Anesthesia dispensing robot

Abstract

The invention provides an anesthesia dispensing robot, which relates to the technical field of robots and comprises a medicine storage area, a medicine taking assembly, a medicine rechecking assembly, a medicine blending assembly, a display assembly, an input assembly and a processor which are arranged in a robot main body structure, the medicine storage area comprises a plurality of storage subareas, and each storage subarea is used for storing one type of anesthetic medicine; the medicine taking assembly is used for taking anesthetic from the medicine storage area according to a medicine taking instruction of the processor; the medicine rechecking assembly is used for weighing the dosage of the anesthetic medicine; the medicine blending assembly is used for mixing the taken anesthetic medicines and manufacturing anesthetic medicine medical equipment under the condition that the taking amount of the anesthetic medicines is consistent with the medicine taking instruction, and the processor is used for generating the medicine taking instruction. According to the method and the device, the recommended anesthetic medicine dispensing information can be optimized based on modification and confirmation of the recommended anesthetic medicine dispensing information by a doctor, and the recommendation accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and in particular to an anesthesia dispensing robot. Background Art

[0002] In the related art, CN119427393A discloses an automatic dispensing robot and method, which includes: a main controller, a human-computer interaction system, a drug detection system and a drug processing system, wherein: the human-computer interaction system is used to input and obtain user information and medication information, and confirm the user information and medication information before putting the medicine, and feed back the confirmed information to the main controller; the drug detection system is used to detect the status of the medicine, and feed back the drug status information to the main controller; the main controller is used to generate instructions according to the feedback information of the human-computer interaction system and the drug detection system; the drug processing system is used to dispense the corresponding medicine after the status detection according to the instructions of the main controller. This solution improves the efficiency and accuracy of drug management, can perform continuous dispensing, and monitor the quality of the medicine in real time to ensure that the medicine meets the conditions for taking. In addition, one robot can be used by multiple people, and has the characteristics of compact structure and high dispensing efficiency.

[0003] CN118386225A discloses an intelligent dispensing robot based on visual recognition technology, wherein the intelligent dispensing robot includes: a medicine box attribute information acquisition subsystem, which is used to obtain the medicine box attribute information of the first target medicine box; an automatic medicine loading subsystem, which is used to automatically replenish the first target medicine box based on the medicine box attribute information based on the visual recognition technology; a medicine dispensing demand acquisition subsystem, which is used to obtain the medicine dispensing demand of the target patient; a medicine dispensing plan determination subsystem, which is used to determine the medicine dispensing plan based on the medicine dispensing demand and the medicine box attribute information; an intelligent medicine dispensing subsystem, which is used to perform intelligent medicine dispensing according to the medicine dispensing plan. The intelligent medicine dispensing robot based on visual recognition technology of this scheme introduces visual recognition technology and automatically fills the first target medicine box according to the medicine box attribute information. In addition, the medicine dispensing plan is determined according to the medicine dispensing demand and the medicine box attribute information, and the medicine is dispensed based on the medicine dispensing plan, without the need for manual participation in the medicine dispensing process, thus avoiding the situation of mis-dispensing, and being more intelligent.

[0004] Therefore, in the related art, although robots can be used for automatic medication dispensing, they are unable to recommend medication information to doctors, and are even more unable to further optimize the recommended medication information based on the doctor's modification and confirmation of the recommended medication information. Summary of the invention

[0005] The present invention provides an anesthesia medication dispensing robot, which can solve the technical problem that the related technology cannot recommend medication information to doctors, and cannot further optimize the recommended medication information based on the doctor's modification and confirmation of the recommended medication information.

[0006] According to a first aspect of the present invention, there is provided an anesthesia dispensing robot, comprising: Robot main structure and moving components; The mobile component is used to carry the robot main structure and move it, and the robot main structure includes a robot shell, and a drug storage area, a drug taking component, a drug review component, a drug preparation component, a display component, an input component and a processor are arranged in the robot shell; The drug storage area includes a plurality of storage partitions, each storage partition is used to store a type of narcotic drugs; The drug taking component is used to take at least one type of narcotic drug from the drug storage area according to the drug taking instruction of the processor; The drug review component is used to weigh the amount of anesthetic drugs taken to determine whether the amount taken is consistent with the drug taking instruction; The drug preparation component is used to mix the taken anesthetic drugs and prepare anesthetic drug medical equipment when the amount of anesthetic drugs taken is consistent with the drug taking instruction; The processor is used to: Generate narcotic drug dispensing information based on patient information and doctor information collected by the input component; Displaying the narcotic drug dispensing information via a display component; After receiving the doctor's confirmation information on the narcotic drug dispensing information through the input component, the drug taking instruction is generated.

