CN118386225A - Intelligent dispensing robot based on visual recognition technology - Google Patents

Abstract

The invention provides an intelligent dispensing robot based on a visual recognition technology, wherein the intelligent dispensing robot comprises: the medicine box attribute information acquisition subsystem is used for acquiring medicine box attribute information of the first target medicine box; the automatic medicine charging subsystem is used for automatically supplementing a first target medicine box according to the attribute information of the medicine box based on a visual identification technology; the dispensing requirement acquisition subsystem is used for acquiring the dispensing requirement of the target patient; the medicine taking scheme determining subsystem is used for determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box; and the intelligent dispensing subsystem is used for intelligent dispensing according to a medicine taking scheme. According to the intelligent dispensing robot based on the visual identification technology, the visual identification technology is introduced, and the first target medicine box is automatically filled according to the attribute information of the medicine box. In addition, according to the requirement of dispensing and the attribute information of the medicine box, a medicine taking scheme is determined, the medicine is dispensed based on the medicine taking scheme, the manual participation in the medicine dispensing process is not needed, the situation of medicine dispensing mistakes is avoided, and the medicine dispensing system is more intelligent.

Description

Intelligent dispensing robot based on visual recognition technology

Technical Field

The invention relates to the technical field of industrial vision, in particular to an intelligent dispensing robot based on a visual identification technology.

Background

Currently, the population base of the elderly with chronic diseases is large, and many of them need to be treated with various drugs for a long period of time. Modern medical technology is developed, the medicine variety is rich, the classification is detailed, and the usage is complex. And the memory is obviously reduced due to the physical function decline of the old, and daily taking and dividing of medicines also become a matter which is easy to forget or make mistakes. The medicine box is used as a common medical auxiliary product and has a dense and indistinguishable effect on nursing diseases of the old. The traditional medicine box has low automation degree and low intelligent degree in product modeling and functions, lacks pain points such as humanized design, and obviously can not meet the medical care requirements of the elderly more and more complicated.

The application number is: the invention patent of CN201911044150.1 discloses a tabletop dispensing robot and a dispensing method thereof, wherein the tabletop dispensing robot comprises a cabinet body, a control panel and an operation window for operators are arranged on the tabletop dispensing robot, a supporting plate is arranged in the cabinet body, the space in the cabinet body is divided by the supporting plate to form an upper space and a lower space, a syringe conveying module, a rotary manipulator module, a needle cap collecting module, an infusion bag conveying module, a penicillin bottle conveying module, a cover opening sterilizing module, a penicillin bottle rotary module, a laser scanning module, an empty penicillin bottle pushing module, an oscillation dissolving module and a syringe needle separating collecting module are arranged in the upper space of the cabinet body; the supporting plate is also respectively provided with a needle cap recovery port, a needle head recovery port of the needle cylinder and a recovery port of the penicillin bottle, and a needle cap recovery barrel, a needle head recovery barrel of the needle cylinder and a recovery barrel of the penicillin bottle are correspondingly arranged in the lower space of the cabinet body. The tabletop dispensing robot and the dispensing method thereof can effectively reduce the labor intensity of operators, improve the dispensing efficiency and reduce the error rate.

At that time, the prior art still needs an operator to assist in dispensing at an operation window, and the situation of dispensing errors exists and the intelligence is not enough.

In view of this, there is a need for an intelligent dispensing robot based on visual recognition technology to address at least the above-mentioned shortcomings.

Disclosure of Invention

The invention aims at providing an intelligent dispensing robot based on a visual identification technology, which introduces the visual identification technology and automatically fills a first target medicine box according to the attribute information of the medicine box. In addition, the medicine dispensing requirement of the target patient is acquired, the medicine taking scheme is determined according to the medicine dispensing requirement and the attribute information of the medicine box, and intelligent medicine dispensing is performed based on the medicine taking scheme, so that manual participation in a medicine dispensing process is not needed, the situation of medicine dispensing mistakes is avoided, and the medicine dispensing system is more intelligent.

The intelligent dispensing robot based on the visual identification technology provided by the embodiment of the invention comprises:

the medicine box attribute information acquisition subsystem is used for acquiring medicine box attribute information of the first target medicine box;

the automatic medicine charging subsystem is used for automatically supplementing a first target medicine box according to the attribute information of the medicine box based on a visual identification technology;

The dispensing requirement acquisition subsystem is used for acquiring the dispensing requirement of the target patient;

The medicine taking scheme determining subsystem is used for determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box;

and the intelligent dispensing subsystem is used for intelligent dispensing according to a medicine taking scheme.

Preferably, the kit attribute information acquisition subsystem includes:

the authority personnel information acquisition module is used for acquiring authority personnel information, wherein the authority personnel information is as follows: personnel information allowing setting of the cartridge attribute information of the first target cartridge;

the setting personnel information acquisition module is used for acquiring setting personnel information for setting the medicine box attribute information of the first target medicine box;

the target setting information determining module is used for determining target setting information of target setting personnel according to the authority personnel information and the setting personnel information;

and the medicine box attribute information determining module is used for determining medicine box attribute information according to the target setting information.

