Operation data processing system based on artificial intelligence

Abstract

The invention relates to the technical field of operation data processing, in particular to an artificial intelligence-based operation data processing system, which comprises a product data acquisition module for acquiring product data and hardware index parameters, an operation data acquisition module for acquiring operation data in a monitoring period, and a feature analysis module, the system comprises a data setting module for setting initial decision operation data of various products, a model building module for building operation scene models of the various products, an operation state judgment module for judging operation states of the various products in a monitoring period and obtaining an overall operation state evaluation result, and a data coupling analysis module for generating related weights of the various products in real time, the inventory accumulation analysis module is used for obtaining accumulation attenuation indexes of various products in the monitoring period, and the operation data processing module is used for generating decision operation data. According to the invention, the processing efficiency of the operation data is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of operation data processing, and particularly to an operation data processing system based on artificial intelligence. Background Art

[0002] With the development of information technology, the amount of data generated in the daily operation of enterprises has increased explosively. How to effectively extract valuable information from these massive data has become an important issue. Traditional data processing methods are often inefficient in the face of large-scale data and difficult to adapt to complex and changing business environments. Therefore, there is an urgent need for an intelligent data processing system that can automatically analyze, learn and predict to improve operation efficiency and decision-making quality.

[0003] Chinese Patent Publication No. CN116502107A discloses a supply chain data processing system for an artificial intelligence-based data intelligent operation platform. The system analyzes according to the time distribution density corresponding to the supply chain data, divides all supply chain data into at least two sparse data clustering sets, obtains the corresponding concentration degree according to the quantity and time distribution characteristics of different types of supply chain data in the sparse data clustering sets, obtains the corresponding integration necessity according to the differences in the corresponding type quantities, time lengths and concentration degrees of any two sparse data clustering sets, integrates the two sparse data clustering sets through the integration necessity to obtain an integrated data clustering set, and performs supply chain data encryption processing through the integrated data clustering set; thus, it can be seen that when the invention processes the operation platform data, it does not perform fusion analysis of multi-modal data to obtain accurate decisions, and there is a problem of low efficiency in processing operation data. Summary of the Invention

[0004] The purpose of the present invention is to provide an operation data processing system based on artificial intelligence to solve at least one of the problems existing in the prior art.

[0005] To achieve the above object, the present invention adopts the following technical solutions: An operation data processing system based on artificial intelligence, characterized by comprising: An operation status judgment module, configured to substitute the operation data within the monitoring period into the operation scenario models of various products to judge the operation status of various products within the monitoring period and integrate them to obtain an overall operation status evaluation result; An inventory accumulation analysis module, configured to perform fusion analysis on the inventory data within the monitoring period to obtain the accumulation decay index of various products within the monitoring period; An operation data processing module, configured to fuse the overall operation status evaluation result, the operation status of various products, and the accumulation decay index of various products within the monitoring period to generate decision-making operation data.

[0006] Optionally, the operation status judgment module includes a numerical analysis unit, which is used to substitute the operation data within the monitoring period into the operation scenario models of various products to judge the operation status of various products within the monitoring period; The numerical analysis unit substitutes the ambient temperature sa and the ambient humidity sb within the monitoring period into the real-time scenario control temperature a and the real-time scenario control humidity b respectively to obtain the operation scenario index F(i) of the i-th type of product within the monitoring period; The numerical analysis unit judges whether the storage status of various products is normal according to the operation scenario index F(i) of various products within the monitoring period, and determines the operation status of various products when the storage status of the products is normal; when the storage status of the products is abnormal, it is determined that the operation status of this type of product within the monitoring period is abnormal.

[0007] Optionally, the operation status judgment module further includes an operation evaluation unit, which is used to count the operation status analysis results of various products and integrate the statistical results to obtain the evaluation result of the overall operation status; The operation evaluation unit counts the proportion μ2 of various products with abnormal operation status within the monitoring period, and judges whether the overall operation status is normal based on the statistical results.

