A robotic run supervision method and system for a sorting system

Abstract

The application provides a robot operation monitoring method and system for a sorting system, and belongs to the technical field of monitoring analysis, and specifically comprises the following steps: determining a time period in which a robot in other sub-areas does not have obstacle avoidance failure data in a latest preset time period in a verification and identification sub-area, and taking the time period as a matching use time period in the verification and identification sub-area; determining an update processing strategy of a matching deviation sub-area in the verification and identification sub-area by using scheduling use data of the robot in other sub-areas in the verification and identification sub-area and the matching use time period in each verification and identification sub-area; and determining an operation monitoring method of the robot by using an update processing result of the matching deviation sub-area and verification data in the matching use time period in different matching sub-areas, so that the reliability of identification processing of the robot with suspected abnormal operation state is improved.

Description

Technical Field

[0001] This invention belongs to the field of monitoring and analysis technology, and in particular relates to a method and system for monitoring the operation of robots in a sorting system. Background Technology

[0002] In intelligent warehousing and logistics sorting systems, AGV / AMR robots undertake the core tasks of cargo handling, sorting, and transportation. Taking the sterilization warehousing of medical products as an example, AGVs need to complete the automatic handling of goods between multiple processes such as "preheating room → sterilization cabinet → primary analysis room → secondary analysis room → waiting area", involving the collaborative operation of multiple AGVs in multiple areas.

[0003] To monitor and analyze the operational status of robots, existing solutions use the monitoring interface of an RCS (Robot Scheduling System) to view the current task, location, and status (running / idle / charging / fault) of each AGV. This is a basic function of the AGV system, allowing the scheduler to view the AGV status in real time through a monitoring client. However, it suffers from the following technical problems: When identifying and processing the operational status of a robot, relying solely on obstacle avoidance failure data from a single sub-region may not be sufficient to accurately identify the operational status. Therefore, determining the verification and identification sub-regions within the sub-regions and utilizing the update processing results of the matching deviation sub-regions within the verification and identification sub-regions to determine the robot's operational monitoring methods, thereby ensuring the reliability and timeliness of cross-regional operational status identification and analysis, has become an urgent technical problem to be solved.

[0004] Specifically, this application provides a method and system for monitoring the operation of a robot in a sorting system. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a method for monitoring the operation of a robot in a sorting system, which includes: S1 uses the usage data of the sorting system robots in each sub-area of ​​the warehouse at different times to determine the usage demand period of the sub-area, and uses the usage demand period of each sub-area and the number of robots used in the usage demand period to determine the identification strategy of the verification and identification sub-area in the sub-area. S2 determines the scheduling and management method for robots in the verification and identification sub-regions based on the verification and identification sub-regions and the number of robots used in each verification and identification sub-region. S3 performs scheduling processing of robots used in the verification and identification sub-region based on the scheduling management method. Using the scheduling management data of robots in different verification and identification sub-regions, it determines the time period in which the verification and identification sub-region uses robots from other sub-regions that do not have obstacle avoidance failure data in the most recent preset time period, and uses this time period as the matching usage time period in the verification and identification sub-region. Using the scheduling and usage data of robots in other sub-regions in the verification and identification sub-region and the matching usage time periods in each verification and identification sub-region, it determines the update processing strategy for the matching deviation sub-region in the verification and identification sub-region. S4 uses the update processing results of the matching deviation sub-region and the verification data in the matching usage time period in different matching sub-regions to determine the robot's operation supervision method.

[0006] The beneficial effects of this invention are as follows: By determining the usage frequency of robots in different sub-regions based on the usage demand time periods in each sub-region, and then determining the recognition strategy for the verification and recognition sub-regions in each sub-region based on the usage frequency of robots in different sub-regions, a foundation is laid for using the verification and recognition sub-regions to identify and analyze the robot's operating status.

[0007] Based on the update processing results of the matching deviation sub-region and the verification data from the matching usage period in the matching sub-regions excluding the matching deviation sub-region, the reliability of using the matching sub-regions excluding the matching deviation sub-region for verification processing of robots with suspected abnormal operating states is determined. By determining the reliability of using the matching sub-regions excluding the matching deviation sub-region for verification processing of robots with suspected abnormal operating states, the robot operation monitoring method is determined. This not only ensures the efficiency of verification processing of robots with suspected abnormal operating states, but also ensures the reliability of identification and processing when the probability of abnormal operating states is high by combining the operating data from multiple sub-regions.

[0008] Furthermore, the robot usage data for the sub-region at different time periods includes the number of robots used in the sub-region at different time periods.

[0009] Furthermore, the usage demand period is the period during which the number of robots used exceeds a preset threshold.

[0010] Furthermore, the method for determining the identification strategy of the verification identification sub-region in the sub-region is as follows: Determine the percentage of usage demand periods in each sub-region based on the usage demand periods in each sub-region; The usage demand weight value for each usage demand period is determined based on the number of robots used during different usage demand periods. The identification strategy for the verification and identification sub-regions in each sub-region is determined based on the proportion of usage demand time periods in each sub-region and the usage demand weight value in each usage demand time period.

[0011] Furthermore, the method for determining the scheduling and management method of the robot in the verification and identification sub-region is as follows: Based on the aforementioned verification and identification sub-regions, determine the number of verification and identification sub-regions; Based on the number of robots used in each verification and identification sub-region, the proportion of usage demand time periods in the verification and identification sub-region is determined, and the proportion of usage demand time periods in the verification and identification sub-region is used as the verification matching weight value of the verification and identification sub-region. By utilizing the number of verification and identification sub-regions and the verification matching weight values ​​of different verification and identification sub-regions, a scheduling and management method for robots in the verification and identification sub-regions is determined.

[0012] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for monitoring the operation of a robot in a sorting system when running the computer program.

[0013] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0014] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0015] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0016] Figure 1 This is a flowchart of a robot operation monitoring method for a sorting system; Figure 2 This is a flowchart illustrating the method for determining the identification strategy for the verification and identification sub-region within the sub-region; Figure 3 This is a flowchart of a method for determining the scheduling and management method of robots in a verified sub-region. Detailed Implementation

[0017] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0018] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0019] Example 1 The core objective of this embodiment is to determine the usage demand periods and identification strategies for verification and recognition sub-regions by using usage data of sorting system robots in each sub-region of the warehouse. This leads to the determination of scheduling and management methods for robots in the verification and recognition sub-regions, and based on scheduling usage data, the update processing strategy for matching deviation sub-regions is determined. Finally, combining the update processing results and verification data, the robot operation monitoring method is determined. This approach reduces the frequency and difficulty of scheduling while ensuring the reliability of robot operation status verification. The overall logic follows the process of "determining the identification strategy for verification and recognition sub-regions → determining the scheduling and management method → ​​determining the update strategy for matching deviation sub-regions → determining the operation monitoring method."

