Data transaction method, device and equipment based on multi-source data and storage medium

Abstract

The embodiment of the invention discloses a data transaction method and device based on multi-source data, equipment and a storage medium, which are used for realizing multi-source data collaborative transaction and improving the utilization efficiency of data resources. The method provided by the embodiment of the invention comprises the following steps: acquiring value information of each data source in a data product and a coupling relationship and a coupling degree between the data sources; constructing a data transaction model based on the value information of each data source and the coupling relationship and the coupling degree between the data sources; solving the data transaction model to obtain the optimal pricing of the data product and the optimal income distribution proportion of the seller of each data source; and performing transaction settlement on the data product according to the optimal pricing of the data product and the optimal income distribution proportion of the seller of each data source. According to the embodiment of the invention, through multi-source data cooperation, the data source utilization rate can be improved; through reasonable income distribution and determination of an optimal pricing strategy, the income of the seller can be increased to the maximum extent, and benefit win-win is realized.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data trading, and in particular, to a data trading method, apparatus, device and storage medium based on multi-source data. Background Art

[0002] In the era of big data, data has become a key production factor, and data trading is an important way to promote the circulation of data resources. The popularity of data trading has promoted data sharing and promoted the rapid development of various industries towards data-driven intelligence.

[0003] However, most existing data trading models adopt a one-to-one direct transaction method between data source sellers and data source buyers, and such trading methods mostly use non-cooperative game models to distribute benefits. However, in this trading model, each data source seller usually formulates its own pricing strategy, resulting in decentralized distribution of benefits, and it is difficult for sellers of different data sources to achieve win-win results. Summary of the invention

[0004] Based on the above problems, the embodiments of the present application provide a data trading method, apparatus, device and storage medium based on multi-source data, with the aim of optimizing the pricing and revenue distribution of data products and achieving a win-win situation among data source sellers through a cooperative trading method of multi-source data.

[0005] In a first aspect, an embodiment of the present application provides a data transaction method based on multi-source data, including:

[0006] Obtaining value information of each of the data sources in the data product and the coupling relationship and coupling degree between each of the data sources;

[0007] Building a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between the data sources;

[0008] Solving the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source;

[0009] The transaction settlement of the data product is performed according to the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source.

[0010] In one embodiment, the data source includes endogenous data for describing the attributes of the data entity itself, and relational data for characterizing the interaction or association between data entities.

[0011] In one embodiment, the sellers of the data source include integration sellers corresponding to data products, data sellers corresponding to endogenous data, and data sellers corresponding to relational data.

[0012] In one embodiment, the data transaction model includes a revenue function, which is used to calculate the net revenue of the data product after deducting the total cost of each data source constituting the data product from the total transaction settlement revenue of the data product; solving the data transaction model to obtain the optimal pricing of the data product includes:

[0013] Generate multiple initial pricing within a preset pricing range;

[0014] For each of the initial prices, the initial prices are adjusted using a local optimization algorithm so that the revenue function converges toward the maximum value, thereby obtaining a local optimal price corresponding to each of the initial prices;

[0015] From the local optimal pricing corresponding to the multiple initial pricings, the local optimal pricing that maximizes the revenue function is obtained, and the local optimal pricing that maximizes the revenue function is used as the global optimal pricing.

[0016] In one embodiment, the local optimization algorithm includes at least one of the following: a gradient descent algorithm, a multi-start local optimization algorithm, a simulated annealing algorithm, and a particle swarm optimization algorithm.

[0017] In one embodiment, the data transaction model includes a Nash negotiation function, which is used to calculate the maximum gain of each seller; the gain represents the additional revenue obtained by the seller through cooperative sales of data sources over and above the case of independent sales of data sources; solving the data transaction model to obtain the optimal revenue distribution ratio of the sellers of each data source includes:

[0018] Using the Lagrange multiplier method to solve the maximization problem of the Nash negotiation function, and constructing the Lagrange function;

[0019] The Lagrangian function is solved to obtain the optimal distribution profit ratio corresponding to each seller of the data source.

