RPA-based warehouse sorting management methods and systems

Abstract

This invention relates to the field of warehouse sorting technology, specifically to a warehouse sorting management method and system based on RPA robots. The method includes: acquiring warehouse sorting order information; determining the sorting storage space for goods to be sorted based on the warehouse sorting order information; acquiring the attribute information of the goods to be sorted and the corresponding storage / exit characteristic values ​​of the sorting storage space; performing joint reasoning on the attribute information and storage / exit characteristic values ​​to deduce the sorting priority index of the goods to be sorted; determining the sorting order of the goods to be sorted based on the sorting priority index and the RPA robot in an idle state; determining the sorting path with the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space as the sorting ending point; dynamically updating the sorting path according to sorting congestion information; and completing the sorting sequentially based on the sorting order of the goods to be sorted and the updated sorting path, thereby improving sorting efficiency and reducing the sorting error rate.

Description

Technical Field

[0001] This invention relates to the field of warehouse sorting technology, specifically to a warehouse sorting management method and system based on RPA robots. Background Technology

[0002] As a key link in the logistics supply chain, the efficiency of warehousing and sorting directly affects order processing speed, customer satisfaction, and overall operating costs. Robotic Process Automation (RPA), as an emerging automation technology, automates business processes by simulating human behavior in computer systems.

[0003] In existing technologies, the increasing volume of warehouse sorting order information leads to low sorting efficiency and high error rates. Therefore, determining the sorting and storage space for goods to be sorted based on warehouse sorting order information, determining the sorting order of goods to be sorted, and determining the sorting path of goods to be sorted are key to solving the problems of low sorting efficiency and high error rates in existing technologies.

[0004] To address the aforementioned issues, this invention proposes a warehouse sorting management method and system based on RPA robots. Summary of the Invention

[0005] The purpose of this invention is to provide a warehouse sorting management method and system based on RPA robots: to solve the technical problems of low warehouse sorting efficiency and high error rate in the prior art.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] On the one hand, warehouse sorting management methods based on RPA robots include:

[0008] Obtain warehouse sorting order information, which includes the delivery address of the goods to be sorted, and determine the sorting and storage space for the goods to be sorted based on the warehouse sorting order information;

[0009] Obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space. Perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted.

[0010] The sorting order of the goods to be sorted is determined based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state.

[0011] The sorting path is determined by taking the location information of the goods to be sorted as the starting point and the location information of the sorting storage space of the goods to be sorted as the ending point. The sorting path is dynamically updated according to the sorting congestion information. The sorting is completed sequentially based on the sorting order of the goods to be sorted and the updated sorting path.

[0012] Furthermore, determining the sorting and storage space for goods to be sorted based on warehouse sorting order information specifically includes the following processes:

[0013] Extract the field names and field types of the receiving address of the goods to be sorted from the warehouse sorting order information;

[0014] Based on association rules, we can identify the field relationships between field names and field types;

[0015] The k-means clustering algorithm is used to process the associated field names to obtain the sorting storage space for the goods to be sorted.

[0016] Furthermore, the k-means clustering algorithm is used to process the associated field names to obtain the sorting storage space for the goods to be sorted. This process specifically includes the following steps:

[0017] Assemble the dataset by associating the field names. ,in Set the k value for the field name based on the size and shape of the dataset; randomly select the dataset. Let one data point be used as the initial centroid; when the number of initial centroids is less than k, let... Let be the initial centroid, where Based on the objective function Calculate the distance D(x) between each field name in the dataset and an existing initial centroid; take the field name corresponding to the maximum value in D(x) as the next initial centroid; obtain k initial centroids in this way, and then apply the k initial centroids to the dataset. Perform clustering to obtain k categories, and allocate a sorting storage space for each category.

[0018] Furthermore, obtaining the storage and exit characteristic values ​​corresponding to the sorting and storage space of the goods to be sorted specifically includes the following processes:

[0019] The previous warehousing and sorting cycle in the sorting and storage space is collected and marked as a time threshold, which is then divided into several sub-time periods.

