A method for dynamic correction of consumable balance and an intelligent monitoring system for consumables
By using a dynamic correction method for consumable inventory balance, combined with basic parameters and big data analysis, a dynamic correction calculation model is constructed. This solves the problems of adaptability and accuracy of consumable inventory balance monitoring on small equipment, and realizes efficient use of consumables and environmental protection.
Patent Information
- Application Number
- CN202611599346.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-10-15
- Publication Date
- 2026-11-17
AI Technical Summary
Existing methods for monitoring consumable inventory levels are difficult to deploy on small and lightweight distributed devices, have low accuracy, and cannot adapt to different usage scenarios and environments, leading to consumable waste or equipment failure, increased costs, and environmental pollution.
A dynamic correction method for consumable inventory balance is adopted. By combining basic consumable parameters, operational data and visual confirmation, full life cycle data is generated. The server is used for big data analysis and environmental compensation to build a dynamic correction calculation model and optimize consumable consumption calculation.
It enables precise monitoring of consumable inventory levels, reduces user costs, minimizes consumable waste pollution, and improves model adaptability and accuracy.
Smart Images

Figure CN123115097A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent monitoring systems for consumables, and more particularly to a method for dynamic correction of consumable balance and an intelligent monitoring system for consumables. Background Technology
[0002] Smart devices and medical equipment commonly use consumable supplies, and monitoring and reminding users of remaining supplies are crucial for ensuring stable operation. Existing methods for monitoring and reminding users of remaining supplies mainly fall into two categories: hardware-based detection and fixed-parameter prediction.
[0003] Hardware-based detection relies on specialized hardware such as sensors and metering devices, which presents challenges such as deployment difficulties, high modification costs, and poor adaptability, making it difficult to integrate with small and lightweight distributed devices. Fixed-parameter prediction methods estimate based solely on factory-set counts or durations, ignoring differences in usage scenarios, habits, and operating conditions. This results in low accuracy and two main problems: first, replacement reminders are triggered before consumables are exhausted, wasting materials and increasing costs; second, consumables are exhausted without timely warnings, leading to equipment failure, work interruptions, and exacerbating industrial waste emissions and environmental pollution. Furthermore, distributed device deployment environments vary greatly, and existing solutions do not differentiate between usage scenarios or collect temperature and humidity data for calculation, further amplifying margin estimation errors.
[0004] For inventory monitoring of smart and medical devices, big data prediction typically relies on high-precision sensors to collect actual inventory levels as training samples. However, many low-cost, small devices cannot deploy sensors, making model training difficult. Furthermore, existing fitting methods often involve batch recalculation of the entire dataset, requiring refitting for each new sample, resulting in high server computational costs. If new samples include noisy, dirty data from industrial environments, direct recalculation can lead to model degradation and prevent the evaluation and selection of new models, potentially resulting in the deployment of even worse models to the terminal. Therefore, this invention proposes a dynamic inventory level correction solution for consumables to address these technical problems. Summary of the Invention
[0005] The solution described in this invention can achieve accurate monitoring of consumable inventory levels at low cost and with high reliability, and is adaptable to different usage scenarios of distributed devices in ordinary office and special industrial environments, reducing users' consumable replacement costs and reducing the pollution of the environment by consumable waste.
[0006] In a first aspect, this application proposes a dynamic correction method for consumable balance, the method comprising: S1, outputting the single-use consumption amount and cumulative consumption amount of consumables based on basic consumable parameters; S2, outputting the over-limit protection result and the remaining amount of consumables based on the single-use consumption amount and cumulative consumption amount; S3, generating consumable lifecycle data based on the over-limit protection result and the remaining amount of consumables, combined with the actual remaining amount Le of consumables confirmed visually; S4, based on the consumable lifecycle data, the server control system receives full-volume data of the same type of consumables reported by multiple electronic devices, and then outputs the optimal correction coefficient; S5, outputting a dynamic correction calculation model based on the optimal correction coefficient; and S6, outputting an updated consumable balance estimation result based on the dynamic correction calculation model.
[0007] The further technical solution is as follows: S1 includes: S11, the consumable management system pre-stores basic consumable parameters in the memory, including consumable category S, pre-set consumable usage cycle T, rated total quantity L, and consumable activation time T1, wherein the consumable activation time T1 is the time of this installation and update of the consumable, and outputs the basic consumable parameters; S12, based on the basic consumable parameters, during equipment operation, the consumable management system statistically analyzes the consumable operation data in real time, including the cumulative number of times the consumable is enabled Esum and the cumulative time the consumable is enabled Tsum; S13, based on the basic consumable parameters and the consumable operation data, the single consumable consumption and cumulative consumption are calculated based on the initial fixed parameters, and the single consumable consumption and cumulative consumption are output.