[0020] To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a method for monitoring the operation of a robot in a sorting system is provided, specifically including: S1 uses the usage data of the sorting system robots in each sub-area of ​​the warehouse at different times to determine the usage demand period of the sub-area, and uses the usage demand period of each sub-area and the number of robots used in the usage demand period to determine the identification strategy of the verification and identification sub-area in the sub-area. Furthermore, the robot usage data for the sub-region at different time periods includes the number of robots used in the sub-region at different time periods.

[0021] Specifically, the usage demand period is the period during which the number of robots used exceeds a preset threshold.

[0022] It should be noted that, as Figure 2 As shown, the method for determining the identification strategy of the verification identification sub-region in the sub-region is as follows: By determining the usage frequency of robots in different sub-regions based on the usage demand time periods in each sub-region, and then determining the recognition strategy for the verification and recognition sub-regions in each sub-region based on the usage frequency of robots in different sub-regions, a foundation is laid for using the verification and recognition sub-regions to identify and analyze the robot's operating status.

[0023] The usage demand period refers to the period when the number of robots used exceeds a preset threshold, reflecting the peak period of robot operation in this sub-region; the verification and identification sub-region refers to the sub-region selected for verifying the robot's operating status. By using robots from other sub-regions to run in the verification and identification sub-region and comparing obstacle avoidance situations, it is determined whether there are any operational anomalies.

[0024] By using the demand period to determine the identification strategy for the verification identification sub-region, and based on the actual usage frequency of the robot, the reliability requirements for the robot's operating status are determined. Based on the reliability requirements for the robot's operating status, suitable sub-regions for operating status verification are selected, thus laying the foundation for verification processing.

[0025] S11 determines the percentage of usage demand periods in each sub-region based on the usage demand periods in each sub-region; The percentage of usage demand periods refers to the proportion of time periods belonging to usage demand periods in a certain sub-region out of the total number of time periods in that sub-region, reflecting the frequency of robot use in that sub-region.

[0026] Suppose that a certain sub-region has a total of multiple time periods, and many of these time periods are periods of high demand for use. This indicates that the robots in this sub-region are used frequently and that there are high requirements for the reliability of robot operation.

[0027] S12 determines the usage demand weight value for each usage demand period based on the number of robots used during different usage demand periods; The usage demand weight value in the usage demand period is determined based on the preset demand weight value corresponding to the number of robots used in the usage demand period. The more robots are used, the greater the usage demand weight value.

[0028] If a large number of robots are used during a certain period of demand, then the demand weight value for that period is larger, reflecting a higher requirement for the reliability of robot operation during that period.

[0029] S13, determine the identification strategy of the verification identification sub-region in the sub-region based on the proportion of the number of usage demand time periods in each sub-region and the usage demand weight value in the usage demand time period.

[0030] Assuming that the usage demand period ratio and usage demand weight value of each sub-region are already determined, the target screening and identification strategy, the basic screening and identification strategy, or the second screening and identification strategy are determined according to the distribution of the average ratio and the verification demand value, respectively, in three cases. The identification strategy is determined by comprehensively considering the usage frequency and usage density. The screening criteria for the verification identification sub-region are determined collaboratively from the two dimensions of usage frequency and density, so as to ensure the reliability of the verification process when the operational reliability requirements are high.

[0031] It should be noted that the identification strategy for the verification and identification sub-regions in each sub-region is determined based on the proportion of usage demand time periods in each sub-region and the usage demand weight value within those time periods. Specifically, this includes: It should be noted that the determination of the identification strategy for the verification identification sub-region includes the following three cases.

[0032] Case 1: If the average percentage of the number of usage demand periods in each sub-region is above the preset threshold for the percentage of demand periods, then the identification strategy of the verification identification sub-region in the sub-region is determined to be the target screening identification strategy.

[0033] The preset demand period percentage threshold refers to the critical value for judging whether the overall usage frequency of each sub-region is relatively high; when the average value is above the threshold, it indicates that the overall usage of each sub-region is relatively frequent, and a more lenient screening strategy is adopted.

[0034] Assuming that the average percentage of usage demand time periods in each sub-region is relatively large, it indicates that the overall usage frequency of robots in the warehouse is high, and the requirements for operational reliability are high. Therefore, adopting a lenient target screening and identification strategy can ensure sufficient verification coverage.

[0035] When the overall usage frequency is high, a lenient screening strategy is adopted. The significance of this strategy is that when each sub-region is generally used frequently, the screening threshold for verifying and identifying sub-regions is lowered, thereby expanding the scope of verification coverage.

[0036] The specific rules of the target screening and identification strategy are as follows: locations in the sub-region that contain obstacle avoidance failure data and whose number of obstacle avoidance failures within the most recent preset time period is less than a preset failure number threshold are considered as available verification locations. If the number of available verification locations in the sub-region is greater than a preset available location number threshold, then the sub-region is determined to belong to the verification and identification sub-region.

[0037] Scenario 2: If the average percentage of usage demand time periods in each sub-region is not above the preset threshold for the percentage of usage demand time periods, the verification demand value in the sub-region is determined based on the percentage of usage demand time periods in the sub-region and the usage demand weight value of different usage demand time periods. If there is no sub-region with a verification demand value greater than the preset threshold, the verification identification sub-region in the sub-region is determined as the basis for the selection of the identification strategy.

[0038] The verification demand value refers to an indicator obtained by combining the proportion of usage demand periods and the usage demand weight value. Specifically, it can be determined based on the proportion of usage demand periods in the sub-region and the average of the average usage demand weight values ​​of different usage demand periods. The preset demand threshold refers to the critical value for judging whether the verification demand is prominent. When there is no sub-region with prominent verification demand value, a basic screening and identification strategy is adopted.

[0039] Assuming that the verification requirement value of each sub-region is not greater than the preset requirement threshold, it indicates that the verification requirement of each sub-region is evenly distributed. A basic screening and identification strategy is adopted. When there is no prominent verification requirement in the sub-region, a basic screening and identification strategy is adopted. When the verification requirement of each sub-region is low, a moderately strict screening standard is adopted to ensure the reliability of verification and identification.

[0040] The specific rules of the basic screening and identification strategy are as follows: locations in the sub-region that contain obstacle avoidance failure data and whose number of obstacle avoidance failures within the most recent preset time period is less than a preset failure number threshold are considered as available verification locations. If the number of available verification locations in the sub-region is greater than a preset available location number threshold, and the number of robots used in different time periods is greater than a preset usage number value, then the sub-region is determined to belong to the verification and identification sub-region.

[0041] The basic screening and identification strategy adds an additional condition of a lower limit on the number of uses based on the target screening and identification strategy. The screening criteria are between the target screening and identification strategy and the second screening and identification strategy.

