An energy distribution method, device and system for handling items

Abstract

This invention relates to the field of computer technology applications, and in particular to an energy allocation method, device, and system for item processing. The method is based on an item processing record data information table (RF). The RF divides items into different clusters and sub-clusters according to visual perception attributes, and records key information such as the maximum batch processing weight threshold, energy consumption weight correlation expression, and cleanliness weight correlation expression for each item sub-cluster under different processing methods. The method obtains the data record table of the items to be processed and combines it with the information in the RF to generate processing information for the current items, achieving precise energy allocation. This method improves energy utilization efficiency, ensures the stability of processing results, enhances the intelligence and automation level of the processing flow, and has good adaptability and scalability, making it suitable for various item processing scenarios.

Description

Technical Field

[0001] This invention relates to the field of computer technology applications, and in particular to an energy distribution method, device and system for handling items. Background Technology

[0002] With the rapid development of industrial automation and intelligent manufacturing, goods handling systems (such as laundry systems) are becoming increasingly common in commercial laundry and household laundry scenarios. As a typical high-energy-consuming goods handling scenario, laundry systems encompass multiple stages, including garment sorting, pre-treatment, washing, drying, ironing, and disinfection. The energy consumption of each stage (such as electrically driven motors, heating devices, and steam systems for heat supply) needs to be coordinated through computer system instruction scheduling. However, the current energy allocation logic of laundry systems still relies on empirically-based, fixed procedures, lacking dynamic optimization capabilities based on data processing. This leads to low energy efficiency, specifically: the energy allocation parameters of existing systems (such as washing water temperature, motor speed, and drying time) are mostly based on manual experience and preset, without precise control through sensor data and algorithm analysis. For example, the fixed parameter of "heating cotton garments at 60℃" in the washing program does not consider details such as the actual degree of soiling (light sweat stains do not require high temperatures) and garment thickness (the difference in heat energy requirements between thin T-shirts and thick coats), resulting in a disconnect between the energy instructions executed by the computer system and actual needs. Under this empirical logic, the ineffective energy consumption of a single wash can reach 15%-25%, which is essentially due to the lack of real-time processing and parameter mapping capabilities for clothing characteristic data. Summary of the Invention

[0003] To address the aforementioned technical problems, the technical solution adopted by this invention is as follows:

[0004] According to a first aspect of the present invention, an energy allocation method for handling items is provided, the method being implemented based on a data processing system, the data processing system including a storage module, the storage module storing an item handling record data information table RF, RF={RF1, RF2, ..., RF...} u , ..., RF q}, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u）}, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v）}, U uv RF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r YC is the energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method. uv r Let the cleanliness weight correlation expression be given for the v-th item subcluster under the r-th processing method; the method includes the following steps:

[0005] S100, the data processing system acquires the digital data of the visual features of the items to be processed and the numerical data of the processing weight through the data acquisition interface, so as to generate a structured data record table and store it in the storage module; each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the items to be processed in the corresponding item sub-cluster.

[0006] S200, the data processing system calls the item processing record data information table and data record table in the storage module to generate processing information for the current item to be processed, and outputs the processing information, which includes processing method and processing batch information.

[0007] According to a second aspect of the present invention, an electronic device is provided, including a processor and a memory; the processor executes the steps of the method described in the first aspect of the present invention by invoking a program or instructions stored in the memory.

[0008] According to a third aspect of the present invention, an energy distribution system for handling articles is provided, the system comprising:

[0009] The storage module stores an item processing record data information table RF; RF = {RF1, RF2, ..., RF...} u , ..., RF q}, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u）}, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv ={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v）}, U uv RF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r YC is the energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method. uv r Let be the cleanliness weight correlation expression for the v-th item sub-cluster under the r-th processing method.

[0010] The data acquisition module is used to acquire the digitized visual feature data and the numerical data of the processing weight of the current item to be processed through the data acquisition interface, so as to generate a structured data record table and store it in the storage module; wherein, each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the item to be processed in the corresponding item sub-cluster.

[0011] The processing information generation module is used to call the item processing record data information table and data record table in the storage module, generate processing information for the current item to be processed, and output the processing information, which includes processing method and processing batch information.

[0012] The energy allocation method for item processing provided in this invention includes: acquiring a current data record table to be processed, the data record table being generated based on the visual features of the current items to be processed; generating processing information for processing the current items to be processed based on RF and the data record table, and outputting the processing information, the processing information including processing method and processing batch information. This method has at least the following technical effects:

[0013] (1) Achieve precise energy allocation: Based on the RF information table of item processing record data, items are subdivided into clusters and subclusters. The subdivision is based on the visual perception attributes of the items, which can more accurately match the characteristics of different item subclusters. By combining the maximum processing weight threshold, energy consumption weight correlation expression and cleanliness weight correlation expression of each subcluster under different processing methods, the optimal energy allocation scheme can be calculated for the specific weight of the item to be processed, so as to avoid energy waste and improve energy utilization efficiency.

[0014] (2) Ensuring the stability of treatment results: Historical data stored in RF can provide a reliable reference for current treatment. By using the cleanliness-weight correlation expression, it can be ensured that the cleanliness of the items will not be reduced due to excessive pursuit of energy saving when allocating energy, so that the treated items always maintain a high level of cleanliness and ensure the stability of the treatment results.

