Mobile robot system early warning method, electronic equipment and storage medium

Abstract

The invention discloses a mobile robot system early warning method, electronic equipment and a storage medium, the method is applied to a mobile robot system, and the method comprises the following steps: obtaining current index values respectively corresponding to a plurality of evaluation indexes of the mobile robot system, the plurality of evaluation indexes belong to at least two of the following dimensions: an equipment fault condition, a platform service operation condition, a task execution condition and a congestion condition; determining a system score of the mobile robot system based on the current index values corresponding to the plurality of evaluation indexes; and performing early warning on the mobile robot system based on the system score. According to the scheme, the operation reliability of the mobile robot system can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of mobile robots, and in particular to a mobile robot system early warning method, electronic equipment, and storage medium. Background Art

[0002] In the existing technology, there are obvious limitations in the evaluation methods for the operating efficiency of autonomous mobile robots (AMR) systems. Specifically, the indicator dimensions and definitions used in the current evaluation system are too single, mainly focusing on isolated indicators such as hardware performance or task completion rate, and failing to fully integrate multi-dimensional factors such as equipment operating capabilities, platform software stability, and overall system coordination, resulting in the evaluation results being difficult to fully reflect the true operating status of the AMR system. In addition, the existing methods lack the ability to dynamically identify potential risks in the system, cannot accurately assess whether the current system has operational risks, and are difficult to predict the future operating trends of the system. This single-dimensional evaluation model not only limits the comprehensive optimization of AMR system performance, but may also lead to the accumulation of potential risks, ultimately affecting the reliability and stability of the system. Summary of the Invention

[0003] This application at least provides a mobile robot system early warning method, electronic equipment, and storage medium, which can improve the reliability of the mobile robot system operation.

[0004] The first aspect of the present application provides a mobile robot system early warning method, which is applied to a mobile robot system. The method includes: obtaining current indicator values corresponding to several evaluation indicators of the mobile robot system, wherein the several evaluation indicators belong to at least two of the following dimensions: equipment failure condition, platform service operation condition, task execution condition and congestion condition; determining the system score of the mobile robot system based on the current indicator values corresponding to the several evaluation indicators; and issuing an early warning to the mobile robot system based on the system score.

[0005] Among them, several evaluation indicators include at least one of the following: the average number of equipment failures, the number of platform service operation anomalies, the task failure rate, the task untimely rate and the congestion anomaly rate, among which the average number of equipment failures represents the ratio of the total number of failures reported by all devices in the mobile robot system per unit time to the total number of all running devices, the number of platform service operation anomalies represents the sum of the number of anomalies in the platform software layer of the mobile robot system per unit time, the task failure rate represents the ratio of the number of tasks that failed to be executed in the mobile robot system per unit time to the total number of executed tasks, the task untimely rate represents the ratio of the number of tasks that cannot be completed within the specified time in the mobile robot system per unit time to the total number of executed tasks, and the congestion anomaly rate represents the ratio of the number of abnormal congestions of devices in the mobile robot system per unit time to the total number of congestions.

[0006] Among them, the system score includes at least one of the system operation score and the risk quantification score; based on the current indicator values corresponding to several evaluation indicators, the system score of the mobile robot system is determined, including: determining the actual indicator score of each evaluation indicator based on the current indicator value corresponding to each evaluation indicator; weighting the actual indicator scores of several evaluation indicators to obtain the system operation score; based on the current indicator value and historical indicator value corresponding to each evaluation indicator, calculating the indicator change rate and indicator statistical value corresponding to each evaluation indicator; based on the indicator change rate and indicator statistical value corresponding to each evaluation indicator, calculating the risk quantification score.

[0007] Among them, based on the current indicator value corresponding to each evaluation indicator, the actual indicator score of each evaluation indicator is determined, including: for each evaluation indicator, the indicator value interval of the current indicator value of the evaluation indicator is determined, and the score matching the indicator value interval of the current indicator value is obtained as the actual indicator score of the evaluation indicator; and / or, several evaluation indicators include at least one first-category evaluation indicator and at least one second-category evaluation indicator; the actual indicator scores of several evaluation indicators are weighted to obtain a system operation score, including: using the weight of each first-category evaluation indicator, the actual indicator score of each first-category evaluation indicator is weighted and summed to obtain a first weighted score; and, using the weight of each second-category evaluation indicator, the actual indicator score of each second-category evaluation indicator is weighted and summed to obtain a second weighted score; using the weights of the first weighted score and the second weighted score, respectively, the first weighted score and the second weighted score are weighted and summed to obtain the system operation score.

[0008] Among them, the first type of evaluation indicators include at least one of the average number of equipment failures, the number of platform service operation anomalies, and the task failure rate; the second type of evaluation indicators include at least one of the task untimely rate and the congestion anomaly rate; and / or, the sum of the weights of each first type of evaluation indicator, the sum of the weights of each second type of evaluation indicator, and the sum of the weights of the first weighted score and the second weighted score are all preset values.

[0009] Among them, based on the current indicator value and historical indicator value corresponding to each evaluation indicator, the indicator change rate and indicator statistical value corresponding to each evaluation indicator are calculated, including at least one of the following steps: for each evaluation indicator, the difference between the current indicator value and the historical indicator value corresponding to the evaluation indicator is used as the first indicator difference value of the evaluation indicator, and the ratio between the first indicator difference of the evaluation indicator and the historical indicator value of the evaluation indicator is used as the indicator change rate corresponding to the evaluation indicator; for each evaluation indicator, a preset multiple of the ratio of the sum of the indicator values corresponding to the evaluation indicator at multiple statistical times to the total statistical time is used as the indicator statistical value, wherein the current indicator value is when The indicator value corresponding to the previous statistical time, the historical indicator value includes the indicator value corresponding to at least one previous statistical time, and the total statistical time is the sum of multiple statistical times; and / or, based on the indicator change rate and the indicator statistical value corresponding to each evaluation indicator, a risk quantification score is calculated, including: for each evaluation indicator, based on the change rate interval in which the indicator change rate of the evaluation indicator is located, determining the indicator change rate score of the evaluation indicator, and, based on the statistical value interval in which the indicator statistical value of the evaluation indicator is located, determining the indicator threshold score of the evaluation indicator; fusing the indicator change rate score and the indicator threshold score corresponding to each evaluation indicator to obtain a risk quantification score.