[0042] Case 3: If there are sub-regions where the verification requirement value is greater than the preset requirement threshold, determine whether the number of sub-regions where the verification requirement value is greater than the preset requirement threshold meets the requirements. If yes, it means that there are a large number of sub-regions where the verification requirement value is greater than the preset requirement threshold, and determine the identification strategy of the verification identification sub-region in the sub-region as the target screening identification strategy. If no, determine the identification strategy of the verification identification sub-region in the sub-region as the second screening identification strategy.

[0043] Case 3 refers to the handling situation when there are sub-regions with prominent verification requirements, and different strategies are adopted according to the number of prominent sub-regions.

[0044] If there are many sub-regions whose verification demand value is greater than the preset demand threshold, it indicates that the verification demand of multiple sub-regions is more prominent, and the target screening and identification strategy can be adopted. If the number is small, a more stringent second screening and identification strategy is adopted. The strategy is further subdivided according to the number of prominent sub-regions. The significance is that when there are many prominent sub-regions, a loose strategy is adopted to improve coverage, and when there are few, a strict strategy is adopted to improve screening accuracy.

[0045] The specific rules of the second screening and identification strategy are as follows: locations in a sub-region where the number of obstacle avoidance failures within the most recent preset time period is less than a preset failure number threshold are considered as available verification locations. If the number of available verification locations in a sub-region is greater than a preset available location number threshold, and if the average number of robots used in different time periods is greater than a preset number of uses, then the sub-region is determined to belong to the verification and identification sub-region.

[0046] The second screening and identification strategy adjusts the judgment condition for the number of uses from "the number of uses in each time period is greater than the preset value" to "the average number of uses is greater than the preset value", which makes the screening criteria more lenient.

[0047] This embodiment realizes a complete process from the statistical analysis of the proportion of usage demand periods to the determination of usage demand weight values ​​and the determination of the identification strategy for verification and recognition sub-regions. It judges the overall usage frequency by using the average proportion of demand periods, and adopts a target screening identification strategy to expand the verification coverage when the frequency is high. It judges whether there are sub-regions with prominent verification demand by the distribution of verification demand values, and adopts a basic screening identification strategy to ensure the reliability of verification and recognition when there are no prominent sub-regions. It further refines the strategy by the number of prominent sub-regions, and reverts to a lenient strategy when the number is large and adopts a second screening identification strategy when the number is small, thereby realizing the adaptive selection of identification strategy.

[0048] A warehouse is divided into 20 sub-areas, A1 to A20, and each day is divided into 6 time periods, T1 to T6. The robot usage data for each sub-area during different time periods has been statistically analyzed.

[0049] Step S11: Calculate the percentage of usage demand time slots for each sub-region. Taking A1 as an example, the number of robots used exceeds 5 in each of the five time slots from T1 to T5, so the percentage of usage demand time slots = 5 / 6 = 0.833. Similarly, calculate the percentages for each sub-region: A2 = 0.667, A3 = 0.500, A4 = 0.333, A5 = 0.167, A6 = 0.500, A7 = 0.667, A8 = 0.833, A9 = 0.333, A10 = 0.500, A11 = 0.167, A12 = 0.667, A13 = 0.333, A14 = 0.500, A15 = 0.167, A16 = 0.667, A17 = 0.500, A18 = 0.333, A19 = 0.167, A20 = 0.667.

[0050] The average percentage of usage during peak demand periods is 0.500.

[0051] Step S12: The usage demand weight value for each usage demand period is determined based on the number of robots used. Taking time period T1 of A1 (20 robots used) as an example, the usage demand weight value = 0.8. The usage demand weight value for each time period ranges from 0.2 to 0.8.

[0052] Step S13: Determine whether the average percentage of usage demand time periods for each sub-region is 0.500 or higher than the preset threshold of 0.30. If 0.500 is greater than 0.30, it belongs to Case 1, and the identification strategy for verifying and identifying the sub-region is determined to be the target screening identification strategy.

[0053] The specific implementation of the target selection and identification strategy is as follows: For each sub-region, locations with obstacle avoidance failure data and whose number of obstacle avoidance failures in the past 7 days is less than 2 are considered usable verification locations. Taking A1 as an example, all 10 verification locations in A1 meet the condition of having less than 2 obstacle avoidance failures, thus there are 10 usable verification locations. The system then checks whether the number of usable verification locations (10) is greater than the preset threshold of 4: if 10 is greater than 4, A1 belongs to the verification identification sub-region.

[0054] S2 determines the scheduling and management method for robots in the verification and identification sub-regions based on the verification and identification sub-regions and the number of robots used in each verification and identification sub-region. Furthermore, the identification processing result of the verification identification sub-region includes the number of verification identification sub-regions.

[0055] It is understandable that, such as Figure 3 As shown, the method for determining the scheduling and management method of robots in the verification and identification sub-region is as follows: In this application, the matching degree of the verification processing reliability of robots in different locations within the verification and identification sub-region and the number of robots used in each verification and identification sub-region are used to determine the verification processing difficulty of the verification processing in the verification and identification sub-region. Based on the matching degree and difficulty of the verification processing, the scheduling and management method of robots in the verification and identification sub-region is determined, that is, how to use robots with higher operating reliability in other sub-regions for verification processing. This further ensures the comprehensiveness and reliability of the verification processing of the robot's obstacle avoidance reliability in different locations within the verification and identification sub-region.

[0056] The robot scheduling and management method refers to the decision rules for how to schedule and use robots from other sub-regions to perform operational status verification in the verification and identification sub-region.

[0057] Assuming the number of verification and identification sub-regions is small, the scheduling difficulty of using reliable robots running in other sub-regions for verification is relatively low. A more proactive scheduling management method can be adopted, which determines the scheduling management method based on the number of verification and identification sub-regions and the number of times they are used. The scheduling trigger conditions of the robots are dynamically determined according to the demand for verification processing and the scheduling difficulty, thereby achieving a balance between verification comprehensiveness and scheduling efficiency.

[0058] S21 determines the number of verification and identification sub-regions based on the aforementioned verification and identification sub-regions; The number of verification and identification sub-regions refers to the total number of verification and identification sub-regions selected according to the identification strategy of S1. Assuming that S1 selects multiple verification and identification sub-regions, their number directly affects the selection of subsequent scheduling and management methods. The overall verification processing scale is judged by the number of verification and identification sub-regions, providing a basis for determining the scale dimension for the differentiated determination of scheduling and management methods.

[0059] It is understandable that if the number of verification and identification sub-regions is less than the threshold number of verification regions, then the verification and identification sub-regions are less difficult to verify using robots in other regions, and the scheduling and management method for the robots in the verification and identification sub-regions is determined to be the preset scheduling and management method.

