Intelligent logistics storage data processing method and system, electronic equipment and storage medium

Abstract

The invention provides an intelligent logistics storage data processing method and system, electronic equipment and a storage medium, and belongs to the technical field of storage data processing, and the method comprises the steps: carrying out the data classification of first data based on a hierarchical clustering algorithm, and obtaining a plurality of first data subsets; the first data is to-be-processed storage data. And performing data screening from the plurality of first data subsets, and selecting a plurality of target data subsets. And in response to a received data processing instruction, processing the plurality of target data subsets based on the data processing instruction and the association rule base. The association rule base comprises association rules among the storage data. According to the intelligent logistics storage data processing method and system, the electronic equipment and the storage medium provided by the invention, the storage data processing quality can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of warehouse data processing, and more specifically, to a smart logistics warehouse data processing method and system, electronic equipment, and storage medium. Background Art

[0002] In the field of logistics and warehousing, with the widespread application of technologies such as the Internet of Things and sensors, the scope and accuracy of data collection have been continuously improved, generating massive amounts of warehousing data, including cargo information, warehousing environment information, logistics operation information, etc. These data have the characteristics of multi-source, heterogeneous, and high-dimensional. Traditional data processing methods based on manual experience or simple statistical analysis are difficult to effectively manage and analyze them, resulting in difficulty in mining data value and low data processing quality. Summary of the invention

[0003] The purpose of the present disclosure is to provide a smart logistics warehousing data processing method and system, electronic equipment, and storage medium to improve the quality of warehousing data processing.

[0004] A first aspect of the embodiments of the present disclosure provides a method for processing smart logistics warehousing data, including: Classifying the first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets; the first data is warehouse data to be processed; Performing data screening from the plurality of first data subsets to select a plurality of target data subsets; In response to receiving the data processing instruction, the plurality of target data subsets are processed based on the data processing instruction and an association rule base; the association rule base includes association rules between warehoused data.

[0005] A second aspect of the embodiments of the present disclosure provides a smart logistics warehousing data processing system, including: A clustering module, used for classifying the first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets; the first data is warehouse data to be processed; A data screening module, used to screen data from the plurality of first data subsets to select a plurality of target data subsets; The data processing module is used to process the multiple target data subsets based on the data processing instructions and an association rule base in response to receiving the data processing instructions; the association rule base includes association rules between warehouse data.

[0006] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned smart logistics warehousing data processing method when executing the computer program.

[0007] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned smart logistics warehousing data processing method are implemented.

[0008] The beneficial effects of the smart logistics warehousing data processing method and system, electronic device, and storage medium provided by the embodiments of the present disclosure are: By classifying the first data through a hierarchical clustering algorithm, complex warehouse data can be quickly divided into multiple subsets according to similar features, reducing the complexity and workload of data processing and improving the processing speed. Data screening from multiple first data subsets to obtain a target data subset helps to remove noise data, outliers and irrelevant data, ensuring that the data used for subsequent analysis has higher accuracy, completeness and representativeness, improving the quality of data processing, and thus improving the reliability of decisions made based on these data. Processing the target data subset based on data processing instructions and association rule libraries can make full use of the association rules between warehouse data and improve the quality and accuracy of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flowchart of a smart logistics warehousing data processing method provided by an embodiment of the present disclosure; Figure 2 A structural block diagram of a smart logistics warehousing data processing system provided in one embodiment of the present disclosure; Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0012] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A flowchart of a smart logistics warehousing data processing method provided in one embodiment of the present disclosure, the method may include S101 to S103.

[0014] S101: Classify first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets. The first data is warehouse data to be processed.

[0015] In this embodiment, the first data is classified based on a hierarchical clustering algorithm to obtain a plurality of first data subsets, including: The first data is classified based on a hierarchical clustering algorithm to obtain a multi-level classification result. Each level of the multi-level classification result includes multiple clusters.

[0016] The target layer classification results are selected from the multi-level classification results based on the number of clusters of each layer classification result in the multi-level classification results and the amount of data in each cluster.

[0017] The multiple clusters in the target layer classification result are formed into multiple first data subsets.

