E-commerce platform commodity price intelligent supervision method and related device

Abstract

The invention discloses an e-commerce platform commodity price intelligent supervision method and a related device. The method comprises the steps of obtaining price time sequence features, semantic features and competitive product features of commodities in an e-commerce platform; inputting the price time sequence features, the semantic features and the competitive product features of the commodities in the e-commerce platform into a price prediction model, and predicting the price trend of the commodities in the future N days; and performing intelligent supervision on the commodity price according to the predicted price trend of the next N days. The method and the related device can perform automatic and accurate intelligent supervision on the price of the e-commerce platform commodity.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent supervision, and relates to an intelligent supervision method and related devices for commodity prices on an e-commerce platform. Background Art

[0002] Currently, prices are obtained through the mall's internal historical data and manually maintained external mall links. External mall prices are updated daily through links. The price index is determined using the lowest price method or the average price method. Parameters are updated every morning, and abnormal products are manually reviewed. The defects are:

[0003] Data uniformity: The data integrated from external platforms is single, making it impossible to detect violations such as "the same product has a normal price on JD.com, but a false original price on Taobao".

[0004] Model lag: The update cycle is 24 hours and cannot detect short-term price anomalies.

[0005] High reliance on manual labor: Exception handling delays of ≥12 hours, missed detection rates as high as 40%, and violations of procurement compliance requirements.

[0006] Due to the above shortcomings, it is impossible to automatically and accurately conduct intelligent supervision of product prices on e-commerce platforms. Summary of the Invention

[0007] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art and provide a method and related device for intelligent price supervision of goods on an e-commerce platform. This method and related device can automatically and accurately perform intelligent supervision on the prices of goods on the e-commerce platform.

[0008] To achieve the above-mentioned purpose, the present invention discloses a method for intelligently supervising commodity prices on an e-commerce platform, comprising:

[0009] Obtain price temporal features, semantic features, and competitive product features of products on e-commerce platforms;

[0010] Input the price time series features, semantic features, and competitive product features of the products on the e-commerce platform into the price prediction model to predict the price trend of the products in the next N days;

[0011] Intelligent supervision of commodity prices is performed based on the predicted price trends for the next N days.

[0012] The further improvement of the method for intelligent price supervision of goods on the e-commerce platform described in the present invention is:

[0013] Furthermore, the process of obtaining the price temporal features, semantic features, and competitive product features of products on the e-commerce platform is as follows:

[0014] The real-time prices of commodities in different transaction platforms are grabbed through an API, and price time sequence features are constructed according to the real-time prices of commodities in each transaction platform, sales records and supplier costs;

[0015] The description and user evaluation of commodities in each transaction platform are acquired, and semantic features are constructed according to the description and user evaluation of commodities in each transaction platform;

[0016] The price median and discount intensity of similar commodities of the commodity in each transaction platform are acquired, and competitive product features are constructed according to the price median and discount intensity.

[0017] Further, the process of intelligent supervision of commodity prices according to the predicted price trend of the next N days is:

[0018] According to the predicted price trend of the next N days, the deviation between the predicted commodity price and the actual price is calculated;

[0019] The intelligent supervision of commodity prices is performed according to the deviation.

[0020] Further, the process of intelligent supervision of commodity prices according to the deviation is:

[0021] When the deviation is greater than or equal to a first preset deviation threshold and less than a second preset deviation threshold, a warning is triggered and a log is recorded;

[0022] When the deviation is greater than or equal to the second preset deviation threshold, the corresponding commodity is automatically unlisted.

[0023] Further, the price prediction model is constructed based on a multi-task learning framework.

[0024] The application discloses an intelligent supervision system for commodity prices on an e-commerce platform, comprising:

[0025] An acquisition module is configured to acquire price time sequence features, semantic features and competitive product features of commodities on an e-commerce platform;

[0026] A prediction module is configured to input the price time sequence features, semantic features and competitive product features of commodities on the e-commerce platform into a price prediction model, and predict a price trend of commodities in the next N days;

[0027] A supervision module is configured to perform intelligent supervision of commodity prices according to the predicted price trend of the next N days.

