Warehouse goods checking method, electronic equipment and storage medium

Abstract

The invention provides a warehouse goods checking method, electronic equipment and a storage medium. The method comprises the steps of selecting a to-be-used identification mode based on cargo attributes of to-be-checked cargos in a target warehouse; according to the to-be-used identification mode, obtaining target checking data of the to-be-checked goods; performing data anomaly detection on the target inventory data by using a target anomaly recognition model to obtain a current detection result, the current detection result being used for indicating whether there is cargo loss and / or repeated inventory in the to-be-inventory cargos; and performing visual display on the current detection result, and / or generating an inventory exception report according to the current detection result. According to the invention, the technical problems of low checking efficiency and poor data accuracy of a warehouse goods checking method provided in the prior art are solved.

Description

Technical Field

[0001] The present disclosure relates to the field of warehouse management and inventory counting, and in particular to a warehouse goods inventory counting method, an electronic device and a storage medium. Background Art

[0002] With the rapid development of e-commerce, the demand for warehouse inventory is increasing. The warehouse inventory system in the related art usually adopts manual inventory mode or barcode scanning mode to realize the inventory and information recording of goods. Among them, the manual inventory mode is to manually check the quantity, location and status of goods by warehouse staff, and record them in paper or electronic forms to realize warehouse inventory; the barcode scanning mode is to use handheld scanning devices to read the barcode information on the goods, and replace manual records with electronic records to improve the data entry speed. However, both warehouse inventory modes in the related art have the problems of low inventory efficiency and poor data accuracy, which makes it difficult to meet the needs of modern high-efficiency and high-precision warehousing management.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present disclosure provide a warehouse cargo inventory method, an electronic device, and a storage medium to at least solve the technical problems of low inventory efficiency and poor data accuracy in the warehouse cargo inventory method provided in the related art.

[0005] According to one aspect of an embodiment of the present disclosure, a method for counting goods in a warehouse is provided, comprising: selecting an identification method to be used based on the goods attributes of the goods to be counted in a target warehouse; obtaining target inventory data of the goods to be counted according to the identification method to be used; performing data anomaly detection on the target inventory data using a target anomaly recognition model to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted; visually displaying the current detection result, and / or generating an inventory anomaly report based on the current detection result.

[0006] Optionally, selecting the identification method to be used based on the attributes of the goods to be counted in the target warehouse includes: in response to the volume of the goods to be counted in the target warehouse satisfying a first preset condition, selecting a QR code identification method; in response to the quantity and value of the goods to be counted in the target warehouse satisfying a second preset condition, selecting a radio frequency identification identification method; in response to the cargo identification frequency and cargo identification distance of the goods to be counted in the target warehouse satisfying a third preset condition, selecting a near field communication identification method.

[0007] Optionally, obtaining target inventory data of goods to be counted according to the identification method to be used includes: collecting initial inventory data of the goods to be counted according to the identification method to be used; integrating data sources of the initial inventory data to obtain integration results; and cleaning the integration results to obtain target inventory data.

[0008] Optionally, the warehouse cargo inventory method in the embodiment of the present disclosure also includes: using historical inventory data to train an initial anomaly recognition model to generate a target anomaly recognition model, wherein the initial anomaly recognition model is used to identify abnormal inventory data generated during the cargo inventory process from multiple feature dimensions, and the multiple feature dimensions include: cargo inventory time dimension, cargo inventory frequency dimension, cargo inventory type dimension, and cargo inventory historical flow data dimension.

[0009] Optionally, the initial anomaly recognition model is trained using historical inventory data to generate a target anomaly recognition model, including: performing data anomaly detection on the historical inventory data using the initial anomaly recognition model to obtain historical detection results; obtaining manual review results corresponding to the historical detection results; and optimizing model parameters of the initial anomaly recognition model based on the manual review results to generate a target anomaly recognition model.

[0010] Optionally, a target anomaly recognition model is used to perform data anomaly detection on the target inventory data to obtain the current detection result, including: comparing the target inventory data with historical inventory data through the target anomaly recognition model to identify goods missing from the inventory, and determining that the current detection result indicates that there are missing goods in the goods to be counted; and / or, identifying through the target anomaly recognition model from the target inventory data that the same batch of goods has been counted multiple times in the same time period, and determining that the current detection result indicates that there are repeated inventories in the goods to be counted.

[0011] Optionally, the warehouse cargo inventory method in the embodiment of the present disclosure further includes at least one of the following: encrypting and storing the target inventory data; maintaining and upgrading the system operating environment that supports multiple different types of identification methods.

[0012] Optionally, the warehouse cargo inventory method in the embodiment of the present disclosure also includes: updating the inventory status in real time based on the target inventory data, wherein the inventory status is used to dynamically monitor the flow of cargo in the target warehouse; and issuing an alarm in response to identifying inventory anomalies based on the inventory status.

