Control and detection method for liquid drug dispensing device

Abstract

The present application relates to the field of control and detection of liquid drug dispensing, and specifically to a control and detection method applied to a liquid drug dispensing device. A specific implementation of the method includes: controlling a liquid drug extraction device corresponding to the liquid drug type to extract liquid drugs from a corresponding liquid drug library; in response to determining that the liquid drug extraction is complete, controlling the liquid drug extraction device to input the extracted liquid drug into a liquid medicine storage tube, and controlling an image acquisition device to capture a real-time video of the drug outflow at the drug outlet pipe of the liquid drug extraction device, wherein the drug outlet pipe of the liquid drug extraction device is in a transparent state, and the liquid medicine storage tube is in a transparent state; determining whether the liquid drug is inputted, and generating drug configuration completion information in response to determining that the liquid drug input is complete. This implementation improves the accuracy and efficiency of liquid drug dispensing configuration, and improves the efficiency and safety of liquid medicine extraction.

Description

Technical Field

[0001] The present application relates to the field of control and detection of flowable drug dispensing, and specifically to a control and detection method applied to a flowable drug dispensing device. Background Art

[0002] In fields such as medicine and pharmacy, liquid medicine extraction devices play a vital role. In medical scenarios, accurately extracting liquid medicine is a key link in drug treatment. When it comes to the extraction of some liquid medicines in hospitals, it is necessary to strictly follow the dispensing recommendations for treatment. For example, nurses often need to extract drugs for treatment during nursing operations, and the accuracy of their extraction directly affects the treatment effect and safety of patients. The traditional manual drug extraction method is inefficient, and the liquid medicine may be contaminated due to improper operation, posing certain safety hazards. In addition, the liquid medicine extraction process is not monitored, and when extracting specific liquid medicines, such as oils, insoluble powders, etc., it is difficult to extract them completely, resulting in inaccurate drug extraction.

[0003] As for the administration of liquid medicines, most of the medicines used by children in clinical practice are liquid medicines. At present, the extraction of liquid medicines mainly adopts a dropper or bottle cap with a scale. However, if the force is not well controlled when using a dropper, it is easy to pour too much or too little, and the bottle cap with a scale has the same problem. This inaccurate way of taking medicine may not only affect the treatment effect, but also cause waste and pollution of liquid medicine. This study aims to explore the control and detection methods of the liquid medicine dispensing device to improve the efficiency and safety of liquid medicine extraction. Summary of the invention

[0004] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0005] Some embodiments of the present application propose control and detection methods, computer equipment, and computer-readable storage media applied to a flowable drug dispensing device to solve the technical problems mentioned in the above background technology section.

[0006] In a first aspect, some embodiments of the present application provide a control and detection method for a liquid drug dispensing device, the method comprising: in response to receiving a drug configuration instruction corresponding to a target user, obtaining diagnosis and treatment information and a pre-set judgment rule information set corresponding to the above-mentioned target user; performing indicator format conversion on the judgment indicators in the above-mentioned diagnosis and treatment information to obtain judgment indicator conversion information, and performing format conversion on the judgment words in the above-mentioned diagnosis and treatment information to obtain judgment word conversion information; selecting target judgment rule information that meets the target judgment conditions from the above-mentioned judgment rule information set, wherein the above-mentioned target judgment rule information comprises: judgment indicator rule information and judgment word rule information, there is an association relationship between the above-mentioned judgment indicator conversion information and the above-mentioned judgment indicator rule information, and there is an association relationship between the above-mentioned judgment word conversion information and the above-mentioned judgment word rule information; determining the diagnosis and treatment judgment information corresponding to the above-mentioned target judgment rule information, and in response to determining that the above-mentioned diagnosis and treatment judgment information is consistent with the previous historical diagnosis and treatment judgment information, according to the target user corresponding to the above-mentioned A historical judgment associated information sequence is used to generate drug dispensing configuration information corresponding to the target user, wherein the drug dispensing configuration information includes: liquid drug name, drug dosage, and liquid drug type; a liquid drug extraction device corresponding to the liquid drug type is controlled to extract liquid drugs from the corresponding liquid drug library; in response to determining that the liquid drug extraction is completed, the liquid drug extraction device is controlled to input the extracted liquid drugs into the associated liquid medicine storage tube, and the associated image acquisition device is controlled to capture the drug outflow video at the drug outlet tube of the liquid drug extraction device in real time, wherein the drug outlet tube of the liquid drug extraction device is in a transparent state, the liquid medicine storage tube is in a transparent state and has a dosage scale, and the liquid medicine storage tube is placed on a weight monitoring device; according to the drug outflow video and the weight data sequence monitored by the weight monitoring device, it is determined whether the liquid drug input is completed, and in response to determining that the liquid drug input is completed, drug configuration completion information is generated.

