Product recommendation method and device, storage medium and electronic equipment

Abstract

The invention discloses a product recommendation method and device, a storage medium and electronic equipment, and relates to the technical field of computers. The method comprises the following steps: acquiring real-time behavior data of a target object on a target system; inputting real-time behavior data of the target object on the target system into the prediction model for processing, and outputting demand information of the target object; determining a recommendation list according to the demand information of the target object and the real-time behavior data of the target object on the target system; and receiving a combined product determined by the target object based on the M target products in the target system, and recommending the combined product and the N target products in the recommendation list to the target object. According to the method and the device, the problem that the effect of recommending products related to power supply and energy management to users is poor in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a product recommendation method and device, a storage medium, and an electronic device. Background Art

[0002] With the rapid development of the electricity market, users' demand for value-added products and services is growing. Accurately tapping into the potential needs of target customers in this vast market is a major challenge facing the promotion of value-added services. Furthermore, product recommendation systems in related technologies generally make predictions based on historical user behavior data and recommend value-added products and services related to power supply and energy management based on the prediction results. However, these product recommendation systems in related technologies have the following shortcomings:

[0003] (1) Lack of real-time prediction capabilities

[0004] Although product recommendation systems in related technologies can analyze user historical behavior, they are often unable to accurately predict users' immediate needs and preferences. This results in recommendation results that may not be accurate and personalized enough and cannot fully meet users' immediate needs.

[0005] (2) Lack of interactivity and flexibility

[0006] Product recommendation systems in related technologies can usually only provide a fixed recommendation list, and users cannot freely combine and customize products or services according to their needs. This lack of interactivity and flexibility limits users' choices and personalized experience.

[0007] Therefore, the product recommendation system using related technologies is less effective in recommending value-added products or services to users.

[0008] Currently, no effective solution has been proposed to the problem that related technologies are less effective in recommending products related to power supply and energy management to users. Summary of the Invention

[0009] The main purpose of this application is to provide a product recommendation method and device, storage medium and electronic device to solve the problem of poor effect in recommending products related to power supply and energy management to users in related technologies.

[0010] To achieve the above-mentioned objective, according to one aspect of the present application, a product recommendation method is provided. The method comprises: obtaining real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, wherein the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; inputting the real-time behavior data of the target object on the target system into a prediction model for processing, and outputting demand information of the target object, wherein the demand information is used to represent the predicted product demanded by the target object; determining a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes information of at least N target products to be recommended to the target object, wherein N is a positive integer less than or equal to M; receiving a combination product determined by the target object based on the M target products in the target system, and recommending the combination product and the N target products in the recommendation list to the target object.

[0011] Furthermore, the real-time behavior data of the target object on the target system is input into the prediction model for processing, and the demand information of the target object is output, including: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-processing the real-time behavior data of the target object on the target system to obtain processed real-time behavior data; analyzing the processed real-time behavior data to determine the frequency information of the target object purchasing the M target products in the target system; and outputting the demand information of the target object based on the frequency information of the target object purchasing the M target products in the target system.

[0012] Furthermore, preprocessing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data includes: determining whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data and erroneous data; if the target type data does not exist in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system is prohibited; if the target type data exists in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system according to a target processing method to obtain the processed real-time behavior data, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data and a processing method for correcting data.

[0013] Furthermore, based on the frequency information of the target object purchasing the M target products in the target system, outputting the demand information of the target object includes: based on the frequency information of the target object purchasing the M target products in the target system, determining S target products from the M target products, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; and outputting the demand information of the target object based on the S target products.

[0014] Furthermore, determining the recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system includes: combining the recommendation algorithm, screening the M target products in the target system based on the demand information of the target object and the real-time behavior data of the target object on the target system to obtain the N target products; and determining the recommendation list based on the N target products.

[0015] Furthermore, receiving the combination product determined by the target object based on the M target products in the target system includes: determining an interaction interface for the target object to interact with the target system; and receiving the combination product determined by the target object based on the M target products in the target system through the interaction interface.

[0016] Furthermore, recommending the combination product and the N target products in the recommendation list to the target object includes: performing a comparative analysis on the combination product and each target product in the recommendation list to obtain an analysis result; based on the analysis result, determining adjustment information for the combination product; and recommending the analysis result and the adjustment information of the combination product to the target object.

[0017] To achieve the above-mentioned object, according to another aspect of the present application, a product recommendation device is provided. The device comprises: a first acquisition unit, configured to acquire real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, wherein the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; a first processing unit, configured to input the real-time behavior data of the target object on the target system into a prediction model for processing, and output demand information of the target object, wherein the demand information is used to represent the predicted product demanded by the target object; a first determination unit, configured to determine a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes information of at least N target products to be recommended to the target object, wherein N is a positive integer less than or equal to M; and a second processing unit, configured to receive a combination product determined by the target object based on the M target products in the target system, and recommend the combination product and the N target products in the recommendation list to the target object.

[0018] Furthermore, the first processing unit includes: a first processing module, used to input the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-process the real-time behavior data of the target object on the target system to obtain processed real-time behavior data; a first analysis module, used to analyze the processed real-time behavior data to determine the frequency information of the target object purchasing the M target products in the target system; a first output module, used to output the demand information of the target object based on the frequency information of the target object purchasing the M target products in the target system.

[0019] Furthermore, the first processing module includes: a first judgment submodule, used to judge whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data and erroneous data; a first processing submodule, used to prohibit preprocessing of the real-time behavior data of the target object on the target system if the target type data does not exist in the real-time behavior data of the target object on the target system; a second processing submodule, used to preprocess the real-time behavior data of the target object on the target system according to a target processing method to obtain processed real-time behavior data if the target type data exists in the real-time behavior data of the target object on the target system, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data and a processing method for correcting data.

