Dynamic pricing method and system for data trust transaction

Abstract

The invention discloses a dynamic pricing method and system for data trust transaction, and relates to the field of data processing. The dynamic pricing method for the data trust transaction comprises the steps of obtaining related data of a to-be-priced data product, wherein the related data comprises production cost, service cost and a market supply and demand relationship; the related data is input into a preset dynamic pricing model, the price of the data product to be priced is determined, and model parameters in the preset dynamic pricing model can be adjusted according to historical transaction data of the data product and the related data of the data product.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a dynamic pricing method and system for data trust transactions. Background Art

[0002] With the advent of the digital economy and the era of big data, data trading and data asset management have become an important technical field. The data trading model in related technologies has problems such as opaque pricing and low transaction efficiency, which makes it difficult to meet the growing data demand. Summary of the invention

[0003] The embodiments of the present application provide a dynamic pricing method and system for data trust transactions to solve the problems of opaque data transaction pricing and low transaction efficiency in related technologies.

[0004] In a first aspect, an embodiment of the present application provides a dynamic pricing method for data trust transactions, including: Obtaining relevant data of the data product to be priced, the relevant data including production cost, service cost and market supply and demand relationship; The relevant data is input into a preset dynamic pricing model to determine the price of the data product to be priced. The model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product.

[0005] In a second aspect, an embodiment of the present application provides a dynamic pricing system for data trust transactions, including: An acquisition module, used to acquire relevant data of the data product to be priced, wherein the relevant data includes production cost, service cost and market supply and demand relationship; The pricing module is used to input the relevant data into a preset dynamic pricing model to determine the price of the data product to be priced. The model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product.

[0006] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the method described in the first aspect.

[0007] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0008] In an embodiment of the present application, firstly, relevant data of the data product to be priced is obtained, and the relevant data includes production cost, service cost and market supply and demand relationship; then the relevant data is input into a preset dynamic pricing model to determine the price of the data product to be priced, and the model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product. In this embodiment, the price of the data product is determined by a model whose model parameters can be adjusted according to the historical transaction data of the data product and the relevant data of the data product, and the price can be made more transparent by dynamic adjustment, and pricing by the model can make the price more in line with the changing market demand, making the data product transaction more flexible and improving the efficiency of the transaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. 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: Figure 1 is a flow chart of a dynamic pricing method for data trust transactions provided in an embodiment of the present application; Figure 2 It is a schematic diagram of a dynamic pricing system for data trust transactions provided in an embodiment of the present application; Figure 3 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0011] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0012] The following is combined with Figures 1 to 3 , a dynamic pricing method and system for data trust transactions provided by an embodiment of the present application are described in detail through specific embodiments and application scenarios.

[0013] like Figure 1 As shown, it is a flow chart of a dynamic pricing method for data trust transactions provided by an embodiment of the present application. Figure 1 As shown, the dynamic pricing method of the data trust transaction may include: the contents shown in S101 to S102.

[0014] In S101, relevant data of the data product to be priced is obtained, and the relevant data includes production cost, service cost and market supply and demand relationship.

[0015] In this embodiment, relevant data of the data product to be priced, such as production cost, service cost, market supply and demand relationship and other information, are obtained to provide data support for the calculation of subsequent pricing models.

[0016] Among them, relevant information of data products can be obtained from the corresponding departments, such as production costs can be obtained from the production department, market supply and demand relationships can be obtained from the market department, etc., which shall be subject to actual application and is not limited in this application.

[0017] The acquisition of relevant data of the data product can be periodically acquired, and the acquisition period can be set according to actual conditions, which is not limited in this embodiment.

[0018] Among them, production costs may include raw material purchase prices, worker wages, equipment depreciation, etc.; service costs may include customer service, technical support, after-sales service, etc.; market supply and demand relationships may include customer order volume, sales forecasts, etc., and analyze the supply situation in the market, including competitor pricing, market share, etc.