[0015] (3) Improve the intelligence and automation level of the processing flow: Based on the data recording table and RF information table, processing information can be automatically generated, reducing manual intervention. There is no need for manual judgment of energy allocation based on experience, which reduces human error and makes the material processing flow more intelligent and automated, thereby improving processing efficiency.

[0016] (4) Enhanced adaptability and scalability: The way item clusters and sub-clusters are divided and the structure of the RF information table enable the method to adapt to the processing needs of different types of items. When a new item type or processing method appears, the new content can be incorporated into the energy allocation system simply by updating and expanding the RF information table accordingly, which has strong adaptability and scalability.

[0017] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of an energy distribution method for handling items, provided as an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Unless otherwise defined, 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 invention pertains. The terminology used herein in the description of this invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] It should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. A process can be terminated when its operation is complete, but it may also have additional steps not included in the figures. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0023] This invention provides an energy allocation method for item processing, which is implemented based on a data processing system. The data processing system includes a storage module that stores an item processing record data information table RF.

[0024] Where RF = {RF1, RF2, ..., RF} u , ..., RF q}, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u）}, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv ={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v）}, U uv RF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r The energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method can be stored in the storage module in the form of a function pointer. YC uv rThe cleanliness weight association expression for the v-th item subcluster under the r-th processing method can be stored as an executable code snippet.

[0025] In this embodiment of the invention, the visual perception attribute may be color. The item clusters are obtained by the data processing system using the digitized features of the item's visual perception attributes (such as color pixel value matrices and texture feature vectors) through a K-means clustering algorithm. During the clustering process, the cluster centers are iteratively optimized to minimize the variance of the data within each cluster.

[0026] In this embodiment of the invention, the item type includes size specifications, material, and dirt level parameters. The unique identifier for an item sub-cluster can be its coded value. This coded value is unique and identifiable, and can be in the form of letters, numbers, or a combination thereof, used to uniquely distinguish different item sub-clusters. For example, "C01-S03" can represent the third item sub-cluster under the first item cluster. The unique identifier for a processing method is its coded value. This coded value is also unique and can be compiled based on the type, parameters, and other characteristics of the processing method to quickly identify the corresponding processing method. For example, "P02-H05" can represent the fifth sub-processing method in the second type of basic processing method. The above coded values ​​should remain globally unique in the item processing record data information table RF to ensure accurate association with the corresponding item sub-cluster and processing method during data storage, retrieval, and processing information generation, avoiding confusion.

[0027] In this embodiment of the invention, the size specification dirtiness parameter value can be determined based on manual labeling or visual inspection. Manual labeling involves operators classifying the dirtiness of items based on experience (e.g., "light," "moderate," "heavy"), and then assigning a fixed parameter value (e.g., 20, 50, 80) to each level. To reduce subjective error, standard reference cards (e.g., sample images of different dirtiness levels) can be developed to ensure more consistent labeling. Visual inspection works by acquiring images of the item's surface using image acquisition devices (e.g., cameras, industrial cameras), analyzing the characteristics of the dirt areas in the images (area, color depth, contrast, etc.), and converting them into dirtiness parameter values. The quantification method involves setting a "cleanliness baseline value" (e.g., the RGB mean of pure white clothing), calculating the deviation between the actual image and the baseline value (e.g., color deviation percentage, grayscale value difference); statistically analyzing the proportion of the dirt area to the item's surface area (e.g., "5%" corresponds to low dirtiness, "30%" corresponds to high dirtiness), and mapping this to a value of 0-100 (0 for completely clean, 100 for severely soiled).

[0028] In this embodiment of the invention, the division of item subclusters is achieved by the data processing system through hierarchical clustering algorithm based on the digital encoding of item type feature parameters, and the feature similarity of data within the subclusters is ≥90%.

[0029] In this embodiment of the invention, the recording information of the processing method is stored through standardized data structure.

[0030] In one illustrative embodiment of the present invention, the article processing process involves performing processing operations on the article through a processing device, specifically clothes that need to be washed, and the processing device being a washing machine.

[0031] Furthermore, in this embodiment of the invention, the processing method for each item sub-cluster is a processing method capable of processing that item sub-cluster. When the item is clothing, the processing method can be a washing mode. The unit of weight processed is a preset unit, such as kg.

[0032] Furthermore, in this embodiment of the invention, YE uv r and YC uv r It can be obtained based on the historical dataset of the v-th item subcluster under the r-th processing method. Each historical data point in the historical dataset includes the processed weight, energy consumption parameter value, and cleanliness parameter value. The historical dataset can be obtained based on the operating logs of the item processing equipment (such as washing machines, dishwashers, etc.).

[0033] In this embodiment of the invention, the energy consumption parameter value E corresponding to the d-th historical data point is... d The following conditions must be met: E d =(Ea d -Eb d ) / Eb d ×100, Ea d Eb represents the actual energy consumption value corresponding to the processing weight in the d-th historical data. d Let d be the baseline energy consumption value corresponding to the processing weight in the d-th historical data, where d ranges from 1 to Q, and Q is the number of historical data.

