Marketing strategy generation method and system based on big data

Abstract

The invention relates to the technical field of marketing, in particular to a marketing strategy generation method and system based on big data. The method comprises the following steps: acquiring commodity data, analyzing the commodity data, and determining commodity attributes; determining a commodity use frequency according to the commodity attribute; determining a commodity use cycle according to the commodity use frequency; and determining a commodity marketing strategy according to the commodity use cycle. Therefore, enterprises can surpass the traditional marketing means, and especially have a greater breakthrough in the aspects of data acquisition, processing and analysis. An enterprise does not simply depend on experience and intuition, but uses massive data to obtain accurate decision support. Through multi-dimensional analysis of data such as sales records, use frequency and consumer behaviors of commodities, the use state and market demand change of the commodities are known in real time. Based on the use cycle and the purchase behavior of the commodity, the marketing activity can be quickly optimized according to data feedback.

Description

Technical Field

[0001] The present application relates to the field of marketing technology, and in particular to a marketing strategy generation method and system based on big data. Background Art

[0002] With the rapid development of big data technology and artificial intelligence technology, companies no longer rely on traditional experience and intuition when conducting marketing activities. Instead, they obtain more accurate marketing strategies and decision-making support through the collection and analysis of large amounts of data.

[0003] Traditional marketing methods usually set marketing strategies based on historical sales data, market research and consumer behavior analysis. However, these methods are usually unable to accurately capture the subtle differences in product attributes, real-time changes in consumer demand and the rapid development of market trends. Summary of the invention

[0004] The present application provides a marketing strategy generation method and system based on big data to solve the above problems.

[0005] In a first aspect, the present application provides a method for generating a marketing strategy based on big data, the method comprising: Acquire commodity data, analyze the commodity data, and determine commodity attributes; Determine the frequency of commodity usage based on the commodity attributes; Determine the commodity usage cycle according to the commodity usage frequency; Determine product marketing strategies based on product usage cycles.

[0006] Through this solution, the development of big data technology and artificial intelligence technology enables enterprises to surpass traditional marketing methods, especially in data collection, processing and analysis. Enterprises no longer rely solely on experience and intuition, but use massive data to obtain accurate decision-making support. Through multi-dimensional analysis of data such as sales records, usage frequency, consumer behavior, etc. of goods, enterprises can understand the usage status of goods and changes in market demand in real time. For example, the usage frequency and life cycle of goods can be accurately predicted through multiple data sources such as consumer purchase behavior, usage records, feedback, etc. Traditional methods cannot cope with the rapidly changing market, while big data technology can adjust marketing strategies through real-time analysis. Based on the usage cycle and purchasing behavior of goods, marketing activities can be quickly optimized based on data feedback. For example, some goods may need to increase the promotion intensity during a certain season or special promotion period, while the promotion frequency needs to be slowed down at other times.

[0007] Optionally, determining the commodity usage cycle according to the commodity usage frequency includes: Determine the basic characteristics of the product based on the product attributes. Analyze the basic characteristics of the product and determine the level of product reuse; The commodity usage cycle is determined according to the commodity reuse level and the commodity usage frequency.

[0008] Through this solution, analyzing the basic characteristics of the product, the possibility of repair, refurbishment or refilling of the product, and the frequency of use of the product will help determine the market positioning of the product, thereby more accurately predicting the product's use cycle and determining the role of the product in the lives of consumers. Comprehensively considering the basic characteristics of the product, the level of reuse and the actual frequency of use, predicting the product's use cycle will help to more accurately understand the product's market performance and consumer behavior, thereby formulating more scientific and effective marketing strategies.

[0009] Optionally, determining the commodity usage cycle according to the commodity reuse level and the commodity usage frequency includes: Determine the product functions and usage scenarios based on the basic characteristics of the product; Determine the single-use consumption of each product function according to the product usage scenario; Determine the useful life of the product based on the single-use consumption; The commodity usage cycle is determined according to the commodity reuse level, the commodity usage frequency and the commodity service life.

[0010] Through this solution, the basic characteristics of commodities are analyzed by natural language processing and machine learning technology, which can improve the accuracy of commodity characteristic analysis and quickly identify the functions and usage scenarios of commodities. It helps enterprises better understand consumers' demand for commodities and provide data support for product design and market positioning. According to the commodity usage scenario, the single-use consumption is calculated using sensor data and user behavior data, which can provide accurate commodity usage data and help understand the loss and performance of commodities. According to the single-use consumption, the service life of commodities is evaluated using statistical models and prediction algorithms, which can predict the expected life of commodities under normal use and help enterprises plan production and inventory management. Provide consumers with more accurate commodity usage guidance and improve customer satisfaction. Through user behavior data, the peak and trough periods of commodity use can be identified to understand the popularity of commodities in different time periods, help enterprises adjust production and marketing strategies, and provide data support for promotional activities, inventory management and supply chain optimization. Using big data analysis technology to analyze the frequency of commodity use patterns, it is possible to understand the role and usage habits of commodities in consumers' lives, provide a basis for product design and marketing strategies, and provide data support for personalized marketing and customer relationship management. Combining the level of product reuse, product lifespan and product usage frequency, predicting the product life cycle can provide data support for companies to formulate more accurate marketing strategies and optimize product design and supply chain management.

[0011] Optionally, determining the commodity usage frequency according to the commodity attribute includes: Acquiring commodity usage data according to the commodity attributes; Determining whether the product has been used within a preset time period according to the product usage data; If the commodity is used within a preset period of time, the commodity usage data is analyzed to determine the frequency of use of the commodity.

[0012] Through this solution, we can obtain comprehensive and real-time commodity usage data, gain an in-depth understanding of the characteristics and attributes of commodities, and provide a basis for subsequent frequency analysis. We can associate commodity attributes with usage data to analyze the usage of commodities with different attributes, discover the potential connection between commodity attributes and usage data, and provide data support for the formulation of marketing strategies. We can accurately calculate the number of times a commodity is used within a preset period of time to understand the usage of the commodity. We can identify the peak period, trough period, seasonal patterns, etc. of commodity usage, and understand the usage of commodities in different time periods. We can predict the future usage frequency of commodities and provide data support for enterprises to formulate more accurate marketing strategies.

