Asset value data determination method and apparatus, electronic device, and readable storage medium

Abstract

The present disclosure relates to the technical field of data processing, and provides an asset value data determination method and device, electronic equipment and readable storage medium. The method comprises: performing mapping processing on asset inventory health based on preset weight reference data and a preset inventory turnover rate threshold to obtain a real-time weight value; performing evaluation processing on the real-time weight value, a quantitative value target function and asset multi-dimensional state data to obtain an asset value adjustment instruction; executing the asset value adjustment instruction to obtain real-time asset flow data and real-time asset inventory data; performing correction processing on the real-time asset flow data and the real-time asset inventory data based on the asset value adjustment instruction to obtain an asset value adjustment correction instruction; and executing the asset value adjustment correction instruction based on the quantitative value target function to obtain target asset value data, thereby improving the evaluation accuracy, enhancing the response flexibility, improving the matching degree of asset value and income expectation, and enhancing the adaptive capability.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to a method, apparatus, electronic device, and readable storage medium for determining asset value data. Background Technology

[0002] Current e-commerce dynamic pricing primarily relies on machine learning models, such as gradient boosting trees or recurrent neural networks, to predict sales volume and optimize pricing using historical sales and market data to maximize short-term sales. However, this method focuses solely on sales data, leading to a disconnect between pricing and inventory management, resulting in inventory backlogs or stockouts. Furthermore, its adjustment mechanisms are rigid, lacking the ability to respond to supply chain fluctuations and adapt. While other methods can incorporate some supply chain data, such as cost information, they do not systematically cover key factors like tariffs and logistics, leaving decision-making incomplete and lacking dynamic linkage with inventory status.

[0003] It is evident that existing technologies suffer from inaccurate pricing due to incomplete data input dimensions and a lack of dynamic linkage with inventory status, as well as a lack of flexibility in adjustment mechanisms, making them unable to adaptively respond to changes in inventory and the supply chain. Summary of the Invention

[0004] In view of this, the present disclosure provides a method, apparatus, electronic device and readable storage medium for determining asset value data, in order to solve the problems in the prior art where incomplete data input dimensions and lack of dynamic linkage with inventory status lead to inaccurate pricing and the adjustment mechanism lacks flexibility and cannot adaptively respond to changes in inventory and supply chain.

[0005] A first aspect of this disclosure provides a method for determining asset value data, comprising: mapping asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain real-time weight values; evaluating the real-time weight values, a quantitative value objective function, and multi-dimensional asset status data to obtain an asset value adjustment instruction; executing the asset value adjustment instruction to obtain real-time asset flow data and real-time asset inventory data; correcting the real-time asset flow data and real-time asset inventory data based on the asset value adjustment instruction to obtain an asset value adjustment correction instruction; and executing the asset value adjustment correction instruction based on the quantitative value objective function to obtain target asset value data.

[0006] In some embodiments, the asset stock health is mapped based on preset weighted comparison data and preset stock turnover rate threshold to obtain a real-time weight value, including: performing segmented comparison processing on the asset stock health and preset stock turnover rate threshold to obtain a health interval code; performing query processing on the health interval code based on preset weighted comparison data to obtain an asset value weight value and a stock weight value; and performing smoothing processing on the asset value weight value and the stock weight value to obtain a real-time weight value.

[0007] In some embodiments, the multidimensional status data includes stock index values ​​and flow index values; the evaluation and processing of real-time weight values, quantitative value objective functions, and multidimensional asset status data to obtain asset value adjustment instructions includes: comparing stock index values ​​and residual index values ​​to obtain an asset stock health score; determining the periodic asset value based on the quantitative value objective function and the asset multidimensional status data; performing weighted fusion processing on the periodic asset value and the asset stock health score to obtain a real-time weighted fusion value; and determining the asset value adjustment instruction based on a preset weighted fusion threshold and the real-time weighted fusion value.

[0008] In some embodiments, the real-time asset flow data and real-time asset stock data are corrected based on the asset value adjustment instruction to obtain the asset value adjustment correction instruction, including: performing anomaly detection processing on the real-time asset flow data and real-time asset stock data to obtain anomaly deviation values; performing moving average calculation processing on the anomaly deviation values ​​to obtain asset correction increments; and processing the asset value adjustment instruction based on the asset correction increments to obtain the asset value adjustment correction instruction.

[0009] In some embodiments, executing an asset value adjustment and correction instruction based on a quantitative value objective function to obtain target asset value data includes: calculating and processing the asset value adjustment and correction instruction based on the quantitative value objective function to obtain the asset value of the correction period; and performing convergence processing on the asset value of the correction period to obtain the target asset value data.

[0010] In some embodiments, before evaluating and processing the real-time weight value, the quantitative value objective function, and the asset multidimensional state data to obtain the asset value adjustment instruction, the method further includes: acquiring initial asset flow data, initial asset input data, and initial asset depreciation data; constructing a quantitative value objective function based on the initial asset flow data, initial asset input data, and initial asset depreciation data; and standardizing the initial asset flow data, initial asset input data, and initial asset depreciation data to obtain asset multidimensional state data.

[0011] In some embodiments, before mapping the asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain a real-time weight value, the method further includes: obtaining an initial asset inventory balance value; performing flow assessment processing on the initial asset inventory balance value based on a preset asset increment cycle to obtain an estimated asset flow value; and performing ratio calculation processing on the initial asset inventory balance value and the estimated asset flow value to obtain the asset health status.

[0012] A second aspect of this disclosure provides an asset value data determination apparatus, comprising: a first processing module for mapping asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain a real-time weight value; a second processing module for evaluating the real-time weight value, a quantitative value objective function, and multi-dimensional asset status data to obtain an asset value adjustment instruction; a third processing module for executing the asset value adjustment instruction to obtain real-time asset flow data and real-time asset inventory data; a fourth processing module for correcting the real-time asset flow data and real-time asset inventory data to obtain an asset value adjustment correction instruction; and a fifth processing module for executing the asset value adjustment correction instruction based on the quantitative value objective function to obtain target asset value data.

[0013] A third aspect of this disclosure provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method described above.

[0014] A fourth aspect of this disclosure provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0015] The beneficial effects of this disclosed embodiment compared with the prior art are as follows: By mapping the health of asset inventory based on preset weighted comparison data and preset inventory turnover rate thresholds, a real-time weight value is obtained; the real-time weight value, quantitative value objective function, and multi-dimensional asset status data can be evaluated to generate an asset value adjustment instruction; executing this asset value adjustment instruction outputs real-time asset flow data and real-time asset inventory data; furthermore, the real-time asset flow data and real-time asset inventory data can be corrected to form an asset value adjustment correction instruction; the asset value adjustment correction instruction can be executed according to the quantitative value objective function to obtain target asset value data, thereby improving the real-time performance and accuracy of asset value assessment, enhancing the flexibility of response to market fluctuations and inventory changes, improving the matching degree between asset value and future return expectations, reducing inventory depreciation risk and financial valuation deviation, and enhancing adaptability. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram illustrating an application scenario of an embodiment of this disclosure; Figure 2 This is a flowchart illustrating a method for determining asset value data provided in an embodiment of this disclosure; Figure 3 This is a flowchart illustrating another method for determining asset value data provided in this embodiment of the disclosure; Figure 4 This is a flowchart illustrating a dual-objective function model training method provided in an embodiment of this disclosure; Figure 5 This is a schematic diagram of the structure of an asset value data determination device provided in an embodiment of this disclosure; Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0018] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, so as to provide a thorough understanding of the embodiments of this disclosure. However, those skilled in the art will understand that this disclosure may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this disclosure with unnecessary detail.