[0008] The further technical solution is as follows: S2 includes: S21, based on the single consumption amount and cumulative consumption amount, combined with big data analysis modeling, the formula for calculating the single consumption amount is: Lc = Category S preset quantity per millisecond × current consumption time of consumables, and outputs the single consumption amount Lc; S22, based on the single consumption amount Lc, the consumable management system iteratively updates the cumulative consumption amount, the update formula is: Lsum = Lsum + Lc, and outputs the cumulative consumption amount Lsum; S23, based on the cumulative consumption amount Lsum and the rated total quantity L of consumables, the system judges the relationship between the cumulative consumption amount Lsum and the rated total quantity L of consumables in real time. If Lsum ≥ L, the system immediately stops the consumables from being enabled and prompts the user to uninstall, check and replace the consumables through the display screen; at the same time, the screen displays the remaining amount of consumables calculated by the system in real time, and outputs the over-limit protection result and the remaining amount of consumables.
[0009] The further technical solution is as follows: S3 includes: S31, in response to the over-limit protection result and the remaining amount of consumables, the device screen displays the remaining amount of consumables and prompts the user to check the consumables; S32, in response to the user's instruction to check the consumables, the system obtains the actual remaining amount Le of the consumables based on visual confirmation, and manually selects the corresponding gear on the device screen to complete the input, and outputs the actual remaining amount Le; S33, based on the actual remaining amount Le, if the actual remaining amount Le entered by the user is the exhausted gear, the system automatically corrects Le to a preset negative value and outputs the corrected actual remaining amount Le; S34, based on the corrected actual remaining amount Le, the basic parameters of the consumables, and the consumables operating data, the consumables management system reports this consumable full life cycle data to the server control system through the network module.
[0010] The further technical solution is as follows: S4 includes: S41, based on the consumable lifecycle data, the server control system receives full data of the same type of consumables reported by multiple electronic devices, stores it uniformly in the background database to form a big data sample set, and outputs the big data sample set; S42, based on the big data sample set, the server control system performs dirty sample filtering: comparing the remaining quantity calculated by the model with the reported actual remaining quantity, if the deviation exceeds a threshold, it is marked as a low-confidence sample, the fitting weight of the sample is reduced, and the filtered sample set is output; S43, based on the filtered sample set, the server control... The system uses a mathematical approximation algorithm to perform fitting calculations and construct a consumable consumption deviation model. The basic model formula is: Esum×a+Tsum×b=L-Le. Through global iterative approximation, the optimal consumable usage frequency deviation correction coefficient 'a' and consumable usage time deviation correction coefficient 'b' are obtained, and the correction coefficients 'a' and 'b' are output. In step S44, the corresponding geographical coordinates G are obtained based on the IP address of the sample reporting device. Based on the geographical coordinates G and weather data, the corresponding temperature Ht and humidity Hh are obtained. In step S45, based on the filtered sample set, geographical coordinates G, and temperature Ht... With humidity Hh, environmental compensation is introduced, and the fitting formula is: Esum×a+Tsum×b+Ht×c+Hh×d=L-Le; where c is the temperature compensation correction coefficient and d is the humidity compensation correction coefficient; based on the geographic coordinates G, the samples are clustered into geographic regions, and samples from the same geographic region are given higher fitting weights. The optimal coefficients a, b, c, and d are obtained by iterative solution, and the correction coefficients a, b, c, and d are output; S46, based on the filtered sample set, a supervised learning feature vector is constructed, and all samples are divided into training set and validation set, and the training set and validation set are output; S4 7. Based on the training set, when the number of newly reported samples reaches a preset threshold, perform incremental machine learning training and output the correction coefficients of candidate a, b, c, and d; S48. Based on the validation set and the correction coefficients of candidate a, b, c, and d, calculate the error of the candidate coefficients on the validation set, compare the estimated error of the candidate model with that of the currently running online model, and output the error comparison result; S49. Based on the error comparison result, if the candidate model error is better, then the candidate model coefficients are enabled; if the candidate model performance deteriorates, then the training result is discarded and the original model coefficients are kept unchanged; output the optimal correction coefficients.
