Inventory processing method and device based on artificial intelligence, computer equipment and medium

Abstract

The invention belongs to the field of artificial intelligence and financial science and technology, and relates to an inventory processing method and device based on artificial intelligence, computer equipment and a storage medium, and the method comprises the steps: obtaining inventory related data corresponding to a target coupon in a preset time period; preprocessing the inventory related data to obtain target inventory related data; calling a pre-trained inventory demand prediction model; performing prediction processing on the target inventory related data to generate an inventory demand prediction result; obtaining a current inventory total amount corresponding to the target coupon based on a streaming processing architecture; generating a numerical comparison result between the inventory demand prediction result and the current total inventory amount; and performing inventory adjustment processing on the target coupons based on the numerical value comparison result. In addition, the invention also relates to a block chain technology, and the inventory demand prediction result can be stored in a block chain. According to the inventory processing method based on the inventory demand prediction model and the streaming processing architecture, the response speed and the processing efficiency of inventory management are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence development technology and the field of financial technology, and in particular to an inventory processing method, device, computer equipment and storage medium based on artificial intelligence. Background Art

[0002] In the financial sector, as the digitalization process accelerates, electronic vouchers, as a convenient and efficient means of payment and promotion, have been widely used in various consumer scenarios, such as online shopping, catering and entertainment, and transportation. The popularity of electronic vouchers not only improves consumers' payment experience, but also provides merchants with more flexible marketing strategies. However, in the management and operation of electronic vouchers, inventory planning and control has become a key issue that needs to be solved urgently.

[0003] Traditionally, inventory planning and replenishment of electronic vouchers rely on manual operations. Although this method can meet basic business needs to a certain extent, its limitations are becoming increasingly prominent in the face of complex and changing market environments and consumer behaviors. Specifically, manual inventory planning often fails to accurately predict changes in market demand, resulting in insufficient inventory during peak periods, affecting customer purchasing experience and merchant sales performance; and during periods of low demand, excess inventory may increase storage costs and even waste resources.

[0004] In addition, manual inventory replenishment processing also has problems such as slow response and low efficiency. When the inventory level is lower than the safety threshold, the replenishment process needs to be manually triggered. In this process, there may be risks such as information transmission delays and decision-making errors, which further increases the difficulty of inventory management. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose an inventory processing method, device, computer equipment and storage medium based on artificial intelligence to solve the technical problems that the existing inventory management method of electronic cards and coupons relies heavily on manual operations, has slow response speed, low efficiency, and easily causes waste of resources.

[0006] In order to solve the above technical problems, the embodiment of the present application provides an inventory processing method based on artificial intelligence, which adopts the following technical solutions:

[0007] Acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data;

[0008] Preprocessing the inventory-related data to obtain corresponding target inventory-related data;

[0009] Call the pre-trained inventory demand forecasting model;

[0010] Based on the inventory demand forecasting model, the target inventory related data is forecasted and processed to generate corresponding inventory demand forecasting results;

[0011] Acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture;

[0012] Generate a numerical comparison result between the inventory demand forecast result and the current total inventory;

[0013] Based on the numerical comparison result, a corresponding inventory adjustment process is performed on the target card or coupon.

[0014] Furthermore, the step of performing corresponding inventory adjustment processing on the target card coupon based on the numerical comparison result specifically includes:

[0015] If the numerical comparison result is that the inventory demand forecast result is greater than the current total inventory, then obtaining a preset replenishment strategy;

[0016] Performing inventory replenishment processing corresponding to the target card or voucher based on the replenishment strategy;

[0017] If the numerical comparison result is that the inventory demand forecast result is less than the current total inventory, then obtaining a preset adjustment strategy;

[0018] An inventory adjustment process corresponding to the target card or ticket is performed based on the adjustment policy.

[0019] Furthermore, the step of preprocessing the inventory-related data to obtain corresponding target inventory-related data specifically includes:

[0020] Performing data cleaning processing on the inventory-related data to obtain corresponding first data;

[0021] Performing standardization processing on the first data to obtain corresponding second data;

[0022] Normalizing the second data to obtain corresponding third data;

[0023] Performing feature construction processing on the third data to obtain corresponding fourth data;

[0024] The fourth data is used as the target inventory related data.

[0025] Furthermore, before the step of calling the pre-trained inventory demand forecasting model, the method further includes:

[0026] Get historical inventory related data;

[0027] Performing data preprocessing on the historical inventory-related data to obtain corresponding first inventory-related data;

[0028] Performing feature engineering processing on the first inventory-related data to obtain corresponding sample data;

[0029] Call the preset initial learning model;

[0030] Based on a preset training strategy, the initial learning model is trained using the sample data to obtain a trained designated learning model;

[0031] The designated learning model is used as the inventory demand prediction model.

[0032] Furthermore, after the step of obtaining the current total inventory corresponding to the target card based on the preset stream processing architecture, the method further includes:

[0033] Get the preset custom alarm conditions;

[0034] Determine whether the current total inventory meets the user-defined alarm condition;

[0035] If yes, generate corresponding inventory warning information based on the current total inventory;

[0036] Identify target notification channels;

[0037] Based on the target notification channel, the inventory warning information is sent to relevant users.

