Method and system for intelligently creating goods based on big data

Abstract

A method and system for intelligently creating a commodity based on big data is provided. The method comprises the steps of generating a hot topic set containing a preset number of sorted hot topics based on a plurality of features of each hot topic in collected hot topics; based on a plurality of indexes of each hot commodity in the collected hot commodities, generating a hot commodity set comprising a predetermined number of sorted hot commodities; and generating one or more commodity combination suggestions based on the generated hot topic set, the generated hot commodity set and a commodity meta-information set, the commodity meta-information set representing an information set of commodities that can be produced and / or planned to be produced by a merchant. Moreover, the method further includes, for each of the generated one or more commodity combination suggestions, automatically generating a copywriting corresponding to the commodity combination suggestion based on the hot topics and the hot-sell commodities on which the commodity combination suggestion is based.

Description

Technical Field

[0001] The present invention relates to commodity creation, and in particular to a method and system for intelligently creating commodities based on big data. Background Art

[0002] In today's rapidly changing retail market, consumer demands are becoming increasingly diverse and personalized. Traditional product development models usually rely on static data or predefined templates, lacking flexibility and the ability to respond quickly to market dynamics, and are difficult to dynamically adapt to changing market demands and complex data sources. Therefore, there is an urgent need for a tool that can combine market trends, hot topics, and product features to improve the efficiency and market adaptability of product development. Summary of the invention

[0003] This Summary is provided to introduce some concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

[0004] According to an embodiment of the present invention, a method for intelligently creating commodities based on big data is provided, comprising: generating a hot topic set including a predetermined number of sorted hot topics based on multiple features of each of the collected hot topics; generating a hot-selling commodity set including a predetermined number of sorted hot-selling commodities based on multiple indicators of each of the collected hot-selling commodities; and generating one or more commodity combination suggestions based on the generated hot topic set, the generated hot-selling commodity set and the commodity meta information set, wherein the commodity meta information set represents an information set of commodities that a merchant can produce and / or plans to produce. .

[0005] According to another embodiment of the present invention, a system for intelligently creating commodities based on big data is provided, including a hot topic set generation module, a hot selling commodity set generation module, a commodity combination suggestion generation module, and a suggested commodity combination copywriting generation module. The hot topic set generation module is configured to generate a hot topic set including a predetermined number of sorted hot topics based on multiple features of each hot topic among the collected hot topics; the hot selling commodity set generation module is configured to generate a hot selling commodity set including a predetermined number of sorted hot selling commodities based on multiple indicators of each hot selling commodity among the collected hot selling commodities; the commodity combination suggestion generation module is configured to generate one or more commodity combination suggestions based on the generated hot topic set, the generated hot selling commodity set, and the commodity meta information set, wherein the commodity meta information set represents an information set of commodities that a merchant can produce and / or plans to produce.

[0006] These and other features and advantages will become apparent by reading the following detailed description and by reference to the associated drawings.It is to be understood that the foregoing general description and the following detailed description are illustrative only and are not restrictive of the aspects of what is claimed. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to understand the manner in which the above features of the present invention are used in detail, the above briefly summarized contents can be described in more detail with reference to various embodiments, some of which are shown in the accompanying drawings. However, it should be noted that the accompanying drawings only show some typical aspects of the present invention and should not be considered to limit its scope, because the description may allow for other equally effective aspects.

[0008] Figure 1 The overall framework 100 of a solution for intelligently creating merchandise based on big data according to one embodiment of the present invention is shown;

[0009] Figure 2 A framework diagram of a system 200 for intelligently creating merchandise based on big data according to an embodiment of the present invention is shown;

[0010] Figure 3 A flowchart of a method 300 for intelligently creating merchandise based on big data according to an embodiment of the present invention is shown; and

[0011] Figure 4 A block diagram of an exemplary computing device according to one embodiment of the present invention is shown. DETAILED DESCRIPTION

[0012] The present invention will be described in detail below in conjunction with the accompanying drawings, and the features of the present invention will be further revealed in the following specific description.

[0013] The following detailed description refers to the accompanying drawings showing exemplary embodiments of the present invention. However, the scope of the present invention is not limited to these embodiments, but is defined by the appended claims. Therefore, embodiments other than those shown in the drawings, such as modified versions of the illustrated embodiments, are still encompassed by the present invention.