[0007] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the method described in any implementation of the first aspect.

[0008] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0009] The above-mentioned embodiments of the present application have the following beneficial effects: the control and detection method for the flowable drug dispensing device provided by the present application improves the accuracy and efficiency of the flowable drug dispensing configuration. On the basis of pre-setting the judgment word rule information set, the target judgment rule information is screened through the judgment indicator format conversion and the judgment word format conversion, which can generate the corresponding diagnosis and treatment information in a lightweight and efficient manner, allowing user patients to be diagnosed and treated more quickly. Thus, the accuracy of the flowable drug dispensing can be guaranteed and dosage deviation can be avoided. In addition, the precise extraction of the liquid medicine can be achieved by using automation technology to reduce the error and contamination risk caused by manual operation. At the same time, different liquid medicine extraction devices are selected for different types of liquid medicines. For example, for oily agents, the residue can be reduced by letting the liquid medicine on the bottle wall to converge. For poorly soluble powders, the negative pressure method or the pre-shock negative pressure method can be used to improve the dissolution rate and extraction effect. Through these measures, the efficiency and safety of liquid medicine extraction are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar figure labels represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0011] Figure 1 is a flow chart of some embodiments of a control and detection method applied to a flowable drug dispensing device according to the present application;

[0012] Figure 2 It is a schematic diagram of the structure of a computer device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0013] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0014] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0015] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0016] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0017] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0018] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0019] Figure 1 1 is a flowchart of some embodiments of the control and detection method for a flowable drug dispensing device according to the present application. 100 of some embodiments of the control and detection method for a flowable drug dispensing device according to the present application is shown. The control and detection method for a flowable drug dispensing device includes the following steps:

[0020] Step 101, in response to receiving a drug configuration instruction corresponding to a target user, obtaining diagnosis and treatment information corresponding to the target user and a preset determination rule information set.

[0021] In some embodiments, the execution subject (e.g., computer device) of the control and detection method applied to the liquid drug dispensing device can obtain the diagnosis and treatment information and the pre-set judgment rule information set corresponding to the target user in response to receiving the drug configuration instruction corresponding to the target user. The above-mentioned diagnosis and treatment information includes: a user body data set and a historical judgment information set. The target user may refer to a patient who is currently being diagnosed and needs to be dispensed. The drug configuration instruction may refer to an instruction to configure a liquid drug (liquid, oil, insoluble powder) for the target user. The diagnosis and treatment information may be the diagnosis and treatment result after the target user is examined. The diagnosis and treatment information may be the result of the visit after data structuring in advance. That is, the diagnosis and treatment information may be data after structured processing in the HIS system. The judgment rule information (diagnosis rule information) may be rule information for determining the diagnosis and treatment information based on the diagnosis and treatment information result. The judgment rule information includes: judgment indicator rule information and judgment word rule information. The judgment indicator rule information may be the indicator value requirement condition corresponding to each judgment indicator. The judgment indicator may refer to a diagnostic indicator. The judgment word may refer to a diagnostic word. For example, for the indicator 1, the corresponding judgment indicator rule information may be "requirement that the corresponding value of judgment indicator A is greater than 5". The judgment word rule information may be the numerical requirement conditions corresponding to each judgment word. For example, for the judgment word 1, the corresponding judgment word rule information may be "requirement that the corresponding value of judgment word A is greater than 20%". The judgment indicator corresponding to the indicator rule information corresponds to the judgment word rule information corresponding to the judgment word. The judgment rule information may represent the disease condition of the user and the diagnosis and treatment information corresponding to the corresponding disease condition. The judgment word is usually a descriptive word involving the naming and classification of the disease. For example: pressure injury, burns, etc. The judgment indicator is a specific body data. For example, blood sugar concentration value, weight, age, gender, systolic blood pressure, diastolic blood pressure measurement value, etc. The judgment rule information set may be a rule information set pre-configured for various judgment indicators and judgment words. The above-mentioned diagnosis and treatment information includes: a user body data set and a historical judgment information set. Among them, the user body data set may be the parameter data content corresponding to each body parameter. The user body data set may include: user age, user gender. The historical judgment information set is a judgment data set judged within a historical time period. The historical judgment information set may include: a historical disease data set. For example, historical disease data sets may include: genetic disease history data, current disease history data, surgical history data, and allergen data.

[0022] The judgment rule information includes: sub-rule information of numerical type, sub-rule information of judgment word type, sub-rule information of yin-yang type, sub-rule information of digital type, sub-rule information of positivity degree type, sub-rule information based on judgment word type and single numerical type, sub-rule information based on judgment word type and double numerical type, sub-rule information based on yin-yang type and numerical type, sub-rule information of body data type, and sub-rule information of disease history type.