[0007] By adopting the above technical solution, the present invention can achieve the following technical effects: According to the present invention, based on the patient information and the doctor information, the recommended anesthetic drug dispensing information can be generated, and after the doctor's confirmation, the drug taking instruction can be generated, so that based on the doctor's modification and confirmation of the recommended anesthetic drug dispensing information, the recommended anesthetic drug dispensing information can be further optimized to improve the accuracy of the recommendation, and when dispensing based on the drug taking instruction, the amount of anesthetic drugs taken can be reviewed by the drug review component to improve the accuracy and safety of the dispensing. When determining the correlation coefficient, the similarity of medication between each doctor and the current doctor when treating similar patients can be calculated, so as to determine the correlation coefficient between the sample doctor information and the doctor information, so as to accurately describe the similarity of medication habits between each doctor and the current doctor, and the reference value of each doctor's medication data for predicting the current doctor's medication habits. When training the narcotic drug dosage prediction model, the dosage error can be determined by the conditional function when the narcotic drug dosage prediction model predicts correctly or incorrectly, and the reference value of historical data for predicting the current doctor's medication habits can be determined based on the similarity between the physical condition of the sample patient and the current patient and the correlation coefficient between the sample doctor information and the current doctor's doctor information, thereby obtaining the loss function of the narcotic drug dosage prediction model, which can be targeted for training historical data with high reference value, improve training efficiency and the accuracy of the narcotic drug dosage prediction model. When determining the judgment conditions, the standard deviation of the error between the actual weight of the narcotic drug and the used weight, the maximum error, and the number of types of inaccurately taken narcotic drugs can be used to judge whether the amount of narcotic drugs taken is consistent with the drug taking instructions, thereby improving the accuracy and comprehensiveness of the judgment. When determining the supplementary extraction flow rate, the relationship between the flow rate extracted by the pump extraction component and the actual weight of the narcotic drug can be determined in the form of a linear function, and the supplementary extraction flow rate can be determined through a conditional function. In the case where the weight error of the narcotic drug is large, the flow weighing function is used to determine the flow rate corresponding to the weight error of the narcotic drug, and the supplementary extraction flow rate is obtained to compensate for the weight error of the narcotic drug and improve the extraction accuracy of the narcotic drug. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of an anesthesia dispensing robot according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0009] Figure 1 A schematic diagram of an anesthesia dispensing robot according to an embodiment of the present invention is exemplarily shown, wherein the anesthesia dispensing robot comprises: Robot main structure and moving components; The mobile component is used to carry the robot main structure and move it, and the robot main structure includes a robot shell, and a drug storage area, a drug taking component, a drug review component, a drug preparation component, a display component, an input component and a processor are arranged in the robot shell; The drug storage area includes a plurality of storage partitions, each storage partition is used to store a type of narcotic drugs; The drug taking component is used to take at least one type of narcotic drug from the drug storage area according to the drug taking instruction of the processor; The drug review component is used to weigh the amount of anesthetic drugs taken to determine whether the amount taken is consistent with the drug taking instruction; The drug preparation component is used to mix the taken anesthetic drugs and prepare anesthetic drug medical equipment when the amount of anesthetic drugs taken is consistent with the drug taking instruction; The processor is used to: Generate narcotic drug dispensing information based on patient information and doctor information collected by the input component; Displaying the narcotic drug dispensing information via a display component; After receiving the doctor's confirmation information on the narcotic drug dispensing information through the input component, the drug taking instruction is generated.

[0010] According to the anesthesia dispensing robot of the embodiment of the present invention, it can generate recommended anesthetic drug dispensing information based on patient information and doctor information, and generate drug taking instructions after the doctor's confirmation, so that based on the doctor's modification and confirmation of the recommended anesthetic drug dispensing information, the recommended anesthetic drug dispensing information can be further optimized to improve the accuracy of the recommendation. When dispensing based on the drug taking instructions, the drug review component can be used to review the amount of anesthetic drugs taken to improve the accuracy and safety of dispensing.

[0011] According to one embodiment of the present invention, the mobile component can be a wheeled mobile component or a tracked mobile component, the mobile component can carry the robot main structure, the robot main structure can be covered by the robot shell, and a drug storage area, a drug retrieval component, a drug review component, a drug preparation component, a display component, an input component and a processor can be arranged in the robot shell.

[0012] According to one embodiment of the present invention, the partition of the drug storage area may be a medicine bottle storing one type of anesthetic drugs, the drug taking component may be a high-precision pump capable of extracting liquid drugs, and may take anesthetic drugs according to the amount described in the drug taking instruction, and output the taken anesthetic drugs to the drug review component. Each drug storage area may correspond to a drug review component, and the drug review component may be a precision weighing component, which may weigh the weight of the taken drugs and determine whether the weight is consistent with the drug taking instruction. The drug preparation component may mix the taken anesthetic drugs when the amount of anesthetic drugs taken is consistent with the drug taking instruction, and make the mixed drugs into anesthetic medical devices, for example, syringes that have extracted anesthetic drugs, etc. The present invention does not limit the specific types of anesthetic medical devices.

