Man-machine function distribution method based on multi-target cost index evaluation

Abstract

The invention discloses a man-machine function distribution method based on multi-target cost index evaluation, and relates to the technical field of logistics distribution. According to the man-machine function distribution method based on multi-target cost index evaluation, sorting rates of each article in different working periods are obtained by analyzing manual and machine sorting historical data. The method comprises the following steps of: firstly, acquiring feature data of to-be-sorted articles and performing type division, then, calculating cost evaluation indexes of sorting staff and machines by combining historical data and article rates, and finally, comparing and analyzing the cost evaluation indexes of the staff and the machines, determining distribution measures according to an analysis result, and selecting a most suitable sorting mode. According to the method, through comprehensive analysis of the manual and machine sorting cost, especially through calculation of the manual and machine sorting rate and cost evaluation indexes, the most suitable sorting mode can be effectively selected, and therefore unnecessary resource waste can be avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics distribution, and specifically to a human-machine function allocation method based on multi-objective cost index evaluation. Background Art

[0002] With the rapid development of the logistics industry, the logistics system faces various demands and challenges. In order to improve the efficiency of logistics operations, reduce costs, and achieve optimized resource allocation, the multi-objective cost index evaluation method has emerged. This method provides a comprehensive evaluation for decision-makers by considering multiple objectives to help them select the optimal solution. In the logistics field, human-machine function allocation refers to the reasonable allocation of tasks and responsibilities between humans and machines in complex logistics operations. Machines and robots are playing an increasingly important role in warehousing, sorting, handling, transportation and other links. However, although machines can provide efficient and stable performance in many tasks, humans still have higher flexibility, adaptability and innovation ability in some cases. Therefore, reasonable human-machine function allocation is crucial for improving the efficiency of the overall logistics system and reducing costs.

[0003] The prior art, such as a sorting task allocation method, device, computer device and storage medium disclosed in the patent application with the publication number of CN1 11626581A, includes: presetting the functional attributes of the operation entities; the functional attributes include load limit and comprehensive workload limit; grouping the operation entities with the same functional attributes to obtain multiple operation groups; when receiving multiple sorting tasks, sorting the task attributes of the sorting tasks according to the instruction for difficulty level; according to the matching relationship between the task attributes of the sorting tasks and the functional attributes of the operation groups, first allocating the sorting tasks with higher ranking to the corresponding operation groups, and then allocating the sorting tasks with lower ranking to the corresponding operation groups; and controlling the sorting tasks allocated to each operation entity in the operation group to meet its load limit and comprehensive workload limit. The present invention takes into account the functional attributes of the operation entities and the task attributes of the sorting tasks, and performs sorting and allocation according to the task difficulty level, so that the allocation result is more in line with the actual situation and meets the actual work requirements.

[0004] Based on the above solutions, it is found that the limitations of the prior art at least include the following problems. The prior art ignores the fact that it is difficult to accurately evaluate the relative cost-benefit of humans and machines in different sorting tasks under different working periods, different task types, and different efficiencies of personnel and machines, resulting in a decrease in the accuracy of task allocation and difficulty in maximizing work efficiency. Secondly, the prior art does not fully consider the specific efficiency of historical working periods, such as the manual sorting rate and the machine sorting rate, making it difficult to effectively adapt to the needs of different sorted items, leading to unreasonable resource allocation of humans and machines, and then affecting the overall efficiency of sorting. Summary of the Invention

[0005] In view of the deficiencies of the prior art, the present invention provides a human-machine function allocation method based on multi-objective cost index evaluation, which solves the problems in the prior art that it is difficult to accurately evaluate the differences in different working periods, task types, and personnel and machine efficiencies, resulting in inaccurate task allocation and unreasonable resource allocation, thus affecting the sorting efficiency.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A human-machine function allocation method based on multi-objective cost index evaluation includes the following steps: Obtain the historical time-series data of manual sorting and the historical data of machine sorting, and perform data analysis on them respectively to obtain the manual sorting rate value for each sorting item in each historical working period and the machine sorting rate value for each sorting item; at the same time, obtain the characteristic data of several sorting items to be sorted, and perform type division to obtain several types of sorting items to be sorted; and obtain the machine sorting cost data, the manual sorting cost data of the current working period of the sorting employees, and combine the manual sorting rate value for each sorting item in the corresponding historical working period and the machine sorting rate value for each sorting item to perform data analysis respectively to obtain the manual cost evaluation index for each sorting item in the current working period of the sorting employees and the machine cost evaluation index for each sorting item; and compare and analyze the manual cost evaluation index of each sorting item in the current working period of the sorting employees with the machine cost evaluation index of each sorting item respectively, and take corresponding allocation measures based on the comparison and analysis results.

[0007] Further, the historical data of manual sorting includes the manual duration value each time in each historical working period, the total value of manual sorting for each sorting item, and the number of manual sorting errors. The historical data of machine sorting includes the machine working duration value, the fault duration value in each historical working period, and the total value of machine sorting for each sorting item. The characteristic data includes the weight value, the color reflection value, and the shape complexity index. The machine sorting cost data includes the machine unit price, the usage duration value, the machine load value, the fault frequency value, and the maintenance frequency value. The manual sorting cost data includes the manual unit price, the suitable temperature value, the suitable humidity value, and the suitable noise value.

[0008] Further, the specific steps for obtaining the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period are as follows: perform ratio analysis on the number of manual sorting errors and the total number of manual sorting for each sorting item in each historical working period each time in history to obtain the manual error rate value for each sorting item in each historical working period each time in history; and perform comprehensive analysis on the manual working duration value in each historical working period each time in history, the total number of manual sorting for each sorting item, and the manual error rate value to obtain the manual sorting rate value for each sorting item in each historical working period; perform ratio analysis on the machine working duration value and the failure duration value for each sorting item in each historical working period to obtain the machine failure index in each historical working period; and perform comprehensive analysis on the total number of machine sorting, the machine working duration value in each historical working period, and the machine failure index for each sorting item to obtain the machine sorting rate value for each sorting item.