[0060] The threshold for the number of verification regions refers to the critical value for judging whether the size of the verification and recognition sub-region is large; when the number is less than this threshold, the verification process is less difficult.

[0061] Assuming that the number of verification and identification sub-regions is small, it indicates that the scope of verification processing is limited and the scheduling difficulty is low. A relaxed preset scheduling management method is adopted. When the number of verification and identification sub-regions is small, the significance of adopting a relaxed scheduling method is that when the scale of verification processing is small, more proactive triggering conditions are used to ensure sufficient coverage of verification processing.

[0062] The specific rules of the preset scheduling management method are as follows: whenever there is a robot that has failed to avoid obstacles in the verification and identification sub-region, the robot that has not failed to avoid obstacles in other sub-regions within the most recent preset time period is used in the verification and identification sub-region to determine whether there is an obstacle avoidance failure.

[0063] Additionally, it can be understood that if the number of the verification identification sub-regions is not less than the verification region number threshold, then proceed to step S22. For example, if there are a large number of verification and identification sub-regions, indicating a wide range of verification processing, proceed to S22 to calculate the verification matching weight value and perform further analysis.

[0064] S22, Based on the number of robots used in each verification and identification sub-region, determine the proportion of usage demand time periods in the verification and identification sub-region, and use the proportion of usage demand time periods in the verification and identification sub-region as the verification matching weight value of the verification and identification sub-region. The verification matching weight value refers to the proportion of time periods in the verification and identification sub-region that belong to the usage demand period, reflecting the frequency of robot use in the sub-region, and thus determining the reliability of the identification of locations in the sub-region where obstacle avoidance processing is abnormal. The verification matching weight value of the verification and identification sub-region is determined based on the reliability of the identification of locations in the sub-region where obstacle avoidance processing is abnormal.

[0065] Suppose that there are multiple time periods in a certain verification and recognition sub-region that belong to the usage demand period. The proportion of the time period is the verification matching weight value of the sub-region. The verification matching weight value is determined by using the proportion of the demand period. The demand level of verification processing is evaluated based on the actual frequency of robot use in the verification and recognition sub-region. The higher the actual frequency of use, the lower the demand level of verification processing.

[0066] It is understandable that the average value of the verification matching weights of different verification and recognition sub-regions is determined to be greater than the preset matching weight threshold. If so, the scheduling and management method of the robot in the verification and recognition sub-region is determined to be the third preset scheduling and management method. If not, the process proceeds to step S23.

[0067] The preset matching weight threshold refers to the critical value for judging whether the degree of verification matching is high. When the average value is greater than the threshold, a more stringent third preset scheduling management method is adopted. It is assumed that the average value of the verification matching weight value is large, indicating that the frequency of use of each verification identification sub-region is high, and the verification processing requires more refined triggering conditions. Therefore, the third preset scheduling management method is adopted.

[0068] The specific rules of the third preset scheduling management method are as follows: if the number of robots that failed to avoid obstacles in the recent preset time period of a set number of locations in the verification and identification sub-region is greater than the preset threshold for the number of robots that failed to avoid obstacles, then the robots that did not fail to avoid obstacles in the recent preset time period in other sub-regions are used in the verification and identification sub-region to determine whether there is an obstacle avoidance failure.

[0069] S23, using the number of verification and recognition sub-regions and the verification matching weight values ​​of different verification and recognition sub-regions, determine the scheduling and management method of the robot in the verification and recognition sub-regions.

[0070] Assuming that the number of verification and identification sub-regions and the verification matching weight value are determined, the third preset scheduling management method or the preset scheduling management method are adopted respectively, depending on whether the comprehensive matching weight value is greater than the matching weight threshold.

[0071] It is understood that the scheduling and management method for robots in the verification and recognition sub-regions is determined by utilizing the number of verification and recognition sub-regions and the verification matching weight values ​​of different verification and recognition sub-regions, specifically including: Using the number of verification and identification sub-regions and the verification matching weight values ​​of different verification and identification sub-regions, the sum of the verification matching weight values ​​of different verification and identification sub-regions is determined and used as the comprehensive matching weight value. It is then determined whether the comprehensive matching weight value is greater than the matching weight threshold. If it is, the scheduling and management method of the robot in the verification and identification sub-region is determined to be the third preset scheduling and management method. If not, the scheduling and management method of the robot in the verification and identification sub-region is determined to be the preset scheduling and management method.

[0072] The comprehensive matching weight value refers to the sum of the verification matching weight values ​​of all verification and recognition sub-regions, reflecting the overall verification requirement level; the matching weight threshold refers to the critical value for judging whether the comprehensive matching degree is high.

[0073] If the overall matching weight value is greater than the matching weight threshold, it indicates that the overall verification requirement is low, and the third preset scheduling management method is adopted; otherwise, the preset scheduling management method is adopted.

[0074] This embodiment realizes a complete process from determining the number of verification and identification sub-regions to calculating the verification matching weight value and determining the scheduling management method. The number of verification and identification sub-regions determines the scale of verification processing. When the scale is small, a pre-set scheduling management method that is actively triggered is adopted. The average value of the verification matching weight value determines the level of verification demand. When the demand is high, a third pre-set scheduling management method is adopted to refine the triggering conditions. By further subdividing the comprehensive matching weight value, a strict scheduling method is adopted when the comprehensive demand is high, thereby realizing the adaptive selection of the scheduling management strategy.

[0075] Continuing with the calculation results of S1, the verified identification sub-regions are A1, A2, A3, A6, A7, A8, A10, A12, A14, A16, A17, and A20, totaling 12.

[0076] Step S21: Verify that the number of identified sub-regions is 12, and determine whether 12 is less than the verification region number threshold of 10: If 12 is not less than 10, proceed to S22.

[0077] Step S22: Calculate the verification matching weight value of each verification identification sub-region (i.e., the proportion of the number of times the requirement is used, taken from S1): A1=0.833, A2=0.667, A3=0.500, A6=0.500, A7=0.667, A8=0.833, A10=0.500, A12=0.667, A14=0.500, A16=0.667, A17=0.500, A20=0.667.

[0078] The mean of the verification matching weight value is 0.625.

[0079] Determine if the mean value of 0.625 is greater than the preset matching weight threshold of 0.40: If 0.625 is greater than 0.40, then the scheduling and management method for the robot in the verification and recognition sub-region is determined to be the third preset scheduling and management method.

[0080] The specific implementation of the third preset scheduling management method is as follows: If the number of robots that have failed to avoid obstacles in the past 7 days in two or more locations in the verification and identification sub-region exceeds the preset threshold of two robots that have failed to avoid obstacles, then robots that have not failed to avoid obstacles in the past 7 days in other sub-regions will be used in the verification and identification sub-region to determine whether there is an obstacle avoidance failure.

