An agricultural product supply chain investment return pricing system based on emerging information services

Abstract

The present application relates to the field of modern agricultural equipment and information technology, in particular to a kind of agricultural product supply chain investment return pricing system based on emerging information service, comprising the following modules: blockchain storage module, for collecting the explicit investment cost and implicit investment cost data of producer, processor, logistics company, seller in agricultural product supply chain;Cost refinement accounting module is connected with the blockchain storage module;Dynamic income iteration module is connected with the cost refinement accounting module;Game equilibrium pricing module is connected with the dynamic income iteration module.The present application accurately records and accounts various costs invested by each party in agricultural product supply chain through blockchain technology, solves the problem that cost data is easy to be tampered with, scattered and inaccurate in traditional mode, and enables producers and sellers to clearly see the cost of each investment, making income calculation and pricing more real and reliable.

Description

Technical Field

[0001] This invention relates to the field of modern agricultural equipment and information technology, specifically to an agricultural product supply chain investment return pricing system based on emerging information services. Background Technology

[0002] The agricultural product supply chain is the core of production, sales and circulation, directly affecting market supply and industry efficiency. The domestic agricultural product supply chain model is traditional and highly fragmented, with loose connections between production and sales links, lacking a unified digital and standardized management mechanism. Industry cost statistics and pricing are relatively scattered, failing to meet the needs of refined agricultural products.

[0003] Currently, the pricing of agricultural product supply chain operations suffers from fragmented cost data across various stages, encompassing both explicit and implicit expenditures. This data is prone to distortion and tampering, leading to inaccurate and ambiguous cost accounting. Agricultural product pricing often relies on subjective judgment based on human experience, lacking scientific basis. Furthermore, the return on investment in the supply chain is difficult to quantify, making it impossible to clearly determine the input-output benefits. According to the authorization announcement number CN120219103A, an intelligent sales management system for agricultural products based on AI digital humans is disclosed. This system addresses the problem that existing technologies cannot comprehensively analyze sales volume, price, and environmental factors to construct sales trend prediction models, failing to provide a comprehensive perspective to improve prediction accuracy and support enterprises in rapidly responding to market dynamics. This invention utilizes historical sales and meteorological data to construct a sales trend prediction model, offering significant advantages. It comprehensively analyzes sales volume, price, and environmental factors, providing a comprehensive perspective to improve prediction accuracy. By generating a sales trend prediction feature vector, this module can instantly predict future sales changes, supporting enterprises in rapidly responding to market dynamics and optimizing inventory, pricing, and marketing strategies.

[0004] Traditional static fixed-coefficient accounting models cannot adapt to dynamic market changes such as seasonality, supply and demand, market conditions, and losses of agricultural products, resulting in large errors in profit calculation. At the same time, traditional pricing only pursues the maximization of profits for a single entity, ignoring the balance of interests between upstream and downstream, which can easily lead to production and sales conflicts. The pricing scheme has poor feasibility and scenario adaptability. Summary of the Invention

[0005] The purpose of this invention is to provide an agricultural product supply chain investment return pricing system based on emerging information services to solve the problems mentioned in the background art.

[0006] To address the aforementioned problems, this invention provides a technical solution: an agricultural product supply chain investment return pricing system based on emerging information services, comprising the following modules:

[0007] The blockchain evidence storage module is used to collect explicit and implicit investment cost data of producers, processors, logistics providers and sellers in the agricultural product supply chain. After performing hash calculation on the cost data, it is uploaded to the blockchain network to generate an immutable cost evidence storage record and timestamp index.

[0008] The cost refinement accounting module is connected to the blockchain evidence storage module. It is used to classify and collect the cost evidence records according to standardized cost items, calculate the unit agricultural product investment cost of each entity, and output a reliable cost dataset.

[0009] The dynamic revenue iteration module, connected to the cost refinement calculation module, is used to receive the trusted cost dataset and access external big data sources to obtain market data, consumer preference data, and circulation loss data. Based on the trusted cost dataset and external big data, the revenue coefficient is iteratively optimized to generate a dynamic revenue calculation model.

[0010] The game equilibrium pricing module, connected to the dynamic revenue iteration module, is used to construct a non-cooperative game equilibrium model by taking the revenue functions of each entity in the supply chain output by the dynamic revenue accounting model as input, solving the Nash equilibrium solution through adaptive weight adjustment, and outputting a pricing decision signal.