[0010] Among them, the indicator change rate score and indicator threshold score corresponding to each evaluation indicator are fused to obtain a risk quantification score, including: for each evaluation indicator, obtaining a fusion score of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator; using the fusion score corresponding to each evaluation indicator for weighted processing to obtain a risk quantification score.

[0011] Among them, the result of weighted processing is the result of weighted summation; and / or, obtaining the fusion score of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator, including: taking the sum of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator as the fusion score corresponding to the evaluation indicator; and / or, using the fusion score corresponding to each evaluation indicator for weighted processing to obtain a risk quantification score, including: taking the preset ratio of the result of weighted processing as the risk quantification score, and the sum of the weights of the fusion scores corresponding to each evaluation indicator is the inverse of the preset ratio.

[0012] Among them, the system score includes at least one of the system operation score and the risk quantification score; based on the system score, an early warning is issued to the mobile robot system, including: in response to the system score including the system operation score, when the system operation score does not meet the preset operation score requirement, based on the actual indicator score of each evaluation indicator, a problem evaluation indicator is selected from several evaluation indicators as the main problem point of the mobile robot system, wherein the actual indicator score is determined based on the current indicator value of the evaluation indicator; in response to the system score including the risk quantification score, when the risk quantification score does not meet the preset risk score requirement, based on at least one risk-related score corresponding to each evaluation indicator, a risk evaluation indicator is selected from several evaluation indicators as the risk point of the mobile robot system, wherein the several risk-related scores are determined based on the current indicator value and historical indicator value of the evaluation indicator.

[0013] Among them, based on the actual indicator score of each evaluation indicator, a problem evaluation indicator is selected from several evaluation indicators as the main problem point of the mobile robot system, including: selecting the problem evaluation indicator with the lowest actual indicator score from several evaluation indicators as the main problem point of the mobile robot system; and / or, the risk-related score includes at least one of the indicator change rate score and the indicator threshold score; and / or, based on at least one risk-related score corresponding to each evaluation indicator, a risk evaluation indicator is selected from several evaluation indicators as the risk point of the mobile robot system, including: selecting at least one risk evaluation indicator with the lowest sum of risk-related scores from several evaluation indicators as the risk point of the mobile robot system.

[0014] The second aspect of the present application provides an electronic device, comprising a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the mobile robot system early warning method in the above-mentioned first aspect.

[0015] A third aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, which, when executed by a processor, implements the mobile robot system early warning method in the first aspect.

[0016] The above solution first selects evaluation indicators from at least two of four dimensions: equipment failure, platform service operation, task execution, and congestion. The current value for each evaluation indicator is then obtained in real time. Subsequently, the current value for each evaluation indicator is used to calculate the mobile robot system's system score. This system score automatically triggers an early warning mechanism for the mobile robot system, enabling risk warning and localization. This comprehensive evaluation of multi-dimensional indicators comprehensively reflects the operational status of the mobile robot system, avoiding the limitations of single-metric evaluation. The resulting system score enables dynamic monitoring and timely early warning, providing a precise basis for operational and maintenance decisions, thereby improving the operational reliability of the mobile robot system.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present application and, together with the specification, are used to illustrate the technical solutions of the present application.

[0019] Figure 1 This is a flow chart of an embodiment of the mobile robot system early warning method of the present application;

[0020] Figure 2 This is a flow chart of an embodiment of step S120 in the mobile robot system early warning method of the present application;

[0021] Figure 3 This is a flow chart of another embodiment of the mobile robot system early warning method of the present application;

[0022] Figure 4 This is a structural diagram of an embodiment of the mobile robot system early warning device of the present application;

[0023] Figure 5 This is a schematic diagram of the framework of an embodiment of the electronic device of the present application;

[0024] Figure 6 It is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application in detail with reference to the accompanying drawings.

[0026] In the following description, for the purpose of explanation rather than limitation, specific details such as specific system structures, interfaces, and technologies are provided to facilitate a thorough understanding of the present application.

[0027] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the previous and next associated objects are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C, can mean including any one or more elements selected from the set consisting of A, B, and C.

[0028] In numerous fields, including industrial automation, logistics and warehousing, and intelligent services, mobile robotic systems have become a key technology for improving production efficiency, reducing labor costs, and enhancing service quality. With the widespread adoption of mobile robotic systems, their operational reliability has drawn significant attention. Traditional evaluation methods often have limitations, making it difficult to comprehensively and real-timely reflect the system's operational status.

[0029] Existing technologies for mobile robot system evaluation have several shortcomings. For example, single-metric evaluation methods cannot fully reflect the system's operating status, easily leading to biased evaluation results. Furthermore, traditional evaluation methods often lack real-time and dynamic capabilities, failing to promptly capture changes and potential risks in system operation.

[0030] This proposal innovatively proposes a mobile robot system early warning method that uses multi-dimensional evaluation indicators to calculate a system score. Based on the system score, the mobile robot system can automatically trigger an early warning mechanism to achieve risk warning and location.

[0031] See also Figure 1 , Figure 1 This is a flow chart of an embodiment of the mobile robot system early warning method of the present application. Specifically, it may include the following steps:

[0032] Step S110: obtaining current index values corresponding to several evaluation indexes of the mobile robot system.

[0033] Among them, several evaluation indicators belong to at least two of the following dimensions: equipment failure conditions, platform service operation conditions, task execution conditions, and congestion conditions.

[0034] In some implementations, sensor detection may be used to obtain current indicator values corresponding to several evaluation indicators of the mobile robot system.