[0020] In one embodiment, the data transaction model includes a Nash negotiation function, which is used to calculate the maximum gain of each seller; the gain represents the additional revenue obtained by the seller through cooperative sales of data sources over and above the case of independent sales of data sources; solving the data transaction model to obtain the optimal revenue distribution ratio of the sellers of each data source includes:

[0021] Using the Lagrange multiplier method to solve the maximization problem of the Nash negotiation function, and constructing the Lagrange function;

[0022] The Lagrangian function is solved to obtain the optimal distribution profit ratio corresponding to each seller of the data source.

[0023] In a second aspect, the embodiment of the present application further provides a data transaction device based on multi-source data, including:

[0024] An acquisition unit, used to acquire value information of each of the data sources in the data product and a coupling relationship and coupling degree between each of the data sources;

[0025] A model building unit, used to build a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between each data source;

[0026] A model solving unit, used to solve the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source;

[0027] The transaction settlement unit is used to perform transaction settlement for the data product according to the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source.

[0028] In a third aspect, an embodiment of the present application further provides a computer device, including:

[0029] CPU, memory, input and output interfaces;

[0030] The memory is a short-term storage memory or a persistent storage memory;

[0031] The central processing unit is configured to communicate with the memory and execute instruction operations in the memory to perform any one of the steps of the above-mentioned data transaction method based on multi-source data.

[0032] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is run on a computer, the steps of any one of the above-mentioned data trading methods based on multi-source data are executed.

[0033] In a fifth aspect, an embodiment of the present application further provides a computer program product having a computer program / instruction stored thereon, which, when executed by a processor, is used to implement any one of the above-mentioned data trading methods based on multi-source data.

[0034] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0035] The embodiment of the present application obtains the value information of each data source in the data product and the coupling relationship and degree between each data source; constructs a data transaction model based on the value information of each data source and the coupling relationship and degree between each data source; solves the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source; and performs transaction settlement of the data product based on the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source. Compared with the traditional one-to-one direct transaction method, the embodiment of the present application can form a richer and more comprehensive data product through multi-source data cooperation, improve the utilization rate and use value of the data source; by comprehensively considering the value of each data source, the coupling relationship and degree between the data sources, the optimal pricing of the data product and the optimal profit distribution ratio between the sellers are obtained, which not only promotes the cooperation between the sellers of each data source, but also avoids the problem of interest dispersion and improves the overall income of the data source sellers. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0037] Figure 1 A schematic diagram of a data transaction method based on multi-source data provided in an embodiment of the present application;

[0038] Figure 2 A schematic diagram of a data transaction system architecture based on multi-source data provided in an embodiment of the present application;

[0039] Figure 3 A schematic diagram of the structure of a data transaction device based on multi-source data provided in an embodiment of the present application;

[0040] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] 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 only 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.

[0042] In the era of big data, data has become a key production factor, and data trading is an important way to promote the circulation of data resources. The popularity of data trading has promoted data sharing and promoted the rapid development of various industries towards data-driven intelligence.

[0043] However, most existing data trading models adopt a one-to-one direct transaction method between data source sellers and data source buyers, and such trading methods mostly use non-cooperative game models to distribute benefits. However, in this trading model, each data source seller usually formulates its own pricing strategy, resulting in decentralized distribution of benefits, and it is difficult for sellers of different data sources to achieve win-win results.

[0044] Based on this, in each embodiment of the present application, sellers of multiple data sources cooperate to obtain data products composed of multiple data sources, and price the data products according to the value information, coupling relationship, and coupling degree of the multiple data sources, and determine the optimal profit distribution ratio among the sellers of each data source to achieve a win-win situation among the data source sellers. In addition, buyers can also integrate data products from multiple data sources to more accurately explore the correlation between data sources and further enhance the actual use value of the data source.

[0045] The various embodiments of the present application are described in further detail below in conjunction with the accompanying drawings.

[0046] The present application embodiment provides a data transaction method based on multi-source data, such as Figure 1 As shown, the method includes steps S101-S104.

[0047] S101: Obtain the value information of each data source in the data product and the coupling relationship and coupling degree between each data source.

[0048] Data products are tradable data assets that are composed of multiple data sources. They usually contain raw data or processed data sets from multiple sources, providing buyers with comprehensive information with commercial value. For example, a data product can be detailed information about consumer behavior, including content from different data sources such as social media, shopping preferences, and geographic location.