[0011] Preferably, the explicit investment costs include the cost of purchasing production equipment, the cost of constructing cold chain facilities, the cost of deploying information technology systems, and the cost of investing in quality inspection equipment;

[0012] The hidden investment costs include brand building amortization costs, supply chain collaborative management costs, technology training sunk costs, and inventory holding opportunity costs.

[0013] Preferably, the refined cost accounting module uses a unit investment cost accounting formula to classify and aggregate the various entities:

[0014] Let the first The supply chain entity in the first Within each time period, its set of explicit cost items is as follows: The set of hidden cost items is The yield per unit of agricultural product is Then the unit investment cost of this entity for:

[0015]

[0016] Both explicit and implicit cost items are included in the calculation after their authenticity is verified by the hash verification value of the blockchain notarization module.

[0017] Preferably, the dynamic revenue iteration module has a built-in revenue coefficient iteration optimization submodule, which uses a dynamic revenue coefficient update formula to correct the input-output conversion rate of each entity in the supply chain in real time: Let the first... The actual output revenue of each entity in period t is Based on the previous cycle's return coefficient Compared with unit investment cost The calculated predicted returns are Then the return coefficient for this period Updated to:

[0018]

[0019] in, The learning rate parameter is preset and its value range is (0,1].

[0020] The market data, consumer preference data, and circulation loss data are used to adjust actual output returns. The backpropagation weights.

[0021] Preferably, the dynamic revenue calculation model output by the dynamic revenue iteration module includes a comprehensive revenue function, used to calculate the short-term and long-term revenues of the supply chain entity:

[0022] Let the first The unit investment cost sequence for each entity within a short-term window T is as follows: , The unit output sequence is Then the short-term overall return for:

[0023]

[0024] Long-term comprehensive income Introducing a decay factor based on the aforementioned short-term returns. And calculates on a rolling basis according to the preset number of cycles N:

[0025] .

[0026] Preferably, when constructing the non-cooperative game equilibrium model, the game equilibrium pricing module uses the payoff functions of each entity in the supply chain. Let be the payment function, where, For the first Pricing decision variables for individual entities The total number of participants in the game; the game equilibrium pricing module uses a Nash equilibrium solver and calculates the pricing combination that satisfies the following conditions through an iterative optimal response algorithm. :

[0027] For any subject and its arbitrary feasible pricing All have ,in To remove the main body The equilibrium pricing vector of other entities.

[0028] Preferably, the game equilibrium pricing module includes a weight adaptive adjustment submodule, used to allocate dynamic game weights to different supply chain entities, wherein the dynamic game weights are based on the volatility of each entity's unit investment cost. elasticity coefficient with market acceptance Adaptive adjustment:

[0029] Set the main body The basic weight is Then the adaptively adjusted weights for:

[0030]

[0031] in, This is an adjustment coefficient, with a value range of [0,1].

[0032] The Nash equilibrium solver calculates the social welfare function after weighted summation. Search for an equilibrium solution under constraints.

[0033] Preferably, the cost evidence record output by the blockchain evidence storage module includes the plaintext hash value of the cost data, the timestamp, the hash value of the previous block, and the digital signature of the evidence storage subject;

[0034] The refined cost accounting module retrieves the corresponding blockchain evidence record for any cost data to be accounted for and performs a hash comparison. Only when the comparison matches will the cost data be included in the accounting.

[0035] Preferably, the external big data sources accessed by the dynamic revenue iteration module include: agricultural product wholesale market price information interface, e-commerce platform sales data interface, meteorological data service interface, and logistics loss monitoring data interface;

[0036] The dynamic revenue iteration module triggers daily or weekly updates of the revenue coefficient and synchronizes the updated dynamic revenue calculation model parameters to the game equilibrium pricing module.

[0037] Preferably, the pricing decision signal output by the game equilibrium pricing module includes the following fields: pricing entity identifier, target agricultural product category code, suggested lower and upper limits of the pricing range, game equilibrium valuation, effective pricing time window, and predicted revenue distribution ratio of each supply chain entity. The pricing decision signal is encrypted and then pushed to the terminal devices of each supply chain entity.