[0038] Furthermore, the inventory processing method based on artificial intelligence also includes:

[0039] Call the preset monitoring tool;

[0040] Collecting system performance indicators corresponding to preset indicator types based on the monitoring tool;

[0041] Determine whether there is an abnormal performance indicator greater than a corresponding preset indicator threshold value among the system performance indicators;

[0042] If so, generating a corresponding warning notification based on the abnormal performance indicator;

[0043] The warning notification is sent to corresponding operation and maintenance personnel.

[0044] Furthermore, the inventory processing method based on artificial intelligence also includes:

[0045] Get the current system load data;

[0046] Determining whether the system load data meets the preset load warning conditions;

[0047] If yes, call the pre-built cloud resource pool;

[0048] Based on the load warning condition, the cloud resource pool is used to perform corresponding resource adjustment processing.

[0049] In order to solve the above technical problems, the embodiment of the present application further provides an inventory processing device based on artificial intelligence, which adopts the following technical solution:

[0050] A first acquisition module is used to acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data;

[0051] A preprocessing module, used for preprocessing the inventory-related data to obtain corresponding target inventory-related data;

[0052] The first calling module is used to call the pre-trained inventory demand forecasting model;

[0053] A prediction module, used to perform prediction processing on the target inventory related data based on the inventory demand prediction model to generate corresponding inventory demand prediction results;

[0054] A second acquisition module, configured to acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture;

[0055] A first generating module, used to generate a numerical comparison result between the inventory demand forecast result and the current total inventory;

[0056] The first adjustment module is used to perform corresponding inventory adjustment processing on the target card based on the numerical comparison result.

[0057] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0058] Acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data;

[0059] Preprocessing the inventory-related data to obtain corresponding target inventory-related data;

[0060] Call the pre-trained inventory demand forecasting model;

[0061] Based on the inventory demand forecasting model, the target inventory related data is forecasted and processed to generate corresponding inventory demand forecasting results;

[0062] Acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture;

[0063] Generate a numerical comparison result between the inventory demand forecast result and the current total inventory;

[0064] Based on the numerical comparison result, a corresponding inventory adjustment process is performed on the target card or coupon.

[0065] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0066] Acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data;

[0067] Preprocessing the inventory-related data to obtain corresponding target inventory-related data;

[0068] Call the pre-trained inventory demand forecasting model;

[0069] Based on the inventory demand forecasting model, the target inventory related data is forecasted and processed to generate corresponding inventory demand forecasting results;

[0070] Acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture;

[0071] Generate a numerical comparison result between the inventory demand forecast result and the current total inventory;

[0072] Based on the numerical comparison result, a corresponding inventory adjustment process is performed on the target card or coupon.

[0073] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0074] The present application first obtains inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data; then the inventory-related data is preprocessed to obtain the corresponding target inventory-related data; then a pre-trained inventory demand forecasting model is called; based on the inventory demand forecasting model, the target inventory-related data is forecasted and processed to generate a corresponding inventory demand forecasting result; subsequently, the current total inventory corresponding to the target card or voucher is obtained based on a preset streaming processing architecture; a numerical comparison result between the inventory demand forecasting result and the current total inventory is further generated; finally, the target card or voucher is subjected to corresponding inventory adjustment processing based on the numerical comparison result. The present application obtains inventory-related data within a preset time period corresponding to a target card or coupon, and pre-processes the inventory-related data to obtain target inventory-related data, and then predicts and processes the target inventory-related data based on a pre-trained inventory demand prediction model to automatically and accurately generate a corresponding inventory demand prediction result, and then obtains the current total inventory corresponding to the target card or coupon based on a preset streaming processing architecture, and intelligently and automatically performs corresponding inventory adjustment processing on the target card or coupon based on a numerical comparison result between the generated inventory demand prediction result and the current total inventory, thereby accurately predicting inventory demand and automatically performing inventory adjustment operations based on the inventory demand prediction model and the inventory processing method of the streaming processing architecture, thereby achieving optimal configuration and dynamic balance of card or coupon inventory, effectively reducing manual operations, improving the response speed and processing efficiency of inventory management, and being able to avoid the situation in which the system has insufficient or excessive inventory of target cards or coupons resulting in waste of resources, thereby improving the efficiency of business operations and customer satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0076] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0077] Figure 2 A flowchart of an embodiment of an artificial intelligence-based inventory processing method according to the present application;

[0078] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based inventory processing device according to the present application;

[0079] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0080] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0081] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0082] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0083] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0084] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0085] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, the tablet computer 1012 or the mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV) player, a laptop computer, a desktop computer, etc.

[0086] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0087] It should be noted that the artificial intelligence-based inventory processing method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based inventory processing device is generally set in the server / terminal device.

[0088] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0089] Continue to refer Figure 2 , showing a flow chart of an embodiment of an artificial intelligence-based inventory processing method according to the present application. According to different requirements, the order of the steps in the flow chart can be changed, and some steps can be omitted. The artificial intelligence-based inventory processing method provided in the embodiment of the present application can be applied to any scenario that requires inventory management, and the artificial intelligence-based inventory processing method can be applied to products in these scenarios, for example, inventory management of electronic cards in the financial insurance field. The artificial intelligence-based inventory processing method includes the following steps:

[0090] Step S201, obtaining inventory-related data within a preset time period corresponding to a target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data.

