Intelligent warehouse management system and method based on big data

Abstract

The invention relates to a warehouse intelligent management system and method based on big data. The system comprises a multi-source storage data management subsystem which is used for obtaining multi-source storage data of stored goods and carrying out semantic extraction to obtain core field data of the stored goods; the storage space intelligent distribution subsystem is used for generating an inter-channel storage space intelligent distribution scheme among the storage channels of the warehouse based on the core field data of the stored goods stored in the warehouse; the storage area dynamic updating subsystem is used for obtaining goods scheduling estimation data and generating an intelligent distribution scheme of storage space in the channel based on the goods scheduling estimation data and the core field data; and the warehouse cargo intelligent scheduling subsystem is used for carrying out intelligent scheduling on the warehouse cargo based on the inter-channel warehouse space intelligent distribution scheme and the in-channel warehouse space intelligent distribution scheme. According to the method, the storage distribution space is dynamically planned and intelligently updated, so that accurate and efficient storage management can be realized.

Description

Technical Field

[0001] This application belongs to the field of warehouse management, and in particular relates to an intelligent warehouse management system and method based on big data. Background Technology

[0002] Traditional warehouse management relies heavily on manual operation and experience-based judgment, involving manual recording of goods information, allocation of storage locations, and dispatching of goods. While simple, this approach is inefficient. However, with the continuous development of IoT technology, warehouse management is gradually becoming intelligent and automated. Intelligent warehouse management systems are a product of the deep integration of modern logistics and information technology. Through intelligent analysis and automated decision-making, these systems can improve the efficiency and accuracy of warehouse management.

[0003] However, existing intelligent warehouse management systems often employ fixed channel allocation models at the spatial management level, which cannot cope with scheduling changes, wastes space resources, and increases the difficulty of goods handling. Furthermore, due to a lack of clear guidelines, existing intelligent warehouse management systems suffer from high scheduling difficulty and chaotic scheduling paths, making it difficult to meet the needs of efficient and precise warehouse operations. Summary of the Invention

[0004] Therefore, it is necessary to provide a big data-based intelligent warehouse management system and method that can achieve accurate and efficient warehouse operation management, addressing the aforementioned technical issues.

[0005] Firstly, this application provides a big data-based intelligent warehouse management system, comprising:

[0006] The multi-source warehousing data management subsystem is used to acquire multi-source warehousing data of stored goods and perform semantic extraction to obtain the core field data of the stored goods. The core field data is used to characterize the physical attributes, storage quantity, turnover data and goods category of the stored goods.

[0007] The intelligent storage space allocation subsystem is used to allocate storage space for different categories of goods based on the core field data of the stored goods in the warehouse, and generate intelligent allocation schemes for storage space between different storage channels in the warehouse.

[0008] The warehouse area dynamic update subsystem is used to obtain cargo scheduling forecast data for each category of goods, and based on the cargo scheduling forecast data and core field data, generate an intelligent allocation scheme for the storage space in each storage aisle of the warehouse.

[0009] The intelligent scheduling subsystem for warehouse goods is used to intelligently schedule warehouse goods based on intelligent allocation schemes for inter-channel and intra-channel warehouse space.

[0010] In one embodiment, the physical attributes of the stored goods include the volume of the goods, and the intelligent storage space allocation subsystem includes:

[0011] The storage space allocation module is used to allocate storage space for each category of goods based on the volume of the goods in each category, and to generate storage space allocation information for each category of goods.

[0012] The warehouse space distribution and allocation module is used to allocate warehouse space locations for different categories of goods based on the warehouse space size allocation information and turnover data of each category of goods, and to generate an intelligent allocation scheme for warehouse space between each warehouse aisle.

[0013] In one embodiment, the turnover data includes historical outbound data and historical inbound data, and the warehouse space distribution module includes:

[0014] The outbound correlation analysis component is used to calculate the outbound support, outbound confidence, outbound lift, and outbound time window transition probability between each goods category based on historical outbound data, and to generate the outbound correlation degree between each goods category based on the weighted sum of the outbound support, outbound confidence, outbound lift, and outbound time window transition probability.

[0015] The inbound correlation analysis component is used to calculate the inbound support, inbound confidence, inbound lift, and inbound time window transition probability between each goods category based on historical inbound data, and to generate the inbound correlation degree between each goods category based on the weighted sum of the inbound support, inbound confidence, inbound lift, and inbound time window transition probability.

[0016] The associated space allocation component is used to allocate the storage space location of warehouse goods of each goods category based on the outbound association degree and inbound association degree between each goods category, and generate an intelligent allocation scheme for inter-channel storage space between each storage channel of the warehouse.

[0017] The expressions for outbound correlation and inbound correlation are as follows:

[0018]

[0019]

[0020] In the formula, and The first Class of goods and the first The correlation between outbound and inbound goods categories , , and The first Class of goods and the first Outbound support, outbound confidence, outbound lift, and outbound time window shift probability among different categories of goods. , , and The first Class of goods and the first The weights for outbound support, outbound confidence, outbound lift, and outbound time window transition probability are calculated based on the outbound support among different goods categories. , , and The first Class of goods and the first Inbound support, inbound confidence, inbound lift, and inbound time window shift probability among different categories of goods. , , and The first Class of goods and the first The weights for inbound support, inbound confidence, inbound lift, and inbound time window transition probability are calculated among different categories of goods.