[0011] The further technical solution is that S5 includes: S51, according to the optimal correction coefficient, the server control system sends the optimal correction coefficient to the consumable management system of all electronic devices of the corresponding category of consumables; S52, according to the optimal correction coefficient, the consumable management system replaces the initial fixed calculation model and enables the dynamic correction calculation model, the dynamic correction calculation model includes the basic dynamic model and / or the environmental compensation dynamic model, and outputs the dynamic correction calculation model.
[0012] The further technical solution is as follows: S6 includes: S61, based on the dynamic correction calculation model, during the subsequent operation of the equipment, the single consumption of consumables is calculated in real time based on the dynamic correction calculation model, the cumulative consumption Lsum, the cumulative number of times enabled Esum, and the cumulative time enabled Tsum are continuously updated, and the updated cumulative consumption Lsum, the cumulative number of times enabled Esum, and the cumulative time enabled Tsum are output; S62, based on the updated cumulative consumption Lsum and the rated total quantity of consumables L, the remaining quantity of consumables is calculated, and the updated estimated quantity of consumables is generated.
[0013] The further technical solution is that, after S6, the method further includes: S71, based on the updated cumulative consumption Lsum and the rated total quantity L of consumables, when Lsum≥L, performing a consumable discontinuation and replacement reminder operation, generating consumable replacement reminder information, and outputting the consumable replacement reminder information; S72, based on the updated cumulative consumption Lsum, cumulative enable times Esum, and cumulative enable time Tsum, the device continuously collects new consumable lifecycle data and reports it to the server. The server refits and optimizes the corresponding correction coefficients based on the newly added sample data, sends out the updated terminal model again, and returns to S51 to continue execution.
[0014] Secondly, this application proposes a consumable intelligent monitoring system, including a consumable management system and multiple electronic devices that are interconnected. The intelligent monitoring system is used to implement the dynamic correction method for consumable balance as described in the first aspect. Its technical advantages include the ability to dynamically iteratively optimize the consumption calculation model using big data on consumables of the same type from multiple devices, and to improve the accuracy and stability of balance estimation and model stability under different usage scenarios for distributed devices by combining geographical coordinates, temperature, humidity environmental compensation, and supervised incremental machine learning. This reduces the cost of consumable replacement for users and minimizes environmental pollution from consumable waste.
[0015] In summary, this invention addresses the problems of existing technologies by proposing a dynamic correction method for consumable inventory levels and an intelligent consumable monitoring system. This system can achieve accurate monitoring of consumable inventory levels at low cost and with high reliability, and is adaptable to different usage scenarios of distributed devices in ordinary office and special industrial environments. It reduces users' consumable replacement costs and minimizes environmental pollution from consumable waste. Attached Figure Description
[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart of the consumable balance dynamic correction method provided by the present invention.
[0019] Figure 2 Another flowchart of the consumable balance dynamic correction method provided by the present invention.
[0020] Figure 3 A block diagram of an electronic device provided by the present invention. Detailed Implementation
[0021] 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, not all, of the embodiments of the present invention. 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.
[0022] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0023] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0024] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to one or any combination of the associated listed items and all possible combinations, and includes such combinations.
[0025] In this specification and the appended claims, there may be multiple ways of expressing the same technical feature or technical term, such as using a superordinate generalization, a subordinate limitation, or a synonym substitution. Those skilled in the art can clearly understand the substantially the same technical meaning referred to by different expressions based on their professional knowledge and in conjunction with the overall content of the specification and the drawings. The differences in different expressions are only reflected in the diversity of words and do not constitute a substantial modification or limitation to the technical solution, nor will they affect the certainty of the scope of protection of this patent claim or the full disclosure of the technical content of the specification.
[0026] Example 1 Please see Figure 1 As shown in other images, in the first aspect, this application proposes a dynamic correction method for consumable balance, the method comprising: S1, outputting the single-use consumption amount and cumulative consumption amount of consumables based on basic consumable parameters; S2, outputting the over-limit protection result and the remaining amount of consumables based on the single-use consumption amount and cumulative consumption amount; S3, generating consumable lifecycle data based on the over-limit protection result and the remaining amount of consumables, combined with the actual remaining amount Le of consumables confirmed visually; S4, based on the consumable lifecycle data, the server control system receives full-volume data of the same type of consumables reported by multiple electronic devices, and then outputs the optimal correction coefficient; S5, outputting a dynamic correction calculation model based on the optimal correction coefficient; S6, outputting the updated consumable balance estimation result based on the dynamic correction calculation model.