[0020] Furthermore, the first output module includes: a first determination submodule, used to determine S target products from the M target products based on the frequency information of the target object purchasing the M target products in the target system, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; and a first output submodule, used to output the demand information of the target object based on the S target products.

[0021] Furthermore, the first determination unit includes: a second processing module, which is used to combine the recommendation algorithm to screen the M target products in the target system according to the demand information of the target object and the real-time behavior data of the target object on the target system to obtain the N target products; a first determination module, which is used to determine the recommendation list based on the N target products.

[0022] Furthermore, the second processing unit includes: a second determination module for determining an interaction interface for the target object to interact with the target system; and a first receiving module for receiving, through the interaction interface, a combination product determined by the target object based on M target products in the target system.

[0023] Furthermore, the second processing unit includes: a second analysis module, used to compare and analyze the combination product and each target product in the recommendation list to obtain an analysis result; a third determination module, used to determine adjustment information for the combination product based on the analysis result; and a third processing module, used to recommend the analysis result and the adjustment information of the combination product to the target object.

[0024] In order to achieve the above-mentioned object, according to another aspect of the present application, a computer-readable storage medium is provided, wherein the storage medium stores a program, wherein the program executes any one of the above-mentioned product recommendation methods.

[0025] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, which includes one or more processors and a memory, and the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the product recommendation method described in any one of the above-mentioned items.

[0026] Through the present application, the following steps are adopted: obtaining real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; inputting the real-time behavior data of the target object on the target system into a prediction model for processing, and outputting demand information of the target object, wherein the demand information is used to represent the predicted product required by the target object; determining a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, and N is a positive integer less than or equal to M; receiving a combination product determined by the target object based on the M target products in the target system, and recommending the combination product and the N target products in the recommendation list to the target object, thereby solving the problem of poor effect of recommending products related to power supply and energy management to users in the related art. By collecting and analyzing user behavior data in real time and combining it with advanced predictive models, we can more accurately predict users' immediate needs and preferences, thereby providing more accurate and personalized recommendation services to meet users' immediate needs. This solution supports users to freely combine and customize personalized product solutions. Users can freely match them according to their needs and preferences to form an integrated combination package solution, which greatly enhances user participation and flexibility, allowing users to better meet their personalized needs, thereby improving the effect of recommending products related to power supply and energy management to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0028] Figure 1 This is the process of the recommended method of the product provided in the embodiment of this application Figure 1 ;

[0029] Figure 2 This is the process of the recommended method of the product provided in the embodiment of this application Figure 2 ;

[0030] Figure 3 This is the process of the recommended method of the product provided in the embodiment of this application Figure 3 ;

[0031] Figure 4 is a schematic diagram of a recommended device for a product provided according to an embodiment of the present application;

[0032] Figure 5 is a schematic diagram of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0034] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] It should be noted that the relevant information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display and analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. For example, an interface is set up between this system and the relevant user or organization. Before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving the consent information fed back by the aforementioned user or organization.

[0037] The present invention will be described below in conjunction with preferred implementation steps. Figure 1 This is the process of the recommended method of the product provided in the embodiment of this application Figure 1 ,like Figure 1 As shown, the method includes the following steps:

[0038] Step S101, obtaining real-time behavior data of the target object on the target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1.

[0039] For example, the target product may be a value-added product or service to be recommended to the user (corresponding to the target object). For example, the products or services may include traditional products or services and value-added products or services. Traditional products or services may include fixed-cost products or services such as electricity bills, while value-added products or services may include charging station construction solutions.

[0040] The above-mentioned target system can be a system for recommending value-added products or services (corresponding to the above-mentioned target products) to users (corresponding to the above-mentioned target objects). Moreover, various behavioral data (corresponding to the above-mentioned real-time behavioral data) of users (corresponding to the above-mentioned target objects) on the system (corresponding to the above-mentioned target system) can be captured in real time by the tracking code deployed on the application (corresponding to the above-mentioned target system). In addition, the above-mentioned real-time behavioral data is the user behavior data collected in real time at the current moment or within a specific time period, and the above-mentioned real-time behavioral data refers to the data generated and immediately collected when the user (corresponding to the above-mentioned target object) operates on the product recommendation system (corresponding to the above-mentioned target system).

[0041] Step S102 : inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and outputting the demand information of the target object, wherein the demand information is used to represent the product demanded by the target object obtained by prediction.

[0042] For example, based on the characteristics of user behavior data and predicted needs, an appropriate machine learning algorithm can be selected to build a prediction model, and the above-mentioned prediction model may include collaborative filtering, content recommendation, deep learning, etc. Then, the real-time behavior data generated and immediately collected when the user (corresponding to the above-mentioned target object) operates on the product recommendation system (corresponding to the above-mentioned target system) can be input into the constructed prediction model, and the prediction model outputs the predicted immediate needs and preferences (corresponding to the above-mentioned demand information) of the user (corresponding to the above-mentioned target object).

[0043] Step S103, determining a recommendation list based on the target object's demand information and the target object's real-time behavior data on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, where N is a positive integer less than or equal to M.

[0044] For example, based on the results of the prediction model, combined with the user's (corresponding to the above-mentioned target object) real-time behavior (corresponding to the above-mentioned real-time behavior data) and real-time needs (corresponding to the above-mentioned demand information), a personalized recommendation list can be generated for the user (corresponding to the above-mentioned target object).

[0045] Step S104: receiving a combination product determined by the target object based on the M target products in the target system, and recommending the combination product and the N target products in the recommendation list to the target object.

