Computer-aided efficient weight measurement method and device

Abstract

The present application relates to the technical field of weight measurement of transported items, and specifically to a computer-aided efficient weight measurement method and device, the method comprising: determining the deviation calibration factor of each weight sequence at the current moment according to the distribution of abnormal values ​​in the weight sequence of items collected by the sensor on the conveyor belt, and the overall weight difference between the items and other sensors; correcting each weight sequence based on the deviation calibration factor, and using a recursive filter to correct the measured weight of each corrected weight sequence twice, the result after the two corrections is the actual weight of the measured item. The present application aims to improve the accuracy of dynamically measuring the weight of items.

Description

Technical Field

[0001] The present application relates to the technical field of weight measurement of transported items, and in particular to a computer-aided efficient weight measurement method and device. Background Art

[0002] Computer technology is a key component of modern industry and scientific research. It uses advanced sensors and data processing capabilities to achieve high-precision and high-efficiency weight detection. The trend of intelligence indicates that computer-aided weight measurement will be more intelligent in data analysis and prediction. On a mobile production line, it is crucial to calibrate the weight of items detected at different times. As the use time increases, the performance of the measuring equipment will decline due to aging and wear, and it will be disturbed by environmental factors such as vibration, which may affect the stability and accuracy of the measuring equipment. Therefore, in order to improve the accuracy of the production line in transporting items, it is necessary to calibrate the weight of the items.

[0003] During the transportation process of the existing production line, the items may experience vibrations during transportation, which will affect the weight detection results of the items. In addition, since the transportation speed of the items on the production line may vary, the speed will affect the stability of the items when weighing. The sensors in the existing technology are not sensitive or stable enough to the rapidly changing dynamic weight and environmental conditions, and the impact of environmental conditions on the production line on weight measurement is difficult to fully control, and it is impossible to accurately measure the weight of dynamic items. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a computer-aided efficient weight measurement method and device, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a computer-aided efficient weight measurement method, the method comprising the following steps:

[0006] A1, determining the number of sensors for weighing the item according to its position on the conveyor belt, and obtaining the weight sequence of the item collected by each sensor for weighing the item;

[0007] A2, determine the deviation intensity of each weight sequence at the current moment according to the number of outliers in each weight sequence at the current moment and the numerical difference between adjacent outliers;

[0008] A3, combining the bias strength of any weight sequence and the overall difference between any weight sequence and all other weight sequences, determines the bias weight of any weight sequence at the current moment;

[0009] A4, combining the deviation weight of each weight sequence at the current moment and the overall difference between each element in each weight sequence and the mean of all elements, determining the deviation calibration factor of each weight sequence at the current moment;

[0010] A5, based on the deviation calibration factor, each weight sequence is corrected, and a recursive filter is used to perform a primary correction on the measured weight of the item for each corrected weight sequence. A recursive filter is used to perform a secondary correction on the result of the primary correction of all sensors. The result of the secondary correction is the actual weight of the measured item.

[0011] Preferably, the method for determining the deviation strength includes:

[0012] Get the proportion of outliers in each weight sequence at the current moment;

[0013] Based on the numerical differences between adjacent abnormal values ​​in each weight sequence at the current moment, determine the abnormal distribution of each weight sequence at the current moment;

[0014] The deviation strength is determined based on the proportion and the abnormal distribution; wherein the proportion and the abnormal distribution are both positively correlated with the deviation strength.

[0015] Preferably, the method for determining the abnormal distribution includes:

[0016] Sort all abnormal values ​​in each weight sequence at the current moment according to the collection time; obtain the differential sequence of the sorting results;

[0017] Calculate the mean of the difference sequence; Calculate the range of the difference sequence;

[0018] The mean and the range are combined to obtain the abnormal distribution.

[0019] Preferably, the method for determining the deviation weight is:

[0020] The product of the degree of deviation of any weight sequence at the current moment and the overall difference between any weight sequence and all other weight sequences is taken as the deviation weight of any weight sequence at the current moment.

[0021] Preferably, the overall difference between any one weight sequence and all other weight sequences includes:

[0022] The box counting method was used to calculate the fractal dimension between any weight sequence and every other weight sequence;

[0023] The average value of the fractal dimension between any weight sequence and all other weight sequences is taken as the overall difference between any weight sequence and all other weight sequences.