[0013] Optionally, determining a product marketing strategy according to the product usage cycle includes: A commodity purchase record corresponding to the commodity data; Determine the time of commodity purchase according to the commodity purchase record; Determine the type of the product according to the product attributes; Determine the product promotion intensity corresponding to the product type according to the purchase time of the product and the usage cycle of the product; Determine the product marketing strategy based on the product promotion frequency.

[0014] Through this solution, the purchase time of goods is clarified, which helps to analyze purchasing behavior and purchase cycles, and provides a time benchmark for determining the use cycle of goods. Classification of product attributes helps to develop personalized marketing strategies for different types of goods. Understanding the use cycle of goods helps to predict the life cycle of goods and the time of re-purchase. According to the use cycle of goods, the appropriate promotion intensity is determined to maintain sales and market share, which helps to optimize promotion budgets and resource allocation. Analyzing the relationship between promotion frequency and sales data helps to evaluate the effectiveness of marketing activities and provide data support for adjusting promotion strategies and frequencies. According to the promotion intensity and promotion frequency of goods, personalized marketing strategies are developed to improve market competitiveness.

[0015] Optionally, determining the commodity promotion intensity corresponding to the commodity type according to the commodity purchase time and the commodity usage cycle includes: If the commodity is not used within a preset period of time, the commodity is determined to be an idle commodity; When there are idle commodities, determining commodity purchasing users according to commodity usage data of the idle commodities; Obtain the purchase record of the user who purchased the product; Analyze the purchase record to determine whether there is a similar product with a functional similarity to the idle product higher than a preset similarity; If so, obtain the purchase time of the similar product and the usage period of the similar product; The product promotion intensity corresponding to the product type is determined according to the product purchase time of the similar products and the product usage cycle of the similar products.

[0016] Through this solution, identifying unused goods helps companies understand the use of goods and potential problems. Provide targeted promotion strategies for subsequent idle goods. Clarifying the identity information of purchasing users helps analyze user purchasing behavior and preferences. Collecting the purchase records of purchasing users helps analyze user purchasing patterns and preferences. Provide a basis for subsequent product recommendations and cross-selling strategies. Analyze purchase records to determine whether there are similar products with functional similarity to idle goods that is higher than the preset similarity. Provide a basis for recommending similar products or formulating targeted marketing strategies. Understanding the market performance and consumer response of similar products helps predict the life cycle and re-purchase time of goods. Analyze the market performance and consumer response of similar products based on the purchase time and usage cycle. Determine the product promotion intensity corresponding to the product type based on the product attributes and usage cycle of idle goods. Formulate corresponding product promotion strategies based on the determined promotion intensity. Consider factors such as promotion channels, promotion content, and promotion frequency to achieve the best marketing effect.

[0017] Optionally, obtaining commodity usage data according to the commodity attributes includes: Determining commodity sales records based on the commodity data; Analyze the sales records of the commodities to determine the sales information; Analyze the sales information to determine the online account information; Obtaining usage authorization status according to the online account information; Based on the usage authorization and according to the commodity attributes, the commodity usage data is obtained.

[0018] Through this solution, we can analyze product sales records, determine sales trends, sales cycles, sales channels and other information, understand the market performance of products and consumer purchasing behavior, and provide a basis for formulating marketing strategies. We can analyze the online account information in sales records to determine the user's identity and purchasing behavior. Through user account information, we can understand the user's purchase history, preferences and purchase frequency, and provide data support for personalized marketing. The use authorization reflects the user's legal right and authority to use the product, which helps to ensure the security of data.

[0019] Optionally, after analyzing the purchase record to determine whether there is a similar product having a functional similarity with the idle commodity higher than a preset similarity, the method further includes: If it does not exist, determine the user-activatable channel based on the usage authorization; Analyze the user's activation channels and determine activation methods; Perform user activation according to the activation means, obtain user activation data in real time, and determine whether to adjust the activation means.

[0020] Through this solution, we can identify the channels through which users may activate idle goods, provide enterprises with potential user contact points, and the coverage and user acceptance of different channels, providing a basis for subsequent activation activities. We can evaluate the effects of different activation channels, which channels can reach users more effectively, and help select the most effective channels. According to the results of channel analysis, we can choose the most suitable activation means to ensure the effectiveness of activation activities. Through activation activities, we can increase users' attention to and willingness to use idle goods. Through data feedback, we can continuously optimize activation strategies, increase user activation rates, and enhance user experience.

[0021] Optionally, analyzing the user activation channels and determining activation means includes: Analyze the user's activation channels and determine the activation means; Determine the product highlights based on the basic characteristics of the product; Analyze the usage data of the product to determine the frequently used functions; Determine the functions that the user has not yet developed based on the product highlights and the frequently used functions; Determine the function promotion method based on the undeveloped functions of the user; Determine activation means based on the function promotion method and the activatable means.

[0022] Through this solution, we can identify and evaluate the channels through which users may activate idle goods, understand the coverage, user activity, cost and effect of different channels, and provide enterprises with potential user contact points so that they can choose the most appropriate channels. Determine the most suitable activation method based on the analysis results of user-activatable channels. Analyze the basic characteristics of the product, such as design, function, performance, etc., to determine the unique selling point or highlight of the product. Collect and analyze user usage data on the product to determine which functions are frequently used. Based on the highlights of the product and the high-frequency use functions, analyze the functions that users may not have fully developed or used. These functions may be hidden features or advanced functions of the product, which users may not know or are not accustomed to using, providing new entry points for activation strategies.

[0023] In a second aspect, the present application provides a marketing strategy generation system based on big data, the system comprising: A data analysis module, used to obtain commodity data, analyze the commodity data, and determine commodity attributes; A frequency determination module, used to determine the frequency of commodity usage according to the commodity attributes; A cycle determination module, used to determine a commodity usage cycle according to the commodity usage frequency; The strategy determination module is used to determine the product marketing strategy based on the product usage cycle. Optionally, when the cycle determination module determines the commodity usage cycle according to the commodity usage frequency, it is used to: Determine the basic characteristics of the product based on the product attributes. Analyze the basic characteristics of the product and determine the level of product reuse; The commodity usage cycle is determined according to the commodity reuse level and the commodity usage frequency.