[0009] Further, the specific formulas for calculating the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period are as follows: Among them, RgF ij is the manual sorting rate value for the j-th sorting item in the i-th historical working period, ZsL uij is the total number of manual sorting for the j-th sorting item in the i-th historical working period for the u-th time in history, ScZ ui is the manual working duration value for the u-th time in the i-th historical working period, α 1 is the manual working duration decay coefficient stored in the database, WcL uij is the manual error rate value for the j-th sorting item in the i-th historical working period for the u-th time in history, α 2 is the manual rate impact coefficient stored in the database, XgF j is the machine sorting rate value for the j-th sorting item, XsC ij is the total number of machine sorting for the j-th sorting item in the i-th historical working period, XcZ i is the machine working duration value in the i-th historical working period, β 1 is the machine working duration decay coefficient stored in the database, XgZ i is the machine failure index in the i-th historical working period, β 2 is the machine rate impact coefficient stored in the database, u = 1, 2, 3, …, u 0 u 0 is the number of historical working periods, i = 1, 2, 3, …, i 0 i0 is the number of historical working periods, and j = 1, 2, 3, …, j 0 , j 0 is the number of types of sorting items.

[0010] Furthermore, the specific steps to obtain several types of items to be sorted are as follows: perform normalization processing on the weight value, color reflection value, and shape complexity index of each sorting item to be sorted; and comprehensively analyze the weight value, color reflection value, and shape complexity index of each sorting item to be sorted after normalization processing to obtain the sorting complexity index of each sorting item to be sorted; and respectively compare and analyze the sorting complexity index of each sorting item to be sorted with a preset sorting complexity index interval to obtain several types of items to be sorted.

[0011] Furthermore, the specific steps to obtain the manual cost evaluation index of each sorting item for the current working period of the sorting employee are as follows: obtain the reference values of the adaptable temperature, adaptable humidity, and adaptable noise of the sorting employee, and comprehensively analyze them in combination with the adaptable temperature value, adaptable humidity value, and adaptable noise value of the current working period to obtain the environmental correction factor of the current working period of the sorting employee; read the historical manual error rate values for each sorting item in each historical working period, and perform mean analysis to obtain the error value of the current working period of the sorting employee; and comprehensively analyze the manual unit value, error value, environmental correction factor of the current working period of the sorting employee, and the manual sorting rate value for each sorting item in the corresponding historical working period to obtain the manual cost evaluation index of each sorting item for the current working period of the sorting employee.

[0012] Furthermore, the specific formula for calculating the manual cost evaluation index of each sorting item for the current working period of the sorting employee is as follows: RgC j = RgF j * RgD * (1 + RcL * θ 1 ) * (1 + HzX * θ 2 ); where RgC j is the manual cost evaluation index of the sorting employee for the j-th sorting item in the current working period, RgF j is the manual sorting rate value of the sorting employee for the j-th sorting item in the historical working period corresponding to the current working period, RgD is the manual unit value of the sorting employee in the current working period, RcL is the error value of the current working period of the sorting employee, θ 1 is the error coefficient stored in the data path, HzX is the environmental correction factor of the current working period of the sorting employee, θ 2 is the environmental correction coefficient stored in the data path, and j = 1, 2, 3, …, j 0 , j 0is the number of types of sorting items.

[0013] Further, the specific steps to obtain the machine cost evaluation index for each sorting item are as follows: 2 Obtain the maximum service life value of the machine, and conduct a comprehensive analysis in combination with the service life value, machine load value, failure frequency value, and maintenance frequency value of the machine to obtain the wear factor of the machine; and conduct a comprehensive analysis of the unit price value of the machine, wear factor, and machine sorting rate value for each sorting item to obtain the machine cost evaluation index for each sorting item.

[0014] Further, the specific formulas for calculating the wear factor of the machine and the machine cost evaluation index for each sorting item are as follows: Among them, HxZ is the wear factor of the machine, SyC is the service life value of the machine, ZdS is the maximum service life value of the machine, ω 1 is the usage coefficient stored in the database, FhZ is the machine load value of the machine, τ is the adjustment coefficient stored in the database, ω 2 is the load coefficient stored in the database, GzP is the failure frequency value of the machine, ByP is the maintenance frequency value of the machine, ω 3 is the failure coefficient stored in the database, XcP j is the machine cost evaluation index for the j-th type of sorting item, XgF j is the machine sorting rate value for the j-th type of sorting item, XqD is the unit price value of the machine, ζ is the wear coefficient stored in the data, j = 1, 2, 3,..., j 0 j 0 is the number of types of sorting items.

[0015] Further, the specific steps to take corresponding allocation measures based on the comparison and analysis results are as follows: If the labor cost evaluation index for each sorting item during the current working period of the sorting employee is lower than the machine cost evaluation index for each sorting item, then take the first allocation measure; if the labor cost evaluation index for each sorting item during the current working period of the sorting employee is higher than the machine cost evaluation index for each sorting item, then take the second allocation measure.

[0016] The present invention has the following beneficial effects:

[0017] (1) The human-machine function allocation method based on multi-objective cost index evaluation can effectively select the most suitable sorting method through a comprehensive analysis of manual and machine sorting costs, especially by calculating the manual and machine sorting rates and cost evaluation indicators, so as to avoid unnecessary resource waste. For example, when the cost of the machine is low, the system will automatically select the machine for sorting, avoiding additional costs caused by inefficient manual sorting. At the same time, considering the adjustment of the manual unit price in the overtime state, the system can accurately optimize the cost allocation between manual and machine, helping the enterprise to maximize the use of resources in different production periods and improve the overall production cost-effectiveness.

[0018] (2) The human-machine function allocation method based on multi-objective cost index evaluation can accurately evaluate the error rate of each sorted item through the analysis of historical data, especially the calculation of the manual error rate, and then determine whether to process specific items manually or by machine. The machine can ensure high accuracy when processing items with high error rates, thus reducing losses caused by human errors. This allocation method significantly improves the accuracy of the sorting process, avoids material losses caused by improper manual operations, and at the same time, by using the machine to sort items with high complexity, it avoids errors caused by reduced manual operation speed or distracted attention, improving the overall sorting accuracy and efficiency.