[0046] For example, an intuitive and easy-to-use interactive interface can be designed to allow users (corresponding to the above-mentioned target objects) to freely select products and services (corresponding to the above-mentioned M target products) and combine them into personalized package plans (corresponding to the above-mentioned combination products). Then, the user (corresponding to the above-mentioned target objects) can be recommended the user's freely combined products or services (corresponding to the above-mentioned combination products) and the products or services in the recommendation list (corresponding to the above-mentioned N target products).

[0047] Through the above steps S101 to S104, by collecting and analyzing user behavior data in real time and combining it with advanced prediction models, users' immediate needs and preferences can be predicted more accurately, thereby providing more accurate and personalized recommendation services to meet users' immediate needs. In addition, this solution supports users to freely combine and customize personalized product solutions. Users can freely match according to their own needs and preferences to form an integrated combination package solution, thereby greatly enhancing user participation and flexibility, enabling users to better meet their personalized needs, and thus improving the effect of recommending products related to power supply and energy management to users.

[0048] Figure 2 This is the process of the recommended method of the product provided in the embodiment of this application Figure 2 ,like Figure 2 As shown, in the product recommendation method provided in the embodiment of the present application, the real-time behavior data of the target object on the target system is input into the prediction model for processing, and the output demand information of the target object includes:

[0049] Step S201: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-processing the real-time behavior data of the target object on the target system to obtain processed real-time behavior data;

[0050] Step S202: Analyze the processed real-time behavior data to determine the frequency information of the target object purchasing M target products in the target system;

[0051] Step S203: outputting the target object's demand information based on the target object's frequency information of purchasing the M target products in the target system.

[0052] For example, when collecting user behavior data, you can first capture the various behavior data (corresponding to the above-mentioned real-time behavior data) of the user (corresponding to the above-mentioned target system) on the system (corresponding to the above-mentioned target system) in real time through the tracking code deployed on the application (corresponding to the above-mentioned target system), and the accuracy and real-time nature of the user behavior data collection need to be guaranteed for subsequent analysis and prediction. Then, the collected user behavior data (corresponding to the above-mentioned real-time behavior data) can be input into the constructed prediction model, and the collected user behavior data (corresponding to the above-mentioned real-time behavior data) can be cleaned and sorted through the prediction model; then, using big data analysis technology, the cleaned and sorted user behavior data can be deeply mined and analyzed, and the user's (corresponding to the above-mentioned target object) interest preferences and consumption habits and other information (corresponding to the above-mentioned frequency information) can be extracted; then, based on the user's (corresponding to the above-mentioned target object) interest preferences and consumption habits and other information (corresponding to the above-mentioned frequency information), the predicted user's (corresponding to the above-mentioned target object) immediate needs and preferences (corresponding to the above-mentioned demand information) can be output.

[0053] Through the above solution, users' immediate needs and preferences can be analyzed in real time, and products or services that users may be interested in can be predicted.

[0054] Optionally, in the product recommendation method provided in the embodiment of the present application, the real-time behavior data of the target object on the target system is preprocessed to obtain the processed real-time behavior data, including: determining whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data, and erroneous data; if there is no target type data in the real-time behavior data of the target object on the target system, preprocessing of the real-time behavior data of the target object on the target system is prohibited; if there is target type data in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system according to the target processing method to obtain the processed real-time behavior data, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data, and a processing method for correcting data.

[0055] For example, the collected user behavior data (corresponding to the above-mentioned real-time behavior data) may contain noise and outliers and need to be cleaned and sorted. And the process of cleaning and sorting the collected user behavior data (corresponding to the above-mentioned real-time behavior data) may include removing duplicate data, processing missing values, correcting erroneous data, etc. For example, if the collected user behavior data (corresponding to the above-mentioned real-time behavior data) contains duplicate data, the collected user behavior data (corresponding to the above-mentioned real-time behavior data) can be pre-processed by removing duplicate data; if the collected user behavior data (corresponding to the above-mentioned real-time behavior data) contains missing data, the collected user behavior data (corresponding to the above-mentioned real-time behavior data) can be pre-processed by filling in missing data; if the collected user behavior data (corresponding to the above-mentioned real-time behavior data) contains erroneous data, the collected user behavior data (corresponding to the above-mentioned real-time behavior data) can be pre-processed by correcting erroneous data.

[0056] Through the above solution, the collected user behavior data can be easily cleaned and sorted, thereby ensuring the accuracy of the collected user behavior data.

[0057] Optionally, in the product recommendation method provided in the embodiment of the present application, based on the frequency information of the target object purchasing M target products in the target system, outputting the target object's demand information includes: based on the frequency information of the target object purchasing M target products in the target system, determining S target products from the M target products, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; based on the S target products, outputting the target object's demand information.

[0058] For example, when using big data analysis technology to conduct in-depth mining and analysis of the cleaned and organized user behavior data, if it is analyzed that the frequency of users (corresponding to the above-mentioned target object) purchasing product A on the product recommendation system (corresponding to the above-mentioned target system) is 95%, the frequency of purchasing product B is 98%, and the frequency of purchasing product C is 96%, and the above-mentioned preset frequency is 90%, that is, the frequency of purchasing product A is 95%, which is greater than the preset frequency of 90%, the frequency of purchasing product B is 98%, which is greater than the preset frequency of 90%, and the frequency of purchasing product C is 96%, which is also greater than the preset frequency of 90%. Then, by analyzing the product characteristics of products A, B and C (corresponding to the S target products mentioned above), the user's (corresponding to the above-mentioned target object) interests, preferences, consumption habits and other information can be determined; then, based on the user's (corresponding to the above-mentioned target object) interests, preferences, consumption habits and other information, the predicted user's (corresponding to the above-mentioned target object) immediate needs and preferences (corresponding to the above-mentioned demand information) are output.