[0024] Preferably, the method for determining the deviation calibration factor includes:

[0025] Based on the overall difference between each element in each weight sequence at the current moment and the mean of all elements, determine the overall deviation degree of each weight sequence at the current moment;

[0026] The deviation calibration factor is determined based on the deviation weight and the overall deviation degree; wherein the deviation weight and the overall deviation degree are both positively correlated with the deviation calibration factor.

[0027] Preferably, the method for determining the overall deviation degree is specifically:

[0028] Calculate the numerical mean of each weight sequence at the current moment, and calculate the difference between each element in each weight sequence at the current moment and the numerical mean;

[0029] The sum of the differences between all elements in each weight sequence at the current moment and the numerical mean is calculated as the overall deviation degree.

[0030] Preferably, the method of correcting each weight sequence based on the deviation calibration factor and using a recursive filter to correct the measured weight of the item for each corrected weight sequence comprises:

[0031] The deviation calibration factors of each weight sequence at all acquisition moments are used to form a deviation factor sequence of the sensor to which the corresponding weight sequence belongs;

[0032] Multiply the deviation factor sequence of each sensor by the corresponding element of the weight sequence to obtain the weight sequence corrected by the corresponding sensor;

[0033] The corrected weight sequence of each sensor is used as the input of the recursive filter for correction, and the current optimal estimated state of each sensor is output.

[0034] Preferably, the results of the primary correction of all sensors are used to perform secondary correction of the measured weight of the item using a recursive filter, including:

[0035] The results of one correction of all sensors are randomly organized into a sequence, which is recorded as the correction weight sequence;

[0036] The corrected weight sequence is used as the input of the recursive filter for secondary correction and the final corrected weight is output.

[0037] In the second aspect, another embodiment of the present application provides a computer-aided efficient weight measurement device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned computer-aided efficient weight measurement method when executing the computer program.

[0038] The embodiments of the present application have at least the following beneficial effects:

[0039] The present invention proposes a computer-aided efficient weight measurement method and device. Aiming at the problem of weight measurement changes of items on a conveyor belt, the present application analyzes the number of abnormal values ​​in the weight sequence and the distribution of numerical differences, reflects the instability of sensor readings during the weighing process, and solves the weight deviation problem caused by sensor errors and external factors; further, the overall difference problem between the weight data of a single sensor and the overall sensor is solved to avoid the interference of a single sensor error on the overall measurement result; then, the overall deviation between the sensor reading and the historical measured weight is reflected to the extent to which the sensor reading needs to be calibrated; subsequently, by calibrating the weight of each sensor and performing two calibrations using a recursive filter, further optimization of the corrected weight sequence is achieved, thereby improving the accuracy of dynamic measurement of the weight of items. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flowchart of the steps of a computer-aided efficient weight measurement method provided in one embodiment of the present application;

[0042] Figure 2 A flow chart of a method for determining deviation strength provided in one embodiment of the present application;

[0043] Figure 3 A process flow chart of a correction provided for one embodiment of the present application;

[0044] Figure 4 A process flow chart of secondary correction provided for one embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the computer-aided efficient weight measurement method and device proposed in the present application, its specific implementation, structure, features and effects in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0047] The specific scheme of the computer-aided efficient weight measurement method and device provided in the present application is described in detail below with reference to the accompanying drawings.

[0048] See also Figure 1 , which shows a flowchart of a computer-aided efficient weight measurement method provided by an embodiment of the present application, the method comprising the following steps:

[0049] A1, determine the number of sensors for weighing the item according to its position on the conveyor belt, and obtain the weight sequence of the item collected by each sensor for weighing the item.

[0050] Install several dynamic weighing sensors on the conveyor belt and ensure that the detection range of the dynamic weighing sensors can cover the entire conveyor belt so that the weight of the items can be measured at any position.

[0051] The conveyor belt is divided into regions according to the detection range of all dynamic weighing sensors. The specific regional division method is: on the basis that the detection range of all dynamic weighing sensors is the same, the detection range of each dynamic weighing sensor is guaranteed to be minimum, and all dynamic weighing sensors need to include all areas of the conveyor belt.