[0019] It should be noted that the user information (including but not limited to terminal device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the technical solution involved in this disclosure is automated processing through an asset recommendation model that has been trained.

[0020] The following will describe in detail, with reference to the accompanying drawings, a method and apparatus for determining asset value data according to an embodiment of the present disclosure.

[0021] Figure 1 This is a schematic diagram illustrating an application scenario of an embodiment of this disclosure. The application scenario may include terminal devices 1, 2, and 3, server 4, and network 5.

[0022] Terminal devices 1, 2, and 3 can be hardware or software. When terminal devices 1, 2, and 3 are hardware, they can be various electronic devices with displays and supporting communication with server 4, including but not limited to smartphones, tablets, laptops, and desktop computers. When terminal devices 1, 2, and 3 are software, they can be installed in the aforementioned electronic devices. Terminal devices 1, 2, and 3 can be implemented as multiple software programs or software modules, or as a single software program or software module; this disclosure does not limit this. Furthermore, various applications can be installed on terminal devices 1, 2, and 3, such as data processing applications, instant messaging tools, social platform software, search applications, shopping applications, etc.

[0023] Server 4 can be a server that provides various services, such as a backend server that receives requests sent by terminal devices with which it has established communication connections. This backend server can receive and analyze the requests sent by the terminal devices and generate processing results. Server 4 can be a single server, a server cluster consisting of several servers, or a cloud computing service center. This disclosure embodiment does not limit this.

[0024] It should be noted that server 4 can be either hardware or software. When server 4 is hardware, it can be various electronic devices that provide various services to terminal devices 1, 2, and 3. When server 4 is software, it can be multiple software programs or software modules that provide various services to terminal devices 1, 2, and 3, or it can be a single software program or software module that provides various services to terminal devices 1, 2, and 3. This disclosure does not limit the scope of the embodiments.

[0025] Network 5 can be a wired network using coaxial cable, twisted pair, and fiber optic connection, or it can be a wireless network that enables interconnection of various communication devices without wiring, such as Bluetooth, Near Field Communication (NFC), and Infrared. This disclosure does not limit the scope of the network.

[0026] Users can establish a communication connection with server 4 via network 5 through terminal devices 1, 2, and 3 to receive or send information. Specifically, server 4 can obtain asset health status, quantitative value objective function, and multi-dimensional asset status data through terminal devices 1, 2, and 3. It can then map the asset health status based on preset weighted comparison data and preset inventory turnover rate thresholds to obtain real-time weight values. The server 4 can evaluate the real-time weight values, quantitative value objective function, and multi-dimensional asset status data to generate asset value adjustment instructions. After executing these instructions, it outputs real-time asset flow data and real-time asset inventory data. Furthermore, it can correct the real-time asset flow data and real-time asset inventory data to form asset value adjustment correction instructions. Finally, it can execute these instructions based on the quantitative value objective function to obtain the target asset value data.

[0027] It should be noted that the specific types, quantities, and combinations of terminal devices 1, 2, and 3, server 4, and network 5 can be adjusted according to the actual needs of the application scenario, and this disclosure embodiment does not impose any restrictions on this.

[0028] Figure 2 This is a flowchart illustrating a method for determining asset value data provided in an embodiment of this disclosure. Figure 2 The method for determining asset value data can be provided by Figure 1 The server executes the command. For example... Figure 2 As shown, the method for determining the asset value data includes: S201: Based on preset weighted comparison data and preset stock turnover rate threshold, the asset stock health is mapped to obtain real-time weight values.

[0029] Specifically, the preset weighted reference data can be a pre-configured correspondence between weight values, or a dataset storing the mapping relationship between different inventory states and weight values. This provides a benchmark reference for dynamic weight adjustment. The preset weighted reference data can also be used to characterize the weight allocation rules under different inventory health levels. The preset inventory turnover rate threshold can be the critical value data for inventory turnover rate, i.e., a numerical boundary that can be used to distinguish between good and bad inventory states. This can serve as a standard for judging asset inventory health and can also be used to define the boundary conditions for inventory turnover efficiency. Asset inventory health can refer to the health status of inventory assets. Indicators are quantitative values ​​that can be used to characterize inventory turnover efficiency and backlog risk, thereby assessing inventory status and driving weight adjustments, and also characterizing the operational health of inventory assets. Mapping processing can be the process of converting input parameters into output values. Mapping processing can be the calculation process of mapping asset health to weight values ​​based on preset weight comparison data, thereby realizing the conversion of inventory status to weight coefficients. Among them, real-time weight values ​​can be dynamically calculated weight coefficients, or weight parameters generated in real time to adjust the objective function, thereby balancing revenue and inventory targets, and also optimizing the real-time nature of pricing decisions.

[0030] Furthermore, the weighted comparison data can include the correspondence between revenue weight and inventory weight. The preset inventory turnover rate threshold can be set to different values ​​according to the asset type. The asset inventory health is obtained by comparing the inventory turnover rate with the preset inventory turnover rate threshold. The mapping process can be implemented by linear interpolation or piecewise function methods.

[0031] For example, in fresh food e-commerce, for products with short shelf life, inventory data and turnover rate can be collected regularly. Based on preset weighted comparison data and preset inventory turnover rate thresholds, the health of asset inventory can be calculated, and real-time weight values ​​can be generated through mapping processing.

[0032] In addition, the mapping process can specifically include finding entries in the preset weighted comparison data that match the asset health status, or performing interpolation calculations using mathematical functions such as piecewise linear functions, thereby ensuring that the weight values ​​match the inventory status in real time.

[0033] This application embodiment maps the asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain real-time weight values, realizing a dynamic correlation between inventory status and pricing weights; it quantifies inventory health and maps it to weight parameters, enabling real-time response to inventory changes; thereby improving the accuracy and adaptability of pricing decisions, avoiding the risks of inventory backlog or stockouts, and optimizing the balance between revenue and inventory turnover.

[0034] S202 evaluates and processes the real-time weight values, the quantitative value objective function, and the multi-dimensional state data of the assets to obtain the asset value adjustment instruction.

[0035] Specifically, the quantitative value objective function can be a dual objective function that collaboratively processes the single-asset cycle increment and inventory turnover rate, thereby combining revenue and inventory objectives into a unified framework. The multi-dimensional asset state data can be a multi-dimensional dataset, including real-time data from multiple dimensions such as sales, supply, and inventory, without limitation. This multi-dimensional asset state data can be obtained through e-commerce platform sales systems, inventory systems, procurement systems, and third-party data platforms, and can be processed through data cleaning, standardization, and feature extraction. The evaluation process can be a process of analyzing and calculating real-time weight values, the quantitative value objective function, and the multi-dimensional asset state data using a deep reinforcement learning model. This allows for the generation of the optimal asset value data determination strategy through the mapping between the state space and action space. It can be based on a Deep Q-Network (DQN), using real-time weight values, the quantitative value objective function, and the multi-dimensional asset state data as input, and calculating action probabilities through a neural network. The asset value adjustment instruction can be an executable control instruction, such as an instruction to adjust asset value data or a pre-sale plan, for example, guiding the e-commerce platform to execute price changes or pre-sale processing.