[0018] In this embodiment, the first data may include a set of original data from various aspects of logistics and warehousing, such as basic information of goods, warehousing operation records, logistics and transportation details, and warehouse environment data. The multi-level classification result indicates that after being processed by the hierarchical clustering algorithm, different levels of classification are presented. Each layer divides the data into multiple clusters with similar characteristics, reflecting the grouping of data at different granularities. A cluster is a set of data objects with high similarity in the clustering process, and these objects show consistency in certain attributes or behavior patterns.

[0019] In this embodiment, each data point in the first data is regarded as an initial separate cluster, and then the similarity between clusters is calculated according to the selected similarity measurement method. For example, for cargo data, the similarity is first calculated according to the basic attributes of the cargo to perform preliminary merging to form a larger cluster; then, other factors such as warehousing operations are considered to further subdivide or merge the clusters, and a tree-like multi-level classification structure is gradually constructed.

[0020] When selecting the classification results of the target layer, the number of clusters in each layer and the amount of data in each cluster are comprehensively considered. If there are too many clusters, the classification may be too detailed, which is not conducive to the overall grasp of the data characteristics; if the number of clusters is too small, important details may be lost. At the same time, clusters with too small data volumes may not be representative, while clusters that are too large may have large internal differences. By weighing these factors, a target layer that can reflect the main characteristics of the data and has an appropriate granularity is selected, and the multiple clusters of this layer are determined as the first data subset for subsequent targeted data screening and analysis.

[0021] For example, in a large e-commerce warehouse, various types of goods are stored, and their storage data is used as the first data. Using the hierarchical clustering algorithm, the first-level classification results are divided according to the major categories of goods, such as electronic products, clothing, food, etc., and each category forms a cluster. In the electronic product cluster, the second-level classification results are divided according to the brand. The third-level classification results are divided according to the time pattern of electronic products entering and leaving the warehouse. Suppose now we want to analyze the inventory management of electronic products of various brands at different sales stages. By evaluating the number of clusters and the amount of data in each layer, we can select the second layer as the target layer classification result, and the corresponding cluster as the first data subset. These subsets can be screened later. After removing outliers, the data can be further processed in combination with the association rule library.

[0022] S102: Screening data from the multiple first data subsets to select multiple target data subsets.

[0023] In this embodiment, data screening is performed from multiple first data subsets to select multiple target data subsets, including: Calculate the number of data samples for each first data subset.

[0024] A first threshold is determined based on the number of data samples of the plurality of first data subsets.

[0025] A first data subset whose number of data samples is greater than or equal to a first threshold is selected from a plurality of first data subsets, and the first data subset is used as a target data subset.

[0026] In this embodiment, the number of data samples refers to the number of data records contained in each subset. The first threshold is used to screen the first data subset. The determination of the first threshold needs to consider factors such as the overall data size of the warehouse data and the requirements for data representativeness for the analysis purpose. For example, if the amount of data is huge and you want to obtain data with broad representativeness, the first threshold can be increased; if it is only for specific fine analysis and the data is limited, the first threshold can be appropriately reduced.

[0027] Exemplarily, the calculation formula of the first threshold is:

[0028] in, represents the first threshold, represents the proportional coefficient, M represents the total number of data samples of all target data subsets, and N represents the number of target data subsets.

[0029] Abnormal subsets with too few data samples can be removed through strict screening of the first threshold. For example, the number of samples of most first data subsets is in the range of 200-1000, and the number of samples of some first data subsets is 10, which are not at the same data level. In this case, the data of the first data subset may be erroneous data.

[0030] S103: In response to receiving the data processing instruction, multiple target data subsets are processed based on the data processing instruction and the association rule base. The association rule base includes association rules between warehouse data.

[0031] In this embodiment, the data processing instructions may include anomaly detection instructions and data sampling instructions. The anomaly detection instructions are used to find data points or patterns in the warehouse data that do not conform to the normal pattern or expected range, and the data sampling instructions are used to extract representative data samples from the target data subset. The association rules between warehouse data may include the association mapping relationship between data features extracted from the warehouse data and the dependency relationship between warehouse data.