[0019] (3) The human-machine function allocation method based on multi-objective cost index evaluation introduces the concept of an environmental correction factor, that is, adjusts the manual sorting efficiency according to environmental factors such as temperature, humidity, and noise in the current working period, so as to ensure that under different working conditions, the working state of sorting employees can match the environmental conditions, thus maintaining high work efficiency. For example, if the environmental temperature is too high, the manual sorting efficiency may decrease, but the machine sorting is not affected by this factor. The system comprehensively considers these environmental factors, calculates the most suitable environmental correction factor, and reasonably allocates the sorting tasks, so as to ensure that the sorting tasks can be completed under optimal conditions in working environments with high temperature, high humidity, or high noise. This not only enhances the flexibility of the system but also effectively reduces the negative impact of environmental changes on production efficiency, ensuring stable production performance in various environments.

[0020] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a flowchart of a human-machine function allocation method based on multi-objective cost index evaluation of the present invention.

[0022] Figure 2It is a specific step flowchart for obtaining the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in a human-machine function allocation method based on multi-objective cost index evaluation according to the present invention.

[0023] Figure 3 It is a specific step flowchart for obtaining the manual cost evaluation index for each sorting item during the current working period of sorting employees in a human-machine function allocation method based on multi-objective cost index evaluation according to the present invention. Specific implementation manners

[0024] The general idea for the problems in the embodiments of this application is as follows:

[0025] First, it is necessary to obtain the historical sorting data of manual and machine, including sorting rate, sorting error rate, working hours, etc. Then, analyze these historical data to obtain the sorting rate values of manual and machine in each historical working period. At the same time, obtain the characteristic data of the items to be sorted (such as weight, color reflection value, shape complexity index), and obtain the shape complexity index through ratio analysis. Obtain the cost data of machine and manual, and combine the working period and the characteristic data of the items to calculate the cost evaluation indexes of manual and machine. Compare and analyze the manual cost and machine cost of each item. According to the comparison result, determine whether to select manual or machine for sorting. Finally, according to the result of the comparison and analysis, take corresponding allocation measures. If the manual cost is lower than the machine cost, then manual sorting is performed; if the machine cost is lower, then machine sorting is performed.

[0026] Please refer to Figure 1, an embodiment of the present invention provides a technical solution: a human-machine function allocation method based on multi-objective cost index evaluation, including the following steps: obtaining historical time-series data of manual sorting and historical data of machine sorting, and respectively performing data analysis to obtain the manual sorting rate value for each sorting item in each historical working period, and the machine sorting rate value for each sorting item; at the same time, obtaining the feature data of several sorting items to be sorted, and performing type division to obtain several types of sorting items to be sorted; and obtaining machine sorting cost data, the manual sorting cost data of the current working period of the sorting employees, and combining the manual sorting rate value for each sorting item in the corresponding historical working period, and the machine sorting rate value for each sorting item to perform data analysis respectively, to obtain the manual cost evaluation index for each sorting item in the current working period of the sorting employees, and the machine cost evaluation index for each sorting item; and comparing and analyzing the manual cost evaluation index of each sorting item in the current working period of the sorting employees with the machine cost evaluation index of each sorting item respectively (it should be noted here that the comparison and analysis are for the same type of sorting items), and taking corresponding allocation measures based on the comparison and analysis results.

[0027] The historical data of manual sorting includes the manual working duration value each time in each historical working period, the total value of manual sorting for each sorting item, and the number of manual sorting errors. The historical data of machine sorting includes the machine working duration value, the fault duration value in each historical working period, and the total value of machine sorting for each sorting item. The feature data includes the weight value, the color reflection value, and the shape complexity index. The machine sorting cost data includes the unit price of the machine (per unit time), the usage duration value, the machine load value, the fault frequency value, and the maintenance frequency value. The manual sorting cost data includes the unit price of labor (per unit time), the suitable temperature value (i.e., the temperature value at which the manual sorting efficiency is the highest), the suitable humidity value (i.e., the humidity value at which the manual sorting efficiency is the highest), and the suitable noise value (i.e., the noise value at which the manual sorting efficiency is the highest).

[0028] Among them, the manual working duration value is the working duration value of the sorting employees in the historical working period, which can be obtained through the production management records in the database.

[0029] The total value of manual sorting can be obtained through the task records in the barcode scanners stored in the database.

[0030] The number of manual sorting errors can be obtained through the label scanning error records stored in the database.

[0031] The machine working duration value is the actual working duration of the machine in the historical working period, which can be obtained through the working duration timer inside the machine.

[0032] The failure duration value is the sum of the failure duration values for each failure, and the failure duration value for each time can be obtained through the failure timer built into the machine.

[0033] The total value of machine sorting can be obtained through the task counter built into the machine.

[0034] The weight value can be obtained through a weight sensor.

[0035] The color reflection value is the reflection ability of the item surface to light of different wavelengths, expressed by the color reflectance or spectral reflectance, and can be measured by a spectrometer (the principle is: by decomposing light into different wavelengths or frequencies, and measuring the intensity of light at each wavelength, and then obtaining the reflectance of the object surface at different light wavelengths, and calculating through the internal algorithm to obtain the result), and the measurement result is uploaded to the database.

[0036] The shape complexity index is the shape feature of the item to be sorted, and can be obtained through the following steps: obtain the surface area value and volume value of the item to be sorted, and perform ratio analysis on the surface area value and volume value of the item to be sorted, and the ratio analysis result is the shape complexity index.

[0037] The machine unit value is the electricity cost consumed per unit time, that is, the product of the power consumption per unit time and the unit price of electricity, and the power consumption can be obtained through the electricity meter built into the machine, and the unit price of electricity can be obtained through the power contract stored in the database.

[0038] The machine load value is the ratio of the operating power to the maximum rated power, that is, the machine load value = operating power / maximum rated power, and the operating power can be obtained through the power meter built into the machine, and the maximum rated power can be obtained through the technical specification stored in the database.

[0039] The failure frequency value can be obtained through the failure log records stored in the database.

[0040] The maintenance frequency value can be obtained through the maintenance log records stored in the database.

[0041] The adaptive temperature value is the temperature value at which the manual sorting efficiency is the highest, and can be obtained through a temperature sensor.