[0013] According to one embodiment of the present invention, when medication is needed, the doctor can input patient information and doctor information through an input component (e.g., a keyboard or a touch screen, etc.), and the processor can generate recommended anesthetic drug dispensing information based on the patient information and the doctor information. For example, the anesthetic drug dispensing information can be recommended based on the doctor's medication habits and the patient's physical condition, etc.

[0014] According to one embodiment of the present invention, narcotic drug dispensing information is generated based on the patient information and doctor information collected by the input component, including: determining the patient's physiological indicator data based on the patient information; determining the doctor's identity information based on the doctor's information; training a narcotic drug dosage prediction model based on the doctor's identity information and the patient's physiological indicator data to obtain a trained narcotic drug dosage prediction model; inputting the patient's physiological indicator data and the doctor's identity information into the trained narcotic drug dosage prediction model to obtain narcotic drug dispensing information.

[0015] According to one embodiment of the present invention, the narcotic drug dosage prediction model can simulate the doctor's medication habits, thereby generating recommended narcotic drug dispensing information based on the doctor's medication habits and the patient's physiological index data (for example, height, weight, blood pressure, blood sugar, previous medical history, etc.). In addition, before each recommendation, training can be performed based on historical data and the current doctor's doctor information and the patient's physiological index data, so as to obtain a trained narcotic drug dosage prediction model that better matches the current doctor's medication habits, and can recommend narcotic drug dispensing information that better matches the current doctor's medication habits.

[0016] According to one embodiment of the present invention, a narcotic drug dosage prediction model is trained based on the doctor's identity information and the patient's physiological indicator data to obtain the trained narcotic drug dosage prediction model, including: obtaining the identity information corresponding to the sample doctor information; obtaining the correlation coefficient between the sample doctor information and the doctor information; obtaining the sample patient information corresponding to the sample doctor information; determining the sample physiological indicator data of the sample patient based on the sample patient information; obtaining the sample doctor information for the sample patient's sample drug taking instructions; inputting the sample doctor's identity information and the sample physiological indicator data of the sample patient into the narcotic drug dosage prediction model to obtain the sample narcotic drug dispensing information; obtaining the loss function of the narcotic drug dosage prediction model based on the sample narcotic drug dispensing information, the sample drug taking instructions, the correlation coefficient, the sample physiological indicator data and the physiological indicator data; training the narcotic drug dosage prediction model based on the loss function of the narcotic drug dosage prediction model to obtain the trained narcotic drug dosage prediction model.

[0017] According to an embodiment of the present invention, in the database of historical data, there is sample doctor information of multiple doctors, which may include the current doctor and other doctors, and the identity information corresponding to each sample doctor information can be obtained. Furthermore, the correlation coefficient between each doctor and the current doctor can be obtained. For example, if a doctor and the current doctor are in a teacher-student relationship, then the medication habits of the two are similar, and the historical data of the doctor has a high reference value for predicting the medication habits of the current doctor.

[0018] According to an embodiment of the present invention, obtaining the correlation coefficient between the sample doctor information and the doctor information includes: determining the correlation coefficient between the i-th sample doctor information and the doctor information according to formula (1): , (1) in, is the sample physiological index vector composed of the sample physiological index data of the jth sample patient corresponding to the i-th sample doctor information, for The transposed vector of is the historical physiological index vector composed of the physiological index data of the sth historical patient information corresponding to the doctor information, Based on The dosage vector composed of the dosage data of multiple narcotic drugs obtained from the sample drug taking instructions of the sample patient with the maximum value, for The transposed vector of Based on A dosage vector consisting of dosage data of multiple anesthetic drugs obtained from the drug taking instructions of historical patients with the maximum value, is the number of historical patient information corresponding to the doctor information, is the number of sample patients corresponding to the i-th sample doctor information, s≤ , j≤ , and s, , j and All are positive integers.

[0019] According to one embodiment of the present invention, is the cosine similarity between the physiological index vector of the jth sample patient corresponding to the i-th sample doctor information and the historical physiological index vector of the s-th historical patient information corresponding to the doctor information of the current doctor, It represents the maximum similarity between the historical physiological index vector of the patients treated by the current doctor and the physiological index vector of the patients treated by the i-th doctor, that is, the similarity between the most similar patients treated by the two doctors. It represents the cosine similarity of the dosage vector of anesthetic drugs used by the current doctor and the ith doctor when treating the most similar patients, that is, the similarity of medication between the two when treating the most similar patients. By multiplying the above two items, the similarity of medication habits between the ith doctor and the current doctor when treating the most similar patients can be determined. When the similarity is high, it means that the medication habits of the ith doctor and the current doctor are similar, and the correlation between the ith doctor and the current doctor is high, which may be a teacher-student relationship, etc. The medication data of the ith doctor has a greater reference value for predicting the medication habits of the current doctor. Therefore, the similarity can be determined as the correlation coefficient between the ith sample doctor information and the doctor information. Similarly, the correlation coefficient between each sample doctor information and the doctor information can be calculated.