[0052] In this embodiment, the collection interval of all dynamic weighing sensors is set to 1s. When an object is placed on the conveyor belt, the position of the object on the conveyor belt and the sensor area it occupies are determined. According to the position of the object, it is identified which sensor data will be used to weigh the object. In this embodiment, n sensors are set to weigh the object, and all sensor weight readings for weighing the object are collected, and the collected data are normalized to finally obtain n weight sequences of the object collected by different sensors at different times.

[0053] A2, according to the number of outliers in each weight sequence at the current moment and the numerical difference between adjacent outliers, determines the deviation intensity of each weight sequence at the current moment.

[0054] For each sensor that weighs the transported items, different sensors may produce measurement errors due to manufacturing tolerances, aging, wear or differences in installation positions. In addition, during dynamic weighing, the moving speed and position changes of the items may affect the measurement results.

[0055] Based on this, each weight sequence of the items is analyzed separately, and each weight sequence of the items is taken as input. The LOF anomaly detection algorithm is used to output the number of detected outliers, and the ratio of the number of outliers to the number of all elements in the weight sequence is calculated, that is, the proportion of the number of outliers in each weight sequence. It is recorded as the first ratio of the weight sequence. The first ratio reflects the frequency of the situation in which the sensor reading deviates greatly from the normal value during the weighing process. The deviation may be caused by sensor errors, improper placement of items, changes in conveyor belt speed or other external factors.

[0056] Among them, the LOF anomaly detection algorithm is a well-known technology and will not be described in detail. In other embodiments of the present application, algorithms such as isolation forest or clustering can also be used to detect outliers.

[0057] All outliers are sorted according to their corresponding collection times, and the difference sequence of the sorting results is calculated. Each element in the difference sequence represents the time interval between two adjacent outliers. The mean of all elements in the difference sequence and the difference between the maximum and minimum values, that is, the range of the difference sequence, are calculated. The mean of the difference sequence represents the average time interval between outliers, and the difference between the maximum and minimum values ​​represents the range of difference between normal intervals and abnormal intervals.

[0058] For each weight sequence at the current moment, based on the weight deviation a of each weight sequence at different collection moments and the distribution b of the weight deviation, the deviation intensity A of the selected weight sequence in the weight detection at the current moment is analyzed for each weight sequence, wherein the deviation intensity A is positively correlated with a and b, respectively.

[0059] It can be understood that a positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. This is determined by actual application and is not specifically limited in this application.

[0060] In this embodiment, the specific calculation relationship is: .

[0061] In other embodiments of the present application, the specific calculation relationship can also be .

[0062] In this application, the specific analysis process of a and b is as follows:

[0063] Among them, the situation a of weight deviation in each weight sequence at different collection moments is obtained by calculating the first ratio of each weight sequence. The first ratio reflects the frequency of the situation in which the sensor reading deviates greatly from the normal value during the weighing process. The larger the value, the higher the frequency of large deviations in the weighing process, and the greater the impact of weight deviation in the transportation of large items, thereby causing the deviation intensity A of the weight detection at the current moment to increase.

[0064] Among them, the abnormal distribution b of weight deviation in each weight sequence is obtained by fusing the mean of all elements in the difference sequence corresponding to the weight sequence with the range of the difference sequence, which represents the intensity and distribution characteristics of the weight deviation in the weighing process. The mean of all elements in the difference sequence corresponding to the weight sequence reflects the density of the deviation, while the difference between the maximum and minimum values ​​reflects the range of the deviation. The larger the value of b, the greater the unevenness of the weight deviation in the weighing process, and the greater the influence of the weight deviation on the actual weight of the detected object, and A increases accordingly.

[0065] It can be understood that fusion can be divided into forward fusion and reverse fusion. This embodiment adopts the forward fusion method. Forward fusion is a fusion method such as addition and multiplication between data. The specific forward fusion method is determined by the implementer according to the actual situation. The application does not impose any special restrictions.

[0066] In this embodiment, the product of the mean of all elements in the difference sequence corresponding to the weight sequence and the range of the difference sequence is used as the abnormal distribution b of the weight deviation of each weight sequence. In other embodiments of the present application, the sum of the two can also be used as the abnormal distribution b of the weight deviation of each weight sequence.

[0067] It should be understood that A represents the intensity and distribution characteristics of the weight deviation in the weighing process of the selected weight sequence up to the current moment, and the larger the value, the higher the instability of the selected sensor in detecting the transported items.