[0036] Furthermore, during the evaluation process, the state space of DQN can include standardized dimensions of multi-dimensional asset state data, and the action space can include multiple asset value data to determine action options. It can be trained through experience replay and target network updates to ensure that the output asset value adjustment instructions match real-time market conditions and inventory status.

[0037] For example, in the fresh food e-commerce scenario, by connecting with the platform's sales and inventory systems, multi-dimensional asset status data such as real-time sales volume, inventory balance, and procurement costs can be collected. Raw material cost fluctuation information can be obtained through the supply chain data platform. After cleaning and standardizing the obtained data, it is input into DQN. DQN can dynamically adjust the weight ratio of revenue and inventory in the quantitative value objective function based on real-time weight values. When the inventory turnover rate is lower than the preset turnover rate threshold, the inventory weight is increased to promote inventory turnover. By evaluating and processing the target asset value data, actions are determined to obtain asset value adjustment instructions such as a 3% price reduction or the generation of pre-sale plans, etc., which are not limited here.

[0038] This application's embodiments evaluate and process real-time weight values, quantitative value objective functions, and multi-dimensional asset status data to obtain asset value adjustment instructions. By dynamically balancing revenue and inventory targets through DQN, real-time coordination between pricing decisions and inventory status is achieved, avoiding high-price stockpiling and low-price stockouts. Through multi-dimensional data input and feature extraction, the completeness and accuracy of asset value data determination decisions are improved, responding to supply chain fluctuations. Combined with an adaptive adjustment mechanism, the flexibility and scenario adaptability of the asset value data determination strategy are enhanced, optimizing operational efficiency and improving user experience.

[0039] S203, execute the asset value adjustment instruction to obtain real-time asset flow data and real-time asset stock data.

[0040] Specifically, real-time asset flow data can be time-series data that characterizes the flow and changes of assets within a unit of time, thereby enabling the monitoring of sales or inventory turnover dynamics. Real-time asset flow data can be real-time order volume and sales information obtained through the sales system. Real-time asset inventory data can be static data that characterizes the remaining inventory level of assets at the current moment, thereby enabling the assessment of inventory health and replenishment needs. Real-time asset inventory data can be real-time inventory balance and loss rate information obtained through the inventory system.

[0041] For example, in the fresh food e-commerce scenario, an instruction to adjust the asset value can be used. The price of the instruction is updated and sales data is collected synchronously. Real-time asset flow data can be generated by obtaining order flow data in real time through an interface. Real-time asset inventory data can be generated by pulling the current inventory status through the warehousing system. Both types of data can be used together for subsequent inventory turnover rate calculation and price adjustment strategy optimization.

[0042] Furthermore, the execution process of the asset value adjustment instruction may include parsing instruction parameters, verifying permissions, and calling the application programming interface (API). The instruction parameters may include the target product identifier, adjustment range, and effective time. The generation of real-time asset flow data may include aggregating sales flow data and extracting the transaction quantity and asset value within the time window. The generation of real-time asset inventory data may include taking snapshots of inventory records and calculating the available inventory quantity by combining inbound and outbound logs.

[0043] This application's embodiments achieve real-time coordination between pricing decisions and inventory status by executing asset value adjustment instructions and acquiring real-time asset flow data and real-time asset inventory data; the instruction-driven execution mechanism reduces manual intervention and improves the response speed of asset value data adjustment actions; the parallel collection of flow and inventory data enhances the accuracy of inventory turnover monitoring; and real-time data updates improve the accuracy of asset value data determination, reduce the risk of backlog and stockouts, and improve operational efficiency.

[0044] S204 performs correction processing on real-time asset flow data and real-time asset stock data to obtain an asset value adjustment correction instruction.

[0045] Specifically, correction processing can be a process of preprocessing real-time asset flow data and real-time asset stock data to eliminate noise and anomalies, including but not limited to data cleaning, data standardization and feature extraction. Correction processing can also be a process of improving data quality and consistency by processing real-time asset flow data and real-time asset stock data.

[0046] Among them, the asset value adjustment and correction instruction can be a price adjustment or pre-sale instruction calculated based on the corrected data. The asset value adjustment and correction instruction can be used as a strategy command to adjust the asset value or initiate a pre-sale.

[0047] This application embodiment generates accurate asset value adjustment instructions by correcting real-time asset flow data and real-time asset inventory data, achieving coordinated optimization of pricing and inventory. The data correction process improves the quality of input data, ensuring the accuracy and reliability of asset value data determination. By combining real-time flow and inventory data, it enables dynamic response to market changes and inventory status, improves the accuracy of asset value data determination, avoids erroneous price adjustments caused by data noise, enhances adaptability to supply chain fluctuations, and reduces the risk of inventory backlog and stockouts.

[0048] For example, in fresh food e-commerce applications, real-time asset flow data can be collected every 5 minutes via API, including real-time order volume and sales data from the sales system, and real-time asset inventory data, including inventory balance and available days data from the inventory system. The collected data can be corrected by using forward imputation to handle missing competitor price data, applying the three-standard-deviation principle to remove outliers in sales volume, and replacing them with the 7-day average. Data standardization can then be performed to normalize all data to the [0,1] interval to eliminate dimensional differences. Furthermore, 7-day moving average trend features and weekly cycle features can be extracted from sales and price time-series data, and Long Short-Term Memory (LSTM) networks can be used. To predict sales in the next 7 days using a Data Quality Network (LSTM), corrected data can be input into a dual-objective optimization model based on Data Quality Network (DQN). The state space can contain 10 dimensions of standardized data, and the action space can include 7 pricing actions. The DQN model can dynamically adjust the weights based on real-time inventory health and output asset value adjustment correction instructions. For example, when the inventory turnover days exceed 15 days, a price reduction instruction is generated to accelerate inventory clearance, or when the inventory can be sold for less than 2 days, a pre-sale plan is generated. The pre-sale price can be calculated based on the replenishment cycle premium, and the upper limit of pre-sale orders can be 80% of the replenishment quantity.

[0049] S205, executes asset value adjustment and correction instructions based on the quantitative value objective function to obtain target asset value data.

[0050] Specifically, the target asset value data can be adjusted asset value information, or it can be commodity value data obtained by executing asset value adjustment and correction instructions. The target asset value data can be used to provide the selling price or value of commodities used in actual sales, ensuring that pricing and inventory status are coordinated. The target asset value data can be obtained by executing asset value adjustment and correction instructions, and based on the optimized output of the quantitative value objective function, it can be used for sales decisions and inventory management on e-commerce platforms.