[0035] Specifically, by installing sensors on key components and equipment in a mobile robot system, such as temperature sensors, current sensors, and vibration sensors, the operating status of the equipment can be monitored in real time. For example, if a motor in a robot system experiences excessive temperature, abnormal current, or excessive vibration, the sensors can promptly detect these changes and transmit the data to the control system, thereby obtaining current indicators of the equipment's fault condition.

[0036] Furthermore, LiDAR and infrared sensors can be deployed within the mobile robot's operating environment to monitor congestion in corridors and work areas in real time. For example, LiDAR can scan the surrounding environment and determine whether there are accumulated obstacles or gatherings of people, thereby determining an indicator of congestion levels.

[0037] In other embodiments, data analysis and processing may be used to obtain current indicator values corresponding to several evaluation indicators of the mobile robot system.

[0038] Specifically, data related to the mobile robot system's platform services is collected, such as server response time, data transmission rate, and system resource utilization. By analyzing this data, the operational quality of the platform services can be assessed, resulting in current indicators related to the platform service's performance. For example, the average and fluctuation range of server response time can be calculated. If the response time is too long or fluctuates significantly, this indicates a possible anomaly in the platform service, and the corresponding indicator value can be obtained.

[0039] Analyze historical data on mobile robot missions, including mission completion time, mission success rate, and number of mission interruptions. For example, by calculating the average time it takes to complete a mission within a certain period and comparing it with a set standard time, we can derive an indicator of mission execution efficiency. Alternatively, we can calculate the mission success rate, which is the ratio of successfully completed missions to the total number of missions, as a key indicator of mission execution.

[0040] Furthermore, mobile robot systems typically record operational logs, which contain information about equipment failures and maintenance records. Therefore, by analyzing these logs, we can obtain the current values corresponding to several evaluation indicators. For example, by analyzing and organizing these logs, we can obtain historical data on equipment failures and, based on the current operational status, update the indicator values for equipment failures.

[0041] The platform service operation log can reflect the system service start and stop time, error information, user access records, etc. Analyzing these logs helps to understand the stability and reliability of the platform service, thereby determining its current operation indicator value.

[0042] In some embodiments, the plurality of evaluation indicators include at least one of the following: average number of equipment failures, number of platform service operation anomalies, task failure rate, task untimely rate, and congestion anomaly rate.

[0043] The average number of device failures represents the ratio of the total number of failures reported by all devices in the mobile robot system per unit time to the total number of all running devices:

[0044] Average number of equipment failures = total number of failures / total number of devices, unit: times / device. Devices can include AMRs and third-party devices within the system, such as equipment loads, AMR charging stations, and floor scrubber robots.

[0045] The number of platform service operation exceptions refers to the sum of the number of exceptions in the platform software layer of the mobile robot system per unit time. The platform software layer is mainly responsible for task processing and issuance, device interaction and management, etc.

[0046] The task failure rate represents the ratio of the number of tasks that failed to execute in a mobile robot system to the total number of executed tasks per unit time:

[0047] Task failure rate = number of failed tasks / total number of executed tasks * 100%.

[0048] The task delay rate refers to the ratio of the number of tasks that cannot be completed within the specified time to the total number of tasks executed in the mobile robot system per unit time:

[0049] Task delay rate = number of tasks that cannot be completed within the specified time / total number of executed tasks * 100%. The total number of executed tasks refers to the total number of tasks completed within a unit of time (day).

[0050] The congestion anomaly rate indicates the ratio of the number of abnormal congestion times of devices in the mobile robot system to the total number of congestion times per unit time:

[0051] Congestion abnormality rate = number of congestion abnormalities / total number of congestion times*100%.

[0052] Among them, the three evaluation indicators of average equipment failures, number of platform service operation anomalies, and task failure rate can be comprehensively constituted as an indicator reflecting the abnormality of the AMR system. The two indicators of task untimely rate and congestion abnormality rate can be comprehensively constituted as an indicator reflecting the efficiency of the AMR system.

[0053] In addition, evaluation indicators may also include: overall equipment efficiency, mean time between failures, task execution accuracy, and task result consistency. Among them, overall equipment efficiency: the product of time availability, performance availability, and qualified product rate, comprehensively reflects the efficiency of the equipment; mean time between failures: the ratio of the total time of trouble-free operation to the number of failures during the statistical base period, reflecting the health of the equipment; task execution accuracy: the proportion of task execution results that meet expected requirements; task result consistency: the degree of consistency of the results of the same task executed at different times or on different equipment. Furthermore, overall equipment efficiency and mean time between failures are evaluation indicators used to reflect equipment performance and reliability, while task execution accuracy and task result consistency are evaluation indicators used to reflect task quality.

[0054] Step S120: Determine the system score of the mobile robot system based on the current indicator values corresponding to the evaluation indicators.

[0055] In some embodiments, before calculating the system score, an evaluation system needs to be determined. Through this evaluation system, a corresponding weight is assigned to each evaluation indicator based on the specific application scenario and needs to reflect its importance in the overall evaluation. Then, the scores of all dimensions in the evaluation indicator are multiplied by their total weights and summed to obtain the system score of the mobile robot. In this embodiment, the system score includes at least one of the system operation score and the risk quantification score. The system operation score is used to evaluate the operating capability of the mobile robot system, and the risk quantification score is used to reflect the hidden dangers in the mobile robot system. For details, please refer to Figure 2 , Figure 2 This is a flow chart of an embodiment of step S120 in the mobile robot system early warning method of the present application. Specifically, it may include the following steps:

[0056] Step S121: determining the actual indicator score of each evaluation indicator based on the current indicator value corresponding to each evaluation indicator.

[0057] In some embodiments, after obtaining the current indicator value corresponding to each evaluation indicator, for each evaluation indicator, the indicator value interval in which the current indicator value of the evaluation indicator is located is determined, and a score matching the indicator value interval in which the current indicator value is located is obtained as the actual indicator score of the evaluation indicator.

