Method and device for calculating water quantity for decocting medicine based on artificial intelligence adaptive learning model

Abstract

The application discloses a decoction medicine water adding amount calculation method and device based on an artificial intelligence adaptive learning model, relates to the technical field of traditional Chinese medicine decoction, and comprises the following steps: receiving a water adding amount calculation request of a target prescription, wherein the water adding amount calculation request is used for requesting to calculate the water adding amount for decocting medicines of the target prescription; analyzing the target prescription to obtain first medicine detailed information of the target prescription, wherein the first medicine detailed information comprises medicine names of a plurality of medicines contained in the target prescription, dosages of the plurality of medicines, and a required liquid medicine amount of the target prescription; and inputting the first medicine detailed information into a water adding amount calculation model to perform water adding amount calculation, so as to obtain the water adding amount, wherein the water adding amount calculation model is an artificial intelligence adaptive learning model.

Description

Technical Field

[0001] This application relates to the field of traditional Chinese medicine decoction technology, and more specifically, to a method and apparatus for calculating the amount of water added during decoction based on an artificial intelligence adaptive learning model. Background Technology

[0002] The accuracy of water addition in traditional Chinese medicine decoction directly affects the concentration of the liquid, the dissolution rate of active ingredients, and clinical efficacy. Calculating the water addition for the first decoction is a core step in the process. Traditionally, the calculation of water addition for the first decoction relies heavily on the water absorption rate of the medicinal herbs, estimating the amount of water needed based on a pre-set absorption rate and the prescription dosage. However, the water absorption rate of medicinal herbs is significantly unstable due to factors such as origin, ambient temperature and humidity, and storage time. This leads to large deviations in the water addition calculated using traditional methods. The actual amount of liquid obtained after decoction often does not match the theoretically required amount in the prescription. Too much water results in an excessively low concentration and dilution of active ingredients, while too little water leads to insufficient dissolution of active ingredients or even scorching and burning. This fails to meet the precise dosage and concentration requirements of clinical medication, hindering the standardization and normalization of traditional Chinese medicine decoction.

[0003] In the relevant technologies, the traditional method of calculating the amount of water added for decocting medicine is based on the water absorption rate of the medicinal materials. However, the water absorption rate of the medicinal materials is affected by various factors such as the place of origin and environmental temperature and humidity, which leads to a large deviation in the calculation results of the amount of water added, affecting the dosage and concentration of the medicine. There is currently no effective solution to this problem.

[0004] Therefore, it is necessary to improve the relevant technology to overcome the aforementioned defects. Summary of the Invention

[0005] This application provides a method and apparatus for calculating the amount of water added during decoction based on an artificial intelligence adaptive learning model. This addresses the problem that in related technologies, the traditional method for calculating the amount of water added during decoction often relies on the water absorption rate of the medicinal slices as the core basis. However, the water absorption rate of the medicinal slices is affected by various factors such as the place of origin and environmental temperature and humidity, resulting in a large deviation in the calculation results and affecting the dosage and concentration of the medicinal liquid.

[0006] According to one aspect of the embodiments of this application, a method for calculating the amount of water added during decoction based on an artificial intelligence adaptive learning model is provided, comprising: receiving a water addition calculation request for a target prescription, wherein the water addition calculation request is used to request the calculation of the amount of water to be added for decocting the target prescription; parsing the target prescription to obtain first drug details information of the target prescription, wherein the first drug details information includes: the names of multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid for the target prescription; inputting the first drug details information into a water addition calculation model to calculate the amount of water added, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0007] In an exemplary embodiment, before inputting the first drug details information into the water addition calculation model for water addition calculation, the method further includes: performing basic water absorption rate tests on multiple drugs to obtain water absorption rate data for the multiple drugs; calculating the first water addition amount for multiple prescription samples based on the water absorption rate data of the multiple drugs, and performing decoction tests on the multiple prescription samples based on the multiple first water addition amounts to obtain multiple decoction test data, wherein the decoction test data includes: second drug details information corresponding to the prescription sample, the actual water addition amount corresponding to the prescription sample, and the final liquid volume obtained after the prescription sample undergoes the decoction test; the second drug details information is of the same category as the first drug details information; constructing a basic database based on the multiple decoction test data; and training a deep learning algorithm based on the basic database to obtain the water addition calculation model.

[0008] In an exemplary embodiment, training a deep learning algorithm based on the basic database to obtain the water addition calculation model includes: continuously collecting real-time decoction data during the clinical decoction process; expanding the basic database based on the real-time decoction data, wherein the real-time decoction data and the plurality of decoction test data are of the same category; cleaning the plurality of decoction data in the basic database to obtain cleaned plurality of decoction data, wherein the plurality of decoction data includes the plurality of decoction test data and the real-time decoction data; and training the deep learning algorithm based on the cleaned plurality of decoction data to obtain the water addition calculation model.

[0009] In an exemplary embodiment, the deep learning algorithm is trained based on the multiple decoction data after cleaning to obtain the water addition calculation model. The training process includes: using the third drug details information of each decoction data in the multiple decoction data after cleaning as input features, and using the actual water addition amount of each decoction data and the deviation between the final decoction volume and the required decoction volume of each decoction data as output labels to train the deep learning algorithm to obtain the water addition calculation model. The third drug details information is of the same category as the second drug details information.