[0042] The adaptive humidity value is the humidity value at which the manual sorting efficiency is the highest, and can be obtained through a humidity sensor.

[0043] The adaptive noise value is the noise value at which the manual sorting efficiency is the highest, and can be obtained through a noise sensor.

[0044] Specifically, such as Figure 2As shown in the figure, the specific steps to obtain the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period are as follows: perform a ratio analysis on the number of manual sorting errors and the total number of manual sorting for each sorting item in each historical working period each time in history to obtain the manual error rate value for each sorting item in each historical working period each time in history; and perform a comprehensive analysis on the manual working duration value in each historical working period each time in history, the total number of manual sorting for each sorting item, and the manual error rate value to obtain the manual sorting rate value for each sorting item in each historical working period; perform a ratio analysis on the machine working duration value and the failure duration value for each sorting item in each historical working period to obtain the machine failure index in each historical working period; and perform a comprehensive analysis on the total number of machine sorting, the machine working duration value in each historical working period, and the machine failure index for each sorting item to obtain the machine sorting rate value for each sorting item.

[0045] The specific formulas for calculating the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period are as follows: Among them, RgF ij is the manual sorting rate value for the j-th sorting item in the i-th historical working period, ZsL uij is the total number of manual sorting for the j-th sorting item in the i-th historical working period for the u-th time in history, ScZ ui is the manual working duration value for the u-th time in the i-th historical working period, α 1 is the manual working duration decay coefficient stored in the database, WcL uij is the manual error rate value for the j-th sorting item in the i-th historical working period for the u-th time in history, α 2 is the manual rate impact coefficient stored in the database, XgF j is the machine sorting rate value for the j-th sorting item, XsC ij is the total number of machine sorting for the j-th sorting item in the i-th historical working period, XcZ i is the machine working duration value in the i-th historical working period, β 1 is the machine working duration decay coefficient stored in the database, XgZ i is the machine failure index in the i-th historical working period, β 2 is the machine rate impact coefficient stored in the database, u = 1, 2, 3,..., u 0 u 0 is the number of historical working periods, i = 1, 2, 3,..., i 0 i 0is the number of historical working periods, and j = 1, 2, 3, …, j 0 , j 0 is the number of types of sorted items.

[0046] It should be explained that α 1 , α 2 can be obtained through the following steps: First, by comparing the manual working hours and sorting efficiency in the historical working periods, the attenuation coefficient of manual working hours is calculated, which reflects the attenuation of manual sorting efficiency as the working hours increase. Second, the manual rate influence coefficient is determined by analyzing the manual sorting rate, error rate, and working environment factors (such as temperature, humidity, etc.) in different historical working periods, so as to evaluate how these factors affect the manual rate.

[0047] β 1 , β 2 can be obtained through the following steps: The attenuation coefficient of machine working hours is obtained by analyzing the relationship between the working hours and sorting efficiency of the machine in different historical working periods, which reflects the attenuation effect between the machine working hours and sorting efficiency. At the same time, the machine rate influence coefficient is obtained by analyzing the failure frequency, working load of the machine, and sorting data in the historical working periods, so as to quantify the influence of these factors on the machine sorting rate. The acquisition of these coefficients can help accurately adjust the sorting capabilities of manual labor and machines to cope with different working periods and working conditions.

[0048] In this implementation plan, by performing ratio analysis on historical data, calculating the manual error rate for each sorted item, and then conducting a comprehensive analysis in combination with manual working hours, total sorting quantity, and error rate, the manual sorting rate of each item in each historical period can be accurately obtained. This method can reveal potential efficiency problems in manual sorting, such as items with a high error rate, avoiding simple quantity statistics, and being able to more precisely identify bottlenecks in the sorting process. At the same time, the machine sorting rate is also calculated by analyzing the machine working hours, breakdown hours, and total sorting quantity, which can clarify the actual performance of the machine. For example, the proportion of machine breakdowns affects the machine sorting rate, which can help identify the weaknesses of the machines in the system and further optimize the maintenance and repair plan. By comparing the sorting rates of manual and machine sorting, more accurate resource allocation decisions can be made in each sorting task. For example, if the manual sorting rate is low or the error rate is high in a certain historical period, the system can automatically select to let the machine undertake this task, thereby reducing manual errors and time waste. And if the machine breaks down in some periods, the system can promptly allocate manual labor to replace the machine to ensure the smooth progress of the sorting task. Such decisions are based on specific data analysis, which can effectively reduce the error of human judgment. By calculating the manual sorting and machine sorting rates in detail, it can clearly reveal which items are more suitable for manual sorting and which are suitable for machine sorting. For example, items with complex shapes may have higher requirements for manual operation, while heavier items may be suitable for machine processing. Such detailed analysis can help optimize resource allocation on the production line, avoid over-reliance on one party (such as over-reliance on machines or manual labor), and thus achieve the best working efficiency and production cost control. In addition, the analysis of the machine's failure index and load status helps predict the wear and failure cycle of the equipment, reduce the unplanned downtime of the equipment, and ensure that the equipment can continuously provide stable sorting capabilities during efficient operation. By identifying potential problems in advance, production interruptions caused by sudden failures can be avoided during the production process.

[0049] Specifically, the specific steps to obtain several items to be sorted are as follows: perform normalization processing (i.e., unit removal) on the weight value, color reflection value, and shape complexity index of each item to be sorted; and conduct a comprehensive analysis on the weight value, color reflection value, and shape complexity index of each item to be sorted after normalization processing to obtain the sorting complexity index of each item to be sorted; and compare and analyze the sorting complexity index of each item to be sorted with a preset sorting complexity index range respectively to obtain several items to be sorted.

[0050] Among them, the specific formula for calculating the sorting complexity index of each item to be sorted is as follows: FzD m =(δ 1 *WzL′ m +δ 2*YsF' m ) * (1 + δ 3 *XzF' m ); where, FzD m is the sorting complexity index of the m-th sorting item to be sorted, WzL' m is the weight value of the m-th sorting item to be sorted after normalization, δ 1 is the weight coefficient stored in the database, YsF' m is the color reflection value of the m-th sorting item to be sorted after normalization, δ 2 is the reflection coefficient stored in the database, XzF' m is the shape complexity index of the m-th sorting item to be sorted after normalization, δ 3 is the shape coefficient stored in the database, m = 1, 2, 3,..., m 0 , m 0 is the number of sorting items.