[0021] In one embodiment, the multi-source warehouse data management subsystem includes:

[0022] The multi-source warehousing data acquisition module is used to acquire data on the attributes of stored goods, the quantity of stored goods, real-time inventory data, transaction order data, and the category of goods.

[0023] The core field semantic generation module is used to perform semantic analysis on the cargo attribute data, storage condition data, storage quantity data, real-time inventory data, transaction order data, and cargo category data of warehoused goods, and generate core field data of warehoused goods.

[0024] In one embodiment, the physical attributes of the stored goods include the weight of the goods, and the warehouse area dynamic update subsystem includes:

[0025] The cargo scheduling data prediction module is used to obtain historical order data and market demand data for warehouse goods of various categories, and generate cargo scheduling prediction data based on the historical order data and market demand data.

[0026] The inter-aisle dynamic update module is used to allocate the number of shelf layers of stored goods in each aisle based on the intelligent allocation scheme of inter-aisle storage space, combined with the weight of stored goods of each category, and generate an intelligent allocation scheme of inter-aisle storage space.

[0027] The channel layer dynamic update module is used to allocate the distance of each category of stored goods from the channel entrance in the same shelf layer of the same storage channel based on the intelligent allocation scheme of storage space between channels and between layers, combined with the turnover data of stored goods of each category of goods, and generate a preliminary storage space allocation scheme for each category of goods.

[0028] The rapid dispatch area management module is used to allocate rapid dispatch areas and static storage areas within the initial storage space allocation plan based on the cargo dispatch prediction data of each cargo category, and to generate an intelligent allocation plan for storage space within the channel.

[0029] In one embodiment, the fast dispatch area management module includes:

[0030] The rapid scheduling area space dynamic allocation component is used to allocate rapid scheduling areas and static storage areas within the initial storage space allocation plan based on the cargo scheduling prediction data of warehouse cargo for each cargo category.

[0031] The fast dispatch area cargo dispatch update component is used to monitor the cargo dispatch load parameters of the warehouse. If the cargo dispatch load parameters are lower than the preset cargo dispatch update threshold, the warehouse cargo in the fast dispatch area and static storage area of ​​each cargo category will be dispatched.

[0032] In one embodiment, the allocation of the rapid dispatch area includes a rapid shelving area and a rapid de-shelving area; the goods dispatch forecast data includes inbound forecast data and outbound forecast data; and the rapid dispatch area space dynamic allocation component includes:

[0033] The rapid shelving area space dynamic allocation unit is used to allocate rapid shelving areas within the initial storage space allocation plan based on the warehouse entry forecast data of warehouse goods of each goods category.

[0034] The rapid destocking area space dynamic allocation unit is used to allocate rapid destocking areas within the initial storage space allocation plan based on the outbound forecast data of warehouse goods for each category.

[0035] In one embodiment, the intelligent scheduling subsystem for warehouse goods includes:

[0036] The intelligent shelving module for warehouse goods is used to respond to the received goods entry instructions for a goods category and dispatch the goods of that category from the warehouse's goods entry area to the rapid shelving area.

[0037] The intelligent destocking module for warehouse goods is used to respond to the outbound instructions for a specific type of goods and dispatch the outbound goods of that type from the rapid destocking area to the outbound goods area of ​​the warehouse.

[0038] In one embodiment, the turnover data includes the stored duration, the goods scheduling update threshold includes a goods scheduling update threshold for fast-release areas and a goods scheduling update threshold for fast-de-release areas, and the fast-scheduling area goods scheduling update component includes:

[0039] The warehouse cargo scheduling load parameter monitoring unit is used to monitor the cargo scheduling load parameters of the warehouse.

[0040] The Quick Shelving Area Goods Scheduling Update Component is used to schedule warehouse goods in the Quick Shelving Area for each goods category to the corresponding static storage area if the goods scheduling load parameter is lower than the preset Quick Shelving Area Goods Scheduling Update Threshold.

[0041] The quick-release area goods scheduling update component is used to schedule warehouse goods in the static storage area of ​​each goods category to the corresponding quick-release area in descending order of storage time if the goods scheduling load parameter is lower than the preset quick-release area goods scheduling update threshold.

[0042] Secondly, this application also provides a warehouse intelligent management method based on big data, including:

[0043] Acquire multi-source warehousing data of stored goods and perform semantic extraction to obtain core field data of stored goods. The core field data is used to characterize the physical attributes, storage quantity, turnover data and goods category of stored goods.

[0044] Based on the core field data of the stored goods in the warehouse, storage space is allocated to different categories of goods, and an intelligent allocation scheme for storage space between storage channels in the warehouse is generated.

[0045] Obtain cargo scheduling forecast data for each category of goods in the warehouse, and based on the cargo scheduling forecast data and core field data, generate an intelligent allocation scheme for the storage space within each storage aisle of the warehouse.

[0046] Based on the intelligent allocation schemes for inter-channel and intra-channel storage space, the stored goods are intelligently scheduled.