[0008] Optionally, it further includes a data coupling analysis module, which is used to generate the relevant weights of various products in real time according to the real-time operation data of the scenario within the monitoring period, and adjust the evaluation process of the overall operation in real time with the relevant weights of various products; The data coupling analysis module includes a relevant weight analysis unit, which is used to generate scenario-related weights in real time according to the real-time operation data of the scenario within the monitoring period, and adjust the evaluation process of the overall operation in real time with the scenario-related weights; The relevant weight analysis unit is used to calculate the scenario-related weight g, and adjust the evaluation process of the overall operation in real time according to the scenario-related weight g. The specific process is as follows: If g < L, the relevant weight analysis unit determines that the scenario disturbance is normal and does not make adjustments; otherwise, the relevant weight analysis unit determines that the scenario disturbance is abnormal, and adjusts the overall sensitivity constant to K', so that the overall sensitivity constant shows a monotonically decreasing form with respect to the scenario-related weight; L is the scenario disturbance constant.

[0009] Optionally, the data coupling analysis module further includes a difference calibration unit, which is used to obtain the scenario time decay factor τ, and calibrate the evaluation process of the real-time adjustment of the overall operation according to the scenario time decay factor. If τ ≥ P, the difference calibration unit does not perform optimization; otherwise, the difference calibration unit calibrates the scenario disturbance constant to L', and controls the judgment range of its judgment of the scenario disturbance with the scenario time decay factor.

[0010] Optionally, the inventory accumulation analysis module is used to count the inventory quantity n(i) of various products, calculate the analysis accumulation ratio μ3(i) of various products, and analyze the accumulation decay index η(i) of various products according to the analysis accumulation ratio μ3(i) of various products: if μ3(i) < G, the inventory accumulation analysis module determines that the decay state of this type of product is normal, and sets the accumulation decay index of this type of product to η(i) = 0; otherwise, the inventory accumulation analysis module determines that the decay state of this type of product is abnormal, and sets the accumulation decay index of this type of product to η(i) = [μ3(i) - G] / G; where G is a preset product accumulation loss index.

[0011] Optionally, the operation data processing module is used to generate decision operation data according to the overall operation status evaluation result within the monitoring period, the operation status of various products, and the accumulation decay index of various products: When the overall operation status is normal, if the operation status of the i-th type of product is normal, the operation data processing module sets the decision operation cycle of this type of product to JT1(i); if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT2(i); When the overall operation status is abnormal, if the operation status of the i-th type of product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT3(i); if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT4(i); The operation data processing module stores the decision operation data in the server.

[0012] Optionally, it further includes: A product data acquisition module, which is used to acquire product data and hardware index parameters by means of user input; An operation data collection module, which is used to collect operation data within the monitoring period by means of periodic collection; A feature analysis module, which is used to extract product features according to product data, and set the initial decision operation data of various products according to the product feature extraction results; A model construction module, which is used to construct an operation scenario model of various products by integrating the initial decision operation data of various products with hardware index parameters; The feature analysis module includes a corruption rate analysis unit, which is used to obtain the corruption rate coefficient SRC(i) of various products according to product data, and set i ∈ N+, and SRC(i) represents the corruption rate coefficient of the i-th type of product; The spoilage rate analysis unit is used to take the spoilage rate coefficient SRC(i) of various products as the product characteristics of various products.

[0013] Optionally, the feature analysis module further includes an initial plan planning unit, which is used to set the initial decision operation data of various products according to the product characteristics; The steps for setting the initial product operation plan are as follows: If SRC(i) < K, the initial plan planning unit sets the operation cycle of this type of product to T(i), and the setting steps of its operation cycle T(i) are as follows: T(i) = v(i); If SRC(i) ≥ K, the initial plan planning unit sets the operation cycle of this type of product to TG(i), and the setting steps of its operation cycle TG(i) are as follows: TG(i) = exp{[SRC(i) - K] / K} × v(i); Where K is a preset product spoilage constant, and v(i) is the historical operation cycle of the i-th type of product; The initial plan planning unit takes the operation cycle as the initial decision operation data.