[0020] In this way, the similarity of medication usage between each doctor and the current doctor when treating similar patients can be calculated, thereby determining the correlation coefficient between the sample doctor information and the doctor information, which is used to accurately describe the similarity of medication habits between each doctor and the current doctor, as well as the reference value of each doctor's medication data for predicting the current doctor's medication habits.

[0021] According to one embodiment of the present invention, sample doctor information and sample drug taking instructions for sample patients, that is, drug dosage information after modification and confirmation by the doctor, can be obtained. In addition, the identity information of the sample doctor and the sample physiological index data of the sample patient can be input into the narcotic drug dosage prediction model to obtain sample narcotic drug dispensing information, thereby using the sample drug taking instructions as the annotation information, determining the error between the sample narcotic drug dispensing information and the annotation information, and thus determining the loss function of the narcotic drug dosage prediction model.

[0022] According to one embodiment of the present invention, the loss function of the narcotic drug dosage prediction model is obtained based on the sample narcotic drug dispensing information, the sample drug taking instruction, the correlation coefficient, the sample physiological indicator data and the physiological indicator data, including: obtaining the loss function of the narcotic drug dosage prediction model according to formula (2): , (2) in, is the correlation coefficient between the i-th sample doctor information and the doctor information, is the sample physiological index vector composed of the sample physiological index data of the jth sample patient corresponding to the i-th sample doctor information, for The transposed vector of , P is the physiological index vector composed of physiological index data, is the dosage data of the kth narcotic drug obtained based on the i-th sample doctor information and the sample drug taking instruction of the j-th sample patient, is the dosage data of the kth narcotic drug obtained based on the i-th sample doctor information and the sample narcotic drug dispensing information of the j-th sample patient, and are all preset coefficients greater than 1, and is the logical operator of "and", if is the conditional function, M is the number of sample doctor information, is the number of sample patients corresponding to the i-th sample doctor information, n is the number of types of anesthetic drugs, k≤n, j≤ , i≤M, and k, n, j, , i and M are all positive integers.

[0023] According to one embodiment of the present invention, in formula (2), the conditional function Indicated in In the case of , otherwise 0. Indicates that the dosage data of narcotic drugs in the sample drug taking instruction is 0, while the dosage data of narcotic drugs in the sample narcotic drug dispensing information is not 0, that is, the actual dosage of the narcotic drug used by the doctor is not 0, while the dosage of the narcotic drug predicted by the narcotic drug dosage prediction model is 0. It can be considered that the narcotic drug dosage prediction model predicts incorrectly. Therefore, the conditional function value can obtain a preset coefficient greater than 1. , otherwise 0. Conditional function Indicated in In the case of , otherwise 0. Indicates that the dosage data of narcotic drugs in the sample drug taking instruction is not 0, while the dosage data of narcotic drugs in the sample narcotic drug dispensing information is 0, that is, the actual dosage of the narcotic drug used by the doctor is 0, while the dosage of the narcotic drug predicted by the narcotic drug dosage prediction model is not 0. It can be considered that the narcotic drug dosage prediction model predicts incorrectly. Therefore, the conditional function value can obtain a preset coefficient greater than 1. , otherwise 0. Indicated in In the case of , otherwise 0. It means that the dosage data of narcotic drugs in the sample drug taking instruction is not 0, while the dosage data of narcotic drugs in the sample narcotic drug dispensing information is not 0, that is, the actual dosage of the narcotic drug used by the doctor is not 0, while the dosage of the narcotic drug predicted by the narcotic drug dosage prediction model is not 0. It can be considered that the prediction of the narcotic drug dosage prediction model is not wrong, but there may be a certain error. Therefore, the relative error between the two can be As the conditional function value. The above three conditional functions are added together to indicate that when the narcotic drug dosage prediction model makes an error in prediction, the sum of the added functions is greater than the preset coefficient of 1. or , when the narcotic drug dosage prediction model predicts no errors, the sum of the relative errors is less than 1 . Therefore, during the training process, when the prediction is wrong, the loss function value can be increased, the penalty intensity and training intensity can be increased, the training efficiency can be improved, and when the prediction is not wrong, the relative error can be reduced, and the prediction accuracy of the dosage of various anesthetic drugs can be improved. The above three conditional function values ​​of various anesthetic drugs can be summed to obtain the total error of the dosage of various anesthetic drugs for the jth sample patient based on the i-th sample doctor information.