[0047] The aforementioned intelligent warehouse management system and method based on big data, by acquiring multi-source data on stored goods and performing deep semantic extraction, can transform scattered multi-source data into core information including the physical attributes of goods, storage quantity, turnover data, and goods category, thereby improving the accuracy and rationality of the intelligent warehouse management system. In the space allocation between aisles, storage space between aisles is allocated to different categories of goods through core field data, which can improve the utilization rate of space between aisles, reduce the difficulty of goods handling, and improve the efficiency of warehousing operations. Dynamic planning and updating of space allocation within storage aisles can ensure that the space allocation within aisles can adapt to both the current storage status of goods and future scheduling needs, thereby reducing warehousing scheduling costs and improving the scheduling efficiency and capability of warehousing area management. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A schematic diagram of the structure of a big data-based intelligent warehouse management system provided in one embodiment of this application. Figure 1 ;

[0050] Figure 2 A schematic diagram of the structure of a big data-based intelligent warehouse management system provided in one embodiment of this application. Figure 2 ;

[0051] Figure 3 This is a flowchart illustrating a big data-based intelligent warehouse management method provided in one embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] In one embodiment, such as Figure 1 As shown, a warehouse intelligent management system 100 based on big data is provided, including:

[0054] Specifically, the multi-source warehouse data management subsystem 110 can be connected to the intelligent warehouse space allocation subsystem 120, the dynamic warehouse area update subsystem 130, and the intelligent warehouse cargo scheduling subsystem 140. The multi-source warehouse data management subsystem 110 can acquire multi-source warehouse data of warehouse cargo and perform semantic extraction to obtain the core field data of the warehouse cargo. The multi-source warehouse data management subsystem 110 can send the core field data of the warehouse cargo to the intelligent warehouse space allocation subsystem 120, the dynamic warehouse area update subsystem 130, and the intelligent warehouse cargo scheduling subsystem 140 via communication channels.

[0055] Optionally, core field data can be used to characterize the physical attributes of stored goods, storage quantity, turnover data, and goods category.

[0056] Specifically, the intelligent warehouse space allocation subsystem 120 can be connected to the multi-source warehouse data management subsystem 110 and the warehouse area dynamic update subsystem 130. The intelligent warehouse space allocation subsystem 120 can obtain the core field data of the stored goods dynamically managed by the multi-source warehouse data management subsystem 110 through a communication channel. Based on the core field data of the stored goods, the intelligent warehouse space allocation subsystem 120 can allocate storage space for different categories of goods, generating an intelligent allocation scheme for inter-channel storage space between warehouse aisles. The intelligent warehouse space allocation subsystem 120 can then send the generated intelligent allocation scheme for inter-channel storage space between warehouse aisles to the warehouse area dynamic update subsystem 130 through the communication channel.

[0057] Specifically, the warehouse area dynamic update subsystem 130 can be connected to the multi-source warehouse data management subsystem 110, the intelligent warehouse space allocation subsystem 120, and the intelligent warehouse cargo scheduling subsystem 140. The warehouse area dynamic update subsystem 130 can obtain core field data of the warehouse cargo dynamically managed by the multi-source warehouse data management subsystem 110 and the intelligent inter-channel storage space allocation scheme of the warehouse's various storage channels dynamically managed by the intelligent warehouse space allocation subsystem 120 through communication channels. The warehouse area dynamic update subsystem 130 can be used to obtain cargo scheduling prediction data for each category of warehouse cargo, and based on the cargo scheduling prediction data and core field data, combined with the inter-channel intelligent storage space allocation scheme, generate an intelligent intra-channel storage space allocation scheme for each storage channel within the warehouse. The warehouse area dynamic update subsystem 130 can send the generated intelligent intra-channel storage space allocation scheme for each storage channel within the warehouse to the intelligent warehouse cargo scheduling subsystem 140 through communication channels.

[0058] Optional, please refer to Figure 2The warehouse area dynamic update subsystem 130 may include a rapid dispatch area management module 134. The rapid dispatch area management module 134 can be used to allocate rapid dispatch areas and static storage areas within the preliminary warehouse space allocation plan based on the cargo dispatch prediction data of warehouse goods of each cargo category, and generate an intelligent allocation plan for warehouse space within the channel.

[0059] For further details, please refer to... Figure 2 The rapid dispatch area management module 134 may include: a rapid dispatch area space dynamic allocation component 231 and a rapid dispatch area goods dispatch update component 232. The rapid dispatch area space dynamic allocation component 231 can be used to allocate rapid dispatch areas and static storage areas within a preliminary storage space allocation plan based on the estimated goods dispatch data for each goods category. The rapid dispatch area goods dispatch update component 232 can be used to monitor the warehouse's goods dispatch load parameters; if the goods dispatch load parameters are lower than a preset goods dispatch update threshold, it can dispatch the stored goods in the rapid dispatch areas and static storage areas for each goods category.

[0060] Specifically, the intelligent warehouse cargo scheduling subsystem 140 can be connected to the multi-source warehouse data management subsystem 110 and the warehouse area dynamic update subsystem 130. The intelligent warehouse cargo scheduling subsystem 140 can obtain core field data of warehouse cargo dynamically managed by the multi-source warehouse data management subsystem 110 and intelligent allocation schemes for warehouse space within aisles dynamically managed by the warehouse area dynamic update subsystem 130 through communication channels. The intelligent warehouse cargo scheduling subsystem 140 can then be used to intelligently schedule warehouse cargo based on the intelligent allocation schemes for warehouse space between and within aisles, combined with the core field data of the warehouse cargo.