[0019] In one example, after obtaining relevant data, in order to ensure the consistency and accuracy of the data, the data can be pre-processed, such as data cleaning, format conversion, standardization, normalization, etc. For questionable data, verification can be carried out with relevant departments to ensure the reliability of the data.

[0020] In one example, the acquired relevant data may also be stored in a database to ensure data security and facilitate subsequent use.

[0021] In S102, relevant data is input into a preset dynamic pricing model to determine the price of the data product to be priced. Model parameters in the preset dynamic pricing model can be adjusted according to historical transaction data of the data product and relevant data of the data product.

[0022] The model can adjust model parameters according to product characteristics, market demand, and transaction conditions to optimize the model, make pricing more accurate, and improve market acceptance.

[0023] In an embodiment of the present application, firstly, relevant data of the data product to be priced is obtained, and the relevant data includes production cost, service cost and market supply and demand relationship; then the relevant data is input into a preset dynamic pricing model to determine the price of the data product to be priced, and the model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product. In this embodiment, the price of the data product is determined by a model whose model parameters can be adjusted according to the historical transaction data of the data product and the relevant data of the data product, and the price can be made more transparent by dynamic adjustment, and pricing by the model can make the price more in line with the changing market demand, making the data product transaction more flexible and improving the efficiency of the transaction.

[0024] In a possible implementation of the present application, the training process of the preset dynamic pricing model may include: obtaining relevant data and pricing factors of data products, the pricing factors including at least one of the following: timeliness of data products, scarcity of data products, uniqueness of data products, and user behavior data; using relevant data and pricing factors as feature vectors to construct an initial dynamic pricing model; and using historical transaction data of data products to train the initial dynamic pricing model to obtain a preset dynamic pricing model.

[0025] In this embodiment, the relevant information of the data product can be obtained from the corresponding department, such as the production cost can be obtained from the production department, the market supply and demand relationship can be obtained from the market department, etc., which is subject to the actual application and is not limited in this application. The acquisition of relevant data of the data product can be periodically acquired, and the acquisition cycle can be set according to the actual situation, which is not limited in this embodiment. Among them, the production cost can include the purchase price of raw materials, workers' wages, equipment depreciation, etc.; the service cost can include customer service, technical support, after-sales service, etc.; the market supply and demand relationship can include customer order volume, sales forecast, etc., and analyze the supply situation in the market, including competitive product pricing, market share, etc.

[0026] In one example, the core attributes of data products can also be determined, such as the freshness, accuracy, completeness, and frequency of use of data, and the basic value of data products can be evaluated based on product attributes to determine their basic pricing range in the market. Customers can also be segmented into different groups, and the needs and willingness to pay for data products of different groups can be analyzed. Based on historical data and trend analysis, future changes in market demand for data products can be predicted.

[0027] In one example, you can track changes in production costs in real time, including raw material costs, labor costs, etc., adjust the weight of service costs in pricing based on the service content and service level provided, collect and analyze market data to understand supply and demand conditions, adjust prices based on changes in demand, consider the pricing strategies of competing products, and determine whether the data products to be priced have a certain degree of competitiveness. At the same time, you can set upper and lower limits on prices to avoid market imbalances, and set the frequency of price adjustments based on market changes, such as daily, weekly or monthly adjustments, and set the magnitude of each price adjustment based on the degree of change in market supply and demand.

[0028] In this embodiment, the model can be flexibly adjusted based on relevant data and pricing factors of data products, such as the timeliness of data products, scarcity of data products, uniqueness of data products, user behavior data, etc., so that the pricing of the model is more in line with market changes.

[0029] Among them, the pricing factor can be determined according to the factors that affect pricing, that is, in addition to production cost, service cost and market supply and demand relationship, at least one of the following pricing factors can also be considered: Timeliness of data products: For example, the freshness of data can be measured by the difference between the time when the data was generated and the current time; Scarcity: the ratio of the supply of a particular data product to the market demand; Uniqueness: The unique value of data products compared to competing products; User behavior data: such as click-through rate, conversion rate, user stay time, etc., can reflect users' interest and demand for data products.