[0051] It should be noted that δ 1 , δ 2 , δ 3 can be obtained through the following steps: They are obtained by analyzing the item feature data stored in the database. Specifically, δ 1 is determined by analyzing the relationship between the weight of the item and the sorting complexity, which reflects the impact of the item weight on the complexity of the sorting task; δ 2 is obtained by analyzing the relationship between the color reflection value of the item and the sorting efficiency, evaluating the impact of the color feature on the sorting task; and δ 3 is determined by analyzing the relationship between the shape feature of the item and the sorting efficiency, indicating the impact of the shape complexity on the difficulty of the sorting task. The calculation of these three coefficients is based on the impact of different item features on the sorting task, thereby helping to optimize the task allocation of the sorting system.

[0052] The specific steps of the comparison and analysis are as follows: If the sorting complexity index of the sorting item to be sorted is lower than the lower limit (i.e., the minimum value) of the preset sorting complexity index interval, then mark this sorting item as a simple type item; if the sorting complexity index of the sorting item to be sorted is within the preset sorting complexity index interval, then mark this sorting item as a medium complexity type item; if the sorting complexity index of the sorting item to be sorted is higher than the upper limit (i.e., the maximum value) of the preset sorting complexity index interval, then mark this sorting item as a high complexity type item.

[0053] In this implementation plan, after normalizing the weight, color reflection value, and shape complexity index of the items to be sorted, the differences in different item units can be eliminated, making the analysis of items with different characteristics more standardized and fair. In this way, the sorting complexity index obtained through comprehensive analysis can objectively and comprehensively quantify the sorting difficulty of each item, providing an accurate basis for formulating subsequent sorting strategies. The classification based on the sorting complexity index (simple category, medium complexity category, and high complexity category) helps the system automatically identify the sorting requirements of different items. For simple items, they can be given priority to be processed manually to avoid wasting machine resources; for complex items, they can be centrally handed over to machines or optimized human-machine collaboration for processing. This intelligent allocation can not only improve the sorting efficiency but also reduce the error rate and improve the operation quality. The dynamic calculation and classification of the sorting complexity index can effectively balance the workloads of humans and machines. When operating manually, if the complexity of the sorted items is too high, fatigue and errors are likely to occur. Using machines to sort high-complexity items can reduce the human burden and avoid cost waste caused by operational mistakes. Handing simple items over to humans for processing can improve resource utilization and ensure the efficient operation of the entire system. In actual production, the types and characteristics of the items to be sorted may fluctuate with changes in the production plan and the types of items. By calculating the sorting complexity index in real time, the system can adjust the sorting strategy in a timely manner according to the actual situation of the items, not only enhancing the adaptability of the production line but also ensuring the correct classification and precise allocation of items during the production process.

[0054] Specifically, as Figure 3 shown, the specific steps to obtain the manual cost evaluation index for each sorted item during the current working period of the sorting employee are as follows: Obtain the reference values of the adapted temperature, adapted humidity, and adapted noise of the sorting employee, and conduct a comprehensive analysis in combination with the adapted temperature value, adapted humidity value, and adapted noise value of the current working period to obtain the environmental correction factor for the current working period of the sorting employee; Read the historical manual error rate values for each sorted item during each historical working period, conduct a mean analysis to obtain the error value for the current working period of the sorting employee; and conduct a comprehensive analysis of the manual unit price, error value, environmental correction factor of the current working period of the sorting employee, and the manual sorting rate value for each sorted item during the corresponding historical working period to obtain the manual cost evaluation index for each sorted item during the current working period of the sorting employee.

[0055] The specific formula for calculating the environmental correction factor for the current working period of the sorting employee is as follows: Among them, HxZ is the environmental correction factor for the current working period of the sorting employee, DwD is the adapted temperature value for the current working period of the sorting employee, CwD is the reference value of the adapted temperature of the sorting employee, φ 1DsZ is the adaptive humidity value of the current working period of the sorting staff, CsZ is the adaptive humidity reference value of the sorting staff, and φ is the adaptive temperature coefficient stored in the database. 2 ZsD is the adaptive noise value of the current working period of the sorting staff, CsD is the adaptive noise reference value of the sorting staff, and φ is the adaptive humidity coefficient stored in the database. 3 φ is the adaptive noise coefficient stored in the database. 1 +φ 2 +φ 3 = 1.

[0056] It should be noted that φ 1 , φ 2 , φ 3 can be obtained through the following steps: Read the adaptive temperature reference value, adaptive humidity reference value, and adaptive noise reference value of the sorting staff, perform normalization processing to obtain the normalized adaptive temperature reference value, adaptive humidity reference value, and adaptive noise reference value of the sorting staff, and perform summation analysis to obtain the adaptive environment correction sum value. Perform ratio analysis on the normalized adaptive temperature reference value, adaptive humidity reference value, and adaptive noise reference value of the sorting staff with the adaptive environment correction sum value respectively, and use the ratio analysis results as the corresponding coefficients.

[0057] The specific implementation example of calculating the environmental correction factor of the current working period of the sorting staff is as follows. The following data are available:

[0058] The temperature value of the current working period of the sorting staff is (unit: °C): 32.30.

[0059] The humidity value of the current working period of the sorting staff: 0.40.

[0060] The noise value of the current working period of the sorting staff is (unit: dB): 86.00.

[0061] The temperature reference value is (unit: °C): 25.00.

[0062] The humidity reference value is: 0.50.

[0063] The noise reference value is (unit: dB): 70.00.

[0064] The temperature coefficient stored in the database is approximately: 0.39.

[0065] The humidity coefficient stored in the database is approximately: 0.29.

[0066] The noise coefficient stored in the database is approximately: 0.32.