[0032] Exemplarily, when an abnormality detection instruction is received, the target data subset is scanned according to the rules in the association rule base regarding the normal in-and-out mode of electronic components, inventory fluctuation range, environmental parameter standards, etc. For example, the association rule base contains the rule that "the in-and-out volume of a certain model of chip is positively correlated with the peak season of electronic product production, and the purchase volume from a specific supplier will increase by 20% during the peak season, and it is stored in a low temperature and low humidity area." When processing the target data subset, if it is found that the in-and-out volume of the chip has not increased during the peak production season, and the purchase volume has decreased, and the storage location is recorded in a high temperature and high humidity area, and the data relationship between these features does not conform to the association rules, then this data is classified as an outlier, prompting the management personnel to check the data accuracy or check whether there are abnormal situations such as errors in the logistics link and supplier problems.

[0033] For data sampling instructions, samples are extracted from the target data subset according to the sampling parameters in the instruction. For example, stratified sampling is used to stratify by electronic component category, supplier, etc., and data is extracted in each stratum according to a set ratio for subsequent rapid analysis or model training, improving processing efficiency while ensuring data representativeness.

[0034] From the above, it can be concluded that by finely classifying the first data through the hierarchical clustering algorithm and then filtering out the target data subset based on the number of data samples, noise data and outliers can be effectively removed, ensuring the data quality of subsequent analysis, making decisions based on these data more accurate and reliable, and reducing decision errors caused by data errors. The use of association rule bases provides a more comprehensive knowledge base for data processing. Whether it is anomaly detection or data sampling, operations can be performed based on the inherent association rules between warehouse data to improve data processing quality.

[0035] Operations such as data screening and stratified sampling can reduce unnecessary data processing and quickly locate key data while ensuring the validity of the data and increasing the speed of data processing, enabling enterprises to respond to market changes more promptly and providing strong support for the efficient operation of smart logistics warehousing.

[0036] In one embodiment of the present disclosure, the smart logistics warehousing data processing method further includes: The second data is classified based on a hierarchical clustering algorithm to obtain a plurality of second data subsets. The second data is historical storage data.

[0037] A base of association rules is determined based on the plurality of second data subsets.

[0038] In this embodiment, determining an association rule base based on multiple second data subsets includes: The association features of the data in each second data subset are calculated, and an initial association rule is established based on the association features corresponding to all the second data subsets.

[0039] The support and confidence of the initial association rule are calculated based on all the second data subsets.

[0040] The initial association rules are screened based on support and confidence to obtain an association rule base.

[0041] In this embodiment, calculating the correlation features of the data in each second data subset includes: Perform feature extraction on the second data subset to obtain a feature data set.

[0042] Calculate the correlation coefficient between feature data sets and determine the associated features based on the correlation coefficient.

[0043] In this embodiment, the second data is the historical storage data within a specific time period in the past. The correlation feature refers to an attribute or indicator that can reflect the internal connection between data. In the cargo data, if certain goods are often in and out of the warehouse at the same time, this is a correlation feature; in the warehouse operation data, the relationship between the frequency of goods in and out of a specific storage area and the equipment maintenance status of the area is also a correlation feature.

[0044] In this embodiment, support refers to the proportion of the number of records that simultaneously meet the antecedent and consequent of a certain association rule in all second data subsets to the total number of records. Support can reflect the frequency of occurrence of the rule in the data set. For example, when analyzing the associated purchase relationship of goods, if the rule "buy a mobile phone and a mobile phone case at the same time" appears frequently in the historical sales data, that is, the support is high, indicating that there is a strong association between the two goods.

[0045] Confidence is used to measure the probability of occurrence of the consequent condition under the condition that the antecedent condition of the rule occurs. Taking the above example, if a high proportion of records of purchasing mobile phones also purchase mobile phone cases at the same time, then the confidence of the rule "buy mobile phone and buy mobile phone case at the same time" is high, which indicates that when customers buy mobile phones, they are likely to buy mobile phone cases as well, and this association has a high reliability.

[0046] In this embodiment, the initial association rules are screened based on support and confidence, including: The evaluation value of the initial association rule is calculated based on the support, confidence and rule screening formula.

[0047] The rule screening formula is:

[0048] in, represents the evaluation value of the initial association rule, , and represents the weight coefficient, Express support, represents the confidence level, n represents the number of factors affecting data quality, represents the evaluation value corresponding to the i-th data quality influencing factor, Represents the weight coefficient of the i-th data quality influencing factor.

[0049] The initial association rules are screened based on the evaluation values ​​of the initial association rules.