[0024] According to one embodiment of the present invention, It is the cosine similarity between the sample physiological indicator vector of the jth sample patient corresponding to the ith sample doctor information and the physiological indicator item vector of the current patient, that is, the similarity between the physical condition of the jth sample patient corresponding to the ith sample doctor information and the current patient. The higher the similarity, the greater the reference value of the dosage data of various anesthetic drugs of the jth sample patient corresponding to the ith sample doctor information for predicting the dosage data of various anesthetic drugs of the current patient. Therefore, the cosine similarity can be used as the weight of the total error of the dosage of various anesthetic drugs of the jth sample patient for the ith sample doctor information, so as to perform weighted summation to obtain the medication prediction error for the ith doctor.

[0025] According to one embodiment of the present invention, is the correlation coefficient between the ith doctor and the current doctor. The higher the correlation coefficient, the higher the reference value of the ith doctor's medication habits for predicting the current doctor's medication habits. Therefore, As the weight of the medication prediction error of the i-th doctor, a weighted sum is performed to obtain the prediction error of each doctor's medication, which can be used as the loss function of the anesthetic drug dosage prediction model. Furthermore, back propagation can be performed based on the loss function to adjust the parameters of the anesthetic drug dosage prediction model. After multiple trainings, a trained anesthetic drug dosage prediction model is obtained.

[0026] In this way, the dosage error when the narcotic drug dosage prediction model predicts correctly or incorrectly can be determined through the conditional function, and the reference value of historical data for predicting the current doctor's medication habits can be determined based on the similarity between the physical condition of the sample patient and the current patient and the correlation coefficient between the sample doctor information and the current doctor's information, thereby obtaining the loss function of the narcotic drug dosage prediction model, which can be used to train historical data with high reference value in a targeted manner, thereby improving the training efficiency and the accuracy of the narcotic drug dosage prediction model.

[0027] According to one embodiment of the present invention, after obtaining the trained narcotic drug dosage prediction model, the doctor information of the current doctor and the physiological index data of the current patient can be input into the trained narcotic drug dosage prediction model to obtain narcotic drug dispensing information, that is, the dosage of multiple narcotic drugs recommended by the trained narcotic drug dosage prediction model. The narcotic drug dispensing information can be displayed on the display component. After viewing the narcotic drug dispensing information, the doctor can modify and confirm it through the input component. After receiving the doctor's confirmation information on the narcotic drug dispensing information (or the modified narcotic drug dispensing information), a drug taking instruction is generated, which can be used to indicate the dosage of multiple narcotic drugs that the doctor believes is accurate. The drug taking component can take at least one narcotic drug according to the drug taking instruction.

[0028] According to one embodiment of the present invention, after taking narcotic drugs, the amount of various narcotic drugs taken can be reviewed by a drug review component. The drug review component is used to: weigh the weights of multiple narcotic drugs and send them to a processor; the processor is used to: determine the usage weights of multiple narcotic drugs according to the drug taking instruction; set multiple judgment conditions according to the usage weights and the weights of the multiple narcotic drugs; and determine that the amount of narcotic drugs taken is inconsistent with the drug taking instruction when at least one of the multiple judgment conditions is met.

[0029] According to an embodiment of the present invention, a plurality of judgment conditions are set according to the usage weight and the weight of the plurality of anesthetic drugs, including: obtaining judgment conditions C1, C2 and C3 according to formula (3), (3) in, for The standard deviation of is the weight of the kth narcotic drug used, is the weight of the kth narcotic drug, max is the maximum value function, if is the conditional function, , , , is the preset coefficient, n is the number of types of narcotic drugs, k≤n, and k and n are both positive integers.

[0030] According to one embodiment of the present invention, in formula (3), the judgment condition C1 indicates that the standard deviation of the relative deviation between the used weight and the actual weight of the anesthetic drug is large, that is, greater than or equal to the preset coefficient In this case, the errors of the weights of various anesthetic drugs are large and the error levels vary, making it difficult to obtain accurate doses of anesthetic drugs. Judgment condition C2 indicates that the maximum value of the relative deviation between the used weight and the actual weight is large, that is, greater than or equal to the preset coefficient , indicating that there is a large error between the actual weight and the used weight of at least one anesthetic drug, and the amount of anesthetic drug taken is inaccurate. In the judgment condition C3, the conditional function Indicated in , the conditional function value is 1, otherwise it is 0, so If the relative deviation between the used weight and the actual weight is large (i.e., greater than or equal to the preset coefficient ) of narcotic drugs, The percentage of narcotic drugs with a large relative deviation between the used weight and the actual weight. If the percentage is greater than or equal to the preset coefficient , it means that the types and quantities of inaccurately taken narcotic drugs are too many. When at least one of the above three judgment conditions is met, it is determined that the amount of narcotic drugs taken is inconsistent with the drug taking instruction, and the amount of narcotic drugs taken needs to be adjusted.