[0014] Optionally, the model construction module constructs the operation scenario model of various products by integrating the initial decision operation data of various products with the hardware index parameters; The model construction module constructs the operation scenario model equation of various products with the hardware index parameters as known constants and the initial decision operation data as control coefficients, and sets the operation scenario model equation of the i-th type of product as: F(i) = the operation cycle of the i-th type of product × {a1 × [(A(i) - a) / A(i)]2 + a2 × [(B(i) - b) / B(i)]}; Where F(i) is the operation scenario index of the i-th type of product, a1 is the scenario temperature control coefficient, a2 is the scenario humidity control coefficient, a is the real-time scenario control temperature, b is the real-time scenario control humidity, A(i) is the optimal scenario temperature of the i-th type of product, and B(i) is the optimal scenario humidity of the i-th type of product.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: By analyzing multi-source heterogeneous data in real time through an AI model, a dynamic decision-making scheme is generated, reducing manual intervention and improving operational efficiency; By combining the corruption rate model and the stacking decay index, the loss risk of perishable products is identified in advance, inventory management is optimized, and resource waste is reduced; By introducing scenario-related weights and dynamic sensitivity constants, the system can quickly respond to external environmental changes and improve robustness in complex scenarios; By setting the operation cycle differently and combining the product status and environmental weights, the optimal allocation of resources is achieved, the slow-moving cycle is shortened, and the turnover rate is increased; The modular design supports function expansion, is applicable to multiple fields such as fresh food retail and cold chain logistics, and has broad application potential. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic structural diagram of the operation data processing system based on artificial intelligence in this embodiment.

[0018] Figure 2 It is a schematic structural diagram of the feature analysis module in this embodiment.

[0019] Figure 3 It is a schematic structural diagram of the operation state judgment module in this embodiment.

[0020] Figure 4 It is a schematic structural diagram of the data coupling analysis module in this embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to more clearly illustrate the present invention, the following further describes the present invention in conjunction with preferred embodiments and the drawings. Similar components in the drawings are denoted by the same reference numerals. Those skilled in the art should understand that the following specifically described content is illustrative rather than restrictive, and should not be used to limit the protection scope of the present invention.

[0022] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so as to implement the embodiments of the present application described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0023] Specifically, the system described in this embodiment is used for processing the operation data in a community fresh food supermarket. The nature of the scenario is a multi-source heterogeneous data and hardware resource-constrained scenario. The system described in this embodiment is installed in a cloud server or a locally deployed server in the form of an application.

[0024] Please refer to Figure 1 as shown, which is a schematic structural diagram of the operation data processing system based on artificial intelligence described in this embodiment, including: A product data acquisition module, which is used to acquire product data and hardware index parameters by means of user input; the product data includes the historical average spoilage cycle, factory-set shelf life cycle, and historical operation cycle of various products; the hardware index parameters include the optimal scenario temperature and optimal scenario humidity of the product.

[0025] It can be understood that the products described in this embodiment are specifically products such as vegetables, dairy products, and meats in a fresh food supermarket that are not easy to preserve and are sensitive to inventory management.

[0026] Please continue to refer to Figure 1 as shown, the system further includes: An operation data collection module, which is used to collect operation data within a monitoring period by means of periodic collection; the operation data includes ambient temperature, ambient humidity, product shelf life, product consumption ratio, scenario real-time operation data, and inventory data; the product consumption ratio is the product sale ratio, and the scenario real-time operation data includes scenario precipitation, scenario temperature, and scenario disturbance wind speed, and the inventory data includes the inventory quantity of various products.

[0027] Specifically, this embodiment does not specifically limit the value of the duration of the monitoring period. Those skilled in the art can freely set it as long as it meets the value requirements of the duration of the monitoring period. The best value of the duration of the monitoring period in this embodiment is 2 hours.

[0028] Specifically, in this embodiment, the acquisition methods of the product data, hardware index parameters, and operation data within the monitoring period are all obtained through external interactive input. The product data and hardware index parameters are obtained through user interactive input, and the operation data within the monitoring period is obtained through Internet of Things collection.

[0029] Please continue to refer to Figure 1 As shown, the system further includes a feature analysis module. The feature analysis module is connected to the product data acquisition module. The feature analysis module is used to extract product features based on the product data and set the initial decision-making operation data for various products according to the product feature extraction results.