[0010] In an exemplary embodiment, the first drug details are input into a water addition calculation model to calculate the water addition amount, which includes: when the target prescription is decocted once, determining the required liquid volume as the final required liquid volume of the target prescription, inputting the first drug details into the water addition calculation model to calculate the water addition amount; when the target prescription is decocted twice, inputting the fourth drug details into the water addition calculation model to calculate the water addition amount, which includes: the required liquid volume for one decoction, the names of the plurality of drugs, and the dosage of the plurality of drugs; the required liquid volume includes the required liquid volume for one decoction.

[0011] In an exemplary embodiment, when the target prescription is decocted twice, the fourth drug details are input into the water addition calculation model to calculate the water addition. After obtaining the water addition, the method further includes: completing the first decoction of the target prescription based on the water addition, and determining the amount of the first decoction liquid; calculating the amount of water added for the second decoction of the target prescription based on the amount of the first decoction liquid and the final required amount of liquid, wherein the required amount of liquid includes the final required amount of liquid; completing the second decoction of the target prescription based on the amount of water added for the second decoction, and obtaining the second decoction liquid; mixing and heating the first decoction liquid and the second decoction liquid to obtain the final liquid of the target prescription.

[0012] In one exemplary embodiment, determining the volume of the obtained decoction liquid includes one of the following: after the decoction barrel has completed the first decoction, the decoction barrel is weighed to obtain a first weight; the decoction liquid is extracted from the decoction barrel using a residue-liquid separator; the decoction barrel is weighed again to obtain a second weight; and the volume of the decoction liquid is determined based on the difference between the first weight and the second weight; or after the decoction barrel has completed the first decoction, the decoction liquid is extracted from the decoction barrel to a packaging machine for temporary storage using the residue-liquid separator; image data of the packaging machine is acquired; visual recognition technology is used to visually recognize the image data to determine the volume of the decoction liquid in the packaging machine; and the volume of the decoction liquid is determined based on the volume of the decoction liquid.

[0013] According to another aspect of the embodiments of this application, a decoction water addition calculation device based on an artificial intelligence adaptive learning model is also provided, comprising: a receiving module, configured to receive a water addition calculation request for a target prescription, wherein the water addition calculation request is used to request calculation of the amount of water to be added for decocting the target prescription; a parsing module, configured to parse the target prescription to obtain first drug details information of the target prescription, wherein the first drug details information includes: the names of multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of decoction liquid of the target prescription; and a calculation module, configured to input the first drug details information into the water addition calculation model to calculate the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0014] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program is configured to execute the above-described method for calculating the amount of water added for decocting medicine based on an artificial intelligence adaptive learning model when it is run.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-mentioned method for calculating the amount of water added for decocting medicine based on an artificial intelligence adaptive learning model through the computer program.

[0016] According to another aspect of the embodiments of this application, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the methods described in various embodiments of this application.

[0017] This application, upon receiving a request to calculate the amount of water to be added for decocting a target prescription, parses the target prescription to obtain its first prescription details. These details include the names, dosages, and required volume of liquid for each of the multiple medications in the prescription. This first medication details are then input into a water addition calculation model, which is an artificial intelligence adaptive learning model. By constructing this model, the application can accurately calculate the amount of water to be added based on the prescription's medication details and weights. This ensures that the deviation between the final volume of decocted liquid and the required volume is controlled within 3%, guaranteeing the stability and standardization of the decoction quality. This solves the problem in related technologies where traditional decoction water addition calculations rely heavily on the water absorption rate of medicinal herbs, which is affected by factors such as origin, environmental temperature and humidity, leading to significant deviations in the calculation results and impacting the dosage and concentration of the decoction. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application 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.

[0020] Figure 1 This is a hardware structure block diagram of a computer terminal for a method of calculating the amount of water added for decocting medicine based on an artificial intelligence adaptive learning model, according to an embodiment of this application.

[0021] Figure 2 This is a flowchart of a method for calculating the amount of water added during decoction based on an artificial intelligence adaptive learning model, according to an embodiment of this application.

[0022] Figure 3 This is a flowchart illustrating a method for calculating the amount of water added during the first decoction of traditional Chinese medicine based on artificial intelligence adaptive learning, according to an embodiment of this application.

[0023] Figure 4 This is a structural block diagram of a decoction water addition calculation device based on an artificial intelligence adaptive learning model, according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] The methods and embodiments provided in this application can be executed on a computer terminal or similar computing device. Taking running on a computer terminal as an example, Figure 1 This is a hardware structure block diagram of a computer terminal for a method of calculating the amount of water added for decocting medicine based on an artificial intelligence adaptive learning model, according to an embodiment of this application. Figure 1 As shown, a computer terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a central processing unit (CPU) or a programmable gate array (FPGA)) and a memory 104 for storing data are also shown. The computer terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the computer terminal described above. For example, the computer terminal may also include components that are more complex than those described above. Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0027] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the data integration method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0028] The computer terminal uses a wireless network provided by a communications provider. In one example, transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0029] This embodiment provides a method for calculating the amount of water to add when decocting medicine based on an artificial intelligence adaptive learning model. Figure 2 This is a flowchart illustrating a method for calculating the amount of water to add during decoction based on an artificial intelligence adaptive learning model, according to an embodiment of this application. Figure 2 As shown, the process includes the following steps:

[0030] Step S202: Receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the amount of water to be added for decocting the target prescription.