[0014] References in this specification to "one embodiment," "an embodiment," "an example embodiment," etc., mean that the embodiment may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Furthermore, these phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in conjunction with an embodiment, it should be understood that the particular feature, structure, or characteristic can be implemented in conjunction with other embodiments within the knowledge of a person skilled in the relevant art, whether or not explicitly described.

[0015] Unless otherwise stated, the term "A or B" used throughout this specification refers to "A and B" and "A or B" but does not mean that A and B are exclusive.

[0016] The present invention can intelligently synthesize and create products based on the hot-selling products and hot topics in the market and in combination with the characteristics of its own products. Specifically, the present invention pays attention to market hot spots in a timely manner, combines the merchant's products and business characteristics, and comprehensively considers them through vector feature extraction and historical copywriting, which greatly improves the inspiration and efficiency of product creation and makes product creation more efficient. In the context of the present invention, "creating products" refers to the development / suggestion of products that merchants can produce.

[0017] Figure 1 The overall framework 100 of a solution for intelligently creating commodities based on big data according to an embodiment of the present invention is shown. The framework 100 schematically illustrates the underlying logic of the present invention, such as data sources and data flows.

[0018] refer to Figure 1 It can be concluded that the data sources mainly include hot topic tracking and market trend analysis. In hot topic tracking, we pay attention to and analyze the hot topics and social events on the Internet in real time to understand the public's interests and focus. In market heat analysis, we identify the hot-selling products in the current market through the analysis of big data such as sales data of e-commerce platforms.

[0019] In the data processing part, after obtaining the relevant data of hot topics and best-selling products, these raw data can be cleaned, feature extracted and processed to obtain a sorted set of social hot spots and a sorted set of best-selling products.

[0020] In the data modeling part, similarity calculations are performed on the above-mentioned social hot spots, hot-selling products, and product meta-information sets that represent products that merchants can produce, etc., to provide product combination suggestions. For example, if a certain type of food is very popular in the market, and a certain topic is also a hot topic, it can be recommended to develop a new product that not only meets the hot topic but also emphasizes the characteristics of the food itself.

[0021] In the data synthesis and product part, we use AI technology to automatically generate product appearance design sketches and product prototype sketches for the product combination suggestions provided, provide corresponding product copywriting services, and write attractive marketing copy based on hot topics.

[0022] Figure 2A framework diagram of a system 200 for intelligently creating commodities based on big data according to an embodiment of the present invention is shown. The system 200 mainly includes a hot topic set generation module 201, a hot-selling commodity set generation module 202, a commodity combination suggestion generation module 203, and a suggested commodity combination copywriting generation module 204. It is fully understood by those skilled in the art that the division of the above modules is only explained for the purpose of clarity. The functions of one or more of the above modules can be combined into a single module or split into more modules. Moreover, one or more of the above modules can be implemented in software, hardware, or a combination thereof. In addition, the data flow between the modules can be implemented in a manner known in the art, which is not within the scope of the present invention. In the context of the present invention, the system 200 can be used by merchants with production capacity, or can be used by third-party agencies based on relevant data provided by customers.

[0023] According to an embodiment of the present invention, the hot topic set generation module 201 can be configured to generate a set of a predetermined number of sorted hot topics based on multiple features of each hot topic collected from the Internet. By tracking hot topics, it is possible to follow and analyze hot topics and social events on the Internet in real time, and understand the public's interests and focus.

[0024] Specifically, generating a set including a predetermined number of sorted hot topics may include:

[0025] (1) Topic collection: Collect hot topic data from multiple online platforms (such as social media, video platforms, news websites, e-commerce platforms, news websites, etc.).

[0026] (2) Topic analysis: Analyze the collected hot topic data to extract multiple features, such as time decay factor, propagation rate, cross-platform popularity, emotional intensity, topic derivative degree, etc.

[0027] (3) Topic sorting: The values ​​of the extracted features of the hot topics are combined with the dynamic weights to sort the hot topics to form a set containing a predetermined number of sorted hot topics.

[0028] The following describes the process of generating a hot topic set from a mathematical perspective.

[0029] Set hot topic event collection , define the feature vector based on the set of hot topic events: .

[0030] The feature definition is as follows:

[0031] a. Time decay factor: represents an exponential decay process, where is a quantity in the time interval After the attenuation value, is the attenuation rate, and its mathematical formula is as follows:

[0032]

[0033] : Event age (hours)

[0034] default

[0035] b. Propagation rate: Propagation rate can be used to describe the speed at which information spreads in a social network or among a group of people.