[0061] In the aforementioned intelligent warehouse management system based on big data, multi-source warehousing data acquisition and semantic extraction are used to comprehensively acquire multi-source warehousing data of stored goods and perform deep semantic extraction to form core field data representing the physical attributes, quantity, turnover data, and categories of stored goods, thus achieving structured management of warehousing big data. Through intelligent planning of warehousing space based on core field data, suitable warehousing space can be allocated for different types of goods, improving the utilization rate of aisle space resources, reducing the difficulty of goods handling, and improving warehousing operation efficiency. Through dynamic space updates that integrate cargo scheduling prediction data and core field data, the space allocation in each warehousing aisle can be dynamically adjusted based on the current status of goods and future scheduling trends, realizing dynamic allocation management of space within the aisles, improving the dynamic adaptability of warehousing space, thereby reducing warehousing scheduling costs and improving the scheduling efficiency and capability of warehousing management.

[0062] In an optional embodiment of this application, the physical properties of the stored goods may include the volume of the goods, please refer to... Figure 2 The intelligent warehouse space allocation subsystem 120 may include:

[0063] Specifically, the storage space allocation module 121 can be used to allocate the storage space size of each category of goods based on the volume of the goods in each category, and generate storage space allocation information for each category of goods.

[0064] Specifically, the warehouse space distribution and allocation module 122 can be used to allocate the warehouse space location of different categories of goods based on the warehouse space size allocation information and the turnover data of each category of goods, and generate an intelligent allocation scheme for the inter-channel warehouse space between the warehouse channels.

[0065] In an optional embodiment of this application, the turnover data may include historical outbound data and historical inbound data. Please refer to [reference needed]. Figure 2 The warehouse space distribution module 122 may include:

[0066] Specifically, the outbound correlation analysis component 221 can be used to calculate the outbound support, outbound confidence, outbound lift, and outbound time window transition probability between each goods category based on historical outbound data, and generate the outbound correlation degree between each goods category based on the weighted sum of the outbound support, outbound confidence, outbound lift, and outbound time window transition probability.

[0067] Specifically, the inbound association analysis component 222 can be used to calculate the inbound support, inbound confidence, inbound lift, and inbound time window transition probability between each goods category based on historical inbound data, and generate the inbound association degree between each goods category based on the weighted sum of the inbound support, inbound confidence, inbound lift, and inbound time window transition probability.

[0068] Specifically, the associated space allocation component 223 can be used to allocate the storage space location of warehouse goods of each category based on the outbound association degree and inbound association degree between each category of goods, and generate an intelligent allocation scheme for inter-channel storage space between each storage channel of the warehouse.

[0069] Optionally, the expressions for outbound correlation and inbound correlation can be:

[0070]

[0071]

[0072] In the formula, and The first Class of goods and the first The correlation between outbound and inbound goods categories , , and The first Class of goods and the first Outbound support, outbound confidence, outbound lift, and outbound time window shift probability among different categories of goods. , , and The first Class of goods and the first The weights for outbound support, outbound confidence, outbound lift, and outbound time window transition probability are calculated based on the outbound support among different goods categories. , , and The first Class of goods and the first Inbound support, inbound confidence, inbound lift, and inbound time window shift probability among different categories of goods. , , and The first Class of goods and the first The weights for inbound support, inbound confidence, inbound lift, and inbound time window transition probability are calculated among different categories of goods.

[0073] Indicatively, Inbound Support (IS) is the number of consecutive data points in historical inbound data. Class of goods and the first The frequency at which goods of the same category are simultaneously received into the warehouse; Inbound Confidence (IC), which is the percentage of warehouse goods of the same category that are known to be received in historical inbound data. When goods of a certain category are received into the warehouse, the first The conditional probability that warehouse goods of the same category are also received into the warehouse; Inbound Lift (IL), which is the probability that, in historical inbound data, the th... Class of goods and the first The ratio of the actual probability of two goods of the same category being simultaneously stored to the probability of them being stored independently can be used to eliminate interference from the base frequency; the inbound transition probability (ITP) is the probability that, within a specified time window, the first... Goods of the first category are first put into storage, and then the second category is... The probability that goods of a certain category will subsequently be stored in the warehouse.

[0074] To illustrate, Outbound Support (OS) is the percentage of outbound data in historical outbound data. Class of goods and the first The frequency with which warehouse goods of the same category are simultaneously dispatched; Outbound Confidence (OC), which is the probability that, in historical outbound data, the first known outbound item is the most likely to be dispatched. When warehouse goods of a certain category are released from storage, the first The conditional probability that warehouse goods of a certain category will also be shipped out; Outbound Lift (OL), is the probability that, in historical outbound data, the first... Class of goods and the first The ratio of the actual probability of simultaneous outbound shipments of goods of the same category to the probability of independent outbound shipments of the two can be used to eliminate interference from the base frequency; the outbound transition probability (OTP) is the probability that, within a specified time window, the first outbound shipment will be outbound from the warehouse at the same time. Goods of the first category are shipped out first, then the second category... The probability that a category of stored goods will subsequently be released from the warehouse.

[0075] In an optional embodiment of this application, please refer to Figure 2 The multi-source warehouse data management subsystem 110 may include:

[0076] Specifically, the multi-source warehousing data acquisition module 111 can be used to acquire cargo attribute data, warehousing quantity data, real-time inventory data, transaction order data, and cargo category data of warehoused goods.

[0077] Specifically, the core field semantic generation module 112 can be used to perform semantic analysis on the cargo attribute data, warehousing condition data, warehousing quantity data, real-time inventory data, transaction order data and cargo category data of warehoused goods, and generate core field data of warehoused goods.