[0013] According to one embodiment of the present disclosure, a warehouse cargo inventory device is also provided, including: a selection module, used to select an identification method to be used based on the cargo attributes of the cargo to be inventoried in the target warehouse; an acquisition module, used to obtain target inventory data of the cargo to be inventoried according to the identification method to be used; a processing module, used to perform data anomaly detection on the target inventory data using a target anomaly recognition model to obtain a current detection result, wherein the current detection result is used to indicate whether there is any cargo missing and / or repeated inventory in the cargo to be inventoried; a display module, used to visually display the current detection result, and / or generate an inventory anomaly report based on the current detection result.

[0014] Optionally, the selection module is also used to: select the identification method to be used based on the attributes of the goods to be counted in the target warehouse, including: in response to the volume of the goods to be counted in the target warehouse satisfying a first preset condition, selecting a QR code identification method; in response to the quantity and value of the goods to be counted in the target warehouse satisfying a second preset condition, selecting a radio frequency identification identification method; in response to the cargo identification frequency and cargo identification distance of the goods to be counted in the target warehouse satisfying a third preset condition, selecting a near field communication identification method.

[0015] Optionally, the acquisition module is also used to: obtain target inventory data of the goods to be counted according to the identification method to be used, including: collecting initial inventory data of the goods to be counted according to the identification method to be used; integrating the data sources of the initial inventory data to obtain an integration result; and cleaning the integration result to obtain target inventory data.

[0016] Optionally, the processing module is also used to: use historical inventory data to train an initial anomaly recognition model to generate a target anomaly recognition model, wherein the initial anomaly recognition model is used to identify abnormal inventory data generated during the cargo inventory process from multiple feature dimensions, and the multiple feature dimensions include: cargo inventory time dimension, cargo inventory frequency dimension, cargo inventory type dimension, and cargo inventory historical flow data dimension.

[0017] Optionally, the processing module is also used to: use the initial anomaly recognition model to perform data anomaly detection on historical inventory data to obtain historical detection results; obtain manual review results corresponding to the historical detection results; optimize the model parameters of the initial anomaly recognition model based on the manual review results to generate a target anomaly recognition model.

[0018] Optionally, the processing module is also used to: compare the target inventory data with the historical inventory data through a target anomaly recognition model to identify missing goods in the inventory, and determine that the current detection result indicates that there are missing goods in the goods to be counted; and / or, identify from the target inventory data through a target anomaly recognition model that the same batch of goods has been counted multiple times in the same time period, and determine that the current detection result indicates that there are repeated inventories in the goods to be counted.

[0019] Optionally, the processing module is also used to: update the inventory status in real time based on the target inventory data, wherein the inventory status is used to dynamically monitor the flow of goods in the target warehouse; and issue an alarm in response to identifying inventory anomalies based on the inventory status.

[0020] According to one embodiment of the present disclosure, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the warehouse cargo inventory method in the embodiment of the present disclosure is executed when the program is running.

[0021] According to one embodiment of the present disclosure, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute the warehouse cargo inventory method in the embodiment of the present disclosure.

[0022] According to one embodiment of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the warehouse goods inventory counting method in the embodiment of the present disclosure is implemented.

[0023] In the disclosed embodiment, the identification method to be used is selected according to the goods attributes of the goods to be counted in the target warehouse, and the target inventory data of the goods to be counted is obtained according to the identification method to be used, and then the target anomaly recognition model is used to perform data anomaly detection on the target inventory data to obtain the current detection result, and finally the current detection result is visualized and / or an inventory anomaly report is generated based on the current detection result, thereby achieving the purpose of refined and intelligent management of warehouse inventory, thereby achieving the technical effect of improving the inventory efficiency and data accuracy of warehouse goods, and thus solving the technical problems of low inventory efficiency and poor data accuracy existing in the warehouse goods inventory method provided in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are used to provide a further understanding of the present disclosure and constitute a part of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure. In the drawings:

[0025] Figure 1 is a flow chart of a warehouse goods inventory method according to one embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of an intelligent inventory system according to one embodiment of the present disclosure;

[0027] Figure 3 It is a structural block diagram of a warehouse cargo inventory counting device according to one embodiment of the present disclosure. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the disclosed solution, the technical solution in the disclosed embodiment will be clearly and completely described below in conjunction with the drawings in the disclosed embodiment. Obviously, the described embodiment is only a part of the disclosed embodiment, not all of the embodiments. Based on the embodiments in the disclosed embodiment, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the disclosed embodiment.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0030] The warehouse cargo inventory system in the related art usually adopts manual inventory mode or barcode scanning mode to realize the inventory and information recording of goods. Among them, the manual inventory mode is to manually check the quantity, location and status of goods by warehouse staff, and record them in paper or electronic forms to realize warehouse cargo inventory; the barcode scanning mode is to use handheld scanning devices to read the barcode information on the goods, and replace manual records with electronic records to improve the data entry speed. However, both warehouse cargo inventory modes in the related art have the problems of low inventory efficiency and poor data accuracy, which makes it difficult to meet the modern high-efficiency and high-precision warehouse management needs.