[0031] In this way, the standard deviation of the error between the actual weight of narcotic drugs and the used weight, the maximum error, and the number and types of inaccurately taken narcotic drugs can be used to judge whether the amount of narcotic drugs taken is consistent with the drug taking instructions, thereby improving the accuracy and comprehensiveness of the judgment.

[0032] According to one embodiment of the present invention, the drug taking component includes a pump extraction component, and the drug review component includes a weighing component; the processor is also used to: when the amount of narcotic drugs taken is inconsistent with the drug taking instruction, obtain a flow weighing function according to the weights of multiple narcotic drugs obtained by the weighing component and the flow rates of multiple narcotic drugs extracted by the pump extraction component; obtain the supplementary extraction flow rates of multiple narcotic drugs according to the flow weighing function, the weights of the narcotic drugs and the drug taking instruction; and extract multiple narcotic drugs according to the supplementary extraction flow rates through the pump extraction component. That is, determine the relationship between the flow rate of narcotic drugs extracted by the pump extraction component and the actual weight of the narcotic drugs, and then determine how to supplement the flow rate of narcotic drugs based on the relationship so that the weight of the supplemented narcotic drugs reaches or approaches the usage weight of the narcotic drugs.

[0033] According to one embodiment of the present invention, when the amount of narcotic drugs taken is inconsistent with the drug taking instruction, a flow weighing function is obtained according to the weights of the multiple narcotic drugs obtained by the weighing component and the flow rates of the multiple narcotic drugs extracted by the pump extraction component, including: obtaining an undetermined coefficient equation of the flow weighing function according to formula (4), (4) in, is the flow rate of the kth narcotic drug, and is an undetermined coefficient; according to the flow rates and weights of a plurality of anesthetic drugs, the undetermined coefficient is solved to obtain a solution value of the undetermined coefficient; according to the solution value of the undetermined coefficient and the undetermined coefficient equation, a flow weighing function is obtained.

[0034] According to one embodiment of the present invention, in formula (4), in order to simplify the calculation and reduce the consumption of computing resources, the undetermined coefficient equation of the flow weighing function can be set in the form of a linear equation to express the relationship between the flow rate and the actual weight of the narcotic drug. The undetermined coefficient in the undetermined coefficient equation can be solved by the flow rate and actual weight of a variety of narcotic drugs to obtain the solution value of the undetermined coefficient, which can be substituted into the undetermined coefficient equation to obtain the flow weighing function to express the relationship between the flow rate and the actual weight of the narcotic drug.

[0035] According to one embodiment of the present invention, the supplementary extraction flow of multiple anesthetic drugs is obtained according to the flow weighing function, the weight of the anesthetic drug and the drug taking instruction, including: obtaining the supplementary extraction flow of the kth anesthetic drug according to formula (5): , (5) in, for The solution value of for The solution value of .

[0036] According to one embodiment of the present invention, in formula (5), the conditional function Indicated in In the case of , otherwise 0. That is, when the relative deviation between the used weight and the actual weight of the kth narcotic drug is greater than or equal to the preset coefficient (that is, the error between the used weight and the actual weight is large), the supplementary extraction flow rate is If the relative deviation between the used weight and the actual weight is less than the preset coefficient, no supplementary extraction is required, that is, the supplementary extraction flow rate is 0. In order to use the error between the weight and the actual weight, the error is substituted into the flow weighing function to obtain the flow corresponding to the error. To compensate for the error, the flow corresponding to the error can be supplemented by extraction, that is, the supplementary extraction flow.

[0037] In this way, the relationship between the flow rate extracted by the pump extraction component and the actual weight of the narcotic drug can be determined in the form of a linear function, and the supplementary extraction flow rate can be determined through a conditional function. In the case where the weight error of the narcotic drug is large, the flow rate corresponding to the weight error of the narcotic drug is determined by the flow weighing function, and the supplementary extraction flow rate is obtained to compensate for the weight error of the narcotic drug and improve the extraction accuracy of the narcotic drug.

[0038] According to one embodiment of the present invention, after the weights of multiple anesthetic drugs meet the requirements, the multiple drugs can be mixed through the drug preparation component to make anesthetic drug medical equipment such as syringes. In addition, the information of the doctor and the patient, as well as the drug taking instructions, can be entered into the historical database, so that other doctors can train the anesthetic drug dosage prediction model when using the anesthesia dispensing robot in the future, thereby more accurately predicting the medication habits of other doctors.