[0067] Substitute the above data into the formula for the environmental correction factor of the current working period of the sorting staff for calculation, and obtain:

[0068] The environmental correction factor of the current working period of the sorting staff =

[0069]

[0070] The specific formula for calculating the labor cost evaluation index for each sorting item in the current working period of the sorting staff is as follows: RgC j = RgF j * RgD * (1 + RcL * θ 1 ) * (1 + HzX * ω 2 ); where, RgC j is the labor cost evaluation index for the j-th sorting item in the current working period of the sorting staff, RgF j is the manual sorting rate value for the j-th sorting item in the corresponding historical working period of the current working period of the sorting staff, RgD is the labor unit value of the current working period of the sorting staff, RcL is the error value of the current working period of the sorting staff, θ 1 is the error coefficient stored in the data path, HzX is the environmental correction factor of the current working period of the sorting staff, θ 2 is the environmental correction coefficient stored in the data path, j = 1, 2, 3,..., j 0 , j 0 is the number of sorting item types.

[0071] It should be noted that θ 1 , θ 2 can be obtained through the following steps: determined by the environmental correction factors of the current working period, θ 1 is obtained by analyzing the relationship between the working environment factors (such as temperature, humidity, etc.) in historical data and the sorting efficiency of employees, reflecting the correction impact of environmental changes on employees' work performance, θ 2 then evaluates the impact of the number of sorting item types on the sorting efficiency by considering the relationship between the number of sorting item types and the sorting efficiency in the current working period. The calculation of these two coefficients can help the system flexibly adjust the sorting process according to different environmental changes and item characteristics, thereby improving the overall efficiency.

[0072] It should be noted here that the labor unit value during the current working period is not fixed. If the current time is within the normal working period (i.e., normal work), the labor unit value of the current working period is maintained. If the current time is not within the normal working period (i.e., in overtime), the labor unit value of the current working period is the labor unit value in the overtime state. For example, the normal working hours of a sorting employee's company in a day are 8 hours, and the labor unit value per hour is 15 yuan. If the current period of the sorting employee is in an overtime working period (such as the 10th period), the labor unit value at this time is 18 yuan.

[0073] In this implementation plan, by considering environmental factors such as temperature, humidity, and noise during the current working period of sorting employees, the labor cost assessment can be dynamically adjusted. The calculation of this environmental correction factor takes into account the performance of employees under different working conditions, which helps to accurately evaluate the impact of environmental changes on employees' work efficiency, ensuring that the cost of employees' work in extreme environments (such as high temperature, high noise, etc.) is not underestimated, thus achieving a more fair and accurate cost calculation. By performing a mean analysis on the manual error rate of sorted items through historical data, it is possible to more precisely judge the error level of sorting employees during the current working period. This method helps the system automatically adapt to the work performance of different employees, adjust work assignments and task requirements. If the error rate of some employees is relatively high, the system can correspondingly increase the labor cost assessment of these employees and optimize task assignments to avoid tasks with too high an error rate affecting the overall efficiency. By comprehensively analyzing multiple indicators such as the labor unit value, error value, environmental correction factor, and sorting rate in historical data during the current working period, the labor cost assessment for each item can be dynamically adjusted. In different working periods, especially during overtime periods, the change in the labor unit price will affect the labor cost. Such adjustments can better reflect the actual work load and economic benefits of employees. For employees in the overtime state, the system automatically increases the labor unit value to ensure that the work efforts of employees are matched with rewards, enhancing the fairness and incentive of the system. Through these calculations, the system can flexibly adjust task assignments according to factors such as different working periods, environmental conditions, and item characteristics. For example, in an environment with high temperature or high noise, the system may choose to reduce the amount of manual sorting tasks or increase the sorting ratio of machines to optimize efficiency and reduce errors. The system can dynamically adjust strategies to better respond to the changing production environment, avoiding resource waste and inefficiency.

[0074] Specifically, the specific steps to obtain the machine cost evaluation index for each sorting item are as follows: Obtain the maximum usage duration value of the machine, and conduct a comprehensive analysis by combining the usage duration value, machine load value, failure frequency value, and maintenance frequency value to obtain the wear factor of the machine; and conduct a comprehensive analysis of the unit price value of the machine, wear factor, and machine sorting rate value for each sorting item to obtain the machine cost evaluation index for each sorting item.

[0075] The specific formulas for calculating the wear factor of the machine and the machine cost evaluation index for each sorting item are as follows: Among them, HxZ is the wear factor of the machine, SyC is the usage duration value of the machine, ZdS is the maximum usage duration value of the machine, ω 1 is the usage coefficient stored in the database, FhZ is the machine load value of the machine, τ is the adjustment coefficient stored in the database, and in this embodiment, it takes the value of 100, ω 2 is the load coefficient stored in the database, GzP is the failure frequency value of the machine, ByP is the maintenance frequency value of the machine, ω 3 is the failure coefficient stored in the database, XcP j is the machine cost evaluation index for the j-th sorting item, XgF j is the machine sorting rate value for the j-th sorting item, XqD is the unit price value of the machine, ζ is the wear coefficient stored in the data, j = 1, 2, 3,..., j 0 , j 0 is the number of sorting item types.

[0076] It should be explained that ω 1 , ω 2 , ω 3 can be obtained through the following steps: Determine by analyzing different factors in the database. ω 1 is obtained by analyzing the usage and load conditions of the machine stored in the database, reflecting the impact of the machine usage on the sorting efficiency. ω 2 is calculated by analyzing the relationship between the machine failure frequency and the sorting task stored in the database, indicating the negative impact of machine failures on the sorting efficiency. ω 3 is obtained by analyzing the relationship between the machine failure frequency and the load condition stored in the database, reflecting the change in the failure frequency of the machine under the load state. Through the analysis of these three coefficients, the impact of factors such as machine usage, failure, and load on the sorting task cost can be evaluated, thereby optimizing the machine allocation and sorting process.