[0031] Specifically, in the manual inventory mode, a large amount of manpower is relied on to check one by one. Warehouse staff need to check each item of goods within a specified time to confirm whether its quantity, location and status match the system records. This is not only time-consuming and labor-intensive, but also in continuous operation or complex environments, staff are prone to errors due to negligence, fatigue or irregular operation. For example, during peak seasons, staff may neglect to check due to high-intensity work, resulting in misreporting of the number of goods; in scenarios with a wide variety of goods, due to the heavy memory burden, information on the location of goods may also be misplaced. In addition, in the process of manual data entry, typing errors or omissions are common problems, which directly affect the accuracy and reliability of inventory data.

[0032] Although the barcode scanning mode can increase the speed of data entry, its efficiency and accuracy are still limited by the characteristics of barcode technology. Barcodes are fragile. Once worn, contaminated or torn, the scanning device may not be able to read them correctly, which will hinder the inventory process. In addition, the sensitivity of barcodes to light and angles is also a major limitation. For example, when the light is insufficient or the barcode label is not facing the scanner, the scanning success rate will drop significantly. The characteristic of only reading one barcode at a time further limits the application efficiency in high-density cargo stacking environments, because each scan needs to find and align a single barcode, and batch or contactless identification cannot be achieved, which becomes a bottleneck when a large number of goods need to be counted quickly. In summary, whether it is human errors in the manual inventory mode or technical limitations in the barcode scanning mode, it is difficult to meet the needs of modern warehouse management for high-efficiency and high-precision inventory.

[0033] In the manual inventory mode, a large number of people are relied on to check one by one, which is not only time-consuming and labor-intensive, but also prone to errors due to human factors such as negligence and fatigue. Although the barcode scanning mode improves the speed of data entry, the fragility of the barcode, its sensitivity to light and angle, and the limitation of only reading one barcode at a time still limit the inventory efficiency and data accuracy.

[0034] According to an embodiment of the present disclosure, a method embodiment of a warehouse cargo inventory method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] The method embodiment can be executed in an electronic device or a similar computing device including a memory and a processor. Taking running on a computer terminal as an example, the computer terminal may include one or more processors (processors may include but are not limited to central processing units (CPU), graphics processing units (GPU), digital signal processing (DSP) chips, microprocessors (MCU), programmable logic devices (Field Programmable Gate Array, FPGA), neural network processors (Neural-network Processor Unit, NPU), tensor processors (TensorProcessing Unit, TPU), artificial intelligence (Artificial Intelligence, AI) type processors and other processing devices) and a memory for storing data. Optionally, the above-mentioned computer terminal may also include a transmission device, an input and output device, and a display device for communication functions. It can be understood by those of ordinary skill in the art that the above-mentioned structural description is only for illustration, and it does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than the above-mentioned structural description, or have a configuration different from the above-mentioned structural description.

[0036] The memory can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the warehouse goods inventory method in the embodiment of the present disclosure. The processor executes various functional applications and data processing by running the computer program stored in the memory, that is, the above-mentioned warehouse goods inventory method is realized. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0037] The transmission device is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0038] The display device may be, for example, a touch screen type liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display may enable a user to interact with a user interface of a mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user may interact with the GUI by finger contacts and / or gestures on a touch-sensitive surface, wherein the human-computer interaction functions here may optionally include the following interactions: creating web pages, drawing, word processing, making electronic documents, games, video conferencing, instant messaging, sending and receiving emails, call interfaces, playing digital videos, playing digital music and / or web browsing, etc. The executable instructions for executing the above human-computer interaction functions are configured / stored in a computer program product or readable storage medium executable by one or more processors.

[0039] Figure 1 is a flow chart of a warehouse goods inventory method according to one embodiment of the present disclosure, such as Figure 1 As shown, the method comprises the following steps:

[0040] Step S11, selecting an identification method to be used based on the properties of the goods to be counted in the target warehouse;

[0041] Step S12, obtaining target inventory data of the goods to be counted according to the identification method to be used;

[0042] Step S13, using the target anomaly recognition model to perform data anomaly detection on the target inventory data to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted;

[0043] Step S14: Visually display the current test results, and / or generate an inventory exception report based on the current test results.

[0044] The above-mentioned cargo attributes refer to characteristic parameters of the cargo to be counted, including but not limited to cargo volume, cargo quantity, cargo value, cargo identification frequency, cargo identification distance, etc.

[0045] The above-mentioned identification methods refer to a variety of technical means used to mark and identify goods in the intelligent inventory system, including but not limited to QR code identification, radio frequency identification and near-field communication identification. The QR code identification method attaches an image containing specific information to the goods and uses a QR code scanner for rapid identification. It is suitable for the identification of small and single goods. The radio frequency identification method embeds wireless radio frequency tags in the goods to achieve long-distance batch identification without direct contact. It is suitable for large-volume, high-value goods or goods that require dynamic tracking. The near-field communication identification method is a short-range wireless identification technology that is suitable for scenarios that require high-frequency and close-range identification.