[0030] It is worth noting that the model in this embodiment can use a machine learning algorithm, such as a gradient boosted tree (GBDT), which can process multiple input factors and learn complex nonlinear relationships. Other machine algorithms can also be used, depending on the actual application. This embodiment is only an example.

[0031] In a possible implementation of the present application, the initial dynamic pricing model is as follows:

[0032] in, is the predicted price, x is the feature vector, including production cost, service cost, market supply and demand, timeliness, scarcity, uniqueness, and user behavior data; is the output of the mth decision tree; is the weight of the tree, and M is the total number of decision trees.

[0033] In a possible implementation of the present application, using the historical transaction data of a data product to train an initial dynamic pricing model to obtain a preset dynamic pricing model may include: preprocessing and dividing the historical transaction data of the data product to obtain preprocessed data; using the preprocessed data to train the initial dynamic pricing model, and minimizing the loss function by adjusting model parameters to obtain the preset dynamic pricing model.

[0034] Preprocessing can include data cleaning, standardization, normalization and other steps to ensure the quality and consistency of input data. Partitioning refers to dividing data into training sets and test sets to improve the accuracy of the model.

[0035] In this embodiment, the training set data is used to train the model during the model training process, and the loss function is minimized by adjusting the model parameters, such as the number of decision trees, the number of layers and neurons of the neural network, the learning rate, etc., and grid search, random search, or Bayesian optimization methods can also be used to find the optimal hyperparameter combination. Finally, the test set can be used to evaluate the performance of the model, such as by calculating indicators such as mean square error (MSE) and root mean square error (RMSE) to measure the accuracy of the predicted price.

[0036] In a possible implementation of the present application, the loss function is as follows:

[0037] in, is the actual price of the data product, and N is the number of samples.

[0038] In a possible implementation of the present application, the dynamic pricing method for data trust transactions may also include: evaluating the quality of data products and market supply and demand relationships according to a preset cycle; and updating model parameters in a preset dynamic pricing model based on the quality of data products and market supply and demand relationships.

[0039] That is to say, in addition to the basic pricing model, the quality and market demand of data products can be regularly evaluated, and the parameters of the pricing model can be updated. Quality assessment can be carried out through indicators such as accuracy, completeness, and consistency of data products; market demand analysis can be carried out by analyzing market demand trends, user feedback and other information.

[0040] Specifically, the specific standards for data accuracy can be clarified, such as the error range, the proportion of outliers, etc., and samples can be randomly selected from the data products, compared with the actual source or other reliable data, and the error range and outliers of the sample data can be analyzed to determine whether the data meets the accuracy standards. Specific standards for data integrity can also be clarified, such as the field missing rate, the proportion of null values, etc., and the fields of the data products can be checked one by one to ensure that all necessary fields exist and are not empty, and the missing values ​​in the statistics can be analyzed. The reasons and proportions of missing values ​​can be analyzed to determine whether the integrity standards are met. Specific standards for data consistency can also be clarified, such as unified format and logical consistency, and whether the format of the data product meets the predefined standards, such as date format, numerical format, etc., and whether the logical relationship between the data is consistent, such as whether the associated fields match and whether the calculation results are reasonable.

[0041] This embodiment collects market data related to data products, such as sales volume, search volume, user feedback, etc., analyzes the changing trends of market data, understands the changes in market demand for data products, and predicts future market demand trends for data products based on historical data and trend analysis. It is also possible to collect user feedback on data products through questionnaires, user interviews, etc., classify and organize user feedback content, identify user satisfaction with data products, improvement suggestions, etc., and integrate user feedback results into market demand analysis as one of the bases for updating pricing model parameters.

