rating prediction module 402 is used to predict the customer project ratings of the target data set to obtain project prediction ratings; The customer classification module 403 is used to construct a customer interest matrix according to the project prediction score, and classify the customers in the customer data set according to the customer interest matrix to obtain a customer category set; The association score calculation module 404 is used to calculate the project association scores between customers in the customer category set according to the project prediction scores, and calculate the path association scores according to the target data set; The customer marketing strategy generating module 405 is used to calculate a recommendation list through the item association score and the path association score, and generate a customer marketing strategy based on the recommendation list.

[0074] In detail, each module described in the customer marketing strategy recommendation system 400 based on artificial intelligence in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The technical means are the same as the artificial intelligence-based customer marketing strategy recommendation method described in, and can produce the same technical effects, so I will not go into details here.

[0075] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 501 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0076] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0077] The present invention also provides an electronic device, which may include a processor, a memory, a communication bus and a communication interface, and may also include a computer program stored in the memory and executable on the processor, such as a method program for improving welding stability of heterogeneous titanium alloy laser welding technology.

[0078] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes various functions and processes data of the electronic device by running or executing programs or modules stored in the memory (for example, executing a welding stability improvement method program for heterogeneous titanium alloy laser welding technology, etc.), and calling data stored in the memory.

[0079] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory may be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory may also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory may also include both an internal storage unit and an external storage device of the electronic device. The memory can be used not only to store application software and various types of data installed in the electronic device, such as the code of the welding stability improvement method program of the heterogeneous titanium alloy laser welding technology, but also to temporarily store data that has been output or is to be output.

[0080] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0081] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0082] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0083] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0084] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0085] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0086] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Acquire a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; Predicting customer project scores for the target data set to obtain project prediction scores; Constructing a customer interest matrix according to the project prediction scores, and classifying customers in the customer data set according to the customer interest matrix to obtain a customer category set; Calculating the project association scores between customers in the customer category set according to the project prediction scores, and calculating the path association scores according to the target data set; A recommendation list is calculated by using the item association score and the path association score, and a customer marketing strategy is generated based on the recommendation list.

[0087] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0088] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0090] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0091] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0092] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0093] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0094] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A customer marketing strategy recommendation method based on artificial intelligence, characterized in that: The method comprises: Acquire a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; Predicting customer project scores for the target data set to obtain project prediction scores; Constructing a customer interest matrix according to the project prediction scores, and classifying customers in the customer data set according to the customer interest matrix to obtain a customer category set; Calculating the project association scores between customers in the customer category set according to the project prediction scores, and calculating the path association scores according to the target data set; A recommendation list is calculated by using the item association score and the path association score, and a customer marketing strategy is generated based on the recommendation list.

2. The customer marketing strategy recommendation method based on artificial intelligence according to claim 1, characterized in that: The calculating the customer correlation factor between each customer in the customer data set includes: Calculating item data for each customer in the customer data set; Counting the total number of identical projects among the customers according to the project data; Calculating the customer correlation factor between the customers according to the total number of the same items; The customer correlation factor between the customers is calculated using the following formula: in, represents the customer-related factor, Represents the preset weight coefficient, Indicates the total number of identical items.

3. The customer marketing strategy recommendation method based on artificial intelligence according to claim 1, characterized in that: The step of supplementing the missing items of the customer data set according to the customer-related factors to obtain a target data set includes: Determine a related customer set for each customer according to the customer related factors, calculate user similarity of the related customer set, and calculate a similar customer set according to the user similarity; Find the missing items of the customer according to the similar customer set and calculate the item score corresponding to the missing item; Calculate the missing item data corresponding to the missing item according to the item score; The project data corresponding to the missing items are calculated using the following formula: in, Indicates missing items The corresponding project data, Indicates the customer The corresponding mean score of the rated items, Indicates the customer The corresponding set of similar customers, Indicates the customer The corresponding similar customers are concentrated in Similar customers for missing items The project ratings, Indicates The average rating of the rated items corresponding to similar customers, Indicates the customer No. The user similarity between similar customers, Indicates the customer With Customer correlation factors between similar customers; The missing item data are used to supplement the missing items to obtain the target data set.