[0034] In this embodiment of the invention, Ea d This can be equal to the product of the actual water consumption corresponding to the processed weight in the d-th historical data point and the water conversion factor, plus the product of the actual electricity consumption corresponding to the processed weight in the d-th historical data point and the electricity conversion factor. The water conversion factor can be approximately equal to 0.000086, and the electricity conversion factor can be approximately equal to 0.1229. Eb d It can be an empirical value, specifically based on historical operating data, and can be obtained by constructing a benchmark mapping relationship of "processing weight - benchmark energy consumption value" through data processing and algorithm modeling.

[0035] In this embodiment of the invention, the cleanliness parameter value can be obtained based on a cleanliness detector or sensory evaluation. The maximum cleanliness parameter value can be set to 10 points; the higher the cleanliness, the larger the corresponding cleanliness parameter value.

[0036] Specific, YEuv r The following method can be used to obtain the data: Preprocess the historical dataset of the v-th item subcluster under the r-th processing method, removing data with abnormal processing weight or energy consumption parameter values ​​(abnormal data is defined as data deviating from the dataset mean by more than 3 standard deviations); using the processing weight in the preprocessed dataset as the independent variable and the energy consumption parameter value as the dependent variable, perform linear fitting using the least squares method to obtain the linear regression equation YE. uv r =k1×N+b1, where k1 is the fitting slope, b1 is the intercept, N is the processing weight, and the goodness of fit R² must be ≥0.9.

[0037] YC uv r The data was obtained as follows: The historical dataset of the v-th item subcluster under the r-th processing method was preprocessed to remove data with abnormal processing weight or cleanliness parameter values ​​(the criteria for judging abnormal data are the same as above); using the processing weight in the preprocessed dataset as the independent variable and the cleanliness parameter value as the dependent variable, a linear regression equation YC was obtained by performing linear fitting using the least squares method. uv r =k2×N+b2, where k2 is the fitting slope and b2 is the intercept, and the goodness of fit R² must be ≥0.9. It should be noted that in practical applications, if the predicted cleanliness parameter value in the fitting result exceeds the maximum cleanliness parameter value Cmax, the predicted cleanliness parameter value Cmax shall be taken.

[0038] In this embodiment of the invention, the maximum processing weight threshold of a certain processing method refers to the maximum weight limit of items that can be processed in a single batch under that processing method. In other words, it is the upper limit of weight that cannot be exceeded in a single processing session while ensuring the preset processing effect (such as meeting cleanliness requirements and keeping energy consumption within a reasonable range). Taking an item processing scenario as an example, if the maximum processing weight threshold of a certain processing method is 10kg, it means that the maximum processing weight is 10kg when processing items in a single batch using this method. When the weight of the items to be processed does not exceed 10kg, processing can be completed in a single batch while ensuring the processing effect; if it exceeds 10kg, single-batch processing may lead to substandard cleanliness and abnormally high energy consumption. In this case, multiple batches need to be processed, and the weight of each batch must not exceed the threshold.

[0039] Furthermore, WT uv r Obtain it through the following methods:

[0040] S1, obtain the historical dataset of the v-th item sub-cluster under the r-th processing method. Each historical data in the historical dataset includes the processing weight, energy consumption parameter value and cleanliness parameter value.

[0041] S2, delete historical data in the historical dataset whose cleanliness parameter value is less than the set cleanliness parameter value threshold, and obtain the historical dataset that has been deleted, which is used as the target dataset.

[0042] S3. For each data point in the target dataset, obtain the corresponding fusion value. The fusion value satisfies the following condition: SM = We × E + Wc × (Cmax - C), where SM is the fusion value corresponding to the data, used to quantify the comprehensive performance of energy consumption and cleanliness. E is the energy consumption parameter value corresponding to the data. C is the cleanliness parameter value corresponding to the data, We is the energy consumption weight, Wc is the cleanliness weight, and We + Wc = 1.

[0043] In this embodiment of the invention, the values ​​of We and Wc can be dynamically adjusted based on actual needs: if energy consumption needs to be reduced first in the processing scenario (such as in energy-saving mode), then We > Wc (for example, We = 0.6, Wc = 0.4); if cleanliness needs to be guaranteed first in the processing scenario (such as in deep cleaning mode), then We < Wc (for example, We = 0.3, Wc = 0.7); if the importance of energy consumption and cleanliness needs to be balanced (such as in standard mode), then We = Wc (for example, We = Wc = 0.5).

[0044] S4. Using the processed weight in the target dataset as the independent variable and the fusion value in the target dataset as the dependent variable, obtain the data fitting curve.

[0045] In this embodiment of the invention, a polynomial fitting or nonlinear fitting method can be used to construct the curve. The type of fitting function must reflect the trend relationship between the processed weight and the fused value. In one illustrative embodiment, a third-order polynomial function can be used, with the expression SM = a × N³ + b × N² + c × N + d, where a, b, c, and d are fitting coefficients. The fitting process uses the least squares method to solve for the coefficients, requiring a goodness of fit R² ≥ 0.9 to ensure the representativeness of the curve to the data trend.

[0046] It should be noted that if the amount of data in the target dataset is less than the preset number, such as less than 30 data points, interpolation can be used to supplement the data before fitting to ensure the stability of the curve.

[0047] S5, obtain the processing weight corresponding to the slope abrupt change point of the data fitting curve as WT. uv r .

