Warehouse goods allocation optimization configuration method based on goods demand prediction

Abstract

The invention discloses a storage goods allocation optimization configuration method based on goods demand prediction, and relates to the technical field of intelligent storage, and the method comprises the steps: receiving storage request information; performing environment positive sample retrieval to obtain cargo storage environment requirements; performing size positive sample retrieval to obtain a cargo storage size demand; based on the storage cargo starting point position, the cargo storage size requirement and the storage cargo allocation number requirement, optimizing storage idle cargo allocations to obtain a storage selected cargo allocation list; and after warehousing transportation is carried out according to the warehousing selected goods allocation list, goods allocation environment distributed configuration is carried out according to goods warehousing environment requirements. The technical problems that in the prior art, a traditional warehousing operation method generally configures warehousing requirements according to experience, the automation degree is low, the warehousing efficiency is poor, and the carrying cost is high are solved, and the technical effects that the warehousing goods allocation is optimally configured based on the warehousing goods requirements, the warehousing operation efficiency is improved, and the carrying cost is reduced are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent warehousing technology, and in particular to a method for optimizing the configuration of warehousing cargo spaces based on cargo demand forecasting. Background Art

[0002] With the rapid development of the logistics industry, warehouse management has become increasingly complex and important. In order to improve warehouse storage efficiency, reduce operating costs and improve customer satisfaction, warehouse storage space configuration has become a key link. Through reasonable storage space configuration, warehouse space utilization can be optimized, cargo storage and retrieval efficiency can be improved, and the risk of cargo damage and loss can be reduced.

[0003] Traditional warehouse storage space allocation is often based on fixed rules or manual experience, which is difficult to adjust dynamically, resulting in low utilization of storage space and affecting storage efficiency. In addition, traditional storage space configuration tends to ignore the optimization of transportation paths, resulting in unnecessary transportation costs when goods enter the warehouse. Summary of the invention

[0004] The present application provides a method for optimizing the configuration of storage cargo spaces based on cargo demand forecasting, which is used to solve the technical problem that traditional warehousing operation methods in the prior art usually configure warehousing demand based on experience, have a low degree of automation, and result in poor warehousing efficiency and high handling costs.

[0005] The present application provides a method for optimizing the configuration of storage cargo spaces based on cargo demand prediction, the method comprising: receiving storage request information, wherein the storage request information comprises the storage cargo model, the storage cargo quantity and the storage cargo starting point; performing positive sample retrieval on the storage cargo model to obtain the cargo storage environment requirement; performing positive sample retrieval on the storage cargo model to obtain the cargo storage size requirement; setting the storage cargo space quantity requirement according to the storage cargo quantity; optimizing idle storage spaces based on the storage cargo starting point, the cargo storage size requirement and the storage cargo space quantity requirement to obtain a storage selected cargo space list; after the storage cargo is transported into the warehouse according to the storage selected cargo space list, performing distributed configuration of the storage space environment for the storage selected cargo space list according to the cargo storage environment requirement.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method for optimizing the configuration of storage cargo spaces based on cargo demand prediction provided by the present application relates to the field of intelligent warehousing technology. Through warehousing request information, cargo storage environment requirements and cargo storage size requirements are retrieved. Based on the starting position of the stored cargo, the cargo storage size requirements and the number of storage cargo spaces, idle storage spaces are optimized, a list of selected storage spaces is obtained for warehousing transportation, and distributed configuration of the storage space environment is performed according to the cargo storage environment requirements. The method solves the technical problem that the traditional warehousing operation method in the prior art usually configures warehousing requirements based on experience, has a low degree of automation, and leads to poor warehousing efficiency and high transportation costs. The method realizes the technical effect of optimizing the configuration of storage cargo spaces based on the storage cargo demand, improving the warehousing operation efficiency and reducing the transportation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0008] Figure 1 A schematic diagram of a flow chart of a method for optimizing storage space allocation based on cargo demand forecasting provided in an embodiment of the present application; Figure 2 A schematic diagram of a process for obtaining cargo storage environment requirements in a method for optimizing storage space configuration based on cargo demand forecasting provided in an embodiment of the present application; Figure 3 A schematic diagram of a process for optimizing idle warehouse cargo spaces and obtaining a list of selected warehouse cargo spaces in a method for optimizing warehouse cargo space configuration based on cargo demand forecasting provided in an embodiment of the present application. DETAILED DESCRIPTION

[0009] The present application provides a method for optimizing the configuration of storage cargo spaces based on cargo demand forecasting, which is used to solve the technical problem that traditional warehousing operation methods in the prior art usually configure warehousing demand based on experience, have a low degree of automation, and result in poor warehousing efficiency and high handling costs.

