Multi-dimensional commodity sorting method and system based on multi-thread processing

Abstract

The invention discloses a multi-dimensional commodity sorting method and system based on multi-thread processing, and relates to the technical field of computer platform load balancing, and the method comprises the steps: carrying out the collection of commodity sales data, carrying out the data segmentation construction, and carrying out the batch processing through a multi-thread technology; evaluating the market response of the commodity by adopting an optimized comprehensive scoring model and considering the gross profit contribution degree, the sales volume, the annual accumulated sales volume, the discount strength, the commodity label and the promotion policy; and the system sorts the commodities according to the comprehensive score, and periodically updates and dynamically adjusts the score dimension. The multi-dimensional commodity sorting method based on multi-thread processing provided by the invention not only considers the sales volume, but also combines various factors such as gross profit and promotion policies to evaluate more comprehensively, updates the ranking according to the latest sales data, and ensures the timeliness of the ranking. Manual weight adjustment is allowed, and response can be quickly made according to market changes.

Description

Technical Field

[0001] The present invention relates to the technical field of commodity sorting, and in particular to a multi-dimensional commodity sorting method and system based on multi-threaded processing. Background Art

[0002] In modern retail, the display and promotion of goods are crucial to attracting customers. In order to better optimize the display of goods, improve customer satisfaction and promote sales, an algorithm that can comprehensively consider multiple factors to sort goods is needed. This algorithm should not only consider the sales volume of goods, but also other important factors such as gross profit contribution, promotional activities, and product labels. Due to the wide variety of goods and huge amount of data, the traditional single-threaded processing method is difficult to meet the real-time and performance requirements, so an efficient data processing solution is needed.

[0003] There are some product recommendation systems or product ranking algorithms on the market, which usually rank products based on single or several factors such as sales volume, user reviews, click-through rate, etc. Although these systems can provide basic product recommendation functions, they are still insufficient in multi-dimensional comprehensive evaluation.

[0004] Existing technologies mainly rely on a single indicator or a few indicators to sort products. For example, some systems only sort products based on sales, while others may combine sales and user reviews. These technologies often use simple statistical methods, such as average calculation, percentage ranking, etc., to sort. Considering only a single indicator such as sales or user reviews cannot fully reflect the value of the product. The weight setting is usually fixed and cannot be flexibly adjusted according to market changes. It fails to perform differentiated sorting according to the market characteristics of different cities or regions. When processing large-scale data, single-threaded processing is inefficient, affecting user experience. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: the existing commodity ranking method only considers single indicators such as sales volume or user evaluation, fails to fully reflect the value of the commodity, the weight setting is usually fixed and cannot be flexibly adjusted according to market changes, fails to perform differentiated ranking according to the market characteristics of different cities or regions, and how to quickly process large-scale data to improve user experience.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-dimensional commodity sorting method based on multi-threaded processing, including collecting commodity sales data, segmenting and constructing data, and processing them in batches through multi-threaded technology. An optimized comprehensive scoring model is adopted to evaluate the market response of commodities by considering gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, commodity labels and promotion policies. The system sorts commodities according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions.

[0008] As a preferred solution of the multi-dimensional commodity sorting method based on multi-threaded processing described in the present invention, wherein: the commodity sales data collection includes data collection, and three types of data collection are performed. The first type collects the annual sales volume, sales volume, monthly sales volume and sales volume nationwide, and collects the annual sales volume, sales volume, monthly sales volume and sales volume of each city.

[0009] The second type of data collects commodity classification data and divides sales data into different commodity categories, which are divided into annual sales and monthly sales.

[0010] The third type of data collection is based on the product model SPU, including the selling price, cost, market average price, marketing topic tags and discount coefficient of the single product.

[0011] As a preferred solution of the multi-dimensional commodity sorting method based on multi-threaded processing described in the present invention, wherein: the commodity sales data collection includes data collection, and three types of data collection are performed. The first type collects the annual sales volume, sales volume, monthly sales volume and sales volume nationwide, and collects the annual sales volume, sales volume, monthly sales volume and sales volume of each city.

[0012] The second type of data collects commodity classification data and divides sales data into different commodity categories, which are divided into annual sales and monthly sales.

[0013] The third type of data collection is based on the product model SPU, including the selling price, cost, market average price, marketing topic tags and discount coefficient of the single product.