[0049] Data sources are the collection of raw data that make up data products. Different data sources contain different types of data information and can come from different suppliers / sellers. In the above data product example, data sources may include user activity data provided by social media platforms, shopping preference data provided by e-commerce platforms, and geographic location data provided by location services.

[0050] Different data sources can provide different values, and value information refers to the relative value contributed by each data source to the entire data product and the overall benefit effect on the data product. For example, if the data source of social media can directly affect the marketing strategy of the data product, then its value information may be higher; while other data sources with less influence have relatively lower values. It is understandable that buyers' purchasing behavior is usually based on their needs for different data sources, and the value information of different data sources has a certain impact on buyers' purchasing decisions.

[0051] The coupling relationship between different data sources indicates the correlation or dependency between different data sources. It can also be understood as the degree of influence of one data source on another. The coupling relationship can provide a more accurate consumer portrait in the initial integration stage of data products. The degree of coupling describes the strength of the association or dependency between data sources. The higher the degree of coupling, the closer the connection between these data sources, the stronger the complementarity in the data product, and the greater the contribution to the overall value. For example, there may be a coupling relationship between shopping data and social media data, and users' interests on social media often affect their shopping preferences. If the degree of coupling between geographic location data and shopping preference data is high, it means that the user's location has a strong influence on shopping preferences. This type of highly coupled data source combination forms a data product that can provide more contextualized value information.

[0052] Therefore, before building data products, it is first necessary to collect the value information of each data source, as well as the coupling relationship and degree of coupling between different data sources, so as to more reasonably build data products with higher value, determine pricing and profit distribution. Obtaining the value information, coupling relationship and degree of coupling of these data sources will help determine which data sources are more important and which combinations are more valuable, thereby achieving a more reasonable data trading strategy.

[0053] S102: Construct a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between the data sources.

[0054] S103: Solve the data transaction model to obtain the optimal pricing of data products and the optimal profit distribution ratio of sellers of various data sources.

[0055] Based on the value information, coupling relationship and coupling degree of each data source obtained above, a data transaction model is designed. In the embodiment of the present application, the data transaction model can be a data transaction model based on Nash equilibrium theory, which is used to calculate the pricing price of data products and the profit distribution ratio of each data source seller. For example, an optimization algorithm is used to solve the optimal pricing plan to ensure that the pricing price of the data product can maximize the profit of each data source seller. Furthermore, the pricing price and profit distribution ratio can be adjusted in real time considering market demand and buyer's willingness to purchase.

[0056] The profit ratio of each data source seller is calculated based on the Nash equilibrium theory. Specifically, the data trading model considers the independent value of each data source and the added value brought by the coupling relationship and degree of coupling to ensure that participating sellers can obtain higher profits than independent sales.

[0057] S104: Perform transaction settlement for data products based on the optimal pricing of the data products and the optimal profit distribution ratio of the sellers of each data source.

[0058] Based on the previously determined optimal pricing of data products and the optimal profit distribution ratio of each data source seller, the system will complete the transaction settlement of data products. At the time of transaction settlement, the system will charge the buyer according to this optimal pricing. After receiving the fees paid by the buyer, the system will distribute the total fees collected from the buyer according to the previously determined profit distribution ratio so that each seller can ultimately obtain the profit that matches the value of their data source and the degree of coupling, ensuring fair distribution of profits and achieving efficient automated transaction settlement.

[0059] Compared with the traditional one-to-one direct transaction method, it mainly focuses on the pricing model or data attributes of a single data source, fails to effectively solve the coordination problem between multi-source data, and cannot fully explore the inherent coupling relationship between different data sources, resulting in low data utilization efficiency, which hinders the further development of data-driven technology. However, the embodiment of the present application can form a richer and more comprehensive data product through multi-source data cooperation, improve the utilization rate and use value of the data source; integrating multiple data sources into one data product can reduce the time and communication cost of separate transactions between buyers and multiple sellers, thereby reducing the overall transaction cost and improving transaction efficiency. By comprehensively considering the value of each data source, the coupling relationship and degree of coupling between data sources, the optimal pricing of data products and the optimal profit distribution ratio between sellers are obtained, which not only promotes the cooperation between sellers of various data sources, but also maximizes the seller's profit, improves the overall profit of data source sellers, and achieves a win-win situation.