[0050] Exemplarily, factors affecting data quality may include data timeliness and data integrity. When the referenced data timeliness and data integrity evaluation values ​​are higher, the reliability of the initial association rules calculated based on the data is higher; conversely, the reliability of the calculated initial association rules is lower.

[0051] For example, a certain electronic product storage center uses the historical storage data of the past year as the second data. The hierarchical clustering algorithm is used to divide these data into second data subsets of different categories of goods, such as home appliances, clothing, digital products, etc. Feature extraction is performed on each subset. Taking home appliances as an example, features such as the storage time, sales volume, and return rate of home appliances of different brands are extracted, and the correlation coefficient is calculated. It is found that when the storage volume of a well-known brand of air conditioners increases significantly in summer, the storage volume of the matching air conditioner brackets and drainage pipes will also increase accordingly, thereby establishing the corresponding initial association rules (summer-air conditioners-storage volume: increase; air conditioner brackets-storage volume: increase; drainage pipes-storage volume: increase).

[0052] Calculate the support and confidence of these initial association rules. Assume that in all historical data records, the proportion of this association rule that satisfies both the antecedent and the consequent is 40%, that is, the support is 0.4; in the records of increased air conditioner inventory, there are 70% cases where the supporting products also increase, that is, the confidence is 0.7.

[0053] Considering the factors affecting data quality, the weight coefficient of data timeliness is 0.3, the weight coefficient of data integrity is 0.7, the current data timeliness evaluation value is 0.8, and the data integrity evaluation value is 0.9. The evaluation value is calculated according to the rule screening formula. If the evaluation value meets the set standard, this association rule will be included in the association rule library.

[0054] This embodiment can more accurately screen out high-value association rules by comprehensively considering multiple factors, avoiding the omission of valuable rules or the misselection of low-quality rules due to single factor judgment. Considering factors affecting data quality enables the rule base to better adapt to business changes, ensuring that association rules always reflect the current real and reliable warehousing laws, providing a solid basis for inventory management, logistics scheduling and other decision-making, and improving the overall efficiency and benefits of smart logistics warehousing operations.

[0055] In one embodiment of the present disclosure, the data processing instructions include anomaly detection instructions.

[0056] Process multiple target data subsets based on data processing instructions and association rule base, including: Determine the data type to which each target data subset belongs.

[0057] If the data processing instruction is an anomaly detection instruction: The target association rules are matched from the association rule library based on the data type to which the target data subset belongs.

[0058] Outlier detection is performed on the target data subset based on the target association rules.

[0059] In this embodiment, the anomaly detection instruction is intended to find data points or patterns in the warehouse data that deviate from the normal pattern. The parameters carried by the anomaly detection instruction may include detection sensitivity and time range. The data type refers to the category of warehouse data represented by the target data subset, such as cargo information category, warehouse operation category, etc.

[0060] In this embodiment, after receiving the abnormal detection instruction, the parameters carried in the instruction are analyzed, such as the detection sensitivity determines the strictness of the abnormal judgment, and the time range clarifies the time period of the detection data. The data type of each target data subset is determined to clarify whether it belongs to the cargo information class, warehousing operation class, etc. The target association rules are accurately matched from the association rule library according to the data type. These rules are normal data patterns mined based on historical data. The actual data of the target data subset is compared with the target association rules one by one. Once the data exceeds the normal range set by the rule, it is determined as an abnormal value, thereby achieving effective detection of abnormal conditions in warehousing data.

[0061] Exemplarily, after receiving the anomaly detection instruction, the data type of each target data subset is identified. According to the data type, a target association rule matching it is searched from the association rule library. For example, for the goods in and out data subset, the association rule about the normal in and out quantity, frequency and time relationship of goods is found as the target association rule. The actual data of the target data subset is compared and analyzed with the target association rule. If the data violates the pattern set in the rule, the data is marked as an outlier, and detailed information of the abnormal situation is recorded, such as abnormal data points, degree of abnormality, possible affected business links, etc., so as to further investigate the cause and take corresponding measures later.

[0062] This embodiment can flexibly and accurately locate warehouse data anomalies through anomaly detection instructions. Detection is performed based on data type matching association rules, which is highly targeted and can promptly detect anomalies such as incorrect cargo information and warehouse operation errors, avoiding decision-making errors caused by data deviations. This helps to optimize warehouse management processes, improve inventory management accuracy, ensure efficient and stable operation of logistics warehousing, and reduce operational risks.