[0031] Step S204: Analyze the target prescription to obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of the multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription;

[0032] Step S206: Input the first drug details into the water addition calculation model to calculate the water addition amount, and obtain the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0033] This application, upon receiving a request to calculate the amount of water to be added for decocting a target prescription, parses the target prescription to obtain its first prescription details. These details include the names, dosages, and required volume of liquid for each of the multiple medications in the prescription. This first medication details are then input into a water addition calculation model, which is an artificial intelligence adaptive learning model. By constructing this model, the application can accurately calculate the amount of water to be added based on the prescription's medication details and weights. This ensures that the deviation between the final volume of decocted liquid and the required volume is controlled within 3%, guaranteeing the stability and standardization of the decoction quality. This solves the problem in related technologies where traditional decoction water addition calculations rely heavily on the water absorption rate of medicinal herbs, which is affected by factors such as origin, environmental temperature and humidity, leading to significant deviations in the calculation results and impacting the dosage and concentration of the decoction.

[0034] In an exemplary embodiment, before inputting the first drug details information into the water addition calculation model for water addition calculation, the method further includes: performing basic water absorption rate tests on multiple drugs to obtain water absorption rate data for the multiple drugs; calculating the first water addition amount for multiple prescription samples based on the water absorption rate data of the multiple drugs, and performing decoction tests on the multiple prescription samples based on the multiple first water addition amounts to obtain multiple decoction test data, wherein the decoction test data includes: second drug details information corresponding to the prescription sample, the actual water addition amount corresponding to the prescription sample, and the final liquid volume obtained after the prescription sample undergoes the decoction test; the second drug details information is of the same category as the first drug details information; constructing a basic database based on the multiple decoction test data; and training a deep learning algorithm based on the basic database to obtain the water addition calculation model.

[0035] The process of constructing the water addition calculation model is as follows: First, a basic water absorption rate test is performed on all Chinese herbal medicine pieces to obtain detailed water absorption rate data as auxiliary information for subsequent analysis. Then, based on this water absorption rate data, the initial water addition required for a series of prescription samples is estimated. A decoction test is then conducted, and the detailed information of the second medicine for each sample, the actual initial water addition, and the final volume of liquid obtained after the decoction process are recorded. The data categories included in the detailed information of the second medicine are consistent with those in the detailed information of the first medicine.

[0036] The collected decoction test data constitutes the basic database, which is an indispensable cornerstone for model training. Next, a deep learning algorithm is selected, using the prescription information, drug weight, water volume, and liquid volume data in the basic database as training materials, to extract the core logic of the water volume calculation model.

[0037] It should be noted that although the water absorption rate data is used to build the database when training the model in this embodiment, the water absorption rate is not directly used as the model input or adjustment parameter. This ensures that the model is independent of the variable water absorption rate and focuses on the intrinsic relationship between the prescription characteristics and the amount of water added, so as to achieve a higher degree of accurate calculation.

[0038] It should be noted that deep learning algorithms, such as neural network algorithms and gradient boosting tree algorithms, are good at handling complex pattern recognition and nonlinear mapping tasks. In this embodiment, they are used to help capture the subtle relationship between drug details and weight, water volume and liquid volume, and can still maintain high accuracy in water volume calculation even when the properties of the medicinal slices fluctuate.

[0039] The trained water addition calculation model can quickly calculate the appropriate amount of water to add based on the input prescription drug information. Its design avoids direct reliance on the water absorption rate of the medicinal slices, and instead emphasizes the drug combination characteristics learned by the model through big data, thereby improving the efficiency of decoction and the consistency of efficacy.

[0040] In an exemplary embodiment, training a deep learning algorithm based on the basic database to obtain the water addition calculation model includes: continuously collecting real-time decoction data during the clinical decoction process; expanding the basic database based on the real-time decoction data, wherein the real-time decoction data and the plurality of decoction test data are of the same category; cleaning the plurality of decoction data in the basic database to obtain cleaned plurality of decoction data, wherein the plurality of decoction data includes the plurality of decoction test data and the real-time decoction data; and training the deep learning algorithm based on the cleaned plurality of decoction data to obtain the water addition calculation model.

[0041] Specifically, the training process of the deep learning algorithm emphasizes the model construction and optimization strategies. The process begins with the construction of a basic database, composed of multiple decoction test data sets, covering the first drug details of the prescription sample, the first water addition suggestion, and the final liquid volume record obtained after decoction. Subsequently, the process enters a real-time data feedback phase, continuously collecting fresh decoction data from clinical decoction sites and seamlessly integrating it with the original database information. Through this approach, the basic database can be continuously expanded to incorporate more diverse decoction scenarios and feedback results. Notably, the real-time decoction data and the decoction test data are of the same category, ensuring data continuity and comparability. Next, the example emphasizes deep cleaning of the accumulated decoction data in the database to remove any outliers caused by equipment malfunctions or human error, ensuring data quality and the accuracy of model training. The cleaned data, including existing decoction test data and newly added real-time decoction data, is used for repeated training and parameter fine-tuning of the deep learning algorithm until a highly accurate and adaptive water addition calculation model is produced.

[0042] It should be noted that the data cleaning process is used to clean the collected data, remove outliers and missing values ​​caused by equipment failure and operational errors, and supplement and improve the data dimensions to form a large-scale, standardized dataset of "prescription-drug details (drugs, weight)-actual amount of water added-volume of decoction".