[0051] This application's embodiments achieve dual-objective optimization of revenue and inventory through a quantitative value objective function, avoiding stockpiling or shortages caused by a disconnect between pricing and inventory, thus improving operational efficiency; and enhance the flexibility and accuracy of asset value data determination through adaptive adjustment of asset value adjustment correction instructions.

[0052] According to the technical solution provided in this disclosure, the health of asset inventory is mapped based on preset weighted comparison data and preset inventory turnover rate threshold to obtain a real-time weight value. The real-time weight value, quantitative value objective function, and multi-dimensional asset status data can be evaluated to generate an asset value adjustment instruction. Executing this asset value adjustment instruction outputs real-time asset flow data and real-time asset inventory data. Furthermore, the real-time asset flow data and real-time asset inventory data can be corrected to form an asset value adjustment correction instruction. The asset value adjustment correction instruction can be executed according to the quantitative value objective function to obtain target asset value data. This improves the real-time performance and accuracy of asset valuation, enhances the flexibility of response to market fluctuations and inventory changes, improves the matching degree between asset value and future return expectations, reduces inventory depreciation risk and financial valuation deviation, and enhances adaptability.

[0053] In some embodiments, the asset stock health is mapped based on preset weighted comparison data and preset stock turnover rate threshold to obtain a real-time weight value, including: performing segmented comparison processing on the asset stock health and preset stock turnover rate threshold to obtain a health interval code; performing query processing on the health interval code based on preset weighted comparison data to obtain an asset value weight value and a stock weight value; and performing smoothing processing on the asset value weight value and the stock weight value to obtain a real-time weight value.

[0054] Specifically, the preset inventory turnover rate threshold can be a turnover rate critical value pre-set according to the characteristics of the asset category. The preset inventory turnover rate threshold can be used to classify the health status of inventory. The preset inventory turnover rate threshold can be a category-specific threshold library set based on historical operating data. The segmented comparison processing can be a logical processing process of matching the asset inventory health and multiple inventory turnover rate thresholds within intervals. This can discretize continuous health values ​​into specific interval identifiers for subsequent query mapping. Among them, the health interval code can be a discrete code used to represent the interval to which the asset inventory health belongs, which can be used to simplify the weight mapping process.

[0055] For example, in the fresh food e-commerce scenario, the inventory balance and recent sales trend of a short-shelf-life product can be monitored in real time. When the asset health score is calculated to be 0.3, it is compared with the preset inventory turnover rate threshold (such as 0.2, 0.5 or 0.8, etc., which is not limited here) to determine that it falls into the "low health" range and generate the corresponding health range code, such as L1.

[0056] In addition, the query processing can be a process of retrieving the corresponding weight value from the preset weight comparison data by matching the health interval code. The asset value weight value can be a coefficient used to adjust the influence of the profit objective function, so as to balance the priority of profit optimization in the determination of asset value data; the inventory weight value can be a coefficient used to adjust the influence of the inventory objective function, so as to strengthen the inventory turnover constraint in the determination of asset value data.

[0057] For example, based on the above application scenario, the preset weighted comparison data can be queried according to the health interval code L1 to obtain an asset value weight of 0.4 and an inventory weight of 0.6, which can indicate that the current decision should prioritize inventory turnover.

[0058] In addition, smoothing can be a process of gradually adjusting the weight values ​​through weighted averaging or filtering algorithms. This can avoid pricing strategy fluctuations caused by sudden changes in weights. For example, in the fresh food e-commerce scenario, an exponential smoothing algorithm can be applied to the asset value weight value of 0.4 and the stock weight value of 0.6 obtained from the query. Combined with historical weight data, the real-time weight values ​​can be 0.45 and 0.55, ensuring a smooth transition of weight changes.

[0059] According to the technical solution provided in this disclosure, by segmenting and mapping the health of asset inventory, the inventory status is transformed into operable weight parameters. Smoothing processing ensures decision stability and achieves precise linkage between inventory health and pricing weights. Discretization of health interval codes simplifies the mapping logic of complex inventory statuses and improves response efficiency. A query mechanism for weighted comparison data enables rapid conversion from inventory status to weights, enhancing real-time decision-making. Smoothing processing avoids pricing fluctuations caused by weight jumps, improving robustness.

[0060] In some embodiments, the multidimensional status data includes stock index values ​​and flow index values; the evaluation and processing of real-time weight values, quantitative value objective functions, and multidimensional asset status data to obtain asset value adjustment instructions includes: comparing stock index values ​​and residual index values ​​to obtain an asset stock health score; determining the periodic asset value based on the quantitative value objective function and the asset multidimensional status data; performing weighted fusion processing on the periodic asset value and the asset stock health score to obtain a real-time weighted fusion value; and determining the asset value adjustment instruction based on a preset weighted fusion threshold and the real-time weighted fusion value.

[0061] Specifically, inventory indicators can be used to characterize the static quantity status of assets at a specific point in time. Inventory indicators can be real-time inventory quantity values ​​collected through the inventory system, which can be used to characterize the current holding scale of assets. Flow indicators can be used to characterize the flow changes of assets within a certain period. Flow indicators can be dynamic data such as sales volume collected through the sales system or warehousing volume collected through the procurement system, which can be used to characterize the turnover trend of assets.

[0062] The asset inventory health score can be a quantitative score that characterizes the health status of asset inventory. The asset inventory health score can be a value calculated by the ratio or difference between inventory and flow.

[0063] The value of a cyclical asset can be the result of an asset's valuation over a specific time period. The value of a cyclical asset can be the expected return value calculated using an objective function and multidimensional data, thereby quantifying the asset's economic benefits.

[0064] The real-time weighted fusion value can be a numerical value used to characterize the comprehensive evaluation result. The real-time weighted fusion value can be a single indicator that integrates the value of cyclical assets with the health score of asset stock through a weighted algorithm, thereby balancing the profit target and the inventory status.

[0065] The preset weighted fusion threshold can be a preset value used to characterize the decision critical point. The preset weighted fusion threshold can be a threshold value set through historical data analysis and business rules, which can trigger adjustment decisions.

[0066] Furthermore, the process of determining the value of cyclical assets can include applying a quantitative value objective function to multidimensional state data. For example, for fresh produce, the quantitative value objective function can calculate the maximum profit value within the cycle by processing procurement costs, sales prices, and inventory holding costs. The weighted fusion processing of real-time weighted fusion values ​​can achieve adaptive balance by adjusting the weight ratio of value and health based on the inventory health score through a dynamic weighting mechanism.

[0067] For example, based on the above application scenarios, inventory indicators such as the current inventory quantity can be obtained from the inventory system, and flow indicators such as the average daily sales volume can be obtained from the sales system. The inventory indicators and flow indicators can be compared and processed to calculate the inventory health score. When the inventory health score is lower than the preset threshold, it indicates that the inventory turnover is slow. The value of the cyclical assets can be determined according to the quantitative value objective function and real-time sales data. Then, the value of the cyclical assets and the health score can be weighted and integrated, with the health score having a higher weight to prioritize clearing inventory, and a real-time weighted integrated value can be obtained. Based on the preset integration threshold, an asset value adjustment instruction such as a 5% price reduction can be generated to accelerate sales.