[0039] According to the anesthesia dispensing robot of the embodiment of the present invention, it can generate recommended anesthetic drug dispensing information based on patient information and doctor information, and generate drug taking instructions after the doctor confirms it, so that it can further optimize the recommended anesthetic drug dispensing information based on the doctor's modification and confirmation of the recommended anesthetic drug dispensing information, improve the accuracy of the recommendation, and can review the amount of anesthetic drugs taken by the drug review component when dispensing based on the drug taking instructions, so as to improve the accuracy and safety of the dispensing. When determining the correlation coefficient, the similarity of medication between each doctor and the current doctor when treating similar patients can be calculated, so as to determine the correlation coefficient between the sample doctor information and the doctor information, so as to accurately describe the similarity of medication habits between each doctor and the current doctor, and the reference value of each doctor's medication data for predicting the current doctor's medication habits. When training the narcotic drug dosage prediction model, the dosage error can be determined by the conditional function when the narcotic drug dosage prediction model predicts correctly or incorrectly, and the reference value of historical data for predicting the current doctor's medication habits can be determined based on the similarity between the physical condition of the sample patient and the current patient and the correlation coefficient between the sample doctor information and the current doctor's doctor information, thereby obtaining the loss function of the narcotic drug dosage prediction model, which can be targeted for training historical data with high reference value, improve training efficiency and the accuracy of the narcotic drug dosage prediction model. When determining the judgment conditions, the standard deviation of the error between the actual weight of the narcotic drug and the used weight, the maximum error, and the number of types of inaccurately taken narcotic drugs can be used to judge whether the amount of narcotic drugs taken is consistent with the drug taking instructions, thereby improving the accuracy and comprehensiveness of the judgment. When determining the supplementary extraction flow rate, the relationship between the flow rate extracted by the pump extraction component and the actual weight of the narcotic drug can be determined in the form of a linear function, and the supplementary extraction flow rate can be determined through a conditional function. In the case where the weight error of the narcotic drug is large, the flow weighing function is used to determine the flow rate corresponding to the weight error of the narcotic drug, and the supplementary extraction flow rate is obtained to compensate for the weight error of the narcotic drug and improve the extraction accuracy of the narcotic drug.

Claims

1. An anesthesia dispensing robot, characterized in that: include: Robot main structure and moving components; The mobile component is used to carry the robot main structure and move it, and the robot main structure includes a robot shell, and a drug storage area, a drug taking component, a drug review component, a drug preparation component, a display component, an input component and a processor are arranged in the robot shell; The drug storage area includes a plurality of storage partitions, each storage partition is used to store a type of narcotic drugs; The drug taking component is used to take at least one type of narcotic drug from the drug storage area according to the drug taking instruction of the processor; The drug review component is used to weigh the amount of anesthetic drugs taken to determine whether the amount taken is consistent with the drug taking instruction; The drug preparation component is used to mix the taken anesthetic drugs and prepare anesthetic drug medical equipment when the amount of anesthetic drugs taken is consistent with the drug taking instruction; The processor is used to: Generate narcotic drug dispensing information based on patient information and doctor information collected by the input component; Displaying the narcotic drug dispensing information via a display component; After receiving the doctor's confirmation information on the narcotic drug dispensing information through the input component, the drug taking instruction is generated.

2. The anesthesia dispensing robot according to claim 1, characterized in that: Generate narcotic drug dispensing information based on the patient information and doctor information collected by the input component, including: Determine the patient's physiological index data according to the patient information; Determine the identity information of the doctor according to the doctor information; According to the doctor's identity information and the patient's physiological index data, the narcotic drug dosage prediction model is trained to obtain a trained narcotic drug dosage prediction model; The patient's physiological index data and the doctor's identity information are input into the trained narcotic drug dosage prediction model to obtain narcotic drug dispensing information.

3. The anesthesia dispensing robot according to claim 2, characterized in that: According to the doctor's identity information and the patient's physiological index data, the narcotic drug dosage prediction model is trained to obtain the trained narcotic drug dosage prediction model, including: Obtain the identity information corresponding to the sample doctor information; Obtaining a correlation coefficient between the sample doctor information and the doctor information; Obtain sample patient information corresponding to sample doctor information; Determine sample physiological index data of the sample patient according to the sample patient information; Obtain sample doctor information to give sample patient sample medication taking instructions; Inputting the identity information of the sample doctors and the sample physiological index data of the sample patients into the narcotic drug dosage prediction model to obtain the sample narcotic drug dispensing information; Obtaining a loss function of a narcotic drug dosage prediction model based on the sample narcotic drug dispensing information, the sample drug taking instruction, the correlation coefficient, the sample physiological index data, and the physiological index data; The narcotic drug dosage prediction model is trained according to the loss function of the narcotic drug dosage prediction model to obtain the trained narcotic drug dosage prediction model.