[0027] A further technical solution is as follows: S1 includes: S11, the consumable management system pre-stores basic consumable parameters in the memory, including consumable category S, pre-set consumable usage cycle T, rated total quantity L, and consumable activation time T1, where the consumable activation time T1 is the time of this installation / update of the consumable, and outputs the basic consumable parameters; S12, based on the basic consumable parameters, during equipment operation, the consumable management system statistically analyzes consumable operation data in real time, including the cumulative number of times the consumable is enabled Esum and the cumulative time the consumable is enabled Tsum; S13, based on the basic consumable parameters and the consumable operation data, the single consumable consumption and cumulative consumption are calculated based on initial fixed parameters, and the single consumable consumption and cumulative consumption are output. In the above solution, the real-time temperature Ht, humidity Hh, and geographical coordinates G of the operating environment of the equipment are collected simultaneously, and the consumable operation data, real-time temperature Ht, humidity Hh, and geographical coordinates G of the equipment are output. In the above scheme, the consumable management system pre-stores basic consumable parameters, including consumable category, preset usage cycle, rated total quantity, and activation time; during equipment operation, the system counts the cumulative number of times and cumulative activation time of consumables in real time; based on the basic parameters and operating data, it calculates the single consumption and cumulative consumption of consumables based on the initial fixed parameters; in addition, it also collects real-time temperature, humidity, and equipment geographic coordinates simultaneously to provide data for subsequent environmental compensation.
[0028] The further technical solution is as follows: S2 includes: S21, based on the single consumption amount and cumulative consumption amount, combined with big data analysis modeling, the formula for calculating the single consumption amount is: Lc = Category S preset quantity per millisecond × current consumption time of consumables, and outputs the single consumption amount Lc; S22, based on the single consumption amount Lc, the consumable management system iteratively updates the cumulative consumption amount, the update formula is: Lsum = Lsum + Lc, and outputs the cumulative consumption amount Lsum; S23, based on the cumulative consumption amount Lsum and the rated total quantity L of consumables, the system judges the relationship between the cumulative consumption amount Lsum and the rated total quantity L of consumables in real time. If Lsum ≥ L, the system immediately stops the consumables from being enabled and prompts the user to uninstall, check and replace the consumables through the display screen; at the same time, the screen displays the remaining amount of consumables calculated by the system in real time, and outputs the over-limit protection result and the remaining amount of consumables. In the above scheme, the single-use consumable consumption is calculated based on the single consumption and cumulative consumption, combined with big data analysis and modeling; the consumable management system iteratively updates the cumulative consumption; the cumulative consumption and the rated total quantity of consumables are judged in real time to determine their relationship; if the cumulative consumption is greater than or equal to the rated total quantity, the consumables are immediately stopped from being enabled, and the user is prompted to uninstall, check and replace the consumables through the display screen, while the remaining amount of consumables calculated by the system is displayed, and the over-limit protection result and the remaining amount of consumables are output.
[0029] The further technical solution is as follows: S3 includes: S31, in response to the over-limit protection result and the remaining amount of consumables, the device screen displays the remaining amount of consumables and prompts the user to check the consumables; S32, in response to the user's instruction to check the consumables, the system obtains the actual remaining amount Le of the consumables based on visual confirmation, and manually selects the corresponding gear on the device screen to complete the input, and outputs the actual remaining amount Le; S33, based on the actual remaining amount Le, if the actual remaining amount Le entered by the user is the exhausted gear, the system automatically corrects Le to a preset negative value and outputs the corrected actual remaining amount Le; S34, based on the corrected actual remaining amount Le, the basic parameters of the consumables, and the consumables operating data, the consumables management system reports this consumable full life cycle data to the server control system through the network module. In the above scheme, the data dimensions of the consumable's full lifecycle data include: consumable category S, consumable preset usage period T, consumable rated total quantity L, consumable activation time T1, consumable cumulative activation count Esum, consumable cumulative activation time Tsum, and corrected actual remaining quantity Le. Preferably, the reported data also includes geographic coordinates G, real-time temperature Ht, and humidity Hh, outputting the consumable's full lifecycle data. In the above scheme, in response to the over-limit protection result and the remaining consumable quantity, the device screen displays the remaining quantity and prompts the user to check the consumables; in response to the user's inspection command, the system obtains the actual remaining quantity of the consumables based on visual confirmation and manually selects the corresponding level on the screen to complete the entry; if the user enters the "used up" level, the system automatically corrects it to a preset negative value; based on the corrected actual remaining quantity, basic parameters, and operating data, the system reports this consumable's full lifecycle data to the server via the network module. The data dimensions include category, period, rated total quantity, activation time, cumulative activation count, cumulative activation time, and corrected actual remaining quantity.