[0063] In one embodiment of the present disclosure, the smart logistics warehousing data processing method further includes: The third data is determined based on the target update frequency and the target time window.

[0064] An association rule corresponding to the third data is determined, and an association rule base is updated based on the association rule corresponding to the third data.

[0065] In this embodiment, the target update frequency refers to the preset time interval for updating the association rule base, and the target time window is the time range for determining the data used to update the association rules. The third data is a data set for updating the association rule base selected from all warehouse data according to the target update frequency and the target time window.

[0066] In this embodiment, the update process is started regularly according to the set target update frequency, and the third data is extracted from the historical warehousing data according to the target time window. For example, if the target update frequency is once a quarter and the target time window is the past month, then the warehousing data of the past month is selected as the third data at the beginning of each quarter. The third data is analyzed, and the same method as the initial association rule base is used to calculate the association characteristics of the data in the third data subset, and determine the corresponding association rules, such as the discovery of new goods combinations frequently entering and leaving the warehouse, and the association between new logistics transportation methods and goods types. These new association rules are compared and integrated with the original association rule base, and new rules that meet certain conditions (such as support and confidence reaching a certain threshold) are added to the association rule base, and old rules that are no longer applicable (such as invalid due to business adjustments or market changes) are eliminated, thereby realizing the update of the association rule base so that it can better reflect the actual situation and internal laws of the current warehousing business.

[0067] This embodiment regularly updates the association rule base according to the target update frequency and time window, which can make the warehouse data processing closely follow the dynamic changes of the business. New rules such as cargo association and logistics transportation association are included in a timely manner, and outdated old rules are eliminated to ensure the continuous improvement of data processing accuracy. It helps to optimize inventory management, improve logistics efficiency, reduce costs, enhance the adaptability and competitiveness of enterprises to market changes, and ensure the efficient operation of smart logistics warehousing systems.

[0068] Corresponding to the smart logistics warehousing data processing method in the above embodiment, Figure 2 This is a block diagram of the structure of a smart logistics warehousing data processing system provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 2 The smart logistics warehousing data processing system 20 includes: a clustering module 21, a data screening module 22 and a data processing module 23.

[0069] The clustering module 21 is used to classify the first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets. The first data is the warehouse data to be processed.

[0070] The data screening module 22 is used to screen the data from the multiple first data subsets and select multiple target data subsets.

[0071] The data processing module 23 is used to process the multiple target data subsets based on the data processing instructions and the association rule base in response to receiving the data processing instructions. The association rule base includes association rules between the warehouse data.

[0072] In one embodiment of the present disclosure, the smart logistics warehousing data processing system 20 further includes: The association calculation module is used to classify the second data based on the hierarchical clustering algorithm to obtain multiple second data subsets. The second data is historical warehouse data.

[0073] A base of association rules is determined based on the plurality of second data subsets.

[0074] In one embodiment of the present disclosure, the association calculation module is specifically used to calculate the association features of the data in each second data subset, and establish an initial association rule based on the association features corresponding to all the second data subsets.

[0075] The support and confidence of the initial association rule are calculated based on all the second data subsets.

[0076] The initial association rules are screened based on support and confidence to obtain an association rule base.

[0077] In one embodiment of the present disclosure, the association calculation module is further configured to calculate the evaluation value of the initial association rule based on the support, confidence and rule screening formula.

[0078] The rule screening formula is:

[0079] in, represents the evaluation value of the initial association rule, , and represents the weight coefficient, Express support, represents the confidence level, n represents the number of factors affecting data quality, represents the evaluation value corresponding to the i-th data quality influencing factor, Represents the weight coefficient of the i-th data quality influencing factor.

[0080] The initial association rules are screened based on the evaluation values ​​of the initial association rules.

[0081] In one embodiment of the present disclosure, the data screening module 22 is specifically configured to calculate the number of data samples of each first data subset.

[0082] A first threshold is determined based on the number of data samples of the plurality of first data subsets.

[0083] A first data subset whose number of data samples is greater than or equal to a first threshold is selected from a plurality of first data subsets, and the first data subset is used as a target data subset.