[0078] In an optional embodiment of this application, the physical properties of the stored goods may include the weight of the goods, please refer to... Figure 2 The warehouse area dynamic update subsystem 130 may include:

[0079] Specifically, the cargo scheduling data prediction module 131 can be used to obtain historical order data and market demand data for warehouse goods of various cargo categories, and generate cargo scheduling prediction data based on the historical order data and market demand data.

[0080] Specifically, the inter-channel dynamic update module 132 can be used to allocate the number of shelf layers of stored goods in each channel based on the intelligent allocation scheme of inter-channel storage space, combined with the weight of stored goods of each category, and generate an intelligent allocation scheme of inter-channel storage space.

[0081] Specifically, the dynamic update module 133 within the channel layer can be used to allocate the distance between the storage space of each category of goods and the channel entrance of the same shelf layer in the same storage channel based on the intelligent allocation scheme of storage space between channels and the intelligent allocation scheme of storage space between layers, combined with the turnover data of the stored goods of each category of goods, and generate a preliminary storage space allocation scheme for the stored goods of each category of goods.

[0082] Specifically, the rapid dispatch area management module 134 can be used to allocate rapid dispatch areas and static storage areas within the preliminary storage space allocation scheme based on the cargo dispatch prediction data of each cargo category, and generate an intelligent allocation scheme for storage space within the channel.

[0083] In an optional embodiment of this application, please refer to Figure 2 The fast dispatch area management module 134 may include:

[0084] Specifically, the rapid scheduling area space dynamic allocation component 231 can be used to allocate rapid scheduling areas and static storage areas within the initial storage space allocation scheme based on the cargo scheduling prediction data of warehouse cargo of each cargo category.

[0085] Specifically, the fast dispatch area goods dispatch update component 232 can be used to monitor the goods dispatch load parameters of the warehouse. If the goods dispatch load parameters are lower than the preset goods dispatch update threshold, the warehouse goods in the fast dispatch area and static storage area of ​​each goods category can be dispatched.

[0086] In an optional embodiment of this application, the allocation of the rapid dispatch area may include a rapid shelving area and a rapid de-shelving area, the cargo dispatch forecast data may include inbound forecast data and outbound forecast data, and the rapid dispatch area space dynamic allocation component 231 may include:

[0087] Specifically, the rapid shelving area space dynamic allocation unit can be used to allocate rapid shelving areas within the initial storage space allocation plan based on the warehouse entry forecast data of warehouse goods of each category.

[0088] Specifically, the rapid destocking area space dynamic allocation unit can be used to allocate rapid destocking areas within the initial storage space allocation plan based on outbound forecast data of warehouse goods for each category.

[0089] In an optional embodiment of this application, please refer to Figure 2 The intelligent dispatching subsystem for warehouse goods 140 may include:

[0090] Specifically, the intelligent shelving module 111 can be used to respond to a goods entry instruction for a goods category and dispatch the goods of that category from the goods entry area of ​​the warehouse to the rapid shelving area.

[0091] Specifically, the intelligent destocking module 112 can be used to respond to a goods outbound instruction for a goods category and dispatch the outbound goods of that goods category from the rapid destocking area to the outbound goods area of ​​the warehouse.

[0092] In an optional embodiment of this application, the turnover data may include the storage duration, the goods scheduling update threshold may include a goods scheduling update threshold for fast-to-shelf areas and a goods scheduling update threshold for fast-to-de-shelf areas, and the fast-scheduling area goods scheduling update component 232 may include:

[0093] Specifically, the warehouse cargo scheduling load parameter monitoring unit can be used to monitor the cargo scheduling load parameters of the warehouse.

[0094] Specifically, the quick-listing area goods scheduling update component can be used to schedule warehouse goods in the quick-listing area of ​​each goods category to the corresponding static storage area if the goods scheduling load parameter is lower than the preset quick-listing area goods scheduling update threshold.

[0095] Specifically, the quick-release area goods scheduling update component can be used to schedule warehouse goods in the static storage area of ​​each goods category to the corresponding quick-release area in descending order of storage time if the goods scheduling load parameter is lower than the preset quick-release area goods scheduling update threshold.

[0096] As an illustration, the quick delisting area goods scheduling update component can prioritize the scheduling of the longest-stored goods in each goods category from the static storage area to the corresponding quick delisting area.

[0097] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0098] Based on the same inventive concept, this application also provides a big data-based intelligent warehouse management method for implementing the aforementioned big data-based intelligent warehouse management system. The solution provided by this method is similar to the implementation scheme described in the above system. Therefore, the specific limitations of one or more embodiments of the big data-based intelligent warehouse management method provided below can be found in the limitations of the big data-based intelligent warehouse management system described above, and will not be repeated here.

[0099] In one exemplary embodiment of this application, such as Figure 3 As shown, a method for intelligent warehouse management based on big data is provided. This embodiment illustrates the application of this method to a warehouse management terminal. It is understood that this method can also be applied to a warehouse management server, and further to a warehouse management system including both a warehouse management terminal and a warehouse management server, and is implemented through the interaction between the warehouse management terminal and the warehouse management server. In this embodiment, the method may include the following steps:

[0100] Step S301: Obtain multi-source warehousing data of stored goods and perform semantic extraction to obtain the core field data of stored goods.