[0030] In one embodiment, S4 specifically includes: S41, based on the consumable lifecycle data, the server control system receives full data of the same type of consumables reported by multiple electronic devices, stores it uniformly in the background database to form a big data sample set, and outputs the big data sample set; S42, based on the big data sample set, the server control system performs dirty sample filtering: comparing the remaining quantity calculated by the model with the reported actual remaining quantity, if the deviation exceeds a threshold, it is marked as a low-confidence sample, the fitting weight of the sample is reduced, and the filtered sample set is output; S43, based on the filtered sample set, the server control system performs fitting calculations through a mathematical approximation algorithm to construct a consumable consumption deviation model, the basic model formula being: Esum×a+Tsum×b=L-Le; through global iterative approximation solution, the optimal model is obtained. The consumable usage frequency deviation correction coefficient 'a' and consumable usage time deviation correction coefficient 'b' are output; S44, obtain the corresponding geographical coordinates G based on the IP address of the device reported by the sample; based on the geographical coordinates G and weather data, obtain the temperature Ht and humidity Hh for the corresponding time; S45, based on the filtered sample set, geographical coordinates G, temperature Ht, and humidity Hh, introduce environmental compensation, and the fitting formula is: Esum×a+Tsum×b+Ht×c+Hh×d=L-Le; where c is the temperature compensation correction coefficient and d is the humidity compensation correction coefficient; perform geographical region clustering on the samples based on the geographical coordinates G, assign higher fitting weights to samples in the same geographical region, iteratively solve for the optimal coefficients a, b, c, and d, and output the correction coefficients a, b, c, and d. In the above scheme, the server receives full data of consumables of the same type reported by multiple electronic devices, stores them uniformly in the background database to form a big data sample set; performs dirty sample filtering, compares the remaining quantity calculated by the model with the reported actual remaining quantity, and marks the sample as low confidence if the deviation exceeds the threshold and reduces the fitting weight; constructs a consumable consumption deviation model through mathematical approximation algorithm fitting calculation, and iteratively solves to obtain the consumable usage frequency deviation correction coefficient and usage time deviation correction coefficient; obtains the geographical coordinates based on the reported device IP, and obtains the temperature and humidity at the corresponding time based on weather data, introduces environmental compensation, and fits to solve the temperature compensation correction coefficient and humidity compensation correction coefficient.
[0031] The weather data can be historical weather data and / or real-time weather data. In one embodiment, the corresponding geographic coordinates G are obtained based on the IP address of the sample reporting device. Based on the geographic coordinates G and historical weather data, the historical temperature Ht1 and historical humidity Hh1 for the corresponding time are obtained. In another embodiment, the corresponding geographic coordinates G are obtained based on the IP address of the sample reporting device. Based on the geographic coordinates G and real-time weather data, the real-time temperature Ht2 and real-time humidity Hh2 for the corresponding time are obtained.
[0032] A further technical solution is that S4 further includes: S46, constructing a supervised learning feature vector based on the filtered sample set, dividing all samples into a training set and a validation set, and outputting the training set and validation set; S47, based on the training set, when the number of newly reported samples reaches a preset threshold, performing incremental machine learning training, and outputting candidate a, b, c, and d correction coefficients; S48, based on the validation set and the candidate a, b, c, and d correction coefficients, calculating the error of the candidate coefficients on the validation set, comparing the estimation error of the candidate model with that of the currently running online model, and outputting the error comparison result; S49, based on the error comparison result, if the candidate model error is better, then the candidate model coefficients are enabled; if the candidate model performance deteriorates, then the training result is discarded, and the original model coefficients remain unchanged; and the optimal correction coefficients are output. Optionally, a supervised learning feature vector is constructed based on the filtered sample set, the feature vector containing {Esum, Tsum, Ht, Hh, geographic clustering label}, and the supervised learning label is L-Le; all samples are divided into a training set and a validation set, and the training set and validation set are output. In the above scheme, a supervised learning feature vector is constructed based on the filtered sample set, which includes the cumulative number of enable times, cumulative enable time, temperature, humidity, and geographical clustering labels. The supervised learning label is the rated total quantity minus the actual remaining quantity. All samples are divided into training set and validation set. When the number of newly reported samples reaches a preset threshold, incremental machine learning training is performed, and candidate correction coefficients are output. The candidate coefficient error is calculated based on the validation set, and the estimation error of the candidate model is compared with that of the currently running online model. If the candidate model error is better, the candidate model coefficient is used; if the effect is worse, it is discarded, the original model coefficient is maintained, and the optimal correction coefficient is output.