[0010] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0011] It should be noted that the terms "first", "second", etc. in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0012] like Figure 1 As shown, the present application provides a method for optimizing storage space configuration based on cargo demand forecasting, the method comprising: P10: receiving storage request information, wherein the storage request information includes the storage goods model, storage goods quantity and storage goods starting point location.

[0013] Specifically, first, storage request information is received, which is usually input by the warehouse management system or the user end. The storage request information contains key cargo information fields, including the storage cargo model, storage cargo quantity and storage cargo starting point. Among them, the storage cargo model refers to the identifier of the cargo to be stored, which can be the specific model or category number of the product. The system retrieves the properties and requirements of this type of cargo through the cargo model, including size, environmental requirements, etc. This information will directly affect the subsequent cargo space configuration and transportation planning. The storage cargo quantity is the number of cargo that actually needs to be stored. The quantity information not only determines how many storage cargo spaces the system needs to reserve for this type of cargo, but also affects the resource allocation (such as manpower, mechanical equipment, etc.) during transportation and the estimation of warehousing time. The storage cargo starting point refers to the current location or source of the cargo, which is crucial for optimizing the warehousing path and reducing the transportation time. By obtaining the starting point, the system can select the optimal path for transportation operations in combination with the logistics information inside or outside the warehouse to improve overall efficiency.

[0014] P20: Perform environmental positive sample retrieval on the warehouse goods model to obtain the goods storage environment requirements.

[0015] Further, such as Figure 2 As shown, step P20 of the embodiment of the present application also includes: P21: Perform storage environment positive sample retrieval based on the stored goods model to obtain the first environmental indicator sample data set until the Nth environmental indicator sample data set; P22: Perform central trend analysis on the first environmental indicator sample data set to obtain the first environmental indicator demand interval; P23: Perform central trend analysis on the Nth environmental indicator sample data set to obtain the Nth environmental indicator demand interval; P24: Add the first environmental indicator demand interval until the Nth environmental indicator demand interval into the cargo storage environment demand.

[0016] It should be understood that the environmental positive sample retrieval is performed on the storage goods model to obtain the environmental requirements of the goods during the storage process. This process mainly predicts and extracts the best storage environment conditions suitable for the goods through comparative analysis of historical data and environmental positive samples.

[0017] First, a positive sample retrieval of the storage environment is performed based on the storage cargo model. Positive sample retrieval refers to extracting the environmental conditions of the cargo when it is stored by analyzing the storage history data of similar cargo in similar environments. The retrieval results will generate a first environmental indicator sample data set to an Nth environmental indicator sample data set, which covers different environmental indicators such as temperature, humidity, light, and vibration.

[0018] For each environmental indicator (such as temperature or humidity), a central tendency analysis is performed on the first environmental indicator sample data set. Central tendency analysis is a technique in statistics that is used to analyze the common or most likely values ​​of a set of data. For example, in multiple warehousing instances, the system may find that the optimal temperature range for storing a certain type of goods is concentrated between 15°C and 20°C. Through this analysis, the first environmental indicator requirement interval can be obtained, that is, the temperature range required for the goods. Similarly, a central tendency analysis is performed on the Nth environmental indicator sample data set to analyze the requirements of other environmental factors (such as humidity) and obtain the corresponding Nth environmental indicator requirement interval.

[0019] Finally, the analysis results from the first environmental indicator demand interval to the Nth environmental indicator demand interval are integrated to form a complete cargo storage environment demand. This demand provides an environmental basis for the subsequent storage space allocation to ensure that the cargo will not be adversely affected by the environment during storage.