[0038] The beneficial effects of this invention are reflected in:

[0039] 1. This invention uses blockchain technology to accurately record and calculate the various costs invested by all parties in the agricultural product supply chain, solving the problems of cost data being easily tampered with, scattered and inaccurate in the traditional model. It enables producers and sellers to clearly see the cost of each investment, making revenue calculation and pricing more real and reliable.

[0040] 2. This invention uses big data technology to capture market price fluctuations, seasonal changes, consumer preferences, and losses during transportation. Combined with the accurate cost data obtained in the first point, it continuously adjusts and optimizes the revenue calculation method, so that the revenue model is no longer rigid and can be corrected in real time with market changes, thereby more accurately predicting the actual returns that all parties can obtain in the short and long term.

[0041] 3. Based on the ability to dynamically calculate revenue, this invention introduces a game equilibrium algorithm to formulate a pricing strategy. Instead of focusing solely on maximizing the interests of one party, it simultaneously considers three aspects: the producer's desire to recoup investment, the seller's desire to make a profit, and the consumer's ability to accept the price. By automatically adjusting the weights of each party, it finds a balance point and ultimately provides a pricing scheme with controllable costs and satisfactory benefits for all parties. Attached Figure Description

[0042] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0043] Figure 1 This is a schematic diagram of the supply chain cost data storage and accounting process of the present invention;

[0044] Figure 2 This is a schematic diagram of the dynamic revenue iteration and game equilibrium pricing process of the present invention;

[0045] Figure 3 This is a schematic diagram of the multi-agent game equilibrium pricing decision output flow of the present invention. Detailed Implementation

[0046] The embodiments of the technical solution of the present invention will now be described in detail with reference to the accompanying drawings. These embodiments are merely illustrative of the technical solution of the present invention and are therefore intended to limit the scope of protection of the present invention.

[0047] It should be noted that, unless otherwise stated, the technical or scientific terms used in this application should have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.

[0048] Example 1

[0049] like Figures 1-3 As shown, an agricultural product supply chain investment return pricing system based on emerging information services includes the following modules:

[0050] The blockchain evidence storage module is used to collect explicit and implicit investment cost data of producers, processors, logistics providers and sellers in the agricultural product supply chain. After hashing the cost data, it is uploaded to the blockchain network to generate an immutable cost evidence storage record and timestamp index.

[0051] The cost refinement accounting module is connected to the blockchain evidence storage module. It is used to classify and collect cost evidence records according to standardized cost items, calculate the unit agricultural product investment cost of each entity, and output a reliable cost dataset.

[0052] The dynamic revenue iteration module, connected to the cost refinement calculation module, is used to receive a reliable cost dataset and access external big data sources to obtain market data, consumer preference data, and circulation loss data. Based on the reliable cost dataset and external big data, the revenue coefficient is iteratively optimized to generate a dynamic revenue calculation model.

[0053] The game equilibrium pricing module, connected to the dynamic revenue iteration module, is used to construct a non-cooperative game equilibrium model by taking the revenue functions of each entity in the supply chain output by the dynamic revenue accounting model as input. It solves the Nash equilibrium solution through adaptive weight adjustment and outputs the pricing decision signal. The Nash equilibrium solver adopts an iterative optimal response algorithm, with a maximum number of iterations of 500 and a convergence threshold of 0.01. When the price change in two consecutive iterations is lower than the convergence threshold, the iteration is terminated and the equilibrium solution is output.

[0054] The Nash equilibrium solver employs an iterative optimal response algorithm, and the specific implementation steps are as follows:

[0055] S1. Set the initial pricing combination Let the number of iterations be... Preset maximum number of iterations Convergence threshold ;

[0056] S2, For each supply chain entity In the current pricing mix of other entities Under the condition that remains unchanged, solve the main body Optimal response pricing:

[0057]

[0058] in, as the main body The payoff function, as the main body The feasible pricing range;

[0059] S3. Calculate the maximum price fluctuation for all entities:

[0060]

[0061] like or If the iteration fails, proceed to step S4; otherwise, proceed to step S5.

[0062] S4, Output Nash Equilibrium Pricing Combination ;

[0063] S5, Order Return to step S2 and continue execution.