[0020] Obtain the storage performance value and outbound performance value of the sorting storage space in each sub-time period. Establish a rectangular coordinate system with the storage performance value and outbound performance value as the Y-axis and the execution time of each sub-time period as the X-axis. Plot the storage performance value curve and the outbound performance value curve by plotting points. Count the number A corresponding to the outbound performance value curve being above the storage performance value curve and the number B corresponding to the outbound performance value curve being below the storage performance value curve. Calculate the ratio of number A to number B.

[0021] The intersection point formed by the first intersection of the warehouse performance value curve and the outbound performance value curve is calculated, and the slope of the outbound performance value curve corresponding to the intersection point is calculated.

[0022] The product of the slope and the ratio is recorded as the storage characteristic value corresponding to the sorting and storage space of the goods to be sorted.

[0023] Furthermore, obtaining the warehousing performance values ​​and outbound performance values ​​of the sorting and storage space within each sub-time period specifically includes the following processes:

[0024] Multiple detection points were set up within each sub-time period to collect the storage rate and shipping rate at each point. The storage rate at each detection point was compared with a preset storage rate threshold. Detection points with storage rates greater than the preset threshold were recorded as "multiplier storage points," while those with storage rates less than or equal to the preset threshold were recorded as "abnormal noise storage points." The number of multiplier storage points (BL) and the number of abnormal noise storage points (YX) were counted. The storage performance value (CC) of the sorting storage space was calculated using a formula. ,in, , These are the storage point coefficient for the leverage ratio and the storage point coefficient for abnormal noise, respectively.

[0025] A rectangular coordinate system is established with the shipment rate corresponding to the detection point as the Y-axis and the detection point number as the X-axis. The shipment rate curve is plotted by plotting points. The definite integral value of the curve above the preset shipment rate curve is calculated and recorded as the outbound performance value.

[0026] Furthermore, the joint reasoning of attribute information and stored feature values ​​to deduce the sorting priority index of the goods to be sorted specifically includes the following process:

[0027] The attribute information includes the weight, quantity, and volume of the goods to be sorted;

[0028] The differences ZL between the weight of the goods to be sorted and the preset standard weight, SL between the quantity of the goods to be sorted and the preset standard quantity, and TJ between the volume of the goods to be sorted and the preset standard volume are calculated respectively.

[0029] Substituting the differences ZL, SL, TJ, and the storage characteristic value TZ into the joint inference formula, the sorting priority index YXZ of the goods to be sorted is inferred. The joint inference formula is as follows: ,in, , and These are the weighting coefficients, and .

[0030] Furthermore, determining the sorting order of goods based on their sorting priority index and the idle RPA robot specifically includes the following process:

[0031] Obtain the status information of the first RPA robot, the status information of the second RPA robot, and so on up to the first... The status information of the RPA robot; wherein, the status information of the first RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; the status information of the second RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; The status information of the RPA robot includes the first Free time, number Sorting distance and the Load capacity value; where idle time is the time during which the RPA robot is not performing a scheduled sorting task, sorting distance is the sum of the distance the RPA robot moves to the goods to be sorted and the distance from the goods to be sorted to the sorting storage space, and load capacity value is the maximum load capacity of the RPA robot.

[0032] The first idle time, the first sorting distance, and the first load capacity value are quantized and then added together to obtain the first RPA robot preferred sorting characteristic value. The sum of the first RPA robot preferred sorting characteristic value and the sorting priority index of the goods to be sorted is recorded as the sorting sequence value of the first goods to be sorted; this process continues until the first... The sorting sequence value of the goods to be sorted;

[0033] The sorting sequence order of the goods to be sorted is recorded as the sorting order of the goods to be sorted.

[0034] Furthermore, dynamically updating the sorting path based on sorting congestion information specifically includes the following processes:

[0035] The sorting path is mapped onto a grid congestion map, and the real-time congestion level of each grid is recorded based on the grid congestion map. ;

[0036] During sorting along the sorting path, the subsequent transport path is monitored in real time. If any issues arise in the subsequent transport path... For grid cells with values ​​greater than 0, a path planning algorithm is used to replan the subsequent transport path.

[0037] Furthermore, the process of replanning subsequent transport routes using path planning algorithms includes the following steps:

[0038] Computational Raster Path cost : ,in, Indicates the distance from the starting grid to the current grid. Path cost, Indicates starting from the current grid The estimated travel time to the target grid. Indicates starting from the current grid Estimated congestion time to the target grid;

[0039] grid Path cost The grid path corresponding to the minimum value is denoted as the subsequent transport path.