[0020] Furthermore, step P22 of the embodiment of the present application also includes: P22-1: According to the first environmental indicator deviation threshold, cluster analysis is performed on the first environmental indicator sample data set to obtain the environmental indicator clustering result; P22-2: Calculate the ratio of the number of clusters of the environmental indicator clustering result to the number of samples of the first environmental indicator sample data set, and set it as the first environmental indicator discreteness; P22-3: When the first environmental indicator discreteness is greater than or equal to the environmental indicator discreteness threshold, delete the first environmental indicator; P22-4: When the first environmental indicator discreteness is less than the environmental indicator discreteness threshold, perform environmental indicator concentration trend analysis on the first environmental indicator sample data set to obtain the first environmental indicator demand range.

[0021] Optionally, the specific process of performing central tendency analysis on the first environmental indicator sample data set may be, first, performing cluster analysis on the first environmental indicator sample data set according to a preset first environmental indicator deviation threshold. Cluster analysis is an unsupervised learning method that groups samples in a data set according to similarity or distance to form multiple clusters. In this example, the first environmental indicator deviation threshold defines the boundary of similarity between samples, and is used to identify sample groups that have similar or small differences in environmental indicators. This step can use clustering algorithms such as K-means and DBSCAN to automatically divide samples into several clusters, providing a basis for subsequent analysis.

[0022] Next, the ratio of the number of clusters of the environmental indicator clustering results to the number of samples in the first environmental indicator sample data set is calculated. This ratio is defined as the first environmental indicator dispersion. Dispersion is an indicator to measure the breadth of data distribution. A higher dispersion indicates that the data distribution range is wider and may contain multiple different environmental condition patterns, while a lower dispersion indicates that the data is relatively concentrated and the environmental conditions are relatively uniform. By calculating the dispersion, the importance and stability of the environmental indicator for cargo storage are preliminarily evaluated.

[0023] Then, the first environmental indicator dispersion is compared with the environmental indicator dispersion threshold. If the first environmental indicator dispersion is greater than or equal to the environmental indicator dispersion threshold, it means that the environmental indicator shows large differences and instability in different samples, and may not be suitable as a basis for judging storage environment requirements. Therefore, it is regarded as an unimportant or unstable environmental indicator and is deleted to avoid interference with subsequent decisions.

[0024] Finally, if the first environmental indicator dispersion is less than the environmental indicator dispersion threshold, the environmental indicator is considered stable and important, and its central trend needs to be further analyzed. The first environmental indicator sample data set is subjected to an environmental indicator central trend analysis. The commonly used methods include calculating statistics such as the mean, median, or mode to obtain the first environmental indicator demand range. This range represents the range of environmental conditions that meet the storage needs of goods and is an important basis for subsequent storage environment settings and regulation.

[0025] P30: Perform size positive sample retrieval on the warehouse cargo model to obtain cargo storage size requirements.

[0026] Furthermore, step P30 of the embodiment of the present application further includes: P31: Perform storage size positive sample retrieval based on the stored goods model to obtain the warehouse height sample data set, the warehouse length sample data set and the warehouse width sample data set; P32: Perform central trend analysis on the warehouse height sample data set to obtain the warehouse height requirement interval; P33: Perform central trend analysis on the warehouse length sample data set to obtain the warehouse length requirement interval; P34: Perform central trend analysis on the warehouse width sample data set to obtain the warehouse width requirement interval; P35: Add the warehouse height requirement interval, the warehouse length requirement interval and the warehouse width requirement interval to the cargo storage size requirements.

[0027] It should be understood that the size positive sample retrieval is performed on the storage goods model to obtain the storage size requirements of the goods, ensuring that the goods can be reasonably stored in the storage space that meets the size requirements, avoiding waste of storage space or damage to the goods.

[0028] First, the positive sample of storage size is retrieved based on the storage cargo model. The "positive sample" here refers to the known and verified warehouse size data suitable for the storage of the cargo model. The system obtains the warehouse height sample data set, warehouse length sample data set, and warehouse width sample data set that match the cargo model by querying the database or calling the relevant API. These data sets are the basis for subsequent analysis and reflect the range of warehouse sizes required for the cargo under different storage conditions.

[0029] Next, the central tendency analysis is performed on the sample data sets of warehouse height, warehouse length and warehouse width respectively. Central tendency analysis is a statistical method used to describe the central position or average level of data distribution. In this case, the system can use statistics such as mean, median or mode to process the sample data sets of warehouse height, length and width to obtain their respective demand intervals. These demand intervals not only reflect the minimum and maximum size restrictions required for cargo storage, but also provide warehouse managers with clear guidance on the selection of warehouse size.