[0036]

[0037] : Number of propagation nodes

[0038] : Propagation depth

[0039]

[0040] c. Cross-platform popularity: It can be understood as the comprehensive popularity of a certain content on multiple different platforms (such as social media, video platforms, news websites, e-commerce platforms, etc.).

[0041]

[0042] :Platform standardization heat

[0043] Example of platform weights: Social platform A (0.4), Social platform B (0.3), E-commerce platform A (0.2), E-commerce platform B (0.1)

[0044] d. Emotional intensity: A quantitative indicator used to measure the intensity of emotions.

[0045]

[0046] : Number of positive / negative reviews

[0047] : Emotional Entropy

[0048] e. Topic derivation degree: refers to the ability or degree to which a topic can generate new topics during the dissemination process. It reflects the evolution trend and diffusion scope of the topic during the dissemination process.

[0049]

[0050] : Number of derived topics

[0051] : Topic variance

[0052] : Derived Depth

[0053] f. Dynamic weight function: It is a strategy that dynamically adjusts weights according to specific conditions or rules. It dynamically adjusts weights according to the characteristics of input data, the training progress of the model, or the priority of the task.

[0054]

[0055] : Real-time heat vector (including breaking news coefficient, holiday coefficient, etc.)

[0056] : Learning rate parameter (default 0.8)

[0057] g. Comprehensive ranking function: refers to a method of sorting data by combining multiple sorting criteria. It is different from sorting in a single dimension. Instead, it calculates the comprehensive score of each data item by combining multiple factors and sorts according to the score.

[0058]

[0059] : Feature mean / standard deviation

[0060] : Interaction coefficient (for example, a value between 0.03 and 0.08)

[0061] h. Algorithm Process

[0062] 1) Feature Standardization:

[0063]

[0064] 2) Weight update: recalculated every hour

[0065] 3) Real-time sorting:

[0066]

[0067] Those skilled in the art can fully understand that the algorithm in the above example is only illustrative, and one or more of the above features or other features can be used to sort the hot topics.

[0068] In addition, those skilled in the art will fully understand that the specific values ​​in the above examples are only illustrative. For example, although the example provides a hot topic set including 10 sorted hot topics, it is entirely possible to include a hot topic set including other predetermined numbers (e.g., 20, 50, etc.) of sorted hot topics according to actual needs.

[0069] According to an embodiment of the present invention, the hot-selling product set generation module 202 may be configured to generate a set of a predetermined number of sorted hot-selling products based on multiple indicators of each of the hot-selling products collected from the Internet.

[0070] Specifically, the hot-selling product collection generation module 202 can be configured to score the hot-selling products on the e-commerce platform (for example, the top predetermined number of products in the sales ranking list, the top predetermined number of products in the recent sales surge list, the top predetermined number of products in the hot search list, etc.) according to the recent sales of the hot-selling product, the highest sales among all products in the product category to which the hot-selling product belongs, the rating of the product (for example, 1-5 points), the number of recent reviews of the product, etc.

[0071] The following describes the process of generating a set of hot-selling products from a mathematical perspective.

[0072] Set up a comprehensive sub-formula:

[0073]

[0074] Set sorting rules: Take the top 10 products

[0075] Top10 = Sort by descending order (Score)[1:10]

[0076] Variable Description:

[0077] Sales: The recent sales volume of the hot-selling product (needs to be normalized)

[0078] max_sales: The highest sales of all products in the product category to which the hot-selling product belongs (for example, if the hot-selling product is a specific type of liquor of brand A, then max_sales represents the highest sales of all products in the liquor category (for example, other brands of liquor or other types of liquor of the brand))

[0079] Rating: The rating of the hot-selling product (1-5 points)

[0080] Reviews: The number of recent reviews for this popular product

[0081] Those skilled in the art can fully understand that the algorithm in the above example is only illustrative, and one or more of the above features or other features can be used to sort the best-selling products.

[0082] In addition, those skilled in the art can fully understand that the specific numerical values ​​in the above examples are only illustrative. For example, although the example provides a hot-selling product set including 10 sorted hot-selling products, a hot-selling product set including other predetermined numbers (e.g., 20, 50, etc.) of sorted hot-selling products can be provided according to actual needs.