[0028] The intelligent supervision system for commodity prices on the e-commerce platform is further improved in that:

[0029] Further, the acquisition module comprises:

[0030] The first construction unit is configured to capture real-time prices of commodities in different transaction platforms through an API, and construct price time sequence features according to the real-time prices of commodities in the transaction platforms, sales records and supplier costs.

[0031] The second construction unit is configured to acquire descriptions and user reviews of commodities in the transaction platforms, and construct semantic features according to the descriptions and user reviews of the commodities in the transaction platforms.

[0032] The third construction unit is configured to acquire a price median and a discount intensity of similar commodities of the commodity in the transaction platforms, and construct competitor features according to the price median and the discount intensity.

[0033] Further, the supervision module comprises:

[0034] The calculation unit is configured to calculate a deviation degree between the predicted commodity price and an actual commodity price according to the predicted price trend of the future N days.

[0035] The supervision unit is configured to intelligently supervise the commodity price according to the deviation degree.

[0036] The present application discloses a kind of computer equipment, including memory, processor and computer program stored in the memory and can be run on the processor, when the processor executes the computer program, the steps of the method for intelligently supervising the commodity price of the e-commerce platform are realized.

[0037] The present application discloses a kind of computer readable storage medium, the computer readable storage medium stores computer program, when the computer program is executed by processor, the steps of the method for intelligently supervising the commodity price of the e-commerce platform are realized.

[0038] The present application has the following beneficial effects:

[0039] The e-commerce platform commodity price intelligent supervision method and related device described in the application input the price time sequence features, semantic features and competitor features of the commodities in the e-commerce platform into the price prediction model, predict the price trend of the commodities in the future N days, and then intelligently supervise the commodity price according to the predicted price trend of the future N days, to realize automatic and accurate intelligent supervision of the commodity price of the e-commerce platform. It should be noted that the present application predicts the price trend of the future N days based on price time sequence features, semantic features and competitor features, and the prediction accuracy is relatively high. BRIEF DESCRIPTION OF DRAWINGS

[0040] The drawings accompanying the specification of the present application form part of the present application and serve to further understand the present application, and the illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 is a method flowchart of the present application;

[0042] Figure 2 is a system structure diagram of the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0044] In the description of the present application, it should be understood that the terms “include” and “contain” indicate the existence of described features, whole, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.

[0045] It should also be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and the appended claims of the present application, unless otherwise clear from the context, the singular forms “a”, “an” and “the” are intended to include the plural forms.

[0046] It should be further understood that the term “and / or” used in the specification and the appended claims of the present application means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations, for example, A and / or B can represent three cases of A alone, A and B together, and B alone. In addition, the character “ / ” in the present application generally represents an “or” relationship between the front and rear associated objects.

[0047] It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application to describe the preset ranges, etc., these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from each other. For example, the first preset range can also be referred to as the second preset range, and similarly, the second preset range can also be referred to as the first preset range without departing from the scope of the embodiments of the present application.

[0048] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if [a stated condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the stated condition or event]" or "in response to detecting [the stated condition or event]."

[0049] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Generally, the components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0050] Various structural schematic diagrams according to the disclosed embodiments of the present application are shown in the drawings. These diagrams are not drawn to scale, in which some details are exaggerated for the purpose of clarity and some details can be omitted. The shapes of various regions, layers and their relative sizes and positional relationships shown in the drawings are only exemplary, and in actuality, there can be deviations due to manufacturing tolerances or technical limitations, and a person skilled in the art can additionally design regions / layers with different shapes, sizes and relative positions according to actual needs.