[0042] This embodiment conducts a comprehensive analysis of the data product quality assessment results and market demand analysis results to understand the actual value and market acceptance of the data product, and adjusts the pricing strategy according to the assessment results, such as increasing or decreasing the price, adjusting the discount strategy, etc. The parameters of the pricing model are updated according to the adjusted pricing strategy to ensure that the pricing model can accurately reflect the value of the data product and changes in market demand. The updated pricing strategy is implemented in the data trading system to ensure that the new strategy can be smoothly implemented, and the market response to the new pricing strategy is monitored, including changes in indicators such as sales volume and user satisfaction. The pricing strategy and model parameters are continuously optimized according to the market response to ensure efficient and fair data trading.

[0043] In addition to the basic pricing model, this embodiment also has a dynamic adjustment strategy to adjust the price in real time according to market changes. The strategy may include at least one of the following: Dynamic discounts based on time periods: Apply different discount rates during different time periods (such as peak periods and off-peak periods).

[0044] Personalized pricing based on user purchase history: Customize prices based on historical data such as user purchase frequency and purchase amount.

[0045] Reactive pricing based on competitor behavior: When competitors adjust their prices, automatically adjust your own prices to remain competitive.

[0046] These dynamic adjustment strategies can be integrated into the pricing model or used as an additional processing step after the model output. Through the above implementation methods, a dynamic pricing model that can handle multiple input factors, learn complex relationships, and adjust prices in real time can be built. This will help improve the pricing efficiency and accuracy of the data trust trading platform and promote the healthy development of the market.

[0047] In a specific implementation of the present application, the data trust trading platform needs to build a dynamic pricing model for data products, for example, considering the following pricing factors: C: production cost; S: service cost; D: market demand index (reflecting the market demand for the data product); T: timeliness (data freshness, T∈[0,1]); R: scarcity index (reflecting the scarcity of similar products in the market). Assuming that there is a nonlinear relationship between the price P and the above pricing factors, this relationship can be approximated by a machine learning model.

[0048] First, collect historical transaction data and preprocess pricing factors, including data cleaning, standardization, etc. In addition, feature engineering can be performed, such as: creating interactive features: considering the interaction between production cost and service cost, or the interaction between timeliness and scarcity; transforming features: converting timeliness T and scarcity index R into a form that is easier for the model to handle.

[0049] The gradient boosting tree (GBDT) algorithm is used to build a dynamic pricing model. GBDT approximates complex functions by integrating multiple decision trees and is suitable for processing nonlinear relationships. The model can be expressed as:

[0050] Where F is the predicted price; is the output of the mth decision tree; is the weight of the tree, and M is the total number of decision trees.

[0051] Use the training set data to train the GBDT model, and optimize the model performance by adjusting hyperparameters (such as the number of trees, learning rate, tree depth, etc.); cross-validation and other methods can be used to find the optimal parameter combination.

[0052] Based on the predicted price output by the model, dynamic adjustment strategies are designed, such as time-based discounts, competitor price monitoring, etc. The trained model is deployed to the data trust trading platform, and the performance of the model is monitored in real time, and new transaction data is collected for continuous optimization of the model.

[0053] The performance of the model is evaluated through the test set data, and indicators such as mean square error (MSE) and root mean square error (RMSE) are calculated. At the same time, user feedback and market response are collected and incorporated into the continuous optimization process of the model to form a closed-loop feedback mechanism.

[0054] Through the above steps, a dynamic pricing model with multi-dimensional comprehensive pricing, nonlinear relationship modeling and dynamic adjustment capabilities was constructed. The innovation of this model lies in its comprehensive consideration of multiple pricing factors and the use of advanced machine learning algorithms to approximate complex pricing relationships, thereby achieving a more accurate and flexible pricing strategy.

[0055] In a possible implementation of the present application, after inputting relevant data into a preset dynamic pricing model and determining the price of the data product to be priced, the dynamic pricing method of the data trust transaction may also include: displaying the price of the data product; when the demander purchases the data product based on the price, triggering the transaction process and recording transaction information, the transaction information including transaction time, transaction price, and information of both parties to the transaction.