[0059] Through the above solution, the user's immediate needs and preferences can be quickly and accurately determined based on information such as the user's interest preferences and consumption habits.

[0060] Optionally, in the product recommendation method provided in the embodiment of the present application, determining the recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system includes: combining the recommendation algorithm, screening and processing the M target products in the target system based on the demand information of the target object and the real-time behavior data of the target object on the target system to obtain the N target products; and determining the recommendation list based on the N target products.

[0061] For example, a personalized recommendation algorithm can be designed by combining the results of a prediction model with historical user behavior data. This recommendation algorithm can then be used to generate a personalized recommendation list in real time based on the user's (corresponding to the target object) immediate needs and preferences (corresponding to the demand information) output by the prediction model and the user's real-time behavior data. Furthermore, recommendation algorithms can be collaborative filtering, deep learning, and graph-based.

[0062] Through the above solution, a personalized recommendation list can be generated in real time according to the user's real-time behavior and needs, thereby ensuring the real-time and accuracy of the recommendation.

[0063] Figure 3 This is the process of the recommended method of the product provided in the embodiment of this application Figure 3 ,like Figure 3 As shown, in the product recommendation method provided in the embodiment of the present application, receiving a combination product determined by a target object based on M target products in a target system includes:

[0064] Step S301, determining an interactive interface for the target object to interact with the target system;

[0065] Step S302: receiving, through an interactive interface, a combination product determined by a target object based on M target products in a target system.

[0066] For example, an intuitive and easy-to-use interactive interface can be designed within a product recommendation system (corresponding to the aforementioned target system), allowing users (corresponding to the aforementioned target objects) to freely select products and services and combine them into personalized packages. This interface can also provide clear navigation and prompt information to help users (corresponding to the aforementioned target objects) easily complete operations. Furthermore, during the user's DIY (Do It Yourself) combination process, the system (corresponding to the aforementioned target system) can calculate and display information such as the price and revenue of the combined product (corresponding to the aforementioned combined product) in real time. This allows the system (corresponding to the aforementioned target system) to provide users with real-time feedback through its dynamic calculation and display capabilities.

[0067] Through the above solution, users can be provided with more choices and flexibility, allowing them to freely match according to their needs and preferences, thereby enhancing user participation and flexibility, and enabling users to better meet their personalized needs.

[0068] Optionally, in the product recommendation method provided in the embodiment of the present application, recommending the combination product and N target products in the recommendation list to the target object includes: performing a comparative analysis on the combination product and each target product in the recommendation list to obtain an analysis result; based on the analysis result, determining adjustment information for the combination product; and recommending the analysis result and the adjustment information of the combination product to the target object.

[0069] For example, algorithms can be designed to conduct comparative analyses of different solutions, including comparisons of price, revenue, and application effectiveness. This can comprehensively consider multiple factors and provide users (corresponding to the aforementioned target objects) with comprehensive comparison results. Furthermore, the system (corresponding to the aforementioned target system) can provide optimization suggestions (corresponding to the aforementioned adjustment information) based on the results of the solution comparison. These optimization suggestions (corresponding to the aforementioned adjustment information) can include replacing certain products, adjusting combinations, etc., to help users (corresponding to the aforementioned target objects) improve their solutions and enhance their effectiveness.

[0070] The above solutions can help users evaluate the differences and advantages and disadvantages between different solutions and make more informed decisions.

[0071] For example, the DIY product interactive recommendation system combines technologies from multiple fields, including user behavior analysis, predictive modeling, and interaction design. User behavior analysis captures users' clicks, browsing behavior, and other behaviors during the product and service selection process, thereby uncovering their interests and preferences. Predictive models leverage machine learning and deep learning algorithms to predict products or services that users may be interested in based on historical user behavior data and profile information. Interaction design, on the other hand, focuses on presenting these recommendations in an intuitive and easy-to-use manner, allowing users to easily combine and customize the products or services they need.

[0072] Therefore, in this embodiment, by combining user behavior analysis, predictive modeling, and interactive design technologies, a more intelligent and personalized DIY product interactive recommendation system is provided. This system can analyze users' immediate needs and preferences in real time, predict products or services that users may be interested in, and support users in freely combining and customizing personalized product solutions. Furthermore, the system can provide detailed solution comparisons and pros and cons analysis to help users make more informed decisions.

[0073] Moreover, this embodiment provides a DIY product interactive recommendation system based on user behavior and prediction models, aiming to solve the problems existing in the existing technology, improve the real-time prediction capability, interactivity and flexibility of the recommendation system, and provide solution comparison and pros and cons analysis functions.

[0074] Specifically, the purposes of the method provided in this embodiment include:

[0075] (1) Improve real-time prediction capabilities

[0076] By combining user behavior analysis and prediction models, the method provided in this embodiment can analyze users' immediate needs and preferences in real time, thereby providing users with more accurate and personalized recommendation services.

[0077] (2) Enhance interactivity and flexibility

[0078] This embodiment supports users to freely combine and customize personalized product solutions to meet their personalized needs. Users can freely select products and services on the system interface according to their preferences and needs to form an integrated combination package solution.

[0079] (3) Provide solution comparison and pros and cons analysis functions

[0080] This example allows users to compare DIY packages with system-recommended or fixed packages in terms of price, revenue, and performance. The analysis results are presented through detailed difference information and indicator charts. This helps users evaluate the differences and advantages and disadvantages of different plans and make more informed decisions.