[0083] According to one embodiment of the present invention, the commodity combination suggestion generation module 203 may be configured to generate one or more commodity combination suggestions based on the generated hot topic set, the generated hot-selling commodity set, and the commodity meta information set. The commodity meta information set represents the information set of the commodities that the merchant can produce and / or plans to produce. The purpose of using the commodity meta information set is to avoid the generated commodity combination suggestions from including commodities that the merchant cannot produce. For example, if the merchant cannot produce smart devices, the commodity combination suggestions containing smart devices are useless to the merchant.

[0084] For example, the product combination suggestion generating module 203 may be configured to generate a final product combination suggestion by performing similarity calculation based on a hot topic set and a hot-selling product set through feature extraction and vectorization.

[0085] Here are the detailed steps:

[0086] (1) Feature extraction and vectorization: Extract the features of each set in the product metadata set, hot topic set, and best-selling product set, and perform vectorization processing.

[0087] (2) Similarity calculation: Calculate the similarity between the product metadata set, hot topic set, and best-selling product set, and establish a three-dimensional matching matrix.

[0088] (3) Feature screening: Based on the similarity calculation results, filter out the top-N (first N) product combinations.

[0089] (4) Product combination verification: Filter the top N product combinations selected by constraints (e.g., category consistency, material-form compatibility, etc.) to verify the market adaptability, physical feasibility, etc. of these product combinations, so as to exclude product combinations that are obviously inconsistent with common sense, thereby retaining one or more verified product combinations.

[0090] (5) Product combination recommendation generation: For one or more verified product combinations, a template-based approach is used to uniformly synthesize the final one or more product combination recommendations.

[0091] The following describes the process of generating product combination suggestions from a mathematical perspective.

[0092] a. Feature extraction and vectorization to establish product feature sets

[0093] The product meta information set is:

[0094]

[0095] The hot topics are:

[0096]

[0097] The best-selling products are:

[0098]

[0099] b. Similarity calculation, establishing a three-dimensional matching matrix:

[0100]

[0101] c. Feature screening

[0102] Take the Top-N combination:

[0103]

[0104] d.Combination verification

[0105] Filter by constraints:

[0106]

[0107] in is the dimension weight, is the threshold value.

[0108] e. Product combination suggestion generation: a template-based approach is used to unify and synthesize the final product combination suggestions. Attribute words can be derived from hot topics, and category words can be derived from hot-selling products / product meta information:

[0109]

[0110]

[0111] According to one embodiment of the present invention, the suggested product combination copy generation module 204 is configured to automatically generate a copy corresponding to the generated product combination suggestion for each of the one or more generated product combination suggestions based on the hot topics and hot-selling products on which the product combination suggestion is based.

[0112] Specifically, for each of the one or more generated product combination suggestions, the traceability generated by the product combination suggestion is input into the AI ​​model, so that the copy generated by the AI ​​model is consistent with the hot topics and hot-selling products based on the product combination suggestion, rather than just based on the physical properties of the product combination. In addition, AI technology can also be used to generate design sketches corresponding to the product combination suggestion.

[0113] The following describes the process of generating the suggested product combination copy from a mathematical perspective.

[0114] Extract keywords based on attention mechanism:

[0115]

[0116] in is the product feature, K / V is the historical advertising slogan / marketing copy library

[0117] Verification indicators:

[0118]

[0119] in It is an adjustable parameter.

[0120] Figure 3 A flowchart of a method 300 for intelligently creating a commodity based on big data according to an embodiment of the present invention is shown.

[0121] At 301, a set of a predetermined number of sorted hot topics is generated based on multiple features of each of the collected hot topics, wherein the multiple features include multiple of the following: time decay factor, propagation rate, cross-platform popularity, emotional intensity, topic derivation, etc.

[0122] At 302, based on the multiple indicators of each of the collected hot-selling products, a set of hot-selling products in a predetermined number of sorted order is generated, wherein the multiple indicators may include multiple of the following: recent sales, the highest sales among all products in the product category to which the hot-selling product belongs, the rating of the product, the number of recent reviews of the product, etc.

[0123] At 303, one or more product combination suggestions are generated based on the generated hot topic set, the generated hot selling product set and the product meta information set, wherein the product meta information set represents an information set of products that the merchant can produce and / or plans to produce.

[0124] At 304 , for each of the one or more generated product combination suggestions, based on the hot topics and hot-selling products on which the product combination suggestion is based, a copy corresponding to the generated product combination suggestion is automatically generated.