[0060] In one embodiment, the data source includes endogenous data for describing the attributes of the data entity itself, and relational data for characterizing the interaction or association between data entities.

[0061] Endogenous data refers to information that describes the attributes of a single data entity itself, that is, data that does not involve other entities. For example, customer attribute data (such as the customer's age, gender, place of residence, hobbies, etc.); product attribute data (such as product price, type, specifications, brand, etc.). Endogenous data can directly reflect the individual characteristics and utility of each data source, that is, the information value brought by endogenous data in an independent situation. For example, understanding the customer's attribute data can help sellers analyze customer characteristics, but this data does not involve the relationship between the customer and other entity data.

[0062] Relational data refers to information that describes the interaction or association between data entities, involving the relationship between two or more data entities. For example, transaction records are used to show the purchase behavior between customers and products, such as the number of times, frequency, and time when a customer purchased a certain product. Relational data combines different endogenous data to form interactive information between entities, which can show the interaction or association between different endogenous data, revealing related information that a single data source cannot provide, such as customer preferences, consumption behavior patterns, etc., further enhancing the actual use value of data.

[0063] In one embodiment, the sellers of data sources include integration sellers corresponding to data products, data sellers corresponding to endogenous data, and data sellers corresponding to relational data. Figure 2 , Figure 2 This is a schematic diagram of a data transaction system architecture based on multi-source data provided in an embodiment of the present application, showing the relationship between various roles in the data transaction process and the direction of data flow.

[0064] On the left side of the figure are data buyers, that is, individuals or institutions that need to purchase data. In the middle are integration sellers, who are responsible for integrating data from multiple data sources and providing them to data buyers. On the right side of the figure is the data source part, which is divided into two categories, namely endogenous data and relational data. Endogenous data is located in the upper right corner of the figure and includes multiple data sellers (such as data seller A and data seller B). Endogenous data describes the attribute data provided by each data seller separately, such as customer attributes or product attributes. Relational data is located in the lower right corner of the figure and is provided by data seller C. Relational data describes the association between data entities, such as transaction records between customers and products. The arrows of the data flow illustrate the flow of information and data between data buyers and integration sellers. Specifically, arrow 1 indicates that the data buyer sends data product purchase demand information to the integration seller, arrow 2 indicates that the integration seller analyzes the purchase demand of the data buyer and feeds back the required data source information obtained from the purchase demand to the corresponding data seller, arrow 3 indicates that the data buyer has completed the payment to the integration seller, and then each data seller transmits the data source to the integration seller, so that the integration seller can clean, analyze and integrate the received multiple data sources, and arrow 4 indicates that the integration seller provides data products to the data buyer.

[0065] The integration seller is responsible for collecting, deduplicating, cleaning, formatting and integrating multiple data sources during the data transaction process. The integration seller packages each data source into a complete data product and sells it to the data buyer, avoiding the problem of individual data source sellers setting their own prices and decentralized transactions, thereby achieving a win-win situation for all parties. In the data transaction architecture, the integration seller also plays the role of an intermediary platform and value-added service. Its existence simplifies the procurement process for data buyers, so that data buyers do not need to purchase and integrate data separately from multiple data sources, thereby reducing transaction costs and time costs and improving transaction efficiency. In addition, by cleaning and analyzing data, the integration seller can provide data products that are more valuable than a single data source. For example, by combining customer attribute data with transaction records, the integration seller can provide more in-depth customer behavior analysis or trend prediction, thereby enhancing the actual value of the data product.

[0066] In one embodiment, the data trading model includes a revenue function, which is used to calculate the net revenue of the data product after deducting the total cost of each data source constituting the data product from the total transaction settlement revenue; solving the data trading model to obtain the optimal pricing of the data product, including: generating multiple initial prices within a preset pricing range; for each initial price, using a local optimization algorithm to adjust the initial price so that the revenue function converges toward the maximum value, and obtaining the local optimal price corresponding to each initial price; from the local optimal prices corresponding to the multiple initial prices, obtaining the local optimal price that maximizes the revenue function, and using the local optimal price that maximizes the revenue function as the global optimal price.