[0101] Optionally, core field data can be used to characterize the physical attributes of stored goods, storage quantity, turnover data, and goods category.

[0102] Step S302: Based on the core field data of the stored goods in the warehouse, allocate storage space for different categories of goods and generate an intelligent allocation scheme for inter-channel storage space between the warehouse's various storage channels.

[0103] Step S303: Obtain cargo scheduling forecast data for each category of goods, and based on the cargo scheduling forecast data and core field data, generate an intelligent allocation scheme for storage space within each storage aisle of the warehouse.

[0104] Step S304: Based on the intelligent allocation scheme for inter-channel storage space and the intelligent allocation scheme for intra-channel storage space, intelligent scheduling of stored goods is carried out.

[0105] In an optional embodiment of this application, the physical attributes of the stored goods may include the volume of the goods. Step S302, based on the core field data of the stored goods in the warehouse, allocates storage space for different categories of goods and generates an intelligent allocation scheme for inter-channel storage space between the various storage channels of the warehouse. This may further include:

[0106] Specifically, the warehouse management terminal can allocate storage space for each category of goods based on the volume of the goods, and generate storage space allocation information for each category of goods.

[0107] Specifically, the warehouse management terminal can allocate storage space locations for different categories of goods based on the storage space size allocation information and turnover data of each category of goods, and generate an intelligent allocation scheme for storage space between different storage channels in the warehouse.

[0108] In an optional embodiment of this application, based on the storage space allocation information of each category of goods and the turnover data of each category of goods, storage space locations for different categories of goods are allocated, generating an intelligent allocation scheme for inter-aisle storage space between storage aisles in the warehouse, which may include:

[0109] Specifically, the warehouse management terminal can calculate the outbound support, outbound confidence, outbound lift, and outbound time window transition probability among each goods category based on historical outbound data, and generate the outbound correlation degree among each goods category based on the weighted sum of the outbound support, outbound confidence, outbound lift, and outbound time window transition probability.

[0110] Specifically, the warehouse management terminal can calculate the inbound support, inbound confidence, inbound lift, and inbound time window transition probability of each goods category based on historical inbound data, and generate the inbound correlation degree between each goods category based on the weighted sum of the inbound support, inbound confidence, inbound lift, and inbound time window transition probability.

[0111] Specifically, the warehouse management terminal can allocate the storage space location of warehouse goods of each category based on the outbound and inbound correlation between each category of goods, and generate an intelligent allocation scheme for the storage space between each storage channel of the warehouse.

[0112] In an optional embodiment of this application, step S301, acquiring multi-source warehousing data of stored goods and performing semantic extraction to obtain core field data of the stored goods, may further include:

[0113] Specifically, the warehouse management terminal can obtain data on the attributes of stored goods, the quantity of stored goods, real-time inventory data, transaction order data, and the category of goods.

[0114] Specifically, the warehouse management terminal can perform semantic analysis on the cargo attribute data, storage condition data, storage quantity data, real-time inventory data, transaction order data, and cargo category data of stored goods to generate core field data of stored goods.

[0115] In an optional embodiment of this application, the physical attributes of the stored goods may include the weight of the goods. Step S303 involves obtaining estimated cargo scheduling data for each category of stored goods, and generating an intelligent allocation scheme for storage space within each storage aisle of the warehouse based on the estimated cargo scheduling data and core field data. This may further include:

[0116] Specifically, the warehouse management terminal can obtain historical order data and market demand data for warehouse goods of various categories, and generate cargo scheduling forecast data based on the historical order data and market demand data.

[0117] Specifically, the warehouse management terminal can allocate the number of shelf layers for stored goods in each aisle based on the intelligent allocation scheme for storage space between aisles, combined with the weight of stored goods of each category, and generate an intelligent allocation scheme for storage space between layers.

[0118] Specifically, the warehouse management terminal can, based on the intelligent allocation schemes for storage space between aisles and between floors, and combined with the turnover data of stored goods of each category, allocate the distance of stored goods of each category from the aisle entrance within the same shelf layer of the same storage aisle, and generate a preliminary storage space allocation scheme for each category of stored goods.

[0119] Specifically, the warehouse management terminal can allocate rapid dispatch areas and static storage areas within the initial warehouse space allocation plan based on the cargo scheduling forecast data of warehouse goods of each cargo category, and generate an intelligent allocation plan for warehouse space within the channel.

[0120] In an optional embodiment of this application, based on the estimated cargo scheduling data of warehouse goods for each cargo category, a rapid scheduling area and a static storage area are allocated within the preliminary warehouse space allocation scheme to generate an intelligent warehouse space allocation scheme within the channel. This may further include:

[0121] Specifically, the warehouse management terminal can allocate rapid dispatch areas and static storage areas within the initial warehouse space allocation plan based on the cargo dispatch forecast data of each cargo category.

[0122] Specifically, the warehouse management terminal can monitor the warehouse's cargo scheduling load parameters. If the cargo scheduling load parameters are lower than the preset cargo scheduling update threshold, it can schedule the stored goods in the fast scheduling area and static storage area of ​​each cargo category.

[0123] In an optional embodiment of this application, allocating a rapid dispatch area may include a rapid shelving area and a rapid descrambling area. The cargo dispatch forecast data may include inbound forecast data and outbound forecast data. Based on the cargo dispatch forecast data for each category of stored goods, the rapid dispatch area and static storage area are allocated within the initial storage space allocation scheme. This may further include:

[0124] Specifically, the warehouse management terminal can allocate rapid shelving areas within the initial warehouse space allocation plan based on the inbound forecast data of warehouse goods for each category.