[0058] Specifically, x i represents the current index value of the i-th evaluation index, then the actual score S of the five evaluation indicators is i The calculation is as follows:

[0059] 1. x1 represents the current index value of the first evaluation index, that is, the current index value of the average number of equipment failures. The actual score S1 of the average number of equipment failures is calculated as follows:

[0060]

[0061] 2. x2 represents the current indicator value of the second evaluation indicator, that is, the current indicator value of the number of platform service operation anomalies. The actual score S2 of the number of platform service operation anomalies is calculated as follows:

[0062]

[0063] 3. x3 represents the current indicator value of the third evaluation indicator, that is, the current indicator value of the task failure rate. The actual score S3 of the task failure rate is calculated as follows:

[0064]

[0065] 4. x4 represents the current indicator value of the fourth evaluation indicator, that is, the current indicator value of the task delay rate. The actual score S4 of the task delay rate is calculated as follows:

[0066]

[0067] 5. x5 represents the current index value of the fifth evaluation index, that is, the current index value of the congestion abnormality rate. The actual score S5 of the congestion abnormality rate is calculated as follows:

[0068]

[0069] From the above, we can see that the actual score calculation methods of some evaluation indicators are the same, while the actual score calculation methods of some evaluation indicators are different.

[0070] Step S122: Perform weighted processing on the actual indicator scores of several evaluation indicators to obtain a system operation score.

[0071] In some embodiments, the actual index scores of several evaluation indicators can be directly weighted to obtain the system operation score. 总 =a1×S1+a2×S2+a3×S3+a4×S4+a5×S5, where a1+a2+a3+a4+a5=1.S 总 Score the system operation.

[0072] In other embodiments, considering that evaluation indicators of different categories may have different dimensions and magnitudes, directly performing weighted summation may cause certain evaluation indicators to have too large or too small an impact on the total score. Therefore, a classification method is first adopted to classify evaluation indicators of different properties, and then the classified evaluation indicators are used to calculate the system operation score. Specifically, the evaluation indicators include at least one first-category evaluation indicator and at least one second-category evaluation indicator. Then, using the weight of each first-category evaluation indicator, the actual indicator score of each first-category evaluation indicator is weighted and summed to obtain a first weighted score. And, using the weight of each second-category evaluation indicator, the actual indicator score of each second-category evaluation indicator is weighted and summed to obtain a second weighted score. Finally, using the weight corresponding to the first weighted score and the weight corresponding to the second weighted score, the first weighted score and the second weighted score are weighted and summed to obtain the system operation score.

[0073] For example, the first type of evaluation indicators includes at least one of the average number of equipment failures, the number of platform service operation anomalies, and the task failure rate, and the second type of evaluation indicators includes at least one of the task delay rate and the congestion anomaly rate. In addition, the sum of the weights of each first type of evaluation indicator, the sum of the weights of each second type of evaluation indicator, and the sum of the weights of the first weighted score and the second weighted score are all preset values. In this embodiment, the preset value is 1, so the system operation score is calculated as follows:

[0074]

[0075] in,

[0076] Step S123: Based on the current indicator value and the historical indicator value corresponding to each evaluation indicator, the indicator change rate and the indicator statistical value corresponding to each evaluation indicator are calculated.

[0077] In some embodiments, for each evaluation indicator, to obtain the indicator change rate corresponding to each evaluation indicator, the difference between the current indicator value and the historical indicator value corresponding to the evaluation indicator can be first used as the first indicator difference value of the evaluation indicator, and then the ratio between the first indicator difference value of the evaluation indicator and the historical indicator value of the evaluation indicator can be used as the indicator change rate corresponding to the evaluation indicator. Specifically, formula (7) can be combined:

[0078]

[0079] Among them, R i Indicates the index change rate of the i-th evaluation index, x i|t represents the current indicator value of the i-th evaluation indicator at the current time t, x i|t-1 represents the historical index value of the i-th evaluation index within the previous time t-1, x i|t-x i|t-1 The first indicator difference.

[0080] For each evaluation indicator, to obtain the corresponding indicator statistical value, a preset multiple of the ratio of the sum of the indicator values corresponding to multiple statistical times to the total statistical time is used as the indicator statistical value. The current indicator value is the indicator value corresponding to the current statistical time, the historical indicator value includes the indicator value corresponding to at least one previous statistical time, and the total statistical time is the sum of multiple statistical times. Specifically, it can be combined with formula (8):

[0081]

[0082] Among them, T i represents the statistical value of the i-th evaluation indicator, x i|j represents the index value of the i-th evaluation index at time j, t is the total statistical time, and m is the preset multiple. In this embodiment, m=2.

[0083] Step S124: Calculate the risk quantification score based on the indicator change rate and indicator statistical value corresponding to each evaluation indicator.

[0084] In some embodiments, for each evaluation indicator, the indicator change rate score of the evaluation indicator is determined based on the change rate interval of the indicator change rate of the evaluation indicator, and the indicator threshold score of the evaluation indicator is determined based on the statistical value interval of the indicator statistical value of the evaluation indicator. Among them, the indicator change rate score focuses on the change trend of the evaluation indicator over time, which helps to discover which risks are gradually worsening; the indicator threshold score focuses on whether the evaluation indicator exceeds the normal range, which can capture sudden abnormal situations in time. By fusing the two, the potential risks of the mobile robot system in different aspects can be more comprehensively evaluated. Afterwards, the indicator change rate score and the indicator threshold score corresponding to each evaluation indicator are fused to obtain a risk quantification score. Specifically, please refer to formulas (9) and (10):

[0085]

[0086]

[0087] in, It represents the index change rate score of the i-th evaluation index, Represents the indicator threshold score of the i-th evaluation indicator.