[0064] Furthermore, explicit investment costs include the cost of purchasing production equipment, the cost of constructing cold chain facilities, the cost of deploying information technology systems, and the cost of investing in quality inspection equipment;

[0065] Hidden investment costs include brand building amortization costs, supply chain collaborative management costs, technology training sunk costs, and inventory holding opportunity costs.

[0066] Furthermore, the refined cost accounting module uses a unit investment cost accounting formula to classify and aggregate the various entities involved:

[0067] Let the first The supply chain entity in the first Within each time period, its set of explicit cost items is as follows: The set of hidden cost items is The yield per unit of agricultural product is Then the unit investment cost of this entity for:

[0068]

[0069] Both explicit and implicit cost items are included in the calculation after their authenticity is verified by the hash verification value of the blockchain notarization module.

[0070] Furthermore, the dynamic revenue iteration module incorporates a revenue coefficient iteration optimization submodule, which uses a dynamic revenue coefficient update formula to perform real-time correction of the input-output conversion rate of each entity in the supply chain: Let the... The actual output revenue of each entity in period t is Based on the previous cycle's return coefficient Compared with unit investment cost The calculated predicted returns are Then the return coefficient for this period Updated to:

[0071]

[0072] in, The learning rate parameter is a preset value, ranging from (0,1]. The value is adaptively determined based on the degree of market volatility: when the price volatility in the external big data source exceeds 20%, The value is set between 0.6 and 1.0 to achieve a rapid response; when price volatility is below 5%, The value is set between 0.1 and 0.3 to maintain model stability; otherwise... The value ranges from 0.3 to 0.6. The volatility figures above are calculated based on data from the past 7 trading days.

[0073] Market data, consumer preference data, and circulation loss data are used to adjust actual output returns. The backpropagation weights.

[0074] Furthermore, the dynamic revenue calculation model output by the dynamic revenue iteration module includes a comprehensive revenue function, used to calculate the short-term and long-term revenues of the supply chain entity:

[0075] Let the first The unit investment cost sequence for each entity within a short-term window T is as follows: , The unit output sequence is Then the short-term overall return for:

[0076]

[0077] Long-term comprehensive income Introducing a decay factor based on the aforementioned short-term returns. And calculates on a rolling basis according to the preset number of cycles N:

[0078] .

[0079] Furthermore, when constructing the non-cooperative game equilibrium model, the game equilibrium pricing module uses the payoff functions of each entity in the supply chain. Let be the payment function, where, For the first Pricing decision variables for individual entities The total number of participants in the game; the game equilibrium pricing module uses a Nash equilibrium solver and calculates the pricing combination that satisfies the following conditions through an iterative optimal response algorithm. :

[0080] For any subject and its arbitrary feasible pricing All have ,in To remove the main body The equilibrium pricing vector of other entities.

[0081] Furthermore, the game equilibrium pricing module includes a weight adaptive adjustment submodule, which is used to assign dynamic game weights to different supply chain entities. The dynamic game weights are based on the volatility of each entity's unit investment cost. elasticity coefficient with market acceptance Adaptive adjustment:

[0082] Set the main body The basic weight is Then the adaptively adjusted weights for:

[0083]

[0084] in, This is an adjustment coefficient, with a value range of [0,1].

[0085] The Nash equilibrium solver for the weighted summation of the social welfare function Search for an equilibrium solution under constraints;

[0086] When the volatility of unit investment cost When the value is higher than the preset threshold of 0.2, The value is automatically set to 0.7-1.0, based on the market acceptance elasticity coefficient. When the value is higher than the preset threshold of 0.5, The value is automatically set to 0-0.3.

[0087] Furthermore, the cost evidence record output by the blockchain evidence storage module includes the plaintext hash value of the cost data, timestamp, hash value of the previous block, and digital signature of the evidence storage subject;

[0088] The cost refinement accounting module retrieves the corresponding blockchain evidence record for any cost data to be accounted for and performs a hash comparison. Only when the comparison matches will the cost data be included in the accounting.

[0089] Furthermore, the external big data sources accessed by the dynamic revenue iteration module include: agricultural product wholesale market price information interface, e-commerce platform sales data interface, meteorological data service interface, and logistics loss monitoring data interface;

[0090] The dynamic revenue iteration module triggers daily or weekly updates of the revenue coefficients and synchronizes the updated dynamic revenue calculation model parameters to the game equilibrium pricing module.