[0125] Specifically, the warehouse management terminal can allocate rapid destocking areas within the initial warehouse space allocation plan based on outbound forecast data for warehouse goods of each category.

[0126] In an optional embodiment of this application, step S304, which involves intelligently scheduling stored goods based on the intelligent allocation schemes for inter-channel storage space and intra-channel storage space, may further include:

[0127] Specifically, the warehouse management terminal can respond to the receiving instruction for goods of a certain category by dispatching the goods of that category from the goods receiving area of ​​the warehouse to the fast shelving area.

[0128] Specifically, the warehouse management terminal can respond to the outbound instructions for a specific category of goods by dispatching the outbound goods from the quick-removal area to the outbound area of ​​the warehouse.

[0129] In an optional embodiment of this application, the turnover data may include the storage duration, and the goods scheduling update threshold may include a goods scheduling update threshold for the fast-listing area and a goods scheduling update threshold for the fast-delisting area. Monitoring the warehouse's goods scheduling load parameters, if the goods scheduling load parameters are lower than a preset goods scheduling update threshold, scheduling the stored goods in the fast scheduling area and static storage area for each goods category may include:

[0130] Specifically, the warehouse management terminal can monitor the warehouse's cargo scheduling load parameters.

[0131] Specifically, if the cargo scheduling load parameter is lower than the preset cargo scheduling update threshold for the fast-listing area, the warehouse management terminal can schedule the warehouse cargo in the fast-listing area of ​​each cargo category to the corresponding static storage area.

[0132] Specifically, if the cargo scheduling load parameter is lower than the preset cargo scheduling update threshold for the fast delisting area, the warehouse management terminal can schedule the warehouse cargo in the static storage area of ​​each cargo category to the corresponding fast delisting area in descending order of storage time.

[0133] As an illustration, the warehouse management terminal can prioritize the transfer of the longest-stored goods of each category from the static storage area to the corresponding fast-release area.

[0134] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described intelligent warehouse management method based on big data.

[0135] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0136] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0137] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A warehouse intelligent management system based on big data, characterized in that, The system includes: The multi-source warehousing data management subsystem is used to acquire multi-source warehousing data of stored goods and perform semantic extraction to obtain the core field data of the stored goods. The core field data is used to characterize the physical attributes, storage quantity, turnover data and goods category of the stored goods. The intelligent storage space allocation subsystem is used to allocate storage space for different categories of goods based on the core field data of the stored goods in the warehouse, and generate an intelligent allocation scheme for inter-channel storage space between the various storage channels of the warehouse. The warehouse area dynamic update subsystem is used to obtain cargo scheduling prediction data for the warehouse cargo of each cargo category, and generate an intelligent allocation scheme for the storage space in each storage channel of the warehouse based on the cargo scheduling prediction data and the core field data. The intelligent scheduling subsystem for warehouse goods is used to intelligently schedule the warehouse goods based on the intelligent allocation scheme for warehouse space between channels and the intelligent allocation scheme for warehouse space within channels.

2. The system according to claim 1, characterized in that, The physical attributes of the stored goods include the volume of the goods, and the intelligent storage space allocation subsystem includes: The storage space allocation module is used to allocate the storage space size of the stored goods for each category of goods based on the volume of the stored goods for each category of goods, and generate storage space allocation information for the stored goods for each category of goods. The storage space distribution and allocation module is used to allocate storage space locations for different categories of goods based on the storage space size allocation information of the stored goods for each category and the turnover data of the stored goods for each category, and to generate an intelligent allocation scheme for inter-channel storage space between the storage channels of the warehouse.

3. The system according to claim 2, characterized in that, The turnover data includes historical outbound data and historical inbound data. The warehouse space distribution and allocation module includes: The outbound correlation analysis component is used to calculate the outbound support, outbound confidence, outbound lift, and outbound time window transition probability among the goods categories based on the historical outbound data, and to generate the outbound correlation degree among the goods categories based on the weighted sum of the outbound support, outbound confidence, outbound lift, and outbound time window transition probability. The inbound correlation analysis component is used to calculate the inbound support, inbound confidence, inbound lift, and inbound time window transition probability among the goods categories based on the historical inbound data, and to generate the inbound correlation degree among the goods categories based on the weighted sum of the inbound support, the inbound confidence, the inbound lift, and the inbound time window transition probability. An associated space allocation component is used to allocate the storage space location of the stored goods of each of the goods categories based on the outbound association degree and the inbound association degree between each of the goods categories, and to generate an intelligent allocation scheme for the inter-channel storage space between each of the storage channels of the warehouse. The expressions for the outbound correlation degree and the inbound correlation degree are as follows: In the formula, and The first The categories of goods described in the class and the first The outbound correlation and the inbound correlation between the categories of goods are described. , , and The first The categories of goods described in the class and the first The outbound support, outbound confidence, outbound lift, and outbound time window transition probability among the aforementioned goods categories. , , and The first The categories of goods described in the class and the first The weights for the outbound support, outbound confidence, outbound lift, and outbound time window transition probability among the aforementioned goods categories. , , and The first The categories of goods described in the class and the first The inbound support, inbound confidence, inbound lift, and inbound time window transition probability among the aforementioned goods categories. , , and The first The categories of goods described in the class and the first The weights of the inbound support, inbound confidence, inbound lift, and inbound time window transition probability among the categories of goods are: inbound support weight, inbound confidence weight, inbound lift weight, and inbound time window transition probability weight.