[0030] Specifically, we first analyze the warehouse height sample data set, that is, analyze the common height requirements in the data set. By analyzing the storage height data of similar goods stored in the past, we identify the height range suitable for current goods storage and obtain the warehouse height requirement range. Similarly, we perform a central trend analysis on the warehouse length sample data set to obtain the warehouse length requirement range to ensure that the stored goods have enough storage space in length and are not restricted by length constraints. Finally, we perform a central trend analysis on the warehouse width sample data set to obtain the warehouse width requirement range to avoid storage problems caused by insufficient width.

[0031] Finally, these three demand intervals (warehouse height demand interval, warehouse length demand interval and warehouse width demand interval) are integrated to form a complete cargo storage size requirement. This requirement defines the minimum storage space required for the cargo to ensure that the cargo can be effectively stored in the appropriate cargo space.

[0032] P40: According to the quantity of the stored goods, set the quantity requirement of the storage space.

[0033] Specifically, based on the quantity of stored goods, the quantity requirement of storage locations is determined. First, the total quantity of stored goods is received or calculated. This quantity may be based on a variety of sources such as order data, inventory count results, or production plans. Subsequently, based on the quantity of stored goods, the quantity requirement of storage locations is directly set. The "storage location" here refers to the specific spatial location in the warehouse for storing goods, which can be a grid on a shelf, a pallet location, or a ground stacking area, etc.

[0034] The process of setting the number of storage locations required is relatively straightforward, but there are some key factors to consider. For example, the size, shape, and weight of the goods will affect the number of goods that can be accommodated in each storage location. For example, if a user needs to store 500 of the same model, further calculations are performed based on the number of these goods. The number of goods is combined with the previously obtained storage size requirements for the goods (including the required range for the height, length, and width of the warehouse) to determine how many goods can be stored in each storage location. Based on these calculations, the maximum capacity of each storage location is estimated, and this value is compared with the total number of stored goods to derive the required number of storage locations. For example, if each storage location can accommodate a maximum of 50 goods, and the user has 500 goods to store, it is calculated that at least 10 storage locations are required.

[0035] P50: Based on the starting position of the stored goods, the storage size requirements of the goods and the number of storage cargo spaces, optimize the idle storage spaces to obtain a list of selected storage spaces.

[0036] Further, such as Figure 3 As shown, step P50 of the embodiment of the present application also includes: P51: Perform primary sorting on the idle storage locations according to the storage size requirements of the goods, and obtain a list of primary sorted storage locations; P52: Obtain a list of primary sorted storage locations of the list of primary sorted storage locations; P53: Based on the starting position of the stored goods and based on the list of primary sorted storage locations, sort the list of primary sorted storage locations by distance from near to far, and obtain a sorting result of the primary sorted storage locations; P54: Perform secondary sorting according to the sorting result of the primary sorted storage locations according to the quantity requirements of the storage storage locations, and obtain a list of selected storage locations.

[0037] Optionally, based on the starting point of the warehouse goods, the storage size requirements and the number of storage locations, the idle storage locations are optimized and finally a list of selected storage locations is generated. This ensures that the goods are stored in the most suitable locations, thereby improving storage efficiency and reducing unnecessary handling costs.

[0038] First, the idle cargo spaces in the warehouse are sorted according to the storage size requirements of the goods. By comparing the size of each idle cargo space with the storage size required for the goods, the cargo spaces that can meet the size requirements of the goods are screened out to form a list of first-level sorted cargo spaces. This process ensures that the selected cargo spaces can accommodate the target goods in terms of physical space.

[0039] Then, the specific location information of each cargo location in the first-level sorting cargo location list is obtained to generate a first-level sorting cargo location list. The location information may include the coordinates of the cargo location in the warehouse, the shelf number and the number of layers, etc. This information is crucial for subsequent distance calculation and sorting.