[0023] Here, the determination rule information set is the rule information for periodic rule maintenance. That is, as the judgment requirements and indicator requirements corresponding to the medical terminal are updated, the judgment requirements and indicator requirements of the determination rule information set involved in the update are updated through the determination indicator mapping relationship table. The determination indicator mapping relationship table can characterize the mapping relationship between the determination indicators and determination words corresponding to the execution subject and the determination indicators and determination words in the doctor terminal. The sub-rule information of the numerical type can be the sub-rule information of the determination indicator and / or the determination word corresponding to the value range of the numerical type. The sub-rule information of the determination word type can be the rule information for determining whether there is a target determination word. The sub-rule information of the yin-yang type can be the rule information for the determination indicator or determination word to be the yin-yang type judgment. The sub-rule information of the digital type can be the rule information for the indicator to be the Roman numeral type judgment. The horse numeral represents the level corresponding to the determination indicator. The sub-rule information based on the determination word type and the single numerical type can be the rule information of the type under the determination word and numerical restriction. For example, the determination word is blood glucose concentration. The sub-rule information based on the determination word type and the double numerical type can be the rule information of the type under the determination word and two numerical restrictions. The sub-rule information based on the yin-yang type and the numerical type may be the sub-rule information under the restriction that the determination index corresponds to the yin-yang type and a single numerical value.

[0024] The sub-rule information of the physical data type may be the sub-rule information for the user's physical parameters. For example, it may include: gender and age. The sub-rule information of the medical history type may be the sub-rule information set for the user's existing medical history. For the setting of the sub-rule information of the medical history type, a set of disease standards ICD (International Classification of Diseases) may be maintained in the database to associate the hospital's diseases with the ICD. Then, when configuring the disease list, use the standard ICD code to record each disease. Finally, the sub-rule information composed of the standard ICD is stored in the library.

[0025] The judgment criteria for the generated sub-rule information is: using CollectionUtil.containsAny, whether the disease ICD list configured on the operation side (the side where the execution subject is located) contains any disease ICDCode synchronized from the HIS system.

[0026] Correspondingly, 8 types of setting contents are planned corresponding to the judgment words and judgment indicators, and the judgment words and judgment indicators can be set for the corresponding 8 types of contents on the corresponding pages in the medical consultation terminal.

[0027] For numerical types, you can use numbers to represent the results, such as blood pressure, diastolic blood pressure, body fat percentage, etc. The judgment conditions can be: greater than, less than, equal to, greater than or equal to, less than or equal to {set value}.

[0028] For the judgment word type, the medical professional phrase is used to describe the result. The judgment condition can be: equal to the set judgment word.

[0029] For positive and negative types, use positive or negative to describe the result. For example, HIV positive. The judgment condition is: equal to the set negative or positive.

[0030] For Roman numeral types, Roman numerals are used to describe the severity of the disease. The judgment condition can be: equal to the Roman numeral.

[0031] For positive types, the result is described using the positive degree. The judgment condition is: equal to the set positive degree.

[0032] For the predicate + single value type, it is the same as the value type, the difference is that the value describes the predicate.

[0033] The type of predicate + double value is the same as the type of predicate + single value. The difference is that there are two restricted values.

[0034] For positive / negative+value type, for example, the judgment condition is: (negative or positive)+set value.

[0035] Step 102, converting the determination index in the diagnosis and treatment information into an index format to obtain determination index conversion information, and converting the determination word in the diagnosis and treatment information into a format to obtain determination word conversion information.

[0036] In some embodiments, the above-mentioned execution entity can perform indicator format conversion on the judgment indicators in the above-mentioned diagnosis and treatment information to obtain judgment indicator conversion information, and perform format conversion on the judgment words in the above-mentioned diagnosis and treatment information to obtain judgment word conversion information. Among them, the indicator format conversion can be converted into the indicator format of the current corresponding match, and the indicator format is the same as the indicator corresponding format in the judgment rule information. The judgment word format conversion can be converted into the judgment word format of the current corresponding match, and the judgment word format is the same as the judgment word corresponding format in the judgment rule information. For example, the judgment indicators and judgment words in the above-mentioned diagnosis and treatment information can be converted into key-value pair set formats respectively to generate judgment indicator conversion data in the key-value pair set format and judgment word conversion data in the key-value pair set format. The key-value pair set format can be a Map data format.

[0037] In an actual application scenario, the execution subject may perform indicator format conversion on the determination indicator in the diagnosis and treatment information to obtain determination indicator conversion information, and perform format conversion on the determination word in the diagnosis and treatment information to obtain determination word conversion information through the following steps:

[0038] The first step is to obtain a preset determination indicator mapping relationship table. The determination indicator mapping relationship table can represent the mapping transformation relationship between the determination indicator and the determination word. That is, the determination indicator mapping relationship table includes: the mapping relationship corresponding to the determination indicator and the mapping relationship of the determination word.