[0033] A further technical solution is as follows: S5 includes: S51, based on the optimal correction coefficient, the server control system sends the optimal correction coefficient to the consumable management system of all electronic devices corresponding to the consumable category; S52, based on the optimal correction coefficient, the consumable management system replaces the initial fixed calculation model and enables a dynamic correction calculation model. The dynamic correction calculation model includes a basic dynamic model and / or an environmental compensation dynamic model, and outputs the dynamic correction calculation model. In the above solution, based on the optimal correction coefficient, the server control system sends the optimal correction coefficient to the consumable management system of all electronic devices corresponding to the consumable category; after receiving it, the consumable management system replaces the initial fixed calculation model and enables the dynamic correction calculation model; the dynamic correction calculation model includes a basic dynamic model and / or an environmental compensation dynamic model; the basic dynamic model uses a usage frequency deviation correction coefficient and a usage time deviation correction coefficient, and the environmental compensation dynamic model introduces a temperature compensation correction coefficient and a humidity compensation correction coefficient on this basis, and outputs the dynamic correction calculation model.
[0034] A further technical solution is as follows: S6 includes: S61, based on the dynamic correction calculation model, during subsequent equipment operation, the single-use consumable consumption is calculated in real time based on the dynamic correction calculation model, and the cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum are continuously updated, and the updated cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum are output; S62, based on the updated cumulative consumption Lsum and the rated total quantity L of consumables, the remaining quantity of consumables is calculated, and an updated consumable remaining quantity estimation result is generated. In the above solution, based on the dynamic correction calculation model, during subsequent equipment operation, the single-use consumable consumption is calculated in real time based on the dynamic correction calculation model, and the cumulative consumption, cumulative enable count, and cumulative enable time are continuously updated; based on the updated cumulative consumption and the rated total quantity of consumables, the remaining quantity of consumables is calculated, and an updated consumable remaining quantity estimation result is generated; this step switches the consumable remaining quantity estimation from a fixed parameter model to a dynamic correction model, which can continuously correct according to the actual use of the equipment and changes in the environment, improving the accuracy of the remaining quantity estimation.
[0035] A further technical solution is as follows: after S6, the method further includes: S71, based on the updated cumulative consumption Lsum and the rated total quantity L of consumables, when Lsum≥L, performing a consumable discontinuation and replacement reminder operation, generating a consumable replacement reminder message, and outputting the consumable replacement reminder message; S72, based on the updated cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum, the device continuously collects new consumable lifecycle data and reports it to the server. The server refits and optimizes the corresponding correction coefficients based on the newly added sample data, reissues the updated terminal model, and returns to S51 to continue execution. In the above solution, based on the updated cumulative consumption and the rated total quantity of consumables, when the cumulative consumption is greater than or equal to the rated total quantity, performing a consumable discontinuation and replacement reminder operation, generating a consumable replacement reminder message; based on the updated cumulative consumption, cumulative enable count, and cumulative enable time, the device continuously collects new consumable lifecycle data and reports it to the server; the server refits and optimizes the corresponding correction coefficients based on the newly added sample data, reissues the updated terminal model, and returns to the reissue step to continue execution, forming a closed loop of continuous optimization.
[0036] Secondly, this application proposes a consumable intelligent monitoring system, including a consumable management system and multiple electronic devices that are interconnected. The intelligent monitoring system is used to implement the dynamic correction method for consumable balance as described in the first aspect. Its technical advantages include the ability to dynamically iteratively optimize the consumption calculation model using big data on consumables of the same type from multiple devices, and to improve the accuracy and stability of balance estimation and model stability under different usage scenarios for distributed devices by combining geographical coordinates, temperature, humidity environmental compensation, and supervised incremental machine learning. This reduces the cost of consumable replacement for users and minimizes environmental pollution from consumable waste.