[0024] Optionally, when the cycle determination module determines the commodity usage cycle according to the commodity reuse level and the commodity usage frequency, it is used to: Determine the product functions and usage scenarios based on the basic characteristics of the product; Determine the single-use consumption of each product function according to the product usage scenario; Determine the useful life of the product based on the single-use consumption; The commodity usage cycle is determined according to the commodity reuse level, the commodity usage frequency and the commodity service life.

[0025] Optionally, when the frequency determination module determines the commodity usage frequency according to the commodity attribute, it is used to: Acquiring commodity usage data according to the commodity attributes; Determining whether the product has been used within a preset time period according to the product usage data; If the commodity is used within a preset period of time, the commodity usage data is analyzed to determine the frequency of use of the commodity.

[0026] Optionally, when the strategy determination module determines the product marketing strategy according to the product usage cycle, it is used to: A commodity purchase record corresponding to the commodity data; Determine the time of commodity purchase according to the commodity purchase record; Determine the type of the product according to the product attributes; Determine the product promotion intensity corresponding to the product type according to the purchase time of the product and the usage cycle of the product; Determine the product marketing strategy based on the product promotion frequency.

[0027] Optionally, when the strategy determination module determines the commodity promotion intensity corresponding to the commodity type according to the commodity purchase time and the commodity usage cycle, it is used to: If the commodity is not used within a preset period of time, the commodity is determined to be an idle commodity; When there are idle commodities, determining commodity purchasing users according to commodity usage data of the idle commodities; Obtain the purchase record of the user who purchased the product; Analyze the purchase record to determine whether there is a similar product with a functional similarity to the idle product higher than a preset similarity; If so, obtain the purchase time of the similar product and the usage period of the similar product; The product promotion intensity corresponding to the product type is determined according to the product purchase time of the similar products and the product usage cycle of the similar products.

[0028] Optionally, when the frequency determination module obtains the commodity usage data according to the commodity attribute, it is used to: Determining commodity sales records based on the commodity data; Analyze the sales records of the commodities to determine the sales information; Analyze the sales information to determine the online account information; Obtaining usage authorization status according to the online account information; Based on the usage authorization and according to the commodity attributes, the commodity usage data is obtained.

[0029] Optionally, the marketing strategy generation system further includes a user activation module, which is used to: If it does not exist, determine the user-activatable channel based on the usage authorization; Analyze the user's activation channels and determine activation methods; Perform user activation according to the activation means, obtain user activation data in real time, and determine whether to adjust the activation means.

[0030] Optionally, when the user activation module analyzes the user activation channel and determines the activation means, it is used to: Analyze the user's activation channels and determine the activation means; Determine the product highlights based on the basic characteristics of the product; Analyze the usage data of the product to determine the frequently used functions; Determine the functions that the user has not yet developed based on the product highlights and the frequently used functions; Determine the function promotion method based on the undeveloped functions of the user; Determine activation means based on the function promotion method and the activatable means. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0032] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application; Figure 2 A flowchart of a marketing strategy generation method based on big data provided in one embodiment of the present application; Figure 3 A schematic diagram of the structure of a marketing strategy generation system based on big data provided in one embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0035] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0036] With the rapid development of big data technology and artificial intelligence technology, companies no longer rely on traditional experience and intuition when conducting marketing activities. Instead, they obtain more accurate marketing strategies and decision-making support through the collection and analysis of large amounts of data.

[0037] Traditional marketing methods usually set marketing strategies based on historical sales data, market research and consumer behavior analysis. However, these methods are usually unable to accurately capture the subtle differences in product attributes, real-time changes in consumer demand and the rapid development of market trends.

[0038] Based on this, the present application provides a marketing strategy generation method and system based on big data, which obtains commodity data, analyzes the commodity data, determines commodity attributes; determines the frequency of commodity use according to the commodity attributes; determines the commodity use cycle according to the commodity use frequency; and determines the commodity marketing strategy according to the commodity use cycle. The development of big data technology and artificial intelligence technology has enabled enterprises to surpass traditional marketing methods, especially in data collection, processing and analysis. Enterprises no longer rely solely on experience and intuition, but use massive data to obtain accurate decision support. Through multi-dimensional analysis of data such as sales records, usage frequency, and consumer behavior of commodities, enterprises can understand the usage status and market demand changes of commodities in real time. For example, the frequency of use and life cycle of commodities can be accurately predicted through multiple data sources such as consumer purchase behavior, usage records, and feedback. Traditional methods cannot cope with rapidly changing markets, while big data technology can adjust marketing strategies through real-time analysis. Based on the use cycle and purchasing behavior of commodities, marketing activities can be quickly optimized based on data feedback. For example, some commodities may need to increase the promotion intensity during a season or special promotion period, while the promotion frequency needs to be slowed down at other times.

[0039] Figure 1A schematic diagram of an application scenario provided for this application is used when an enterprise formulates a marketing strategy. Specifically, the method provided by this application is applied to any server, and the server interacts with the internal data management library of the enterprise to collect commodity data through the internal data management library of the enterprise. It helps to understand the market performance, user needs and market trends of commodities, and provide data support for subsequent analysis. Through data analysis and mining, key information such as the performance, user satisfaction, and sales trends of commodities can be discovered. It helps to identify the advantages and disadvantages of commodities and provide a basis for formulating targeted marketing strategies. By analyzing commodity data, the characteristics, functions, design, price and other attributes of commodities can be clarified. It helps to understand the differentiated characteristics of commodities and provide a basis for product positioning and market segmentation. By analyzing the data of users purchasing and using commodities, the frequency and habits of users using commodities can be understood. It helps to predict the demand and sales cycle of commodities and provide a basis for inventory management and supply chain optimization. By analyzing the frequency of commodity use and user feedback, the service life and replacement cycle of commodities can be determined. It helps to plan the life cycle management of products and provide a basis for new product development and listing strategies. Targeted marketing strategies can be formulated based on commodity attributes, frequency of use and cycle of use. It helps to improve the popularity and market share of the product, and increase sales and market share. The specific implementation method can refer to the following embodiments.

[0040] Figure 2 This is a flowchart of a method for generating a marketing strategy based on big data provided by an embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. Figure 2 As shown, the method includes: S201: Acquire product data, analyze the product data, and determine product attributes.