[0039] The second step is to perform indicator mapping processing on the determination indicators in the diagnosis and treatment information according to the determination indicator mapping relationship table to obtain mapped determination indicators.

[0040] The third step is to perform a determination word mapping process on the determination words in the diagnosis and treatment information according to the determination indicator mapping relationship table to obtain a mapped determination word.

[0041] The fourth step is to transform the mapping judgment index and the mapping judgment word into a key-value pair set to generate judgment index transformation information and judgment word transformation information. The judgment index transformation information includes: judgment index sub-data in the form of each key-value pair, the judgment word transformation information includes: judgment word sub-data in the form of each key-value pair, and the judgment rule information is a regular expression.

[0042] Therefore, through the determination indicator mapping relationship table, the determination indicators and determination words are mapped and converted into key-value pairs, so as to unify the determination indicator format and the determination word format, which is convenient for determining the subsequent target determination rule information. Thus, it is convenient to screen the target determination rule information.

[0043] Step 103: Select target determination rule information that meets the target determination condition from the above determination rule information set.

[0044] In some embodiments, the execution subject may select target determination rule information that satisfies the target determination condition from the determination rule information set. The target determination rule information includes: determination indicator rule information and determination word rule information, and there is an association relationship between the determination indicator conversion information and the determination indicator rule information, and there is an association relationship between the determination word conversion information and the determination word rule information. The target determination condition may be that the determination indicator conversion information and the determination word conversion information satisfy at least one sub-condition in the determination rule information. That is, the determination rule information includes: at least one sub-condition. Each sub-condition corresponds to the determination indicator rule information or the determination word rule information. The association relationship between the determination indicator conversion information and the determination indicator rule information indicates that the corresponding data content of the determination indicator conversion information is substituted into the determination indicator rule information. The association relationship between the determination word conversion information and the determination word rule information indicates that the corresponding data content of the determination word conversion information is substituted into the determination word rule information. The determination indicator conversion information includes: determination indicator sub-data in the form of each key-value pair, and the determination word conversion information includes: determination sub-data in the form of each key-value pair, and the determination rule information is a determination rule expression. The determination indicator conversion information may be data in the form of a key-value pair set.

[0045] In an actual application scenario, the execution subject may select target determination rule information that meets the target determination condition from the determination rule information set through the following steps:

[0046] In the first step, for each determination rule information in the determination rule information set, the following processing steps are performed:

[0047] 1. For each determination indicator sub-data, substitute the determination indicator sub-data into the corresponding determination indicator condition in the corresponding rule expression to obtain the determination indicator comparison result. The determination indicator comparison result can be a comparison result of whether the data content corresponding to the determination indicator sub-data meets the determination indicator condition.

[0048] 2. For each judgment word sub-data, substitute the judgment word sub-data into the corresponding judgment word index condition in the above regular expression to obtain the judgment word comparison result. The judgment word comparison result can be a comparison result of whether the data content corresponding to the judgment word sub-data meets the judgment word index condition.

[0049] 3. Determine the number of the above-mentioned determination index comparison results that meet the determination index condition as the first number. The determination index condition may be a corresponding determination index requirement.

[0050] 4. Determine the number of the judgment word comparison results that meet the judgment index condition among the above judgment word comparison results as the second number.

[0051] 5. Generate a body data comparison result set corresponding to the above user body data set.

[0052] 6. Generate a historical judgment data comparison result set corresponding to the above historical judgment data set.

[0053] 7. Determine the number corresponding to each body data comparison result that meets the user's physical condition in the body data comparison result set as a third number.

[0054] 8. Determine the number corresponding to each historical determination data comparison result that meets the historical determination condition in the historical determination data comparison result set as a fourth number.

[0055] 9. For each determination rule information, perform weighted summation on the corresponding first quantity, the corresponding second quantity, the third quantity and the fourth quantity to generate a weighted value as a comprehensive determination index comparison result.

[0056] In the second step, the judgment rule information corresponding to the comprehensive judgment index comparison result as the target result is selected from the above judgment rule information set as the target judgment rule information. Among them, the target result can be the result value set for each judgment index comparison result and each judgment word comparison result, and the result meets the preset condition. In practice, the preset condition can be any pre-set condition that meets the application of the scenario. For example, the preset condition can be the target result with the highest ratio of judgment index comparison results and the highest ratio of judgment word comparison results.