[0081] S3 performs scheduling processing of robots used in the verification and identification sub-region based on the scheduling management method. Using the scheduling management data of robots in different verification and identification sub-regions, it determines the time period in which the verification and identification sub-region uses robots from other sub-regions that do not have obstacle avoidance failure data in the most recent preset time period, and uses this time period as the matching usage time period in the verification and identification sub-region. Using the scheduling and usage data of robots in other sub-regions in the verification and identification sub-region and the matching usage time periods in each verification and identification sub-region, it determines the update processing strategy for the matching deviation sub-region in the verification and identification sub-region. Specifically, the method for determining the update processing strategy for the matching deviation sub-region in the verification and identification sub-region is as follows: Specifically, by verifying the scheduling and usage data of the verification robot in the verification and recognition sub-region and the matching usage time periods in different verification and recognition sub-regions, the frequency of the verification robot's scheduling and the frequency of verification processing in the verification and recognition sub-regions are determined. Based on the frequency of the verification robot's scheduling and the frequency of verification processing in the verification and recognition sub-regions, the difficulty of the verification processing in the verification and recognition sub-regions is determined. And by using the difficulty of the verification processing in the verification and recognition sub-regions, the update processing strategy for the matching deviation sub-regions in the verification and recognition sub-regions is determined. This lays the foundation for timely updating of the matching deviation value sub-regions, thereby reducing the difficulty and frequency of scheduling and processing.

[0082] The verification robot refers to a robot that has no obstacle avoidance failure data in other sub-regions within the most recent preset time period, i.e., a robot with a reliable operating status; the matching deviation sub-region refers to a sub-region that is more difficult to verify and needs to be removed or updated from the set of verification and identification sub-regions.

[0083] If verification robots from other sub-regions are frequently used in certain verification and recognition sub-regions, and the duration of matching usage in these sub-regions accounts for a high proportion, it indicates that verification processing is frequent and data processing is difficult. It may be necessary to speed up the updating of the matching deviation sub-region set. The update processing strategy can be determined by the usage data of verification robots and the matching usage time. The matching deviation sub-region set can be dynamically updated according to the frequency and difficulty of verification processing, thereby reducing the difficulty of scheduling processing.

[0084] S31, take the sub-regions other than the verification and identification sub-regions as other sub-regions, and take the robots in the other sub-regions that do not have obstacle avoidance failure data in the most recent preset time period as verification robots, so as to verify the scheduling and usage data of the verification robots in the verification and identification sub-regions, determine the usage time period of the verification robots in the verification and identification sub-regions, and the proportion of the usage time period of the verification robots, and use it as the usage time ratio of the verification robots. The usage time ratio refers to the proportion of the time the verification robot spends in the verification and identification sub-region to its total runtime, reflecting the frequency with which the verification robot is scheduled to the verification and identification sub-region.

[0085] Suppose that the total runtime of a verification robot during the operation monitoring period is multiple hours, of which the usage time in the verification and identification sub-region is a portion of the hours. The ratio of this usage time to the total runtime is the usage time ratio. By determining the usage time ratio of the verification robot, the frequency of the verification robot's scheduling can be quantified.

[0086] S32, determine the duration percentage of the matching usage time period in the verification and identification sub-region based on the matching usage time period in different verification and identification sub-regions; The matching usage period refers to the period during which the verification and identification sub-region uses robots from other sub-regions that do not have obstacle avoidance failure data in the most recent preset period; the duration ratio refers to the proportion of the matching usage period to the total running time of the verification and identification sub-region.

[0087] If the matching usage time period of a certain verification and recognition sub-region accounts for a large proportion, it indicates that the sub-region often needs to schedule verification robots from other regions for verification processing, and the verification processing frequency is high. The verification processing frequency of the verification and recognition sub-region is evaluated by the proportion of the matching usage time period, which provides a sub-region dimension basis for the selection of subsequent update strategies.

[0088] It is understandable that, in the above steps, based on the proportion of matching usage time periods in different verification and identification sub-regions, it is determined whether there is a verification and identification sub-region where the proportion of matching usage time periods is greater than a preset time period proportion threshold. If so, proceed to step S33. If not, the verification and identification sub-region at this time uses robots from other sub-regions for verification processing less frequently. Therefore, the update processing strategy for the matching deviation sub-region in the verification and identification sub-region is determined to be that the verification robot in the verification and identification sub-region with more than a preset failure number threshold in the location is regarded as the associated risk robot of the location. If there is a location in the verification and identification sub-region where the number of associated risk robots is greater than a preset risk robot number threshold, then the verification and identification sub-region is determined to belong to the matching deviation sub-region.

[0089] The preset duration percentage threshold refers to the critical value for judging whether the frequency of verification processing is high. If there is no verification identification sub-region where the duration percentage of the matching usage period is greater than the preset duration percentage threshold, it indicates that the overall verification processing is not very frequent. In this case, the associated risk robot number judgment strategy is adopted. When the frequency of verification processing is low, the associated risk robot number judgment strategy is adopted. When the verification processing is not frequent, a higher trigger threshold is used to determine the matching deviation sub-region and remove the high-risk sub-region in time.

[0090] S33, based on the usage time ratio of the verification robot and the duration ratio of matching usage time in different verification and identification sub-regions, determine the update processing strategy for the matching deviation sub-region in the verification and identification sub-region.

[0091] Assuming there are sub-regions with frequent verification processing, the update strategy is further subdivided based on the verification processing frequency coefficient and the number of robots that frequently change. The update strategy is determined by combining the usage frequency of the verification robots and the verification frequency of the verification identification sub-regions, and the difficulty of verification processing is jointly evaluated from two dimensions: robots and sub-regions.

[0092] Specifically, based on the usage time ratio of the verification robot and the duration ratio of matching usage time periods in different verification and recognition sub-regions, the update processing strategy for the matching deviation sub-regions in the verification and recognition sub-regions is determined, including: S331, the verification identification sub-regions whose duration of matching usage time is greater than a preset duration percentage threshold are identified as frequent verification identification sub-regions. The verification processing frequency coefficient is determined based on the number of frequent verification identification sub-regions and the duration percentage of matching usage time in different verification identification sub-regions. It is then determined whether the verification processing frequency coefficient is greater than a preset frequency coefficient threshold. If so, the update processing strategy for the matching deviation sub-regions in the verification identification sub-regions is determined as follows: the verification robots in the verification identification sub-regions whose number of obstacle avoidance failures in the location is greater than a preset failure number threshold are identified as the associated risk robots of the location. If the number of associated risk robots in the verification identification sub-regions is greater than a preset risk robot number threshold, the verification identification sub-regions are determined to belong to the matching deviation sub-regions. Otherwise, proceed to step S332. The verification processing frequency coefficient is determined based on the number of frequently verified identification sub-regions and the proportion of matching usage time periods. Specifically, it can be determined by the sum of the proportions of matching usage time periods in different verification identification sub-regions. The more frequently verified identification sub-regions there are and the higher the proportion of matching usage time periods, the greater the verification processing frequency coefficient will be.