[0041] Product data can be all information related to a product, such as the product's name, description, price, inventory, sales records, user reviews, purchase history, usage records, etc.

[0042] Product attributes can be the inherent characteristics of a product, such as category, size, color, material, function, applicable scenarios, brand, etc.

[0043] Specifically, extracting effective information from massive amounts of product data and formulating appropriate marketing strategies based on the product's usage cycle, functional characteristics, and reuse level are still key challenges for current technology. Key parameters such as product usage frequency and usage cycle are usually affected by multiple factors such as consumer purchasing behavior, product functional characteristics, and changes in market demand. The interaction of these factors requires precise algorithms and models to analyze. Obtain product data from the company's internal data management library, including sales records, user behavior data, market research data, etc. Integrate data from different channels to ensure data consistency and accuracy. Clean data to remove noise and inconsistent data points. Convert data formats to make it suitable for subsequent analysis and processing. Use natural language processing and machine learning techniques to analyze text data such as product descriptions and user comments to extract key attributes of products.

[0044] S202: Determine the commodity usage frequency according to commodity attributes.

[0045] The frequency of product usage can be the average number of times a consumer uses a product within a certain period of time.

[0046] Specifically, the frequency of product usage is one of the key factors affecting its life cycle and marketing strategy. Traditional methods often rely on experience and cannot understand the usage of products in real time. Through big data analysis, more accurate product usage data can be obtained. Through user purchase records collected by e-commerce platforms or retailers, analyze the frequency of consumers purchasing a certain product. Obtain the actual frequency of product usage through smart devices, mobile applications, IoT (Internet of Things) technology, etc. For example, smart home appliances can feedback their usage data in real time through networking. Collect user feedback on product usage frequency and satisfaction through social media, evaluation systems and other channels.

[0047] S203: Determine the commodity usage cycle according to the commodity usage frequency.

[0048] The product life cycle can be the entire time interval from the time the consumer purchases the product to the time the product is no longer used or needs to be replaced.

[0049] Specifically, the product life cycle is the basis for determining product marketing strategies. The frequency of product use is closely related to its life cycle. For example, some products may be high-frequency and short-term consumer goods, while others may be low-frequency durable goods. By analyzing the frequency of product use, the product life cycle can be predicted. High-frequency used products may have a shorter life cycle, while low-frequency used products may have a longer life cycle. Factors such as the function and durability of the product will also affect its life cycle. For example, durable electrical appliances tend to have a longer life cycle, while disposable consumer goods have a shorter life cycle.

[0050] S204. Determine the product marketing strategy based on the product usage cycle.

[0051] A product marketing strategy can be a series of planned, purposeful actions and plans taken by a business to promote and sell its products.

[0052] Specifically, the life cycle of a product directly affects the formulation of its marketing strategy. Traditional marketing methods usually formulate promotion plans based on static data, while big data methods can dynamically adjust strategies based on the life cycle of the product. When a product is nearing the end of its life cycle, it can be stimulated to buy through promotions, discounts, and other means; while in the early stages of the product life cycle, it can be used to attract consumers by increasing awareness and exposure. Based on big data technology, the sales and use of products can be monitored in real time, and the marketing intensity of the products can be adjusted. If it is found that the frequency of use of a product decreases during a certain period of time, the promotion method can be adjusted.

[0053] Through this solution, the development of big data technology and artificial intelligence technology enables enterprises to surpass traditional marketing methods, especially in data collection, processing and analysis. Enterprises no longer rely solely on experience and intuition, but use massive data to obtain accurate decision-making support. Through multi-dimensional analysis of data such as sales records, usage frequency, consumer behavior, etc. of goods, enterprises can understand the usage status of goods and changes in market demand in real time. For example, the usage frequency and life cycle of goods can be accurately predicted through multiple data sources such as consumer purchase behavior, usage records, feedback, etc. Traditional methods cannot cope with the rapidly changing market, while big data technology can adjust marketing strategies through real-time analysis. Based on the usage cycle and purchasing behavior of goods, marketing activities can be quickly optimized based on data feedback. For example, some goods may need to increase the promotion intensity during a certain season or special promotion period, while the promotion frequency needs to be slowed down at other times.

[0054] In some embodiments, the basic characteristics of the product are determined based on the product attributes, and the basic characteristics of the product are analyzed to determine the level of reuse of the product; the use cycle of the product is determined based on the level of reuse of the product and the frequency of use of the product.

[0055] The basic characteristics of a product may be the inherent attributes and characteristics of the product, such as function, design, material, durability, maintainability, upgradeability, environmental protection characteristics, etc.

[0056] The level of product reuse can be the ability of a product to be reused or repurposed, such as repairability, refurbishability, shareability, upgradeability, modular design, etc.

[0057] Specifically, based on the attributes of the goods, identify the basic characteristics of the goods, such as whether they are consumables, whether parts need to be replaced regularly, whether they are upgradeable, etc. Analyze the possibility of reusing the goods based on whether the goods are repairable, refurbishable, or refillable. Collect data on the frequency of use of goods from channels such as sales records, user feedback, and after-sales service data. Analyze the frequency of use of goods and determine the role of the goods in consumers' lives, such as daily necessities, seasonal goods, and goods used on special occasions. Identify patterns and trends in the frequency of use of goods, such as peak periods, trough periods, etc. Comprehensively consider the basic characteristics of the goods, the level of reuse, and the actual frequency of use to predict the use cycle of the goods.

[0058] Through this solution, analyzing the basic characteristics of the product, the possibility of repair, refurbishment or refilling of the product, and the frequency of use of the product will help determine the market positioning of the product, thereby more accurately predicting the product's use cycle and determining the role of the product in the lives of consumers. Comprehensively considering the basic characteristics of the product, the level of reuse and the actual frequency of use, predicting the product's use cycle will help to more accurately understand the product's market performance and consumer behavior, thereby formulating more scientific and effective marketing strategies.

[0059] In some embodiments, the functions of the goods and the usage scenarios of the goods are determined based on the basic characteristics of the goods; the single-use consumption of each function of the goods is determined based on the usage scenarios of the goods; the service life of the goods is determined based on the single-use consumption; the use cycle of the goods is determined based on the reuse level of the goods, the frequency of use of the goods and the service life of the goods.