Preferably, the automatic charge subsystem comprises:

the shooting image acquisition module is used for acquiring shooting images of medicines to be supplemented;

The medicine identification information to be supplemented determining module is used for determining medicine identification information to be supplemented according to the photographed image based on the visual identification technology, and the medicine identification information to be supplemented comprises: identifying the package and identifying the type of the drug;

The package disassembly scheme determining module is used for determining a package disassembly scheme of the medicine to be supplemented according to the identified package;

the medicine box input scheme determining module is used for determining a medicine box input scheme of the medicine to be supplemented according to the medicine type identification and the medicine box attribute information;

and the automatic supplementing module is used for automatically supplementing the first target medicine box according to the package disassembling scheme and the medicine box throwing scheme.

Preferably, the drug identification information determining module to be supplemented includes:

the text information determining sub-module is used for determining text information on the outer package of the medicine to be supplemented according to the photographed image based on the visual recognition technology;

The first text semantic determining submodule is used for determining first text semantics according to the text information;

The second text semantic determining submodule is used for determining second text semantics according to the first text semantics, and the second text semantics comprise: medicine name semantics and medicine package semantics;

the to-be-supplemented medicine identification information determining submodule is used for determining to-be-supplemented medicine identification information according to the second text semantics;

Wherein, text information confirms submodule, include:

An outer package contour information determination unit for determining outer package contour information based on the photographed image;

The text anchor point determining unit is used for determining text anchor points on the outer package according to the outer package outline information and preset package specifications;

The local shooting image determining unit is used for determining a local shooting image according to the text anchor point;

And the text information determining unit is used for determining text information according to the character recognition technology and the local shot image.

Preferably, the dispensing demand acquisition subsystem comprises:

a medicine taking method acquisition module for acquiring at least one medicine taking method input by a target patient;

the medicine dispensing requirement determining module is used for determining the medicine dispensing requirement according to the medicine taking method;

wherein, the demand of dispensing confirms the module, include:

the medicine taking information determining submodule is used for determining the expected medicine taking time point and the medicine taking type and the medicine taking amount corresponding to the expected medicine taking time point according to the medicine taking method;

The current time acquisition sub-module is used for acquiring the current time;

and the medicine dispensing requirement determining submodule is used for taking medicine taking types and medicine taking amounts corresponding to the predicted medicine taking time points reached at the current time as medicine dispensing requirements if the current time reaches any predicted medicine taking time point.

Preferably, the medication intake scheme determination subsystem comprises:

the first target medicine determining module is used for determining a first target medicine in a first target medicine box according to the medicine box attribute information;

The second target medicine box determining module is used for determining a second target medicine box in the first target medicine box according to the medicine taking type and the first target medicine in the medicine dispensing requirement;

the calibration information acquisition module is used for acquiring the calibration information of the second target medicine box;

and the medicine taking scheme determining module is used for determining a medicine taking scheme according to the medicine taking amount and the calibration information.

Preferably, the intelligent dispensing subsystem comprises:

the calibration medicine box rotating module is used for controlling the second target medicine box to rotate to the position below the preset medicine suction pipe according to the calibration information;

And the intelligent dispensing module is used for controlling the drug sucking pipe to suck the second target drug of the dosage in the second target drug box after the second target drug box rotates to the lower part of the drug sucking pipe.

Preferably, the calibration kit rotation module comprises:

The first medicine box number acquisition sub-module is used for acquiring a first medicine box number of a first target medicine box nearest to a preset medicine suction tube;

A second medicine box number obtaining sub-module for obtaining a second medicine box number of a second target medicine box which is not subjected to the sucking operation;

the first target difference value calculation sub-module is used for calculating a first target difference value of the first medicine box number and the second medicine box number;

The second target difference value calculation sub-module is used for determining a second target difference value according to the maximum number of the first target medicine box and the first target difference value;

The comparison result determining submodule is used for determining a comparison result of the first target difference value and the second target difference value and correlating the comparison result with the second target medicine box;

The third target medicine box control submodule is used for determining a third target medicine box according to the comparison result and controlling the third target medicine box to rotate below the medicine suction tube according to the comparison result of the third target medicine box;

And the circulation sub-module is used for repeatedly executing the first medicine box number acquisition sub-module, the second medicine box number acquisition sub-module, the first target difference value calculation sub-module, the second target difference value calculation sub-module, the comparison result determination sub-module and the third target medicine box control sub-module until the second target medicine box which is not subjected to the sucking operation completely completes the sucking operation.