4. The method for recommending customer marketing strategies based on artificial intelligence according to claim 1, characterized in that: The step of predicting the customer project scores on the target data set to obtain project prediction scores includes: Extracting the project rating of each customer from the target data set, and calculating the customer rating similarity based on the project rating; Selecting customers with similar ratings based on the customer rating similarity; Calculate the predicted project score for each customer based on customers with similar scores; The project prediction score is calculated using the following formula: in, Indicates Clients on projects The project prediction score, Indicates The average item rating of the rated items by customers, Indicates The set of customers with similar ratings to the customer. represents the set of customers who have rated the item, Indicates Customers and The similarity of customer ratings between customers, Indicates Clients on projects The project ratings, Indicates The mean item rating of the rated items by customers.

5. The method for recommending customer marketing strategies based on artificial intelligence according to claim 1, characterized in that: The step of constructing a customer interest matrix according to the project prediction scores includes: Calculate the time decay coefficient corresponding to the predicted score of the project; Calculate the project interest according to the time decay coefficient and the project prediction score; A customer interest matrix is ​​constructed based on the project interest levels.

6. The method for recommending customer marketing strategies based on artificial intelligence according to claim 1, characterized in that: The step of classifying the customers in the customer data set according to the customer interest matrix to obtain a customer category set includes: Performing principal component dimensionality reduction on the customer interest matrix to obtain a dimensionality reduction matrix; Pre-clustering the dimension reduction matrix to obtain pre-clustering clusters, and determining the number of cluster centers according to the pre-clustering clusters; The customers in the customer data set are clustered according to the number of cluster centers to obtain a customer category set.

7. The method for recommending customer marketing strategies based on artificial intelligence according to claim 1, characterized in that: The calculating the project association scores between customers in the customer category set according to the project prediction scores includes: Calculate the difference in project scores between customers in each customer category set according to the project prediction scores; Calculating the item difference entropy between the customers of the category according to the item score differences; The project difference entropy is calculated using the following formula: in, represents the item difference entropy, Expressing the The difference in project scores for each project, represents the frequency of occurrence of item score differences, Indicates the total number of items corresponding to the difference in item scores; The item differences are used to determine item association scores between the categories of customers.

8. The method for recommending customer marketing strategies based on artificial intelligence according to claim 1, characterized in that: The calculating the recommendation list by using the item association score and the path association score includes: Determine project-associated customers according to the project-associated scores, and extract a list of associated projects from the associated users; Determine path-associated customers according to the path-associated scores, extract path categories of the path-associated customers and convert them into feature vectors; Calculate the path similarity according to the feature vector, and calculate the path item list according to the path similarity; A recommendation list is generated according to the associated item list and the path item list.

9. A customer marketing strategy recommendation system based on artificial intelligence, characterized in that: The system comprises: A missing item supplementation module is used to obtain a customer data set, calculate a customer correlation factor between each customer in the customer data set, and supplement the missing items of the customer data set according to the customer correlation factor to obtain a target data set; A rating prediction module is used to predict customer project ratings for the target data set to obtain project prediction ratings; A customer classification module, used to construct a customer interest matrix according to the project prediction score, and classify the customers in the customer data set according to the customer interest matrix to obtain a customer category set; A correlation score calculation module, used to calculate the project correlation scores between customers in the customer category set according to the project prediction scores, and calculate the path correlation scores according to the target data set; The customer marketing strategy generation module is used to calculate a recommendation list through the item association score and the path association score, and generate a customer marketing strategy based on the recommendation list.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the customer marketing strategy recommendation method based on artificial intelligence as described in any one of claims 1 to 8 is implemented.

Images