[0060] Product functions can be specific uses or capabilities of a product.

[0061] The product usage scenario can be the specific environment and conditions in which consumers use the product in real life.

[0062] Single-use consumption can be the resources or materials consumed by a product or its components during one use of the product, such as the amount of ink consumed by a printer's ink cartridge each time it prints, or the amount of fuel consumed by a car each time it drives.

[0063] The useful life of a product can be the length of time that the product can maintain its functionality and reliability under normal use and maintenance conditions.

[0064] Specifically, natural language processing and machine learning technologies are used to analyze the basic characteristics of products and extract the functions and usage scenarios of products. According to the usage scenarios of products, sensor data and user behavior data are used to accurately calculate the consumption of products in specific scenarios, so as to analyze the single-use consumption of each product function, such as battery life, consumables consumption, etc. Based on single-use consumption, statistical models and prediction algorithms are used to evaluate the service life of products. Through user behavior data, the peak and trough periods of product use and possible reasons are identified. Big data analysis technology is used to analyze the frequency of product use patterns, such as daily use, seasonal use, and use on special occasions. Combining the level of product reuse, product service life, and product usage frequency, time series analysis and machine learning models are used to predict the use cycle of products.

[0065] Evaluation of product life: By calculating statistics such as mean, median, and standard deviation, the basic characteristics of data such as product usage frequency and single-use consumption are described. A relationship model between product life and factors such as usage frequency and single-use consumption is established to predict the average life of the product. Recurrent neural networks (RNNs) can also be used to predict product life by learning time series data on product usage frequency.

[0066] Through this solution, the basic characteristics of commodities are analyzed by natural language processing and machine learning technology, which can improve the accuracy of commodity characteristic analysis and quickly identify the functions and usage scenarios of commodities. It helps enterprises better understand consumers' demand for commodities and provide data support for product design and market positioning. According to the commodity usage scenario, the single-use consumption is calculated using sensor data and user behavior data, which can provide accurate commodity usage data and help understand the loss and performance of commodities. According to the single-use consumption, the service life of commodities is evaluated using statistical models and prediction algorithms, which can predict the expected life of commodities under normal use and help enterprises plan production and inventory management. Provide consumers with more accurate commodity usage guidance and improve customer satisfaction. Through user behavior data, the peak and trough periods of commodity use can be identified to understand the popularity of commodities in different time periods, help enterprises adjust production and marketing strategies, and provide data support for promotional activities, inventory management and supply chain optimization. Using big data analysis technology to analyze the frequency of commodity use patterns, it is possible to understand the role and usage habits of commodities in consumers' lives, provide a basis for product design and marketing strategies, and provide data support for personalized marketing and customer relationship management. Combining the level of product reuse, product lifespan and product usage frequency, predicting the product life cycle can provide data support for companies to formulate more accurate marketing strategies and optimize product design and supply chain management.

[0067] In some embodiments, commodity usage data is obtained based on commodity attributes; based on the commodity usage data, it is determined whether the commodity is used within a preset time period; if the commodity is used within the preset time period, the commodity usage data is analyzed to determine the frequency of commodity use.

[0068] Product usage data can be detailed records and information about how consumers use products, such as usage time, usage frequency, usage duration, usage pattern, user behavior, consumption data, etc.

[0069] The preset time period may be a preset time range for analyzing or evaluating the usage pattern of the product and stored in a preset database.

[0070] Specifically, use machine learning algorithms, such as classification and clustering, to classify and group products according to product attributes. Associate product attributes with usage data to analyze the usage of products with different attributes. Use data mining techniques, such as association rule learning, to find potential connections between product attributes and usage data. Based on product usage data, calculate the number of times each product is used within a preset time period. Use time series analysis technology to analyze the changing trend of product usage frequency over time. Use pattern recognition algorithms to identify peak periods, trough periods, seasonal patterns, etc. for product usage. If the product is used within a preset time period, analyze user behavior data to understand the usage and reasons of the product in different time periods. Use prediction models, such as time series prediction models, machine learning prediction models, etc., to predict future product usage frequencies.

[0071] Through this solution, we can obtain comprehensive and real-time commodity usage data, gain an in-depth understanding of the characteristics and attributes of commodities, and provide a basis for subsequent frequency analysis. We can associate commodity attributes with usage data to analyze the usage of commodities with different attributes, discover the potential connection between commodity attributes and usage data, and provide data support for the formulation of marketing strategies. We can accurately calculate the number of times a commodity is used within a preset period of time to understand the usage of the commodity. We can identify the peak period, trough period, seasonal patterns, etc. of commodity usage, and understand the usage of commodities in different time periods. We can predict the future usage frequency of commodities and provide data support for enterprises to formulate more accurate marketing strategies.

[0072] In some embodiments, based on the commodity purchase record corresponding to the commodity data; determining the commodity purchase time based on the commodity purchase record; determining the commodity type based on the commodity attributes; determining the commodity promotion intensity corresponding to the commodity type based on the commodity purchase time and the commodity usage cycle; and determining the commodity marketing strategy based on the commodity promotion frequency.

[0073] The commodity purchase record may be a data set that records relevant information about the consumer's purchase of commodities, such as purchase date and time, purchase quantity, purchase price, purchase channel, and customer information.

[0074] The commodity purchase time may be the specific date and time when the consumer purchases the commodity.

[0075] Product type can be classified according to specific attributes or characteristics of the product, such as product category, product brand, product price range, product function or purpose.

[0076] Product promotion intensity can be the strength of a company's promotion of a specific product in its marketing activities, such as the size of the promotion budget, the scale and frequency of promotion activities, the choice of promotion channels (such as online advertising, social media, offline activities, etc.), and the attractiveness of the promotion content.

[0077] Product promotion frequency can be the number of times a specific product is promoted within a certain period of time.