Preferably, the intelligent dispensing module comprises:

The grabbing information determining sub-module is used for determining grabbing information of the second target medicine according to the calibration information;

the grabbing feature determining submodule is used for determining grabbing features according to grabbing information;

the grabbing test record acquisition sub-module is used for acquiring grabbing test records;

The grabbing model training submodule is used for training the grabbing model according to the grabbing test record;

The grabbing strategy obtaining submodule is used for inputting grabbing characteristics into the grabbing model to obtain the grabbing strategy of the medicine suction tube, and the grabbing strategy comprises the following steps: a suction nozzle of the medicine suction pipe and the suction force of the medicine suction pipe;

and the medicine grabbing sub-module is used for controlling the medicine sucking pipe to suck the second target medicine in the second target medicine box according to the medicine grabbing strategy.

The intelligent dispensing robot based on the visual identification technology provided by the embodiment of the invention further comprises:

The reminding subsystem is used for reminding a target patient to take medicine in time;

Wherein, remind the subsystem, include:

The sensing information acquisition module is used for acquiring sensing information of the dispensing box after intelligent dispensing is completed;

the medicine taking judging module is used for judging whether the target patient finishes medicine taking according to the sensing information;

The remote binding information acquisition module is used for acquiring remote binding information if the target patients do not finish taking the medicine within the target time after the intelligent medicine dispensing is finished;

the first reminding information determining module is used for determining the first reminding information according to the remote binding information and sending the first reminding information to a remote binding person;

the environment information acquisition module is used for acquiring environment information;

The reminding person identification module is used for attempting to identify reminding persons according to the environmental information;

and the second reminding information broadcasting module is used for broadcasting the second reminding information based on a preset voice broadcasting rule if the attempt identification is successful.

The intelligent dispensing method based on the visual identification technology provided by the embodiment of the invention comprises the following steps:

Step 1: acquiring medicine box attribute information of a first target medicine box;

step 2: based on the visual recognition technology, automatically supplementing a first target medicine box according to the medicine box attribute information;

Step 3: acquiring the dispensing requirement of a target patient;

step 4: determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box;

step 5: according to the medicine taking scheme, intelligent medicine dispensing is carried out.

The beneficial effects of the invention are as follows:

the invention introduces a visual recognition technology and automatically fills the first target medicine box according to the attribute information of the medicine box. In addition, the medicine dispensing requirement of the target patient is acquired, the medicine taking scheme is determined according to the medicine dispensing requirement and the attribute information of the medicine box, and intelligent medicine dispensing is performed based on the medicine taking scheme, so that manual participation in a medicine dispensing process is not needed, the situation of medicine dispensing mistakes is avoided, and the medicine dispensing system is more intelligent.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objects and other advantages of the application may be realized and obtained by means of the instrumentalities particularly pointed out in the specification.

The technical scheme of the invention is further described in detail through the drawings and the embodiments.

Drawings

The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:

FIG. 1 is a schematic diagram of an intelligent dispensing robot based on visual recognition technology in an embodiment of the invention;

fig. 2 is a schematic diagram of an intelligent dispensing method based on a visual recognition technology in an embodiment of the invention.

Detailed Description

The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.

The embodiment of the invention provides an intelligent dispensing robot based on a visual identification technology, as shown in fig. 1, comprising:

The medicine box attribute information acquisition subsystem 1 is used for acquiring medicine box attribute information of a first target medicine box; wherein, first target medicine box is: the medicine box is arranged on the intelligent dispensing robot and used for storing the to-be-dispensed medicines; the medicine box attribute information is as follows: a kit number and kit contents;

An automatic medicine charging subsystem 2 for automatically supplementing a first target medicine box according to the attribute information of the medicine box based on a visual identification technology; when the first target medicine box is automatically replenished, identifying the medicine to be replenished and the attribute information of the medicine box based on a visual identification technology, and throwing the medicine to be replenished into the corresponding first target medicine box by using a mechanical arm;

A dispensing demand acquisition subsystem 3 for acquiring the dispensing demand of the target patient; wherein, the requirement of dispensing is: what kind of medicine is needed to be prepared at the current moment, and how much of each medicine is prepared;

a medication intake scheme determination subsystem 4 for determining a medication scheme according to the medication requirement and the attribute information of the medication box; wherein, the medicine taking scheme is as follows: when a certain amount of medicine needs to be taken from which first target medicine box;

The intelligent dispensing subsystem 5 is used for intelligent dispensing according to a medicine taking scheme. Wherein, carry out intelligent medicine dispensing and refer to the accurate absorption of required quantity of medicines of medicine pipe that utilizes being connected with the vacuum pump.

The working principle and the beneficial effects of the technical scheme are as follows:

the application introduces a visual recognition technology and automatically fills the first target medicine box according to the attribute information of the medicine box. In addition, the medicine dispensing requirement of the target patient is acquired, the medicine taking scheme is determined according to the medicine dispensing requirement and the attribute information of the medicine box, and intelligent medicine dispensing is performed based on the medicine taking scheme, so that manual participation in a medicine dispensing process is not needed, the situation of medicine dispensing mistakes is avoided, and the medicine dispensing system is more intelligent.