[0046] The above-mentioned target inventory data refers to the data set automatically collected from the goods to be counted through the integrated identification technology in the intelligent inventory system, including but not limited to the unique identification information of the goods, location information, inventory quantity, status information, inventory time and frequency, and historical flow data.

[0047] The above-mentioned target anomaly recognition model refers to a machine learning model used to detect and identify anomalies in inventory data in the intelligent inventory system, including but not limited to anomaly detection and feature engineering. Among them, anomaly detection uses statistical analysis and machine learning algorithms, such as isolation forests and support vector machines, to model normal inventory data and identify data points that deviate from normal patterns; feature engineering is used to extract key features that affect inventory accuracy, such as inventory time, frequency, type of goods and their historical flow data, to enhance the recognition ability of the model.

[0048] Exemplarily, first, according to the cargo attributes of the cargo to be counted in the target warehouse, such as cargo volume, cargo quantity, cargo value, cargo identification frequency and cargo identification distance, the identification method to be used is selected; then, the target inventory data including the unique identification of the cargo, location information, inventory quantity, cargo status and inventory time are collected through the identification method to be used, and data points that do not conform to the normal pattern are identified based on statistical analysis and machine learning algorithms to determine whether there is any missing cargo and / or repeated inventory in the cargo to be counted; finally, the cargo inventory status and abnormal situations are displayed in real time through a visual interface, and a detailed inventory abnormality report is generated, listing the specific abnormality types, quantities and handling suggestions, so as to provide a basis for subsequent inventory adjustments and management optimization.

[0049] Based on the above steps S11 to S14, the identification method to be used is selected according to the goods attributes of the goods to be counted in the target warehouse, and the target inventory data of the goods to be counted is obtained according to the identification method to be used, and then the target anomaly recognition model is used to perform data anomaly detection on the target inventory data to obtain the current detection result, and finally the current detection result is visualized and / or an inventory anomaly report is generated based on the current detection result, thereby achieving the purpose of refined and intelligent management of warehouse inventory, thereby achieving the technical effect of improving the efficiency of warehouse goods inventory and data accuracy, and thus solving the technical problems of low inventory efficiency and poor data accuracy in the warehouse goods inventory method provided in the related art.

[0050] The following is a further introduction to the warehouse cargo inventory method in the embodiment of the present disclosure.

[0051] Optionally, in step S11, selecting the identification method to be used based on the properties of the goods to be counted in the target warehouse includes:

[0052] Step S111, in response to the volume of the goods to be counted in the target warehouse meeting the first preset condition, selecting a QR code identification method;

[0053] Step S112, in response to the quantity and value of the goods to be counted in the target warehouse satisfying the second preset condition, selecting a radio frequency identification identification method;

[0054] Step S113, in response to the goods identification frequency and the goods identification distance of the goods to be counted in the target warehouse satisfying the third preset condition, selecting the near field communication identification mode.

[0055] The above-mentioned first preset condition means that in the target warehouse, the volume of the goods to be counted meets a specific size range, ensuring that the QR code can be properly attached to the surface of the goods, and in the target warehouse environment, when quickly identified by a handheld device or a fixed scanner, the size and position of the QR code will not constitute an identification obstacle.

[0056] For example, assuming that the first preset condition is that the cargo size threshold is 30 cm, that is, the length, width and height of the cargo to be counted do not exceed 30 cm, it can be judged that the cargo to be counted meets the first preset condition at this time, and the QR code can be reasonably attached to the surface of the cargo, and the QR code will not be difficult to scan because the cargo is too large, or the cargo is too small to attach a QR code large enough for identification.

[0057] The second preset condition mentioned above refers to the fact that the quantity of goods to be counted and the value of each item in the target warehouse meet or exceed the specific standards set by the system. In scenarios where goods are large in batches and high in value, the non-contact reading and long-distance recognition capabilities of the RFID tagging method enable rapid positioning and data collection of goods even in densely stacked and fast-moving environments, thereby effectively avoiding the time-consuming manual scanning and goods loss caused by contact-based inventorying that are common in traditional inventory methods.

[0058] Exemplarily, assuming that the second preset condition is that the threshold value of the number of goods is 1,000 pieces, or the upper limit of the value of a single good is 500 yuan, that is, when the number of goods to be counted reaches or exceeds 1,000 pieces, or the value of a single good is above 500 yuan, it can be judged that the goods to be counted at this time meet the second preset condition. The use of radio frequency identification technology can effectively utilize its non-contact and multi-tag simultaneous reading characteristics, significantly reducing the time and manpower required for large-scale goods inventory. At the same time, for high-value goods, the use of radio frequency tags can improve the accuracy of goods tracking, reduce the risk of goods loss, and enhance warehousing safety.