[0040] Next, based on the starting location of the goods and the list of first-level sorting cargo locations, the first-level sorting cargo location list is sorted from near to far. By calculating the straight-line distance between each cargo location and the starting location of the goods (or the actual walking distance adjusted according to the warehouse layout), the cargo locations are sorted from near to far according to the distance to form the first-level sorting cargo location sorting result. This step is intended to give priority to cargo locations that are closer to the starting point to shorten the distance and time of cargo transportation.

[0041] Finally, according to the demand for the number of storage locations, the second-level sorting is carried out according to the sorting results of the first-level sorting locations. From the sorted location list, select the locations in order according to the required quantity to form the final list of selected storage locations. If the number of storage locations required is greater than the number of storage locations in the sorted list, you may need to further consider other factors (such as the correlation between storage locations, the frequency of access to goods, etc.) to make a selection; if the demand is less than the number of storage locations in the list, you can directly select the first N storage locations.

[0042] In order to effectively screen and sort cargo spaces based on cargo size requirements, we can use the warehouse's digital map and spatial positioning technology, as well as optimization algorithms (such as greedy algorithms or dynamic programming) to select cargo spaces. The entire process is automated to ensure maximum utilization of storage resources and minimize transportation costs.

[0043] Furthermore, step P54 of the embodiment of the present application also includes: P54-1: According to the storage cargo location quantity requirement, the first-level sorting cargo location list is configured to obtain several storage selected cargo location solutions; P54-2: Based on the first-level sorting cargo location location list, the distance from the starting position of the stored goods is calculated to obtain the first-level sorting cargo location entry distance list; P54-3: Based on the first-level sorting cargo location location list, the distance of the first-level sorting cargo location is calculated to obtain the first-level sorting cargo location distribution distance set; P54-4: Based on the first-level sorting cargo location distribution distance set, the several storage selected cargo location solutions are traversed to perform distribution variance analysis to obtain several distribution variance eigenvalues, Among them, the distribution variance eigenvalue has a first weight; P54-5: Based on the first-level sorting cargo location entry distance list, traverse the several storage selected cargo location plans to calculate the mean of the entry distance, and obtain several entry distance eigenvalues, wherein the entry distance eigenvalue has a second weight; P54-6: According to the first weight and the second weight, the several distribution variance eigenvalues ​​and the several entry distance eigenvalues ​​are integrated to obtain several entry loss eigenvalues; P54-7: Based on the several entry loss eigenvalues, the several storage selected cargo location plans are sorted with minimum loss to obtain the storage selected cargo location list.

[0044] Specifically, multiple factors are introduced to optimize the decision-making process of warehouse selected cargo locations to ensure that the efficiency of cargo handling and warehouse space utilization are taken into account while meeting the number of cargo location requirements. First, according to the number of storage cargo locations required, the first-level sorting cargo location list is flexibly configured to generate several possible storage selected cargo location solutions. These solutions represent different cargo location combinations and are intended to provide a basis for subsequent analysis and comparison.

[0045] Next, based on the first-level sorting cargo location list, the distance between each cargo location and the starting point of the stored goods is calculated to form a first-level sorting cargo location entry distance list. This step is the key to evaluating the cost of cargo handling, because a shorter entry distance means lower handling costs and faster handling speeds. Then, the relative distances between the first-level sorting cargo locations are further calculated to form a first-level sorting cargo location distribution distance set to evaluate the balance of cargo location distribution and avoid excessive concentration or dispersion of goods, which would affect the overall operational efficiency of the warehouse.

[0046] Then, all the warehouse selected cargo location plans are traversed, and the distribution variance analysis is performed on each plan. The distribution variance eigenvalue reflects the degree of dispersion of cargo location distribution and has the first weight, that is, the system believes that this factor occupies an important position in the decision-making process. By comparing the distribution variance eigenvalues ​​of different plans, a cargo location combination with a more balanced distribution can be preliminarily screened out.

[0047] Next, based on the list of first-level sorting location entry distances, the average entry distance of each solution is calculated to form several entry distance characteristic values. This step takes into account the total cost of cargo handling. The entry distance characteristic value has the second weight, indicating that the system also attaches importance to the impact of handling efficiency on overall operations.

[0048] Furthermore, the first weight and the second weight are used to merge the distribution variance eigenvalue and the warehousing distance eigenvalue to calculate the warehousing loss eigenvalue of each solution. This step is the key to comprehensively evaluate the advantages and disadvantages of different solutions. The lower the warehousing loss eigenvalue, the better the solution performs in terms of handling cost and cargo space distribution balance.