In one embodiment, the kit attribute information acquisition subsystem comprises:

The authority personnel information acquisition module is used for acquiring authority personnel information, wherein the authority personnel information is as follows: personnel information allowing setting of the cartridge attribute information of the first target cartridge; wherein, personnel information is: personal unique identity information;

the setting personnel information acquisition module is used for acquiring setting personnel information for setting the medicine box attribute information of the first target medicine box; wherein the kit attribute information for performing the first target kit is set as: setting the behavior of which medicines are placed in a first target medicine box;

The target setting information determining module is used for determining target setting information of target setting personnel according to the authority personnel information and the setting personnel information; wherein, the target setting personnel are: a person with the set authority set by the medicine box attribute information of the first target medicine box is determined by performing authority matching according to the set personnel information and the authority personnel information; the target setting information is: setting operation of the drug box attribute information of the target setting personnel;

and the medicine box attribute information determining module is used for determining medicine box attribute information according to the target setting information.

The working principle and the beneficial effects of the technical scheme are as follows:

according to the application, the authority personnel information and the setting personnel information are introduced, the medicine box attribute information setting operation of the target setting personnel is determined according to the authority personnel information and the setting personnel information, and the medicine box attribute information is determined according to the target setting information, so that the acquisition suitability of the medicine box attribute information is improved.

In one embodiment, an automated charging subsystem includes:

The shooting image acquisition module is used for acquiring shooting images of medicines to be supplemented; wherein, the medicines to be supplemented are as follows: preparing medicines stored in the intelligent dispensing robot; the photographed image is: taking a photo of the medicine to be supplemented;

The medicine identification information to be supplemented determining module is used for determining medicine identification information to be supplemented according to the photographed image based on the visual identification technology, and the medicine identification information to be supplemented comprises: identifying the package and identifying the type of the drug; wherein, the identification package is: how the pharmaceutical product to be replenished is packaged, such as: plastic bottles, such as: strip-shaped packaging; the identification of the drug categories is: drug type identification results of the drug to be replenished;

The package disassembly scheme determining module is used for determining a package disassembly scheme of the medicine to be supplemented according to the identified package; wherein, the package disassembly scheme is: identifying a corresponding disassembly scheme for the package, such as: unscrewing the vial cap, again for example: puncturing the aluminum package;

The medicine box input scheme determining module is used for determining a medicine box input scheme of the medicine to be supplemented according to the medicine type identification and the medicine box attribute information; wherein, the medicine box input scheme is: which first target kit to throw into;

and the automatic supplementing module is used for automatically supplementing the first target medicine box according to the package disassembling scheme and the medicine box throwing scheme.

The working principle and the beneficial effects of the technical scheme are as follows:

At present, a manual assembly mode is generally adopted for loading the tablets into the medicine box, but the manual loading process is complicated and the pollution of medicines is easy to cause, so that the application introduces the shooting image of the medicines to be supplemented, and determines the identification package of the medicines to be supplemented and the identification type of the medicines based on the visual identification technology. And determining a package disassembly scheme according to the identification package, and determining a medicine box input scheme according to the identification medicine type and the medicine box attribute information. The package disassembly scheme is based on the package disassembly scheme, the package of the medicine to be supplemented is disassembled, and the medicine to be supplemented after the package disassembly is supplemented to the corresponding first target medicine box based on the medicine box input scheme, so that the medicine box is more sanitary and convenient.

In one embodiment, the drug identification information determination module to be supplemented includes:

the text information determining sub-module is used for determining text information on the outer package of the medicine to be supplemented according to the photographed image based on the visual recognition technology; the text information comprises the following steps: identifying characters on the outer package of the medicine to be replenished;

the first text semantic determining submodule is used for determining first text semantics according to the text information; the first text semantics are: meaning of text information representation;

The second text semantic determining submodule is used for determining second text semantics according to the first text semantics, and the second text semantics comprise: medicine name semantics and medicine package semantics; wherein, the medicine name semantics are: the text information indicates the meaning of the drug name; the medicine package semantics are: the text information indicates the meaning of the medicine package;

the to-be-supplemented medicine identification information determining submodule is used for determining to-be-supplemented medicine identification information according to the second text semantics;

Wherein, text information confirms submodule, include:

An outer package contour information determination unit for determining outer package contour information based on the photographed image; wherein, the external packing contour information is: three-dimensional scanning information of the outer package;

The text anchor point determining unit is used for determining text anchor points on the outer package according to the outer package outline information and preset package specifications; wherein, the preset packaging standard is: packaging standard of medicines; the text anchor points are: normalized labeling positions of texts on the outer package outline information;

The local shooting image determining unit is used for determining a local shooting image according to the text anchor point; wherein, the local shooting image is: shooting a local image corresponding to the text anchor point in the image;

And the text information determining unit is used for determining text information according to the character recognition technology and the local shot image.