[0091] In this embodiment, the electronic device (e.g. Figure 1The server / terminal device shown in the figure) can obtain inventory-related data through a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi DeBand) connection, and other wireless connection methods currently known or to be developed in the future. The execution subject of the present application may be specifically an inventory management system, or simply referred to as a system. The present application can be applied to the business scenario of inventory management of electronic card coupons in the financial insurance field. The above-mentioned target card coupons may be any electronic card coupons in the financial insurance field, such as insurance coupons, electronic insurance policies, points exchange coupons, value-added service coupons, etc. Among them, the above-mentioned preset time period is not specifically limited, for example, it may be the past week, the past month or the past six months corresponding to the current time. The above-mentioned inventory-related data at least includes inventory data, market data, time data and production data. Specifically, the above-mentioned inventory data may include inventory data within a preset time period, including the beginning inventory, the ending inventory and the change in inventory, and may also include sales data corresponding to the inventory. The above market data may include sales data, market trend analysis data, and promotion activity data. Among them, sales data refers to sales records within a preset time period, including sales quantity, sales amount, sales channels, etc. Market trend analysis data refers to data that provides information such as market development trends and changes in consumer behavior, such as market analysis reports and industry research reports. Promotion activity data refers to records of promotion activities, including data such as promotion time, promotion method, and promotion effect that will affect future inventory demand. The above time data includes time series data and holiday factor data. Among them, time series data refers to data used to analyze seasonal changes in inventory demand, such as data arranged in chronological order, such as months, quarters, years, etc. Holiday factor data refers to data on the impact of specific holidays (such as the Spring Festival, National Day, etc.) on inventory demand. The above production data includes supplier information and production plan data. Among them, supplier information refers to data such as the supplier's production capacity, delivery time, and delivery stability that affect the speed and safety of inventory replenishment. Production plan data refers to data such as the company's own production plan, production cycle, and production capacity that determine the speed and quantity of inventory generation.

[0092] Step S202: pre-process the inventory-related data to obtain corresponding target inventory-related data.

[0093] In this embodiment, the above-mentioned specific implementation process of preprocessing the inventory-related data to obtain the corresponding target inventory-related data will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0094] Step S203, calling a pre-trained inventory demand forecasting model.

[0095] In this embodiment, the specific construction process of the above inventory demand forecasting model will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated in detail here.

[0096] Step S204: performing forecasting processing on the target inventory-related data based on the inventory demand forecasting model to generate corresponding inventory demand forecasting results.

[0097] In this embodiment, by inputting the target inventory-related data into the above-mentioned inventory demand forecasting model, the inventory demand forecasting model will automatically perform calculation and reasoning processes based on the target inventory-related data, and perform a series of mathematical operations and transformations on the target inventory-related data to generate corresponding inventory demand forecasting results. Among them, the operations and transformations are based on the rules and patterns learned by the inventory demand forecasting model during the training phase. In addition, after the inventory demand forecasting model is calculated, the generated inventory demand forecasting results are usually expressed in numerical form, specifically including inventory demand forecast values ​​for a period of time in the future (such as daily, weekly or monthly). The inventory demand forecasting results can be directly used for inventory management and decision support, thereby helping enterprises better respond to market changes.

[0098] Step S205: acquiring the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture.

[0099] In this embodiment, the above stream processing architecture is suitable for scenarios that require real-time processing of large amounts of data streams, which can be implemented through frameworks such as Apache Kafka and Spark Streaming. The stream processing architecture framework can efficiently process real-time data streams and support high throughput and low latency. By using the stream processing architecture, the current total inventory corresponding to the target card or voucher can be quickly obtained in real time, and inventory problems can be captured in a timely manner and alarms can be issued, which helps companies quickly respond to and resolve inventory shortages or excesses to avoid business interruptions or other losses.

[0100] Step S206, generating a numerical comparison result between the inventory demand forecast result and the current total inventory.

[0101] In this embodiment, the inventory demand forecast result and the current total inventory can be numerically compared to generate a corresponding numerical comparison result, wherein the numerical comparison result includes that the inventory demand forecast result is greater than the current total inventory, or the numerical comparison result is that the inventory demand forecast result is less than the current total inventory.

[0102] Step S207: performing corresponding inventory adjustment processing on the target card or voucher based on the numerical comparison result.

[0103] In this embodiment, the specific implementation process of performing the corresponding inventory adjustment processing on the target card coupon based on the numerical comparison result will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated in detail here.