[0014] As a preferred solution of the multi-dimensional commodity sorting method based on multi-threaded processing described in the present invention, wherein: the data segmentation and construction and batch processing by multi-threaded technology also include the system using Java's ExecutorService to create a thread pool, and the segmented data subsets are processed in parallel by multi-threaded technology. Each thread is responsible for processing an independent data subset. After each thread is processed, the system processes the sub-results generated by each thread through a ConcurrentHashMap data structure to store the intermediate results.

[0015] Use Java's concurrency tool ExecutorService to manage threads, track the execution of asynchronous tasks through Future objects, and manage thread lifecycles.

[0016] As a preferred solution of the multi-dimensional commodity ranking method based on multi-threaded processing described in the present invention, wherein: the optimized comprehensive scoring model is adopted to consider the gross profit contribution, sales volume, annual cumulative sales volume, discount intensity and market response of the topic tag evaluation commodity, including calculating the gross profit contribution:

[0017]

[0018] in, S is the gross profit contribution score. 30 is the 30-day sales volume of the SPU to be sorted, P c is the price of the SPU to be sorted, C c is the SPU cost to be sorted, μ P and σ P are the market average price and standard deviation respectively.

[0019] Sales score:

[0020]

[0021] in, Score for sales volume, Indicates the acceleration of sales volume.

[0022] Annual cumulative sales score:

[0023]

[0024] Among them, S 365 is the annual sales volume of the SPU to be sorted, is the annual cumulative sales score, S 365 (ω) is the frequency domain representation of annual sales.

[0025] Discount Strength Score:

[0026]

[0027] in, is the discount strength score, P o is the current SPU original price, and β is the adjustment coefficient.

[0028] Hashtag score:

[0029]

[0030] in, Score the product label promotion policy, pi is the proportion of the i-th topic tag, and N is the number of tags.

[0031] As a preferred solution of the multi-dimensional commodity ranking method based on multi-threaded processing described in the present invention, wherein: the optimized comprehensive scoring model is used to evaluate the market response of commodities by considering gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, commodity labels and promotion policies, and also includes adding points according to the sales activities of each SPU. Each activity marked as flash sale, special price, discount with coupons, and discount is added 5 points, and the total does not exceed 20 points. The scoring weight of the commodity is adjusted in combination with the trend judgment of experts, which is expressed as:

[0032]

[0033] Among them, x represents the expert scoring weight, Add points to the activity.

[0034] As a preferred solution of the multi-dimensional commodity sorting method based on multi-threaded processing described in the present invention, the system sorts the commodities according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions, including storing the sorted commodity list in the database, and updating the commodity display interface of the management end and the user end, collecting the first and second category data once a month, and collecting the third category data once a day and updating the sorting.

[0035] Another object of the present invention is to provide a multi-dimensional commodity sorting system based on multi-threaded processing, which can improve processing efficiency by taking into account the large amount of data such as SPU, commodity classification, and city, and adopts a multi-threaded batch processing method. This processing method can divide large data sets into smaller tasks and assign them to multiple threads for parallel processing, thereby speeding up the processing speed. It solves the problem that the current commodity sorting contains low efficiency of single-threaded processing when processing large-scale data, which affects the user experience.

[0036] As a preferred solution of the multi-dimensional commodity sorting system based on multi-threaded processing described in the present invention, it includes: a data collection module, a scoring module, and a sorting adjustment module.

[0037] The data collection module is used to collect commodity sales data, segment and construct data, and process them in batches through multi-threading technology.

[0038] The scoring module is used to evaluate the market response of the product by adopting an optimized comprehensive scoring model, taking into account gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, product label and promotion policy.

[0039] The ranking adjustment module is used by the system to sort the products according to the comprehensive scores, and to regularly update and dynamically adjust the scoring dimensions.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a multi-dimensional commodity sorting method based on multi-threaded processing.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a multi-dimensional commodity sorting method based on multi-threaded processing.

[0042] Beneficial effects of the present invention: The multi-dimensional commodity sorting method based on multi-threaded processing provided by the present invention not only considers sales volume, but also combines multiple factors such as gross profit and promotion policy for a more comprehensive evaluation, and updates rankings based on the latest sales data to ensure the timeliness of rankings. Manual adjustment of weights is allowed, and quick response can be made according to market changes. Analysis by city and region is supported, which helps to adopt multi-threaded batch processing in a regional manner, thereby improving the speed and efficiency of data processing. The stability and reliability of the system are guaranteed by concurrent collection classes and Java concurrent tool classes. The present invention achieves better results in terms of efficiency, security, and adjustability. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0044] Figure 1 An overall flow chart of a multi-dimensional commodity sorting method based on multi-threaded processing provided in the first embodiment of the present invention.