[0084] In one embodiment of the present disclosure, the data processing instruction includes an anomaly detection instruction. The data processing module 23 is specifically configured to determine the data type to which each target data subset belongs.

[0085] If the data processing instruction is an anomaly detection instruction: The target association rules are matched from the association rule library based on the data type to which the target data subset belongs.

[0086] Outlier detection is performed on the target data subset based on the target association rules.

[0087] In one embodiment of the present disclosure, the smart logistics warehousing data processing system 20 further includes: The rule updating module is used to determine the third data based on the target updating frequency and the target time window.

[0088] An association rule corresponding to the third data is determined, and an association rule base is updated based on the association rule corresponding to the third data.

[0089] See also Figure 3 , Figure 3 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned system embodiments, such as Figure 2 The functions of modules 21 to 23 are shown.

[0090] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0091] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0092] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0093] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the smart logistics warehousing data processing method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device 300 described in the embodiments of the present disclosure, which will not be repeated here.

[0094] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0095] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0096] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0097] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed electronic device and method can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of units is only 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0099] 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present disclosure.

[0100] 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.

[0101] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A smart logistics warehousing data processing method, characterized in that: include: Classifying the first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets; The first data is storage data to be processed; Performing data screening from the plurality of first data subsets to select a plurality of target data subsets; In response to receiving the data processing instruction, processing the plurality of target data subsets based on the data processing instruction and an associated rule base; The association rule base includes association rules between warehouse data.

2. The method for processing intelligent logistics warehousing data according to claim 1, characterized in that: Also includes: Classifying the second data based on a hierarchical clustering algorithm to obtain a plurality of second data subsets; The second data is historical storage data; A base of association rules is determined based on the plurality of second data subsets.

3. The method for processing intelligent logistics warehousing data as claimed in claim 2, characterized in that: The determining of an association rule base based on the plurality of second data subsets comprises: Calculate the association features of the data in each second data subset, and establish an initial association rule based on the association features corresponding to all the second data subsets; Calculating the support and confidence of the initial association rule based on all second data subsets; The initial association rules are screened based on the support and the confidence to obtain an association rule base.

4. The method for processing intelligent logistics warehousing data according to claim 3, characterized in that: The screening of the initial association rules based on the support and the confidence includes: Calculating the evaluation value of the initial association rule based on the support, the confidence and the rule screening formula; The rule screening formula is: in, represents the evaluation value of the initial association rule, , and represents the weight coefficient, Express support, represents the confidence level, n represents the number of factors affecting data quality, represents the evaluation value corresponding to the i-th data quality influencing factor, Represents the weight coefficient of the i-th data quality influencing factor; The initial association rules are screened based on the evaluation values ​​of the initial association rules.

5. The method for processing intelligent logistics warehousing data according to claim 1, characterized in that: The step of screening data from the plurality of first data subsets to select a plurality of target data subsets includes: Calculate the number of data samples of each first data subset; Determine a first threshold based on the number of data samples of the plurality of first data subsets; A first data subset whose number of data samples is greater than or equal to a first threshold is selected from a plurality of first data subsets, and the first data subset is used as a target data subset.

6. The intelligent logistics warehousing data processing method according to claim 1, characterized in that: The data processing instructions include anomaly detection instructions; The processing of the plurality of target data subsets based on the data processing instructions and the association rule base includes: Determine the data type to which each target data subset belongs; If the data processing instruction is an exception detection instruction: Matching a target association rule from the association rule library based on the data type to which the target data subset belongs; Outlier detection is performed on the target data subset based on the target association rule.

7. The method for processing intelligent logistics warehousing data according to claim 1, characterized in that: Also includes: determining third data based on the target update frequency and the target time window; An association rule corresponding to the third data is determined, and an association rule library is updated based on the association rule corresponding to the third data.

8. A smart logistics warehousing data processing system, characterized in that: include: A clustering module, used for classifying the first data based on a hierarchical clustering algorithm to obtain a plurality of first data subsets; The first data is storage data to be processed; A data screening module, used to screen data from the plurality of first data subsets to select a plurality of target data subsets; a data processing module, configured to, in response to receiving a data processing instruction, process the plurality of target data subsets based on the data processing instruction and an association rule base; The association rule base includes association rules between warehouse data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images