[0057] For example, first, determine the proportion of the judgment indicator comparison results corresponding to the judgment indicator comparison results that represent that the data content meets the index conditions in each judgment indicator comparison result. Then, determine the proportion of the judgment word comparison results corresponding to the judgment word comparison results that represent that the data content meets the judgment conditions in each judgment word comparison result. After that, select the judgment rule information with the highest judgment indicator comparison result proportion and the highest judgment word comparison result proportion from the judgment rule information set as the target judgment rule information.

[0058] Step 104, determine the diagnosis and treatment judgment information corresponding to the above-mentioned target judgment rule information, and in response to determining that the above-mentioned diagnosis and treatment judgment information is consistent with the previous historical diagnosis and treatment judgment information, generate the drug dispensing configuration information corresponding to the above-mentioned target user according to the historical judgment association information sequence corresponding to the above-mentioned target user.

[0059] In some embodiments, the execution subject may determine the diagnosis and treatment judgment information corresponding to the target judgment rule information, and in response to determining that the diagnosis and treatment judgment information is consistent with the previous historical diagnosis and treatment judgment information, generate the drug dispensing configuration information corresponding to the target user according to the historical judgment association information sequence corresponding to the target user. Among them, the drug dispensing configuration information includes: the name of the liquid drug, the drug dosage, and the liquid drug type. That is, it is determined that the diagnosis and treatment judgment information is the same as the previous historical diagnosis and treatment judgment information. The drug dosage can indicate the amount of the liquid drug. The liquid drug type can indicate that the liquid drug is a liquid or powder type. For example, the drug dispensing dosage of the target user can be adjusted by the judgment information change value of the historical judgment association information sequence to obtain the drug dispensing configuration information. The judgment information change value may refer to the difference value of the change of the historical judgment indicator. The previous historical diagnosis and treatment judgment information may refer to the historical judgment information of the target user corresponding to the same disease last time. The historical judgment association information sequence is the same as the disease judgment corresponding to the previous historical diagnosis and treatment judgment information.

[0060] In an actual application scenario, the execution subject can generate the drug dispensing configuration information corresponding to the target user through the following steps:

[0061] The first step is to input the current weight information of the target user, the diagnosis and treatment judgment information, and the historical judgment related information sequence into the pre-trained drug delivery information prediction model to obtain drug delivery prediction information. Among them, the historical judgment related information includes: user historical weight information and historical judgment information. The drug delivery information prediction model can be a pre-trained time series model, which takes the current weight information of the target user, the diagnosis and treatment judgment information, and the historical judgment related information sequence as input, and takes drug delivery prediction information as output. For example, the time series model can be: autoregressive moving average model (ARMA), autoregressive integrated moving average model (ARIMA), vector autoregressive model (VAR), seasonal autoregressive integrated moving average model (SARIMA).

[0062] The second step is to send the drug dispensing prediction information to the associated review terminal, and in response to receiving the confirmation information corresponding to the drug dispensing prediction information sent by the review terminal, determine the drug dispensing configuration information corresponding to the target user with the drug dispensing prediction information. The review terminal may refer to a doctor's terminal or a terminal that confirms the drug dispensing prediction information.

[0063] Step 105 , controlling the flowable drug extraction device corresponding to the flowable drug type to extract the flowable drug from the corresponding flowable drug library.

[0064] In some embodiments, the above-mentioned execution subject can control the fluidity drug extraction device corresponding to the above-mentioned fluidity drug type to extract fluidity drugs from the corresponding fluidity drug library. That is, different fluidity drug types use different fluidity drug extraction devices. For example, the fluidity drug extraction device can be a liquid medicine extraction device (liquid medicine filling machine or liquid medicine transferor). The fluidity drug library can refer to a storage library for storing fluidity drugs corresponding to drug dispensing configuration information, which can be a medicine tank. For example, according to the drug dosage recorded in the drug dispensing configuration information of the target user, the fluidity drug extraction device can be controlled to extract the corresponding dosage of fluidity drugs from the corresponding fluidity drug library. It should be noted that when extracting fluidity drugs, the fluidity drug extraction device can increase the extracted dosage by one unit, that is, it can ensure that the fluidity drugs extracted once meet the demand in the case of residual loss due to wall hanging.

[0065] Step 106, in response to determining that the above-mentioned fluid drug extraction is completed, controlling the above-mentioned fluid drug extraction device to input the extracted fluid drug into the associated drug solution storage tube, and controlling the associated image acquisition device to capture real-time drug outflow video at the drug outlet pipe of the above-mentioned fluid drug extraction device.