[0045] Figure 2 An overall flow chart of a multi-dimensional commodity sorting system based on multi-threaded processing provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a multi-dimensional commodity sorting method based on multi-threaded processing, comprising:

[0048] S1: Collect commodity sales data, segment and construct data, and process them in batches using multi-threading technology.

[0049] Furthermore, the collection of commodity sales data includes data collection, and three types of data collection are performed. The first type collects annual sales, sales volume, monthly sales and sales volume nationwide, and collects annual sales, sales volume, monthly sales and sales volume in each city. The second type of data collects commodity classification data, and divides sales data by different commodity categories into annual sales and monthly sales. The third type of data collection is based on the commodity model SPU, including the selling price, cost, market average price, marketing topic tags and discount coefficients of individual products.

[0050] It should be noted that data segmentation and construction through batch processing using multi-threading technology includes dividing the data set into multiple independent subsets according to data type and dimension after data collection is completed. The dimensions include geographical dimension, time dimension and commodity classification dimension.

[0051] The regional dimension includes the province dimension and city dimension division for provinces, and the city dimension and district dimension division for municipalities directly under the central government. The city dimension of municipalities directly under the central government and the province dimension of provinces are the superior division dimensions, and the district dimension of municipalities directly under the central government and the city dimension of provinces are the secondary division dimensions.

[0052] The time dimension includes annual and monthly sales segmentation, with annual being the superior segmentation dimension and monthly being the secondary segmentation dimension.

[0053] The product classification dimension is segmented. After the segmentation is completed, the product area in the second half of the total sales volume is segmented using the upper dimension to construct subsets. The products in the first half of the total sales volume are segmented and subsets are constructed using the secondary segmentation dimension, and the SPU in each subset is identified.

[0054] Through multi-threading technology, multiple data subsets can be processed simultaneously, significantly improving data processing speed and shortening response time. Using concurrent tools such as Java's ExecutorService and ConcurrentHashMap, thread resources can be effectively managed, reducing the waste of system resources and improving system stability.

[0055] By tracking the execution of asynchronous tasks through Future objects, processing strategies and resource allocation can be adjusted in real time to adapt to dynamic changes in data processing requirements.

[0056] Segmented geographical and temporal dimensions allow for more targeted data analysis and processing, helping merchants develop more precise marketing and sales strategies for different markets and periods.

[0057] It should also be noted that the data segmentation and batch processing through multi-threading technology also includes the system using Java's ExecutorService to create a thread pool, and the multi-threading technology is used to process the segmented data subsets in parallel. Each thread is responsible for processing an independent data subset. After each thread completes the processing, the system processes the sub-results generated by each thread through the ConcurrentHashMap data structure to store the intermediate results.

[0058] Use Java's concurrency tool ExecutorService to manage threads, track the execution of asynchronous tasks through Future objects, and manage thread lifecycles.

[0059] S2: An optimized comprehensive scoring model is used to evaluate the market response of products by considering gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, product labels and promotion policies.

[0060] Furthermore, an optimized comprehensive scoring model is used to consider gross profit contribution, sales volume, annual cumulative sales volume, discount strength, and the market response of topic tags to evaluate products, including calculating gross profit contribution:

[0061]

[0062] in, S is the gross profit contribution score. 30 is the 30-day sales volume of the SPU to be sorted, P c is the price of the SPU to be sorted, C c is the SPU cost to be sorted, μ P and σ P are the market average price and standard deviation respectively.

[0063] Sales score:

[0064]

[0065] in, Score for sales volume, Indicates the acceleration of sales volume.

[0066] Annual cumulative sales score:

[0067]

[0068] Among them, S 365 is the annual sales volume of the SPU to be sorted, is the annual cumulative sales score, S 365 (ω) is the frequency domain representation of annual sales.

[0069] Discount Strength Score:

[0070]

[0071] in, is the discount strength score, P o is the current SPU original price, and β is the adjustment coefficient.

[0072] Hashtag score:

[0073]

[0074] in, Score the product label promotion policy, p i is the proportion of the i-th topic tag, and N is the number of tags.

[0075] Calculate the optimal pricing strategy based on maximizing expected profit by considering the cost C of the specific product SPU c and the average price μ P , combined with the Gaussian distribution of price sensitivity, to adjust prices to maximize profits. It reflects price elasticity and consumer sensitivity to price changes and is designed to reasonably set prices and increase sales.