[0093] If the verification processing frequency coefficient is greater than the preset frequency coefficient threshold, it indicates that the verification processing is relatively frequent. Then, the strategy of determining the number of associated risk robots is adopted to determine the matching deviation sub-region. When the verification processing frequency is high, the strategy of determining the number of associated risk robots is adopted. When the verification processing is frequent, high-risk sub-regions are removed with a lower trigger threshold to reduce scheduling pressure.

[0094] S332, based on the usage time ratio of the verification robots, verification robots with a usage time ratio greater than a preset time ratio threshold are identified as frequently changing robots. It is determined whether the number of frequently changing robots meets the requirements. If so, the number of frequently changing robots is relatively large. Therefore, the update processing strategy for the matching deviation sub-region in the verification identification sub-region is determined as follows: verification robots in the verification identification sub-region with an obstacle avoidance failure count greater than a preset failure count threshold are identified as associated risk robots for that location. If the number of associated risk robots in the verification identification sub-region is greater than a preset risk robot number threshold, the verification identification sub-region is determined to belong to the matching deviation sub-region. Otherwise, the update processing strategy for the matching deviation sub-region in the verification identification sub-region is determined as follows: verification robots in the verification identification sub-region with an obstacle avoidance failure count greater than a preset failure count threshold are identified as associated risk robots for that location. If the number of associated risk robots in the verification identification sub-region is greater than a preset risk robot number threshold, and there is a location where the number of associated risk robots is greater than the target robot number threshold (less than the preset risk robot number threshold), the verification identification sub-region is determined to belong to the matching deviation sub-region.

[0095] The frequently changing robot refers to a verification robot whose usage time exceeds a preset time ratio threshold; the target robot quantity threshold refers to an auxiliary threshold for judging whether the number of risk-associated robots at a certain location has reached a high level.

[0096] If the number of frequently changing robots is large, it indicates that a large number of verification robots are being scheduled frequently. A lower trigger threshold is used to determine the matching deviation sub-region. If the number is small, additional conditions are added for locations with a large number of associated risk robots. The update strategy is further subdivided according to the number of frequently changing robots. When verification robots are frequently scheduled, high-risk sub-regions are removed in a timely manner with lenient conditions. When scheduling is infrequent, matching deviation sub-regions are precisely screened with strict conditions.

[0097] This embodiment realizes a complete process from calculating the usage time ratio of the verification robot to analyzing the usage time ratio of the matching period and determining the update strategy for the matching deviation sub-region. It quantifies the scheduling frequency of the verification robot by the usage time ratio of the verification robot; evaluates the verification frequency of the verification identification sub-region by the usage time ratio of the matching period; and dynamically adjusts the update conditions of the matching deviation sub-region when the frequency is different by using a hierarchical judgment of the verification processing frequency coefficient and the number of frequently changing robots, thereby achieving adaptive selection of the update strategy.

[0098] Continuing with the calculation results of S2, the 12 verification and identification sub-regions, such as A1, are managed using the third preset scheduling method. The verification robots are 30 robots from the remaining 8 sub-regions B1 to B8 that have no obstacle avoidance failure data in the last 7 days.

[0099] Step S31: Verify the usage time ratio of the verification robot in the verification and recognition sub-region: Taking verification robot R1 as an example, R1 has a total runtime of 200 hours, and 60 hours of usage time in the verification and recognition sub-region. The usage time ratio = 60 / 200 = 0.30. Similarly, calculate the usage time ratio of 30 verification robots, and the average value is 0.25.

[0100] Step S32: The percentage of time periods used for matching in each verification and identification sub-region. Statistics show: A1=0.40, A2=0.25, A3=0.35, A6=0.45, A7=0.20, A8=0.50, A10=0.30, A12=0.15, A14=0.55, A16=0.28, A17=0.32, A20=0.22.

[0101] Determine if there are any verification identification sub-regions where the proportion of the matching usage time period is greater than the preset time proportion threshold of 0.30: A1 (0.40), A3 (0.35), A6 (0.45), A8 (0.50), A14 (0.55), A17 (0.32), a total of 6, and proceed to S33.

[0102] Step S331: Six verification and identification sub-regions are designated as frequently used verification and identification sub-regions, with a time usage percentage greater than 0.30. The verification processing frequency coefficient equals the sum of the time usage percentages of each verification and identification sub-region, totaling 3.97. It is then determined whether 3.97 exceeds the preset frequency coefficient threshold of 1.5: If 3.97 is greater than 1.5, then the update processing strategy for the matching deviation sub-region is as follows: Verification robots in the verification and identification sub-region that have failed obstacle avoidance more than twice at a given location are designated as associated risk robots for that location. If the number of associated risk robots in the verification and identification sub-region is greater than three, then the verification and identification sub-region is determined to belong to the matching deviation sub-region.

[0103] S4 uses the update processing results of the matching deviation sub-region and the verification data in the matching usage time period in different matching sub-regions to determine the robot's operation supervision method.

[0104] It should be noted that the method for determining the operation monitoring method of the robot is as follows: In this embodiment, based on the update processing result of the matching deviation sub-region and the verification data in the matching usage period in the matching sub-region excluding the matching deviation sub-region, the reliability of using the matching sub-region excluding the matching deviation sub-region for verification processing of robots with suspected abnormal operating states is determined. By determining the reliability of using the matching sub-region excluding the matching deviation sub-region for verification processing of robots with suspected abnormal operating states, the robot operation monitoring method is determined. This not only ensures the efficiency of verification processing of robots with suspected abnormal operating states, but also ensures the reliability of identification processing when the probability of abnormal operating states is high by combining the operating data in multiple sub-regions.

[0105] The robot operation monitoring method refers to the decision-making rules for how to use the remaining verification and identification sub-regions to verify and process robots with suspected abnormalities in their operating status within a normally operating sub-region.

[0106] If the number of remaining matching sub-regions is small, the reliability of the verification process is low, and more sensitive triggering conditions are required for verification. The operation monitoring method is determined by the number of remaining matching sub-regions and the verification matching weight coefficient. The robot's operation status verification triggering conditions and operation status monitoring and analysis methods are dynamically determined based on the available verification resources.

[0107] S41, based on the update processing result of the matching deviation sub-region, determine the matching sub-region excluding the matching deviation sub-region, and take it as the remaining matching sub-region; The remaining matching sub-region refers to the sub-region remaining after removing the matching deviation sub-region from the verification and recognition sub-region.