[0043] This embodiment feeds back the details of the new prescription's medicines, the actual amount of water added, and the deviation data between the volume of the decoction and the theoretically required volume of the decoction to the basic database. The AI ​​model (i.e., the water addition calculation model mentioned above) is retrained and its parameters are fine-tuned periodically using the expanded dataset. This establishes a self-evolving and continuously learning deep learning model. It can not only make preliminary water addition calculations based on historical decoction data, but also continuously absorb new data in practical applications, self-correct and optimize, ultimately achieving high accuracy and strong adaptability in water addition calculation. It can adaptively offset the interference caused by variables such as the origin of the medicinal materials, environmental temperature and humidity, and storage time, and always maintain a high accuracy in water addition calculation, greatly improving the standardization level and clinical efficacy of traditional Chinese medicine decoction.

[0044] In an exemplary embodiment, the deep learning algorithm is trained based on the multiple decoction data after cleaning to obtain the water addition calculation model. The training process includes: using the third drug details information of each decoction data in the multiple decoction data after cleaning as input features, and using the actual water addition amount of each decoction data and the deviation between the final decoction volume and the required decoction volume of each decoction data as output labels to train the deep learning algorithm to obtain the water addition calculation model. The third drug details information is of the same category as the second drug details information.

[0045] During the training process of the deep learning algorithm, each cleaned and error-free decoction data entry contains third-party drug details, which serve as input features for model training. These third-party drug details share the same data category as the second-party drug details. Simultaneously, the actual amount of water added and the deviation between the actual and ideal decoction volume for each data entry serve as output labels. These labels guide the deep learning algorithm to learn how to convert the drug details into the most suitable water addition amount, minimizing the deviation in decoction volume and achieving precise water addition calculation. This training strategy, by directly linking the characteristics of prescription drugs with the differences in decoction results, encourages the model to autonomously discover and master the complex relationships, ultimately producing a calculation model capable of accurately predicting the amount of water added.

[0046] Through the training process of this embodiment, a deep learning model capable of adaptive learning was obtained. It can not only accurately calculate the amount of water required for decocting medicine based on the prescription drug details, but also actively optimize the calculation results and reduce the deviation of the liquid volume. In practical applications, this significantly improves the standardization of Chinese medicine decoction and the reliability of the decoction effect.

[0047] In an exemplary embodiment, the first drug details are input into a water addition calculation model to calculate the water addition amount, which includes: when the target prescription is decocted once, determining the required liquid volume as the final required liquid volume of the target prescription, inputting the first drug details into the water addition calculation model to calculate the water addition amount; when the target prescription is decocted twice, inputting the fourth drug details into the water addition calculation model to calculate the water addition amount, which includes: the required liquid volume for one decoction, the names of the plurality of drugs, and the dosage of the plurality of drugs; the required liquid volume includes the required liquid volume for one decoction.

[0048] This embodiment describes a process for refining the calculation of water dosage using a water dosage calculation model for target prescriptions with different decoction times. When the prescription specifies one decoction, the system directly uses the final required amount of liquid for the entire pharmacy as the calculation target. Then, the first drug details—the names and dosages of all drugs in the prescription—are input into a pre-trained deep learning model. The model randomly outputs the optimal water dosage for one decoction of that prescription. Conversely, for prescriptions requiring two decoctions, a step-by-step strategy is adopted. First, the fourth drug details are determined, including the required amount of liquid for the first decoction, the specific names of the drugs in the prescription, and their respective dosages. This information is submitted to the water dosage calculation model, which then outputs the water dosage for the first decoction. The water dosage for the second decoction is adjusted based on the remaining state of the herbs after the first decoction and the need to retain medicinal efficacy, ensuring that the total amount of liquid produced throughout the decoction process meets the overall requirements of the prescription.

[0049] This embodiment uses a dynamic calculation model to customize the water addition amount according to the requirements of different decoction times for different prescriptions. This effectively reduces the loss of efficacy or excessive dilution caused by improper water addition, promotes the refinement and standardization of Chinese medicine decoction, and can more precisely control the water addition amount for each decoction in the complex case of two decoctions, ensuring the accuracy of the final liquid volume and thus improving the clinical treatment effect.

[0050] In an exemplary embodiment, when the target prescription is decocted twice, the fourth drug details are input into the water addition calculation model to calculate the water addition. After obtaining the water addition, the method further includes: completing the first decoction of the target prescription based on the water addition, and determining the amount of the first decoction liquid; calculating the amount of water added for the second decoction of the target prescription based on the amount of the first decoction liquid and the final required amount of liquid, wherein the required amount of liquid includes the final required amount of liquid; completing the second decoction of the target prescription based on the amount of water added for the second decoction, and obtaining the second decoction liquid; mixing and heating the first decoction liquid and the second decoction liquid to obtain the final liquid of the target prescription.

[0051] For prescriptions requiring two decoctions, the first step is to submit the fourth set of drug details—the names and dosages of all drugs in the prescription—along with the expected volume of liquid for the first decoction, to a computational model trained through deep learning for analysis. Based on complex mapping patterns learned from existing data, the model quickly derives the required amount of water for the first decoction. The person preparing the medicine adds water accordingly to complete the first decoction, obtaining the actual volume of liquid. Then, based on this actual volume and the final required volume specified in the prescription, the required amount of water for the second decoction is calculated, ensuring that the total volume of the combined decoction accurately matches the prescription requirements. After confirming the water amount for the second decoction, the second decoction is prepared according to a predetermined procedure, generating the second decoction. Finally, the liquids from the first and second decoctions are combined in the same container and mixed again by heating to obtain the final liquid, meeting the quantified efficacy requirements of the prescription.