[0076] Sales volume score, taking into account the time variation of product demand. 2 S(t) / dt 2 Represents the acceleration of demand, indicating the speed at which demand changes. This model can also be used to adjust inventory or production speed to respond to rapid changes in market demand.

[0077] The annual cumulative sales score combines time series analysis and processes periodic data through Fourier transformation to understand and predict seasonal changes in demand for products. It allows companies to better plan promotional activities and inventory management. For products with significant seasonal fluctuations, the score fluctuates greatly.

[0078] The discount intensity score has a relatively small impact on the overall score, but the special price bonus indirectly compensates for the problem of too small an impact on the overall score.

[0079] Hashtags It has a great impact on online shopping. Current consumers are accustomed to using topics to learn about items in a purposeful manner, so topic tags have a relatively large impact.

[0080] These models provide scientific decision support tools for enterprises by integrating market dynamics, consumer behavior, cost-effectiveness and market diversity. Each model is designed to solve specific business problems, thereby improving efficiency, profitability and market competitiveness.

[0081] It should be noted that the optimized comprehensive scoring model is used to evaluate the market response of products by considering gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, product labels and promotion policies. It also includes adding points according to the sales activities of each SPU. Each activity marked as flash sale, special price, discount with coupons, and discount with full discount will add 5 points, with a total of no more than 20 points. The scoring weight of the product is adjusted in combination with the trend judgment of experts, expressed as:

[0082]

[0083] Among them, x represents the expert scoring weight, Add points to the activity.

[0084] S3: The system sorts products according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions.

[0085] Furthermore, the system sorts the products according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions, including storing the sorted product list in the database and updating the product display interface on the management and user sides. The first and second category data are collected once a month, and the third category data is collected once a day and the sorting is updated.

[0086] Example 2, an embodiment of the present invention, provides a multi-dimensional commodity sorting method based on multi-threaded processing. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0087] First, in this embodiment, it will be demonstrated how to apply a multi-dimensional commodity sorting method based on multi-threaded processing to optimize the market performance of commodities. First, a comprehensive collection of commodity sales data is performed, including annual sales, monthly sales, commodity classification sales data, and sales data by commodity model SPU. These data are used to preliminarily evaluate the market performance and sales potential of commodities.

[0088] Next, use Java's ExecutorService to create a thread pool that is responsible for processing each independent data subset. The data subsets are divided according to dimensions such as region, time, and product category. For example, one thread may specialize in processing data for a municipality, while another thread processes data for a specific product category. This approach can greatly improve the efficiency and response speed of data processing.

[0089] After data processing is completed, ConcurrentHashMap is used to store intermediate results to ensure data consistency and thread safety. Then, the market response of each SPU is scored through a comprehensive scoring model. The scoring model includes gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, and topic tag scores. These scores reflect the comprehensive performance of the product in the market and the response of consumers.

[0090] Throughout the implementation process, each step is designed to ensure data accuracy and processing efficiency, while ensuring that the scoring model can truly reflect the market performance of the product.

[0091] Table 1 Experimental data comparison table

[0092]

[0093] It is obvious from the analysis of the above data that product D has the highest gross profit contribution and topic tag score, indicating that it has the strongest appeal and profitability in the market. Product C has the highest annual cumulative sales score, showing its continued popularity in the market. Although product B has a high discount strength score, it performs poorly in other aspects, probably because of the high discount strength at the expense of profit. It can be seen from this that our invention can be promoted to the ranking of products, and can be avoided by artificial regulation, which enhances its adaptability to the market.

[0094] Example 3, reference Figure 2 , which is an embodiment of the present invention, provides a multi-dimensional commodity sorting system based on multi-threaded processing, including a data collection module, a scoring module, and a sorting adjustment module.

[0095] The data collection module is used to collect product sales data, segment data, and process them in batches using multi-threading technology. The scoring module is used to evaluate the market response of products by using an optimized comprehensive scoring model, taking into account gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, product labels, and promotion policies. The sorting and adjustment module is used to sort products according to the comprehensive scores, and regularly update and dynamically adjust the scoring dimensions.

[0096] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0097] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0098] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0099] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-dimensional commodity sorting method based on multi-threaded processing, characterized in that: include: Collect commodity sales data, segment and construct data, and process them in batches through multi-threading technology; An optimized comprehensive scoring model is used to evaluate the market response of products by considering gross profit contribution, sales volume, annual cumulative sales volume, discount strength, product labels and promotion policies; The system sorts products according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions.

2. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 1, characterized in that: The commodity sales data collection includes data collection, and three types of data collection are performed. The first type collects the annual sales, sales volume, monthly sales and sales volume of the whole country, and collects the annual sales, sales volume, monthly sales and sales volume of each city; The second type of data collects commodity classification data, and divides sales data by different commodity categories into annual sales and monthly sales; The third type of data collection is based on the product model SPU, including the selling price, cost, market average price, marketing topic tags and discount coefficient of the single product.

3. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 2, characterized in that: The data segmentation and construction is carried out by batch processing through multi-threading technology, including dividing the data set into multiple independent subsets according to data type and dimension after data collection is completed, and the dimension includes geographical dimension, time dimension and commodity classification dimension; The regional dimension includes the province dimension and city dimension segmentation for provinces, and the city dimension and district dimension segmentation for municipalities directly under the central government. The city dimension of municipalities directly under the central government and the province dimension of provinces are the upper segmentation dimensions, and the district dimension of municipalities directly under the central government and the city dimension of provinces are the secondary segmentation dimensions. The time dimension includes annual and monthly sales volume segmentation, with annual being the superior segmentation dimension and monthly being the secondary segmentation dimension; The product classification dimension is segmented. After the segmentation is completed, the product area in the second half of the total sales volume is segmented using the upper dimension to construct subsets. The products in the first half of the total sales volume are segmented and subsets are constructed using the secondary segmentation dimension, and the SPU in each subset is identified.

4. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 3, characterized in that: The data segmentation and batch processing by multi-threading technology also includes the system using Java's ExecutorService to create a thread pool, and the multi-threading technology is used to parallel process the segmented data subsets. Each thread is responsible for processing an independent data subset. After each thread completes the processing, the system processes the sub-results generated by each thread through the ConcurrentHashMap data structure to store the intermediate results. Use Java's concurrency tool ExecutorService to manage threads, track the execution of asynchronous tasks through Future objects, and manage thread lifecycles.

5. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 4, characterized in that: The optimized comprehensive scoring model is used to consider gross profit contribution, sales volume, annual cumulative sales volume, discount strength, and the market response of topic tags to evaluate products, including calculating gross profit contribution: in, S is the gross profit contribution score. 30 is the 30-day sales volume of the SPU to be sorted, P c is the price of the SPU to be sorted, C c is the SPU cost to be sorted, μ P and σ P are the market average price and standard deviation respectively; Sales score: in, Score for sales volume, Indicates the acceleration of sales volume; Annual cumulative sales score: Among them, S 365 is the annual sales volume of the SPU to be sorted, is the annual cumulative sales score, S 365 (ω) is the frequency domain representation of annual sales; Discount Strength Score: in, is the discount strength score, P o is the current SPU original price, β is the adjustment coefficient; Hashtag score: in, Score the product label promotion policy, p i is the proportion of the i-th topic tag, and N is the number of tags.

6. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 5, characterized in that: The optimized comprehensive scoring model is used to evaluate the market response of the product by considering gross profit contribution, sales volume, annual cumulative sales volume, discount intensity, product label and promotion policy. It also includes adding points according to the sales activities of each SPU. Each activity marked as flash sale, special price, discount with coupons, and discount is added 5 points, with a total of no more than 20 points. The scoring weight of the product is adjusted in combination with the trend judgment of the expert, which is expressed as: Among them, x represents the expert scoring weight, Add points to the activity.

7. The multi-dimensional commodity sorting method based on multi-threaded processing according to claim 6, characterized in that: The system sorts the products according to the comprehensive scores, and regularly updates and dynamically adjusts the scoring dimensions, including storing the sorted product list in the database, and updating the product display interface of the management and user ends, collecting the first and second category data once a month, and collecting the third category data once a day and updating the sorting.

8. A system using the multi-dimensional commodity sorting method based on multi-threaded processing as claimed in any one of claims 1 to 7, characterized in that: Including data collection module, scoring module, and sorting adjustment module; The data collection module is used to collect commodity sales data, segment and construct data and process them in batches through multi-threading technology; The scoring module is used to evaluate the market response of the product by using an optimized comprehensive scoring model, taking into account gross profit contribution, sales volume, annual cumulative sales volume, discount strength, product label and promotion policy; The ranking adjustment module is used by the system to sort the products according to the comprehensive scores, and to regularly update and dynamically adjust the scoring dimensions.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-dimensional commodity sorting method based on multi-thread processing described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-dimensional commodity sorting method based on multi-thread processing described in any one of claims 1 to 7 are implemented.

Images