[0125] Embodiment 1:

[0126] By analyzing the hot topics and hot-selling products collected on the Internet, it is concluded that "environmental protection" is a hot topic, and "organic chocolate" is a hot-selling product. Based on this, the intelligent product creation tool of the present invention can suggest the development of an organic chocolate with degradable packaging. Keywords are extracted based on the attention mechanism to generate attractive marketing copy, for example, the copy content includes product features (such as "100% degradable packaging" and "organic chocolate"), selling points (such as "environmentally friendly and healthy"), etc.

[0127] Embodiment 2:

[0128] By analyzing the hot topics and hot-selling products collected on the Internet, it is concluded that "more convenient fitness (for example, involving the use of smart sensors for monitoring during fitness, the use of AI fitness coaches, etc.)" is a hot topic, and "full-length mirror" is a hot-selling product. Based on this, the smart product creation tool of the present invention can suggest the development of a smart fitness mirror that integrates smart sensors and AI fitness coach functions. Keywords are extracted based on the attention mechanism to generate attractive marketing copy, for example, the copy content includes product features (such as "AI fitness coach", "smart fitness mirror"), selling points (such as "enjoy professional fitness guidance at home"), etc.

[0129] In summary, the present invention combines merchant products and business characteristics through multi-dimensional feature fusion and constraint verification, and performs a series of vector feature calculations, ultimately ensuring that the recommended products have hot spot relevance, market adaptability and physical feasibility at the same time.

[0130] Figure 4 A block diagram of an exemplary computing device according to one embodiment of the present invention is shown, which is one example of a hardware device applicable to various aspects of the present invention.

[0131] refer to Figure 4 , a computing device 400 will now be described, which is an example of a hardware device applicable to various aspects of the present invention. The computing device 400 can be any machine that can be configured to perform processing and / or computing, and can be but is not limited to a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal digital assistant, a smart phone, a vehicle-mounted computer, or any combination thereof. The various methods / apparatus / server / client devices described above can be implemented in whole or in part by the computing device 400 or a similar device or system.

[0132] The computing device 400 may include components that may be connected or communicated via one or more interfaces and a bus 402. For example, the computing device 400 may include a bus 402, one or more processors 404, one or more input devices 406, and one or more output devices 408. The one or more processors 404 may be any type of processor and may include, but are not limited to, one or more general-purpose processors and / or one or more special-purpose processors (e.g., a dedicated processing chip). The input device 406 may be any type of device capable of inputting information to the computing device and may include, but are not limited to, a mouse, a keyboard, a touch screen, a microphone, and / or a remote controller. The output device 408 may be any type of device capable of presenting information and may include, but are not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The computing device 400 may also include or be connected to a non-transient storage device 410, which may be any storage device that is non-transient and capable of data storage, and may include, but is not limited to, a disk drive, an optical storage device, a solid-state memory, a floppy disk, a floppy disk, a hard disk, a tape or any other magnetic medium, an optical disk or any other optical medium, a ROM (read-only memory), a RAM (random access memory), a cache memory, and / or any memory chip or cassette, and / or any other medium from which a computer can read data, instructions, and / or code. The non-transient storage device 410 may be detachable from the interface. The non-transient storage device 410 may have data / instructions / code for implementing the above methods and steps. The computing device 400 may also include a communication device 412. The communication device 412 can be any type of device or system that can communicate with internal devices and / or with a network and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication device and / or a chipset, such as a Bluetooth device, an IEEE 1302.11 device, a WiFi device, a WiMax device, a cellular communication device and / or the like.

[0133] The bus 402 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0134] The computing device 400 may also include a working memory 414 , which may be any type of working memory capable of storing instructions and / or data that facilitate the operation of the processor 404 and may include, but is not limited to, a random access memory and / or a read-only storage device.

[0135] Software components may be located in the working memory 414, including but not limited to an operating system 416, one or more application programs 418, drivers and / or other data and codes. Instructions for implementing the above methods and steps may be included in the one or more application programs 418, and the modules / units / components of the aforementioned various devices / servers / client devices may be implemented by the processor 404 reading and executing the instructions of the one or more application programs 418.

[0136] It should also be recognized that changes may be made according to specific needs. For example, custom hardware may also be used, and / or specific components may be implemented in hardware, software, firmware, middleware, microcode, hardware description language, or any combination thereof. In addition, connections to other computing devices, such as network input / output devices, etc. may be employed. For example, programming hardware (e.g., programmable logic circuits including field programmable gate arrays (FPGAs) and / or programmable logic arrays (PLAs)) with assembly language or hardware programming languages ​​(e.g., VERILOG, VHDL, C++) may be used to implement part or all of the disclosed methods and devices using logic and algorithms according to the present invention.