[0067] Since there may be complex interactions and coupling relationships between data products, the shape of the revenue function is not a simple convex shape, but a non-convex shape with multiple local optimal points, making it difficult to find the global optimal pricing. Although the entire problem is non-convex, by decomposing the problem into multiple sub-problems, some sub-problems can be solved by convex optimization methods, or each sub-problem is a convex local optimal solution in a local area, and by evaluating multiple different local optimal solutions, the global optimal solution can be gradually approached. For example, in some cases, through methods such as Lagrange multiplier method and dual decomposition, the local problem in the non-convex optimization problem can be converted into solving a set of controllable equations or inequalities, and the global optimal solution can be directly obtained through mathematical derivation.

[0068] Exemplarily, it is assumed that multiple data sellers (A, B, C) in the advertising platform have different data sources, including user behavior data, interest data and purchase records. The combination of these data sources can provide advertisers and buyers with more accurate user portraits and advertising decision-making basis. Therefore, the pricing and revenue distribution of data products on the platform will be non-convex due to complex factors such as the value of different data sources and coupling relationships, resulting in multiple local optimal solutions. The specific solution process is as follows: Generate multiple initial prices within a preset pricing range through different initial pricing strategies (such as interval value selection, differentiated pricing). The pricing strategy needs to meet the needs of different buyers, that is, it is dynamically adjusted according to different auction requirements. For each initial price, the initial price is adjusted using a local optimization algorithm so that the revenue function converges to the maximum value, and the local optimal price corresponding to each initial price is obtained. In one embodiment, the local optimization algorithm includes at least one of the following: gradient descent algorithm, multi-start local optimization algorithm, simulated annealing algorithm, particle swarm optimization algorithm. Here, a method combining multi-start local optimization (Multi-Start Local Optimization) and simulated annealing can be used to solve:

[0069] Assume that the data trading model selects several initial prices, such as $10, $15, and $20 per thousand pieces of data, as the initial solutions for multi-start local optimization. Introduce small random disturbances near each initial pricing point (such as $10) to simulate multiple small-scale initial pricing adjustments.

[0070] It is understandable that buyers’ willingness to purchase is related to the pricing of data products. By analyzing historical transaction data, the data transaction model can learn the changes in market demand under different pricing. For example, it can learn the sales volume of past data products at different prices and identify the relationship between price and demand.

[0071] By testing the buyer's willingness to buy and the value of the benefit function through random perturbations (such as ±1 USD), the revenue corresponding to each initial price is obtained to reach a local optimal solution, that is, the best price found near the initial price. Through multiple iterations, the pricing converges to a local optimal point. For example, suppose that near the initial point of 10 USD, a stable local optimal point is adjusted to 12 USD, and near the initial pricing point of 15 USD, a stable local optimal point is adjusted to 16 USD. Finally, from all the local optimal pricing, the local optimal pricing that maximizes the revenue function is selected as the final optimal pricing of the data product. This method of determining the optimal pricing can ensure that the price of the data product can generate the highest net profit within the range acceptable to buyers, which not only protects the interests of sellers, but also takes into account changes in market demand and promotes win-win results for all parties.

[0072] The embodiment of the present application uses a revenue function and a local optimization algorithm to find the maximum value of the revenue function based on multiple initial pricing to determine the global optimal pricing. At the same time, by decomposing the complex non-convex optimization problem into sub-problems and deriving a closed-form solution, the challenges brought by non-convex optimization are overcome, thereby ensuring that the pricing and revenue distribution of data products reach the global optimal level.

[0073] In one embodiment, the data transaction model includes a Nash negotiation function, which is used to calculate the maximized gain of each seller; the gain represents the additional gain obtained by the seller through cooperative sale of data sources beyond the case of independent sale of data sources; the data transaction model is solved to obtain the optimal profit distribution ratio of the sellers of each data source, including: using the Lagrangian multiplier method to solve the maximization problem of the Nash negotiation function and constructing a Lagrangian function; solving the Lagrangian function to obtain the optimal distribution profit ratio corresponding to the sellers of each data source.