[0049] Finally, based on several warehousing loss characteristic values, the storage selected cargo location schemes are sorted with the minimum loss. By comparing the warehousing loss characteristic values ​​of each scheme, the scheme with the minimum loss is selected as the final list of storage selected cargo locations to ensure that the selected cargo locations meet the quantity requirements while also taking into account the optimization of handling efficiency and warehouse space utilization.

[0050] Further, to obtain the first weight and the second weight, the embodiment of the present application further includes step P54a, and step P54a further includes: P54-1a: Send the distribution variance and the entry distance in parallel to M importance evaluation parties whose information is not interconnected, and obtain M distribution variance importance scores and M entry distance importance scores; P54-2a: Perform weight distribution based on the M distribution variance importance scores and the M entry distance importance scores, and obtain the first weight and the second weight.

[0051] In a possible embodiment of the present application, in order to determine the first weight and the second weight, importance scores are obtained from independent information sources through multiple parallel evaluation steps to achieve a more scientific and fair weight distribution.

[0052] First, the two characteristic parameters, distribution variance and entry distance, are sent to M importance evaluation parties whose information is not interconnected. These evaluation parties can be independent algorithm modules, expert systems or third-party data analysis platforms, and they do not share information with each other to ensure the independence and diversity of the scoring process. Each evaluation party will generate a distribution variance importance score and an entry distance importance score based on its own analysis model or empirical standard. Through this parallel processing, independent evaluations of the two features are obtained from multiple perspectives, avoiding the deviation that may be caused by a single evaluation standard.

[0053] Next, weight distribution is performed based on the M distribution variance importance scores and the M entry distance importance scores. Specifically, the scores from each evaluation party can be summarized by weighted average or other statistical methods to obtain the first weight (importance of distribution variance) and the second weight (importance of entry distance). This ensures that the weight distribution is based on the independent evaluation results of multiple parties and has high reliability and fairness.

[0054] Furthermore, step P54-2a of the embodiment of the present application further includes: P54-21a: Add the M distribution variance importance scores and the M warehouse entry distance importance scores to obtain the sum of the importance scores; P54-22a: Add the M distribution variance importance scores to obtain the sum of the distribution variance importance scores, calculate the ratio of the sum of the distribution variance importance scores to the sum of the importance scores, and obtain the first weight; P54-23a: Add the M warehouse entry distance importance scores to obtain the sum of the warehouse entry distance importance scores, calculate the ratio of the sum of the warehouse entry distance importance scores to the sum of the importance scores, and obtain the second weight.

[0055] It should be understood that in order to accurately calculate the weights of distribution variance (i.e., the balance of cargo location distribution) and warehouse distance (i.e., the total cost of cargo handling) in the decision-making of warehouse selected cargo location, first, the distribution variance importance scores and warehouse distance importance scores collected from M independent evaluators are summed up to obtain the sum of the overall importance scores of the two indicators in all evaluators. These summation results reflect the overall views of the evaluator group on the importance of the two indicators, and provide basic data for the subsequent weight calculation.

[0056] Next, add up all M distribution variance importance scores to obtain the sum of the distribution variance importance scores. Then, calculate the ratio of the sum of the distribution variance importance scores to the sum of the importance scores (i.e., the sum of the scores of the two indicators). This ratio represents the importance of the distribution variance in all evaluation indicators, i.e., the first weight. The calculation of the first weight fully considers the subjective evaluation of the evaluation party on the importance of the distribution variance, and converts it into an objective quantitative indicator, which provides strong support for subsequent decision analysis.

[0057] Subsequently, a similar method is used to calculate the second weight of the warehouse entry distance. First, all M warehouse entry distance importance scores are added up to obtain the sum of the warehouse entry distance importance scores. Then, the ratio of the sum of the warehouse entry distance importance scores to the sum of the importance scores is calculated to obtain the importance ratio of the warehouse entry distance in all evaluation indicators, that is, the second weight. The calculation of the second weight also reflects the transformation process of the evaluator's subjective evaluation of the importance of the warehouse entry distance into an objective quantitative indicator.