[0137] Although various aspects of the present invention have been described so far with reference to the accompanying drawings, the above-described methods, systems and devices are merely examples, and the scope of the present invention is not limited to these aspects, but is limited only by the appended claims and their equivalents. Various components may be omitted or replaced by equivalent components. In addition, the steps may be implemented in an order different from the order described in the present invention. In addition, various components may be combined in various ways. It is also important that, as technology develops, many of the components described may be replaced by equivalent components that appear later.

Claims

1. A method for intelligently creating commodities based on big data, comprising: Based on multiple features of each of the collected hot topics, generating a hot topic set including a predetermined number of sorted hot topics; Based on the multiple indicators of each of the collected hot-selling products, a hot-selling product set including a predetermined number of sorted hot-selling products is generated; as well as Generate one or more product combination suggestions based on the generated hot topic set, the generated hot-selling product set, and the product meta-information set, wherein the product meta-information set represents an information set of products that the merchant can produce and / or plans to produce; The generating one or more product combination suggestions further includes: Calculate the similarity between the product meta information set, the hot topic set and the hot-selling product set, and establish a three-dimensional matching matrix; According to the similarity calculation results, a predetermined number of product combinations are screened out; Verify the selected predetermined number of product combinations through constraint conditions; For one or more verified product combinations, a templated approach is used to uniformly synthesize the final one or more product combination recommendations.

2. The method of claim 1, further comprising: For each of the one or more generated product combination suggestions, based on the hot topics and hot-selling products on which the product combination suggestion is based, a copy corresponding to the product combination suggestion is automatically generated.

3. The method of claim 1, wherein: The multiple features of the hot topic include multiple ones of the following: the time decay factor of the hot topic, the propagation rate of the hot topic, the cross-platform popularity of the hot topic, the emotional intensity or topic derivation of the hot topic.

4. The method of claim 1, wherein: The multiple indicators of the hot-selling product include more than one of the following: recent sales of the hot-selling product, the highest sales of all products in the product category to which the hot-selling product belongs, the rating of the hot-selling product, or the number of recent reviews of the hot-selling product.

5. The method of claim 1, wherein: The constraints include category consistency and material-morphology compatibility.

6. The method of claim 1, wherein: The templated method includes attribute words and category words.

7. A system for intelligently creating merchandise based on big data, comprising: A hot topic set generation module, the hot topic set generation module being configured to generate a hot topic set including a predetermined number of sorted hot topics based on a plurality of features of each of the collected hot topics; a hot-selling commodity set generation module, wherein the hot-selling commodity set generation module is configured to generate a hot-selling commodity set including a predetermined number of sorted hot-selling commodities based on a plurality of indicators of each of the collected hot-selling commodities; as well as a commodity combination suggestion generating module, the commodity combination suggestion generating module being configured to generate one or more commodity combination suggestions based on the generated hot topic set, the generated hot-selling commodity set, and the commodity meta information set, wherein the commodity meta information set represents an information set of commodities that the merchant can produce and / or plans to produce; The commodity combination suggestion generation module is further configured to: Calculate the similarity between the product meta information set, the hot topic set and the hot-selling product set, and establish a three-dimensional matching matrix; According to the similarity calculation results, a predetermined number of product combinations are screened out; Verify the selected predetermined number of product combinations through constraint conditions; For one or more verified product combinations, a templated approach is used to uniformly synthesize the final one or more product combination recommendations.

8. The system of claim 7, further comprising: The suggested product combination copy generation module is configured to automatically generate a copy corresponding to each of the one or more generated product combination suggestions based on the hot topics and hot-selling products on which the product combination suggestions are based.

9. The system of claim 7, wherein: The multiple features of the hot topic include multiple ones of the following: the time decay factor of the hot topic, the propagation rate of the hot topic, the cross-platform popularity of the hot topic, the emotional intensity or topic derivation of the hot topic; and / or The multiple indicators of the hot-selling product include more than one of the following: recent sales of the hot-selling product, the highest sales of all products in the product category to which the hot-selling product belongs, the rating of the hot-selling product, or the number of recent reviews of the hot-selling product.

Images