[0048] In this embodiment of the invention, the slope abrupt change point satisfies the following condition:

[0049] In the left neighborhood of the processed weight corresponding to the slope abrupt change point, the absolute value of the slope of the data fitting curve is less than or equal to K1, and the slope sign is negative or close to zero, that is, the fusion value SM shows a significant upward trend with the increase of processed weight. K1 is a preset gentle slope threshold.

[0050] In the right neighborhood of the processed weight corresponding to the slope abrupt change point, the absolute value of the slope of the data fitting curve is greater than or equal to K2, and the slope sign is positive, meaning that the fusion value SM shows a significant upward trend with the increase of processed weight. K2 is a preset steep slope threshold, and K2 > K1.

[0051] The slope abrupt change point is the inflection point where the first derivative of the curve changes abruptly from less than or equal to K1 to greater than or equal to K2, and the second derivative at this inflection point is greater than or equal to M, where M is a preset second derivative threshold.

[0052] The values ​​of K1, K2, and M need to be calibrated through experimental data based on the specific processing scenario (such as the type of item and the processing technology). For example, for textile items, K1=0.1, K2=0.5, and M=0.3 can be set.

[0053] Those skilled in the art should understand that the method for obtaining the abrupt change point of the slope of the data fitting curve falls within the scope of existing technology.

[0054] Furthermore, embodiments of the present invention provide an energy distribution method for handling articles, which may include... Figure 1 The following steps are shown:

[0055] S100, the data processing system acquires digitized visual feature data and numerical data of the processed weight of the items to be processed through the data acquisition interface, and generates a structured data record table, which is stored in the storage module. In this embodiment of the invention, visual features may include visual perception attributes, material, size specifications, and degree of contamination. The specific generation logic of the data record table is as follows: visual features of the items to be processed are extracted through image recognition, sensor detection, and other technical means (such as determining the material through spectral analysis, obtaining size specifications through image size measurement, and judging the degree of contamination through grayscale value analysis, etc.). The extracted features are compared and matched with a preset item sub-cluster feature library to determine the item sub-cluster to which each item to be processed belongs, and then relevant information is recorded according to the item sub-cluster.

[0056] In addition, the data record table can include auxiliary information such as record generation time, feature recognition confidence (such as the probability value of successful matching), and data verification code. The feature recognition confidence is used to evaluate the reliability of the sub-cluster matching results. When the confidence is lower than a preset threshold (such as 85%), it needs to be manually reviewed before generating the formal data record table to ensure the accuracy of the data basis.

[0057] In this embodiment of the invention, each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the item to be processed in the corresponding item sub-cluster.

[0058] S200, the data processing system calls the item processing record data information table and data record table in the storage module to generate processing information for the current item to be processed, and outputs the processing information, which includes processing method and processing batch information.

[0059] Those skilled in the art should understand that the processing information for processing the current items to be processed includes the processing information for the items to be processed corresponding to each row of data in the data record table.

[0060] In this embodiment of the invention, the data processing system is a functional unit for performing electronic digital data processing. It may include a data acquisition module, a data processing module, a storage module, and an output module. Each module interacts with the other via an internal data link, specifically defined as follows: Data Acquisition Module: Responsible for receiving digitized visual feature data (such as pixel value arrays and feature vectors) and processing weight numerical data through a data interface. It converts analog signals into digital signals and transmits them to the data processing submodule. Data Processing Module: Equipped with data processing algorithms, it performs cluster analysis, correlation expression calculation, comparison and filtering, and other operations on the input digitized data to generate intermediate processing results. Storage Module: Employs digital storage media to store the item processing record data information table RF, the structured data record table, and intermediate data during the processing. It supports digital reading, writing, and indexing of data. Output Module: Converts the generated processing information into standardized digital formats (such as JSON and XML) and outputs it to other digital systems or terminals through a data interface.

[0061] Furthermore, the S200 specifically includes:

[0062] S210, obtain the processing weight threshold set NS(i) = {N1(i), N2(i), ..., N} corresponding to the item sub-cluster in the data record table. j (i), ..., N m (i)}, where N j (i) represents the maximum processing weight threshold of the item sub-cluster corresponding to the i-th row of data under the j-th processing method, where j ranges from 1 to m, m is the number of processing methods for the item sub-cluster corresponding to the i-th row of data, i ranges from 1 to HM, and HM is the number of rows of data in the data record table.

[0063] S220, iterate through NS(i), for each N reached... j (i) If N j (i)≥N i , will Nj (i) The unique identifier of the corresponding processing method is added to the processing method record set; N i The processing weight is the data in the i-th row of the data record table. The initial value of the processing method record set is empty.

[0064] S230, if the number of unique identifiers in the processing method record set Q=1, use the unique identifiers in the processing method record set as the target identifiers corresponding to the i-th row of data, and generate the processing information for the item to be processed corresponding to the i-th row of data as: single batch processing, processing method is the processing method corresponding to the target identifier; if Q>1, obtain the fusion value corresponding to each unique identifier in the processing method record, use the unique identifier corresponding to the minimum fusion value as the target identifiers corresponding to the i-th row of data, and generate the processing information for the item to be processed corresponding to the i-th row of data as: single batch processing, processing method is the processing method corresponding to the target identifier; if Q=0, execute S240.