[0058] P60: After the stored goods are transported into the warehouse according to the warehouse selected cargo location list, the warehouse selected cargo location list is distributedly configured according to the storage environment requirements of the goods.

[0059] Optionally, according to the previously determined list of warehouse selected cargo locations, the warehoused goods are officially put into the warehouse for transportation. This step marks the entry of the goods from the sorting and sorting stage into the actual storage stage. After the warehousing is completed, the distributed configuration of the cargo location environment is immediately transferred.

[0060] Distributed configuration of cargo space environment is a process of refined management based on the storage environment requirements of goods. First, according to the specific environmental requirements of each type of goods (such as temperature, humidity, light, etc.), the corresponding environmental parameter standards are retrieved from the warehouse management database. These environmental parameter standards are the key basis for ensuring that the quality of goods remains stable during storage.

[0061] Next, the Internet of Things (IoT) technology is used to monitor the environmental parameters of each storage location in the selected storage location list in real time. Through the sensor network deployed around the storage location, the system can collect environmental data such as temperature, humidity, and light in real time and transmit it to the central processing unit for analysis.

[0062] After obtaining real-time environmental data, the distributed configuration of the cargo space environment is carried out. This process mainly relies on intelligent control algorithms to automatically adjust the temperature control system, humidification / dehumidification equipment, and lighting control devices in the cargo space area according to the environmental requirements of the goods to ensure that the cargo space environment is always kept in the best state. For example, for goods that need to be stored at low temperatures, the system will start the refrigeration equipment to reduce the temperature of the cargo space area; for goods that need to be moisture-proof, the dehumidification equipment will be started to reduce the humidity level.

[0063] In addition, to ensure the accuracy and effectiveness of the cargo space environment configuration, regular environmental inspections and calibrations are carried out. By comparing the actual environmental data with the preset environmental parameter standards, environmental deviations can be discovered and corrected in a timely manner to prevent damage or quality degradation of goods caused by environmental factors.

[0064] In summary, the embodiments of the present application have at least the following technical effects: This application performs positive sample retrieval through warehousing request information to obtain the cargo storage environment requirements and cargo storage size requirements, optimizes the idle storage locations based on the starting location of the stored cargo, the cargo storage size requirements and the number of storage locations, obtains the list of selected storage locations for warehousing transportation, and performs distributed configuration of the storage location environment based on the cargo storage environment requirements.

[0065] The technical effect of optimizing the storage space configuration based on the storage cargo demand, improving the storage operation efficiency and reducing the transportation cost has been achieved.

[0066] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0067] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0068] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for optimizing storage space configuration based on cargo demand forecasting, characterized in that: include: Receiving storage request information, wherein the storage request information includes the storage goods model, storage goods quantity and storage goods starting point location; Performing an environmental positive sample search for the storage cargo model to obtain cargo storage environment requirements; Performing size positive sample retrieval on the warehouse cargo model to obtain cargo storage size requirements; According to the quantity of the stored goods, the quantity requirement of the storage space is set; Based on the starting position of the stored goods, the storage size requirements of the goods and the number of storage cargo spaces, optimizing the idle storage cargo spaces to obtain a list of selected storage cargo spaces; After the stored goods are transported into the warehouse according to the warehouse selected cargo location list, the warehouse selected cargo location list is distributedly configured according to the cargo storage environment requirements.

2. The method according to claim 1, characterized in that Perform environmental positive sample retrieval on the storage cargo model to obtain cargo storage environment requirements, including: Performing a storage environment positive sample search based on the storage goods model to obtain a first environmental indicator sample data set to an Nth environmental indicator sample data set; Performing a central trend analysis on the first environmental indicator sample data set to obtain a first environmental indicator demand range; Until a central trend analysis is performed on the Nth environmental indicator sample data set to obtain the Nth environmental indicator demand range; The first environmental indicator requirement interval to the Nth environmental indicator requirement interval are added to the cargo storage environmental requirements.