[0051] Embodiment one

[0052] With reference to Figure 1 The e-commerce platform commodity price intelligent supervision method described in the present application comprises:

[0053] 1) acquiring price time sequence features, semantic features and competitive product features of commodities in an e-commerce platform;

[0054] The process of step 1) is:

[0055] 11) grabbing real-time prices of commodities in different transaction platforms through API, and constructing price time sequence features according to real-time prices, sales records and supplier costs of commodities in each transaction platform;

[0056] Among them, the real-time prices of commodities in different transaction platforms (Jingdong, Tmall, Taobao and other external mainstream e-commerce platforms) are obtained through API, and the historical sales records and supplier costs of commodities in each transaction platform are integrated, and then data alignment is performed to realize the normalization of the same commodity, and then the price time sequence characteristics are constructed, which are used to represent the sliding mean, volatility, seasonal decomposition and other indicators of historical prices, which are used to capture the periodicity and trend of commodity prices;

[0057] 12) Obtain the description and user evaluation of the commodity in each transaction platform, and construct semantic features according to the description and user evaluation of the commodity in each transaction platform, which are used to quantify the influence of market feedback on price;

[0058] 13) Obtain the price median and discount intensity of the same commodity of the commodity in each transaction platform, and construct competitive product features according to the price median and discount intensity.

[0059] 2) Input the price time sequence characteristics, semantic features and competitive product features of the commodity in the e-commerce platform into the price prediction model to predict the future N-day price trend of the commodity;

[0060] The price time sequence characteristics, semantic features and competitive product features of the commodity are jointly encoded based on the Transformer architecture of DeepSeek, the calculation complexity of long sequence (>1000 time steps) is reduced through the ProbSparse self-attention mechanism, the gradient disappearance problem of traditional LSTM is solved, and the text semantics are fused to enhance the prediction logic.

[0061] Based on the multi-task learning framework, the price prediction model is constructed, the jointly encoded results are input into the price prediction model, and the future N-day price trend of the commodity is predicted, for example, the future 7-day category-level price index, and the loss function adopts weighted MAE.

[0062] 3) According to the predicted future N-day price trend, intelligent supervision of commodity price is carried out.

[0063] The specific process of step 3) is:

[0064] 31) According to the predicted future N-day price trend, the deviation between the predicted commodity price and the actual price is calculated, wherein the deviation = |actual price-predicted mean| / predicted standard deviation;

[0065] 32) According to the deviation, intelligent supervision of commodity price is carried out.

[0066] Specifically, when the deviation is greater than or equal to a first preset deviation threshold and less than a second preset deviation threshold, a warning is triggered and a log is recorded; when the deviation is greater than or equal to the second preset deviation threshold, the corresponding commodity is automatically unlisted.

[0067] It should be noted that, on the supplier side: based on the model prediction result, the optimal listing price interval is recommended, for example, it is suggested that the pricing is less than or equal to 95% of the median price of the competitor; in addition, the platform rule library is matched in real time, and the listing request of the illegal commodity is intercepted. On the platform side, when an exception occurs, the unlisting process is automatically triggered (response time < 5 seconds), and an audit work order is generated for manual review.

[0068] It should be noted that, in the present application, the price time series data (price fluctuation), text semantics (user comments, promotion rules) and external competitor features are fused through multi-modal data fusion and dynamic feature modeling, and multi-modal joint modeling is realized through an improved Transformer architecture. In addition, through expert hybrid model (MoE) optimization, a sparse activation mechanism is adopted, and only specific domain experts (such as price prediction experts and compliance experts) are dynamically called, which reduces the consumption of computing resources while improving the reasoning speed. At the same time, the model can be extended to related scenarios such as inventory prediction and demand planning, and by adjusting the input features and loss function to adapt to new tasks, private deployment and API opening are supported, and flexible connection with enterprise ERP and risk control systems is realized.

[0069] In the present application, the long sequence dependent modeling and incremental learning mechanism enable the model to capture the long-term fluctuation law of the market and quickly respond to sudden changes (such as competitor promotions), forming a technical closed loop of “high-precision prediction-compliance decision-dynamic iteration”, and systematically solving the real-time, safety and explainability problems of pricing strategies in the e-commerce field.