[0030] Please refer to Figure 2 As shown, the feature analysis module includes a spoilage rate analysis unit, which is used to obtain the spoilage rate coefficient SRC(i) of various products according to the product data, where i ∈ N+, and SRC(i) represents the spoilage rate coefficient of the i-th type of product; The process of obtaining the spoilage rate coefficient SRC(i) of various products is as follows: SRC(i)=α(i)×exp{β(i)}; Among them, α(i) represents the basic spoilage rate of the i-th type of product, and α(i)=tm(i) / TM(i) is set, where tm(i) represents the historical average spoilage cycle of the i-th type of product, and TM(i) represents the factory-set shelf life of the i-th type of product. β(i) represents the temperature sensitivity index of the i-th type of product, and β(i)=[R1(i) / R2(i)]^{10 / [t1-t2]} is set. R1(i) is the carbon dioxide generation rate of the i-th type of product at temperature t1, R2(i) is the carbon dioxide generation rate of the i-th type of product at temperature t2, and t1 and t2 are the set detection temperature values respectively; The spoilage rate analysis unit is used to take the spoilage rate coefficient SRC(i) of various products as the product features of various products; based on parameters such as the product historical spoilage cycle and temperature sensitivity index, a spoilage rate model (SRC(i)) is constructed to quantify the spoilage risk of the product and provide a scientific basis for setting the subsequent operation cycle.

[0031] Specifically, in this embodiment, R1(i), R2(i), t1, and t2 are all input to the server through user interaction, and their specific values are determined by the user himself. Their value range is limited to t1 ≠ t2, and -10°C < [t1, t2] < 40°C.

[0032] Please continue to refer to Figure 2 As shown, the feature analysis module further includes an initial plan planning unit. The initial plan planning unit is connected to the spoilage rate analysis unit. The initial plan planning unit is used to set the initial decision-making operation data for various products according to the product features; The steps for setting the initial product operation plan are as follows: If SRC(i) < K, the initial plan planning unit sets the operation cycle of this type of product to T(i), and the steps for setting its operation cycle T(i) are as follows: T(i) = v(i); If SRC(i) ≥ K, the initial plan planning unit sets the operation cycle of this type of product to TG(i), and the steps for setting its operation cycle TG(i) are as follows: TG(i) = exp{[SRC(i) - K] / K} × v(i); Where K is the preset product spoilage constant, and v(i) is the historical operation cycle of the i-th type of product; The initial plan planning unit takes the operation cycle as the initial decision operation data; according to the spoilage rate coefficient and the preset spoilage constant, it differentially sets the initial operation cycle (T(i) or TG(i)) to achieve the rapid turnover of high-risk products and reduce spoilage losses.

[0033] Specifically, in this embodiment, the value of the preset product spoilage constant K is not specifically limited, and those skilled in the art can freely set it as long as it meets the value requirements of the preset product spoilage constant K. The best value of the preset product spoilage constant K in this embodiment is 1.3; it can be understood that in this embodiment, the historical operation cycle is the time cycle for replenishing a certain type of product.

[0034] Please continue to refer to Figure 1 As shown, the system is further provided with a model construction module, which is connected to the feature analysis module. The model construction module is used to construct the operation scenario model of various products by integrating the initial decision operation data of various products with the hardware index parameters; The model construction module constructs the operation scenario model equation of various products with the hardware index parameters as known constants and the initial decision operation data as control coefficients. The operation scenario model equation of the i-th type of product is set as: F(i) = the operation cycle of the i-th type of product × {a1 × [(A(i) - a) / A(i)]2 + a2 × [(B(i) - b) / B(i)]}; Among them, F(i) is the operation scenario index of the i-th type of product, a1 is the scenario temperature control coefficient, a2 is the scenario humidity control coefficient, a is the real-time scenario control temperature, b is the real-time scenario control humidity, A(i) is the optimal scenario temperature of the i-th type of product, and B(i) is the optimal scenario humidity of the i-th type of product; by integrating the hardware index parameters and the initial decision-making data, a multi-variable operation scenario model (F(i) = operation cycle × [temperature control term + humidity control term]) is constructed to achieve the deep coupling of environmental parameters and product characteristics, providing high-precision input for the judgment of the operation state.

[0035] It can be understood that in this embodiment, both a and b are equation variables and are substituted by actual parameters; at the same time, the values of a1 and a2 in this embodiment are not specifically set in this embodiment, and only need to meet their value requirements. The optimal values of the scenario temperature control coefficient a1 and the scenario humidity control coefficient a2 in this embodiment are 1 and 0.7 respectively; the specific process of their values can be obtained by non-linear fitting of historical data; at the same time, in the equation "F(i) = the operation cycle of the i-th type of product × {a1 × [(A(i) - a) / A(i)]^2 + a2 × [(B(i) - b) / B(i)]}", F(i) is the unknown, and only parameter explanations are made here without assigning values to it.