[0078] Specifically, collect product purchase record data from e-commerce platforms, sales systems, customer relationship management systems (CRM) and other channels. Clean the data to remove erroneous, duplicate or incomplete data records. Integrate data from different sources to ensure data consistency and accuracy. Extract the purchase time of the product from the purchase record to analyze the purchase behavior and purchase cycle. Classify the products into different types according to product attributes (such as price, function, purpose, etc.). Use machine learning techniques such as clustering algorithms or decision trees to classify products. Analyze product purchase records to determine the average use cycle and life cycle of the products. Use methods such as time series analysis or survival analysis to predict the use cycle of products. Determine the promotion intensity of different products based on product type and use cycle. For example, for products with a shorter use cycle, more frequent promotion may be required to maintain sales. Analyze the promotion frequency of different products, including the number of advertisements, the frequency of promotional activities, etc. Use statistical methods to analyze the relationship between promotion frequency and sales data. Develop personalized marketing strategies based on the promotion intensity and promotion frequency of products. Consider factors such as seasonality, holidays, and market trends to adjust marketing strategies.

[0079] Through this solution, the purchase time of goods is clarified, which helps to analyze purchasing behavior and purchase cycles, and provides a time benchmark for determining the use cycle of goods. Classification of product attributes helps to develop personalized marketing strategies for different types of goods. Understanding the use cycle of goods helps to predict the life cycle of goods and the time of re-purchase. According to the use cycle of goods, the appropriate promotion intensity is determined to maintain sales and market share, which helps to optimize promotion budgets and resource allocation. Analyzing the relationship between promotion frequency and sales data helps to evaluate the effectiveness of marketing activities and provide data support for adjusting promotion strategies and frequencies. According to the promotion intensity and promotion frequency of goods, personalized marketing strategies are developed to improve market competitiveness.

[0080] In some embodiments, the product promotion intensity corresponding to the product type is determined based on the purchase time and the product usage cycle, including: if the product is not used within a preset time period, the product is determined to be an idle product; when there are idle products, the user who purchased the product is determined based on the product usage data of the idle products; the purchase record of the user who purchased the product is obtained; the purchase record is analyzed to determine whether there are similar products whose functional similarity with the idle products is higher than a preset similarity; if so, the product purchase time and the product usage cycle of the similar products are obtained; the product promotion intensity corresponding to the product type is determined based on the product purchase time and the product usage cycle of the similar products.

[0081] Idle goods may be those that have not been used by consumers within a preset period of time. The reasons for non-use are: consumers are not satisfied with the functions of the goods, the goods do not meet consumers' expectations, consumers have forgotten the existence of the goods, and the goods need to be used in conjunction with other accessories or equipment, but the accessories or equipment are missing.

[0082] The preset similarity can be a threshold set for analyzing the similarity between products, and is used to determine whether two products are similar enough in terms of function, use, price, etc., so as to formulate further marketing strategies.

[0083] Similar products can be other products that have a high degree of similarity with idle goods in terms of function, purpose, price, etc.

[0084] Specifically, if a product is not used within a preset period of time, it will be marked as an idle product. Based on the purchase record of the idle product, determine the identity information of the purchasing user. Collect the purchase record of the purchasing user, including all purchased products and their purchase time. Analyze the purchase records to determine whether there are similar products with functional similarity to the idle product that is higher than the preset similarity. If there are similar products, obtain the purchase time and usage cycle data of the similar products. Analyze the market performance and consumer response of similar products based on the purchase time and usage cycle. Determine the product promotion intensity corresponding to the product type in combination with the product attributes and usage cycle of the idle product. Formulate corresponding product promotion strategies based on the determined promotion intensity.

[0085] Through this solution, identifying unused goods helps companies understand the use of goods and potential problems. Provide targeted promotion strategies for subsequent idle goods. Clarifying the identity information of purchasing users helps analyze user purchasing behavior and preferences. Collecting the purchase records of purchasing users helps analyze user purchasing patterns and preferences. Provide a basis for subsequent product recommendations and cross-selling strategies. Analyze purchase records to determine whether there are similar products with functional similarity to idle goods that is higher than the preset similarity. Provide a basis for recommending similar products or formulating targeted marketing strategies. Understanding the market performance and consumer response of similar products helps predict the life cycle and re-purchase time of goods. Analyze the market performance and consumer response of similar products based on the purchase time and usage cycle. Determine the product promotion intensity corresponding to the product type based on the product attributes and usage cycle of idle goods. Formulate corresponding product promotion strategies based on the determined promotion intensity. Consider factors such as promotion channels, promotion content, and promotion frequency to achieve the best marketing effect.

[0086] In some embodiments, obtaining commodity usage data based on commodity attributes includes: determining commodity sales records based on commodity data; analyzing commodity sales records to determine sales information; analyzing sales information to determine online account information; obtaining usage authorization status based on the online account information; and obtaining commodity usage data based on commodity attributes based on the usage authorization status.

[0087] A product sales record may be a detailed data set that records product sales-related information, such as product ID or number, sales time (date and time), sales quantity, sales price, sales channel (such as online, offline, specific store, etc.), transaction ID or order number.

[0088] Sales information can be data extracted from commodity sales records and used to analyze sales conditions, such as total sales, sales growth rate, sales volume, sales ranking, sales trend, and sales area distribution.

[0089] Online account information may be user account information related to Internet services or platforms, such as user name, registered email address, registered mobile phone number, user ID, user level or points, and other information associated with the account (such as payment method, address book, etc.).

[0090] The authorization status may be the user's legal rights and conditions for using goods or services, such as authorization type (such as permanent authorization, temporary authorization, per-time authorization, etc.), authorization period (start and end date), authorization scope (such as region, number of devices, etc.), authorized functions (such as full functions, partial functions, etc.), and authorization conditions.

[0091] Specifically, based on the product data, determine the sales records of the product, such as product ID, sales time, sales quantity, sales price, etc., analyze the product sales records, and determine sales information such as sales trends, sales cycles, and sales channels. Analyze the online account information in the sales records to determine the user's identity and purchase behavior. Understand the user's purchase history, preferences, and purchase frequency through user account information. Based on the online account information, obtain the user's use authorization, such as authorization time, authorization type, authorization scope, etc. Based on the use authorization, obtain the product usage data, such as usage time, usage frequency, usage pattern, etc.