[0081] For example, the method provided in this embodiment is as follows:

[0082] 1. System Architecture Overview

[0083] The interactive DIY product recommendation system based on user behavior and prediction models proposed in this embodiment primarily includes the following modules: a user behavior analysis module, a simulation and measurement module, an intelligent recommendation module, a DIY combination module, a solution comparison module, and a parameter management module. These modules work together to accurately predict user needs, freely combine products, and compare the pros and cons of solutions.

[0084] 2. Key components

[0085] (1) User behavior collection and analysis module

[0086] This module is responsible for collecting various user behavior data, including but not limited to browsing history, search keywords, click behavior, etc. Through big data technology, this data is cleaned, organized and analyzed to extract key information such as user interests, preferences, and consumption habits.

[0087] (2) Prediction models and algorithms

[0088] Based on the results of user behavior analysis, machine learning algorithms are used to build predictive models. These models can predict users' immediate needs and preferences, as well as the likely effects of different product combinations. Model selection and training must take into account factors such as data characteristics, prediction accuracy, and real-time performance.

[0089] (3) Intelligent Recommendation Engine

[0090] The intelligent recommendation engine is one of the system's core components. It generates personalized recommendations based on the results of the predictive model, combined with the user's historical behavior and real-time needs. The recommendation algorithm must consider multiple factors, including user interests, product features, and market trends, to ensure accurate recommendations and high user satisfaction.

[0091] (4) DIY combination and interactive interface

[0092] To provide users with more choices and flexibility, the system features a DIY combination function. Users can freely select products and services on the system interface and combine them into a personalized package. The interactive interface is intuitive and easy to use, making it easy for users to operate and select.

[0093] (5) Scheme comparison and optimization module

[0094] To help users make informed choices, the system offers a plan comparison feature. Users can compare DIY plans with system-recommended or fixed plans in terms of price, benefits, and performance. The system also provides optimization suggestions to help users refine their plans and improve results.

[0095] (6) Parameter management and update module

[0096] Parameters in prediction models and recommendation algorithms require regular updates and adjustments to adapt to market changes and evolving user needs. The parameter management and update module is responsible for centralized management of these parameters, including operations such as viewing, modifying, and saving parameters. This module also ensures timely updates of valid data to ensure model accuracy and efficiency.

[0097] 3. Technical Implementation

[0098] (1) User behavior collection and analysis

[0099] Data collection: Tracking code deployed in the application captures user behavior data on other systems in real time. Data collection must be accurate and timely to facilitate subsequent analysis and prediction.

[0100] Data cleaning and organization: The collected raw data may contain noise and outliers and needs to be cleaned and organized. This process includes removing duplicate data, handling missing values, and correcting erroneous data.

[0101] User behavior analysis: Leveraging big data analysis techniques, we conduct in-depth mining and analysis of user behavior data. By extracting information such as user interests, preferences, and consumption habits, we provide basic data for subsequent predictions and recommendations.

[0102] (2) Prediction models and algorithms

[0103] Model selection: Based on the characteristics of the data and prediction requirements, select appropriate machine learning algorithms to build prediction models, including collaborative filtering, content recommendation, and deep learning.

[0104] Model training and optimization: Use historical user behavior data to train the model, evaluate the model's performance through methods such as cross-validation, and optimize and adjust the model based on the evaluation results to improve the accuracy and real-time performance of the prediction.

[0105] (3) Intelligent Recommendation Engine

[0106] Recommendation algorithm: Combine the results of the prediction model with the user's historical behavior data to design a personalized recommendation algorithm, taking into account multiple factors such as user interest preferences, product characteristics, and market trends to ensure the accuracy of recommendations and user satisfaction.

[0107] Real-time recommendation: Generate personalized recommendation lists in real time based on users' real-time behavior and needs to ensure the real-time and accuracy of recommendations.

[0108] (4) DIY combination and interactive interface

[0109] Interaction Design: Design an intuitive and easy-to-use interactive interface that allows users to freely choose products and services and combine them into personalized packages. The interface provides clear navigation and prompt information to help users complete operations easily.

[0110] Dynamic display: During the user's DIY combination process, the system calculates and displays the price, profit and other information of the combination in real time, providing users with real-time feedback through the system's dynamic calculation and display capabilities.

[0111] (5) Scheme comparison and optimization module

[0112] Solution comparison algorithm: The algorithm is designed to conduct comparative analysis of different solutions, including comparison of price, benefits, and application effects. It can comprehensively consider multiple factors and provide users with comprehensive comparison results.

[0113] Optimization suggestions: The system provides optimization suggestions based on the results of the plan comparison, including replacing certain products, adjusting the combination method, etc., to help users improve the plan and enhance the effect.

[0114] (6) Parameter management and update module

[0115] Parameter management interface: Provides a parameter management interface that allows administrators to view, modify and save parameters of different models. The interface provides clear parameter descriptions and operation procedures so that administrators can easily complete parameter management.

[0116] Parameter update mechanism: Establish a parameter update mechanism to ensure that model parameters can be updated in a timely manner to adapt to market changes and changes in user needs.

[0117] The method provided in this embodiment mainly focuses on the following aspects:

[0118] (1) Combining real-time user behavior analysis with prediction models

[0119] The key point is that this embodiment combines real-time user behavior analysis with a predictive model. By collecting and analyzing user behavior data and electricity profile information, it can predict users' immediate needs and preferences in real time. This combination enables the system to provide more accurate and personalized recommendation services to meet users' immediate needs.

[0120] (2) DIY combination and personalized recommendation

[0121] Another key aspect of this embodiment is its support for users to freely combine and customize product solutions. Users can freely select products and services on the system interface to form an integrated package. This DIY combination function provides users with more choices and flexibility, allowing them to freely combine products and services based on their needs and preferences. At the same time, combined with a personalized recommendation algorithm, the system can provide users with recommendations that better meet their needs.