[0036] Please continue to refer to Figure 1 As shown, the system further includes an operation state judgment module, which is connected to the model construction module. The operation state judgment module is used to substitute the operation data within the monitoring period into the operation scenario models of various types of products to judge the operation states of various types of products within the monitoring period, and integrate the operation states of various types of products to obtain an overall operation state evaluation result.

[0037] Please refer to Figure 3 As shown, the operation state judgment module includes a numerical analysis unit, which is used to substitute the operation data within the monitoring period into the operation scenario models of various types of products to judge the operation states of various types of products within the monitoring period; The numerical analysis unit substitutes the environmental temperature sa and environmental humidity sb within the monitoring period into the real-time scenario control temperature a and the real-time scenario control humidity b respectively to obtain the operation scenario index F(i) of the i-th type of product within the monitoring period; The numerical analysis unit judges the operation states of various types of products within the monitoring period according to the operation scenario index F(i) of various types of products within the monitoring period. The specific judgment process is as follows: When F(i) < YF, the numerical analysis unit determines that the storage status of this type of product during the monitoring period is normal. At this time, if μ1(i) ≥ U(i), the numerical analysis unit determines that the operation status of this type of product is normal; otherwise, the numerical analysis unit determines that the operation status of this type of product is abnormal. When F(i) ≥ YF, the numerical analysis unit determines that the operation status of this type of product during the monitoring period is abnormal; by substituting real-time data such as environmental temperature and humidity into the operation scenario model, the operation scenario index (F(i)) of the product is dynamically calculated to achieve real-time monitoring of the product status. Combining the consumption ratio (μ1(i)) with the preset thresholds (YF, U(i)), quickly determine whether the product operation is abnormal, and improve the accuracy and timeliness of status recognition; Among them, YF is the preset operation status index, μ1(i) is the consumption ratio of the i-th type of product during the monitoring period, and U(i) is the preset consumption ratio of the i-th type of product.

[0038] Specifically, in this embodiment, the value of the preset operation status index YF is not specifically limited, and those skilled in the art can freely set it as long as it meets the value requirements of the preset operation status real number YF. The best value of the preset operation status index YF in this embodiment is 2 days; at the same time, in this embodiment, U(i) is obtained by taking the average value of historical data.

[0039] Please continue to refer to Figure 3 As shown, the operation status judgment module further includes an operation evaluation unit. The operation evaluation unit is connected to the numerical analysis unit. The operation evaluation unit is used to count the operation status analysis results of various types of products and integrate the statistical results to obtain an evaluation result of the overall operation status; The operation evaluation unit counts the proportion μ2 of the operation status of various types of products being abnormal during the monitoring period, and evaluates the overall operation status based on the statistical results: if <K, the operation status evaluation unit determines that the overall operation status is normal; otherwise, the operation status evaluation unit determines that the overall operation status is abnormal; where K is the overall sensitivity constant, and F(j) is the product category with the j-th operation status being abnormal; by counting the proportion of abnormal products (μ2) and integrating it into the overall operation status evaluation result, it helps the manager quickly grasp the overall operation health status and avoid local abnormalities affecting the overall efficiency.

[0040] Specifically, in this embodiment, the value of the overall sensitivity constant K is not specifically limited, and those skilled in the art can freely set it as long as it meets the value requirements of the overall sensitivity constant K. The best value of the overall sensitivity constant K in this embodiment is 0.3.

[0041] Please continue to refer to Figure 1As shown, the system further includes a data coupling analysis module, which is connected to the operation status judgment module. The data coupling analysis module is used to generate relevant weights of various products in real time according to the real-time operation data of the scenario within the monitoring period, and adjust the evaluation process of the overall operation in real time with the relevant weights of various products.