[0037] In summary, this invention addresses the problems of existing technologies by proposing a dynamic correction method for consumable inventory levels and an intelligent consumable monitoring system. This system can achieve accurate monitoring of consumable inventory levels at low cost and with high reliability, and is adaptable to different usage scenarios of distributed devices in ordinary office and special industrial environments. It reduces users' consumable replacement costs and minimizes environmental pollution from consumable waste.
[0038] Example 2 Please see Figure 3 , Figure 3 This is a block diagram of an electronic device provided by the present invention. The electronic device can be a terminal or a server; wherein the terminal can be an electronic device with communication functions such as a smartphone, tablet computer, laptop computer, desktop computer, personal digital assistant, and wearable device. The electronic device can remotely connect to a consumables intelligent monitoring system, specifically including a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, communication interface 112, and memory 113 communicate with each other through the communication bus 114.
[0039] Furthermore, the memory 113 is used to store computer programs. In one embodiment of the present invention, when the processor 111 executes the program stored in the memory 113, it implements the consumable balance dynamic correction method provided in any of the foregoing method embodiments.
[0040] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.
[0041] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions, but such implementations should not be considered beyond the scope of this invention.
[0042] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is only a logical functional division, and there may be other division methods in actual implementation. For example, units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0043] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0044] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.
[0045] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0046] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.
[0047] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A method for dynamic correction of consumable balance, characterized in that, The method includes: S1, based on the basic parameters of consumables, outputs the consumption amount of consumables in a single transaction and the cumulative consumption amount; S2, based on the single consumption and cumulative consumption of consumables, outputs the over-limit protection result and the remaining amount of consumables; S3 generates full lifecycle data for consumables based on the over-limit protection results and the remaining amount of consumables, combined with the actual remaining amount Le of consumables confirmed visually. S4, based on the full life cycle data of consumables, the server control system receives full data of the same type of consumables reported by multiple electronic devices, and then outputs the optimal correction coefficient. S5, based on the optimal correction coefficients, outputs the dynamic correction calculation model; S6, based on the dynamic correction calculation model, outputs the updated consumable balance estimation results.
2. The method for dynamic correction of consumable balance according to claim 1, characterized in that, S1 includes: S11, the consumable management system stores basic consumable parameters in the memory in advance. The basic consumable parameters include consumable category S, consumable preset usage cycle T, consumable rated total quantity L, and consumable activation time T1. The consumable activation time T1 is the time of this consumable installation and update. The basic consumable parameters are output. S12, Based on the basic parameters of the consumables, during the operation of the equipment, the consumables management system collects the consumables operation data in real time. The consumables operation data includes the cumulative number of times the consumables are enabled (Esum) and the cumulative time the consumables are enabled (Tsum). S13, based on the basic parameters of consumables and the operation data of consumables, calculate the single consumption and cumulative consumption of consumables based on the initial fixed parameters, and output the single consumption and cumulative consumption of consumables.
3. The method for dynamic correction of consumable balance according to claim 2, characterized in that, S2 includes: S21. Based on the single consumption amount and cumulative consumption amount, combined with big data analysis and modeling, the formula for calculating the single consumption amount of consumables is: Lc = Category S preset quantity per millisecond × current consumable usage time, and output the single consumption amount Lc. S22, based on the single consumption amount Lc, the consumable management system iteratively updates the cumulative consumption amount. The update formula is: Lsum=Lsum+Lc, and the cumulative consumption amount Lsum is output. S23, based on the cumulative consumption Lsum and the rated total quantity L of consumables, determine the relationship between the cumulative consumption Lsum and the rated total quantity L of consumables in real time. If Lsum≥L, immediately stop the consumables from being enabled and prompt the user to uninstall, check and replace the consumables through the display screen. At the same time, the screen displays the remaining quantity of consumables calculated by the system in real time and outputs the over-limit protection result and the remaining quantity of consumables.
4. The method for dynamic correction of consumable balance according to claim 3, characterized in that, S3 includes: S31, in response to the over-limit protection result and the remaining amount of consumables, the device screen displays the remaining amount of consumables and prompts the user to check the consumables; S32 responds to the user's instruction to check consumables, obtains the actual remaining amount Le of consumables based on visual confirmation, manually selects the corresponding level on the device screen to complete the entry, and outputs the actual remaining amount Le; S33, based on the actual remaining amount Le, if the actual remaining amount Le entered by the user is the exhausted position, the system will automatically correct Le to a preset negative value and output the corrected actual remaining amount Le; S34, based on the corrected actual remaining quantity Le, basic consumable parameters, and consumable operation data, the consumable management system reports this consumable lifecycle data to the server control system through the network module.