[0066] In some embodiments, the execution subject may, in response to determining that the extraction of the fluid drug is complete, control the fluid drug extraction device to input the extracted fluid drug into the associated liquid medicine storage tube, and control the associated image acquisition device to capture the video of the drug outflow at the drug outlet tube of the fluid drug extraction device in real time. The drug outlet tube of the fluid drug extraction device is transparent, the liquid medicine storage tube is transparent and has a dosage scale, and the liquid medicine storage tube is placed on a weight monitoring device. The liquid medicine storage tube may be a medicine tube for storing fluid drugs for users. The weight monitoring device may be an electronic weighing device. The image acquisition device may be a camera for capturing the video of the drug outflow at the drug outlet tube of the fluid drug extraction device.

[0067] Step 107 , determining whether the fluidity drug input is completed based on the drug outflow video and the weight data sequence monitored by the weight monitoring device, and generating drug configuration completion information in response to determining that the fluidity drug input is completed.

[0068] In some embodiments, the execution subject may determine whether the input of the fluid drug is complete based on the video of the drug outflow and the weight data sequence monitored by the weight monitoring device, and generate drug configuration completion information in response to determining that the input of the fluid drug is complete. For example, if the last weight data in the weight data sequence is less than the target weight, it is determined that the input of the fluid drug is not complete. For another example, if the last weight data in the weight data sequence is greater than or equal to the target weight, it is determined that the input of the fluid drug is complete. For another example, if the last frame of the image in the drug outflow video indicates that there is still fluid drug remaining, it indicates that the input of the fluid drug is not complete. The drug configuration completion information may indicate information on the completion of drug configuration, and may be automatically generated after determining that the input of the fluid drug is complete.

[0069] In an actual application scenario, the above execution entity can determine whether the liquid drug input is completed through the following steps:

[0070] In the first step, in response to determining that the last weight data in the weight data sequence is less than the target weight, the drug outflow video is framed to obtain a drug outflow video image sequence. The target weight is the sum of the drug outflow weight corresponding to the drug outflow configuration information and the net weight of the test tube for storing the drug solution. The drug outflow video can be framed to obtain a drug outflow video image sequence by using the video frame method of OpenCV.

[0071] In the second step, each drug outflow video image that meets the target image condition is selected from the above drug outflow video image sequence as the drug outflow video image group to be detected. The above target image condition is: the clarity of the drug outflow video image is greater than the preset clarity, and the position corresponding to the drug outflow video image is within the preset position interval. The preset position interval may refer to the position interval sorted in the last 5 frames in the drug outflow video image sequence.

[0072] The third step is to input the above-mentioned drug outflow video image group to be detected into a pre-trained drug residue status recognition model to obtain a drug residue status recognition result. The drug residue status recognition model can be a pre-trained neural network model that takes the drug outflow video image group to be detected as input and takes the drug residue status recognition result as output. The drug residue status recognition result can indicate whether there is drug residue in the drug outflow video image. The drug residue status recognition model can be a pre-trained target detection model, for example, the drug residue status recognition model can be a YOLOv7 model, an EfficientDet model, a RetinaNet model, or a CenterNet model.

[0073] In a fourth step, in response to determining that the drug residue status identification result indicates that there is drug residue, determining that the flowable drug input is incomplete.

[0074] The pre-trained drug residue state recognition model can be trained by the following steps:

[0075] The first step is to obtain a drug outflow video image sample set. The drug outflow video image sample includes: a sample drug outflow video image and a drug residue sample label. The drug residue sample label can indicate whether there is drug residue.

[0076] The second step is to determine the initial drug residue state recognition model. The initial drug residue state recognition model includes: an initial drug image feature extraction layer, an initial residual drug image contour extraction layer, an initial residual drug image area feature extraction layer, an initial multi-level drug image feature encoding layer, an initial feature fusion layer and an initial drug residue state recognition output layer. The initial drug image feature extraction layer can be used to extract the image features of the flowable drug in the sample drug outflow video image. The initial drug image feature extraction layer can be a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), etc. The initial residual drug image contour extraction layer can be an extraction network layer for extracting the residual drug area contour in the sample drug outflow video image. For example, the initial residual drug image contour extraction layer can be an edge detection layer. The initial residual drug image area feature extraction layer can be an extraction layer that takes the output of the initial residual drug image contour extraction layer as input and takes the residual drug image area feature as output. The initial residual drug image area feature extraction layer can be a convolutional neural network layer (CNN). The initial multi-level drug image feature encoding layer may include: an initial drug image feature encoding layer (encoder) and an initial drug image feature decoding layer (decoder), the initial drug image feature encoding layer includes: an initial drug image feature decoupling layer (including an autoencoder network, an LSTM network) and an initial drug image feature fusion layer (VAE (Variational AutoEncoder, variational encoder), the initial drug image feature fusion layer includes: an initial fusion layer, an initial reparameterization layer. The initial fusion layer may be a Feature Pyramid Network (FPN) or a Self-Attention Mechanism network. The initial reparameterization layer may include: DyRep (Dynamic Re-parameterization) and ACNet (Asymmetric Convolution Net). The initial drug residue state recognition output layer may be an output layer (OutputLayer) for outputting drug residue state recognition results. The initial feature fusion layer may be a feature fusion layer (Feature Fusion).