[0040] On the other hand, a warehouse sorting management system based on RPA robots includes:

[0041] The sorting and storage space determination unit is used to obtain warehouse sorting order information, wherein the warehouse sorting order information includes the delivery address of the goods to be sorted, and the sorting and storage space of the goods to be sorted is determined based on the warehouse sorting order information;

[0042] The joint reasoning unit is used to obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space, and to perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted.

[0043] The sorting sequence determination unit is used to determine the sorting sequence of the goods to be sorted based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state.

[0044] The sorting path planning unit is used to determine the sorting path by taking the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space of the goods to be sorted as the sorting ending point. It also dynamically updates the sorting path according to the sorting congestion information and completes the sorting in sequence based on the sorting order of the goods to be sorted and the updated sorting path.

[0045] Compared to existing solutions, the beneficial effects achieved by this invention are:

[0046] This invention generates a sorting priority index by jointly reasoning the attribute information and storage space feature values ​​of the goods to be sorted, ensuring that high-priority goods are processed first, reducing order delays and improving overall sorting efficiency; combined with real-time sorting congestion information, it dynamically optimizes the sorting path, avoids robot path conflicts and congestion, reduces invalid movement time, and further improves sorting speed.

[0047] Furthermore, by combining attribute information with storage space feature values, it ensures that goods are accurately sorted to the appropriate storage location, avoiding errors caused by human operation. The RPA robot strictly follows the preset rules to perform sorting tasks, reducing human intervention, reducing sorting errors caused by fatigue or negligence, and lowering the sorting error rate. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0049] Figure 1 This is a flowchart of the first warehouse sorting management method based on RPA robots according to an embodiment of the present invention;

[0050] Figure 2 This is a flowchart of the second RPA robot-based warehouse sorting management method according to an embodiment of the present invention;

[0051] Figure 3 This is a system block diagram of a warehouse sorting management system based on RPA robots according to an embodiment of the present invention. Detailed Implementation

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0053] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more exemplary embodiments. Numerous specific details are provided in the following description to give a full understanding of exemplary embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, steps, etc., can be employed. In other instances, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0054] This embodiment provides a warehouse sorting management method based on RPA robots. Figure 1 This is a flowchart of the first RPA robot-based warehouse sorting management method according to an embodiment of the present invention, as follows: Figure 1As shown, the method includes the following steps:

[0055] Step S101: Obtain warehouse sorting order information, wherein the warehouse sorting order information includes the delivery address of the goods to be sorted, and determine the sorting storage space of the goods to be sorted based on the warehouse sorting order information;

[0056] Step S102: Obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space, and perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted.

[0057] Step S103: Determine the sorting order of the goods to be sorted based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state;

[0058] Step S104: Using the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space of the goods to be sorted as the sorting ending point, determine the sorting path, and dynamically update the sorting path according to the sorting congestion information. Based on the sorting order of the goods to be sorted and the updated sorting path, complete the sorting in sequence.

[0059] In summary, this invention generates a sorting priority index by jointly reasoning about the attribute information and storage space feature values ​​of the goods to be sorted, ensuring that high-priority goods are processed first, reducing order delays, and improving overall sorting efficiency. Combined with real-time sorting congestion information, it dynamically optimizes the sorting path, avoiding robot path conflicts and congestion, reducing unnecessary movement time, and further improving sorting speed. Through joint reasoning of attribute information and storage space feature values, it ensures that goods are accurately sorted to the appropriate storage location, avoiding errors caused by human operation. The RPA robot strictly follows preset rules to execute sorting tasks, reducing human intervention and lowering sorting errors caused by fatigue or negligence, thus reducing the sorting error rate.