[0074] The Nash negotiation function is a mathematical function used in cooperative games to determine how multiple participants share benefits in a collaboration. In this data trading model, the Nash negotiation function is used to calculate the gain of each data source seller. Gain refers to the gain that a seller gains from selling data sources in collaboration over and above the gain when selling data sources alone. Sellers use Nash negotiations to determine the revenue distribution of joint data products, so that each seller can reasonably share the revenue according to the contribution of their data products to the joint product.

[0075] In order to find the optimal profit distribution ratio, the data trading model can use the Lagrange multiplier method to solve the maximization problem of the Nash negotiation function. The Lagrange multiplier method is an optimization algorithm that is suitable for optimization problems with constraints. In this model, the constraint condition can be that the distribution of total profit is equal to the total cooperation profit.

[0076] Specifically, we can first construct a Lagrangian function, combine the Nash negotiation function and the constraints, and ensure that the optimal profit distribution ratio is found when the conditions are met. After constructing the Lagrangian function, we can find the solution to the optimal profit distribution ratio by taking the derivative of each variable and setting the derivative to zero.

[0077] For example, the Nash negotiation function can be set to max(P A -D A )*(P B -D B )*(P C -D C )

[0078] Among them, P A , P B , P C are the final profits allocated to sellers A, B, and C respectively; D A , D B , D C They are the threat points of sellers A, B, and C respectively. The threat point can be the profit when the data source is sold separately.

[0079] Define the total value V of the data product total , total value V total It is expressed as the sum of the independent value of each data source and the coupling gain;

[0080] To ensure that the total allocation is equal to the total value of the data product V total , add constraints:

[0081] V total =V A +V B +V C +C AB +C AC +C BC

[0082] Among them, V A 、V B 、V C are the independent values ​​of data sources A, B, and C respectively; C AB The additional utility brought by the combination of data source A and data source B, C AC The additional utility brought by the combination of data source A and data source C, BC The additional utility brought to the combination of data source B and data source C.

[0083] Construct the Lagrangian function to solve for the optimal allocation:

[0084] L=(P A -D A )*(P B-D B )*(P C -D C )+λ(V total -P A -P B -P C )

[0085] P A , P B , P C , λ respectively and set them to zero, and we get P A ′、P B ′、P C The value of ′ corresponds to the optimal profit distribution ratio of sellers A, B, and C, and determines P A ′、P B ′、P C ′ satisfies the constraint conditions and the profit of each seller exceeds its threat point, then determine P A ′: P B ′: P C ′ is the optimal profit distribution ratio.

[0086] It should be noted that the independent value of the data source and the additional utility brought by the coupling between different data sources can be set through experimental data and experience, and can also be calculated through algorithms such as machine learning and reinforcement learning, which is not limited in this embodiment of the present application.

[0087] The embodiment of the present application incorporates the coupling relationship between data sources into the data transaction model, uses the Nash negotiation function type and the two-stage Stackelberg game, and can reasonably distribute the benefits and formulate the optimal pricing to maximize the seller's profit. In the data transaction system architecture based on multi-source cooperation provided by the embodiment of the present application, in the first stage of the Stackelberg game, multiple data sellers jointly set prices based on the Nash negotiation framework, and negotiate the proportion of transaction revenue distribution, comprehensively consider the degree of coupling of data products, and use the optimal pricing strategy to improve overall revenue. In the second stage, buyers make purchasing decisions based on the set price. Buyers' decisions are based on their needs for endogenous data and relational data. At the same time, the degree of coupling between these data affects the overall utility of buyers.

[0088] Furthermore, when determining the optimal pricing and optimal profit distribution ratio, a prediction model based on machine learning or deep learning algorithms can be introduced to analyze data market trends in real time and dynamically adjust pricing strategies. At the same time, the data trading framework can be deployed on cloud platforms, such as Amazon Web Services (AWS) and Microsoft's cloud computing platform Azure, to use its elastic computing resources to process large-scale data transactions and queries, integrate and query real-time data, ensure seamless collaboration and transactions of multi-source data, and meet data needs of different scales.

[0089] The data transaction method based on multi-source cooperation provided in the embodiment of the present application can also be deployed in a distributed architecture. Multiple independent data sources can collaborate through the network, and each data source is connected to the central transaction system through an API to realize the generation and pricing of joint data. It is suitable for scenarios where data sources are widely distributed and can support efficient data integration and real-time transactions.