The working principle and the beneficial effects of the technical scheme are as follows:

The application determines the outline information of the external package of the medicine to be supplemented, determines the text anchor point on the external package according to the outline information of the external package and the preset package standard, extracts the local shooting image corresponding to the text anchor point, and determines the text information according to the character recognition technology and the local shooting image. The meaning of the text information is obtained, the medicine name semantic and the medicine package semantic are determined, and the medicine name semantic and the medicine package semantic are used as the identification information of the medicine to be supplemented, so that the obtaining efficiency and accuracy of the identification information of the medicine to be supplemented are improved.

In one embodiment, the medication dispensing requirement acquisition subsystem comprises:

A medicine taking method acquisition module for acquiring at least one medicine taking method input by a target patient; the medicine taking method comprises the following steps: how to take, for example: medicine A, one in the morning and one in the evening, two in each time;

the medicine dispensing requirement determining module is used for determining the medicine dispensing requirement according to the medicine taking method;

wherein, the demand of dispensing confirms the module, include:

the medicine taking information determining submodule is used for determining the expected medicine taking time point and the medicine taking type and the medicine taking amount corresponding to the expected medicine taking time point according to the medicine taking method;

The current time acquisition sub-module is used for acquiring the current time;

and the medicine dispensing requirement determining submodule is used for taking medicine taking types and medicine taking amounts corresponding to the predicted medicine taking time points reached at the current time as medicine dispensing requirements if the current time reaches any predicted medicine taking time point.

The working principle and the beneficial effects of the technical scheme are as follows:

According to the method for taking the medicine input by the target patient, the instant medicine dispensing requirement is determined according to the medicine taking method, and the medicine dispensing requirement is obtained more reasonably.

In one embodiment, the medication intake protocol determination subsystem comprises:

The first target medicine determining module is used for determining a first target medicine in a first target medicine box according to the medicine box attribute information; wherein the first target drug is: a drug stored in a first target kit;

the second target medicine box determining module is used for determining a second target medicine box in the first target medicine box according to the medicine taking type and the first target medicine in the medicine dispensing requirement; wherein the second target kit is: medicine taking boxes corresponding to the medicine dispensing requirements;

The calibration information acquisition module is used for acquiring the calibration information of the second target medicine box; the calibration information comprises the following steps: kit attribute information of a second target kit, comprising: the medicine box number, the current position, medicine box content information and the like;

and the medicine taking scheme determining module is used for determining a medicine taking scheme according to the medicine taking amount and the calibration information.

The working principle and the beneficial effects of the technical scheme are as follows:

The application determines a first target medicine in a first target medicine box, and determines a medicine taking medicine box corresponding to a dispensing requirement, namely a second target medicine box, according to the medicine taking type in the dispensing requirement and the first target medicine. And acquiring the medicine box number and the current position of the second target medicine box, and determining a medicine taking scheme according to the medicine dosage and the calibration information, wherein the acquisition of the medicine taking scheme is more suitable.

In one embodiment, the intelligent dispensing subsystem comprises:

The calibration medicine box rotating module is used for controlling the second target medicine box to rotate to the position below the preset medicine suction pipe according to the calibration information; wherein, the control of the rotation of the second target medicine box to the lower part of the preset medicine suction pipe is to start the rotating disc stepping motor for placing the first target medicine box to rotate forward to drive the medicine box frame to rotate, and the second target medicine box fixed on the frame is sent to the lower part of the medicine suction pipe; the drug sucking pipe is connected with a vacuum pump;

And the intelligent dispensing module is used for controlling the drug sucking pipe to suck the second target drug of the dosage in the second target drug box after the second target drug box rotates to the lower part of the drug sucking pipe. Wherein the second target drug is: a drug in a second target kit.

The working principle and the beneficial effects of the technical scheme are as follows:

According to the application, the relative position of the second target medicine box in the medicine box frame is determined according to the calibration information, and the medicine sucking pipe is controlled to suck the second target medicine of the dosage in the second target medicine box after the second target medicine box is controlled to rotate below the preset medicine sucking pipe, so that the accurate dosage degree is improved.

In one embodiment, a calibration kit rotation module includes:

The first medicine box number acquisition sub-module is used for acquiring a first medicine box number of a first target medicine box nearest to a preset medicine suction tube; wherein, the first medicine box is numbered: the cartridge number of the first target cartridge closest to the preset cartridge, such as: 3, a step of;

A second medicine box number obtaining sub-module for obtaining a second medicine box number of a second target medicine box which is not subjected to the sucking operation; wherein, the sucking operation is as follows: a medication operation corresponding to the current medication demand; the second kit is numbered: the cartridge number of the second target cartridge for which the sucking operation is not performed, such as: 2.5 and 8;

The first target difference value calculation sub-module is used for calculating a first target difference value of the first medicine box number and the second medicine box number; wherein the first target difference is: the difference between the first and second cassette numbers yields results such as: +1, -2, and-5;