[0059] The third preset condition mentioned above refers to the frequency of goods identification reaching or exceeding the high frequency threshold preset by the system, or the identification distance is short. In the case of high frequency of goods identification and short identification distance, the contactless data exchange capability and short-range communication characteristics of the near-field communication identification method can meet the needs of high-frequency and short-range identification. When goods need to be intensively identified in a short period of time, such as in a retail environment, a busy logistics center, or a fast-flowing link on a production line, near-field communication tags can be read quickly and accurately without direct contact or long-distance scanning.

[0060] For example, when the volume of the goods to be counted is small and meets the first preset condition, such as books, cosmetics, etc., a QR code identification method can be used to ensure that each small commodity has a clear and identifiable label, which is convenient for warehouse staff to quickly scan with mobile devices, thereby achieving efficient data entry and verification. For large quantities of high-value goods, such as electronic products, precious raw materials, etc., when the quantity and value of the goods meet the second preset condition, the radio frequency identification identification method is selected. The radio frequency identification identification method supports remote and batch identification, which can reduce manual operations and improve the efficiency and accuracy of goods inventory. In scenarios with frequent movement and close-range operations, such as fast-processing items in retail areas or assembly lines, the identification frequency and identification distance of the goods meet the third preset condition, so the near-field communication identification method is used. The short-range contactless reading and writing capabilities of the near-field communication identification method ensure the real-time and accuracy of data exchange in high-frequency and close-range identification operations, and can reduce inventory errors caused by signal interference or misreading, and ensure the safety of the inventory process and data accuracy.

[0061] Based on the above optional embodiments, different identification methods are selected according to different preset conditions, which can not only improve the efficiency of goods inventory and reduce labor costs, but also ensure the accuracy and security of inventory data.

[0062] Optionally, in step S12, obtaining target inventory data of goods to be counted according to the identification method to be used includes:

[0063] Step S121, collecting initial inventory data of the goods to be counted according to the identification method to be used;

[0064] Step S122, integrating the data sources of the initial inventory data to obtain an integration result;

[0065] Step S123, performing data cleaning on the integration result to obtain target inventory data.

[0066] The above data source integration refers to the process of integrating the initial inventory data collected through different identification technologies, such as QR code identification, radio frequency identification, and near-field communication identification, into a data platform or database. By integrating the data collected by multiple identification technologies, a comprehensive and unified data view is formed to support subsequent data analysis and management decisions.

[0067] The above-mentioned data cleaning refers to the process of identifying and correcting incomplete, inconsistent or inaccurate data in the inventory data during the data preprocessing stage, including but not limited to removing duplicate data, filling missing values, format standardization and data type. Its purpose is to improve data quality and ensure that the results of data analysis or data mining are more accurate and reliable.

[0068] For example, the initial inventory data of the goods to be counted in the target warehouse is first collected through the QR code identification method, the radio frequency identification identification method, and the near field communication identification method. Subsequently, the initial inventory data is transmitted to the unified data platform of the data center for data source integration. Finally, the data integration results are cleaned, duplicate data is removed, missing values ​​are filled, and the data is formatted to obtain the target inventory data.

[0069] Based on the above optional embodiments, the initial inventory data of the goods to be counted are collected according to the identification method to be used, and the data sources of the initial inventory data are integrated to obtain the integration results. Finally, the integration results are cleaned to obtain the target inventory data, which can eliminate data problems caused by technical differences or operational errors, thereby improving the reliability and availability of the data.

[0070] Optionally, the warehouse cargo inventory method in the embodiment of the present disclosure also includes: using historical inventory data to train an initial anomaly recognition model to generate a target anomaly recognition model, wherein the initial anomaly recognition model is used to identify abnormal inventory data generated during the cargo inventory process from multiple feature dimensions, and the multiple feature dimensions include: cargo inventory time dimension, cargo inventory frequency dimension, cargo inventory type dimension, and cargo inventory historical flow data dimension.

[0071] For example, the initial anomaly recognition model is trained using historical inventory data, and the generated target anomaly recognition model can identify anomalies that may occur during the inventory process from multiple feature dimensions of the inventory, including inventory time, frequency, type, and historical flow data. Through deep learning technology, the initial anomaly recognition model continuously learns normal and abnormal patterns in historical inventory data. As the training continues to deepen, the recognition accuracy and efficiency of the initial anomaly recognition model are significantly improved. The target anomaly recognition model generated in the end can analyze the newly generated inventory data in real time, quickly detect abnormal situations such as lost goods and repeated inventory, and provide timely feedback to the warehouse management department, thereby effectively reducing inventory errors, optimizing inventory management processes, and improving overall operational efficiency.

[0072] Based on the above optional embodiment, the initial anomaly recognition model is trained using historical inventory data to generate a target anomaly recognition model, which can provide feedback and adjustments based on anomalies in the historical inventory data to continuously optimize and improve recognition capabilities.

[0073] Optionally, the initial anomaly recognition model is trained using historical inventory data to generate a target anomaly recognition model including:

[0074] Step S21, using the initial anomaly recognition model to perform data anomaly detection on the historical inventory data to obtain historical detection results;

[0075] Step S22, obtaining the manual review results corresponding to the historical test results;

[0076] Step S23, optimizing the model parameters of the initial anomaly recognition model based on the manual review result to generate a target anomaly recognition model.