[0056] In this embodiment, the real-time price of the data product is calculated according to the dynamic pricing model and displayed on the platform, so that the price information can be updated in real time, ensuring that the demander can obtain the latest price data in a timely manner. When the demander purchases the data product according to the real-time price, the transaction process is triggered, and the system automatically records the transaction information, including key information such as transaction time, transaction price, and transaction parties. That is to say, after the pre-processed data is input into the preset dynamic pricing model, the model determines the price of the data product, and then the calculated real-time price information can be sent to the data trading platform. According to the preset display rules and formats, the real-time price of the data product is displayed to the demander in an intuitive and easy-to-understand manner. The display method may include price lists, price charts, etc., to ensure that the price information can be updated in real time. Once the pricing model calculates a new real-time price, the displayed data should be updated immediately to ensure that the demander can obtain the latest price data in a timely manner.

[0057] In one example, a price information monitoring mechanism can be set up to monitor price changes in real time to ensure the accuracy and stability of price calculations. Feedback from demanders, such as price questions and unreasonable prices, can also be received to promptly handle and adjust pricing or display. Based on market response and user needs, the performance and effects of pricing and display are regularly evaluated. Based on the evaluation results, pricing and display are optimized and iterated to improve the accuracy of price calculations and the user experience of display effects. The optimized pricing and display are deployed on the data trading platform to ensure that the system can continue to provide efficient, accurate, and real-time price services.

[0058] In one example, the demander browses data products on the data trading platform and selects the products he wants to buy. After confirming his willingness to buy, the demander clicks the buy button or performs the corresponding operation to trigger a purchase request. The purchase request contains the identification, quantity and other information of the selected data product. After receiving the purchase request, the system first verifies the validity of the request. Then, the system obtains the real-time price of the data product selected by the demander according to the real-time pricing model and displays the real-time price to the demander. After the demander confirms that the price is correct, it continues to execute the purchase operation. After the demander confirms the transaction price, the system generates a transaction order. The order contains key information such as the transaction time, transaction price, and the two parties to the transaction (data provider and demander). The system notifies the data provider of information about the transaction order. After the data provider confirms that the order content is correct, it agrees to execute the transaction. The demander completes the payment operation according to the payment method in the transaction order. The system verifies the payment result to ensure that the payment is successful and updates the order status to paid. The system automatically records transaction information, including transaction time (accurate to the second), transaction price, transaction parties (including account information of data providers and demanders), transaction quantity, payment method and other key information. The system saves the transaction information in the transaction record database for subsequent query, audit and data analysis. Once the transaction is completed (i.e. payment is successful and the data provider agrees to the transaction), the system updates the order status to completed, and the system sends a transaction completion notification to both parties, including detailed information of the transaction order and subsequent operation instructions.

[0059] In a possible implementation of the present application, the dynamic pricing method for data trust transactions may further include: adjusting model parameters in a preset dynamic pricing model based on transaction information.

[0060] In other words, the parameters of the pricing model can be adjusted according to the transaction situation to optimize future pricing strategies. That is, by analyzing historical transaction data, problems and deficiencies in the pricing model can be discovered, and the model can be improved and optimized.

[0061] In one example, historical transaction data can be regularly collected and organized, including detailed information such as the time of each transaction, transaction price, transaction quantity, transaction parties, payment method, etc., and then data preprocessing can be performed to eliminate outliers and erroneous data. Then, the collected historical transaction data can be statistically analyzed, including the changing trend of transaction volume, the distribution of transaction prices, the characteristics of customer purchasing behavior, etc. By comparing transaction data in different time periods and different market conditions, the changing trend of market demand and the reasons for price fluctuations can be analyzed. By using data mining and machine learning techniques, the potential laws and patterns in historical transaction data can be discovered to provide data support for the optimization of the pricing model. Based on the historical transaction data, the performance of the current pricing model can be evaluated, including indicators such as pricing accuracy, market acceptance, and profitability. The predicted price of the pricing model can be compared with the actual transaction price, and the deviation and error of the model in the pricing process can be analyzed. Combined with customer feedback and market reaction, the competitiveness of the pricing model in the market and customer satisfaction can be evaluated. Finally, based on the evaluation results, problems with the model can be discovered, such as excessive pricing deviation and insensitive response to changes in market demand, and model parameters can be adjusted, or the algorithm logic can be optimized, or new pricing factors can be introduced. Use historical transaction data and simulation data to test and verify the improved pricing model to ensure that the new model can better reflect market demand and product value.