[0088] For each evaluation metric, before fusing the corresponding indicator change rate score and indicator threshold score, a fused score of the corresponding indicator change rate score and indicator threshold score can be obtained. The fused score for each evaluation metric is then weighted to produce a risk quantification score. Specifically, the sum of the corresponding indicator change rate score and the indicator threshold score is used as the fused score for the evaluation metric. A preset ratio of the weighted results is then used as the risk quantification score, with the sum of the weights of the fused scores for each evaluation metric being the inverse of the preset ratio. A weighted approach is employed to calculate the risk quantification score, assigning different weights to each evaluation metric based on its importance to the system risk. This approach can highlight the impact of key indicators on the risk quantification score, making the assessment results more realistic. For example, for a mobile robot operating in a complex environment, the accuracy of the perception system may be more critical than the execution time of a single task. By assigning appropriate weights, the risk quantification score can be more representative of the system's core risks.

[0089] The result of weighted processing is the result of weighted summation. Please refer to formula (11):

[0090]

[0091] Among them, S 风 It is important to note that W in formula (11) i and W in formula (6) i Similarly, 1 / 2 is the reciprocal of the preset ratio.

[0092] Step S130: Based on the system score, an early warning is issued to the mobile robot system.

[0093] In some embodiments, a mobile robot system can be warned based on the system score. For example, if the system score includes a system operation score, if the system operation score does not meet the preset operation score requirements, a problem evaluation indicator is selected from a number of evaluation indicators based on the actual indicator scores of each evaluation indicator, as the main problem point of the mobile robot system, wherein the actual indicator score is determined based on the current indicator value of the evaluation indicator. In order to accurately locate the main problem point, an intuitive and effective method can be adopted: from a number of evaluation indicators, the problem evaluation indicator with the lowest actual indicator score is selected as the main problem point of the mobile robot system. In this way, the parts of the mobile robot system that are most in need of improvement can be quickly and accurately identified, providing clear direction guidance for subsequent optimization and upgrades, thereby improving the performance and performance of the entire system and ensuring that the robot can operate stably and efficiently in various complex and changing task scenarios.

[0094] For another example, if the system score includes a risk quantification score, and the risk quantification score does not meet the preset risk score requirements, a risk assessment indicator is selected from a number of evaluation indicators based on at least one risk-related score corresponding to each evaluation indicator to serve as the risk point for the mobile robot system. The risk-related scores are determined based on the current and historical values of the evaluation indicators. The risk-related scores include at least one of an indicator change rate score and an indicator threshold score. The indicator change rate score reflects the changing trend of the evaluation indicator over time, helping the system identify situations where the indicator value fluctuates abnormally or changes too quickly, which often indicate potential risks. The indicator threshold score is determined based on whether the evaluation indicator exceeds the preset normal range. When the indicator value approaches or exceeds the threshold, the system risk increases accordingly. By comprehensively considering these risk-related scores, the degree of risk inherent in each evaluation indicator can be comprehensively assessed.

[0095] To accurately identify risk points in a mobile robot system, one can select at least one risk assessment indicator with the lowest sum of risk-related scores from a number of evaluation indicators. This indicator is considered as the risk point in the mobile robot system. The advantage of this approach is that it not only considers the impact of a single risk factor but also integrates the combined effects of multiple risk factors, making the risk assessment more comprehensive and accurate. This approach can quickly and accurately identify the highest-risk aspects of the system, providing clear guidance for subsequent risk management and system optimization. For example, if the sum of the risk-related scores of a particular evaluation indicator is significantly lower than that of other indicators, this indicates that the system function or performance represented by this indicator has a higher risk and requires priority improvement and optimization.

[0096] See also Figure 3 , Figure 3 This is a flow chart of another embodiment of the mobile robot system early warning method of the present application. Specifically, it may include the following steps:

[0097] Step S310: Obtain current indicator values and historical indicator values corresponding to several evaluation indicators of the mobile robot system.

[0098] In some embodiments, the current indicator value corresponding to the evaluation indicator can be directly obtained through sensors, or through data analysis or other methods. The historical indicator value corresponding to the evaluation indicator can be retrieved from a database. Specifically, the corresponding data in the database can be retrieved based on the unique identifier corresponding to the evaluation indicator. Alternatively, the historical indicator value corresponding to the evaluation indicator can be obtained from the local storage space of the mobile robot system.

[0099] Step S320: Determine the system score of the mobile robot system based on the current indicator values corresponding to the evaluation indicators.

[0100] This step is the same as the above step S120 and will not be described again here.

[0101] Step S330: Based on the historical indicator values corresponding to the plurality of evaluation indicators, determining the change trend of each evaluation indicator within a preset time period.

[0102] In some embodiments, historical indicator value data for evaluation indicators is analyzed to observe their changing trends and predict possible future risks. If an evaluation indicator shows a sustained upward or downward trend and approaches or exceeds a preset warning line, the system issues an alert. For example, if historical indicator value data for task failure rate is analyzed and it is found to have been rising continuously over the past month, although the current value has not yet exceeded the threshold, the upward trend indicates that there may be potential problems, requiring early warning and action. The preset time period can be one month, one week, one day, etc.

[0103] You can also analyze the changing trends of multiple related indicators together to more comprehensively determine whether the system is at risk. For example, if the average number of device failures and the number of platform service anomalies are both increasing, even if individual indicators have not yet exceeded the threshold, it may be a sign of overall system performance degradation, necessitating an early warning.

[0104] In addition, in this embodiment, the change trend can be expressed in binary form. For example, 00 indicates that the change trend is normal, 01 indicates that the change trend is continuously rising, 10 indicates that the change trend is continuously falling, and 11 indicates a sudden change in data (which can indicate a sudden rise or fall in data) and an immediate alarm is required.

[0105] Step S340: Based on the system score and change trend, an early warning is issued to the mobile robot system.

[0106] By combining the system score and the changing trends of various evaluation indicators, we can quickly and accurately locate the problem points of the mobile robot system, and at the same time, we can also issue early warnings for possible risk points in the future so that we can prepare in advance.