[0122] (3) Function of scheme comparison and pros and cons analysis

[0123] This embodiment also provides a solution comparison and pros and cons analysis function, allowing users to compare the pros and cons of DIY package solutions with system-recommended solutions or fixed package solutions in terms of price, benefits, and application effects. This helps users evaluate the differences and pros and cons of different solutions, thereby making more informed decisions. It also provides users with a more comprehensive and objective solution evaluation tool, thereby improving user decision-making efficiency and satisfaction.

[0124] The method provided in this embodiment has the following advantages:

[0125] Higher real-time performance and accuracy: Traditional recommendation systems often make predictions based on users' historical behavior data. However, this embodiment collects and analyzes user behavior data and electricity archival information data in real time, combined with advanced prediction models, to more accurately predict users' immediate needs and preferences. The real-time performance and accuracy make the recommendation results of this embodiment closer to the actual needs of users, thereby improving the accuracy of recommendations and user satisfaction.

[0126] Enhanced user engagement and flexibility: Traditional recommendation systems often only offer fixed recommendations, limiting user choice. This embodiment, however, allows users to freely combine and customize product solutions. Users can freely combine and match products based on their needs and preferences to create an integrated package. This DIY combination feature significantly enhances user engagement and flexibility, allowing users to better meet their personalized needs.

[0127] More comprehensive solution comparison and evaluation: Existing recommendation systems often only offer a single recommended solution, making it difficult for users to compare and evaluate different solutions. This embodiment, however, provides a solution comparison and pros and cons analysis function, allowing users to compare DIY package solutions with system-recommended or fixed package solutions in terms of price, benefits, and performance. This function provides users with a more comprehensive and objective solution evaluation tool, helping them make more informed decisions.

[0128] More efficient parameter management and update mechanism: Traditional recommendation systems often lack effective management and update mechanisms for model parameters, which impacts model accuracy and real-time performance. This embodiment, however, establishes a parameter management and update mechanism that allows administrators to view, modify, and save parameters for different models in real time to adapt to market changes and user needs. This ensures the accuracy and real-time performance of the prediction model and recommendation algorithm, enabling the system to continuously provide users with high-quality recommendation services.

[0129] In summary, the product recommendation method provided in the embodiment of the present application obtains real-time behavior data of the target object on the target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; the real-time behavior data of the target object on the target system is input into the prediction model for processing, and the demand information of the target object is output, wherein the demand information is used to represent the predicted product required by the target object; based on the demand information of the target object and the real-time behavior data of the target object on the target system, a recommendation list is determined, wherein the recommendation list includes at least information of N target products to be recommended to the target object, and N is a positive integer less than or equal to M; a combination product determined by the target object based on the M target products in the target system is received, and the combination product and the N target products in the recommendation list are recommended to the target object, thereby solving the problem of poor effect of recommending products related to power supply and energy management to users in the related art. By collecting and analyzing user behavior data in real time and combining it with advanced predictive models, we can more accurately predict users' immediate needs and preferences, thereby providing more accurate and personalized recommendation services to meet users' immediate needs. This solution supports users to freely combine and customize personalized product solutions. Users can freely match them according to their needs and preferences to form an integrated combination package solution, which greatly enhances user participation and flexibility, allowing users to better meet their personalized needs, thereby improving the effect of recommending products related to power supply and energy management to users.

[0130] 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 that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0131] The present application also provides a product recommendation device. It should be noted that the product recommendation device of the present application can be used to execute the product recommendation method provided in the present application. The product recommendation device provided in the present application is introduced below.

[0132] Figure 4Schematic diagram of a recommended device for a product according to an embodiment of the present application. Figure 4 As shown, the device includes: a first acquiring unit 401 , a first processing unit 402 , a first determining unit 403 and a second processing unit 404 .

[0133] Specifically, the first acquisition unit 401 is configured to acquire real-time behavior data of a target subject on a target system, wherein the target system includes at least M target products to be recommended to the target subject, the M target products being products related to power supply and energy management, and M being a positive integer greater than 1;

[0134] The first processing unit 402 is configured to input the real-time behavior data of the target object on the target system into the prediction model for processing, and output the target object's demand information, wherein the demand information is used to represent the product predicted to be required by the target object;

[0135] A first determining unit 403 is configured to determine a recommendation list based on the target object's demand information and the target object's real-time behavior data on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, where N is a positive integer less than or equal to M;

[0136] The second processing unit 404 is configured to receive a combination product determined by the target object based on the M target products in the target system, and recommend the combination product and the N target products in the recommendation list to the target object.

[0137] In summary, the product recommendation device provided in the embodiment of the present application obtains the real-time behavior data of the target object on the target system through the first acquisition unit 401, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; the first processing unit 402 inputs the real-time behavior data of the target object on the target system into the prediction model for processing, and outputs the demand information of the target object, wherein the demand information is used to represent the predicted product required by the target object; the first determination unit 403 determines the recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, and N is a positive integer less than or equal to M; the second processing unit 404 receives the combination product determined by the target object based on the M target products in the target system, and recommends the combination product and the N target products in the recommendation list to the target object, thereby solving the problem of poor effect of recommending products related to power supply and energy management to users in the related art. By collecting and analyzing user behavior data in real time and combining it with advanced predictive models, we can more accurately predict users' immediate needs and preferences, thereby providing more accurate and personalized recommendation services to meet users' immediate needs. This solution supports users to freely combine and customize personalized product solutions. Users can freely match them according to their needs and preferences to form an integrated combination package solution, which greatly enhances user participation and flexibility, allowing users to better meet their personalized needs, thereby improving the effect of recommending products related to power supply and energy management to users.