[0068] According to the technical solution provided in this disclosure, by introducing stock index values ​​and flow index values ​​as components of multi-dimensional status data, and combining them with comparative processing to generate an asset stock health score, the inventory status can be quantified into an assessable score, thus achieving precise monitoring of asset health. By determining the value of cyclical assets based on a quantitative value objective function, the revenue target can be dynamically combined with real-time data, improving the accuracy of value calculation. By weighted fusion processing of cyclical asset value and health score, and adopting a dynamic weighting mechanism to balance revenue and inventory targets, the adaptability of decision-making is enhanced. By determining adjustment instructions based on preset thresholds, automated response is achieved, improving processing efficiency, increasing asset turnover, and enhancing the accuracy of asset value data determination. Through an adaptive adjustment mechanism, robustness in changing scenarios and user experience are improved.

[0069] In some embodiments, real-time asset flow data and real-time asset stock data are corrected to obtain an asset value adjustment correction instruction, including: performing anomaly detection processing on real-time asset flow data and real-time asset stock data to obtain anomaly deviation values; performing moving average calculation on the anomaly deviation values ​​to obtain asset correction increments; and processing the asset value adjustment instruction based on the asset correction increments to obtain asset value adjustment correction instructions.

[0070] Specifically, anomaly detection and processing can identify outliers in real-time asset flow data and real-time asset inventory data based on statistical distribution, eliminating noise data caused by system failures or external interference, and ensuring the reliability of subsequent processing. Among them, the anomaly deviation value can be used to characterize the difference between the detected abnormal data points and the normal data range, and can be used to quantify the degree of data anomaly. This anomaly deviation value can be calculated by using the three-standard-deviation principle from the raw real-time asset flow data and real-time asset inventory data obtained through data acquisition.

[0071] Furthermore, anomaly detection processing can be achieved by setting a threshold for the normal data range. Real-time data can be compared with the normal data range threshold. When the real-time data exceeds the normal data range threshold, it is marked as an anomaly, and its deviation from the mean is calculated as the anomaly deviation value.

[0072] In addition, the moving average calculation process can be a process of calculating the average value of data within a time window, which can smooth the fluctuation of abnormal deviation values ​​and avoid the excessive impact of single-point anomalies on the correction process; the asset correction increment can be used to characterize the correction magnitude value obtained through smoothing; the asset correction increment can be calculated by moving average of the abnormal deviation values ​​obtained from the anomaly detection process.

[0073] Furthermore, the moving average calculation process can be performed by setting a fixed time window size, such as a 7-day window, to calculate the arithmetic mean of the abnormal deviation value sequence within the fixed time window, thereby obtaining the asset correction increment.

[0074] In addition, asset value adjustment correction instructions can be generated by weighting the asset correction increment as an adjustment factor with the value in the asset value adjustment instruction.

[0075] For example, based on the above application scenarios, real-time asset flow data such as order volume and real-time asset inventory data such as inventory balance can be collected every 5 minutes in advance. Anomaly detection and processing can be performed on the real-time asset flow data and real-time asset inventory data. When sales suddenly increase by 10 times at a certain moment, the abnormal deviation value can be calculated by the three-standard deviation principle. Then, the asset correction increment can be calculated by the 7-day moving average of the abnormal deviation value. The asset value adjustment instruction can be corrected based on the asset correction increment to generate the asset value adjustment correction instruction.

[0076] According to the technical solution provided in this disclosure, by performing anomaly detection and moving average processing on real-time asset flow data and real-time asset inventory data, an asset correction increment is generated and adjustment instructions are corrected, eliminating the impact of data noise and abnormal fluctuations, improving the accuracy and stability of asset value decision data, and avoiding pricing or inventory management errors caused by data distortion.

[0077] In some embodiments, executing an asset value adjustment and correction instruction based on a quantitative value objective function to obtain target asset value data includes: calculating and processing the asset value adjustment and correction instruction based on the quantitative value objective function to obtain the asset value of the correction period; and performing convergence processing on the asset value of the correction period to obtain the target asset value data.

[0078] Specifically, the asset value in the correction period can be the asset value calculated within a specific optimization period; the asset value in the correction period can be obtained by calculating and processing the asset value adjustment and correction instructions through a quantitative value objective function, which can be achieved by inputting the instruction parameters into the quantitative value objective function and performing numerical solution.

[0079] Furthermore, the calculation process may include parsing the price adjustment range and inventory constraints in the instruction, and substituting them into a bi-objective function model for iterative calculation to output an asset value estimate for the period.

[0080] In addition, convergence processing can stabilize numerical results through iterative calculations. Convergence processing can be used to eliminate fluctuations in the value of assets during the correction period. Convergence processing can be applied to the value of assets during the correction period, such as when the reward function value fluctuates for multiple consecutive steps and is less than or equal to a threshold.

[0081] For example, based on the above application scenarios, after receiving the asset value adjustment and correction instruction, the asset value of the correction period can be calculated and processed based on the quantitative value objective function. This quantitative value objective function integrates real-time sales, inventory balance and supply chain cost data, and can optimize profit and inventory turnover rate through deep reinforcement learning model; then the asset value of the correction period can be converged, and the asset value can be stabilized within the short shelf life of fresh products through iterative calculation, so as to obtain the target asset value data for automatic price adjustment.

[0082] According to the technical solution provided in this disclosure, the asset value of the correction period is obtained by performing calculation processing based on the quantitative value objective function, and the stability of the data is ensured by combining convergence processing. The integration of dual-objective optimization and numerical convergence mechanism improves the accuracy and reliability of asset value data, avoids excessive fluctuations in the determination of asset value data, reduces the risk of inventory backlog and stockouts, and enhances adaptability in dynamic environments.

[0083] In some embodiments, before evaluating and processing the real-time weight value, the quantitative value objective function, and the asset multidimensional state data to obtain the asset value adjustment instruction, the method further includes: acquiring initial asset flow data, initial asset input data, and initial asset depreciation data; constructing a quantitative value objective function based on the initial asset flow data, initial asset input data, and initial asset depreciation data; and standardizing the initial asset flow data, initial asset input data, and initial asset depreciation data to obtain asset multidimensional state data.

[0084] Specifically, initial asset flow data can be data on the flow of assets within a specific time period, including sales volume and order volume, which can be used to characterize the market demand and liquidity of assets. This initial asset flow data can be collected in real time through the e-commerce platform's sales system and can be cleaned to eliminate outliers. Initial asset input data can be cost data involved in the acquisition or production of assets, including procurement costs and logistics costs, which can be used to build a cost basis to support profit calculation. This initial asset input data can be obtained through the procurement system and supply chain data platform. Initial asset depreciation data can be data on the depreciation of assets during storage or sales, including inventory depreciation rate and holding costs, which can be used to assess asset maintenance efficiency and optimize inventory management. This initial asset depreciation data can be obtained through the inventory system and can be used to characterize the depreciation characteristics caused by the warehousing environment.

[0085] Furthermore, the aforementioned data can be periodically synchronized from internal and external data sources via API interfaces. Internal data sources may include sales and inventory systems, while external data sources may include competitor monitoring platforms and supply chain data platforms, ensuring the real-time nature and completeness of data collection.