[0052] Through the two-stage decoction water addition calculation process in this embodiment, combined with the intelligent prediction of the deep learning model, not only is the water addition amount precisely controlled, ensuring the final amount of medicine reaches the standard, but the efficiency of the decoction process and the consistency of the efficacy are also significantly improved, making an important contribution to the modernization and standardization of the field of traditional Chinese medicine decoction.

[0053] In one exemplary embodiment, determining the volume of the obtained decoction liquid includes one of the following: after the decoction barrel has completed the first decoction, the decoction barrel is weighed to obtain a first weight; the decoction liquid is extracted from the decoction barrel using a residue-liquid separator; the decoction barrel is weighed again to obtain a second weight; and the volume of the decoction liquid is determined based on the difference between the first weight and the second weight; or after the decoction barrel has completed the first decoction, the decoction liquid is extracted from the decoction barrel to a packaging machine for temporary storage using the residue-liquid separator; image data of the packaging machine is acquired; visual recognition technology is used to visually recognize the image data to determine the volume of the decoction liquid in the packaging machine; and the volume of the decoction liquid is determined based on the volume of the decoction liquid.

[0054] This embodiment details two implementation schemes for determining the amount of decoction liquid. The first scheme focuses on achieving accurate calculation of the amount of decoction liquid through weight measurement. Specifically, after the first decoction is completed, the decoction container is first weighed and the first weight is recorded. Then, a residue separator is used to separate the decocted liquid from the residue, and the decoction container is weighed again to obtain the second weight. By calculating the difference between the first weight and the second weight, the exact weight of the decoction liquid can be obtained, thereby indirectly determining the amount of decoction liquid.

[0055] The second approach uses visual recognition technology. After the first decoction is completed, the liquid is transferred to a packaging machine for temporary storage using a residue-liquid separator. The image data of the packaging machine is then automatically acquired, and these images are analyzed using advanced visual recognition algorithms to accurately locate the volume boundary of the liquid, thereby directly reading the volume value of the liquid and determining the specific amount of the first decoction.

[0056] Both schemes aim to provide a more refined means of measuring the amount of medicine, getting rid of the extensive limitations of traditional methods, and ensuring the standardization of the decoction process and the controllability of the efficacy.

[0057] It should be noted that the residue-liquid separator is a device specifically used in the process of decocting traditional Chinese medicine to separate the decocted liquid from the herbal residue. It has functions such as efficient separation and automatic liquid extraction, and is a key tool in the modern decoction process.

[0058] It should be noted that visual recognition technology is based on the principles of computer vision. It can automatically identify and measure the shape, size, color and other features of objects by analyzing image data. When applied to the decoction process of traditional Chinese medicine, it can achieve non-contact, rapid and accurate measurement of the amount of liquid.

[0059] This embodiment proposes two methods for measuring the volume of medicinal liquid, achieving an unprecedented level of precision and standardization in the decoction process. Whether by measuring the volume of the medicinal liquid directly through weight difference or visual recognition technology, the volume of the first decoction can be effectively monitored and controlled, ensuring the accurate execution of subsequent decoction processes, thereby significantly improving the stability of the efficacy of traditional Chinese medicine and the safety of patient treatment.

[0060] In an optional embodiment, to address the problem that traditional methods for calculating the amount of water added during decoction in related technologies lack accuracy due to reliance on the water absorption rate of medicinal slices and interference from multiple factors, this application provides a method for calculating the amount of water added during the first decoction based on artificial intelligence adaptive learning. The process of this method is as follows: Figure 3 As shown, it includes the following steps:

[0061] 1. Experimental Data Collection and Basic Database Construction: A comprehensive basic water absorption rate test was conducted on all Chinese herbal medicine pieces (equivalent to the aforementioned drugs). Water absorption rate data for each type of herbal medicine piece was obtained through a standardized experimental procedure. This data was only included in the dataset as an auxiliary reference (not as a core variable of the model or as the basis for adjustment). Focusing on a large number of clinical prescriptions, the complete drug details (including drug name, prescription weight / dosage), actual amount of water added, and final volume of decoction were recorded for each prescription to construct an initial dataset. The core of the dataset covers the full-dimensional correlation data of "prescription - corresponding drug details (drug, weight) (equivalent to the second drug details information mentioned above) - actual amount of water added - volume of decoction." Water absorption rate data is used to assist in traceability and comparison.

[0062] 2. Big Data Expansion and Preprocessing: Continuously collect real-time data during the clinical decoction process (equivalent to the aforementioned real-time decoction data), focusing on the drug details (drug name, weight / dosage), actual water added, and the volume of decoction liquid after decoction for newly added prescriptions. Simultaneously, basic information on the medicinal materials (origin, storage temperature and humidity, storage time) can be recorded for traceability reference. The collected data is cleaned to remove outliers and missing values ​​caused by equipment malfunctions or operational errors, supplementing and improving data dimensions to form a large-scale, standardized dataset linking "prescription - drug details (drug, weight) - actual water added - volume of decoction liquid after decoction".

[0063] 3. AI Model Training and Optimization (Equivalent to the Water Addition Calculation Model Explained Above): A deep learning algorithm (such as a neural network algorithm or a gradient boosting tree algorithm) is selected. The core input feature is the "prescription drug details (drug name, prescription weight / dosage)" from the large dataset. The output labels are "actual water addition" and "deviation between the volume of the decocted medicine and the theoretically required volume." During training, the water absorption rate is not adjusted as a variable parameter. Instead, the model parameters are iteratively adjusted and feature weights are optimized based on the correlation between the core input features and the output labels. This allows the model to accurately capture the non-linear relationship between drug type, weight, water addition, and the deviation in the volume of the decocted medicine, forming a water addition calculation model with adaptive learning capabilities.