[0108] Suppose that 3 matching deviation sub-regions are removed from the 12 verification and identification sub-regions, then the remaining 9 are the remaining matching sub-regions. The significance of determining the set of remaining sub-regions that can be used for verification processing is to provide a range of available verification resources for determining the subsequent operation and supervision methods.

[0109] Specifically, if the number of remaining matching sub-regions is less than a preset threshold for the number of remaining regions, the reliability of using the remaining matching sub-regions to identify and analyze the robot's operating status is low. In this case, the timeliness of the verification and analysis of the operating status is high. Therefore, the method for monitoring the robot's operation is as follows: if the number of obstacle avoidance failures in the sub-region within the most recent preset time period is greater than a preset failure number, then the remaining matching sub-regions are used to identify and analyze the robot's operating status. That is, the robot is forced to operate in the remaining matching sub-regions to determine whether there are obstacle avoidance failures. In other words, if the number of obstacle avoidance failures in the remaining matching sub-regions is greater than a preset failure number threshold or the number of remaining matching sub-regions with obstacle avoidance failure data is greater than a preset threshold for the number of remaining regions, then it is determined that its operating status is abnormal.

[0110] The preset remaining area quantity threshold refers to the critical value for judging whether the remaining verification resources are sufficient. If the number of remaining matching sub-regions is small and the verification resources are insufficient, then a lower trigger threshold is used to verify the robot suspected of being abnormal, and the lower trigger threshold is used to determine that its operating status is abnormal.

[0111] When verification resources are insufficient, a lenient regulatory approach is adopted. When the available verification area is limited, the verification trigger threshold and the threshold for identifying abnormal states are lowered to ensure timely identification of abnormal robots.

[0112] S42, Based on the verification data in the matching usage period in the remaining matching sub-region, determine the verification robots in the remaining matching sub-region and the associated risk robots among the verification robots, and determine the verification matching weight coefficient in the remaining matching sub-region based on the number of verification robots in the remaining matching sub-region and the proportion of the number of associated risk robots among the verification robots. The verification matching weight coefficient is determined based on the number of verification robots in the remaining matching sub-regions and the proportion of associated risk robots among the verification robots. The more verification robots there are and the smaller the proportion of associated risk robots, the higher the verification matching weight coefficient will be.

[0113] If a certain remaining matching sub-region has a large number of verification robots and a high proportion of associated risk robots, then the verification matching weight coefficient of that sub-region is small, indicating that the reliability of the verification data in that sub-region is high. The verification matching weight coefficient is determined by the number of verification robots and the proportion of associated risk, thereby quantifying the verification reliability of each remaining matching sub-region.

[0114] It is understandable that in the above steps, based on the verification matching weight value coefficients in different remaining matching sub-regions, it is determined whether there are remaining matching sub-regions whose verification matching weight coefficients are greater than the preset matching weight coefficient threshold. If so, proceed to step S43; otherwise, determine that the robot's operation monitoring method is as follows: if the number of obstacle avoidance failures in the sub-region within the most recent preset time period is greater than the preset failure number value, then the remaining matching sub-region is used to identify and analyze the robot's operating status, that is, it is forced to operate in the remaining matching sub-region to determine whether there is an obstacle avoidance failure. That is, when the number of obstacle avoidance failures in the remaining matching sub-region is greater than the preset failure number threshold or the number of remaining matching sub-regions with obstacle avoidance failure data is greater than the preset remaining region number threshold, then it is determined that its operating status is abnormal.

[0115] The preset matching weight coefficient threshold refers to the critical value for determining whether there is a high-reliability verification sub-region. If there are no remaining matching sub-regions with a verification matching weight coefficient greater than the preset matching weight coefficient threshold, it indicates that the overall verification reliability is low, and a lenient monitoring method is adopted. A lenient monitoring method is used when there are no high-reliability verification sub-regions, and the anomaly detection threshold is lowered when the verification data quality is insufficient to support strict judgment.

[0116] S43, using the remaining matching sub-regions and the verification matching weight coefficients in different remaining matching sub-regions, determine the operation monitoring method of the robot.

[0117] Assuming the existence of a high-reliability verification sub-region, the regulatory method is further subdivided based on the comprehensive matching weight value. The regulatory method is determined by combining the number of remaining matching sub-regions and the verification matching weight coefficient. The judgment conditions for the operational status are determined collaboratively from the two dimensions of verification resource quantity and verification reliability.

[0118] It is understood that the method for determining the operation monitoring of the robot by utilizing the remaining matching sub-regions and the verification matching weight coefficients in different remaining matching sub-regions specifically includes: Based on the number of remaining matching sub-regions and the verification matching weight coefficients in different remaining matching sub-regions, the sum of the verification matching weight coefficients in different remaining matching sub-regions is determined and used as the filtering matching weight value. It is then determined whether the filtering matching weight value is greater than a preset matching weight value. If so, the robot's operation monitoring method is as follows: if the number of obstacle avoidance failures in a sub-region within the most recent preset time period is greater than a second preset failure number (greater than the preset failure number), then the remaining matching sub-regions are used to identify and analyze the robot's operating status, i.e., it is forced to operate within the remaining matching sub-regions to determine whether there are obstacle avoidance failures. If the number of obstacle avoidance failures in a matching sub-region exceeds a preset failure threshold, then the robot's operating status is determined to be abnormal. Otherwise, the robot's operation monitoring method is as follows: If the number of obstacle avoidance failures in the sub-region within the most recent preset time period exceeds a second preset failure value, then the remaining matching sub-regions are used to identify and analyze the robot's operating status. That is, the robot is forced to operate in the remaining matching sub-regions to determine whether there are obstacle avoidance failures. Specifically, if the number of obstacle avoidance failures in the remaining matching sub-regions exceeds a preset failure threshold or the number of remaining matching sub-regions with obstacle avoidance failure data exceeds a preset remaining region number threshold, then the robot's operating status is determined to be abnormal.

[0119] The second preset number of failures refers to a higher standard for judging whether obstacle avoidance failure is serious; the preset value of matching weight (used in S43) refers to a critical value for judging whether the degree of matching in the comprehensive verification is high. Among them, the second preset number of failures > the preset number of failures.

[0120] If the overall matching weight value is greater than the preset matching weight threshold, it indicates that the overall verification reliability is high, and a strict regulatory approach is adopted—a higher threshold for the number of obstacle avoidance failures is set for the triggering conditions, and a higher threshold for anomaly identification is also set. If the overall matching weight value is not greater than the preset matching weight threshold, a moderate regulatory approach is adopted—a higher threshold for the number of obstacle avoidance failures is set for the triggering conditions, but the anomaly judgment conditions are more lenient. The regulatory approach is further subdivided by the overall matching weight value. When the verification reliability is high, strict conditions are used to trigger the verification to reduce unnecessary verifications. When the reliability is moderate, moderate conditions are used to trigger the verification to balance verification coverage and efficiency.