[0091] Furthermore, the pricing decision signal output by the game equilibrium pricing module includes the following fields: pricing entity identifier, target agricultural product category code, suggested lower and upper limits of the pricing range, game equilibrium pricing value, effective pricing time window, and predicted revenue distribution ratio of each supply chain entity. The pricing decision signal is encrypted and then pushed to the terminal devices of each supply chain entity.

[0092] Example 2

[0093] Based on the full-chain implementation of the peach agricultural product supply chain, a peach from a certain production area was selected as the target agricultural product. The supply chain involves: fruit farmers - producers, cold chain transporters - logistics providers, regional wholesalers - processors / transferrs, and community fresh food chain stores - retailers.

[0094] The process includes:

[0095] A1. Data on the blockchain: Fruit farmers write the costs of fertilizer and seedling purchases and the sunk costs of technical training into the blockchain to generate a timestamp index. Cold chain transporters automatically collect and upload cold storage electricity costs, equipment depreciation, and inventory holding opportunity costs through IoT sensors. Each evidence record contains a data hash value and a digital signature of the main entity to prevent reconciliation tampering.

[0096] A2. Detailed Cost Accounting: Calculate the unit investment cost for the listing period in May (t=1) and the closing period in August (t=2). Substituting the formula: fruit farmer's yield Q = 5000 kg, explicit cost set E = {30000 yuan}, implicit cost set Im = {5000 yuan}, we get... =(30000+5000) / 5000=7 yuan / kg;

[0097] A3. Dynamic Revenue Iteration: Integrating meteorological data, high temperatures caused the loss rate to rise from 5% to 15%, while e-commerce platforms showed that the retail price of peaches during the same period dropped from 12 yuan / kg to 9 yuan / kg. Dynamic revenue coefficient updates are then implemented: [Settings omitted for brevity]. =0.3, previous cycle =0.8, actual output revenue decreased in this cycle. The formula is recalculated to 0.65, representing the short-term comprehensive return SR and the long-term return LR, along with the decay factor. =0.9, outputting two different forecasts respectively;

[0098] A4. Game Equilibrium Pricing: Construct a three-party non-cooperative game, fruit farmers-wholesalers-retailers, and run the Nash equilibrium solver for 200 iterations;

[0099] Weighted adaptive adjustment: Fruit farmer cost volatility High, assigned a weight of 0.5; market acceptance elasticity coefficient High retailer weighting decreases;

[0100] Output pricing signal: Suggested retail price range [14.5 yuan / kg, 16.2 yuan / kg], equilibrium value 15.3 yuan / kg, effective time window 7 days.

[0101] Verification results: Under traditional pricing, wholesalers drive down prices to 10 yuan / kg, causing losses for fruit farmers; Example 2 output pricing enables the profit distribution ratio of all parties to reach 2:3:5, and the overall profit of the supply chain increases by 22%.

[0102] Example 3

[0103] Based on the implementation of a cross-regional, multi-seasonal bulk grain supply chain, this study focuses on the japonica rice supply chain, involving: large-scale planting cooperatives, railway + highway joint logistics providers, provincial grain reserves, and nationwide supermarket chains. The time span covers both the autumn harvest season and the lean season.

[0104] Specific procedures:

[0105] B1. Data Structure Storage: The cooperative will put land transfer fees, combine harvester rental fees, brand geographical indication amortization, and sunk costs of order defaults on the blockchain in batches. The logistics provider will encrypt and store railway trunk freight and highway short-haul floating freight separately to ensure that costs across transportation modes can be separated and traced.

[0106] B2. Multi-period cost accounting: The unit cost for October and May of the following year is calculated using the formula in claim 3. Long-term comprehensive income (LR) is calculated on a rolling basis: N = 4 quarters. =0.85, providing a basis for the decision on whether the cooperative should reserve 30% of high-quality rice for delayed sale;

[0107] B3. Big Data-Driven Dynamic Iteration: By accessing the national wholesale market data API, we discovered changes in the elasticity of domestic japonica rice demand caused by the impact of Southeast Asian rice imports, and the dynamic return coefficient. Adjusted to a modified model that includes import substitution factors: ,in, The import substitution coefficient is the proportion of imported agricultural products in the market. The trigger cycle is every two weeks. It is more suitable for grain products with long storage periods than Example 2.