[0077] In this implementation plan, by comprehensively analyzing factors such as the machine's usage duration, load condition, failure frequency, and maintenance frequency, the machine's wear factor can be accurately calculated. The calculation of this wear factor helps enterprises predict the degree of performance decline of the machine during different working periods, thereby providing data support for machine maintenance and replacement. This enables enterprises to better control the machine's maintenance costs and avoid production interruptions and repair costs caused by excessive machine wear. Combining the machine's wear factor, the single value of the machine, and the sorting rate for comprehensive analysis can obtain more accurate machine cost evaluation indicators. These indicators consider the machine's workload, usage conditions, and failure rate, and can more accurately reflect the actual costs of the machine under different working states, thereby helping managers optimize the machine's usage efficiency and production task allocation. Through the analysis of various factors of the machine, the system can dynamically adjust the sorting task allocation of the machine during the production process. For example, when the machine is in a high-load state or frequently fails, the system can reduce the sorting task volume of this machine or allocate it to tasks with a lighter load, thereby reducing the failure rate and improving production efficiency. At the same time, the system can also adjust tasks according to the machine's maintenance situation to avoid production interruptions or efficiency reduction caused by machine failures. The machine's failure frequency and load status have an important impact on production efficiency. By analyzing this data, the system can better predict the risk of machine failures and adjust the production plan according to the failure risk, avoiding high-risk machines from continuing to perform key tasks. This forward-looking management method helps reduce the interference of machine failures on sorting tasks, thereby improving the stability and reliability of the production line.

[0078] Specifically, the specific steps for taking corresponding allocation measures based on the comparison and analysis results are as follows: If the manual cost evaluation index of each sorting item during the current working period of the sorting employee is lower than the machine cost evaluation index of each sorting item, then take the first allocation measure (i.e., delivering this sorting item to the manual for sorting); if the manual cost evaluation index of each sorting item during the current working period of the sorting employee is higher than the machine cost evaluation index of each sorting item, then take the second allocation measure (i.e., delivering this sorting item to the machine for sorting).

[0079] In this implementation, by comparing and allocating sorting tasks based on the cost evaluation indicators of manual labor and machines, optimal resource allocation can be achieved. When the manual cost of sorting items is lower than the machine cost, choosing manual sorting can reduce the machine burden, lower the machine usage cost, and avoid unnecessary high-load operation. When the manual cost is high, switching to machine sorting can improve efficiency and reduce the manual cost. Such dynamic allocation can ensure the efficient utilization of manual and machine resources. The allocation measure based on cost evaluation can minimize cost expenditure while ensuring efficiency. For sorting tasks with lower costs, using manual sorting can reduce the machine usage frequency and machine maintenance cost. For high-cost tasks, machine sorting can speed up the processing speed, reduce the error rate, and improve production efficiency. This strategy helps the enterprise reduce the overall operation cost while ensuring the efficient completion of production tasks. By analyzing the cost evaluation of manual labor and machines, the enterprise can flexibly respond to changes in the working environment. For example, if certain factors in the working environment (such as temperature, humidity, noise) affect the work efficiency of employees, the system can adjust according to real-time data, avoid errors or inefficiencies caused by manual sorting tasks, and at the same time, this flexible resource adjustment method can reduce production fluctuations caused by environmental factors and maintain the stability of the sorting process. Through the clear comparison and analysis of manual and machine costs, the allocation measure becomes more scientific and transparent, avoiding the allocation method that relies on subjective judgment. This decision-making process based on data and cost evaluation ensures the reasonable allocation of sorting tasks under different conditions, ensuring work efficiency and avoiding unfairness or inefficiency caused by human factors.

[0080] In summary, this application has at least the following effects:

[0081] Through a comprehensive analysis of the sorting costs of manual labor and machines, especially by calculating the sorting rates and cost evaluation indicators of manual labor and machines, the most suitable sorting method can be effectively selected, thus avoiding unnecessary resource waste. For example, when the machine cost is low, the system will automatically select the machine for sorting, avoiding additional costs caused by inefficient manual sorting. At the same time, considering the adjustment of the manual labor unit price in the overtime state, the system can accurately optimize the cost allocation between manual labor and machines, helping the enterprise maximize the utilization of resources at different production times and enhancing the cost-effectiveness of overall production.

[0082] Through the analysis of historical data, especially the calculation of the manual error rate, the error rate of each sorted item can be accurately evaluated, and then it can be decided whether to process a specific item manually or by machine. The machine can ensure high accuracy when processing items with a high error rate, thus reducing the losses caused by human errors. This allocation method significantly improves the accuracy of the sorting process and avoids material losses caused by improper manual operations. At the same time, by using machines to sort items with high complexity, errors caused by reduced manual operation speed or distracted attention are avoided, improving the overall sorting accuracy and efficiency.

[0083] By introducing the concept of an environmental correction factor, that is, adjusting the manual sorting efficiency according to environmental factors such as temperature, humidity, and noise in the current working period, it is ensured that under different working conditions, the working state of sorting employees can match the environmental conditions, thus maintaining high work efficiency. For example, if the environmental temperature is too high, the manual sorting efficiency may decrease, but machine sorting is not affected by this factor. The system calculates the most suitable environmental correction factor by comprehensively considering these environmental factors and reasonably allocates sorting tasks, so as to ensure that sorting tasks can be completed under optimal conditions in working environments with high temperature, high humidity, or high noise. This not only enhances the flexibility of the system but also effectively reduces the negative impact of environmental changes on production efficiency, ensuring stable production performance in various environments.

[0084] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0085] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for allocating human-machine functions based on multi-objective cost index evaluation, characterized in that: The following steps are involved: Obtaining the historical time series data of manual sorting and the historical data of machine sorting, and performing data analysis respectively, to obtain the manual sorting rate value for each sorted item in each historical working period, and the machine sorting rate value for each sorted item; At the same time, characteristic data of several sorting items to be sorted are obtained, and the types are classified to obtain several types of items to be sorted; And obtain machine sorting cost data, manual sorting cost data of the sorting staff in the current working period, and, in combination with the manual sorting rate value for each sorted item in the corresponding historical working period, and the machine sorting rate value for each sorted item, respectively perform data analysis to obtain the manual cost evaluation index for each sorted item in the current working period of the sorting staff, and the machine cost evaluation index for each sorted item; The labor cost evaluation index of each sorting item in the current working period of the sorting staff is compared and analyzed with the machine cost evaluation index of each sorting item, and corresponding allocation measures are taken based on the comparison and analysis results.

2. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 1 is characterized in that: The manual sorting history data includes the historical labor time value in each historical working period, the total manual sorting value for each sorted item, and the number of manual sorting errors; the machine sorting history data includes the machine working time value and failure time value in each historical working period, and the total machine sorting value for each sorted item; the characteristic data includes weight value, color reflection value, and shape complexity index; the machine sorting cost data includes machine unit value, usage time value, machine load value, failure frequency value, and maintenance frequency value; the manual sorting cost data includes labor unit value, adaptive temperature value, adaptive humidity value, and adaptive noise value.

3. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 2 is characterized in that: The specific steps for obtaining the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period are as follows: Perform a ratio analysis on the number of manual sorting errors and the total number of manual sorting for each sorting item in each historical working period in history, and obtain the manual error rate value for each sorting item in each historical working period in history; A comprehensive analysis is performed on the historical labor time values ​​in each historical working period, the total number of manual sortings for each sorted item, and the manual error rate value, to obtain the manual sorting rate value for each sorted item in each historical working period; Perform a ratio analysis of the machine duration and failure duration of each sorted item in each historical working period to obtain the machine failure index in each historical working period. A comprehensive analysis is performed on the total number of machine sortings, the machine time value, and the machine failure index for each sorted item in each historical working period to obtain the machine sorting rate value for each sorted item.

4. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 2 is characterized in that: The specific formula for calculating the manual sorting rate value for each sorting item and the machine sorting rate value for each sorting item in each historical working period is as follows: Among them, RgF ij is the manual sorting rate value for the jth sorting item in the i-th historical working period, ZsL uij ScZ is the total number of manual sortings for the jth sorting item in the uth historical working period, ui is the labor time value of the uth time in the i-th historical working period, α1 is the attenuation coefficient of the labor time stored in the database, WcL uij is the manual error rate value for the jth sorting item in the ith historical working period, α2 is the manual rate influence coefficient stored in the database, XgF j is the machine sorting rate value for the jth sorting item, XsC ij is the total number of machine sorting for the jth sorting item in the i-th historical working period, XcZ i is the machine working time value in the i-th historical working period, β1 is the machine working time attenuation coefficient stored in the database, XgZ i The machine failure index in the i-th historical working period, β2 is the machine rate influence coefficient stored in the database, u=1, 2, 3, …, u0, u0 is the number of historical working periods, i=1, 2, 3, …, i0, i0 is the number of historical working periods, j=1, 2, 3, …, j0, j0 is the number of sorting items.

5. The method for human-machine function allocation based on multi-objective cost index evaluation according to claim 2 is characterized in that: The specific steps to obtain several types of items to be sorted are: Normalize the weight value, color reflection value, and shape complexity index of each sorted item to be sorted; And the weight value, color reflection value and shape complexity index of each sorting item to be sorted after normalization are comprehensively analyzed to obtain the sorting complexity index of each sorting item to be sorted; The sorting complexity index of each sorting item to be sorted is compared and analyzed with the preset sorting complexity index interval to obtain several kinds of items to be sorted.

6. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 2 is characterized in that: The specific steps to obtain the labor cost evaluation index for each sorting item during the current working period of the sorting employee are as follows: Obtain the temperature adaptation reference value, humidity adaptation reference value, and noise adaptation reference value of the sorting employees, and conduct a comprehensive analysis based on the temperature adaptation value, humidity adaptation value, and noise adaptation value of the current working period to obtain the environmental correction factor of the sorting employees in the current working period; Read the historical manual error rate value for each sorting item in each historical working period, perform mean analysis, and obtain the error value of the sorting employee's current working period; A comprehensive analysis is conducted on the labor order value, error value, environmental correction factor of the sorting employee's current working period, and the manual sorting rate value for each sorted item in the corresponding historical working period to obtain the labor cost evaluation index for each sorted item in the sorting employee's current working period.

7. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 6 is characterized in that: The specific formula for calculating the labor cost evaluation index for each sorting item during the current working period of the sorting employee is as follows: RgC j =RgF j *RgD*(1+RcL*θ1)*(1+HzX*θ2); Among them, RgC j is the labor cost evaluation index for the jth sorting item during the current working period of the sorting staff, RgF j is the manual sorting rate value for the jth sorting item in the historical working period corresponding to the current working period of the sorting employee, RgD is the labor unit value of the current working period of the sorting employee, RcL is the error value of the current working period of the sorting employee, θ1 is the error coefficient stored in the data path, HzX is the environmental correction factor of the current working period of the sorting employee, θ2 is the environmental correction coefficient stored in the data path, j=1, 2, 3,…, j0, j0 is the number of sorting items.

8. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 2 is characterized in that: The specific steps to obtain the machine cost evaluation index for each sorting item are as follows: Obtain the maximum usage time of the machine, and conduct a comprehensive analysis based on the usage time, machine load, failure frequency, and maintenance frequency to obtain the wear factor of the machine; The machine unit value, wear factor and machine sorting rate value for each sorted item are comprehensively analyzed to obtain the machine cost evaluation index for each sorted item.

9. The method for allocating human-machine functions based on multi-objective cost index evaluation according to claim 8 is characterized in that: The specific formula for calculating the machine's wear factor and the machine cost evaluation index for each sorted item is as follows: Among them, HxZ is the wear factor of the machine, SyC is the usage time of the machine, ZdS is the maximum usage time of the machine, ω1 is the usage coefficient stored in the database, FhZ is the machine load value of the machine, τ is the adjustment coefficient stored in the database, ω2 is the load coefficient stored in the database, GzP is the fault frequency value of the machine, ByP is the maintenance frequency value of the machine, ω3 is the fault coefficient stored in the database, XcP j is the machine cost evaluation index for the jth sorting item, XgF j is the machine sorting rate value for the jth sorted item, XqD is the machine unit value of the machine, ζ is the wear coefficient stored in the data, j=1, 2, 3,…, j0, j0 is the number of sorted items.

10. The red tide monitoring and early warning system based on data analysis according to claim 1 is characterized in that: The specific steps for taking corresponding allocation measures based on the comparison analysis results are as follows: If the labor cost evaluation index of each sorted item in the current working period of the sorting employee is lower than the machine cost evaluation index of each sorted item, the first allocation measure is adopted; If the labor cost evaluation index of each sorted item in the current working period of the sorting employee is higher than the machine cost evaluation index of each sorted item, the second allocation measure is taken.

Images