[0064] 4. Precise Water Addition Calculation: When receiving a request to calculate the water addition for a new prescription (equivalent to the target prescription mentioned above), only the complete drug details (drug name, corresponding weight / dosage) of the prescription are extracted, without needing to input the water absorption rate as a core parameter. The drug details data are input into the trained AI model, which directly calculates the theoretical water addition for the prescription by calling the "drug type-weight-water addition" correlation pattern learned from historical big data, achieving accurate prediction based on historical data.

[0065] 5. Adaptive Iterative Model Update: The details of the new prescription's medicines, actual water addition, and deviations between the decoction volume and the theoretically required volume are fed back to a large dataset. The expanded dataset is used periodically to retrain the AI ​​model and fine-tune its parameters. The model is always iteratively optimized based on the core data of "medicine-weight-water addition-volume decoction," without relying on water absorption rate adjustments. It can adaptively offset interference from variables such as the origin of the medicinal materials, environmental temperature and humidity, and storage time, maintaining a high-precision water addition calculation capability.

[0066] This scheme downplays the role of water absorption rate of medicinal slices, using it only as basic reference data. The core is to build a model by collecting feedback data on prescription drug details, weight, actual water added, and final liquid volume to accurately calculate the amount of water added. This ensures that the deviation between the final liquid volume and the theoretical required liquid volume is controlled within 0-3%, guaranteeing the stability and standardization of decoction quality.

[0067] The following detailed description of this solution uses a specific embodiment as an example:

[0068] Example: A specific application of a decoction-first-decoction water addition calculation method based on artificial intelligence adaptive learning.

[0069] 1. Basic Data Collection Phase: Basic water absorption rate tests were conducted on all Chinese herbal medicine pieces involved in the prescription. Standardized experimental procedures were used to determine the water absorption rate data of each type of herbal medicine piece. This data is only used as a reference for subsequent decoction traceability and data comparison, and is not used as the core variable of the model or the basis for adjustment. 15,000 clinical decoction prescriptions were collected in a key area. The name of the medicine, the corresponding weight, the actual amount of water added, and the amount of decoction liquid after decoction were fully recorded for each prescription. At the same time, the place of origin of the herbal medicine pieces, storage environment (temperature 20℃ / humidity 50%, temperature 30℃ / humidity 70%, temperature 10℃ / humidity 30%), and storage time (1 month, 3 months, 6 months, 12 months) were recorded for traceability. The initial dataset was constructed, and the core data dimensions focused on "medicine-weight-water-decoction liquid volume".

[0070] 2. Big Data Preprocessing: The initial dataset is cleaned to remove abnormal data caused by equipment failure or operational errors (such as data with a deviation of more than 10% in the amount of medicinal liquid), and information such as the place of origin, storage environment, and storage time of each medicinal slice is added to form a big dataset containing 12,000 valid records.

[0071] 3. AI Model Training: A hybrid deep learning model was constructed using a convolutional neural network (CNN) combined with a gradient boosting tree (XGBoost). The core input features were "drug name (encoded)" and "prescription weight," excluding water absorption rate. The output target was "optimal actual water volume." The model was trained using a pre-processed large dataset. During training, 5-fold cross-validation was used to adjust parameters such as the learning rate, number of iterations, and feature dimensions, ensuring that the model's prediction of the correct amount of medicine added was consistently within the target range of 0% to +3%.

[0072] 4. Practical Application Testing: One hundred new clinical prescriptions were selected, covering different combinations of medicinal herbs, dosages, and background parameters of the herbs. The amount of water added for one decoction was calculated using both the method of this invention and the traditional water absorption rate method, and a comparative decoction experiment was conducted. The results showed that the deviation between the final volume of the decoction calculated by the method of this invention and the theoretical required volume was within 0% to +3%; while the deviation range of the traditional method was -15.3% to +22.6%, with an average deviation of 16.5%. The accuracy of the method of this invention is significantly better than that of the traditional method.

[0073] 5. Model Iteration and Update: The actual decoction data (water addition and liquid volume deviation) of 100 test prescriptions are added to the large dataset. The model is fine-tuned and trained every two weeks using the updated dataset to continuously optimize model performance and ensure computational accuracy in long-term applications.

[0074] This solution completely abandons the traditional calculation logic that relies solely on the water absorption rate of medicinal slices, weakening the role of water absorption rate and using it only as a reference. By deeply mining the core correlation patterns of "drug details - weight - water added - liquid volume" in historical big data through AI models, there is no need to adjust the water absorption rate as a variable parameter. It can adaptively offset the influence of interference factors such as the origin of medicinal slices, environmental temperature and humidity, and storage time, so that the deviation between the final decoction volume and the theoretical required volume of the prescription is controlled within 0-3%, which is significantly better than the traditional method and ensures the stability of the concentration and efficacy of the liquid.