[0065] S240, obtain the processing batches C(i,j) required for the item to be processed corresponding to the i-th row of data under the j-th processing method, C(i,j) = roundup(N). i / N j (i)), roundup() means rounding up; where the processing weight of each processing batch in the first C(i,j)-1 processing batches is N. j (i), the processing weight corresponding to the C(i,j)th processing batch is N. i -(C(i,j)-1)×N j (i).

[0066] S250, obtain the total energy consumption ET of the item to be processed corresponding to the i-th row of data under the j-th processing method. ij .

[0067] ET ij =∑ C（i，j） v=1 E ij (v) + (C(i,j)-1)×△E0, where E ij (v) represents the energy consumption parameter value corresponding to the v-th batch, determined based on the energy consumption-weight correlation expression corresponding to the j-th processing method. Specifically, the processing weight corresponding to the v-th batch is substituted into the corresponding energy consumption-weight correlation expression to obtain E. ij(v), where v ranges from 1 to C(i,j), and ΔE0 represents the start-up energy consumption between batches, which can be determined based on factors such as the type and power of the processing equipment. When the processing equipment is an industrial laundry unit, the instantaneous power during startup of a traditional industrial laundry unit can reach 45kW. If the startup time is 1 minute, the startup energy consumption is approximately 0.75 kWh. With a frequency converter, the startup power can be reduced to 30kW, and the energy consumption for a 1-minute startup time is approximately 0.5 kWh.

[0068] S260, obtain min(ET) i1 ET i2 , ..., ET ij , ..., ET im The processing method corresponding to the i-th row of data is used as the target processing method, and the processing information for the items to be processed corresponding to the i-th row of data is generated as follows: batch processing, with the processing weight of the v-th batch under the j-th processing method being N. ij (v), the processing method is the target processing method.

[0069] In this embodiment of the invention, if min(ET) i1 ,ET i2 , ..., ET ij , ..., ET im There are multiple processing methods available, and you can select the processing method with the smallest batch size as the target processing method.

[0070] Processes S210 to S260 can be used to obtain the processing information of the items to be processed corresponding to all rows of data in the data record table.

[0071] Furthermore, in another embodiment of the present invention, the following steps are also included:

[0072] S300, set counter h=1.

[0073] S310: If h≤HM, execute S320; otherwise, execute S380.

[0074] S320: For the h-th processing information in the processing information set corresponding to the data record table, if the processing weight of the last batch in the processing information is less than the corresponding maximum processing weight threshold, execute S330.

[0075] S330, if the intermediate processing information set includes the h-th processing information, delete the h-th processing information from the intermediate processing information set, and obtain processing information from the intermediate processing information set after deleting the h-th processing information that has the same processing method, similar visual perception attributes and item type as the h-th processing information as the candidate information for the h-th processing information. If the intermediate processing information set does not include the h-th processing information, obtain processing information from the intermediate processing information set that has the same processing method, similar visual perception attributes and item type as the h-th processing information, and whose last batch processing weight is less than the corresponding maximum processing weight threshold as the candidate information for the h-th processing information. The initial value of the intermediate processing information set is the processing information set corresponding to the data record table.

[0076] In this embodiment of the invention, visual perception similarity refers to the difference in visual features between items being within a preset threshold range, which may include: color: belonging to the same color system (such as light red and pink, dark blue and navy blue), or color difference value (such as CIEDE2000 color difference value) ≤ 5; texture: similarity of texture density, direction, and roughness ≥ 80% (calculated by image texture feature extraction algorithm, such as gray-level co-occurrence matrix, to calculate the cosine similarity of feature vectors); shape: matching degree of geometric shape ≥ 70% (such as circle and ellipse, rectangle and square, calculated by edge detection algorithm to calculate the overlap of shape contours).

[0077] Similar item types refer to items whose materials, uses, and physical properties belong to adjacent subcategories within the same category system. For example: in terms of materials, cotton and linen (cotton and linen) and chemical fibers (polyester and nylon) are considered similar; in terms of uses, kitchenware (bowls and plates) and clothing accessories (scarves and shawls) are considered similar; in terms of physical properties, the difference in parameters such as hardness and temperature resistance is ≤20% (based on industry standard parameter grading).

[0078] The above determination can be achieved through automated matching using a preset feature comparison database. When the similarity meets the above threshold, it is determined to be "similar".

[0079] S340, obtain the sum NT of the processing weight of the h-th processing information and the processing weight of the x-th candidate information of the h-th processing information. hx If the common processing method corresponding to the h-th processing information and the x-th candidate information has a maximum processing weight threshold greater than or equal to NT, hx If the processing method is correct, then use this processing method as the target candidate processing method corresponding to the h-th processing information and the x-th candidate information, and execute S360; otherwise, execute S350.

[0080] In this embodiment of the invention, if the maximum processing weight threshold is greater than or equal to NT in the common processing method corresponding to the h-th processing information and the x-th candidate information,hx There are multiple processing methods. The processing method with the smallest maximum processing weight threshold is selected as the target candidate processing method corresponding to the h-th processing information and the x-th candidate information.

[0081] S350, set x = x + 1. If x ≤ g(h), execute S340; otherwise, execute S370. The initial value of x is 1, and g(h) is the number of candidate information for the h-th information to be processed.