[0077] The third step is to train the initial drug residue state recognition model based on the drug outflow video image sample set to obtain a trained drug residue state recognition model.

[0078] The third step may include:

[0079] In the first sub-step, a drug outflow video image sample is selected from the drug outflow video image sample set as a target drug outflow video image sample.

[0080] In the second sub-step, the sample drug outflow video image included in the target drug outflow video image sample is input into the initial drug image feature extraction layer to obtain the initial drug image feature.

[0081] The third sub-step is to input the above initial drug image features into the initial multi-level drug image feature encoding layer to obtain the initial multi-level drug image features.

[0082] In a fourth sub-step, the sample drug outflow video image included in the target drug outflow video image sample is input into an initial residual drug image contour extraction layer to obtain at least one initial residual drug image contour feature.

[0083] The fifth sub-step is to input the at least one initial residual drug image contour feature into the initial residual drug image area feature extraction layer to obtain at least one initial residual drug image area feature.

[0084] The sixth sub-step is to input the above-mentioned initial multi-level drug image features and the above-mentioned at least one initial residual drug image area feature into the initial feature fusion layer to obtain the residual drug fusion feature.

[0085] The seventh sub-step is to input the above residual drug fusion features into the initial drug residual state recognition output layer to obtain the initial drug residual state recognition result.

[0086] The eighth sub-step is to determine the loss value between the above-mentioned initial drug residue state recognition result and the corresponding drug residue sample label. The loss value between the above-mentioned initial drug residue state recognition result and the corresponding drug residue sample label can be determined by a damage function. The loss function can be: mean square error loss (MSE Loss) function, cross-entropy loss (Cross-Entropy Loss) function, and mean absolute error (MAE) function.

[0087] A ninth sub-step, in response to determining that the above loss value is less than or equal to a preset loss value, determines the initial drug residue status recognition model as a trained drug residue status recognition model.

[0088] Therefore, the drug residue state recognition model constructed in this application can fully capture the multi-level information of the drug residue image area and enhance the efficiency and accuracy of the autoencoder in feature untangling. In addition, an initial drug residue state recognition output layer is constructed to help the model capture the complex nonlinear relationship of the drug residue image area and improve the accuracy of drug residue detection.

[0089] Further, in response to determining that the fluidity drug input is not completed, the residual drug extraction method corresponding to the fluidity drug type is determined, and according to the residual drug extraction method, the residual drug in the fluidity drug extraction device is extracted into the liquid medicine storage test tube, and it is determined whether the weight data monitored by the current weight monitoring device is greater than or equal to the target weight. For example, if the fluidity drug type represents a liquid medicine type, the residual drug in the fluidity drug extraction device can be pressed into the liquid medicine storage test tube by a negative pressure method. For another example, if the fluidity drug type represents an oily drug type, the residual drug in the fluidity drug extraction device can be pressed into the liquid medicine storage test tube by a method of allowing the liquid medicine on the bottle wall to be statically concentrated. For another example, if the fluidity drug type represents a poorly soluble powder type, the pre-shock negative pressure method can be used to press the residual drug in the fluidity drug extraction device into the liquid medicine storage test tube.

[0090] Further, in response to determining that the weight data currently monitored by the weight monitoring device is greater than or equal to the target weight, drug dispensing completion information is generated.

[0091] The present application also provides a computer device 200. Figure 2 As shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate with each other through the bus 201. The computer device 200 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 200.

[0092] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 201 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 201 may include a path for transmitting information between various components of the computer device 200 (for example, the memory 203, the processor 202, and the communication interface 204).

[0093] The processor 202 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0094] The memory 203 may include a volatile memory, such as a random access memory (RAM). The memory 203 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0095] The memory 203 stores executable program codes, and the processor 202 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby implementing the aforementioned control and detection method for the flowable drug dispensing device. That is, the memory 203 stores instructions for executing the aforementioned control and detection method for the flowable drug dispensing device.

[0096] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or a communication network.

[0097] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned control and detection method applied to the flowable drug dispensing device.

[0098] The embodiment of the present application also provides a computer-readable storage medium. The above-mentioned computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The above-mentioned available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk), etc. The computer-readable storage medium includes instructions, and the above-mentioned instructions instruct the computing device to execute the above-mentioned method for controlling and detecting the flowable drug dispensing device.