[0107] Based on the system score and the severity of the indicator change trend, risk warnings are divided into different levels, such as low risk, medium risk, high risk, etc. Different levels of risk warnings correspond to different response measures and processing priorities.

[0108] In some embodiments, historical indicator values corresponding to evaluation indicators can be used to train machine learning models. This model can learn the complex relationships between each evaluation indicator and system risk. For example, using algorithms such as decision trees and neural networks, a risk prediction model can be trained based on historical indicator values and corresponding risk events. During system operation, real-time evaluation indicator data is input into the trained machine learning model. The model can then automatically predict the current risk status of the system and trigger corresponding warnings based on the prediction results. This approach can improve the accuracy and intelligence of risk warnings and promptly identify potential risk issues.

[0109] This application comprehensively considers multiple dimensions such as equipment, platform services, task efficiency, and traffic congestion in the AMR operating system. The indicators are more comprehensive and more universal, and are not limited by the working scenarios of the AMR system. A risk warning method is proposed, and a calculation method for system operation risk is defined. The risk score is quantified based on the two dimensions of the comprehensive indicator change rate and the indicator statistical value. By quantifying the risk, the risk points of the current system operation can be more clearly defined, so that relevant early warning measures can be taken in time to improve the reliability and stability of the system operation. In addition, this application defines a separate scoring calculation method for each evaluation indicator, so that each indicator is independent. When the system score is low, the scores of each indicator can be combined to quickly locate the optimizable points in the current system.

[0110] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0111] See also Figure 4 , Figure 4 : This is a structural diagram of an embodiment of a mobile robot system early warning device 400 of the present application. The system early warning device 400 includes an acquisition module 410, a statistics module 420, and an early warning module 430. The acquisition module 410 executes to obtain the current indicator values corresponding to several evaluation indicators of the mobile robot system, wherein the several evaluation indicators belong to at least two of the following dimensions: equipment failure status, platform service operation status, task execution status, and congestion status. The statistics module 420 executes to determine the system score of the mobile robot system based on the current indicator values corresponding to the several evaluation indicators. The early warning module 430 executes to issue an early warning to the mobile robot system based on the system score.

[0112] In some embodiments, several evaluation indicators include at least one of the following: the average number of equipment failures, the number of platform service operation anomalies, the task failure rate, the task untimely rate and the congestion anomaly rate, wherein the average number of equipment failures represents the ratio of the total number of failures reported by all devices in the mobile robot system per unit time to the total number of all running devices, the number of platform service operation anomalies represents the sum of the number of anomalies in the platform software layer of the mobile robot system per unit time, the task failure rate represents the ratio of the number of tasks that failed to be executed in the mobile robot system per unit time to the total number of executed tasks, the task untimely rate represents the ratio of the number of tasks that cannot be completed within the specified time in the mobile robot system per unit time to the total number of executed tasks, and the congestion anomaly rate represents the ratio of the number of abnormal congestions that occur in the equipment in the mobile robot system per unit time to the total number of congestions.

[0113] In some embodiments, the statistical module 420 executes a system score including at least one of a system operation score and a risk quantification score; based on the current indicator values corresponding to several evaluation indicators, the system score of the mobile robot system is determined, including: determining the actual indicator score of each evaluation indicator based on the current indicator value corresponding to each evaluation indicator; weighting the actual indicator scores of several evaluation indicators to obtain a system operation score; based on the current indicator value and historical indicator value corresponding to each evaluation indicator, calculating the indicator change rate and indicator statistical value corresponding to each evaluation indicator; based on the indicator change rate and indicator statistical value corresponding to each evaluation indicator, calculating the risk quantification score.

[0114] In some embodiments, the statistical module 420 determines the actual indicator score of each evaluation indicator based on the current indicator value corresponding to each evaluation indicator, including: for each evaluation indicator, determining the indicator value interval in which the current indicator value of the evaluation indicator is located, and obtaining a score that matches the indicator value interval in which the current indicator value is located as the actual indicator score of the evaluation indicator; and / or, several evaluation indicators include at least one first-category evaluation indicator and at least one second-category evaluation indicator; weighted processing is performed on the actual indicator scores of several evaluation indicators to obtain a system operation score, including: using the weight of each first-category evaluation indicator, weighted summing the actual indicator scores of each first-category evaluation indicator to obtain a first weighted score; and, using the weight of each second-category evaluation indicator, weighted summing the actual indicator scores of each second-category evaluation indicator to obtain a second weighted score; using the weights of the first weighted score and the second weighted score, respectively, weighted summing the first weighted score and the second weighted score to obtain a system operation score.

[0115] In some embodiments, the statistical module 420 executes the first category of evaluation indicators including the average number of equipment failures, the number of platform service operation anomalies, and the task failure rate, and the second category of evaluation indicators including at least one of the task untimely rate and the congestion anomaly rate; and / or, the sum of the weights of each first category of evaluation indicators, the sum of the weights of each second category of evaluation indicators, the sum of the weights of the first weighted score and the second weighted score are all preset values.

[0116] In some embodiments, the statistical module 420 calculates the indicator change rate and indicator statistical value corresponding to each evaluation indicator based on the current indicator value and the historical indicator value corresponding to each evaluation indicator, including at least one of the following steps: for each evaluation indicator, the difference between the current indicator value and the historical indicator value corresponding to the evaluation indicator is used as the first indicator difference value of the evaluation indicator, and the ratio between the first indicator difference value of the evaluation indicator and the historical indicator value of the evaluation indicator is used as the indicator change rate corresponding to the evaluation indicator; for each evaluation indicator, a preset multiple of the ratio of the sum of the indicator values corresponding to the evaluation indicator at multiple statistical times to the total statistical time is used as the indicator statistical value, wherein, The current indicator value is the indicator value corresponding to the current statistical time, the historical indicator value includes the indicator value corresponding to at least one previous statistical time, and the total statistical time is the sum of multiple statistical times; and / or, based on the indicator change rate and the indicator statistical value corresponding to each evaluation indicator, a risk quantification score is calculated, including: for each evaluation indicator, based on the change rate interval in which the indicator change rate of the evaluation indicator is located, determining the indicator change rate score of the evaluation indicator, and, based on the statistical value interval in which the indicator statistical value of the evaluation indicator is located, determining the indicator threshold score of the evaluation indicator; fusing the indicator change rate score and the indicator threshold score corresponding to each evaluation indicator to obtain a risk quantification score.