[0070] Embodiment two

[0071] Reference Figure 2 The e-commerce platform commodity price intelligent supervision system provided by the present application comprises:

[0072] The acquisition module is configured to acquire price time series features, semantic features and competitor features of commodities in the e-commerce platform.

[0073] The prediction module is configured to input the price time series features, semantic features and competitor features of the commodities in the e-commerce platform into a price prediction model to predict the price trend of the commodities in the next N days.

[0074] The supervision module is configured to intelligently supervise the prices of the commodities according to the predicted price trend of the commodities in the next N days.

[0075] In the present embodiment, the acquisition module comprises:

[0076] The first construction unit is configured to capture real-time prices of commodities in different transaction platforms through an API, and construct price time sequence features according to the real-time prices of commodities in the transaction platforms, sales records and supplier costs;

[0077] The second construction unit is configured to acquire descriptions and user evaluations of commodities in the transaction platforms, and construct semantic features according to the descriptions and user evaluations of the commodities in the transaction platforms;

[0078] The third construction unit is configured to acquire a price median and a discount intensity of a similar commodity of the commodity in the transaction platforms, and construct competitor features according to the price median and the discount intensity.

[0079] In the embodiment, the supervision module comprises:

[0080] The calculation unit is configured to calculate a deviation degree between the predicted commodity price and the actual commodity price according to the predicted price trend of the future N days;

[0081] The supervision unit is configured to intelligently supervise the commodity price according to the deviation degree.

[0082] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, the function modules in each embodiment of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0083] Embodiment three

[0084] The computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the e-commerce platform commodity price intelligent supervision method when executing the computer program, for example, comprising: acquiring the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodities in the e-commerce platform; inputting the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodities in the e-commerce platform into a price prediction model to predict the price trend of the commodities in the next N days; and intelligently supervising the price of the commodities according to the predicted price trend of the commodities in the next N days. The process of acquiring the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodities in the e-commerce platform comprises: grabbing the real-time prices of the commodities in different transaction platforms through API, constructing the price time sequence characteristics according to the real-time prices, sales records and supplier costs of the commodities in each transaction platform; acquiring the descriptions and user reviews of the commodities in each transaction platform, and constructing the semantic characteristics according to the descriptions and user reviews of the commodities in each transaction platform; acquiring the median price and discount intensity of the similar commodities of the commodity in each transaction platform, and constructing the competitive product characteristics according to the median price and discount intensity. The memory can include a memory, such as a high-speed random memory, and can also include a non-volatile memory, such as at least one disk memory; the processor, network interface and memory are connected with each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard structure bus, etc., and the bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs, specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0085] Embodiment four

[0086] A computer readable storage medium stores a computer program, the computer program is executed by a processor to implement steps of the e-commerce platform commodity price intelligent supervision method, for example, comprising: obtaining the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodity in the e-commerce platform; inputting the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodity in the e-commerce platform into a price prediction model to predict the price trend of the commodity in the future N days; according to the predicted price trend of the future N days, intelligent supervision of the commodity price is carried out, the process of obtaining the price time sequence characteristics, semantic characteristics and competitive product characteristics of the commodity in the e-commerce platform is: the real-time price of the commodity in different transaction platforms is grabbed through API, the price time sequence characteristics are constructed according to the real-time price, sales record and supplier cost of the commodity in each transaction platform; the description and user evaluation of the commodity in each transaction platform are obtained, and the semantic characteristics are constructed according to the description and user evaluation of the commodity in each transaction platform; the median price and discount intensity of the same kind of commodity of the commodity in each transaction platform are obtained, and the competitive product characteristics are constructed according to the median price and discount intensity. Specifically, the computer readable storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory can include random access memory and / or cache memory, etc. The non-volatile memory can include read-only memory, hard disk, flash memory, optical disc, magnetic disc, etc.

[0087] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media having computer-usable program code contained therein.