4. The system according to claim 1, characterized in that, The multi-source warehouse data management subsystem includes: The multi-source warehousing data acquisition module is used to acquire the cargo attribute data, warehousing quantity data, real-time inventory data, transaction order data, and cargo category data of the warehoused goods; The core field semantic generation module is used to perform semantic analysis on the cargo attribute data, storage condition data, storage quantity data, real-time inventory data, transaction order data and cargo category data of the stored goods, and generate the core field data of the stored goods.

5. The system according to any one of claims 1 to 4, characterized in that, The physical attributes of the stored goods include the weight of the goods, and the dynamic update subsystem for the storage area includes: The cargo scheduling data prediction module is used to obtain historical order data and market demand data of the warehoused goods for each of the cargo categories, and generate cargo scheduling prediction data based on the historical order data and the market demand data. The inter-channel dynamic update module is used to allocate the number of shelf layers of the stored goods in each channel based on the intelligent allocation scheme for inter-channel storage space, combined with the weight of the stored goods in each category of goods, and generate an intelligent allocation scheme for inter-channel storage space. The channel layer dynamic update module is used to allocate the distance of the stored goods of each category of goods from the channel entrance in the same shelf layer of the same storage channel based on the intelligent allocation scheme of storage space between channels and the intelligent allocation scheme of storage space between layers, combined with the turnover data of the stored goods of each category of goods, and generate a preliminary storage space allocation scheme for the stored goods of each category of goods. The rapid dispatch area management module is used to allocate rapid dispatch areas and static storage areas within the preliminary storage space allocation scheme based on the estimated dispatch data of the stored goods for each of the aforementioned goods categories, and to generate an intelligent allocation scheme for storage space within the channel.

6. The system according to claim 5, characterized in that, The rapid dispatch area management module includes: A rapid scheduling area space dynamic allocation component is used to allocate rapid scheduling areas and static storage areas within the preliminary storage space allocation scheme based on the cargo scheduling prediction data of the stored goods for each of the cargo categories. The fast dispatch area cargo dispatch update component is used to monitor the cargo dispatch load parameters of the warehouse. If the cargo dispatch load parameters are lower than the preset cargo dispatch update threshold, the stored goods in the fast dispatch area and the static storage area of ​​each cargo category are dispatched.

7. The system according to claim 6, characterized in that, The rapidly allocated scheduling area includes a rapidly shelving area and a rapidly de-shelving area; the cargo scheduling forecast data includes inbound forecast data and outbound forecast data; and the rapidly allocated scheduling area space dynamic allocation component includes: A rapid shelving area space dynamic allocation unit is used to allocate the rapid shelving area within the preliminary storage space allocation scheme based on the inbound prediction data of the stored goods for each of the aforementioned goods categories. A rapid destocking area space dynamic allocation unit is used to allocate the rapid destocking area within the preliminary storage space allocation scheme based on the outbound prediction data of the stored goods for each of the aforementioned goods categories.

8. The system according to claim 7, characterized in that, The intelligent dispatching subsystem for warehouse goods includes: The intelligent shelving module for warehouse goods is used to respond to receiving a goods entry instruction for the goods category and dispatch the goods of the goods category from the goods entry area of ​​the warehouse to the rapid shelving area; The intelligent destocking module for warehouse goods is used to respond to the receipt of a goods outbound instruction for the goods category and dispatch the outbound goods of the goods category from the rapid destocking area to the goods outbound area of ​​the warehouse.

9. The system according to claim 7, characterized in that, The turnover data includes the storage duration, the goods scheduling update threshold includes the goods scheduling update threshold for the fast-release area and the goods scheduling update threshold for the fast-de-release area, and the goods scheduling update component for the fast-schedule area includes: A warehouse cargo scheduling load parameter monitoring unit is used to monitor the cargo scheduling load parameters of the warehouse. A fast-listing area goods scheduling update component is used to schedule the warehouse goods in the fast-listing area of ​​each goods category to the corresponding static storage area if the goods scheduling load parameter is lower than the preset fast-listing area goods scheduling update threshold. The fast-delisting area goods scheduling update component is used to schedule the warehouse goods in the static storage area of ​​each goods category to the corresponding fast-listing area in descending order of the stored time if the goods scheduling load parameter is lower than the preset fast-delisting area goods scheduling update threshold.

10. A warehouse intelligent management method based on big data, characterized in that, The method includes: Multi-source warehousing data of stored goods is acquired and semantic extraction is performed to obtain the core field data of the stored goods. The core field data is used to characterize the physical attributes, storage quantity, turnover data and goods category of the stored goods. Based on the core field data of the stored goods in the warehouse, storage space is allocated for the stored goods of different categories, and an intelligent allocation scheme for inter-channel storage space between the various storage channels of the warehouse is generated. Obtain cargo scheduling prediction data for the warehouse cargo of each cargo category, and based on the cargo scheduling prediction data and the core field data, generate an intelligent allocation scheme for the storage space in each storage channel of the warehouse. Based on the intelligent allocation scheme for inter-channel storage space and the intelligent allocation scheme for intra-channel storage space, the stored goods are intelligently scheduled.

Images