[0082] S360, obtain the sum of the fusion value corresponding to the h-th processed information and the fusion value corresponding to the x-th processed information SM1 hx And based on the energy consumption weight correlation expression and cleanliness weight correlation expression corresponding to the target candidate processing method corresponding to the h-th processing information and the x-th candidate information, obtain NT. hx The corresponding fusion value SM2 hx If SM2 hx <SM1 hx SM2 hx If a candidate fusion value is added to the candidate fusion value record set, execute S350; otherwise, execute S350; the initial value for adding a candidate fusion value to the candidate fusion value record set is empty.

[0083] S370, take the candidate information corresponding to the minimum candidate fusion value in the candidate fusion value record set as the target candidate information of the h-th processing information, generate the merged processing information corresponding to the h-th processing information, delete the h-th processing information and the corresponding target candidate information from the intermediate processing information set, set h=h+1, and execute S310; the merged processing information corresponding to the h-th processing information includes merging the items to be processed in the last batch of the h-th processing information and the items to be processed in the last batch of the target candidate information together, and process them according to the processing method corresponding to the minimum candidate fusion value;

[0084] S380: Update the processing information obtained in S200 based on all the merged processing information to obtain the updated processing information, which serves as the final processing information for the data record table.

[0085] In this embodiment of the invention, S380 may specifically include:

[0086] S3801, Identify the original information to be replaced, including locating the original record (including processing batch, batch weight, processing method, etc.) corresponding to the h-th processing information and its target candidate information from the processing information generated in S200.

[0087] S3802, Replace the information of the merged batch, including deleting the record of "last batch" in the h-th processing information and the record of "last batch" in the target candidate information; and adding a new merged batch record: the processing weight is NThx (the sum of the weights of the last batches of both), the processing method is "the processing method corresponding to the minimum candidate fusion value", and the fusion value is updated to SM2hx.

[0088] S3803, retain the information of non-merged batches, including the processing weight, processing method and other information of the batches other than the last batch in the h-th processing information and target candidate information.

[0089] S3804, update batch number and statistics, including renumbering all merged batches in sequence (e.g., after merging the original batches 1, 2, 3 with candidate batches 1, 2, 4, the new batch numbers are 1, 2, 3, 4); and update the total number of batches processed (total batches = original total batches - 2 + 1 = original total batches - 1), and the total fusion value (total fusion value = original total fusion value - SM1hx + SM2hx).

[0090] S3804, generate the final processing information table, which integrates the updated batch information, processing methods, total energy consumption, total cleanliness, and other parameters into a structured table, replacing the original processing information generated in S200 as the final output. For example: Original processing information: The h-th processing information contains 3 batches (weight 5kg, 5kg, 3kg), the target candidate information contains 2 batches (weight 5kg, 2kg), after merging, delete the last two batches (3kg and 2kg), add a new merged batch of 5kg (3kg + 2kg), the final batches are 5kg, 5kg, 5kg, and the processing method is updated to the optimal method corresponding to the merge.

[0091] By following the steps above, we can ensure that the updated processing information reflects both the results of the merge and optimization, and fully retains the valid data in the original processing logic.

[0092] In this embodiment of the invention, the following technical effects can be achieved through S300:

[0093] Improving processing efficiency and reducing energy waste: The aforementioned content only generates processing information for a single item sub-cluster. There may be cases where the last batch of processing information has a smaller processing weight, leading to frequent equipment startups or low resource utilization. By merging the last batch of items to be processed, the S300 can reduce the number of processing batches and lower the startup energy consumption between batches (e.g., ΔE0). At the same time, by comparing fusion values ​​and selecting a better merging method, it can further reduce total energy consumption and improve energy utilization efficiency.

[0094] Optimizing the flexibility and economy of the processing scheme: Without affecting the processing effect, by finding candidate information that can be merged, the processing batches can be dynamically adjusted, avoiding the inefficient processing mode of "small batches, multiple batches". Especially when multiple processing information have similar attributes, merging processing can reduce equipment idle time, increase the processing volume per unit time, and enhance the economy of the scheme.

[0095] Enhancing the rationality and accuracy of information processing: During the merging process, the comparison of fusion values ​​(SM1hx and SM2hx) ensures that the merged processing method has better overall performance in terms of energy consumption and cleanliness, rather than blindly merging. At the same time, the selection criteria for candidate information (same processing method, similar attributes, etc.) are clearly defined to ensure the feasibility of merging processing and make the final processed information more in line with actual needs.

[0096] The energy allocation method for item processing provided in this invention transforms the energy allocation problem into data-driven optimization decision-making by constructing a mapping system of "item characteristics - processing method - energy consumption model," achieving a leap from extensive experience-based control to precise algorithmic control. Its core innovation lies in the deep coupling of visual perception technology with the energy consumption model, providing a systematic energy-saving solution for high-energy-consuming item processing systems (such as laundry and food processing).

[0097] Based on the same inventive concept, embodiments of the present invention also provide an energy distribution system for article handling, the system comprising:

[0098] The storage module stores an item processing record data information table RF; RF = {RF1, RF2, ..., RF...} u , ..., RF q}, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of the items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u）}, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv ={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v）}, U uvRF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r YC is the energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method. uv r Let be the cleanliness weight correlation expression for the v-th item sub-cluster under the r-th processing method.

[0099] The data acquisition module is used to acquire the digitized visual feature data and the numerical data of the processing weight of the current item to be processed through the data acquisition interface, so as to generate a structured data record table and store it in the storage module; wherein, each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the item to be processed in the corresponding item sub-cluster.