[0104] The present application first obtains inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data; then the inventory-related data is preprocessed to obtain the corresponding target inventory-related data; then a pre-trained inventory demand forecasting model is called; based on the inventory demand forecasting model, the target inventory-related data is forecasted and processed to generate a corresponding inventory demand forecasting result; subsequently, the current total inventory corresponding to the target card or voucher is obtained based on a preset streaming processing architecture; a numerical comparison result between the inventory demand forecasting result and the current total inventory is further generated; finally, the target card or voucher is subjected to corresponding inventory adjustment processing based on the numerical comparison result. The present application obtains inventory-related data within a preset time period corresponding to a target card or coupon, and pre-processes the inventory-related data to obtain target inventory-related data, and then predicts and processes the target inventory-related data based on a pre-trained inventory demand prediction model to automatically and accurately generate a corresponding inventory demand prediction result, and then obtains the current total inventory corresponding to the target card or coupon based on a preset streaming processing architecture, and intelligently and automatically performs corresponding inventory adjustment processing on the target card or coupon based on a numerical comparison result between the generated inventory demand prediction result and the current total inventory, thereby accurately predicting inventory demand and automatically performing inventory adjustment operations based on the inventory demand prediction model and the inventory processing method of the streaming processing architecture, thereby achieving optimal configuration and dynamic balance of card or coupon inventory, effectively reducing manual operations, improving the response speed and processing efficiency of inventory management, and being able to avoid the situation in which the system has insufficient or excessive inventory of target cards or coupons resulting in waste of resources, thereby improving the efficiency of business operations and customer satisfaction.

[0105] In some optional implementations, step S207 includes the following steps:

[0106] If the numerical comparison result is that the inventory demand forecast result is greater than the current total inventory, a preset replenishment strategy is obtained.

[0107] In this embodiment, the replenishment strategy may include formulating a corresponding inventory replenishment plan based on the inventory demand forecast result. The difference between the inventory demand forecast result and the current total inventory amount may be calculated, and the sum of the difference and the preset standby quantity may be calculated, and the sum may be used as the replenishment quantity corresponding to the inventory replenishment plan. The value of the standby quantity is not specifically limited and may be determined based on actual standby test experiments.

[0108] A stock replenishment process corresponding to the target card or ticket is performed based on the replenishment policy.

[0109] In this embodiment, according to the formulated replenishment strategy, a corresponding automated script or program can be written to perform inventory replenishment operations to avoid insufficient inventory in the inventory management system. Among them, a scheduled task or event trigger can also be set to ensure that the relevant operations are automatically executed at the appropriate time.

[0110] If the numerical comparison result is that the inventory demand forecast result is less than the current total inventory, a preset adjustment strategy is obtained.

[0111] In this embodiment, the adjustment strategy may include a strategy of price reduction promotion or adjustment of production plan.

[0112] An inventory adjustment process corresponding to the target card or ticket is performed based on the adjustment policy.

[0113] In this embodiment, according to the policy content of the formulated adjustment policy, a corresponding automated script or program can be written to execute the promotional operation corresponding to the inventory adjustment or the operation of adjusting the production plan to avoid excess inventory in the inventory management system.

[0114] In the present application, if it is detected that the numerical comparison result is that the inventory demand prediction result is greater than the current total inventory, a preset replenishment strategy is obtained; then, based on the replenishment strategy, the inventory replenishment processing corresponding to the target card or voucher is performed; and if it is detected that the numerical comparison result is that the inventory demand prediction result is less than the current total inventory, a preset adjustment strategy is obtained; and subsequently, the inventory adjustment processing corresponding to the target card or voucher is performed based on the adjustment strategy. The present application performs forecasting processing on the target inventory-related data based on the inventory demand forecasting model to generate an inventory demand forecasting result, and generates a numerical comparison result between the inventory demand forecasting result and the current total inventory. Then, by analyzing the numerical comparison result, if the numerical comparison result is that the inventory demand forecasting result is greater than the current total inventory, the application will intelligently perform inventory replenishment processing corresponding to the target card coupon based on the replenishment strategy, and if the numerical comparison result is that the inventory demand forecasting result is less than the current total inventory, the application will perform inventory adjustment processing corresponding to the target card coupon based on the adjustment strategy, thereby effectively achieving more accurate inventory planning and replenishment processing for the target card coupon, avoiding insufficient or excessive inventory of the target card coupon in the system, and thus improving the efficiency of business operations and customer satisfaction.

[0115] In some optional implementations of this embodiment, step S202 includes the following steps:

[0116] The inventory-related data is cleansed to obtain corresponding first data.

[0117] In this embodiment, the above-mentioned data cleaning process includes removing duplicate data, processing missing values, removing outliers, and data consistency check processing. Among them, removing duplicate data includes: checking and deleting duplicate records in the data set. Processing missing values ​​includes: selecting corresponding missing value processing methods according to the characteristics of the data and business logic, such as filling default values, using interpolation, deleting records containing missing values, etc. Removing outliers includes: identifying and processing outliers in the data, which may be caused by data entry errors, equipment failures, etc. Statistical methods (such as box plots, Z-scores) can be used to identify outliers and decide whether to keep, correct or delete them. Data consistency checks include: ensuring that data between different data sources are logically consistent, for example, sales data should match inventory reductions.

[0118] The first data is standardized to obtain corresponding second data.

[0119] In this embodiment, the above-mentioned standardization process includes: for certain features, such as price, sales volume, etc., it is necessary to convert them into a standard form, that is, to adopt a method of subtracting the mean and dividing by the standard deviation to eliminate the influence of different dimensions on model training.

[0120] The second data is normalized to obtain corresponding third data.

[0121] In this embodiment, the normalization process includes: scaling the eigenvalues ​​to a small specific interval, such as [0, 1], so that the model can converge faster.