[0077] For example, historical inventory data is input into the initial anomaly recognition model to perform data anomaly detection and identify possible anomalies in the inventory. Subsequently, manual review is performed to verify whether the above anomalies actually exist, and the manual review results are fed back to the model to further optimize the learning process and generate a target anomaly recognition model.

[0078] Based on the above optional embodiments, an initial anomaly recognition model is used to perform data anomaly detection on historical inventory data to obtain historical detection results, and then obtain manual review results corresponding to the historical detection results. Finally, the model parameters of the initial anomaly recognition model are optimized based on the manual review results. The generated target anomaly recognition model can not only detect anomalies from real-time inventory data more accurately, but also predict possible abnormal situations based on the inventory time, frequency, type and historical flow data of the goods, thereby reducing inventory errors and optimizing inventory management processes.

[0079] Optionally, in step S13, a target anomaly recognition model is used to perform data anomaly detection on the target inventory data, and obtaining the current detection result includes: comparing the target inventory data with the historical inventory data through the target anomaly recognition model, identifying the missing goods in the inventory, and determining that the current detection result indicates that there are missing goods in the goods to be counted; and / or, identifying from the target inventory data through the target anomaly recognition model that the same batch of goods has been counted multiple times in the same time period, and determining that the current detection result indicates that there are repeated inventories in the goods to be counted.

[0080] For example, during the inventory process, when the target anomaly recognition model compares the target inventory data with the historical inventory data, it detects that a certain item does not appear in the latest inventory data, but the item is marked as in stock in the historical inventory data, indicating that there is missing goods in the goods to be counted; when the target anomaly recognition model detects that the same batch of goods is recorded multiple times in the same time period, it indicates that there is an abnormal situation of repeated inventory, which will not only reduce the accuracy of the inventory data, but may also cause a series of problems in subsequent supply chain management.

[0081] Based on the above optional embodiments, the target anomaly recognition model is used to identify the loss and repeated inventory of goods in the goods to be counted, so that abnormal situations in the goods inventory can be discovered in time, losses can be reduced, and the accuracy of the goods inventory can be ensured.

[0082] Optionally, the warehouse cargo inventory method further includes at least one of the following: encrypting and storing the target inventory data; maintaining and upgrading the system operating environment that supports multiple different types of identification methods.

[0083] Exemplarily, end-to-end encryption measures are adopted in the process of transmitting the inventory data to the central database to ensure that even if the data is intercepted during the transmission process, it cannot be cracked by a third party. After the inventory data reaches the server, an encryption storage solution based on public key infrastructure is further adopted to encrypt the data using a symmetric encryption algorithm. At the same time, a key pair is generated through asymmetric encryption technology, and the private key is stored in high-strength encryption hardware. The public key is used for data encryption to ensure that even if the database is illegally accessed, the inventory data is difficult to be cracked due to encryption protection, thereby ensuring the security of the cargo inventory information to the greatest extent. Furthermore, a regular key rotation and data integrity verification mechanism is implemented to prevent the potential security risks caused by the long-term use of the same key, while ensuring the integrity and consistency of the encrypted data and avoiding the risk of data being tampered with during storage.

[0084] For example, the system operating environment that supports multiple different types of identification methods is regularly maintained and upgraded, such as updating the antenna layout of the radio frequency identification reader to enhance signal reception capability, upgrading the near field communication module to support the latest device standards, and optimizing the image recognition algorithm of the QR code scanner to improve reading accuracy under different lighting conditions.

[0085] Based on the above optional embodiments, the target inventory data is encrypted and stored, and the system operating environment that supports multiple types of identification methods is maintained and upgraded, which can enhance the security of the target inventory data, avoid data leakage risks, and improve the stability of the intelligent inventory system.

[0086] Optionally, the warehouse cargo inventory method further includes: updating the inventory status in real time based on the target inventory data, wherein the inventory status is used to dynamically monitor the flow of cargo within the target warehouse; and issuing an alarm in response to identifying an inventory anomaly based on the inventory status.

[0087] For example, after each inventory count, the target inventory data is uploaded to the central database, and the pre-set data processing process is used for real-time analysis to update the inventory status. When an abnormal inventory situation is detected, the alarm mechanism is immediately triggered to send a real-time alarm to the warehouse manager via email, SMS or a dedicated mobile application, detailing the nature, location and possible cause of the abnormality.

[0088] Based on the above optional embodiments, the inventory status is updated in real time based on the target inventory data, and an alarm is issued when the inventory is abnormal. It can not only monitor the flow of goods in the warehouse in real time, but also respond quickly to inventory abnormalities, thereby improving the efficiency and accuracy of warehouse management.