[0042] Please refer to Figure 4 As shown, the data coupling analysis module includes a relevant weight analysis unit, which is used to generate scenario-related weights in real time according to the real-time operation data of the scenario within the monitoring period, and adjust the evaluation process of the overall operation in real time with the scenario-related weights; The relevant weight analysis unit is used to calculate the scenario-related weight g, and set g = s1×|t - WT| + s2×|jy - JY| / JY + s3×wf; where s1 is the temperature offset coefficient, s2 is the precipitation perturbation coefficient, s3 is the wind speed perturbation coefficient, t is the scenario temperature within the monitoring period, WT is the offset temperature threshold, jy is the precipitation amount in the scenario within the monitoring period, JY is the perturbation precipitation threshold, and wf is the scenario perturbation wind speed; The relevant weight analysis unit adjusts the evaluation process of the overall operation in real time according to the scenario-related weight g. The specific process is as follows: If g < L, the relevant weight analysis unit determines that the scenario perturbation is normal and does not make adjustments; otherwise, the relevant weight analysis unit determines that the scenario perturbation is abnormal and adjusts the overall sensitivity constant to K', and sets K' = K×exp{-(g - L) / L}; L is the scenario perturbation constant; by calculating the scenario-related weight (g) through environmental parameters (temperature, precipitation, wind speed), the overall sensitivity constant is dynamically adjusted to enhance the adaptability of the system to external environmental perturbations and ensure the robustness of the evaluation results.

[0043] Specifically, the premise for adjusting the evaluation process of the overall operation status in real time according to the scenario-related weight is g≠0; in this embodiment, the value of the temperature offset coefficient s1 is 0.1, and those skilled in the art can also freely set it as long as it meets its value requirements. The value requirements for the precipitation perturbation coefficient s2 and the wind speed perturbation coefficient s3 are s2 + s3 = 1; this embodiment does not specifically limit the value of the scenario perturbation constant L, and those skilled in the art can freely set it as long as it meets the value requirements of the scenario perturbation constant L. The best value of the scenario perturbation constant L in this embodiment is 0.5.

[0044] Please continue to refer to Figure 4As shown, the data coupling analysis module further includes a difference calibration unit. The difference calibration unit is connected to the correlation weight analysis unit. The difference calibration unit is used to obtain the scenario time decay factor τ, and calibrate the evaluation process of the overall operation adjusted in real time according to the scenario time decay factor. If τ≥P, the difference calibration unit does not perform optimization; otherwise, the difference calibration unit calibrates the scenario perturbation constant to L’, and sets L’ = L / ln{e + [τ - P] / P}, where e is the natural logarithm and P is the preset time decay constant; by combining the weight change to calibrate the data deviation, the stability of the model in complex scenarios is improved.

[0045] In this embodiment, the method for obtaining the scenario time decay factor τ is as follows: τ = 1 / (1 + ln(st + 1)); where st is the product shelf life.

[0046] Specifically, in this embodiment, the value of the preset time decay constant P is not specifically limited, and those skilled in the art can freely set it as long as it meets the value requirements of the preset time decay constant P. The best value of the preset time decay constant P in this embodiment is 0.5.

[0047] Please continue to refer to Figure 1 As shown, the system further includes an inventory accumulation analysis module. The inventory accumulation analysis module is connected to the operation data collection module. The inventory accumulation analysis module is used to perform fusion analysis on the inventory data of various products to obtain the accumulation decay index of various products within the monitoring period; The inventory accumulation analysis module is used to count the inventory quantity n(i) of various products, and calculate the analysis accumulation ratio μ3(i) of various products, and set μ3(i) = [n(i) - the operation cycle of the i-th product / T×μ1(i)] / n(i); where T is the duration of the monitoring period; The inventory accumulation analysis module analyzes the accumulation decay index η(i) of various products according to the analysis accumulation ratio μ3(i) of various products: if μ3(i) < G, the inventory accumulation analysis module determines that the decay state of this type of product is normal, and sets the accumulation decay index of this type of product to η(i) = 0; otherwise, the inventory accumulation analysis module determines that the decay state of this type of product is abnormal, and sets the accumulation decay index of this type of product to η(i) = [μ3(i) - G] / G; where G is the preset product accumulation loss index; by calculating the analysis accumulation ratio (μ3(i)) and the accumulation decay index, combining the inventory quantity and operation cycle data, predicting the backlog and loss risks of products, dynamically adjusting the decay index based on the preset threshold, optimizing the inventory turnover strategy, and reducing the losses of unsalable and spoiled products.