[0122] Perform feature construction processing on the third data to obtain corresponding fourth data.

[0123] In this embodiment, the feature construction process includes constructing key factors that affect inventory demand as features, which may include time series features, seasonal features, and other business-related features. Among them, time series features may include: extracting useful features from time series data, such as the average sales volume in the last week / month, the slope of the trend line, etc. Seasonal features may include: creating features based on seasonal patterns, such as month, quarter, whether it is a holiday, etc. Other business-related features may include: promotion activity identification, new product launch identification, etc.

[0124] The fourth data is used as the target inventory related data.

[0125] The present application performs data cleaning on the inventory-related data to obtain the corresponding first data; then performs standardization on the first data to obtain the corresponding second data; then performs normalization on the second data to obtain the corresponding third data; subsequently performs feature construction on the third data to obtain the corresponding fourth data; and finally uses the fourth data as the target inventory-related data. The present application performs data cleaning, standardization, normalization, and feature construction on the inventory-related data to quickly and accurately complete the preprocessing of the inventory-related data, and effectively ensure the data accuracy of the obtained target inventory-related data.

[0126] In some optional implementations, before step S203, the electronic device may further perform the following steps:

[0127] Get historical inventory related data.

[0128] In this embodiment, historical inventory-related data may be extracted from a data warehouse or a data lake, and the historical inventory-related data may include historical inventory data, historical market data, historical time data, and historical production data, and may include, for example, daily / weekly / monthly inventory, sales, and returns.

[0129] Data preprocessing is performed on the historical inventory-related data to obtain corresponding first inventory-related data.

[0130] In this embodiment, the process of preprocessing the historical inventory-related data may refer to the process of preprocessing the inventory-related data, and will not be described in detail herein.

[0131] Perform feature engineering processing on the first inventory-related data to obtain corresponding sample data.

[0132] In this embodiment, the feature engineering process may include: according to business needs, selecting key factors that affect inventory demand as features, such as time (date, month, season), promotion activity identifier, market trend indicators (such as growth rate in industry reports), holidays, etc. Then, the time feature is encoded, such as using one-hot encoding to process categorical variables such as season and month, or converting the date into continuous variables such as year, month, day, week, etc.

[0133] Call the preset initial learning model.

[0134] In this embodiment, there is no specific limitation on the selection of the above-mentioned initial learning model. A suitable machine learning model can be selected according to data characteristics and prediction requirements. For example, ARIMA, LSTM (Long Short-Term Memory Network) and other models can be selected as the above-mentioned initial learning model.

[0135] Based on a preset training strategy, the initial learning model is trained using the sample data to obtain a trained designated learning model.

[0136] In this embodiment, the training strategy may include: dividing the data set into a training set and a test set. Then, the training set data is used to train the initial learning model, and the model parameters of the initial learning model are adjusted to optimize the prediction performance (such as mean square error, mean absolute error, etc.). Then, the test set data is used to evaluate the model performance of the initial learning model to ensure that the model of the initial learning model has good generalization ability, thereby obtaining a trained designated learning model.

[0137] The designated learning model is used as the inventory demand prediction model.

[0138] In this embodiment, in the process of model prediction, the impact of external factors such as seasonality, promotional activities, market trends, etc. on inventory demand is considered. These factors can be used as input features of the model, or the predicted value can be adjusted to reflect the impact of these factors.

[0139] The present application obtains historical inventory-related data; performs data preprocessing and feature engineering on the historical inventory-related data to obtain corresponding first inventory-related data; then performs feature engineering on the first inventory-related data to obtain corresponding sample data; then calls a preset initial learning model; subsequently, based on a preset training strategy, uses the sample data to train the initial learning model to obtain a trained designated learning model; and finally uses the designated learning model as the inventory demand forecasting model. The present application obtains historical inventory-related data; performs data preprocessing and feature engineering on the historical inventory-related data to obtain corresponding sample data; then, based on a preset training strategy, uses the sample data to train the preset initial learning model to obtain a trained inventory demand forecasting model, so as to complete the construction process of the inventory demand forecasting model, effectively improving the construction efficiency of the inventory demand forecasting model, and ensuring the model effect of the obtained inventory demand forecasting model.

[0140] In some optional implementations, after step S205, the electronic device may further perform the following steps:

[0141] Get the preset custom alarm conditions.

[0142] In this embodiment, a flexible alarm rule configuration is pre-designed to allow relevant users to customize the alarm conditions and trigger alarm rules corresponding to the inventory of cards and coupons according to specific needs. For example, different inventory thresholds, alarm urgency and notification methods can be set according to different types of cards and coupons.

[0143] Determine whether the current total inventory meets the custom alarm condition.

[0144] In this embodiment, the above-mentioned custom alarm condition may include that the inventory quantity is greater than a preset high inventory threshold, or the inventory quantity is less than a preset low inventory threshold. There is no specific limitation on the values ​​of the above-mentioned high inventory threshold and low inventory threshold, and they can be set according to actual inventory warning requirements.

[0145] If so, corresponding inventory warning information is generated based on the current total inventory.