[0060] In some embodiments, Figure 2 This is a flowchart illustrating the second RPA robot-based warehouse sorting management method according to an embodiment of the present invention. Figure 2 As shown, determining the sorting and storage space for goods to be sorted based on warehouse sorting order information includes the following steps:

[0061] Step S201: Extract the field name and field type of the receiving address of the goods to be sorted from the warehouse sorting order information;

[0062] Specifically, based on NLP (Natural Language Processing), all relevant data fields are identified: field name and field type. Data fields are columns or attributes used in a database to store data. Based on the data type and purpose, data fields can be categorized into different types, including primary keys, foreign keys, text fields, and numeric fields. Primary Key: A primary key is a field used to uniquely identify each row of data in a table. It allows for quick location of a specific record and ensures data uniqueness. Primary keys must be unique and cannot be null. Foreign Key: A foreign key is a field in one table whose value comes from the primary key of another table. Foreign keys are used to establish relationships between two tables and ensure referential integrity. Text Field: Text fields are used to store character data, such as strings and text comments. They are typically used to store variable-length non-numeric data. Numeric Field: Numeric fields are used to store numeric data, such as integers and floating-point numbers.

[0063] Step S202: Mine the field relationships between field names and field types based on association rules;

[0064] Specifically, data preparation includes: selecting the dataset to be analyzed and ensuring data quality; determining the fields to be analyzed, which can be numerical, categorical, or textual; and performing necessary preprocessing on the data, such as data cleaning, transformation, and discretization (for continuous data).

[0065] Define support and confidence:

[0066] Support: The frequency with which an itemset appears across all transactions. In field association analysis, it can be understood as the frequency with which two or more field values ​​appear simultaneously.

[0067] Confidence level: The conditional probability that a transaction containing X also contains Y, expressed as Support(X, Y) / Support(X). In field correlation analysis, it can be understood as the probability that field Y takes a certain value when field X takes a certain value.

[0068] Application of association rule mining algorithm:

[0069] Association rule mining algorithms such as Apriori and FP-Growth are used to identify frequent itemsets and generate association rules. Based on the association rule mining, the association between fields is determined by field names and field types.

[0070] Step S203: Process the associated field names using the k-means clustering algorithm to obtain the sorting storage space for the goods to be sorted.

[0071] Specifically, the associated field names are used to form the dataset. ,in The field name is `k`. The value of `k` is set according to the size and shape of the dataset. For small datasets (m < 1000): a smaller `k` value (3-5) is chosen to avoid underfitting the model due to an excessively large `k` value. For medium datasets (1000 < m < 10000): the `k` value can be selected in the range of 5-15. For large neighborhood datasets (m > 10,000) with sufficient samples: a larger `k` value (15-30) can be chosen. In this embodiment, the preferred `k` value is 5. The dataset is randomly selected. Let one data point be used as the initial centroid; when the number of initial centroids is less than k, let... Let be the initial centroid, where Based on the objective function Calculate the distance D(x) between each field name in the dataset and an existing initial centroid; take the field name corresponding to the maximum value in D(x) as the next initial centroid; obtain k initial centroids in this way, and then apply the k initial centroids to the dataset. Perform clustering to obtain k categories, and allocate a sorting storage space for each category.

[0072] In some embodiments, obtaining the storage characteristic value corresponding to the sorting storage space of the goods to be sorted specifically includes the following process:

[0073] The previous warehousing and sorting cycle in the sorting and storage space is collected and marked as a time threshold, which is then divided into several sub-time periods.

[0074] Obtain the storage performance value and outbound performance value of the sorting storage space in each sub-time period. Establish a rectangular coordinate system with the storage performance value and outbound performance value as the Y-axis and the execution time of each sub-time period as the X-axis. Plot the storage performance value curve and the outbound performance value curve by plotting points. Count the number A corresponding to the outbound performance value curve being above the storage performance value curve and the number B corresponding to the outbound performance value curve being below the storage performance value curve. Calculate the ratio of number A to number B.

[0075] The intersection point formed by the first intersection of the warehouse performance value curve and the outbound performance value curve is calculated, and the slope of the outbound performance value curve corresponding to the intersection point is calculated.

[0076] The product of the slope and the ratio is recorded as the storage characteristic value corresponding to the sorting and storage space of the goods to be sorted.