[0062] By introducing a dynamic pricing mechanism, the embodiment of the present application can calculate and display the real-time price based on factors such as the production cost, service cost, and market supply and demand relationship of the data product. This dynamic adjustment method makes the price more transparent, and the demander can more intuitively understand the value of the data product, thereby making more reasonable purchasing decisions.

[0063] like Figure 2 As shown, it is a schematic diagram of a dynamic pricing system for data trust transactions provided by an embodiment of the present application. Figure 2 As shown, the dynamic pricing system for data trust transactions may include: an acquisition module 201 and a pricing module 202 .

[0064] Among them, the acquisition module 201 is used to obtain relevant data of the data product to be priced, and the relevant data includes production cost, service cost and market supply and demand relationship; the pricing module 202 is used to input the relevant data into the preset dynamic pricing model to determine the price of the data product to be priced. The model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product.

[0065] In the embodiment of the present application, first, the acquisition module 201 acquires the relevant data of the data product to be priced, and the relevant data includes production cost, service cost and market supply and demand relationship; then the pricing module 202 inputs the relevant data into the preset dynamic pricing model to determine the price of the data product to be priced, and the model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product. In this embodiment, the price of the data product is determined by a model whose model parameters can be adjusted according to the historical transaction data of the data product and the relevant data of the data product, and the price can be made more transparent by dynamic adjustment. And pricing through the model can make the price more in line with the changing market demand, make the data product transaction more flexible, and improve the efficiency of the transaction.

[0066] In a possible implementation of the present application, the pricing module 202 is used to: obtain relevant data and pricing factors of data products, where the pricing factors include at least one of the following: timeliness of data products, scarcity of data products, uniqueness of data products, and user behavior data; use the relevant data and pricing factors as feature vectors to construct an initial dynamic pricing model; and use the historical transaction data of data products to train the initial dynamic pricing model to obtain a preset dynamic pricing model.

[0067] In a possible implementation of the present application, the initial dynamic pricing model is as follows:

[0068] in, is the predicted price, x is the feature vector, including production cost, service cost, market supply and demand, timeliness, scarcity, uniqueness, and user behavior data; is the output of the mth decision tree; is the weight of the tree, and M is the total number of decision trees.

[0069] In a possible implementation of the present application, the pricing module 202 is used to: preprocess and divide the historical transaction data of the data product to obtain preprocessed data; use the preprocessed data to train the initial dynamic pricing model, and obtain the preset dynamic pricing model by adjusting the model parameters to minimize the loss function.

[0070] In a possible implementation of the present application, the loss function is as follows:

[0071] in, is the actual price of the data product, and N is the number of samples.

[0072] In a possible implementation of the present application, the dynamic pricing system for data trust transactions may further include: an evaluation module and an update module.

[0073] Among them, the evaluation module is used to evaluate the quality of data products and the market supply and demand relationship according to the preset cycle; the update module is used to update the model parameters in the preset dynamic pricing model based on the quality of data products and the market supply and demand relationship.

[0074] In a possible implementation of the present application, the dynamic pricing system for data trust transactions may further include: a display module and a transaction module.

[0075] Among them, the display module is used to display the price of the data product; the transaction module is used to trigger the transaction process and record the transaction information when the demander purchases the data product based on the price. The transaction information includes the transaction time, transaction price, and information of the two parties to the transaction.

[0076] In a possible implementation of the present application, the dynamic pricing system for data trust transactions may further include: a parameter adjustment module.

[0077] Among them, the parameter adjustment module is used to adjust the model parameters in the preset dynamic pricing model based on transaction information.