[0108] B4. Game Equilibrium and Weight Adaptation: Introducing the National Minimum Purchase Price as an External Constraint;

[0109] Weight adaptive adjustment: Cooperatives suffer from high volatility in storage costs =0.3 receives a high weight, while provincial grain depots have a lower weight due to their low elasticity coefficient;

[0110] Output pricing signal: Includes a minimum support price field; equilibrium pricing is 8% higher than the support price.

[0111] Verification results: Under the traditional model, the cooperative misjudged the market during the lean season, resulting in inventory backlog; Example 3, through long-term rolling calculation of returns, suggests locking in forward contracts 2 months in advance, reducing warehousing costs by 18%.

[0112] Example 4

[0113] Based on the implementation of a high-value, short-shelf-life fresh emergency supply chain, two comparative categories were selected: imported cherries and local bayberries. The supply chain involved: overseas farms / local farmers, port / airport logistics, e-commerce live streaming sellers, and community group buying platforms.

[0114] Specific procedures:

[0115] C1. High-frequency evidence storage and rapid accounting: For bayberries with a 48-hour loss rate of up to 30%, data on cold chain temperature and cost losses caused by packaging damage are uploaded once per hour. The blockchain evidence storage adds an instant verification function: any node that uploads abnormal data will automatically trigger a cost warning.

[0116] C2. Short-window dynamic return coefficient update: learning rate The default value of 0.3 has been increased to 0.8, enabling the return coefficient to respond quickly to market fluctuations. The short-term comprehensive return SR calculation window T has been shortened to 24 hours, replacing the conventional weekly window.

[0117] C3. Special constraints of game equilibrium: A dual game of price and sales volume is formed between e-commerce sellers and community group buying platforms. The Nash equilibrium solver adds a sales volume prediction regression term, and the weight adaptive adjustment introduces a freshness loss weight: the bargaining power of logistics companies with a loss rate of more than 20% is temporarily restricted in the game.

[0118] Output pricing signals: Add a field for real-time suggested price adjustment instructions, which will be updated every 4 hours;

[0119] C4. Cost Accuracy: Blockchain records the hidden costs of each stage of the bayberry's journey from the branch to cold storage, making... The accuracy reaches 0.01 yuan / piece;

[0120] Dynamic iteration: Precise cost data enables The iteration error was reduced from ±15% in the traditional model to ±3%.

[0121] Verification results: Traditional systems cannot handle the instantaneous traffic of live-streaming e-commerce, and pricing delays lead to losses; Example 4: During a major e-commerce promotion, the system automatically adjusted the price of cherries from 79 yuan / jin to 105 yuan / jin, increasing the gross profit margin by 12 percentage points, and no return wave occurred.

[0122] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A pricing system for investment returns in the agricultural product supply chain based on emerging information services, characterized in that: Includes the following modules: The blockchain evidence storage module is used to collect explicit and implicit investment cost data of producers, processors, logistics providers and sellers in the agricultural product supply chain. After performing hash calculation on the cost data, it is uploaded to the blockchain network to generate an immutable cost evidence storage record and timestamp index. The cost refinement accounting module is connected to the blockchain evidence storage module. It is used to classify and collect the cost evidence records according to standardized cost items, calculate the unit agricultural product investment cost of each entity, and output a reliable cost dataset. The dynamic revenue iteration module, connected to the cost refinement calculation module, is used to receive the trusted cost dataset and access external big data sources to obtain market data, consumer preference data, and circulation loss data. Based on the trusted cost dataset and external big data, the revenue coefficient is iteratively optimized to generate a dynamic revenue calculation model. The game equilibrium pricing module, connected to the dynamic revenue iteration module, is used to construct a non-cooperative game equilibrium model by taking the revenue functions of each entity in the supply chain output by the dynamic revenue accounting model as input, solving the Nash equilibrium solution through adaptive weight adjustment, and outputting a pricing decision signal.

2. The agricultural product supply chain investment return pricing system based on emerging information services according to claim 1, characterized in that: The explicit investment costs include the cost of purchasing production equipment, the cost of constructing cold chain facilities, the cost of deploying information technology systems, and the cost of investing in quality inspection equipment; The hidden investment costs include brand building amortization costs, supply chain collaborative management costs, technology training sunk costs, and inventory holding opportunity costs.