[0100] The processing information generation module is used to call the item processing record data information table and data record table in the storage module, generate processing information for the current item to be processed, and output the processing information, which includes processing method and processing batch information.

[0101] This system can be used to perform Figure 1 The method shown in the illustrated embodiment can be used as a reference for understanding the functions that each functional module of the system can achieve. Figure 1 The embodiments shown are described in detail below.

[0102] This invention also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being configured to perform the method described in this invention.

[0103] This invention also provides a computer-readable storage medium storing computer-executable instructions for performing the methods described in this invention.

[0104] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this invention can be achieved, and this is not limited herein.

[0105] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An energy distribution method for handling items, characterized in that, The method is implemented based on a data processing system, which includes a storage module. The storage module stores an item processing record data information table RF, where RF = {RF1, RF2, ..., RF...} u , ..., RF q }, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of the items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u） }, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv ={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v） }, U uv RF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r YC is the energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method. uv r Let the cleanliness weight correlation expression be given for the v-th item subcluster under the r-th processing method; the method includes the following steps: S100, the data processing system acquires the digital data of the visual features of the current item to be processed and the numerical data of the processing weight through the data acquisition interface, so as to generate a structured data record table and store it in the storage module; each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the item to be processed in the corresponding item sub-cluster. S200, the data processing system calls the item processing record data information table and data record table in the storage module to generate processing information for the current item to be processed, and outputs the processing information, which includes processing method and processing batch information.

2. The method according to claim 1, characterized in that, WT uv r Obtain it through the following methods: S1, obtain the historical dataset of the v-th item sub-cluster under the r-th processing method. Each historical data in the historical dataset includes the processing weight, energy consumption parameter value and cleanliness parameter value. S2, delete historical data in the historical dataset whose cleanliness parameter value is less than the set cleanliness parameter value threshold, and obtain the historical dataset that has been deleted, which is used as the target dataset; S3. For each data point in the target dataset, obtain the fusion value corresponding to that data point. The fusion value satisfies the following condition: SM = We × E + Wc × (Cmax - C), where SM is the fusion value corresponding to that data point, E is the energy consumption parameter value corresponding to that data point, C is the cleanliness parameter value corresponding to that data point, We is the energy consumption weight, Wc is the cleanliness weight, We + Wc = 1, and Cmax is the maximum cleanliness parameter value. S4. Using the processed weight in the target dataset as the independent variable and the fusion value in the target dataset as the dependent variable, obtain the data fitting curve; S5, obtain the processing weight corresponding to the slope abrupt change point of the data fitting curve as WT. uv r .

3. The method according to claim 2, characterized in that, The energy consumption parameter value E corresponding to the d-th historical data point d The following conditions must be met: E d =(Ea d -Eb d ) / Eb d ×100, Ea d Eb represents the actual energy consumption value corresponding to the processing weight in the d-th historical data. d Let d be the baseline energy consumption value corresponding to the processing weight in the d-th historical data, where d ranges from 1 to Q, and Q is the number of historical data.

4. The method according to claim 3, characterized in that, S200 specifically includes: S210, obtain the processing weight threshold set NS(i) = {N1(i), N2(i), ..., N} corresponding to the item sub-cluster in the data record table. j (i), ..., N m (i)}, where N j (i) represents the maximum processing weight threshold of the item subcluster corresponding to the i-th row of data under the j-th processing method, where j ranges from 1 to m, m is the number of processing methods for the item subcluster corresponding to the i-th row of data, i ranges from 1 to HM, and HM is the number of rows of data in the data record table. S220, iterate through NS(i), for each N reached... j (i) If N j (i)≥N i , will N j (i) The unique identifier of the corresponding processing method is added to the processing method record set; N i The processing weight is the data in the i-th row of the data record table. The initial value of the processing method record set is empty. S230, if the number of unique identifiers in the processing method record set Q=1, use the unique identifiers in the processing method record set as the target identifiers corresponding to the i-th row of data, and generate the processing information for the item to be processed corresponding to the i-th row of data as: single batch processing, processing method is the processing method corresponding to the target identifier; if Q>1, obtain the fusion value corresponding to each unique identifier in the processing method record, use the unique identifier corresponding to the minimum fusion value as the target identifiers corresponding to the i-th row of data, and generate the processing information for the item to be processed corresponding to the i-th row of data as: single batch processing, processing method is the processing method corresponding to the target identifier; if Q=0, execute S240; S240, obtain the processing batches C(i,j) required for the item to be processed corresponding to the i-th row of data under the j-th processing method, C(i,j) = roundup(N). i / N j (i)), roundup() means rounding up; where the processing weight of each processing batch in the first C(i,j)-1 processing batches is N. j (i), the processing weight corresponding to the C(i,j)th processing batch is N. i -(C(i,j)-1)×N j (i); S250, obtain the total energy consumption ET of the item to be processed corresponding to the i-th row of data under the j-th processing method. ij ; ET ij =∑ C（i，j） v=1 E ij (v) + (C(i,j)-1)×△E0, where E ij (v) is the energy consumption parameter value corresponding to the vth batch, which is determined based on the energy consumption weight correlation expression corresponding to the jth processing method. The value of v ranges from 1 to C(i,j), and △E0 is the startup energy consumption between batches. S260, obtain min(ET) i1 ,ET i2 , ..., ET ij , ..., ET im The processing method corresponding to the i-th row of data is used as the target processing method, and the processing information for the items to be processed corresponding to the i-th row of data is generated as follows: batch processing, with the processing weight of the v-th batch under the j-th processing method being N. ij (v), the processing method is the target processing method.