[0075] Furthermore, the AI ​​model proposed in this solution (i.e. the water addition calculation model mentioned above) has adaptive learning capabilities, which can continuously optimize the model through real-time feedback of decoction data, realize dynamic iterative updates of the model, and further improve the calculation accuracy as the amount of data accumulates. It can adapt to the needs of decoction of medicinal slices in different batches and under different conditions without the need for frequent manual adjustment of parameters.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0077] Figure 4 This is a structural block diagram of a decoction water addition calculation device based on an artificial intelligence adaptive learning model according to an embodiment of this application. The device includes:

[0078] The receiving module 42 is used to receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the amount of water to be added for decocting the target prescription.

[0079] The parsing module 44 is used to parse the target prescription and obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine in the target prescription;

[0080] The calculation module 46 is used to input the first drug details into the water addition calculation model to calculate the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0081] The aforementioned device receives a request to calculate the amount of water needed for decocting a target prescription. It then analyzes the target prescription to obtain its first prescription details, which include the names, dosages, and required volume of liquid for each of the multiple medications in the prescription. This first prescription details are input into a water addition calculation model, which is an artificial intelligence adaptive learning model. By constructing this model, the present application can accurately calculate the amount of water needed based on the prescription's medication details and weights. This ensures that the deviation between the final volume of decocted liquid and the required volume is controlled within 3%, guaranteeing the stability and standardization of the decoction quality. This solves the problem in related technologies where traditional decoction water addition calculations rely heavily on the water absorption rate of medicinal slices. However, the water absorption rate of medicinal slices is affected by various factors such as origin, environmental temperature, and humidity, leading to significant deviations in the calculated water addition and impacting the dosage and concentration of the decoction.

[0082] In an exemplary embodiment, the calculation module 46 is further configured to perform a basic water absorption rate test on multiple drugs to obtain water absorption rate data of the multiple drugs; calculate a first water addition amount for multiple prescription samples based on the water absorption rate data of the multiple drugs, and perform a decoction test on the multiple prescription samples based on the multiple first water addition amounts to obtain multiple decoction test data, wherein the decoction test data includes: second drug detail information corresponding to the prescription sample, the actual water addition amount corresponding to the prescription sample, and the final liquid volume obtained after the prescription sample undergoes the decoction test; the second drug detail information is of the same category as the first drug detail information; construct a basic database based on the multiple decoction test data; and train a deep learning algorithm based on the basic database to obtain the water addition amount calculation model.

[0083] In an exemplary embodiment, the above-mentioned calculation module 46 is further configured to continuously collect real-time decoction data during the clinical decoction process, expand the basic database based on the real-time decoction data, wherein the real-time decoction data is of the same category as the plurality of decoction test data; perform data cleaning on the plurality of decoction data in the basic database to obtain multiple cleaned decoction data, wherein the multiple decoction data includes the plurality of decoction test data and the real-time decoction data; and train the deep learning algorithm based on the multiple cleaned decoction data to obtain the water addition calculation model.

[0084] In an exemplary embodiment, the above-mentioned calculation module 46 is further configured to use the third drug details information of each decoction data in the multiple decoction data after cleaning as input features, and the actual amount of water added to each decoction data and the deviation between the final amount of medicine liquid and the required amount of medicine liquid in each decoction data as output labels to train the deep learning algorithm to obtain the water addition calculation model, wherein the third drug details information is of the same category as the second drug details information.

[0085] In an exemplary embodiment, the calculation module 46 is further configured to: determine the required amount of medicinal liquid as the final required amount of medicinal liquid for the target prescription when the prescription is decocted once; input the first drug details into the water addition calculation model to calculate the water addition amount; and input the fourth drug details into the water addition calculation model to calculate the water addition amount when the prescription is decocted twice, wherein the fourth drug details include: the required amount of medicinal liquid for one decoction, the names of the plurality of drugs, and the dosage of the plurality of drugs; the required amount of medicinal liquid includes the required amount of medicinal liquid for one decoction.

[0086] In an exemplary embodiment, the calculation module 46 is further configured to: complete the first decoction of the target prescription based on the amount of water added, and determine the amount of the first decoction liquid obtained; calculate the amount of water added for the second decoction of the target prescription based on the amount of the first decoction liquid and the final required amount of liquid, wherein the required amount of liquid includes the final required amount of liquid; complete the second decoction of the target prescription based on the amount of water added for the second decoction, and obtain the second decoction liquid; mix and heat the first decoction liquid and the second decoction liquid to obtain the final liquid of the target prescription.

[0087] In an exemplary embodiment, the above-mentioned calculation module 46 is further configured to: weigh the decoction barrel after the first decoction is completed to obtain a first weight; extract the decoction liquid from the decoction barrel using a residue-liquid separator; weigh the decoction barrel again to obtain a second weight; determine the amount of the decoction liquid based on the difference between the first weight and the second weight; and, after the first decoction is completed, extract the decoction liquid from the decoction barrel to a packaging machine for temporary storage using the residue-liquid separator; acquire image data of the packaging machine; perform visual recognition on the image data using visual recognition technology to determine the volume of the decoction liquid in the packaging machine; and determine the amount of the decoction liquid based on the volume of the decoction liquid.

[0088] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above method embodiments when run.

[0089] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0090] S1, Receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the water addition for decocting the target prescription.

[0091] S2, parse the target prescription to obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of the multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription;

[0092] S3, input the first drug details into the water addition calculation model to calculate the water addition amount, and obtain the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0093] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0094] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0095] Embodiments of this application also provide an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0096] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0097] S1, Receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the water addition for decocting the target prescription.