[0146] In this embodiment, when it is detected that the current total inventory meets the custom alarm condition, the alarm rule will be automatically triggered, and the corresponding inventory alarm information will be generated based on the current total inventory. Specifically, the current total inventory can be automatically filled into the preset inventory alarm information template to generate the corresponding inventory alarm information. The template content of the above inventory alarm information template can be written according to the actual inventory warning requirements.

[0147] Identify target notification channels.

[0148] In this embodiment, the target notification channel may include not only traditional email and SMS notifications, but also newly added mobile application push notifications or instant message notifications, so as to convey the warning information to relevant personnel in a timely manner.

[0149] Based on the target notification channel, the inventory warning information is sent to relevant users.

[0150] In this embodiment, by using the target notification channel to send the inventory warning information to the relevant users, the timeliness and reliability of the inventory warning can be improved, which is conducive to helping the relevant users to take actions more quickly to solve the current inventory problems.

[0151] This application obtains the preset custom alarm condition; then determines whether the current total inventory meets the custom alarm condition; if so, generates corresponding inventory alarm information based on the current total inventory; then determines the target notification channel; and subsequently sends the inventory alarm information to relevant users based on the target notification channel. This application intelligently provides users with the function of customizing alarm conditions and triggering alarm rules according to specific inventory alarm requirements, so that it can flexibly adapt to the alarm processing of different types of cards and coupons and the needs of different business scenarios, effectively improving the system's adaptability and flexibility to inventory alarm processing.

[0152] In some optional implementations of this embodiment, step S203 includes the following steps:

[0153] Call the preset monitoring tool.

[0154] In this embodiment, the monitoring tool may be a professional monitoring tool, such as Zabbix, Prometheus, etc., or a monitoring function provided in the inventory management system may be used.

[0155] Based on the monitoring tool, system performance indicators corresponding to preset indicator types are collected.

[0156] In this embodiment, the preset indicator type is an indicator type corresponding to each key indicator of the inventory management system. The system performance indicators include but are not limited to inventory, order processing speed, system response time, database load, etc.

[0157] Determine whether there is an abnormal performance indicator in the system performance indicators that is greater than the corresponding preset indicator threshold.

[0158] In this embodiment, according to actual monitoring needs, reasonable indicator thresholds are set in advance for key indicators corresponding to the inventory management system. Once the indicator exceeds the threshold, the system automatically triggers an early warning notification so that problems can be discovered and measures can be taken in time.

[0159] If so, a corresponding warning notification is generated based on the abnormal performance indicator.

[0160] In this embodiment, if it is detected that there is an abnormal performance indicator greater than the corresponding preset indicator threshold in the system performance indicator, the abnormal performance indicator is screened out from the system performance indicator, and the abnormal performance indicator is filled into the preset abnormal warning notification template to generate a corresponding warning notification. The above abnormal warning notification template is a warning notification template constructed according to the actual warning notification requirements when abnormal performance indicators exist in the inventory management system, and the content of the abnormal warning notification template can be written according to actual needs.

[0161] The warning notification is sent to corresponding operation and maintenance personnel.

[0162] In this embodiment, the above-mentioned operation and maintenance personnel may specifically be the staff responsible for operation and maintenance in the inventory management system. The warning notification may be sent to the corresponding operation and maintenance personnel through traditional email and SMS notifications, or through newly added mobile application push notifications or instant message notifications, so as to timely convey the warning notification to the operation and maintenance personnel.

[0163] This application calls a preset monitoring tool; then based on the monitoring tool, it collects system performance indicators corresponding to the preset indicator type; then determines whether there are abnormal performance indicators in the system performance indicators that are greater than the corresponding preset indicator threshold; if so, generates a corresponding early warning notification based on the abnormal performance indicator; and subsequently sends the early warning notification to the corresponding operation and maintenance personnel. During the operation of the system, this application will also intelligently monitor the system performance based on the use of monitoring tools to collect system performance indicators corresponding to the preset indicator type, and when it is detected that there are abnormal performance indicators in the system performance indicators that are greater than the corresponding preset indicator threshold, it will automatically and timely generate a corresponding early warning notification based on the abnormal performance indicator and send it to the corresponding operation and maintenance personnel, so that the operation and maintenance personnel can timely deal with the current performance problems of the system by checking the early warning notification, which is conducive to ensuring the stable operation of the system and avoiding business interruptions in the system.

[0164] In some optional implementations of this embodiment, before step S201, the electronic device may further perform the following steps:

[0165] Get current system load data.

[0166] In this embodiment, the current system load data of the inventory management system can be collected by calling a preset load monitoring tool, wherein the load monitoring tool is a pre-built tool with a system load data collection function.

[0167] Determine whether the system load data meets the preset load warning condition.

[0168] In this embodiment, the load warning condition includes high load or low load. If the current system load data is greater than a preset high load threshold, it is determined that the current inventory management system is in a high load state. If the current system load data is less than a preset low load threshold, it is determined that the current inventory management system is in a low load state. There is no specific limitation on the values ​​of the high load threshold and the low load threshold, and they can be set according to the actual system load analysis requirements.

[0169] If yes, call the pre-built cloud resource pool.

[0170] In this embodiment, a cloud resource pool (such as AWS, Azure, Alibaba Cloud, etc.) is pre-established in the inventory management system to dynamically adjust computing resources, storage resources, and network resources according to business needs.