5. The method according to claim 4, characterized in that, It also includes the following steps: S300, set counter h=1; S310, if h≤HM, execute S320; otherwise, execute S380. S320, for the h-th processing information in the processing information set corresponding to the data record table, if the processing weight of the last batch in the processing information is less than the corresponding maximum processing weight threshold, execute S330; S330, if the intermediate processing information set includes the h-th processing information, delete the h-th processing information from the intermediate processing information set, and obtain processing information with the same processing method, similar visual perception attributes and item type as the h-th processing information from the intermediate processing information set after deleting the h-th processing information as candidate information for the h-th processing information. If the intermediate processing information set does not include the h-th processing information, obtain processing information with the same processing method, similar visual perception attributes and item type as the h-th processing information, and whose last batch processing weight is less than the corresponding maximum processing weight threshold from the intermediate processing information set as candidate information for the h-th processing information. The initial value of the intermediate processing information set is the processing information set corresponding to the data record table. S340, obtain the sum NT of the processing weight of the h-th processing information and the processing weight of the x-th candidate information of the h-th processing information. hx If the common processing method corresponding to the h-th processing information and the x-th candidate information has a maximum processing weight threshold greater than or equal to NT, hx If the processing method is correct, then use this processing method as the target candidate processing method corresponding to the h-th processing information and the x-th candidate information, and execute S360; otherwise, execute S350. S350, set x = x + 1. If x ≤ g(h), execute S340; otherwise, execute S370. The initial value of x is 1, and g(h) is the number of candidate information for the h-th information to be processed. S360, obtain the sum of the fusion value corresponding to the h-th processed information and the fusion value corresponding to the x-th processed information SM1 hx And based on the energy consumption weight correlation expression and cleanliness weight correlation expression corresponding to the target candidate processing method corresponding to the h-th processing information and the x-th candidate information, obtain NT. hx The corresponding fusion value SM2 hx If SM2 hx <SM1 hx SM2 hx Add it to the candidate fusion value record set as a candidate fusion value, and execute S350; Otherwise, execute S350 directly; The initial value for adding candidate fusion values ​​to the candidate fusion value record set is empty; S370, take the candidate information corresponding to the minimum candidate fusion value in the candidate fusion value record set as the target candidate information of the h-th processing information, generate the merged processing information corresponding to the h-th processing information, delete the h-th processing information and the corresponding target candidate information from the intermediate processing information set, set h=h+1, and execute S310; the merged processing information corresponding to the h-th processing information includes merging the items to be processed in the last batch of the h-th processing information and the items to be processed in the last batch of the target candidate information together, and process them according to the processing method corresponding to the minimum candidate fusion value; S380: Update the processing information obtained in S200 based on all the merged processing information to obtain the updated processing information, which serves as the final processing information for the data record table.

6. The method according to claim 1, characterized in that, The visual perception attribute is color, and the item type includes size specifications, material, and dirt level parameters.

7. An electronic device, characterized in that, Including processor and memory; The processor executes the steps of the method as described in any one of claims 1 to 6 by invoking programs or instructions stored in the memory.

8. An energy distribution system for handling items, characterized in that, The system includes: The storage module stores an item processing record data information table RF; RF = {RF1, RF2, ..., RF...} u , ..., RF q }, RF u This is the record information for the u-th item cluster, where u ranges from 1 to q, and q is the number of item clusters. Item clusters are obtained based on the visual perception attributes of the items; RF u ={RF u1 , ..., RF uv , ..., RF uf（u） }, RF uv For RF u The record information of the v-th item subcluster in the RF, where v takes values ​​from 1 to f(u), and f(u) is the RF. u The number of item subclusters in RF; uv ={U uv RF uv 1 , ..., RF uv r , ..., RF uzv z（u，v） }, U uv RF is the unique identifier for the v-th item subcluster. uv r This represents the record information for the v-th item subcluster under the r-th processing method, where r ranges from 1 to z(u,v), and z(u,v) is the number of processing methods for the v-th item subcluster; RF uv r =(UT uv r WT uv r YE uv r YC uv r ), U uv r WT is a unique identifier for the r-th processing method. uv r YE represents the maximum processing weight threshold for a single batch of processing of the v-th item subcluster under the r-th processing method. uv r YC is the energy consumption-weight correlation expression for the v-th item subcluster under the r-th processing method. uv r Let V be the cleanliness weight correlation expression for the v-th item sub-cluster under the r-th processing method; The data acquisition module is used to acquire the digital data of the visual features of the items to be processed and the numerical data of the processing weight through the data acquisition interface, so as to generate a structured data record table and store it in the storage module; wherein, each row of data in the data record table corresponds to an item sub-cluster, and each row of data includes: the unique identifier of the corresponding item sub-cluster and the processing weight of the items to be processed in the corresponding item sub-cluster. The processing information generation module is used to call the item processing record data information table and data record table in the storage module, generate processing information for the current item to be processed, and output the processing information, which includes processing method and processing batch information.

Images