[0138] Optionally, in the product recommendation device provided in the embodiment of the present application, the first processing unit includes: a first processing module, used to input the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-process the real-time behavior data of the target object on the target system to obtain processed real-time behavior data; a first analysis module, used to analyze the processed real-time behavior data to determine the frequency information of the target object purchasing M target products in the target system; a first output module, used to output the demand information of the target object based on the frequency information of the target object purchasing M target products in the target system.

[0139] Optionally, in the product recommendation device provided in the embodiment of the present application, the first processing module includes: a first judgment submodule, used to judge whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data and erroneous data; a first processing submodule, used to prohibit preprocessing of the real-time behavior data of the target object on the target system if there is no target type data in the real-time behavior data of the target object on the target system; a second processing submodule, used to preprocess the real-time behavior data of the target object on the target system according to a target processing method to obtain processed real-time behavior data if there is target type data in the real-time behavior data of the target object on the target system, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data and a processing method for correcting data.

[0140] Optionally, in the product recommendation device provided in the embodiment of the present application, the first output module includes: a first determination submodule, used to determine S target products from M target products based on the frequency information of the target object purchasing M target products in the target system, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; the first output submodule, used to output the demand information of the target object based on the S target products.

[0141] Optionally, in the product recommendation device provided in the embodiment of the present application, the first determination unit includes: a second processing module, which is used to combine the recommendation algorithm to screen and process the M target products in the target system based on the demand information of the target object and the real-time behavior data of the target object on the target system to obtain the N target products; and a first determination module, which is used to determine a recommendation list based on the N target products.

[0142] Optionally, in the product recommendation device provided in the embodiment of the present application, the second processing unit includes: a second determination module, used to determine the interactive interface for the target object to interact with the target system; and a first receiving module, used to receive, through the interactive interface, the combination product determined by the target object based on M target products in the target system.

[0143] Optionally, in the product recommendation device provided in the embodiment of the present application, the second processing unit includes: a second analysis module, used to compare and analyze the combination product and each target product in the recommendation list to obtain an analysis result; a third determination module, used to determine adjustment information for the combination product based on the analysis result; and a third processing module, used to recommend the analysis result and the adjustment information of the combination product to the target object.

[0144] The product recommendation device includes a processor and a memory. The above-mentioned first acquisition unit 401, first processing unit 402, first determination unit 403 and second processing unit 404 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0145] The processor contains a kernel, which retrieves the corresponding program unit from the memory. One or more kernels can be configured, and kernel parameters can be adjusted to improve the effectiveness of recommending products related to power supply and energy management to users.

[0146] The memory may include non-permanent memory in a computer-readable medium, 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.

[0147] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, the product recommendation method is implemented.

[0148] An embodiment of the present invention provides a processor, which is used to run a program, wherein the product recommendation method is executed when the program is run.

[0149] like Figure 5 As shown, an embodiment of the present invention provides an electronic device, which includes a processor, a memory, and a program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the program: obtaining real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; inputting the real-time behavior data of the target object on the target system into a prediction model for processing, and outputting demand information of the target object, wherein the demand information is used to represent the predicted product required by the target object; determining a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, and N is a positive integer less than or equal to M; receiving a combination product determined by the target object based on the M target products in the target system, and recommending the combination product and the N target products in the recommendation list to the target object.

[0150] When the processor executes the program, the following steps are also implemented: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and outputting the demand information of the target object, including: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-processing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data; analyzing the processed real-time behavior data to determine the frequency information of the target object purchasing M target products in the target system; and outputting the demand information of the target object based on the frequency information of the target object purchasing M target products in the target system.

[0151] When the processor executes the program, the following steps are also implemented: preprocessing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data, including: determining whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data, and erroneous data; if there is no target type data in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system is prohibited; if there is target type data in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system according to the target processing method to obtain the processed real-time behavior data, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data, and a processing method for correcting data.

[0152] When the processor executes the program, it also implements the following steps: based on the frequency information of the target object purchasing M target products in the target system, outputting the demand information of the target object includes: based on the frequency information of the target object purchasing M target products in the target system, determining S target products from the M target products, wherein the purchase frequency of each target product in the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; based on the S target products, outputting the demand information of the target object.

[0153] When the processor executes the program, it also implements the following steps: determining a recommendation list based on the target object's demand information and the target object's real-time behavior data on the target system, including: combining a recommendation algorithm, screening and processing the M target products in the target system based on the target object's demand information and the target object's real-time behavior data on the target system to obtain the N target products; determining a recommendation list based on the N target products.

[0154] When the processor executes the program, the following steps are also implemented: receiving the combination product determined by the target object based on the M target products in the target system, including: determining an interactive interface for the target object to interact with the target system; receiving the combination product determined by the target object based on the M target products in the target system through the interactive interface.

[0155] When the processor executes the program, the following steps are also implemented: recommending the combination product and N target products in the recommendation list to the target object includes: performing a comparative analysis on the combination product and each target product in the recommendation list to obtain an analysis result; based on the analysis result, determining adjustment information for the combination product; and recommending the analysis result and the adjustment information of the combination product to the target object.

[0156] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0157] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program initialized with the following method steps: obtaining real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; inputting the real-time behavior data of the target object on the target system into a prediction model for processing, and outputting demand information of the target object, wherein the demand information is used to represent the predicted product required by the target object; determining a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list includes at least information of N target products to be recommended to the target object, and N is a positive integer less than or equal to M; receiving a combination product determined by the target object based on the M target products in the target system, and recommending the combination product and the N target products in the recommendation list to the target object.