[0068] In one embodiment of the present application, a flow chart of a method for determining the deviation strength is shown in the attached Figure 2 shown.

[0069] A3, combining the bias strength of any weight sequence and the overall difference between any weight sequence and all other weight sequences, determines the bias weight of any weight sequence at the current moment.

[0070] When analyzing the weight sequence separately, only local problems are focused on, and the weight changes of the items detected by different sensors are not analyzed from a macro perspective. As a result, the performance of the entire weighing system cannot be fully evaluated, and the common trends and patterns of items reflected by multiple sensors cannot be identified, and the performance of the entire weighing system cannot be fully evaluated.

[0071] Based on this, for any weight sequence, the present application combines the deviation strength A of any weight sequence and the overall difference c between any weight sequence and all other weight sequences to determine the deviation weight B of any weight sequence at the current moment. The specific calculation relationship is: , the specific analysis process is as follows:

[0072] This application combines any weight sequence with other weight sequences in pairs to ensure that all combinations are non-repetitive, takes each combination as input, uses the box counting method to output the fractal dimension of each combination respectively, and calculates the fractal dimension mean of all combinations. The box counting method is a well-known technology and will not be described in detail.

[0073] In another embodiment of the present application, the overall difference c between any weight sequence and all other weight sequences is: calculating the DTW distance between each combination, and taking the average of the DTW distances of all combinations as the overall difference c between any weight sequence and all other weight sequences.

[0074] Among them, the overall difference c between any weight sequence and all other weight sequences is obtained by calculating the mean fractal dimension of any weight sequence and other weight sequences in all combinations. c reflects the consistency difference of the sensor belonging to any weight sequence relative to other sensors when measuring the same object. By calculating the mean fractal dimension of the combination of the selected sensor and other sensor weight sequences, the consistency difference of the selected sensor relative to other sensors can be evaluated. The larger the value, the greater the difference in measurement results between the selected sensor and other sensors, and the greater the influence of B.

[0075] Among them, the deviation intensity A of any weight sequence is calculated through the above step A2. A represents the deviation intensity of the weight detection of the sensor belonging to any weight sequence, reflecting the intensity and distribution characteristics of the weight deviation during the weighing process. The larger its value is, the greater the deviation between the sensor's measurement result and the actual value, the higher the measurement instability, and B increases accordingly.

[0076] It should be understood that B represents the degree of deviation of the sensor belonging to any weight sequence during the measurement process and the significance of this deviation relative to other sensors. The higher the value, the greater the deviation of the selected sensor during the measurement process, that is, the greater the error between the sensor reading and the actual weight.

[0077] A4, combining the deviation weight of each weight sequence at the current moment and the overall difference between each element in each weight sequence and the mean of all elements, determines the deviation calibration factor of each weight sequence at the current moment.

[0078] When analyzing the weight sequence, in addition to the differences between the abnormal values ​​analyzed above and the weight sequences of other sensors at the same moment, it is also necessary to consider the overall weight changes measured by the sensor at historical moments before the current moment. If there is a fluctuating deviation in the overall weight measurement process, the greater the deviation between the sensor reading and the actual weight, the greater the need for calibration adjustment of the sensor.

[0079] For each weight sequence at the current moment, the deviation calibration factor C of each weight sequence at the current moment is determined by combining the deviation weight B of each weight sequence and the overall difference between each element in each weight sequence and the mean of all elements. The overall difference between each element in each weight sequence and the mean of all elements is recorded as the overall deviation degree d of each weight sequence. The deviation weight and the overall deviation degree are both positively correlated with the deviation calibration factor.

[0080] In this embodiment, the specific calculation relationship is: .

[0081] In other embodiments of the present application, the specific calculation relationship can also be: .

[0082] In this application, The specific analysis process is as follows:

[0083] Among them, the deviation weight B of each weight sequence at the current moment is obtained through the calculation in the above step A3. B represents the degree of deviation of the sensor to which each weight sequence belongs during the measurement process and the significance of this deviation relative to other sensors, reflecting the degree of deviation of the sensor relative to other sensors when measuring the same object at a historical moment. The larger the value of B, the greater the deviation of the sensor during the measurement process, that is, the greater the error between the sensor reading and the actual weight, and C will also increase accordingly.