[0088] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0089] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0090] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the Figure 1 function specified in the flow or flows and / or blocks Figure 1 of the block or blocks.

[0091] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.

[0092] It is to be understood that the application is not limited to the precise construction described herein and as illustrated in the accompanying drawings, and that various modifications and changes can be made by those skilled in the art without departing from the scope of the application. The scope of the application is limited only by the claims that follow.

[0093] The above description is only preferred embodiments of the application, not any limitation to the application, any simple modification, change and equivalent structure change according to the technical essence of the application to the above embodiments, still belong to the protection scope of the technical scheme of the application.

Claims

1. A method for intelligently monitoring commodity prices on an e-commerce platform, characterized in that: include: Obtain price temporal features, semantic features, and competitive product features of products on e-commerce platforms; Input the price time series features, semantic features, and competitive product features of the products on the e-commerce platform into the price prediction model to predict the price trend of the products in the next N days; Intelligent supervision of commodity prices is performed based on the predicted price trends for the next N days.

2. The method for intelligent price supervision of goods on an e-commerce platform according to claim 1, characterized in that: The process of obtaining the price temporal features, semantic features, and competitive product features of products on the e-commerce platform is as follows: Capture the real-time prices of commodities on different trading platforms through APIs, and build price time series features based on the real-time prices, sales records, and supplier costs of commodities on each trading platform; Obtain product descriptions and user reviews on each trading platform, and construct semantic features based on the product descriptions and user reviews on each trading platform; Obtain the median price and discount strength of similar products of the product on each trading platform, and construct competitive product features based on the median price and discount strength.

3. The method for intelligent price supervision of goods on an e-commerce platform according to claim 1, characterized in that: The process of intelligently monitoring commodity prices based on the predicted price trends for the next N days is as follows: Calculate the deviation between the predicted commodity price and the actual price based on the predicted price trend for the next N days; Intelligent supervision of commodity prices is performed based on the deviation.

4. The method for intelligently monitoring commodity prices on an e-commerce platform according to claim 3, characterized in that: The process of intelligently regulating commodity prices based on the deviation is as follows: When the deviation is greater than or equal to a first preset deviation threshold and less than a second preset deviation threshold, an early warning is triggered and a log is recorded; When the deviation is greater than or equal to a second preset deviation threshold, the corresponding product is automatically removed from the shelf.

5. The method for intelligent price supervision of goods on an e-commerce platform according to claim 1, characterized in that: The price prediction model is built based on a multi-task learning framework.

6. An intelligent price supervision system for goods on an e-commerce platform, characterized in that: include: The acquisition module is used to obtain the price time series features, semantic features, and competitive product features of products on the e-commerce platform; A prediction module is used to input the price time series features, semantic features, and competitive product features of the products on the e-commerce platform into the price prediction model to predict the price trend of the products in the next N days; The supervision module is used to perform intelligent supervision of commodity prices based on the price trends of the next N days obtained by the prediction.

7. The intelligent price supervision system for goods on the e-commerce platform according to claim 6 is characterized in that: The acquisition module includes: The first construction unit is used to capture the real-time prices of commodities on different trading platforms through APIs, and construct price time series features based on the real-time prices, sales records, and supplier costs of commodities on each trading platform; The second construction unit is used to obtain descriptions and user reviews of products on each trading platform, and to construct semantic features based on the descriptions and user reviews of products on each trading platform; The third construction unit is used to obtain the median price and discount intensity of similar products of the product on each trading platform, and construct competitive product features based on the median price and discount intensity.

8. The intelligent price supervision system for goods on the e-commerce platform according to claim 7 is characterized in that: The supervision module includes: A calculation unit, configured to calculate a deviation between the predicted commodity price and the actual price based on the predicted price trend for the next N days; The supervision unit is used to perform intelligent supervision of commodity prices based on the deviation.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for intelligent price supervision of goods on an e-commerce platform as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for intelligent price supervision of goods on an e-commerce platform as described in any one of claims 1 to 5 are implemented.

Images