[0090] Furthermore, the embodiments of the present application can be applied to the trading platform of the auction mechanism, supporting multiple data sellers to jointly auction data products by setting the starting price and profit distribution mechanism through cooperation. During the auction, the system can dynamically adjust the price according to the buyer's bid, thereby maximizing the seller's profit.

[0091] In order to implement the data transaction method based on multi-source data in the embodiment of the present application, the embodiment of the present application also provides a data transaction device based on multi-source data, such as Figure 3 As shown, the device comprises:

[0092] An acquisition unit 301 is used to acquire value information of each of the data sources in the data product and a coupling relationship and coupling degree between each of the data sources;

[0093] A model building unit 302, configured to build a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between each data source;

[0094] A model solving unit 303 is used to solve the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source;

[0095] The transaction settlement unit 304 is used to perform transaction settlement for the data product according to the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source.

[0096] In one embodiment, the data source includes endogenous data for describing the attributes of the data entity itself, and relational data for characterizing the interaction or association between data entities.

[0097] In one embodiment, the sellers of the data source include integration sellers corresponding to data products, data sellers corresponding to endogenous data, and data sellers corresponding to relational data.

[0098] In one embodiment, the data transaction model includes a revenue function, which is used to calculate the net revenue after deducting the total cost of each data source constituting the data product from the total transaction settlement revenue of the data product;

[0099] The processing unit is further used to generate a plurality of initial prices within a preset pricing range;

[0100] The processing unit is further configured to adjust each of the initial prices using a local optimization algorithm so that the revenue function converges toward a maximum value, thereby obtaining a local optimal price corresponding to each of the initial prices;

[0101] The processing unit is also used to obtain the local optimal pricing that maximizes the profit function from the local optimal pricing corresponding to the multiple initial pricings, and use the local optimal pricing that maximizes the profit function as the global optimal pricing.

[0102] In one embodiment, the local optimization algorithm includes at least one of the following: a gradient descent algorithm, a multi-start local optimization algorithm, a simulated annealing algorithm, and a particle swarm optimization algorithm.

[0103] In one embodiment, the data transaction model includes a Nash negotiation function, which is used to calculate the maximum gain of each seller; the gain represents the additional gain obtained by the seller through cooperative sale of data sources over and above the case of independent sale of data sources;

[0104] The processing unit is further used to solve the maximization problem of the Nash negotiation function by using the Lagrange multiplier method and construct a Lagrangian function;

[0105] The processing unit is further used to solve the Lagrangian function to obtain the optimal distribution profit ratio corresponding to each seller of the data source.

[0106] In actual application, the processing unit can be realized by a processor in a computer device combined with a communication interface, and the acquisition unit 301, the model building unit 302, the model solving unit 303, and the transaction settlement unit 304 can be realized by a communication interface in a data transaction device based on multi-source data.

[0107] It should be noted that: the above embodiment provides a data transaction device based on multi-source data. When performing data transactions based on multi-source data, only the division of the above program modules is used as an example. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device is divided into different program modules to complete all or part of the processing described above. In addition, the data transaction device based on multi-source data provided in the above embodiment and the data transaction method embodiment based on multi-source data belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0108] Based on the hardware implementation of the above program modules, and in order to implement a data transaction method based on multi-source data provided in the embodiment of the present application, the embodiment of the present application also provides a computer device, such as Figure 4 As shown, the computer device 400 includes:

[0109] CPU 401, memory 402 and input / output interface 403;

[0110] The memory 402 is a temporary storage memory or a permanent storage memory;

[0111] The central processor 401 is configured to communicate with the memory 402 and execute instructions in the memory 402 to perform any step of the above-mentioned data transaction method based on multi-source data.

[0112] Of course, in actual application, the various components in the computer device 400 are coupled together through the bus system 404. It can be understood that the bus system 404 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 404 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 4 Various buses are labeled as bus system 404 .

[0113] The memory 402 in the embodiment of the present application is used to store various types of data to support the operation of the computer device 400. Examples of such data include: any computer program used to operate on the computer device 400.