[0084] The process of obtaining the overall deviation degree d of each weight sequence is as follows: calculate the numerical mean of each weight sequence, record the difference between each element in the weight sequence and the numerical mean as y; calculate the sum Y of the differences between all elements in the weight sequence and the numerical mean, and use the sum Y as the overall deviation degree d of the corresponding weight sequence. The overall deviation degree d represents the deviation of the current weight value from the long-term mean, reflecting the degree of deviation between the reading of the selected sensor and the overall historical trend at the current moment. The larger its value, the greater the deviation between the current measurement value and the long-term trend, and the value of C increases accordingly.

[0085] It should be understood that C combines the influence of the deviation weight B and the overall deviation degree d, reflecting to what extent the reading of the sensor belonging to the selected weight sequence needs to be calibrated and adjusted at the current moment to be closer to the actual weight value. The larger the value of C, the greater the deviation between the sensor reading and the actual weight, and the sensor needs a larger calibration adjustment.

[0086] A5, based on the deviation calibration factor, each weight sequence is corrected, and a recursive filter is used to perform a primary correction on the measured weight of the item for each corrected weight sequence. A recursive filter is used to perform a secondary correction on the result of the primary correction of all sensors. The result of the secondary correction is the actual weight of the measured item.

[0087] For each weight sequence collected by each sensor, at each collection moment, a deviation calibration factor C corresponding to the collection moment is calculated when the collection moment is the latest collection moment.

[0088] For each sensor, the deviation calibration factors of all acquisition moments are arranged in ascending chronological order to form the deviation factor sequence of the sensor. The deviation factor sequence of each sensor is multiplied by the value at the corresponding acquisition moment in the weight sequence of the sensor to obtain the corrected weight sequence of each sensor.

[0089] Then, the weight of the measured object is corrected using the extended Kalman filter with the corrected weight sequence of each sensor as input, and the current optimal estimated state is output, which is used as the corrected weight of the object measured by the sensor.

[0090] In one embodiment of the present application, a process flow chart of a correction is shown in the attached Figure 3 shown.

[0091] The extended Kalman filter applies the standard Kalman filter by linearizing the nonlinear model. In the dynamic weighing system, through the principle of linearizing the nonlinear system model, a continuously updated state estimate and a corresponding covariance matrix are finally obtained, so that the state estimate can represent the corrected weight value. Among them, the calculation process of the extended Kalman filter is a well-known technology and will not be repeated.

[0092] In another embodiment of the present application, the recursive least square method is used to perform a correction on the weight of the measured object calculated by the corrected weight sequence of each sensor, and the current optimal estimation state of each sensor is output.

[0093] In one embodiment of the present application, the process flow chart of the secondary correction is as shown in the attached Figure 4 shown.

[0094] In other embodiments of the present application, other recursive filters may be used to output the current optimal estimation state of the corrected weight sequence of each sensor.

[0095] Then, the corrected weights output by all sensors through the extended Kalman filter algorithm are randomly combined to form a new corrected weight sequence. The new corrected weight sequence is used as input, and the new corrected weight sequence is corrected twice using the extended Kalman filter to output the final corrected weight, which is the weight of the item.

[0096] The embodiment of the present application also proposes a computer-assisted efficient weight measurement device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the steps of the computer-assisted efficient weight measurement method described above when executing the computer program. Since the computer-assisted efficient weight measurement method has been described in detail above, it will not be repeated here.

[0097] The various embodiments in the present application are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0098] It should be noted that, unless otherwise specified and limited, terms such as "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a circuit structure, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such article or device. In the absence of further restrictions, an element defined by the sentence "including one..." does not exclude the existence of other identical elements in the article or device including the element. In addition, the term "and\or" used herein includes any and all combinations of one or more related listed items.

[0099] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not invented by the present application.

[0100] It should be understood that the present application is not limited to the exact construction that has been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof.