[0158] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and outputting the demand information of the target object including: inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and pre-processing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data; analyzing the processed real-time behavior data to determine the frequency information of the target object purchasing M target products in the target system; and outputting the demand information of the target object based on the frequency information of the target object purchasing M target products in the target system.

[0159] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: preprocessing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data, including: determining whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data and erroneous data; if there is no target type data in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system is prohibited; if there is target type data in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system according to the target processing method to obtain the processed real-time behavior data, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for filling data and a processing method for correcting data.

[0160] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: based on the frequency information of the target object purchasing M target products in the target system, outputting the target object's demand information includes: based on the frequency information of the target object purchasing M target products in the target system, determining S target products from the M target products, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; based on the S target products, outputting the target object's demand information.

[0161] When executed on a data processing device, it is also suitable for executing a program initialized with the following method steps: determining a recommendation list based on the demand information of the target object and the real-time behavior data of the target object on the target system, including: combining a recommendation algorithm, screening and processing the M target products in the target system based on the demand information of the target object and the real-time behavior data of the target object on the target system to obtain the N target products; determining a recommendation list based on the N target products.

[0162] When executed on a data processing device, it is also suitable for executing an initialization program having the following method steps: receiving a combination product determined by a target object based on M target products in a target system, including: determining an interactive interface for the target object to interact with the target system; receiving the combination product determined by the target object based on the M target products in the target system through the interactive interface.

[0163] When executed on a data processing device, it is also suitable for executing an initialized program having the following method steps: recommending a combination product and N target products in a recommendation list to a target object, including: performing a comparative analysis on the combination product and each target product in the recommendation list to obtain an analysis result; based on the analysis result, determining adjustment information for the combination product; and recommending the analysis result and the adjustment information of the combination product to the target object.

[0164] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0165] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0166] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0167] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0168] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0169] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0170] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0171] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0172] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A product recommendation method, characterized in that: include: Acquire real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; Inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and outputting the demand information of the target object, wherein the demand information is used to represent the predicted product required by the target object; Determine a recommendation list according to the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list at least includes information of N target products to be recommended to the target object, where N is a positive integer less than or equal to M; A combination product determined by the target object based on the M target products in the target system is received, and the combination product and the N target products in the recommendation list are recommended to the target object.

2. The method according to claim 1, characterized in that: Inputting the real-time behavior data of the target object on the target system into the prediction model for processing, and outputting the demand information of the target object includes: Inputting the real-time behavior data of the target object on the target system into a prediction model for processing, and preprocessing the real-time behavior data of the target object on the target system to obtain processed real-time behavior data; Analyze the processed real-time behavior data to determine the frequency information of the target object purchasing the M target products in the target system; Based on the frequency information of the target object purchasing the M target products in the target system, the demand information of the target object is output.

3. The method according to claim 2, characterized in that Preprocessing the real-time behavior data of the target object on the target system to obtain the processed real-time behavior data includes: Determine whether there is target type data in the real-time behavior data of the target object on the target system, wherein the target type data includes at least one of the following: duplicate data, missing data, and erroneous data; If the target type data does not exist in the real-time behavior data of the target object on the target system, preprocessing the real-time behavior data of the target object on the target system is prohibited; If the target type data exists in the real-time behavior data of the target object on the target system, the real-time behavior data of the target object on the target system is preprocessed according to a target processing method to obtain processed real-time behavior data, wherein the target processing method includes at least one of the following: a processing method for deleting data, a processing method for completing data, and a processing method for correcting data.

4. The method according to claim 2, characterized in that: Based on the frequency information of the target object purchasing the M target products in the target system, outputting the demand information of the target object includes: Based on the frequency information of the target object purchasing the M target products in the target system, determine S target products from the M target products, wherein the purchase frequency of each of the S target products is greater than a preset frequency, and S is a positive integer less than or equal to M; Based on the S target products, demand information of the target object is output.

5. The method according to claim 1, characterized in that Determining the recommendation list according to the demand information of the target object and the real-time behavior data of the target object on the target system includes: In combination with the recommendation algorithm, based on the demand information of the target object and the real-time behavior data of the target object on the target system, the M target products in the target system are screened to obtain the N target products; Based on the N target products, the recommendation list is determined.

6. The method according to claim 1, characterized in that Receiving a combination product determined by the target object based on the M target products in the target system includes: Determining an interaction interface for the target object to interact with the target system; A combination product determined by the target object based on the M target products in the target system is received through the interactive interface.

7. The method according to claim 1, characterized in that Recommending the combined product and the N target products in the recommendation list to the target object includes: Performing comparative analysis on the combination product and each target product in the recommendation list to obtain analysis results; Based on the analysis results, determining adjustment information for the combination product; The analysis results and adjustment information of the combination product are recommended to the target object.

8. A product recommendation device, characterized in that: include: A first acquisition unit is used to acquire real-time behavior data of a target object on a target system, wherein the target system includes at least M target products to be recommended to the target object, the M target products are products related to power supply and energy management, and M is a positive integer greater than 1; A first processing unit is used to input the real-time behavior data of the target object on the target system into a prediction model for processing, and output demand information of the target object, wherein the demand information is used to represent the product that the target object needs as predicted; A first determining unit is used to determine a recommendation list according to the demand information of the target object and the real-time behavior data of the target object on the target system, wherein the recommendation list at least includes information of N target products to be recommended to the target object, where N is a positive integer less than or equal to M; The second processing unit is configured to receive a combination product determined by the target object based on the M target products in the target system, and recommend the combination product and the N target products in the recommendation list to the target object.

9. A computer-readable storage medium, characterized in that: The storage medium stores a program, wherein the program executes the product recommendation method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the product recommendation method described in any one of claims 1 to 7.

Images