[0114] It is understandable that when the processor in the computer device described above executes the computer program, it can also implement the functions of the various units in the above-mentioned corresponding device embodiments, which will not be repeated here. Exemplarily, the computer program can be divided into one or more modules / units, one or more modules / units are stored in the memory, and executed by the processor to complete the various embodiments of the present application. One or more modules / units can be a series of computer program instruction segments that can perform specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device. For example, the computer program can be divided into the various units in the above-mentioned computer device, and each unit can implement the specific functions described in the above-mentioned corresponding computer device.

[0115] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the processor and the memory are merely examples of computer devices and do not constitute a limitation on the computer device. The computer device may include more or fewer components, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0116] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0117] The memory can be used to store computer programs and / or modules. The processor implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the terminal, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SMC, Smart Media Card), a secure digital (SD, Secure Digital) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0118] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is run on a computer, the steps of any one of the above-mentioned data transaction methods based on multi-source data are executed.

[0119] An embodiment of the present application also provides a computer program product having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, it is used to implement the data trading method based on multi-source data described in the first aspect of the embodiment of the present application or any specific implementation method of the first aspect.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

Claims

1. A data trading method based on multi-source data, characterized in that: include: Obtaining value information of each of the data sources in the data product and the coupling relationship and coupling degree between each of the data sources; Building a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between the data sources; Solving the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source; The transaction settlement of the data product is performed according to the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source.

2. The data transaction method based on multi-source data according to claim 1, characterized in that: The data source includes endogenous data for describing the attributes of the data entity itself, and relational data for characterizing the interaction or association between data entities.

3. The data transaction method based on multi-source data according to claim 2, characterized in that: The sellers of the data sources include integration sellers corresponding to data products, data sellers corresponding to endogenous data, and data sellers corresponding to relational data.

4. The data transaction method based on multi-source data according to claim 1, characterized in that: The data transaction model includes a revenue function, which is used to calculate the net revenue of the data product after deducting the total cost of each data source constituting the data product from the total transaction settlement revenue of the data product; Solving the data transaction model to obtain the optimal pricing of the data product includes: Generate multiple initial pricing within a preset pricing range; For each of the initial prices, the initial prices are adjusted using a local optimization algorithm so that the revenue function converges toward the maximum value, thereby obtaining a local optimal price corresponding to each of the initial prices; From the local optimal pricing corresponding to the multiple initial pricings, the local optimal pricing that maximizes the revenue function is obtained, and the local optimal pricing that maximizes the revenue function is used as the global optimal pricing.

5. The data transaction method based on multi-source data according to claim 4, characterized in that: The local optimization algorithm includes at least one of the following: gradient descent algorithm, multi-start local optimization algorithm, simulated annealing algorithm, particle swarm optimization algorithm.

6. The data transaction method based on multi-source data according to claim 1, characterized in that: The data transaction model includes a Nash negotiation function, which is used to calculate the maximum gain of each seller; the gain represents the additional gain obtained by the seller through cooperative sale of data sources over and above the case of independent sale of data sources; Solving the data transaction model to obtain the optimal profit distribution ratio of the sellers of each data source includes: Using the Lagrange multiplier method to solve the maximization problem of the Nash negotiation function, and constructing the Lagrange function; The Lagrangian function is solved to obtain the optimal distribution profit ratio corresponding to each seller of the data source.

7. A data transaction device based on multi-source data, characterized in that: include: An acquisition unit, used to acquire value information of each of the data sources in the data product and a coupling relationship and coupling degree between each of the data sources; A model building unit, used to build a data transaction model based on the value information of each data source and the coupling relationship and coupling degree between each data source; A model solving unit, used to solve the data transaction model to obtain the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source; The transaction settlement unit is used to perform transaction settlement for the data product according to the optimal pricing of the data product and the optimal profit distribution ratio of the sellers of each data source.

8. A computer device, characterized in that: include: CPU, memory and input / output interface; The memory is a short-term storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute instruction operations in the memory to perform the data transaction method based on multi-source data as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is run on a computer, the data transaction method based on multi-source data as claimed in any one of claims 1 to 6 is executed.

10. A computer program product having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, they are used to implement the data trading method based on multi-source data as described in any one of claims 1 to 6.

Images