[0092] Through this solution, we can analyze product sales records, determine sales trends, sales cycles, sales channels and other information, understand the market performance of products and consumer purchasing behavior, and provide a basis for formulating marketing strategies. We can analyze the online account information in sales records to determine the user's identity and purchasing behavior. Through user account information, we can understand the user's purchase history, preferences and purchase frequency, and provide data support for personalized marketing. The use authorization reflects the user's legal right and authority to use the product, which helps to ensure the security of data.

[0093] In some embodiments, after analyzing the purchase records to determine whether there are similar products with functional similarity to the idle goods higher than a preset similarity, it also includes: if not, determining the user activation channel based on the use authorization situation; analyzing the user activation channel to determine the activation means; activating the user based on the activation means, and obtaining user activation data in real time to determine whether to adjust the activation means.

[0094] User activation channels can be the channels or platforms through which users can be contacted to activate idle goods or services.

[0095] Activation means can be the specific method or strategy used to activate the product.

[0096] User activation data may be a collection of data about user activation behavior.

[0097] Specifically, if it does not exist, analyze the purchase records and usage authorization status to determine which channels the user may use to activate the idle goods. Analyze each activatable channel and evaluate its coverage, user acceptance, activation success rate and other factors. Determine the advantages and disadvantages of each channel in order to select the most effective activation method. Determine the best activation method based on the analysis results of the user's activatable channels. Perform user activation activities based on the determined activation method. Communicate with users through emails, text messages, application push, phone calls, etc. to guide users to activate idle goods. During the user activation process, collect user activation data in real time, such as activation time, activation method, user feedback, etc. Based on the real-time user activation data obtained, evaluate the effectiveness of the activation method. If the activation effect is not ideal, adjust the activation method based on data feedback to improve the user activation rate.

[0098] Through this solution, we can identify the channels through which users may activate idle goods, provide enterprises with potential user contact points, and the coverage and user acceptance of different channels, providing a basis for subsequent activation activities. We can evaluate the effects of different activation channels, which channels can reach users more effectively, and help select the most effective channels. According to the results of channel analysis, we can choose the most suitable activation means to ensure the effectiveness of activation activities. Through activation activities, we can increase users' attention to and willingness to use idle goods. Through data feedback, we can continuously optimize activation strategies, increase user activation rates, and enhance user experience.

[0099] In some embodiments, analyzing user activatable channels and determining activation means include: analyzing user activatable channels and determining activation means; determining product highlights based on basic product characteristics; analyzing product usage data and determining frequently used functions; determining user undeveloped functions based on product highlights and frequently used functions; determining function promotion methods based on user undeveloped functions; and determining activation means based on function promotion methods and activatable means.

[0100] The activatable means may be various measures or methods that can be taken to motivate or guide users to activate idle goods or services.

[0101] Product highlights can be the unique selling points or features of a product that can attract users and generate their interest.

[0102] High-frequency use functions may be product functions that are frequently used by users in daily use.

[0103] Unexplored user features may be features of a product that are not yet fully used or understood by users.

[0104] Functional promotion methods can be methods or channels used to promote product functions.

[0105] Specifically, collect and analyze data on the channels through which users may activate idle goods.

[0106] Evaluate the user coverage, user activity, channel costs and effects of each channel. The cost-effectiveness, user acceptance and potential activation success rate of different activation methods, so determine the most suitable activation method based on the analysis results of user-activatable channels. Highlights are usually an important factor in attracting users and can be used to formulate activation strategies. It is necessary to analyze the basic characteristics of the product, such as design, function, performance, etc., to determine the unique selling point or highlight of the product. Collect and analyze user usage data on the product to determine which functions are frequently used. Based on the product highlights and high-frequency used functions, analyze the functions that users may not have fully developed or used. Based on the functions that users have not developed, determine how to promote and introduce these functions to users. Combine the function promotion method and the activatable means to determine the final activation method. Ensure that the activation method can effectively convey the information of product highlights and undeveloped functions to attract users to activate.

[0107] Through this solution, we can identify and evaluate the channels through which users may activate idle goods, understand the coverage, user activity, cost and effect of different channels, and provide enterprises with potential user contact points so that they can choose the most appropriate channels. Determine the most suitable activation method based on the analysis results of user-activatable channels. Analyze the basic characteristics of the product, such as design, function, performance, etc., to determine the unique selling point or highlight of the product. Collect and analyze user usage data on the product to determine which functions are frequently used. Based on the highlights of the product and the high-frequency use functions, analyze the functions that users may not have fully developed or used. These functions may be hidden features or advanced functions of the product, which users may not know or are not accustomed to using, providing new entry points for activation strategies.

[0108] Figure 3 A schematic diagram of a marketing strategy generation system based on big data provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the marketing strategy generation system 300 based on big data of this embodiment includes: a data analysis module 301 , a frequency determination module 302 , a cycle determination module 303 , and a strategy determination module 304 .

[0109] The data analysis module 301 is used to obtain commodity data, analyze the commodity data, and determine commodity attributes; A frequency determination module 302, used to determine the frequency of commodity usage according to the commodity attributes; A cycle determination module 303, used to determine a commodity usage cycle according to the commodity usage frequency; The strategy determination module 304 is used to determine the product marketing strategy according to the product usage cycle. Optionally, when the cycle determination module 303 determines the commodity usage cycle according to the commodity usage frequency, it is used to: Determine the basic characteristics of the product based on the product attributes. Analyze the basic characteristics of the product and determine the level of product reuse; The commodity usage cycle is determined according to the commodity reuse level and the commodity usage frequency.

[0110] Optionally, when the cycle determination module 303 determines the commodity usage cycle according to the commodity reuse level and the commodity usage frequency, it is used to: Determine the product functions and usage scenarios based on the basic characteristics of the product; Determine the single-use consumption of each product function according to the product usage scenario; Determine the useful life of the product based on the single-use consumption; The commodity usage cycle is determined according to the commodity reuse level, the commodity usage frequency and the commodity service life.

[0111] Optionally, when the frequency determination module 302 determines the commodity usage frequency according to the commodity attribute, it is used to: Acquiring commodity usage data according to the commodity attributes; Determining whether the product has been used within a preset time period according to the product usage data; If the commodity is used within a preset period of time, the commodity usage data is analyzed to determine the frequency of use of the commodity.