4. The anesthesia dispensing robot according to claim 3, characterized in that: Obtaining the correlation coefficient between the sample doctor information and the doctor information includes: According to the formula ; Determine the correlation coefficient between the i-th sample doctor information and the doctor information ,in, is the sample physiological index vector composed of the sample physiological index data of the jth sample patient corresponding to the i-th sample doctor information, for The transposed vector of is the historical physiological index vector composed of the physiological index data of the sth historical patient information corresponding to the doctor information, Based on The dosage vector composed of the dosage data of multiple narcotic drugs obtained from the sample drug taking instructions of the sample patient with the maximum value, for The transposed vector of Based on A dosage vector consisting of dosage data of multiple anesthetic drugs obtained from the drug taking instructions of historical patients with the maximum value, is the number of historical patient information corresponding to the doctor information, is the number of sample patients corresponding to the i-th sample doctor information, s≤ , j≤ , and s, 、j、 All are positive integers.

5. The anesthesia dispensing robot according to claim 3, characterized in that: According to the sample anesthetic drug dispensing information, the sample drug taking instruction, the correlation coefficient, the sample physiological index data and the physiological index data, a loss function of the anesthetic drug dosage prediction model is obtained, including: According to the formula ; Obtain the loss function of the narcotic drug dosage prediction model ,in, is the correlation coefficient between the i-th sample doctor information and the doctor information, is the sample physiological index vector composed of the sample physiological index data of the jth sample patient corresponding to the i-th sample doctor information, for The transposed vector of , P is the physiological index vector composed of physiological index data, is the dosage data of the kth narcotic drug obtained based on the i-th sample doctor information and the sample drug taking instruction of the j-th sample patient, is the dosage data of the kth narcotic drug obtained based on the i-th sample doctor information and the sample narcotic drug dispensing information of the j-th sample patient, and are all preset coefficients greater than 1, and is the logical operator of "and", if is the conditional function, M is the number of sample doctor information, is the number of sample patients corresponding to the i-th sample doctor information, n is the number of types of anesthetic drugs, k≤n, j≤ , i≤M, and k, n, j, , i and M are all positive integers.

6. The anesthesia dispensing robot according to claim 1, characterized in that: The drug review component is used to: Weighs and sends various narcotic drugs to processors; The processor is used to: Determining the weight of multiple narcotic drugs to be used according to the drug taking instructions; Setting a plurality of judgment conditions according to the usage weight and the weights of the plurality of anesthetic drugs; When at least one of the plurality of judgment conditions is satisfied, it is determined that the amount of narcotic drugs taken is inconsistent with the drug taking instruction.

7. The anesthesia dispensing robot according to claim 6, characterized in that: According to the usage weight and the weight of the plurality of anesthetic drugs, a plurality of judgment conditions are set, including: According to the formula ; Obtain judgment conditions C1, C2 and C3, where: for The standard deviation of is the weight of the kth narcotic drug used, is the weight of the kth narcotic drug, max is the maximum value function, if is the conditional function, , , , is the preset coefficient, n is the number of types of narcotic drugs, k≤n, and k and n are both positive integers.

8. The anesthesia dispensing robot according to claim 7, characterized in that: The medicine taking component includes a pump extraction component, and the medicine review component includes a weighing component; The processor is further configured to: In the case where the amount of narcotic drugs taken is inconsistent with the drug taking instruction, a flow weighing function is obtained according to the weights of the multiple narcotic drugs obtained by the weighing component and the flow rates of the multiple narcotic drugs extracted by the pump extraction component; Obtaining supplementary extraction flows of a plurality of anesthetic drugs according to the flow weighing function, the weight of the anesthetic drugs and the drug taking instruction; A variety of anesthetic drugs are extracted by the pump-type extraction component according to the supplementary extraction flow rate.

9. The anesthesia dispensing robot according to claim 8, characterized in that: In the case that the amount of narcotic drugs taken is inconsistent with the drug taking instruction, a flow weighing function is obtained according to the weights of the multiple narcotic drugs obtained by the weighing component and the flow rates of the multiple narcotic drugs extracted by the pump extraction component, including: According to the formula ; The undetermined coefficient equation of the flow weighing function is obtained, where: is the flow rate of the kth narcotic drug, and is the undetermined coefficient; according to the flow rates of the various anesthetic drugs and the weights of the various anesthetic drugs, the undetermined coefficient is solved to obtain the solution value of the undetermined coefficient; A flow weighing function is obtained according to the solved value of the undetermined coefficient and the undetermined coefficient equation.

10. The anesthesia dispensing robot according to claim 9, characterized in that: According to the flow weighing function, the weight of the anesthetic drug and the drug taking instruction, the supplementary extraction flow of multiple anesthetic drugs is obtained, including: According to the formula ; Get the supplementary extraction flow of the kth anesthetic drug ,in, for The solution value of for The solution value of .

Images