Claims

1. A computer-aided efficient weight measurement method, characterized in that: The method comprises the following steps: A1, determining the number of sensors for weighing the item according to its position on the conveyor belt, and obtaining the weight sequence of the item collected by each sensor for weighing the item; The method for obtaining the weight sequence is: Use the same sensor to weigh the same item at different collection times, collect the sensor weight readings and perform normalization processing to obtain the weight sequence of the item corresponding to the sensor; A2, determine the deviation intensity of each weight sequence at the current moment according to the number of outliers in each weight sequence at the current moment and the numerical difference between adjacent outliers; A3, combining the bias strength of any weight sequence and the overall difference between any weight sequence and all other weight sequences, determines the bias weight of any weight sequence at the current moment; A4, combining the deviation weight of each weight sequence at the current moment and the overall difference between each element in each weight sequence and the mean of all elements, determining the deviation calibration factor of each weight sequence at the current moment; A5, based on the deviation calibration factor, each weight sequence is corrected, and a recursive filter is used to perform a primary correction on the measured weight of the item for each corrected weight sequence. A recursive filter is used to perform a secondary correction on the result of the primary correction on the measured weight of the item, and the result of the secondary correction is the actual weight of the measured item.

2. The computer-aided efficient weight measurement method according to claim 1, characterized in that: The method for determining the deviation strength includes: Get the proportion of outliers in each weight sequence at the current moment; Based on the numerical differences between adjacent abnormal values ​​in each weight sequence at the current moment, determine the abnormal distribution of each weight sequence at the current moment; The deviation strength is determined based on the proportion and the abnormal distribution; wherein the proportion and the abnormal distribution are both positively correlated with the deviation strength.

3. The computer-aided efficient weight measurement method according to claim 2, characterized in that: The method for determining the abnormal distribution includes: Sort all abnormal values ​​in each weight sequence at the current moment according to the collection time; obtain the differential sequence of the sorting results; Calculate the mean of the difference sequence; Calculate the range of the difference sequence; The mean and the range are combined to obtain the abnormal distribution.

4. The computer-aided efficient weight measurement method according to claim 2, characterized in that: The method for determining the deviation weight is: The product of the deviation strength of any weight sequence at the current moment and the overall difference between any weight sequence and all other weight sequences is taken as the deviation weight of any weight sequence at the current moment.

5. The computer-aided efficient weight measurement method according to claim 4, characterized in that: The overall difference between any one weight sequence and all other weight sequences includes: The box counting method was used to calculate the fractal dimension between any weight sequence and every other weight sequence; The average value of the fractal dimension between any weight sequence and all other weight sequences is taken as the overall difference between any weight sequence and all other weight sequences.

6. The computer-aided efficient weight measurement method according to claim 4, characterized in that: The method for determining the deviation calibration factor includes: Based on the overall difference between each element in each weight sequence at the current moment and the mean of all elements, determine the overall deviation degree of each weight sequence at the current moment; The deviation calibration factor is determined based on the deviation weight and the overall deviation degree; wherein the deviation weight and the overall deviation degree are both positively correlated with the deviation calibration factor.

7. The computer-aided efficient weight measurement method according to claim 6, characterized in that: The method for determining the overall deviation degree is specifically as follows: Calculate the numerical mean of each weight sequence at the current moment, and calculate the difference between each element in each weight sequence at the current moment and the numerical mean; The sum of the differences between all elements in each weight sequence at the current moment and the numerical mean is calculated as the overall deviation degree.

8. The computer-aided efficient weight measurement method according to claim 6, characterized in that: The method of correcting each weight sequence based on the deviation calibration factor and using a recursive filter to correct the measured weight of the item for each corrected weight sequence includes: The deviation calibration factors of each weight sequence at all acquisition moments are used to form a deviation factor sequence of the sensor to which the corresponding weight sequence belongs; Multiply the deviation factor sequence of each sensor by the corresponding element of the weight sequence to obtain the weight sequence corrected by the corresponding sensor; The corrected weight sequence of each sensor is used as the input of the recursive filter for correction, and the current optimal estimated state of each sensor is output.

9. The computer-aided efficient weight measurement method according to claim 8, characterized in that: The result of the primary correction of the measured weight of the item is used to perform a secondary correction of the measured weight of the item using a recursive filter, including: The results of one correction of all sensors are randomly organized into a sequence, which is recorded as the correction weight sequence; The corrected weight sequence is used as the input of the recursive filter for secondary correction and the final corrected weight is output.

10. A computer-aided efficient weight measuring device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the computer-aided efficient weight measurement method as described in any one of claims 1 to 9 are implemented.

Images