5. The method for dynamic correction of consumable balance according to claim 4, characterized in that, S4 includes: S41, based on the full life cycle data of consumables, the server control system receives full data of the same type of consumables reported by multiple electronic devices, stores them uniformly in the background database, forms a big data sample set, and outputs the big data sample set. S42, Based on the big data sample set, the server controls the system to perform dirty sample filtering: compare the remaining quantity calculated by the model with the reported actual remaining quantity. If the deviation exceeds the threshold, it is marked as a low-confidence sample, the fitting weight of the sample is reduced, and the filtered sample set is output. S43, Based on the filtered sample set, the server control system performs fitting calculations using a mathematical approximation algorithm to construct a consumable consumption deviation model. The basic model formula is: Esum×a+Tsum×b=L-Le; Through global iterative approximation solution, the optimal consumable usage frequency deviation correction coefficient a and consumable usage time deviation correction coefficient b are obtained, and the correction coefficients a and b are output. S44. Obtain the corresponding geographical coordinates G based on the IP address of the sample reporting device. Based on the geographical coordinates G and combined with weather data, obtain the temperature Ht and humidity Hh for the corresponding time. S45. Based on the filtered sample set, geographic coordinates G, temperature Ht, and humidity Hh, environmental compensation is introduced, and the fitting formula is: Esum×a+Tsum×b+Ht×c+Hh×d=L-Le; where c is the temperature compensation correction coefficient and d is the humidity compensation correction coefficient; the samples are clustered into geographic regions based on geographic coordinates G, and samples in the same geographic region are given higher fitting weights. The optimal coefficients a, b, c, and d are obtained by iterative solution, and the correction coefficients a, b, c, and d are output. S46. Based on the filtered sample set, construct supervised learning feature vectors, divide all samples into training set and validation set, and output training set and validation set; S47. Based on the training set, when the number of newly reported samples reaches a preset threshold, perform incremental machine learning training and output the correction coefficients of candidates a, b, c, and d. S48. Based on the validation set and the correction coefficients of candidates a, b, c, and d, calculate the error of the candidate coefficients on the validation set, compare the estimation error of the candidate model with that of the currently running online model, and output the error comparison result. S49. Based on the error comparison results, if the candidate model has a better error, then the candidate model coefficients are enabled; if the candidate model's performance deteriorates, then the training results are discarded and the original model coefficients are kept unchanged; the optimal correction coefficients are output.
6. The method for dynamic correction of consumable balance according to claim 5, characterized in that, S5 includes: S51, Based on the optimal correction coefficient, the server control system sends the optimal correction coefficient to the consumable management system of all electronic devices of the corresponding category of consumables; S52, Based on the optimal correction coefficient, the consumable management system replaces the initial fixed calculation model and enables the dynamic correction calculation model. The dynamic correction calculation model includes the basic dynamic model and / or the environmental compensation dynamic model, and outputs the dynamic correction calculation model.
7. The method for dynamic correction of consumable balance according to claim 6, characterized in that, S6 includes: S61, based on the dynamic correction calculation model, during the subsequent operation of the equipment, the single consumable consumption is calculated in real time based on the dynamic correction calculation model, and the cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum are continuously updated, and the updated cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum are output. S62, calculate the remaining amount of consumables based on the updated cumulative consumption Lsum and the rated total quantity of consumables L, and generate the updated consumables remaining quantity estimate.
8. The method for dynamic correction of consumable balance according to claim 7, characterized in that, Following S6, the method further includes: S71, based on the updated cumulative consumption Lsum and the rated total quantity L of consumables, when Lsum≥L, execute the consumable discontinuation and replacement reminder operation, generate consumable replacement reminder information, and output the consumable replacement reminder information; S72, based on the updated cumulative consumption Lsum, cumulative enable count Esum, and cumulative enable time Tsum, the device continuously collects new consumable lifecycle data and reports it to the server. The server refits and optimizes the corresponding correction coefficients based on the newly added sample data, sends out the updated terminal model again, and returns to S51 to continue execution.
9. A consumables intelligent monitoring system, characterized in that, The system includes a consumables management system and multiple electronic devices that are interconnected. The intelligent consumables monitoring system is used to implement the dynamic correction method for consumables balance as described in any one of claims 1 to 8.