[0089] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present disclosure, 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, a disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0090] Figure 2 is a schematic diagram of an intelligent inventory system according to one embodiment of the present disclosure, such as Figure 2 As shown, the system includes: an abnormal data analysis unit, an identification method integration unit, a real-time inventory tracking unit and a device layer. Among them, the abnormal data analysis unit is responsible for data collection and preprocessing through data source integration and data cleaning, and anomaly identification based on anomaly detection and feature engineering, and then classifies the abnormal situation into lost goods and repeated inventory, and performs visual detection based on the real-time monitoring panel, generates anomaly reports, and continuously learns and optimizes the abnormal identification model based on historical inventory data and feedback mechanisms; the identification method integration unit includes three different identification methods, namely: QR code identification method, radio frequency identification identification method and near-field communication identification method. Its system architecture includes software layer and hardware layer, and realizes automatic identification and data integration of goods through intelligent selection mechanism and unified data management, and realizes real-time inventory tracking based on dynamic update and inventory monitoring, and at the same time, Data security and system stability are guaranteed through encrypted storage and maintenance upgrades; the real-time inventory tracking unit collects real-time data based on multi-technology data integration and automatic identification mechanisms, and realizes inventory status monitoring based on dynamic updates and abnormal alarm mechanisms. It also analyzes data through inventory analysis and historical inventory data comparison, generates reports, and builds a visual interface through real-time monitoring panels and mobile applications. It can also be integrated with existing systems for scalability design and improved system compatibility. The device layer includes QR code scanners, radio frequency tag readers, near-field communication devices, mobile terminal devices, servers and network devices. The above hardware devices work together with the abnormal data analysis unit, identification method integration unit and real-time inventory tracking unit to collect data and transmit data.

[0091] In the embodiments of the present disclosure, a warehouse cargo inventory device is also provided, which is used to implement the above embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0092] Figure 3 is a structural block diagram of a warehouse cargo inventory device according to one embodiment of the present disclosure, such as Figure 3 As shown, the device comprises:

[0093] A selection module 301 is used to select a to-be-used identification method based on the properties of the goods to be counted in the target warehouse;

[0094] An acquisition module 302 is used to acquire target inventory data of the goods to be counted according to the identification method to be used;

[0095] The processing module 303 is used to perform data anomaly detection on the target inventory data using the target anomaly recognition model to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted;

[0096] The display module 304 is used to visually display the current detection results and / or generate an inventory exception report based on the current detection results.

[0097] Optionally, the selection module 301 is also used to: select the identification method to be used based on the properties of the goods to be counted in the target warehouse, including: in response to the volume of the goods to be counted in the target warehouse satisfying a first preset condition, selecting a QR code identification method; in response to the quantity and value of the goods to be counted in the target warehouse satisfying a second preset condition, selecting a radio frequency identification identification method; in response to the cargo identification frequency and cargo identification distance of the goods to be counted in the target warehouse satisfying a third preset condition, selecting a near field communication identification method.

[0098] Optionally, the acquisition module 302 is also used to: obtain target inventory data of the goods to be counted according to the identification method to be used, including: collecting initial inventory data of the goods to be counted according to the identification method to be used; integrating the data sources of the initial inventory data to obtain an integration result; and cleaning the integration result to obtain target inventory data.

[0099] Optionally, the processing module 303 is also used to: use historical inventory data to train an initial anomaly recognition model to generate a target anomaly recognition model, wherein the initial anomaly recognition model is used to identify abnormal inventory data generated during the cargo inventory process from multiple feature dimensions, and the multiple feature dimensions include: cargo inventory time dimension, cargo inventory frequency dimension, cargo inventory type dimension, and cargo inventory historical flow data dimension.

[0100] Optionally, the processing module 303 is also used to: use the initial anomaly recognition model to perform data anomaly detection on historical inventory data to obtain historical detection results; obtain manual review results corresponding to the historical detection results; optimize the model parameters of the initial anomaly recognition model based on the manual review results to generate a target anomaly recognition model.

[0101] Optionally, the processing module 303 is also used to: compare the target inventory data with the historical inventory data through the target anomaly recognition model, identify the missing goods in the inventory, and determine that the current detection result indicates that there are missing goods in the goods to be counted; and / or, identify from the target inventory data through the target anomaly recognition model that the same batch of goods has been counted multiple times in the same time period, and determine that the current detection result indicates that there are repeated inventories in the goods to be counted.

[0102] Optionally, the processing module 303 is also used to: update the inventory status in real time based on the target inventory data, wherein the inventory status is used to dynamically monitor the flow of goods in the target warehouse; and issue an alarm in response to identifying inventory anomalies based on the inventory status.

[0103] According to one embodiment of the present disclosure, there is also provided an electronic device, including: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned warehouse cargo inventory method is executed when the program is running.

[0104] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0105] S1, selecting the identification method to be used based on the properties of the goods to be counted in the target warehouse;

[0106] S2, obtaining target inventory data of the goods to be counted according to the identification method to be used;

[0107] S3, using the target anomaly recognition model to perform data anomaly detection on the target inventory data to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted;

[0108] S4, visually display the current test results, and / or generate an inventory exception report based on the current test results.