The second target difference value calculation sub-module is used for determining a second target difference value according to the maximum number of the first target medicine box and the first target difference value; wherein the maximum number is determined according to the total number of first target kits, such as: the total number of the first target medicine boxes is 8, and the maximum number is 8; the second target difference is: if the first target difference is positive, the second target difference is the maximum number minus the first target difference, and if the first target difference is not positive, the second target difference is the maximum number plus the first target difference;

The comparison result determining submodule is used for determining a comparison result of the first target difference value and the second target difference value and correlating the comparison result with the second target medicine box; wherein, the comparison result is: the first target difference value or the second target difference value with smaller absolute value in the first target difference value and the second target difference value;

The third target medicine box control submodule is used for determining a third target medicine box according to the comparison result and controlling the third target medicine box to rotate below the medicine suction tube according to the comparison result of the third target medicine box; when a third target medicine box is determined according to the comparison result, the second target medicine box with the smallest absolute value of the comparison result is used as the third target medicine box;

And the circulation sub-module is used for repeatedly executing the first medicine box number acquisition sub-module, the second medicine box number acquisition sub-module, the first target difference value calculation sub-module, the second target difference value calculation sub-module, the comparison result determination sub-module and the third target medicine box control sub-module until the second target medicine box which is not subjected to the sucking operation completely completes the sucking operation.

The working principle and the beneficial effects of the technical scheme are as follows:

The method comprises the steps of determining the medicine box number of a first target medicine box closest to a preset medicine suction pipe, simultaneously obtaining the medicine box number of a second target medicine box which is not sucked, and determining a second target difference value according to the maximum number of the first target medicine box and the first target difference value. The first target difference value or the second target difference value with smaller absolute value in the first target difference value and the second target difference value is obtained as a comparison result, the smaller the absolute value of the comparison result is, the closer the corresponding second target medicine box is to the medicine suction tube, the second target medicine box with the smallest absolute value of the comparison result is taken as a third target medicine box, meanwhile, the comparison result is analyzed, the rotating direction of the turntable stepping motor control is determined according to the sign of the comparison result, the rotating angle of the turntable stepping motor control is determined according to the absolute value of the comparison result, the turntable stepping motor control the minimum rotating variable is determined, and the medicine dispensing speed is improved.

In one embodiment, the smart dispensing module comprises:

the grabbing information determining sub-module is used for determining grabbing information of the second target medicine according to the calibration information; the grabbing information is as follows: information related to grasping a second target medication, such as: a second drug of interest in the form of a composition comprising: capsules, tablets, and glass jars;

The grabbing feature determining submodule is used for determining grabbing features according to grabbing information; wherein, snatch the characteristic and be: capturing a characterization representation of information, such as: grasping information types and corresponding information contents (for example, existence form of medicine: capsule, weight: 90mg, etc.);

the grabbing test record acquisition sub-module is used for acquiring grabbing test records; wherein, the test record of the drug grabbing is: manually setting a suction nozzle of a medicine suction pipe and medicine suction pressure to carry out medicine taking process records, and selecting only records of successful medicine taking according to medicine grabbing test records;

The grabbing model training submodule is used for training the grabbing model according to the grabbing test record; wherein, the medicine taking model is: learning an AI model of a dispensing logic of the intelligent dispensing robot;

The grabbing strategy obtaining submodule is used for inputting grabbing characteristics into the grabbing model to obtain the grabbing strategy of the medicine suction tube, and the grabbing strategy comprises the following steps: a suction nozzle of the medicine suction pipe and the suction force of the medicine suction pipe;

And the medicine grabbing sub-module is used for controlling the medicine sucking pipe to suck the second target medicine in the second target medicine box according to the medicine grabbing strategy. The suction nozzles with various shapes can be preset in the suction tube, and after the suction nozzle of the suction tube with the medicine grabbing strategy is determined, the suction nozzle with the corresponding shape is selected for sucking medicine.

The working principle and the beneficial effects of the technical scheme are as follows:

The application determines the grabbing information of the second target medicine and characterizes the grabbing information to obtain grabbing characteristics. According to the successful grabbing test record of grabbing results, the grabbing model is trained, grabbing features are input into the grabbing model, the suction force of the suction nozzle of the proper medicine suction pipe and the suction force of the medicine suction pipe are determined, and according to the grabbing strategy, the medicine suction pipe is controlled to suck the second target medicine in the second target medicine box, so that the situation that the medicine is dropped or cannot be sucked when the medicine is sucked is avoided, and the medicine grabbing device is more suitable.