[0086] Furthermore, the quantitative value objective function can be designed as a dual objective, which can include a revenue objective and an inventory objective. The revenue objective can be based on maximizing the profit of a single asset cycle, while the inventory objective can use inventory turnover rate as a constraint. The priority of the two can be adjusted through a dynamic weighting mechanism to ensure that the quantitative value objective function can respond to real-time market and supply chain changes.

[0087] In addition, standardization processing can include steps such as data cleaning, missing value imputation, and outlier removal. These steps are not limited here. Data cleaning can handle missing values ​​using the forward imputation method, and outlier removal can identify and replace outliers based on statistical principles, outputting standardized multidimensional data.

[0088] For example, based on the above application scenarios, initial asset flow data, including daily sales volume and real-time order volume, can be obtained from the sales system through API interfaces; initial asset input data, including procurement costs and logistics expenses for fresh produce, can be obtained from the procurement system; and initial asset loss data, including warehousing loss rate and holding costs, can be obtained from the inventory system. A quantitative value objective function can be constructed based on the above data. This quantitative value objective function can combine revenue objectives and inventory turnover constraints and be optimized through a deep reinforcement learning model. The obtained initial data can be standardized, including normalizing sales volume, costs, and loss rates to [0,1], and extracting 7-day moving average trend features to generate multi-dimensional asset status data.

[0089] According to the technical solution provided in this disclosure, by acquiring multi-dimensional initial data and constructing a quantitative value objective function, the integrity and accuracy of the data are ensured, and the reliability of asset value data determination is improved; by generating multi-dimensional asset state data through standardized processing, the difference in data dimensions is eliminated, and the stability and efficiency of calculation are enhanced; by data preprocessing and function optimization, a data foundation for asset value adjustment is provided, and the accuracy is improved.

[0090] In some embodiments, before mapping the asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain a real-time weight value, the method further includes: obtaining an initial asset inventory balance value; performing flow assessment processing on the initial asset inventory balance value based on a preset asset increment cycle to obtain an estimated asset flow value; and performing ratio calculation processing on the initial asset inventory balance value and the estimated asset flow value to obtain the asset health status.

[0091] Specifically, the initial asset inventory balance value can be the current inventory quantity of assets at a specific point in time, which can be used to characterize the real-time status of inventory. This can provide basic data input for inventory health calculation. The initial asset inventory balance value can be collected in real time through the inventory management system, for example, by extracting the current number of salable goods from the inventory database of an e-commerce platform.

[0092] Furthermore, the inventory management system can connect with the sales and purchasing systems via API interfaces to ensure real-time data updates. The initial asset inventory balance can include finished goods inventory and semi-finished goods inventory, and distinguish between available inventory and reserved inventory.

[0093] In addition, the preset asset increment cycle can be a fixed time interval for asset replenishment or addition, which can be used to characterize the time range of flow forecasting, thereby providing a cyclical benchmark for flow assessment. For example, the replenishment cycle for fresh produce can be 7 days. Flow assessment processing can be a data processing method that predicts future asset changes based on historical data and cyclical patterns, thereby generating estimated asset inflows or outflows for future time periods. Flow assessment processing can be implemented through machine learning models such as the LSTM algorithm, using historical sales and cyclical characteristics for prediction. The estimated asset flow value can be the predicted value of future asset changes output by flow assessment processing, which can be used to characterize inventory dynamics, thereby providing future-oriented data for inventory health calculation. The estimated asset flow value can be calculated based on the initial asset stock balance and the asset increment cycle.

[0094] In addition, the ratio calculation process can be used to compare the relative relationship between the initial asset stock balance and the estimated asset flow value, thereby combining the current stock and the predicted flow into a single health indicator. The ratio calculation process can be achieved by division or ratio formula based on the initial asset stock balance and the estimated asset flow value.

[0095] Furthermore, the ratio calculation can use the ratio formula of stock to flow. For example, the health status is equal to the initial asset stock balance value divided by the estimated asset flow value, and normalized to [0,1]. The asset stock health status can also be calibrated in combination with the inventory threshold to ensure that the indicator matches the actual operational needs.

[0096] For example, based on the above application scenarios, the initial asset inventory balance can be obtained through the inventory database. For instance, if the current inventory of a certain seafood product is 500 jin, the flow can be assessed based on a preset asset increment cycle of 7 days. By analyzing historical sales data through an LSTM model, the estimated asset flow value for the next 7 days can be predicted to be 300 jin. The ratio of the initial asset inventory balance of 500 jin to the estimated asset flow value of 300 jin can be calculated, and the ratio can be normalized to obtain an asset inventory health level of 0.6.

[0097] According to the technical solution provided in this disclosure, by obtaining the initial asset inventory balance value, performing flow assessment processing based on the asset increment cycle to obtain the estimated asset flow value, and performing ratio calculation processing on the two to obtain the asset inventory health, a quantitative assessment of inventory status is achieved. By predicting future inventory changes through flow assessment processing and generating health indicators by integrating current and future data through ratio calculation processing, the accuracy and real-time performance of inventory health calculation are improved, providing a reliable basis for subsequent dynamic pricing and inventory optimization, and improving operational efficiency.

[0098] All of the above-mentioned optional technical solutions can be combined in any way to form optional embodiments of this disclosure, and will not be described in detail here.

[0099] Figure 3 This is a schematic diagram of another method for determining asset value data provided in this disclosure. Figure 3 As shown, the method for determining the asset value data includes: 1. Data Acquisition Layer: Connects to two types of data sources via API interfaces: Internal data sources: e-commerce platform sales system (historical sales volume, real-time order volume), inventory system (real-time inventory, loss rate), and procurement system (procurement cycle, replenishment response time). External data sources: third-party competitor monitoring platforms (real-time selling prices and price adjustment frequency of similar products), supply chain data platforms (raw material costs and tariff rates), and market demand platforms (promotional activities and holiday demand fluctuations); The above data together constitute multidimensional asset status data.

[0100] For example, the data collection frequency can be 5 minutes per time to ensure real-time performance.

[0101] 2. Data Processing Layer: Preprocesses the collected data (multi-dimensional asset status data) to provide high-quality input for model calculations. Data cleaning: The "forward imputation method" is used to handle missing values ​​(e.g., if one competitor's price is missing, it is filled with the previous data), and the "three standard deviation principle" is used to remove outliers (e.g., if sales suddenly increase by 10 times, it is an outlier and is replaced with the 7-day average). Data standardization: Standardization normalizes all data to the [0,1] range, eliminating differences in units (e.g., mapping "sales of 1000 units" and "cost of 50 yuan" to the [0,1] range). Feature extraction: Extract trend features (7-day moving average) and periodic features (weekly sales fluctuations) from time-series data (sales volume, price). Predict sales volume for the next 7 days using the LSTM algorithm (output S). t pred This serves as the basis for setting inventory safety thresholds.