[0098] S2, parse the target prescription to obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of the multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription;

[0099] S3, input the first drug details into the water addition calculation model to calculate the water addition amount, and obtain the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0100] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0101] Embodiments of this application also provide a computer program product, including a non-volatile computer-readable storage medium storing the computer program product, wherein the computer program, when executed by a processor, implements the steps of the methods described in various embodiments of this application.

[0102] Optionally, in this embodiment, the computer program described above can be configured to perform the following steps when executed by the processor:

[0103] S1, Receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the water addition for decocting the target prescription.

[0104] S2, parse the target prescription to obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of the multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription;

[0105] S3, input the first drug details into the water addition calculation model to calculate the water addition amount, and obtain the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

[0106] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0107] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular hardware and software combination.

[0108] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for calculating the amount of water to add during decoction based on an artificial intelligence adaptive learning model, characterized in that, include: Receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the amount of water to be added for decocting the target prescription; The target prescription is parsed to obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription; The first drug details are input into the water addition calculation model to calculate the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

2. The method according to claim 1, characterized in that, Before inputting the first drug details into the water addition calculation model for water addition calculation, the method further includes: Basic water absorption rate tests were conducted on various drugs to obtain water absorption rate data for these drugs. The first water addition amount for multiple prescription samples is calculated based on the water absorption rate data of the various drugs, and the multiple prescription samples are subjected to decoction tests based on the multiple first water addition amounts to obtain multiple decoction test data. The decoction test data includes: second drug details information corresponding to the prescription sample, the actual water addition amount corresponding to the prescription sample, and the final liquid volume obtained after the prescription sample is decocted. The second drug details information is of the same category as the first drug details information. A basic database is constructed based on the aforementioned multiple boiling test data; The deep learning algorithm is trained based on the aforementioned basic database to obtain the water addition calculation model.

3. The method according to claim 2, characterized in that, The deep learning algorithm is trained based on the aforementioned basic database to obtain the water addition calculation model, which includes: Continuously collect real-time decoction data during the clinical decoction process, and expand the basic database based on the real-time decoction data, wherein the real-time decoction data is of the same category as the multiple decoction test data; Data cleaning is performed on multiple decoction data in the basic database to obtain multiple cleaned decoction data, wherein the multiple decoction data includes the multiple decoction test data and the real-time decoction data; The deep learning algorithm is trained based on multiple decoction data after cleaning to obtain the water addition calculation model.

4. The method according to claim 3, characterized in that, The deep learning algorithm is trained based on multiple decoction data after cleaning to obtain the water addition calculation model, including: Using the third drug details information of each decoction data in the multiple decoction data after cleaning as input features, and the actual amount of water added and the deviation between the final amount of medicine liquid and the required amount of medicine liquid in each decoction data as output labels, the deep learning algorithm is trained to obtain the water addition calculation model, wherein the third drug details information is of the same category as the second drug details information.

5. The method according to claim 1, characterized in that, The first drug details are input into the water addition calculation model to calculate the water addition amount, which includes: If the target prescription is to be decocted once, the required amount of liquid is determined to be the final required amount of liquid for the target prescription. The first drug details are input into the water addition calculation model to calculate the water addition amount. When the target prescription is decocted twice, the fourth drug details are input into the water addition calculation model to calculate the water addition amount. The fourth drug details include: the required amount of decoction for one decoction, the names of the multiple drugs, and the dosage of the multiple drugs; the required amount of decoction includes the required amount of decoction for one decoction.

6. The method according to claim 5, characterized in that, When the target prescription is decocted twice, the fourth drug details are input into the water addition calculation model to calculate the water addition. After obtaining the water addition, the method further includes: Based on the amount of water added, complete the first decoction of the target prescription and determine the amount of the first decoction liquid obtained. The amount of water to be added for the second decoction of the target prescription is calculated based on the amount of the first decoction and the final required amount of decoction, wherein the required amount of decoction includes the final required amount of decoction. The second decoction of the target prescription is completed according to the amount of water added for the second decoction, and the second decoction liquid is obtained. The first decoction and the second decoction are mixed and heated to obtain the final decoction of the target prescription.

7. The method according to claim 6, characterized in that, The amount of the first decoction obtained is determined by one of the following: After the decoction barrel has completed the first decoction, the decoction barrel is weighed to obtain a first weight. The decoction liquid is then extracted from the decoction barrel using a residue-liquid separator, and the decoction barrel is weighed again to obtain a second weight. The amount of the decoction liquid is determined based on the difference between the first weight and the second weight. After the decoction is completed in the decoction barrel, the decoction liquid is extracted from the decoction barrel to the packaging machine for temporary storage by the residue-liquid separator. Image data of the packaging machine is acquired, and the image data is visually recognized by visual recognition technology to determine the volume of the decoction liquid in the packaging machine. The amount of the decoction liquid is determined based on the volume of the liquid.

8. A device for calculating the amount of water added during decoction based on an artificial intelligence adaptive learning model, characterized in that, include: The receiving module is used to receive a water addition calculation request for the target prescription, wherein the water addition calculation request is used to request the calculation of the amount of water to be added for decocting the target prescription. The parsing module is used to parse the target prescription and obtain the first drug details information of the target prescription, wherein the first drug details information includes: the names of multiple drugs included in the target prescription, the dosage of the multiple drugs, and the required amount of liquid medicine for the target prescription; The calculation module is used to input the first drug details into the water addition calculation model to calculate the water addition amount, wherein the water addition calculation model is an artificial intelligence adaptive learning model.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images