[0048] Specifically, in this embodiment, the value of the preset product stacking loss index G is not specifically limited, and those skilled in the art can freely set it as long as the value requirement of the preset product stacking loss index G is met. In this embodiment, the optimal value of the preset product stacking loss index G is 0.7.

[0049] Please continue to refer to Figure 1 As shown, the system further includes an operation data processing module, which is connected to the inventory stacking analysis module and the data coupling analysis module. The operation data processing module is used to generate decision operation data based on the overall operation status evaluation result within the monitoring period, the operation status of various products, and the stacking decay index of various products: When the overall operation status is normal, if the operation status of the i-th type of product is normal, the operation data processing module sets the decision operation cycle of this type of product to JT1(i), and sets JT1(i) = the operation cycle of the i-th type of product; if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT2(i), and sets JT2(i) = the operation cycle of the i-th type of product / η(i); When the overall operation status is abnormal, if the operation status of the i-th type of product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT3(i), and sets JT3(i) = the operation cycle of the i-th type of product × ( -K) / K; if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT4(i), and sets JT4(i) = the operation cycle of the i-th type of product / η(i) × ( -K) / K; The operation data processing module stores the decision operation data in the server; according to the overall operation status and the abnormal conditions of each product, it dynamically generates a differentiated decision operation cycle, and realizes the precise allocation of resources by adjusting the association rule between the operation cycle and the decay index, improving the operation flexibility and response speed.

[0050] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An operation data processing system based on artificial intelligence, characterized in that: include: The operation status judgment module is used to substitute the operation data within the monitoring period into the operation scenario models of various products to judge the operation status of various products within the monitoring period, and integrate them to obtain the overall operation status evaluation result; Inventory accumulation analysis module, which is used to integrate and analyze the inventory data within the monitoring period to obtain the accumulation decay index of various products within the monitoring period; The operation data processing module is used to integrate the overall operation status evaluation results within the monitoring period, the operation status of various products and the accumulation attenuation index of various products to generate decision-making operation data.

2. The artificial intelligence-based operation data processing system according to claim 1, characterized in that: The operation status judgment module includes a numerical analysis unit, which is used to substitute the operation data within the monitoring period into the operation scenario model of each product to judge the operation status of each product within the monitoring period; The numerical analysis unit substitutes the ambient temperature sa and ambient humidity sb in the monitoring period into the real-time scene control temperature a and the real-time scene control humidity b, respectively, to obtain the operation scene index F(i) of the i-th category product in the monitoring period; The numerical analysis unit determines whether the storage status of each type of product is normal based on the operation scenario index F(i) of each type of product during the monitoring period, and determines the operation status of each type of product when the storage status of the product is normal; when the storage status of the product is abnormal, it determines that the operation status of this type of product during the monitoring period is abnormal.

3. The artificial intelligence-based operation data processing system according to claim 2, characterized in that: The operation status judgment module also includes an operation evaluation unit, which is used to collect statistics on the operation status analysis results of various products and integrate the statistical results to obtain an evaluation result of the overall operation status; The operation evaluation unit counts the proportion μ2 of abnormal operation status of various products during the monitoring period, and determines whether the overall operation status is normal based on the statistical results.

4. The artificial intelligence-based operation data processing system according to claim 3 is characterized in that: It also includes a data coupling analysis module, which is used to generate the relevant weights of various products in real time according to the real-time operation data of the scenarios within the monitoring period, and adjust the overall operation evaluation process in real time based on the relevant weights of various products; The data coupling analysis module includes a relevant weight analysis unit, which is used to generate scenario-related weights in real time according to the real-time operation data of the scenarios within the monitoring period, and adjust the evaluation process of the overall operation in real time with the scenario-related weights; The relevant weight analysis unit is used to calculate the scene-related weight g, and adjust the overall operation evaluation process in real time according to the scene-related weight g. The specific process is as follows: If g<L, the relevant weight analysis unit determines that the scene disturbance is normal and does not make any adjustment; otherwise, the relevant weight analysis unit determines that the scene disturbance is abnormal and adjusts the overall sensitivity constant to K', so that the overall sensitivity constant shows a monotonically decreasing form with respect to the scene-related weight; L is the scene disturbance constant.