[0117] In some embodiments, the statistical module 420 performs a fusion of the indicator change rate score and the indicator threshold score corresponding to each evaluation indicator to obtain a risk quantification score, including: for each evaluation indicator, obtaining a fusion score of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator; using the fusion score corresponding to each evaluation indicator for weighted processing to obtain a risk quantification score.

[0118] In some embodiments, the result of the weighted processing performed by the statistical module 420 is the result of weighted summation; and / or, a fusion score of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator is obtained, including: the sum of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator is used as the fusion score corresponding to the evaluation indicator; and / or, weighted processing is performed using the fusion score corresponding to each evaluation indicator to obtain a risk quantification score, including: a preset ratio of the result of the weighted processing is used as the risk quantification score, and the sum of the weights of the fusion scores corresponding to each evaluation indicator is the inverse of the preset ratio.

[0119] In some embodiments, the early warning module 430 executes a system score including at least one of a system operation score and a risk quantification score; based on the system score, an early warning is issued to the mobile robot system, including: in response to the system score including the system operation score, when the system operation score does not meet the preset operation score requirements, based on the actual indicator score of each evaluation indicator, a problem evaluation indicator is selected from several evaluation indicators as the main problem point of the mobile robot system, wherein the actual indicator score is determined based on the current indicator value of the evaluation indicator; in response to the system score including the risk quantification score, when the risk quantification score does not meet the preset risk score requirements, based on at least one risk-related score corresponding to each evaluation indicator, a risk evaluation indicator is selected from several evaluation indicators as the risk point of the mobile robot system, wherein the several risk-related scores are determined based on the current indicator value and historical indicator value of the evaluation indicator.

[0120] In some embodiments, the early warning module 430 executes the selection of problem evaluation indicators from several evaluation indicators based on the actual indicator scores of each evaluation indicator as the main problem points of the mobile robot system, including: selecting the problem evaluation indicator with the lowest actual indicator score from several evaluation indicators as the main problem points of the mobile robot system; and / or, the risk-related score includes at least one of the indicator change rate score and the indicator threshold score; and / or, based on at least one risk-related score corresponding to each evaluation indicator, selecting a risk evaluation indicator from several evaluation indicators as the risk point of the mobile robot system, including: selecting at least one risk evaluation indicator with the lowest sum of risk-related scores from several evaluation indicators as the risk point of the mobile robot system.

[0121] See also Figure 5 , Figure 5 FIG2 is a schematic diagram of an embodiment of an electronic device 50 of the present application. The electronic device 50 includes a memory 51 and a processor 52 coupled to each other. The processor 52 is configured to execute program instructions stored in the memory 51 to implement the steps of any of the aforementioned embodiments of the mobile robot system early warning method. In a specific implementation scenario, the electronic device 50 may include, but is not limited to, a microcomputer and a server. Furthermore, the electronic device 50 may also include mobile devices such as laptops and tablet computers, which are not limited herein.

[0122] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps in any of the above-mentioned mobile robot system early warning method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0123] See also Figure 6 , Figure 6 Schematic diagram of a computer-readable storage medium 60 according to an embodiment of the present invention. The computer-readable storage medium 60 stores program instructions 601 that can be executed by a processor, and the program instructions 601 are used to implement the steps of any of the above-mentioned mobile robot system early warning method embodiments.

[0124] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments. For the sake of brevity, it will not be repeated here.

[0125] The above description of the various embodiments tends to emphasize the differences between the various embodiments. The same or similar aspects can be referenced with each other and will not be repeated herein for the sake of brevity.

[0126] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation methods described above are only illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0127] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A mobile robot system early warning method, characterized in that: The method is applied to a mobile robot system, and the method comprises: Obtaining current indicator values corresponding to a plurality of evaluation indicators of the mobile robot system, wherein the plurality of evaluation indicators belong to at least two of the following dimensions: equipment failure status, platform service operation status, task execution status, and congestion status; Determining a system score of the mobile robot system based on current indicator values corresponding to the plurality of evaluation indicators; Based on the system score, an early warning is issued to the mobile robot system.

2. The method according to claim 1, characterized in that The several evaluation indicators include at least one of the following: the average number of equipment failures, the number of platform service operation anomalies, the task failure rate, the task untimely rate and the congestion anomaly rate, wherein the average number of equipment failures represents the ratio of the total number of failures reported by all devices in the mobile robot system per unit time to the total number of all running devices, the number of platform service operation anomalies represents the sum of the number of anomalies of the platform software layer of the mobile robot system per unit time, the task failure rate represents the ratio of the number of tasks that failed to be executed in the mobile robot system per unit time to the total number of executed tasks, the task untimely rate represents the ratio of the number of tasks that cannot be completed within the specified time in the mobile robot system per unit time to the total number of executed tasks, and the congestion anomaly rate represents the ratio of the number of abnormal congestion occurring in the equipment in the mobile robot system per unit time to the total number of congestion times.

3. The method according to claim 1, characterized in that The system score includes at least one of a system operation score and a risk quantification score; The determining of the system score of the mobile robot system based on the current indicator values corresponding to the plurality of evaluation indicators includes: Determining an actual indicator score for each evaluation indicator based on the current indicator value corresponding to each evaluation indicator; Performing weighted processing on the actual indicator scores of the several evaluation indicators to obtain a system operation score; Calculate the indicator change rate and indicator statistical value corresponding to each evaluation indicator based on the current indicator value and the historical indicator value corresponding to each evaluation indicator; The risk quantification score is calculated based on the indicator change rate and indicator statistical value corresponding to each evaluation indicator.