3. The agricultural product supply chain investment return pricing system based on emerging information services according to claim 1, characterized in that: The refined cost accounting module uses a unit investment cost accounting formula to classify and aggregate the various entities: Let the first The supply chain entity in the first Within each time period, its set of explicit cost items is as follows: The set of hidden cost items is The yield per unit of agricultural product is Then the unit investment cost of this entity for: Both explicit and implicit cost items are included in the calculation after their authenticity is verified by the hash verification value of the blockchain notarization module.

4. The agricultural product supply chain investment return pricing system based on emerging information services according to claim 1, characterized in that: The dynamic revenue iteration module has a built-in revenue coefficient iteration optimization submodule, which uses a dynamic revenue coefficient update formula to correct the input-output conversion rate of each entity in the supply chain in real time: Let the first... The actual output revenue of each entity in period t is Based on the previous cycle's return coefficient Compared with unit investment cost The calculated predicted returns are Then the return coefficient for this period Updated to: in, The learning rate parameter is preset and its value range is (0,1]. The market data, consumer preference data, and circulation loss data are used to adjust actual output returns. The backpropagation weights.

5. The agricultural product supply chain investment return pricing system based on emerging information services according to claim 1, characterized in that: The dynamic revenue calculation model output by the dynamic revenue iteration module includes a comprehensive revenue function, which is used to calculate the short-term and long-term revenues of the supply chain entity. Let the first The unit investment cost sequence for each entity within a short-term window T is as follows: , The unit output sequence is Then the short-term overall return for: Long-term comprehensive income Introducing a decay factor based on the aforementioned short-term returns. And calculates on a rolling basis according to the preset number of cycles N: 。 6. The agricultural product supply chain investment return pricing system based on emerging information services according to claim 1, characterized in that: When constructing the non-cooperative game equilibrium model, the game equilibrium pricing module uses the payoff functions of each entity in the supply chain. Let be the payment function, where, For the first Pricing decision variables for individual entities The total number of participants in the game; the game equilibrium pricing module uses a Nash equilibrium solver and calculates the pricing combination that satisfies the following conditions through an iterative optimal response algorithm. : For any subject and its arbitrary feasible pricing All have ,in To exclude the main body The equilibrium pricing vector of other entities.

7. A pricing system for investment returns in agricultural product supply chains based on emerging information services, as described in claim 6, is characterized in that: The game equilibrium pricing module includes a weight adaptive adjustment submodule, used to allocate dynamic game weights to different supply chain entities. These dynamic game weights are based on the volatility of each entity's unit investment cost. elasticity coefficient with market acceptance Adaptive adjustment: Set the main body The base weight is Then the adaptively adjusted weights for: in, This is an adjustment coefficient, with a value range of [0,1]. The Nash equilibrium solver calculates the social welfare function after weighted summation. Search for an equilibrium solution under constraints.

8. A pricing system for investment returns in the agricultural product supply chain based on emerging information services, as described in claim 1, is characterized in that: The cost evidence record output by the blockchain evidence storage module includes the plaintext hash value of the cost data, the timestamp, the hash value of the previous block, and the digital signature of the evidence storage subject. The refined cost accounting module retrieves the corresponding blockchain evidence record for any cost data to be accounted for and performs a hash comparison. Only when the comparison matches will the cost data be included in the accounting.

9. A pricing system for investment returns in the agricultural product supply chain based on emerging information services, as described in claim 1, is characterized in that: The external big data sources accessed by the dynamic revenue iteration module include: agricultural product wholesale market price information interface, e-commerce platform sales data interface, meteorological data service interface, and logistics loss monitoring data interface; The dynamic revenue iteration module triggers daily or weekly updates of the revenue coefficient and synchronizes the updated dynamic revenue calculation model parameters to the game equilibrium pricing module.

10. A pricing system for investment returns in agricultural product supply chains based on emerging information services, as described in claim 1, is characterized in that: The pricing decision signal output by the game equilibrium pricing module includes the following fields: pricing entity identifier, target agricultural product category code, suggested lower and upper limits of the pricing range, game equilibrium pricing value, effective pricing time window, and predicted revenue distribution ratio of each supply chain entity. The pricing decision signal is encrypted and then pushed to the terminal devices of each supply chain entity.

Images