[0077] In some embodiments, obtaining the warehousing performance value and outbound performance value of the sorting storage space within each sub-time period specifically includes the following processes:

[0078] Multiple detection points were set up within each sub-time period to collect the storage rate and shipping rate at each point. The storage rate at each detection point was compared with a preset storage rate threshold. Detection points with storage rates greater than the preset threshold were recorded as "multiplier storage points," while those with storage rates less than or equal to the preset threshold were recorded as "abnormal noise storage points." The number of multiplier storage points (BL) and the number of abnormal noise storage points (YX) were counted. The storage performance value (CC) of the sorting storage space was calculated using a formula. ,in, , These are the storage point coefficient for the leverage ratio and the storage point coefficient for abnormal noise, respectively.

[0079] A rectangular coordinate system is established with the shipment rate corresponding to the detection point as the Y-axis and the detection point number as the X-axis. The shipment rate curve is plotted by plotting points. The definite integral value of the curve above the preset shipment rate curve is calculated and recorded as the outbound performance value.

[0080] In some embodiments, the joint reasoning of attribute information and stored feature values ​​to deduce the sorting priority index of goods to be sorted specifically includes the following process:

[0081] The attribute information includes the weight, quantity, and volume of the goods to be sorted;

[0082] The differences ZL between the weight of the goods to be sorted and the preset standard weight, SL between the quantity of the goods to be sorted and the preset standard quantity, and TJ between the volume of the goods to be sorted and the preset standard volume are calculated respectively.

[0083] Substituting the differences ZL, SL, TJ, and the storage characteristic value TZ into the joint inference formula, the sorting priority index YXZ of the goods to be sorted is inferred. The joint inference formula is as follows: ,in, , and These are the weighting coefficients, and .

[0084] In some embodiments, determining the sorting order of goods based on their sorting priority index and the idle RPA robot specifically includes the following process:

[0085] Obtain the status information of the first RPA robot, the status information of the second RPA robot, and so on up to the first... The status information of the RPA robot; wherein, the status information of the first RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; the status information of the second RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; The status information of the RPA robot includes the first Free time, number Sorting distance and the Load capacity value; where idle time is the time during which the RPA robot is not performing a scheduled sorting task, sorting distance is the sum of the distance the RPA robot moves to the goods to be sorted and the distance from the goods to be sorted to the sorting storage space, and load capacity value is the maximum load capacity of the RPA robot.

[0086] The first idle time, the first sorting distance, and the first load capacity value are quantized and then added together to obtain the first RPA robot preferred sorting characteristic value. The sum of the first RPA robot preferred sorting characteristic value and the sorting priority index of the goods to be sorted is recorded as the sorting sequence value of the first goods to be sorted; this process continues until the first... The sorting sequence value of the goods to be sorted;

[0087] The sorting sequence order of the goods to be sorted is recorded as the sorting order of the goods to be sorted.

[0088] In some embodiments, dynamically updating the sorting path based on sorting congestion information specifically includes the following process:

[0089] The sorting path is mapped onto a grid congestion map. The real-time congestion level of each grid is recorded based on this map. The grid congestion map is a two-dimensional table with the same number of rows and columns as the grid map. Each position records the grid congestion degree of the corresponding grid at the current time. The location where the goods to be sorted in the sorting path are placed is recorded as a grid. The grid congestion degree of grid g in the t-th time period is then calculated. for: ;in, Let be the estimated number of RPA robots that should pass through in the t-th time period, where The expression is as follows:

[0090] ;in, For the J-th RPA robot, This indicates that in t time periods, in order to pass through the grid... The resulting waiting time;

[0091] During sorting along the sorting path, the subsequent transport path is monitored in real time. If any issues arise in the subsequent transport path... For grid cells with values ​​greater than 0, a path planning algorithm is used to replan the subsequent transport path.

[0092] Furthermore, the process of replanning subsequent transport routes using path planning algorithms includes the following steps:

[0093] Computational Raster Path cost : ,in, Indicates the distance from the starting grid to the current grid. Path cost, Indicates starting from the current grid The estimated travel time to the target grid. Indicates starting from the current grid Estimated congestion time to the target grid;

[0094] grid Path cost The grid path corresponding to the minimum value is denoted as the subsequent transport path.

[0095] In some embodiments, Figure 3 This is a system block diagram of a warehouse sorting management system based on RPA robots according to an embodiment of the present invention, such as... Figure 3 As shown, the system includes:

[0096] The sorting and storage space determination unit is used to obtain warehouse sorting order information, wherein the warehouse sorting order information includes the delivery address of the goods to be sorted, and the sorting and storage space of the goods to be sorted is determined based on the warehouse sorting order information;

[0097] The joint reasoning unit is used to obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space, and to perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted.