3. The method according to claim 2, characterized in that Performing a central trend analysis on the first environmental indicator sample data set to obtain a first environmental indicator demand range includes: Performing cluster analysis on the first environmental indicator sample data set according to the first environmental indicator deviation threshold to obtain an environmental indicator clustering result; Calculating the ratio of the number of clusters of the environmental indicator clustering result to the number of samples of the first environmental indicator sample data set, and setting it as the first environmental indicator dispersion; When the first environmental indicator dispersion is greater than or equal to the environmental indicator dispersion threshold, deleting the first environmental indicator; When the first environmental indicator dispersion is less than the environmental indicator dispersion threshold, an environmental indicator concentration trend analysis is performed on the first environmental indicator sample data set to obtain a first environmental indicator demand range.

4. The method according to claim 1, characterized in that Perform size positive sample retrieval on the storage cargo model to obtain cargo storage size requirements, including: Perform storage size positive sample retrieval based on the storage cargo model to obtain a warehouse height sample data set, a warehouse length sample data set, and a warehouse width sample data set; Performing a central trend analysis on the cargo hold height sample data set to obtain a cargo hold height requirement interval; Performing a central trend analysis on the cargo hold length sample data set to obtain a cargo hold length requirement interval; Performing a central trend analysis on the cargo hold width sample data set to obtain a cargo hold width requirement interval; The cargo warehouse height requirement interval, the cargo warehouse length requirement interval and the cargo warehouse width requirement interval are added to the cargo storage size requirement.

5. The method according to claim 1, characterized in that Based on the starting position of the stored goods, the storage size requirement of the goods and the quantity requirement of the storage cargo spaces, optimizing the idle storage cargo spaces to obtain a list of selected storage cargo spaces, including: Performing primary sorting on the idle storage spaces according to the storage size requirements of the goods, and obtaining a list of primary sorted storage spaces; Obtaining a first-level sorting cargo location list of the first-level sorting cargo location list; Based on the starting position of the stored goods and based on the first-level sorting cargo location position list, the first-level sorting cargo location list is sorted from near to far to obtain a first-level sorting cargo location sorting result; According to the quantity demand of the storage cargo locations, secondary sorting is performed according to the sorting result of the primary sorting cargo locations to obtain the list of the selected storage cargo locations.

6. The method according to claim 5, characterized in that Also includes: According to the storage cargo location quantity requirement, the first-level sorting cargo location list is configured to obtain several storage selected cargo location solutions; Based on the first-level sorting cargo location list, calculate the distance from the starting point of the stored goods to obtain the first-level sorting cargo location entry distance list; Based on the first-level sorting cargo location position list, performing distance calculation of the first-level sorting cargo location positions to obtain a first-level sorting cargo location distribution distance set; Based on the primary sorting cargo location distribution distance set, traverse the plurality of storage selected cargo location plans to perform distribution variance analysis to obtain a plurality of distribution variance eigenvalues, wherein the distribution variance eigenvalues ​​have a first weight; Based on the first-level sorting cargo location entry distance list, traverse the plurality of storage selected cargo location plans to perform mean entry distance calculation to obtain a plurality of entry distance characteristic values, wherein the entry distance characteristic value has a second weight; According to the first weight and the second weight, the plurality of distribution variance eigenvalues ​​and the plurality of warehousing distance eigenvalues ​​are integrated to obtain a plurality of warehousing loss eigenvalues; Based on the plurality of warehousing loss characteristic values, the plurality of warehousing selected cargo location solutions are sorted for minimum loss to obtain the warehousing selected cargo location list.

7. The method according to claim 6, characterized in that Also includes: The distribution variance and the entry distance are sent in parallel to M importance evaluation parties whose information is not interconnected, and M distribution variance importance scores and M entry distance importance scores are obtained; Weight distribution is performed according to the M distribution variance importance scores and the M warehouse entry distance importance scores to obtain a first weight and a second weight.

8. The method according to claim 7, characterized in that The weight distribution is performed according to the M distribution variance importance scores and the M warehouse entry distance importance scores to obtain a first weight and a second weight, including: Adding the M distribution variance importance scores and the M warehouse entry distance importance scores to obtain a sum of importance scores; Adding the M distribution variance importance scores to obtain a distribution variance importance score sum result, calculating a ratio of the distribution variance importance score sum result to the importance score sum result, and obtaining the first weight; The M warehouse entry distance importance scores are added up to obtain a sum of the warehouse entry distance importance scores, and the ratio of the sum of the warehouse entry distance importance scores to the sum of the importance scores is calculated to obtain the second weight.

Images