[0109] According to one embodiment of the present disclosure, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored executable program, wherein when the executable program runs, the device where the storage medium is located is controlled to execute the warehouse cargo inventory method in the embodiment of the present disclosure.

[0110] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0111] S1, selecting the identification method to be used based on the properties of the goods to be counted in the target warehouse;

[0112] S2, obtaining target inventory data of the goods to be counted according to the identification method to be used;

[0113] S3, using the target anomaly recognition model to perform data anomaly detection on the target inventory data to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted;

[0114] S4, visually display the current test results, and / or generate an inventory exception report based on the current test results.

[0115] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0116] According to one embodiment of the present disclosure, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, the warehouse goods inventory counting method in the embodiment of the present disclosure is implemented.

[0117] Optionally, in this embodiment, the computer program product may be configured as a computer program for executing the following steps:

[0118] S1, selecting the identification method to be used based on the properties of the goods to be counted in the target warehouse;

[0119] S2, obtaining target inventory data of the goods to be counted according to the identification method to be used;

[0120] S3, using the target anomaly recognition model to perform data anomaly detection on the target inventory data to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted;

[0121] S4, visually display the current test results, and / or generate an inventory exception report based on the current test results.

[0122] The serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0123] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0124] In the several embodiments provided in the present disclosure, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0126] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0127] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0128] The above is only a preferred embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present disclosure. These improvements and modifications should also be regarded as the scope of protection of the present disclosure.

Claims

1. A warehouse cargo inventory method, characterized in that: include: Select the identification method to be used based on the properties of the goods to be counted in the target warehouse; Acquire target inventory data of the goods to be counted according to the identification method to be used; Using a target anomaly recognition model to perform data anomaly detection on the target inventory data to obtain a current detection result, wherein the current detection result is used to indicate whether there is any missing goods and / or repeated inventory in the goods to be counted; Visually display the current detection results, and / or generate an inventory exception report based on the current detection results.

2. The warehouse cargo inventory method according to claim 1, characterized in that: Selecting the identification method to be used based on the properties of the goods to be counted in the target warehouse includes: In response to the volume of the goods to be counted in the target warehouse meeting a first preset condition, selecting a QR code identification method; In response to the quantity and value of the goods to be counted in the target warehouse satisfying a second preset condition, selecting a radio frequency identification identification method; In response to the cargo identification frequency and the cargo identification distance of the cargo to be counted in the target warehouse satisfying a third preset condition, a near field communication identification mode is selected.

3. The warehouse cargo inventory method according to claim 1, characterized in that: Acquiring the target inventory data of the goods to be counted according to the identification method to be used includes: Collecting initial inventory data of the goods to be counted according to the identification method to be used; Integrate the data sources of the initial inventory data to obtain an integration result; The integration result is cleaned to obtain the target inventory data.

4. The warehouse cargo inventory method according to claim 1, characterized in that: The warehouse cargo inventory method also includes: The initial anomaly recognition model is trained using historical inventory data to generate the target anomaly recognition model, wherein the initial anomaly recognition model is used to identify abnormal inventory data generated during the goods inventory process from multiple feature dimensions, and the multiple feature dimensions include: goods inventory time dimension, goods inventory frequency dimension, goods inventory type dimension, and goods inventory historical flow data dimension.

5. The warehouse cargo inventory method according to claim 4, characterized in that: Using the historical inventory data to train the initial anomaly recognition model to generate the target anomaly recognition model includes: Using the initial anomaly recognition model to perform data anomaly detection on the historical inventory data to obtain historical detection results; Obtaining manual review results corresponding to the historical test results; The model parameters of the initial anomaly recognition model are optimized based on the manual review result to generate the target anomaly recognition model.

6. The warehouse cargo inventory method according to claim 1, characterized in that: The target anomaly recognition model is used to perform data anomaly detection on the target inventory data, and the current detection result obtained includes: Comparing the target inventory data with historical inventory data through the target anomaly recognition model to identify goods missing from the inventory, and determining that the current detection result indicates that goods are missing from the goods to be counted; and / or, The target anomaly recognition model identifies from the target inventory data that the same batch of goods is counted multiple times within the same time period, and determines that the current detection result indicates that repeated counts exist in the goods to be counted.

7. The warehouse cargo inventory method according to claim 1, characterized in that: The warehouse cargo inventory method further includes at least one of the following: Encrypting and storing the target inventory data; Maintain and upgrade the system operating environment that supports multiple different types of identification methods.

8. The warehouse cargo inventory method according to claim 1, characterized in that: The warehouse cargo inventory method also includes: updating the inventory status in real time based on the target inventory data, wherein the inventory status is used to dynamically monitor the flow of goods in the target warehouse; In response to identifying an inventory anomaly based on the inventory status, an alarm is issued.

9. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the warehouse cargo inventory method described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the warehouse cargo inventory method according to any one of claims 1 to 8.

11. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the warehouse goods inventory counting method according to any one of claims 1 to 8.

Images