5. The artificial intelligence-based operation data processing system according to claim 4, characterized in that: The data coupling analysis module also includes a difference calibration unit, which is used to obtain the scene time decay factor τ, and calibrate the evaluation process of adjusting the overall operation in real time according to the scene time decay factor. If τ≥P, the difference calibration unit will not be optimized; otherwise, the difference calibration unit will calibrate the scene disturbance constant to L', and control the judgment range of the scene disturbance with the scene time decay factor.

6. The artificial intelligence-based operation data processing system according to claim 5, characterized in that: The inventory accumulation analysis module is used to count the inventory quantity n(i) of each type of product, calculate the analysis accumulation ratio μ3(i) of each type of product, and analyze the accumulation attenuation index η(i) of each type of product according to the analysis accumulation ratio μ3(i) of each type of product: if μ3(i)<G, the inventory accumulation analysis module determines that the attenuation state of this type of product is normal, and sets the accumulation attenuation index of this type of product to η(i)=0; otherwise, the inventory accumulation analysis module determines that the attenuation state of this type of product is abnormal, and sets the accumulation attenuation index of this type of product to η(i)=[μ3(i)-G] / G; wherein G is a preset product accumulation loss index.

7. The artificial intelligence-based operation data processing system according to claim 6, characterized in that: The operation data processing module is used to generate decision-making operation data according to the overall operation status evaluation results within the monitoring period, the operation status of various products and the stacking decay index of various products: When the overall operation status is normal, if the operation status of the i-th product is normal, the operation data processing module sets the decision operation cycle of this type of product to JT1(i); if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT2(i); When the overall operation status is abnormal, if the operation status of the i-th product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT3(i); if the operation status of the product is abnormal, the operation data processing module sets the decision operation cycle of this type of product to JT4(i); The operation data processing module stores the decision operation data in the server.

8. The artificial intelligence-based operation data processing system according to claim 7, characterized in that: Also includes: Product data acquisition module, used to obtain product data and hardware indicator parameters through user input; An operation data collection module is used to collect operation data within the monitoring period through periodic collection; Feature analysis module, used to extract product features based on product data, and set initial decision-making operation data for various products based on the product feature extraction results; Model building module, which is used to build operation scenario models for various products by integrating the initial decision-making operation data of various products with hardware indicator parameters; The feature analysis module includes a corruption rate analysis unit, which is used to obtain the corruption rate coefficient SRC(i) of each type of product according to the product data, and set i∈N+, SRC(i) represents the corruption rate coefficient of the i-th type of product; The corruption rate analysis unit is used to use the corruption rate coefficient SRC(i) of each product as the product feature of each product.

9. The artificial intelligence-based operation data processing system according to claim 8, characterized in that: The feature analysis module also includes an initial solution planning unit, which is used to set initial decision-making operation data for various products based on product features; The steps to set up an initial product operation plan are as follows: If SRC(i)<K, the initial solution planning unit sets the operating period of this type of product to T(i), and the steps for setting the operating period T(i) are as follows: T(i)=v(i); If SRC(i)≥K, the initial plan planning unit sets the operating period of this type of product to TG(i), and the steps for setting the operating period TG(i) are as follows: TG(i)=exp{[SRC(i)-K] / K}×v(i); Among them, K is the preset product corruption constant, v(i) is the historical operation cycle of the i-th product; The initial scheme planning unit uses the operation cycle as initial decision-making operation data.

10. The artificial intelligence-based operation data processing system according to claim 9, characterized in that: The model building module builds the operation scenario models of various products by fusing the initial decision operation data of various products with the hardware indicator parameters; The model building module uses hardware indicator parameters as known constants and initial decision operation data as control coefficients to build operation scenario model equations for various products, and sets the operation scenario model equation for the i-th product as: F(i) = operating period of product category i × {a1 × [(A(i)-a) / A(i)]2 + a2 × [(B(i)-b) / B(i)]}; Among them, F(i) is the operation scenario index of the i-th product, a1 is the scene temperature control coefficient, a2 is the scene humidity control coefficient, a is the real-time scene control temperature, b is the real-time scene control humidity, A(i) is the optimal scene temperature of the i-th product, and B(i) is the optimal scene humidity of the i-th product.

Images