[0078] The function of the dynamic pricing system for data trust transactions described in this application has been Figure 1 The method embodiment shown is described in detail, so for any details not provided in the description of this embodiment, please refer to the relevant descriptions in the aforementioned embodiments, which will not be repeated here.

[0079] like Figure 3 As shown, an embodiment of the present application also provides an electronic device 300, including a processor 301, a memory 302, and a program or instruction stored in the memory 302 and executable on the processor 301. When the program or instruction is executed by the processor 301, each process of the dynamic pricing method embodiment of the above-mentioned data trust transaction is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0080] The embodiment of the present application also provides a storage medium, on which a program or instruction is stored, and when the program or instruction is executed by a processor, each process of the embodiment of the dynamic pricing method for data trust transactions provided in any of the above embodiments is implemented. And the same technical effect can be achieved, and to avoid repetition, it will not be repeated here.

[0081] The processor is the processor in the electronic device described in the above embodiment. The storage medium includes computer storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, etc.

[0082] The embodiments of the present application further provide a computer program / program product, which is stored in a storage medium and is executed by at least one processor to implement the various processes of the above-mentioned dynamic pricing method embodiment for data trust transactions, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0083] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and system in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0084] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0085] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. A dynamic pricing method for data trust transactions, characterized in that: include: Obtaining relevant data of the data product to be priced, the relevant data including production cost, service cost and market supply and demand relationship; The relevant data is input into a preset dynamic pricing model to determine the price of the data product to be priced. The model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product.

2. The method according to claim 1, characterized in that The training process of the preset dynamic pricing model includes: Acquire relevant data and pricing factors of the data product, wherein the pricing factors include at least one of the following: timeliness of the data product, scarcity of the data product, uniqueness of the data product, and user behavior data; Using the relevant data and the pricing factors as feature vectors to construct an initial dynamic pricing model; The initial dynamic pricing model is trained using the historical transaction data of the data product to obtain a preset dynamic pricing model.

3. The method according to claim 2, characterized in that The initial dynamic pricing model is as follows: in, is the predicted price, x is the feature vector, including production cost, service cost, market supply and demand, timeliness, scarcity, uniqueness, and user behavior data; is the output of the mth decision tree; is the weight of the tree, and M is the total number of decision trees.

4. The method according to claim 3, characterized in that The using the historical transaction data of the data product to train the initial dynamic pricing model to obtain a preset dynamic pricing model includes: Preprocessing and dividing the historical transaction data of the data product to obtain preprocessed data; The initial dynamic pricing model is trained using the preprocessed data, and the preset dynamic pricing model is obtained by adjusting the model parameters to minimize the loss function.

5. The method according to claim 4, characterized in that The loss function is as follows: in, is the actual price of the data product, and N is the number of samples.

6. The method according to claim 2, characterized in that The method further comprises: Evaluate the quality of the data products and the market supply and demand relationship according to the preset period; Based on the quality of the data product and the market supply and demand relationship, the model parameters in the preset dynamic pricing model are updated.

7. The method according to claim 1, characterized in that After inputting the relevant data into a preset dynamic pricing model to determine the price of the data product to be priced, the method further includes: Displaying the price of the data product; When the demander purchases the data product based on the price, the transaction process is triggered and transaction information is recorded. The transaction information includes transaction time, transaction price, and information of both transaction parties.

8. The method according to claim 7, characterized in that The method further comprises: The model parameters in the preset dynamic pricing model are adjusted based on the transaction information.

9. A dynamic pricing system for data trust transactions, characterized in that: include: An acquisition module, used to acquire relevant data of the data product to be priced, wherein the relevant data includes production cost, service cost and market supply and demand relationship; The pricing module is used to input the relevant data into a preset dynamic pricing model to determine the price of the data product to be priced. The model parameters in the preset dynamic pricing model can be adjusted according to the historical transaction data of the data product and the relevant data of the data product.

10. An electronic device, characterized in that: It includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the dynamic pricing method for data trust transactions as described in any one of claims 1 to 8.

Images