4. The method according to claim 3, characterized in that The determining of the actual indicator score of each evaluation indicator based on the current indicator value corresponding to each evaluation indicator includes: For each evaluation indicator, determining the indicator value interval in which the current indicator value of the evaluation indicator lies, and obtaining a score that matches the indicator value interval in which the current indicator value lies as the actual indicator score of the evaluation indicator; And / or, the plurality of evaluation indicators include at least one first-category evaluation indicator and at least one second-category evaluation indicator; and the weighted processing of actual indicator scores of the plurality of evaluation indicators to obtain the system operation score includes: Using the weights of the first-category evaluation indicators, performing a weighted summation on the actual indicator scores of the first-category evaluation indicators to obtain a first weighted score; and Using the weights of the second-category evaluation indicators, perform weighted summation on the actual indicator scores of the second-category evaluation indicators to obtain a second weighted score; The first weighted score and the second weighted score are weightedly summed using the weights of the first weighted score and the second weighted score respectively to obtain the system operation score.

5. The method according to claim 4, characterized in that The first type of evaluation indicators include at least one of the average number of equipment failures, the number of platform service operation anomalies, and the task failure rate; the second type of evaluation indicators include at least one of the task delay rate and the congestion anomaly rate; And / or, the sum of the weights of the first-category evaluation indicators, the sum of the weights of the second-category evaluation indicators, and the sum of the weights of the first weighted score and the second weighted score are all preset values.

6. The method according to claim 3, characterized in that The step of calculating the indicator change rate and the indicator statistical value corresponding to each evaluation indicator based on the current indicator value and the historical indicator value corresponding to each evaluation indicator comprises at least one of the following steps: For each evaluation indicator, the difference between the current indicator value and the historical indicator value corresponding to the evaluation indicator is used as the first indicator difference value of the evaluation indicator, and the ratio between the first indicator difference value of the evaluation indicator and the historical indicator value of the evaluation indicator is used as the indicator change rate corresponding to the evaluation indicator; For each evaluation indicator, a preset multiple of the ratio of the sum of the indicator values corresponding to multiple statistical times to the total statistical time is used as the indicator statistical value, wherein the current indicator value is the indicator value corresponding to the current statistical time, the historical indicator value includes the indicator value corresponding to at least one previous statistical time, and the total statistical time is the sum of multiple statistical times; And / or, the risk quantification score is calculated based on the indicator change rate and the indicator statistical value corresponding to each evaluation indicator, including: For each of the evaluation indicators, the indicator change rate score of the evaluation indicator is determined based on the change rate interval of the indicator change rate of the evaluation indicator, and the indicator threshold score of the evaluation indicator is determined based on the statistical value interval of the indicator statistical value of the evaluation indicator; the indicator change rate score and the indicator threshold score corresponding to each of the evaluation indicators are fused to obtain a risk quantification score.

7. The method according to claim 6, characterized in that The indicator change rate score and the indicator threshold score corresponding to each evaluation indicator are integrated to obtain a risk quantification score, including: For each evaluation indicator, obtaining a fusion score of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator; The fusion score corresponding to each evaluation indicator is weighted to obtain the risk quantification score.

8. The method according to claim 7, characterized in that The result of the weighted processing is the result of weighted summation; And / or, obtaining a fusion score of an indicator change rate score and an indicator threshold score corresponding to the evaluation indicator includes: The sum of the indicator change rate score and the indicator threshold score corresponding to the evaluation indicator is used as the fusion score corresponding to the evaluation indicator; And / or, performing weighted processing on the fusion scores corresponding to the evaluation indicators to obtain the risk quantification score includes: The preset ratio of the result of the weighted processing is used as the risk quantification score, and the sum of the weights of the fusion scores corresponding to the evaluation indicators is the reciprocal of the preset ratio.

9. The method according to claim 1, characterized in that The system score includes at least one of a system operation score and a risk quantification score; The step of providing an early warning to the mobile robot system based on the system score includes: In response to the system score including the system operation score, if the system operation score does not meet a preset operation score requirement, selecting a problem evaluation indicator from the plurality of evaluation indicators based on an actual indicator score of each of the evaluation indicators as a main problem point of the mobile robot system, wherein the actual indicator score is determined based on a current indicator value of the evaluation indicator; In response to the system score including the risk quantification score, when the risk quantification score does not meet the preset risk score requirements, based on at least one risk-related score corresponding to each of the evaluation indicators, a risk evaluation indicator is selected from the several evaluation indicators to serve as the risk point of the mobile robot system, wherein the several risk-related scores are determined based on the current indicator value and historical indicator value of the evaluation indicator.

10. The method according to claim 9, characterized in that The problem evaluation indicators are selected from the plurality of evaluation indicators based on the actual indicator scores of the evaluation indicators as the main problem points of the mobile robot system, including: Selecting the problem evaluation indicator with the lowest actual indicator score from the plurality of evaluation indicators as the main problem point of the mobile robot system; and / or, the risk-related score includes at least one of an indicator change rate score and an indicator threshold score; And / or, selecting a risk evaluation indicator from the plurality of evaluation indicators based on at least one risk-related score corresponding to each of the evaluation indicators as a risk point of the mobile robot system includes: From the plurality of evaluation indicators, a risk evaluation indicator having the lowest sum of the at least one risk-related score is selected as a risk point of the mobile robot system.

11. An electronic device, characterized in that: It comprises a memory and a processor coupled to each other, wherein the processor is used to execute program instructions stored in the memory to implement the system early warning method according to any one of claims 1 to 10.

12. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the system early warning method according to any one of claims 1 to 10 is implemented.

Images