[0102] 3. Model Calculation Layer: The core is a dual-objective optimization model based on DQN, namely "revenue-inventory", which enables intelligent calculation of pricing decisions; 4. Decision Execution Layer: Based on the model output, automatically execute price adjustment operations or generate pre-sale plans, and feed back actual sales and inventory data to the data acquisition layer to form a closed-loop optimization.

[0103] According to the technical solution provided in this disclosure, a dual-objective function model is used to improve the profit per product cycle while ensuring inventory turnover rate; reduce inventory backlog rate and reduce stockout losses; the adaptive adjustment mechanism reduces extreme pricing situations and avoids the perception of "low price and low quality" caused by excessive price reduction; on the other hand, the pre-sale linkage reduces stockout waiting time, achieving dual optimization of "user experience" and "platform revenue".

[0104] Figure 4 This is a schematic diagram of a dual-objective function model training method provided in an embodiment of this disclosure. Figure 4 As shown, the training method for this dual-objective function model includes: A dual-objective optimization function (quantitative value objective function) is constructed based on the DQN algorithm to simultaneously optimize "profit per unit" and "inventory turnover rate". The specific design is as follows: 1. Profit Objective Function: Based on the objective of "maximizing profit per product cycle", the formula is:

[0105] Among them, P t C represents the selling price of the commodity at time t (unit: yuan); t S represents the unit comprehensive cost at time t (including procurement cost, logistics cost, and tariff cost, updated in real time); t H represents the actual sales volume at time t (unit: pieces / catties); t I represents the unit inventory holding cost at time t (including warehousing and loss costs, unit: yuan / day); t The remaining inventory at time t is represented by units of pieces per kilogram; T represents the optimization period (T=7 days for fresh produce and T=30 days for cross-border products).

[0106] 2. Inventory Target Constraints: For example, inventory turnover rate (Turnover = Periodic Sales / Average Inventory) can be used as a hard constraint, with category-specific thresholds set (e.g., fresh produce turnover days less than or equal to 15 days, cross-border goods less than or equal to 30 days), and integrated into the DQN reward function through a "dynamic weighting mechanism".

[0107] Where ω1 represents the profit weight, ω2 represents the inventory weight, and ω1+ω2=1; Health represents the inventory health (Health = actual inventory / safety stock), and the expression for safety stock is: ; For example, the weighting adjustment rule is as follows: when the inventory turnover rate is lower than the threshold (e.g., the turnover days are greater than 30 days), ω1=0.4, ω2=0.6 (prioritize ensuring inventory turnover); when the turnover rate is higher than the threshold (e.g., the turnover days are less than 20 days), ω1=0.8, ω2=0.2 (prioritize improving profits).

[0108] 3. The training details of the DQN model can be illustrated using the following example: State space: contains standardized data in 10 dimensions (sales volume, inventory, cost, competitor prices, demand fluctuation factors, etc.). Action options: 7 pricing actions (price increase of 5%, price increase of 3%, price increase of 2%, maintain original price, price decrease of 2%, price decrease of 3%, price decrease of 5%). Training parameters: learning rate 0.001, experience replay pool size 10000, target network updated once every 100 steps; Convergence condition: The model training is complete when the reward function value fluctuates by less than or equal to 5% for 1000 consecutive steps.

[0109] 4. Multi-dimensional data input system We construct comprehensive internal and external data inputs to supplement supply chain data. Specific data items and their functions are shown in the table below: Table 1 Multidimensional Data Collection Table

[0110] 5. Adaptive dynamic adjustment mechanism In some embodiments, a dual mechanism of "real-time price adjustment step size optimization" and "pre-sale linkage" can be designed to achieve adaptive coordination between inventory and pricing: (1) Real-time price adjustment step size optimization: The price adjustment range is dynamically adjusted based on the inventory health status, and the rules are as follows: Table 2 Dynamic Adjustment Range Table

[0111] (2) Pre-sale linkage strategy: When the expression for the inventory gap risk value (Risk) is:

[0112] Automatically generate pre-sale plans: Pre-sale price P pre calculate:

[0113] Where α represents the "replenishment cycle premium coefficient", which balances user acceptance and replenishment costs; Pre-sale order control: The pre-sale order limit = replenishment quantity × 80% to avoid order defaults caused by replenishment delays; Pre-sale termination condition: When the total amount of actual inventory and pre-sale orders is greater than or equal to the safety stock, the pre-sale will automatically end and normal price adjustment will resume.

[0114] According to the technical solution provided in this disclosure, by introducing supply chain data, the pricing model can adapt to cost changes in real time: for example, when cross-border goods encounter tariff increases, the system can update costs and adjust prices to avoid cost inversion; when the price of raw materials for fresh produce rises, it can enhance the ability to resist risks.

[0115] The following are embodiments of the apparatus disclosed herein, which can be used to execute embodiments of the method disclosed herein. For details not disclosed in the apparatus embodiments of this disclosure, please refer to the embodiments of the method disclosed herein.

[0116] Figure 5 This is a schematic diagram of an asset value data determination device provided in an embodiment of this disclosure. Figure 5 As shown, the asset value data determination device includes: The first processing module 501 is used to map the asset health status based on preset weighted comparison data and preset stock turnover rate threshold to obtain real-time weight values. The second processing module 502 is used to evaluate and process the real-time weight value, the quantitative value objective function and the multi-dimensional state data of the asset to obtain the asset value adjustment instruction. The third processing module 503 is used to execute asset value adjustment instructions and obtain real-time asset flow data and real-time asset stock data. The fourth processing module 504 is used to perform correction processing on real-time asset flow data and real-time asset stock data based on asset value adjustment instructions to obtain asset value adjustment correction instructions. The fifth processing module 505 is used to execute asset value adjustment and correction instructions based on the quantitative value objective function to obtain target asset value data.

[0117] According to the technical solution provided in this disclosure, the health of asset inventory is mapped based on preset weighted comparison data and preset inventory turnover rate threshold to obtain a real-time weight value. The real-time weight value, quantitative value objective function, and multi-dimensional asset status data can be evaluated to generate an asset value adjustment instruction. Executing this asset value adjustment instruction outputs real-time asset flow data and real-time asset inventory data. Furthermore, the real-time asset flow data and real-time asset inventory data can be corrected to form an asset value adjustment correction instruction. The asset value adjustment correction instruction can be executed according to the quantitative value objective function to obtain target asset value data. This improves the real-time performance and accuracy of asset valuation, enhances the flexibility of response to market fluctuations and inventory changes, improves the matching degree between asset value and future return expectations, reduces inventory depreciation risk and financial valuation deviation, and enhances adaptability.

[0118] In some embodiments, the first processing module 501 is specifically used to: perform segmented comparison processing on the asset stock health status and a preset stock turnover rate threshold to obtain a health status interval code; perform query processing on the health status interval code based on preset weight comparison data to obtain asset value weight value and stock weight value; and perform smoothing processing on the asset value weight value and stock weight value to obtain a real-time weight value.

[0119] In some embodiments, the second processing module 502 is specifically used to: compare the stock index value and the flow index value to obtain the asset stock health score; determine the periodic asset value based on the quantitative value objective function and the multidimensional asset status data; perform weighted fusion processing on the periodic asset value and the asset stock health score to obtain the real-time weighted fusion value; and determine the asset value adjustment instruction based on the preset weighted fusion threshold and the real-time weighted fusion value.