[0112] Optionally, when the strategy determination module 304 determines the product marketing strategy according to the product usage cycle, it is used to: A commodity purchase record corresponding to the commodity data; Determine the time of commodity purchase according to the commodity purchase record; Determine the type of the product according to the product attributes; Determine the product promotion intensity corresponding to the product type according to the purchase time of the product and the usage cycle of the product; Determine the product marketing strategy based on the product promotion frequency.

[0113] Optionally, when the strategy determination module 304 determines the commodity promotion intensity corresponding to the commodity type according to the commodity purchase time and the commodity usage cycle, it is used to: If the commodity is not used within a preset period of time, the commodity is determined to be an idle commodity; When there are idle commodities, determining commodity purchasing users according to commodity usage data of the idle commodities; Obtain the purchase record of the user who purchased the product; Analyze the purchase record to determine whether there is a similar product with a functional similarity to the idle product higher than a preset similarity; If so, obtain the purchase time of the similar product and the usage period of the similar product; The product promotion intensity corresponding to the product type is determined according to the product purchase time of the similar products and the product usage cycle of the similar products.

[0114] Optionally, when the frequency determination module 304 obtains the commodity usage data according to the commodity attribute, it is used to: Determining commodity sales records based on the commodity data; Analyze the sales records of the commodities to determine the sales information; Analyze the sales information to determine the online account information; Obtaining usage authorization status according to the online account information; Based on the usage authorization and according to the commodity attributes, the commodity usage data is obtained.

[0115] Optionally, the marketing strategy generation system 300 further includes a user activation module 305, which is used to: If it does not exist, determine the user-activatable channel based on the usage authorization; Analyze the user's activation channels and determine activation methods; Perform user activation according to the activation means, obtain user activation data in real time, and determine whether to adjust the activation means.

[0116] Optionally, when the user activation module 305 analyzes the user activatable channels and determines the activation means, it is used to: Analyze the user's activation channels and determine the activation means; Determine the product highlights based on the basic characteristics of the product; Analyze the usage data of the product to determine the frequently used functions; Determine the functions that the user has not yet developed based on the product highlights and the frequently used functions; Determine the function promotion method based on the undeveloped functions of the user; Determine activation means based on the function promotion method and the activatable means.

[0117] The system of this embodiment can be used to execute the method of any of the above embodiments. The implementation principles and technical effects are similar and will not be described in detail here.

Claims

1. A marketing strategy generation method based on big data, characterized in that: include: Acquire commodity data, analyze the commodity data, and determine commodity attributes; Determine the frequency of commodity usage based on the commodity attributes; Determine the commodity usage cycle according to the commodity usage frequency; Determine product marketing strategies based on product usage cycles.

2. The method according to claim 1, characterized in that Determining the commodity usage cycle according to the commodity usage frequency includes: Determine the basic characteristics of the product based on the product attributes. Analyze the basic characteristics of the product and determine the level of product reuse; The commodity usage cycle is determined according to the commodity reuse level and the commodity usage frequency.

3. The method according to claim 2, characterized in that The determining of the commodity usage cycle according to the commodity reuse level and the commodity usage frequency includes: Determine the product functions and usage scenarios based on the basic characteristics of the product; Determine the single-use consumption of each product function according to the product usage scenario; Determine the useful life of the product based on the single-use consumption; The commodity usage cycle is determined according to the commodity reuse level, the commodity usage frequency and the commodity service life.

4. The method according to claim 2, characterized in that: The determining the commodity usage frequency according to the commodity attribute includes: Acquiring commodity usage data according to the commodity attributes; Determining whether the product has been used within a preset time period according to the product usage data; If the commodity is used within a preset period of time, the commodity usage data is analyzed to determine the frequency of use of the commodity.

5. The method according to claim 4, characterized in that Determining the product marketing strategy based on the product usage cycle includes: A commodity purchase record corresponding to the commodity data; Determine the time of commodity purchase according to the commodity purchase record; Determine the type of product according to the product attributes; Determine the product promotion intensity corresponding to the product type according to the purchase time of the product and the use cycle of the product; Determine the product marketing strategy based on the product promotion intensity.

6. The method according to claim 5, characterized in that The determining, according to the purchase time of the commodity and the usage cycle of the commodity, the commodity promotion intensity corresponding to the commodity type includes: If the commodity is not used within a preset period of time, the commodity is determined to be an idle commodity; When there are idle commodities, determining commodity purchasing users according to commodity usage data of the idle commodities; Obtain the purchase record of the user who purchased the product; Analyze the purchase record to determine whether there is a similar product with a functional similarity to the idle product higher than a preset similarity; If so, obtain the purchase time of the similar product and the usage period of the similar product; The product promotion intensity corresponding to the product type is determined according to the product purchase time of the similar products and the product usage cycle of the similar products.

7. The method according to claim 6, characterized in that The obtaining of commodity usage data according to the commodity attributes includes: Determining commodity sales records based on the commodity data; Analyze the sales records of the commodities to determine the sales information; Analyze the sales information to determine the online account information; Obtaining usage authorization status according to the online account information; Based on the usage authorization and according to the commodity attributes, the commodity usage data is obtained.

8. The method according to claim 7, characterized in that After analyzing the purchase record to determine whether there is a similar product with a functional similarity to the idle product higher than a preset similarity, the method further includes: If it does not exist, determine the user-activatable channel based on the usage authorization; Analyze the user's activation channels and determine activation methods; Perform user activation according to the activation means, obtain user activation data in real time, and determine whether to adjust the activation means.

9. The method according to claim 8, characterized in that The analyzing the user activation channels and determining the activation means includes: Analyze the user's activation channels and determine the activation means; Determine the product highlights based on the basic characteristics of the product; Analyze the usage data of the product to determine the frequently used functions; Determine the functions that the user has not yet developed based on the product highlights and the frequently used functions; Determine the function promotion method based on the undeveloped functions of the user; Determine activation means based on the function promotion method and the activatable means.

10. A marketing strategy generation system based on big data, characterized in that: include: A data analysis module, used to obtain commodity data, analyze the commodity data, and determine commodity attributes; A frequency determination module, used to determine the frequency of commodity usage according to the commodity attributes; A cycle determination module, used to determine a commodity usage cycle according to the commodity usage frequency; The strategy determination module is used to determine the product marketing strategy based on the product usage cycle.

Images