The embodiment of the invention provides an intelligent dispensing robot based on a visual identification technology, which further comprises:

The reminding subsystem is used for reminding a target patient to take medicine in time;

Wherein, remind the subsystem, include:

The sensing information acquisition module is used for acquiring sensing information of the dispensing box after intelligent dispensing is completed; wherein, the response information is: sensing information about whether the medicine in the medicine dispensing box is taken out, such as: gravity sensing information of the dispensing box;

the medicine taking judging module is used for judging whether the target patient finishes medicine taking according to the sensing information;

The remote binding information acquisition module is used for acquiring remote binding information if the target patients do not finish taking the medicine within the target time after the intelligent medicine dispensing is finished; the target time length is preset manually; the remote binding information is: a remote terminal bound by the intelligent dispensing robot;

The first reminding information determining module is used for determining the first reminding information according to the remote binding information and sending the first reminding information to a remote binding person; wherein, the first reminding information is: the intelligent dispensing robot sends information on the remote terminal of the remote binding personnel, such as: "detect you associated intelligent dispensing robot dispensed medicine not taken";

the environment information acquisition module is used for acquiring environment information; wherein, the environmental information is: three-dimensional scanning information in a preset range around the intelligent dispensing machine;

The reminding person identification module is used for attempting to identify reminding persons according to the environmental information; wherein, the reminding personnel are: personnel corresponding to the human body model identified in the three-dimensional scanning information;

And the second reminding information broadcasting module is used for broadcasting the second reminding information based on a preset voice broadcasting rule if the attempt identification is successful. Wherein, the preset voice broadcasting rule is preset manually; the second reminding information is as follows: voice broadcast information, such as: dosage not taken out, please take out in time.

The working principle and the beneficial effects of the technical scheme are as follows:

After the dispensing box finishes dispensing, the target patient does not need to take the medicine in time, and the condition of forgetting to take the medicine exists, so that the intelligent dispensing box acquires the sensing information of the dispensing box after the intelligent dispensing is finished, and judges whether the target patient finishes taking the medicine according to the sensing information. If the target patients do not finish taking the medicine in the target time after the intelligent medicine dispensing is finished, the first reminding information is sent to the remote terminal bound by the intelligent medicine dispensing robot, and the remote binding personnel can be the target patients and the relatives of the target patients, so that timely reminding is convenient. In addition, three-dimensional scanning information in a preset range around the intelligent dispensing machine is introduced, and when reminding personnel are identified, a voice broadcasting rule is introduced to broadcast second reminding information, so that the comprehensiveness of reminding is improved.

The embodiment of the invention provides an intelligent dispensing method based on a visual identification technology, which is shown in fig. 2 and comprises the following steps:

Step 1: acquiring medicine box attribute information of a first target medicine box;

step 2: based on the visual recognition technology, automatically supplementing a first target medicine box according to the medicine box attribute information;

Step 3: acquiring the dispensing requirement of a target patient;

step 4: determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box;

step 5: according to the medicine taking scheme, intelligent medicine dispensing is carried out.

It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.

Claims (10)

1. Intelligent dispensing robot based on visual identification technology, its characterized in that includes:

the medicine box attribute information acquisition subsystem is used for acquiring medicine box attribute information of the first target medicine box;

the automatic medicine charging subsystem is used for automatically supplementing a first target medicine box according to the attribute information of the medicine box based on a visual identification technology;

The dispensing requirement acquisition subsystem is used for acquiring the dispensing requirement of the target patient;

The medicine taking scheme determining subsystem is used for determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box;

and the intelligent dispensing subsystem is used for intelligent dispensing according to a medicine taking scheme.

2. The intelligent dispensing robot based on visual identification technology as set forth in claim 1, wherein the kit attribute information acquisition subsystem comprises:

the authority personnel information acquisition module is used for acquiring authority personnel information, wherein the authority personnel information is as follows: personnel information allowing setting of the cartridge attribute information of the first target cartridge;

the setting personnel information acquisition module is used for acquiring setting personnel information for setting the medicine box attribute information of the first target medicine box;

the target setting information determining module is used for determining target setting information of target setting personnel according to the authority personnel information and the setting personnel information;

and the medicine box attribute information determining module is used for determining medicine box attribute information according to the target setting information.

3. A vision-recognition-technology-based intelligent dispensing robot as set forth in claim 1, wherein the automated charge subsystem comprises:

the shooting image acquisition module is used for acquiring shooting images of medicines to be supplemented;

The medicine identification information to be supplemented determining module is used for determining medicine identification information to be supplemented according to the photographed image based on the visual identification technology, and the medicine identification information to be supplemented comprises: identifying the package and identifying the type of the drug;

The package disassembly scheme determining module is used for determining a package disassembly scheme of the medicine to be supplemented according to the identified package;

the medicine box input scheme determining module is used for determining a medicine box input scheme of the medicine to be supplemented according to the medicine type identification and the medicine box attribute information;

and the automatic supplementing module is used for automatically supplementing the first target medicine box according to the package disassembling scheme and the medicine box throwing scheme.