[0121] Continuing with the calculation results of S3, 3 matching deviation sub-regions (A3, A6, A14) are removed from the 12 verification and recognition sub-regions, leaving 9 remaining matching sub-regions: A1, A2, A7, A8, A10, A12, A16, A17, A20.

[0122] Step S41: The number of remaining matching sub-regions is 9. Determine whether 9 is less than the preset threshold of the number of remaining regions, 5: If 9 is not less than 5, proceed to S42.

[0123] Step S42: For each remaining matching sub-region, count the number of verification robots and the proportion of associated risk robots, and calculate the verification matching weight coefficient: A1: Verify 8 robots, associated risk ratio 0.125, coefficient = (8 / preset coefficient 20) + 1 - 0.125 = 1.275, determine whether there are any remaining matching sub-regions whose verification matching weight coefficient is greater than the preset matching weight coefficient threshold of 0.50: for example, A1>0.50, exists, go to S43.

[0124] Step S43: Calculate the comprehensive matching weight value = 10. Determine if 10 is greater than the preset matching weight threshold of 8. If yes, the robot's operation monitoring method is as follows: If the number of obstacle avoidance failures in the sub-region within the last 7 days exceeds the second preset failure number of 5 times, then the remaining matching sub-region is used to identify and analyze the robot's operating status, that is, it is forced to operate in the remaining matching sub-region to determine whether there is an obstacle avoidance failure. That is, when the number of obstacle avoidance failures in the remaining matching sub-region is greater than the preset failure number threshold of 2 times, then its operating status is determined to be abnormal.

[0125] Example 2 In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for monitoring the operation of a robot in a sorting system when running the computer program.

[0126] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0127] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0128] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for monitoring the operation of a robot in a sorting system, characterized in that, Specifically, it includes: Using the usage data of the sorting system robots in each sub-area of ​​the warehouse at different times, the usage demand time period of the sub-area is determined. Using the usage demand time period of each sub-area and the number of robots used during the usage demand time period, the identification strategy of the verification and identification sub-area in the sub-area is determined. Based on the verification and identification sub-regions and the number of robots used in each verification and identification sub-region, the scheduling and management method of robots in the verification and identification sub-regions is determined; Based on the scheduling management method, the scheduling of robots used in the verification and identification sub-region is processed. Using the scheduling management data of robots in different verification and identification sub-regions, the time period in which robots in other sub-regions do not have obstacle avoidance failure data in the most recent preset time period is determined, and this time period is used as the matching usage time period in the verification and identification sub-region. Using the scheduling and usage data of robots in other sub-regions in the verification and identification sub-region and the matching usage time periods in each verification and identification sub-region, the update processing strategy of the matching deviation sub-region in the verification and identification sub-region is determined. By utilizing the update processing results of the matching deviation sub-regions and the verification data from the matching usage periods in different matching sub-regions, a method for monitoring the operation of the robot is determined.

2. The robot operation monitoring method for a sorting system as described in claim 1, characterized in that, The robot usage data for the sub-region at different time periods includes the number of robots used in the sub-region at different time periods.

3. The robot operation monitoring method for a sorting system as described in claim 1, characterized in that, The usage demand period is the period during which the number of robots used exceeds a preset threshold.

4. The robot operation monitoring method for a sorting system as described in claim 1, characterized in that, The method for determining the identification strategy of the verification identification sub-region in the sub-region is as follows: Determine the percentage of usage demand periods in each sub-region based on the usage demand periods in each sub-region; The usage demand weight value for each usage demand period is determined based on the number of robots used during different usage demand periods. The identification strategy for the verification and identification sub-regions in each sub-region is determined based on the proportion of usage demand time periods in each sub-region and the usage demand weight value in each usage demand time period.

5. The robot operation monitoring method for a sorting system as described in claim 4, characterized in that, The identification strategy for the verification and identification sub-regions in each sub-region is determined based on the proportion of usage demand time periods in each sub-region and the usage demand weight value within those time periods. Specifically, this includes: If the average percentage of usage demand time periods in each sub-region is above a preset demand time period percentage threshold, then the identification strategy of the verification identification sub-region in the sub-region is determined as the target screening identification strategy.

6. The robot operation monitoring method for a sorting system as described in claim 5, characterized in that, The target screening and identification strategy specifically includes: Locations in the sub-region that contain obstacle avoidance failure data and whose number of obstacle avoidance failures within the most recent preset time period is less than a preset failure number threshold are designated as available verification locations. If the number of available verification locations in the sub-region is greater than a preset available location number threshold, then the sub-region is determined to belong to the verification and identification sub-region.

7. The robot operation monitoring method for a sorting system as described in claim 1, characterized in that, The method for determining the scheduling and management method of robots in the verification and identification sub-region is as follows: Based on the aforementioned verification and identification sub-regions, determine the number of verification and identification sub-regions; Based on the number of robots used in each verification and identification sub-region, the proportion of usage demand time periods in the verification and identification sub-region is determined, and the proportion of usage demand time periods in the verification and identification sub-region is used as the verification matching weight value of the verification and identification sub-region. By utilizing the number of verification and identification sub-regions and the verification matching weight values ​​of different verification and identification sub-regions, a scheduling and management method for robots in the verification and identification sub-regions is determined.

8. The robot operation monitoring method for a sorting system as described in claim 7, characterized in that, The scheduling and management method for robots in the verification and recognition sub-regions is determined by utilizing the number of verification and recognition sub-regions and the verification matching weight values ​​of different verification and recognition sub-regions, specifically including: Using the number of verification and identification sub-regions and the verification matching weight values ​​of different verification and identification sub-regions, the sum of the verification matching weight values ​​of different verification and identification sub-regions is determined and used as the comprehensive matching weight value. It is then determined whether the comprehensive matching weight value is greater than the matching weight threshold. If it is, the scheduling and management method of the robot in the verification and identification sub-region is determined to be the third preset scheduling and management method. If not, the scheduling and management method of the robot in the verification and identification sub-region is determined to be the preset scheduling and management method.

9. The robot operation monitoring method for a sorting system as described in claim 8, characterized in that, The second preset scheduling management method is as follows: if the number of robots that have failed to avoid obstacles in a certain location in the verification and identification sub-region within the most recent preset time period is greater than the preset threshold for the number of robots that have failed to avoid obstacles, then robots that have not failed to avoid obstacles in other sub-regions within the most recent preset time period are used in the verification and identification sub-region to determine whether there is a failure to avoid obstacles.

10. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a robot operation monitoring method for a sorting system as described in any one of claims 1-9.

Images