[0099] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A control and detection method for a flowable drug dispensing device, the method comprising: In response to receiving a drug configuration instruction corresponding to a target user, obtaining diagnosis and treatment information corresponding to the target user and a preset determination rule information set; Performing indicator format conversion on the determination indicator in the diagnosis and treatment information to obtain determination indicator conversion information, and performing format conversion on the determination word in the diagnosis and treatment information to obtain determination word conversion information; Selecting target determination rule information that meets the target determination condition from the determination rule information set, wherein the target determination rule information includes: determination indicator rule information and determination word rule information, there is an association relationship between the determination indicator conversion information and the determination indicator rule information, and there is an association relationship between the determination word conversion information and the determination word rule information; Determine the diagnosis and treatment determination information corresponding to the target determination rule information, and in response to determining that the diagnosis and treatment determination information is consistent with the previous historical diagnosis and treatment determination information, generate drug dispensing configuration information corresponding to the target user according to the historical determination association information sequence corresponding to the target user, wherein the drug dispensing configuration information includes: a liquid drug name, a drug dosage, and a liquid drug type; Controlling a flowable drug extraction device corresponding to the flowable drug type to extract the flowable drug from the corresponding flowable drug library; In response to determining that the fluid drug extraction is completed, controlling the fluid drug extraction device to input the extracted fluid drug into an associated drug solution storage tube, and controlling an associated image acquisition device to acquire a real-time drug outflow video at a drug outlet tube of the fluid drug extraction device, wherein the drug outlet tube of the fluid drug extraction device is in a transparent state, the drug solution storage tube is in a transparent state and has a dosage scale, and the drug solution storage tube is placed on a weight monitoring device; Determine whether the fluidity drug input is complete based on the drug outflow video and the weight data sequence monitored by the weight monitoring device, and generate drug configuration completion information in response to determining that the fluidity drug input is complete.

2. The control and detection method for a flowable drug dispensing device according to claim 1 is characterized in that: The step of generating drug dispensing configuration information corresponding to the target user according to the historical determination association information sequence corresponding to the target user includes: Inputting the target user's current weight information, the diagnosis and treatment judgment information and the historical judgment association information sequence into a pre-trained drug dispensing information prediction model to obtain drug dispensing prediction information, wherein the historical judgment association information includes: user historical weight information and historical judgment information; The drug dispensing prediction information is sent to an associated audit terminal, and in response to receiving confirmation information corresponding to the drug dispensing prediction information sent by the audit terminal, the drug dispensing prediction information is used to determine the drug dispensing configuration information corresponding to the target user.

3. The control and detection method for a flowable drug dispensing device according to claim 1 is characterized in that: The step of determining whether the fluidity drug has been inputted according to the drug outflow video and the weight data sequence monitored by the weight monitoring device includes: In response to determining that the last weight data in the weight data sequence is less than the target weight, the drug outflow video is frame-processed to obtain a drug outflow video image sequence, wherein the target weight is the sum of the drug outflow weight corresponding to the drug outflow configuration information and the net weight of the drug solution storage tube; Selecting each drug outflow video image that meets the target image condition from the drug outflow video image sequence as a drug outflow video image group to be detected, wherein the target image condition is: the clarity of the drug outflow video image is greater than a preset clarity, and the position corresponding to the drug outflow video image is within a preset position interval; Inputting the drug outflow video image group to be detected into a pre-trained drug residue state recognition model to obtain a drug residue state recognition result; In response to determining that the drug residue status identification result indicates that there is drug residue, it is determined that the flowable drug input is incomplete.

4. The control and detection method for a flowable drug dispensing device according to claim 1 is characterized in that: The method further comprises: In response to determining that the fluidity drug input is not completed, determining a residual drug extraction method corresponding to the fluidity drug type, extracting the residual drug in the fluidity drug extraction device into the drug solution storage tube according to the residual drug extraction method, and determining whether the weight data monitored by the current weight monitoring device is greater than or equal to the target weight; In response to determining that the weight data currently monitored by the weight monitoring device is greater than or equal to the target weight, medication dispensing completion information is generated.

5. The control and detection method for a flowable drug dispensing device according to claim 3 is characterized in that: Before inputting the drug outflow video image group to be detected into a pre-trained drug residue state recognition model to obtain a drug residue state recognition result, the method further includes: Acquire a drug outflow video image sample set, wherein the drug outflow video image sample includes: a sample drug outflow video image and a drug residue sample label; Determine an initial drug residue state recognition model, wherein the initial drug residue state recognition model includes: an initial drug image feature extraction layer, an initial residual drug image contour extraction layer, an initial residual drug image area feature extraction layer, an initial multi-level drug image feature encoding layer, an initial feature fusion layer and an initial drug residue state recognition output layer; Based on the drug outflow video image sample set, the initial drug residue state recognition model is trained to obtain a trained drug residue state recognition model.

6. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images