[0120] In some embodiments, the fourth processing module 504 is specifically used to perform anomaly detection processing on real-time asset flow data and real-time asset stock data to obtain anomaly deviation values; perform moving average calculation processing on the anomaly deviation values ​​to obtain asset correction increments; and process asset value adjustment instructions based on asset correction increments to obtain asset value adjustment correction instructions.

[0121] In some embodiments, the fifth processing module 505 is specifically used to calculate and process the asset value adjustment and correction instruction based on the quantitative value objective function to obtain the asset value of the correction period; and to perform convergence processing on the asset value of the correction period to obtain the target asset value data.

[0122] In some embodiments, the asset value data determination device is further configured to: acquire initial asset flow data, initial asset input data, and initial asset depreciation data; construct a quantitative value objective function based on the initial asset flow data, initial asset input data, and initial asset depreciation data; and perform standardization processing on the initial asset flow data, initial asset input data, and initial asset depreciation data to obtain multidimensional asset status data.

[0123] In some embodiments, the asset value data determination device is further configured to: obtain an initial asset inventory balance value; perform flow assessment processing on the initial asset inventory balance value based on a preset asset increment cycle to obtain an estimated asset flow value; and perform ratio calculation processing on the initial asset inventory balance value and the estimated asset flow value to obtain the asset inventory health status.

[0124] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this disclosure.

[0125] Figure 6 This is a schematic diagram of the electronic device 6 provided in an embodiment of this disclosure. Figure 6 As shown, the electronic device 6 of this embodiment includes a processor 601, a memory 602, and a computer program 603 stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program 603, it implements the steps in the various method embodiments described above. Alternatively, when the processor 601 executes the computer program 603, it implements the functions of each module / unit in the various device embodiments described above.

[0126] Electronic device 6 can be a desktop computer, laptop, handheld computer, cloud server, or other electronic device. Electronic device 6 may include, but is not limited to, processor 601 and memory 602. Those skilled in the art will understand that... Figure 6 This is merely an example of electronic device 6 and does not constitute a limitation on electronic device 6. It may include more or fewer components than shown, or different components.

[0127] The processor 601 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0128] The memory 602 can be an internal storage unit of the electronic device 6, such as a hard disk or RAM of the electronic device 6. The memory 602 can also be an external storage device of the electronic device 6, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 6. The memory 602 can also include both internal and external storage units of the electronic device 6. The memory 602 is used to store computer programs and other programs and data required by the electronic device.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0130] If integrated modules / units are implemented as software functional units and sold or used as independent products, they can be stored in a readable storage medium (e.g., a computer-readable storage medium). Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program may include computer program code, which can be in the form of source code, asset code, executable files, or certain intermediate forms. A computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0131] The above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit it. Although this disclosure 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 of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be included within the protection scope of this disclosure.

Claims

1. A method for determining asset value data, characterized in that, include: The asset health status is mapped based on preset weighted comparison data and preset stock turnover rate threshold to obtain real-time weight values. The real-time weight values, the quantitative value objective function, and the multi-dimensional asset status data are evaluated and processed to obtain asset value adjustment instructions. Execute the asset value adjustment instruction to obtain real-time asset flow data and real-time asset stock data; Based on the asset value adjustment instruction, the real-time asset flow data and the real-time asset stock data are corrected to obtain the asset value adjustment correction instruction. The asset value adjustment and correction instruction is executed based on the quantitative value objective function to obtain the target asset value data.

2. The method for determining asset value data according to claim 1, characterized in that, The process of mapping asset health based on preset weighted comparison data and preset inventory turnover rate threshold to obtain real-time weight values ​​includes: The asset health status and the preset asset turnover rate threshold are compared in segments to obtain a health status interval code. Based on the preset weighted comparison data, the health interval code is queried and processed to obtain the asset value weight value and the stock weight value. The asset value weight value and the stock weight value are smoothed to obtain the real-time weight value.

3. The method for determining asset value data according to claim 1, characterized in that, The multidimensional status data includes stock index values ​​and flow index values; The process of evaluating and processing the real-time weight values, the quantitative value objective function, and the multi-dimensional asset state data to obtain asset value adjustment instructions includes: The stock index value and the flow index value are compared to obtain the asset stock health score. The value of periodic assets is determined based on the quantitative value objective function and the multidimensional state data of the assets. The value of the cyclical assets and the health score of the asset stock are weighted and merged to obtain a real-time weighted fusion value. The asset value adjustment instruction is determined based on the preset weighted fusion threshold and the real-time weighted fusion value.

4. The method for determining asset value data according to claim 1, characterized in that, The step of correcting the real-time asset flow data and the real-time asset stock data based on the asset value adjustment instruction to obtain the asset value adjustment correction instruction includes: Anomaly detection processing is performed on the real-time asset flow data and the real-time asset inventory data to obtain anomaly deviation values; The abnormal deviation values ​​are processed by moving average calculation to obtain the asset correction increment; The asset value adjustment instruction is processed based on the asset correction increment to obtain the asset value adjustment correction instruction.

5. The method for determining asset value data according to claim 1, characterized in that, The step of executing the asset value adjustment and correction instruction based on the quantitative value objective function to obtain target asset value data includes: The asset value adjustment and correction instruction is calculated and processed based on the quantitative value objective function to obtain the asset value during the correction period; The asset value of the correction period is converged to obtain the target asset value data.

6. The method for determining asset value data according to claim 1, characterized in that, Before evaluating and processing the real-time weight value, the quantitative value objective function, and the multi-dimensional asset state data to obtain the asset value adjustment instruction, the method further includes: Acquire initial asset flow data, initial asset input data, and initial asset depreciation data; Based on the initial asset flow data, the initial asset input data, and the initial asset loss data, the quantitative value objective function is constructed. The initial asset flow data, the initial asset input data, and the initial asset loss data are standardized to obtain the multidimensional asset status data.

7. The method for determining asset value data according to claim 1, characterized in that, Before mapping the asset health status based on preset weighted comparison data and preset inventory turnover rate threshold to obtain the real-time weight value, the process further includes: Obtain the initial asset inventory balance value; Based on a preset asset increment cycle, the initial asset stock balance value is subjected to flow assessment processing to obtain the estimated asset flow value. The initial asset inventory balance and the estimated asset flow are proportionally calculated to obtain the asset inventory health status.

8. An asset value data determination device, characterized in that, include: The first processing module is used to map the asset health status based on preset weighted comparison data and preset stock turnover rate threshold to obtain real-time weight values. The second processing module is used to evaluate and process the real-time weight value, the quantitative value objective function, and the multi-dimensional asset status data to obtain an asset value adjustment instruction. The third processing module is used to execute the asset value adjustment instruction to obtain real-time asset flow data and real-time asset stock data. The fourth processing module is used to perform correction processing on the real-time asset flow data and the real-time asset stock data based on the asset value adjustment instruction, so as to obtain the asset value adjustment correction instruction. The fifth processing module is used to execute the asset value adjustment and correction instruction based on the quantitative value objective function to obtain the target asset value data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images