[0098] The sorting sequence determination unit is used to determine the sorting sequence of the goods to be sorted based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state.

[0099] The sorting path planning unit is used to determine the sorting path by taking the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space of the goods to be sorted as the sorting ending point. It also dynamically updates the sorting path according to the sorting congestion information and completes the sorting in sequence based on the sorting order of the goods to be sorted and the updated sorting path.

[0100] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0101] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0102] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0103] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a division of some logical functions, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0104] The units described as separate components may or may not be physically separate. 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 units can be selected to achieve the purpose of this embodiment according to actual needs.

[0105] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A warehouse sorting management method based on RPA robots, characterized in that, The methods include: Obtain warehouse sorting order information, which includes the delivery address of the goods to be sorted, and determine the sorting and storage space for the goods to be sorted based on the warehouse sorting order information; Obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space. Perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted. The sorting order of the goods to be sorted is determined based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state. The sorting path is determined by taking the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space of the goods to be sorted as the sorting ending point. The sorting path is dynamically updated according to the sorting congestion information. The sorting is completed sequentially based on the sorting order of the goods to be sorted and the updated sorting path. The specific process of obtaining the warehousing performance value and outbound performance value of the sorting and storage space within each sub-time period includes the following: Multiple detection points were set up within each sub-time period to collect the storage rate and shipping rate at each point. The storage rate at each detection point was compared with a preset storage rate threshold. Detection points with storage rates greater than the preset threshold were recorded as "multiplier storage points," while those with storage rates less than or equal to the preset threshold were recorded as "abnormal noise storage points." The number of multiplier storage points (BL) and the number of abnormal noise storage points (YX) were counted. The storage performance value (CC) of the sorting storage space was calculated using a formula. ,in, , These are the storage point coefficient for the leverage ratio and the storage point coefficient for abnormal noise, respectively. A rectangular coordinate system is established with the shipment rate corresponding to the detection point as the Y-axis and the detection point number as the X-axis. The shipment rate curve is plotted by plotting points. The definite integral value of the curve above the preset shipment rate curve is calculated and recorded as the warehouse performance value. Dynamically updating the sorting path based on sorting congestion information includes the following processes: The sorting path is mapped onto a grid congestion map, and the real-time congestion level of each grid is recorded based on the grid congestion map. ; During sorting along the sorting path, the subsequent transport path is monitored in real time. If any issues arise in the subsequent transport path... For grid cells with values ​​greater than 0, the subsequent transport path is replanned using a path planning algorithm; The process of replanning subsequent transport routes using path planning algorithms includes the following steps: Computational Raster Path cost : ,in, Indicates the distance from the starting grid to the current grid. Path cost, Indicates starting from the current grid The estimated travel time to the target grid. Indicates starting from the current grid Estimated congestion time to the target grid; grid Path cost The grid path corresponding to the minimum value is denoted as the subsequent transport path.

2. The warehouse sorting management method based on RPA robots according to claim 1, characterized in that, Determining the sorting and storage space for goods to be sorted based on warehouse sorting order information includes the following processes: Extract the field names and field types of the receiving address of the goods to be sorted from the warehouse sorting order information; Based on association rules, we can identify the field relationships between field names and field types; The k-means clustering algorithm is used to process the associated field names to obtain the sorting storage space for the goods to be sorted.

3. The warehouse sorting management method based on RPA robots according to claim 2, characterized in that, The process of using k-means clustering to process the associated field names to obtain the sorting storage space for the goods to be sorted includes the following steps: Assemble the dataset by associating the field names. ,in Set the k value for the field name based on the size and shape of the dataset; randomly select the dataset. One data point is used as the initial centroid; When the number of initial centroids is less than k, let Let be the initial centroid, where Based on the objective function Calculate the distance D(x) between each field name in the dataset and an existing initial centroid; take the field name corresponding to the maximum value in D(x) as the next initial centroid; obtain k initial centroids in this way, and then apply the k initial centroids to the dataset. Perform clustering to obtain k categories, and allocate a sorting storage space for each category.