4. An intelligent dispensing robot based on visual identification technology as set forth in claim 3, wherein the identification information determining module for the medicine to be replenished comprises:

the text information determining sub-module is used for determining text information on the outer package of the medicine to be supplemented according to the photographed image based on the visual recognition technology;

The first text semantic determining submodule is used for determining first text semantics according to the text information;

The second text semantic determining submodule is used for determining second text semantics according to the first text semantics, and the second text semantics comprise: medicine name semantics and medicine package semantics;

the to-be-supplemented medicine identification information determining submodule is used for determining to-be-supplemented medicine identification information according to the second text semantics;

Wherein, text information confirms submodule, include:

An outer package contour information determination unit for determining outer package contour information based on the photographed image;

The text anchor point determining unit is used for determining text anchor points on the outer package according to the outer package outline information and preset package specifications;

The local shooting image determining unit is used for determining a local shooting image according to the text anchor point;

And the text information determining unit is used for determining text information according to the character recognition technology and the local shot image.

5. A vision recognition technology-based intelligent dispensing robot as set forth in claim 1, wherein the dispensing demand acquisition subsystem comprises:

a medicine taking method acquisition module for acquiring at least one medicine taking method input by a target patient;

the medicine dispensing requirement determining module is used for determining the medicine dispensing requirement according to the medicine taking method;

wherein, the demand of dispensing confirms the module, include:

the medicine taking information determining submodule is used for determining the expected medicine taking time point and the medicine taking type and the medicine taking amount corresponding to the expected medicine taking time point according to the medicine taking method;

The current time acquisition sub-module is used for acquiring the current time;

and the medicine dispensing requirement determining submodule is used for taking medicine taking types and medicine taking amounts corresponding to the predicted medicine taking time points reached at the current time as medicine dispensing requirements if the current time reaches any predicted medicine taking time point.

6. The intelligent dispensing robot based on visual identification technology as set forth in claim 1, wherein the medication intake scheme determination subsystem comprises:

the first target medicine determining module is used for determining a first target medicine in a first target medicine box according to the medicine box attribute information;

The second target medicine box determining module is used for determining a second target medicine box in the first target medicine box according to the medicine taking type and the first target medicine in the medicine dispensing requirement;

the calibration information acquisition module is used for acquiring the calibration information of the second target medicine box;

and the medicine taking scheme determining module is used for determining a medicine taking scheme according to the medicine taking amount and the calibration information.

7. A vision-recognition-technology-based intelligent dispensing robot as set forth in claim 1, wherein the intelligent dispensing subsystem comprises:

the calibration medicine box rotating module is used for controlling the second target medicine box to rotate to the position below the preset medicine suction pipe according to the calibration information;

And the intelligent dispensing module is used for controlling the drug sucking pipe to suck the second target drug of the dosage in the second target drug box after the second target drug box rotates to the lower part of the drug sucking pipe.

8. A vision-recognition-technology-based intelligent dispensing robot as set forth in claim 7, wherein the intelligent dispensing module includes:

The grabbing information determining sub-module is used for determining grabbing information of the second target medicine according to the calibration information;

the grabbing feature determining submodule is used for determining grabbing features according to grabbing information;

the grabbing test record acquisition sub-module is used for acquiring grabbing test records;

The grabbing model training submodule is used for training the grabbing model according to the grabbing test record;

The grabbing strategy obtaining submodule is used for inputting grabbing characteristics into the grabbing model to obtain the grabbing strategy of the medicine suction tube, and the grabbing strategy comprises the following steps: a suction nozzle of the medicine suction pipe and the suction force of the medicine suction pipe;

and the medicine grabbing sub-module is used for controlling the medicine sucking pipe to suck the second target medicine in the second target medicine box according to the medicine grabbing strategy.

9. The intelligent dispensing robot based on visual identification technology as set forth in claim 1, further comprising:

The reminding subsystem is used for reminding a target patient to take medicine in time;

Wherein, remind the subsystem, include:

The sensing information acquisition module is used for acquiring sensing information of the dispensing box after intelligent dispensing is completed;

the medicine taking judging module is used for judging whether the target patient finishes medicine taking according to the sensing information;

The remote binding information acquisition module is used for acquiring remote binding information if the target patients do not finish taking the medicine within the target time after the intelligent medicine dispensing is finished;

the first reminding information determining module is used for determining the first reminding information according to the remote binding information and sending the first reminding information to a remote binding person;

the environment information acquisition module is used for acquiring environment information;

The reminding person identification module is used for attempting to identify reminding persons according to the environmental information;

and the second reminding information broadcasting module is used for broadcasting the second reminding information based on a preset voice broadcasting rule if the attempt identification is successful.

10. The intelligent dispensing method based on the visual recognition technology is characterized by comprising the following steps of:

Step 1: acquiring medicine box attribute information of a first target medicine box;

step 2: based on the visual recognition technology, automatically supplementing a first target medicine box according to the medicine box attribute information;

Step 3: acquiring the dispensing requirement of a target patient;

step 4: determining a medicine taking scheme according to the medicine dispensing requirement and the attribute information of the medicine box;

step 5: according to the medicine taking scheme, intelligent medicine dispensing is carried out.