[0171] Based on the load warning condition, the cloud resource pool is used to perform corresponding resource adjustment processing.

[0172] In this embodiment, when it is detected that the system load data meets the preset load warning conditions (high load or low load), the resource scale is automatically adjusted according to the system load by utilizing the automatic scaling service provided by the cloud resource pool (such as AWS Auto Sca ling, Azure Autosca le, etc.) to ensure that the system can quickly expand resources when the load is high, and automatically release resources when the load is low to save costs.

[0173] This application obtains the current system load data; then determines whether the system load data meets the preset load warning conditions; if so, calls the pre-built cloud resource pool; and subsequently uses the cloud resource pool to perform corresponding resource adjustment processing based on the load warning conditions. During the operation of the inventory management system, this application will also automatically obtain the current system load data, and when it detects that the system load data meets the preset load warning conditions, it will automatically perform corresponding resource adjustment processing based on the use of the pre-built cloud resource pool, thereby providing high availability and scalability for the system, effectively ensuring the stability and performance of the system, and supporting large-scale business needs.

[0174] In some optional implementations, the security measures of the inventory management system can also be strengthened, including data encryption, identity authentication, access control, etc., to protect the security and integrity of inventory information, prevent the risk of data leakage and tampering, and enhance the credibility of the system and user trust. In addition, open source technology and cloud-native architecture can be further adopted to reduce the cost of the inventory management system, provide more competitive prices and flexible payment models, help enterprises save costs and improve economic benefits.

[0175] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean 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 embodiment of the present invention.

[0176] It should be emphasized that in order to further ensure the privacy and security of the above inventory demand forecast results, the above inventory demand forecast results can also be stored in a blockchain node.

[0177] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0178] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0179] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0180] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0181] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0182] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of an inventory processing device based on artificial intelligence, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0183] like Figure 3 As shown, the artificial intelligence-based inventory processing device 300 described in this embodiment includes: a first acquisition module 301, a preprocessing module 302, a first calling module 303, a prediction module 304, a second acquisition module 305, a first generation module 306 and a first adjustment module 307. Among them:

[0184] The first acquisition module 301 is used to acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data;

[0185] A preprocessing module 302 is used to preprocess the inventory-related data to obtain corresponding target inventory-related data;

[0186] The first calling module 303 is used to call a pre-trained inventory demand forecasting model;

[0187] A prediction module 304 is used to perform prediction processing on the target inventory related data based on the inventory demand prediction model to generate a corresponding inventory demand prediction result;

[0188] The second acquisition module 305 is used to acquire the current total inventory corresponding to the target card based on a preset stream processing architecture;

[0189] A first generating module 306, configured to generate a numerical comparison result between the inventory demand forecast result and the current total inventory;

[0190] The first adjustment module 307 is used to perform corresponding inventory adjustment processing on the target card based on the numerical comparison result.

[0191] In some optional implementations of this embodiment, the first adjustment module 307 includes:

[0192] A first acquisition submodule is used to acquire a preset replenishment strategy if the numerical comparison result is that the inventory demand forecast result is greater than the current total inventory;

[0193] A first processing submodule, configured to perform inventory replenishment processing corresponding to the target card coupon based on the replenishment strategy;

[0194] A second acquisition submodule is used to acquire a preset adjustment strategy if the numerical comparison result is that the inventory demand forecast result is less than the current total inventory;

[0195] The second processing submodule is used to perform inventory adjustment processing corresponding to the target card or voucher based on the adjustment strategy.

[0196] In some optional implementations of this embodiment, the preprocessing module 302 includes:

[0197] A third processing submodule is used to perform data cleaning processing on the inventory-related data to obtain corresponding first data;

[0198] a fourth processing submodule, configured to perform standardization processing on the first data to obtain corresponding second data;

[0199] a fifth processing submodule, configured to perform normalization processing on the second data to obtain corresponding third data;

[0200] a sixth processing submodule, configured to perform feature construction processing on the third data to obtain corresponding fourth data;

[0201] A determination submodule is used to use the fourth data as the target inventory related data.

[0202] In some optional implementations of this embodiment, the inventory processing device based on artificial intelligence further includes:

[0203] The third acquisition module is used to obtain historical inventory related data;

[0204] A first processing module, configured to perform data preprocessing on the historical inventory-related data to obtain corresponding first inventory-related data;

[0205] A second processing module is used to perform feature engineering processing on the first inventory-related data to obtain corresponding sample data;

[0206] The second calling module is used to call a preset initial learning model;

[0207] A training module, used to train the initial learning model using the sample data based on a preset training strategy to obtain a trained designated learning model;

[0208] The first determination module is used to use the specified learning model as the inventory demand prediction model.

[0209] In some optional implementations of this embodiment, the inventory processing device based on artificial intelligence further includes:

[0210] The fourth acquisition module is used to obtain the preset custom alarm conditions;

[0211] A first judgment module is used to judge whether the current total inventory meets the user-defined alarm condition;

[0212] A second generating module, configured to generate corresponding inventory warning information based on the current total inventory;

[0213] The second determination module is used to determine the target notification channel;

[0214] The first sending module is used to send the inventory warning information to relevant users based on the target notification channel.