4. The warehouse sorting management method based on RPA robots according to claim 1, characterized in that, Obtain the specific storage and exit characteristic values ​​corresponding to the sorting and storage space of the goods to be sorted. Includes the following processes: The previous warehousing and sorting cycle in the sorting and storage space is collected and marked as a time threshold, which is then divided into several sub-time periods. Obtain the storage performance value and outbound performance value of the sorting storage space in each sub-time period. Establish a rectangular coordinate system with the storage performance value and outbound performance value as the Y-axis and the execution time of each sub-time period as the X-axis. Plot the storage performance value curve and the outbound performance value curve by plotting points. Count the number A corresponding to the outbound performance value curve being above the storage performance value curve and the number B corresponding to the outbound performance value curve being below the storage performance value curve. Calculate the ratio of number A to number B. The intersection point formed by the first intersection of the warehouse performance value curve and the outbound performance value curve is calculated, and the slope of the outbound performance value curve corresponding to the intersection point is calculated. The product of the slope and the ratio is recorded as the storage characteristic value corresponding to the sorting and storage space of the goods to be sorted.

5. The warehouse sorting management method based on RPA robots according to claim 1, characterized in that, The process of jointly reasoning about attribute information and stored feature values ​​to deduce the sorting priority index of goods to be sorted includes the following steps: The attribute information includes the weight, quantity, and volume of the goods to be sorted; The differences ZL between the weight of the goods to be sorted and the preset standard weight, SL between the quantity of the goods to be sorted and the preset standard quantity, and TJ between the volume of the goods to be sorted and the preset standard volume are calculated respectively. Substituting the differences ZL, SL, TJ, and the storage characteristic value TZ into the joint inference formula, the sorting priority index YXZ of the goods to be sorted is inferred. The joint inference formula is as follows: ,in, , and These are the weighting coefficients, and .

6. The warehouse sorting management method based on RPA robots according to claim 1, characterized in that, The sorting order of goods to be sorted is determined based on the sorting priority index of the goods to be sorted and the idle RPA robot. Includes the following processes: Obtain the status information of the first RPA robot, the status information of the second RPA robot, and so on up to the first... The status information of the RPA robot; wherein, the status information of the first RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; the status information of the second RPA robot includes the first idle time, the first sorting distance, and the first load capacity value; The status information of the RPA robot includes the first Free time, number Sorting distance and the Load capacity value; where idle time is the time during which the RPA robot is not performing a scheduled sorting task, sorting distance is the sum of the distance the RPA robot moves to the goods to be sorted and the distance from the goods to be sorted to the sorting storage space, and load capacity value is the maximum load capacity of the RPA robot. The first idle time, the first sorting distance, and the first load capacity value are quantized and then added together to obtain the first RPA robot preferred sorting characteristic value. The sum of the first RPA robot preferred sorting characteristic value and the sorting priority index of the goods to be sorted is recorded as the sorting sequence value of the first goods to be sorted; this process continues until the first... The sorting sequence value of the goods to be sorted; The sorting sequence order of the goods to be sorted is recorded as the sorting order of the goods to be sorted.

7. A warehouse sorting management system based on RPA robots, characterized in that, The warehouse sorting management method based on RPA robots, applicable to any one of claims 1 to 6, comprises: The sorting and storage space determination unit is used to obtain warehouse sorting order information, wherein the warehouse sorting order information includes the delivery address of the goods to be sorted, and the sorting and storage space of the goods to be sorted is determined based on the warehouse sorting order information; The joint reasoning unit is used to obtain the attribute information of the goods to be sorted and the storage and exit feature values ​​corresponding to the sorting storage space, and to perform joint reasoning on the attribute information and storage and exit feature values ​​to deduce the sorting priority index of the goods to be sorted. The sorting sequence determination unit is used to determine the sorting sequence of the goods to be sorted based on the sorting priority index of the goods to be sorted and the RPA robot in an idle state. The sorting path planning unit is used to determine the sorting path by taking the location information of the goods to be sorted as the sorting starting point and the location information of the sorting storage space of the goods to be sorted as the sorting ending point. It also dynamically updates the sorting path according to the sorting congestion information and completes the sorting in sequence based on the sorting order of the goods to be sorted and the updated sorting path.

Images