[0215] In some optional implementations of this embodiment, the inventory processing device based on artificial intelligence further includes:

[0216] The third calling module is used to call the preset monitoring tool;

[0217] A collection module, used for collecting system performance indicators corresponding to preset indicator types based on the monitoring tool;

[0218] A second judgment module is used to judge whether there is an abnormal performance indicator greater than a corresponding preset indicator threshold value in the system performance indicators;

[0219] A third generating module, configured to generate a corresponding warning notification based on the abnormal performance indicator if yes;

[0220] The second sending module is used to send the warning notification to corresponding operation and maintenance personnel.

[0221] In some optional implementations of this embodiment, the inventory processing device based on artificial intelligence further includes:

[0222] The fifth acquisition module is used to obtain current system load data;

[0223] A third judgment module is used to judge whether the system load data meets the preset load warning condition;

[0224] A fourth calling module, for calling a pre-built cloud resource pool if yes;

[0225] The second adjustment module is used to use the cloud resource pool to perform corresponding resource adjustment processing based on the load warning condition.

[0226] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0227] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.

[0228] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0229] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the inventory processing method based on artificial intelligence, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0230] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the artificial intelligence-based inventory processing method.

[0231] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0232] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based inventory processing method.

[0233] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0234] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An inventory processing method based on artificial intelligence, characterized in that: The steps include: Acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data; Preprocessing the inventory-related data to obtain corresponding target inventory-related data; Call the pre-trained inventory demand forecasting model; Based on the inventory demand forecasting model, the target inventory related data is forecasted and processed to generate corresponding inventory demand forecasting results; Acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture; Generate a numerical comparison result between the inventory demand forecast result and the current total inventory; Based on the numerical comparison result, a corresponding inventory adjustment process is performed on the target card or coupon.

2. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: The step of performing a corresponding inventory adjustment process on the target card based on the numerical comparison result specifically includes: If the numerical comparison result is that the inventory demand forecast result is greater than the current total inventory, then obtaining a preset replenishment strategy; Performing inventory replenishment processing corresponding to the target card or voucher based on the replenishment strategy; If the numerical comparison result is that the inventory demand forecast result is less than the current total inventory, then obtaining a preset adjustment strategy; An inventory adjustment process corresponding to the target card or ticket is performed based on the adjustment policy.

3. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: The step of preprocessing the inventory-related data to obtain corresponding target inventory-related data specifically includes: Performing data cleaning processing on the inventory-related data to obtain corresponding first data; Performing standardization processing on the first data to obtain corresponding second data; Normalizing the second data to obtain corresponding third data; Performing feature construction processing on the third data to obtain corresponding fourth data; The fourth data is used as the target inventory related data.

4. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: Before the step of calling the pre-trained inventory demand forecasting model, the method further includes: Get historical inventory related data; Performing data preprocessing on the historical inventory-related data to obtain corresponding first inventory-related data; Performing feature engineering processing on the first inventory-related data to obtain corresponding sample data; Call the preset initial learning model; Based on a preset training strategy, the initial learning model is trained using the sample data to obtain a trained designated learning model; The designated learning model is used as the inventory demand prediction model.

5. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: After the step of obtaining the current total inventory corresponding to the target card or coupon based on the preset stream processing architecture, the method further includes: Get the preset custom alarm conditions; Determine whether the current total inventory meets the user-defined alarm condition; If yes, generate corresponding inventory warning information based on the current total inventory; Identify target notification channels; Based on the target notification channel, the inventory warning information is sent to relevant users.

6. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: The artificial intelligence-based inventory processing method further includes: Call the preset monitoring tool; Collecting system performance indicators corresponding to preset indicator types based on the monitoring tool; Determine whether there is an abnormal performance indicator greater than a corresponding preset indicator threshold value among the system performance indicators; If so, generating a corresponding warning notification based on the abnormal performance indicator; The warning notification is sent to corresponding operation and maintenance personnel.

7. The inventory processing method based on artificial intelligence according to claim 1, characterized in that: The artificial intelligence-based inventory processing method further includes: Get the current system load data; Determining whether the system load data meets the preset load warning conditions; If yes, call the pre-built cloud resource pool; Based on the load warning condition, the cloud resource pool is used to perform corresponding resource adjustment processing.

8. An inventory processing device based on artificial intelligence, characterized in that: include: A first acquisition module is used to acquire inventory-related data within a preset time period corresponding to the target card or voucher; wherein the inventory-related data at least includes inventory data, market data, time data and production data; A preprocessing module, used for preprocessing the inventory-related data to obtain corresponding target inventory-related data; The first calling module is used to call the pre-trained inventory demand forecasting model; A prediction module, used to perform prediction processing on the target inventory related data based on the inventory demand prediction model to generate corresponding inventory demand prediction results; A second acquisition module, configured to acquire the current total inventory corresponding to the target card or voucher based on a preset stream processing architecture; A first generating module, used to generate a numerical comparison result between the inventory demand forecast result and the current total inventory; The first adjustment module is used to perform corresponding inventory adjustment processing on the target card based on the numerical comparison result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the artificial intelligence-based inventory processing method as described in any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the artificial intelligence-based inventory processing method according to any one of claims 1 to 7 are implemented.

Images