CN112847376A - Safe medicine purchasing robot and control method thereof - Google Patents

Safe medicine purchasing robot and control method thereof Download PDF

Info

Publication number
CN112847376A
CN112847376A CN202110142829.5A CN202110142829A CN112847376A CN 112847376 A CN112847376 A CN 112847376A CN 202110142829 A CN202110142829 A CN 202110142829A CN 112847376 A CN112847376 A CN 112847376A
Authority
CN
China
Prior art keywords
user
medicine
robot
drug
similarity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110142829.5A
Other languages
Chinese (zh)
Inventor
李亚
林煜森
戴青云
刘伯甫
罗日红
朱智锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Shenhua Pharmaceutical Co ltd
Guangdong Polytechnic Normal University
Original Assignee
Guangdong Shenhua Pharmaceutical Co ltd
Guangdong Polytechnic Normal University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Shenhua Pharmaceutical Co ltd, Guangdong Polytechnic Normal University filed Critical Guangdong Shenhua Pharmaceutical Co ltd
Priority to CN202110142829.5A priority Critical patent/CN112847376A/en
Publication of CN112847376A publication Critical patent/CN112847376A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J11/00—Manipulators not otherwise provided for
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B25J19/02—Sensing devices
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1679—Programme controls characterised by the tasks executed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00—Programme-controlled manipulators
    • B25J9/16—Programme controls
    • B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion

Landscapes

  • Engineering & Computer Science (AREA)
  • Robotics (AREA)
  • Mechanical Engineering (AREA)
  • Manipulator (AREA)

Abstract

The invention provides a safe medicine purchasing robot and a control method thereof, and the robot comprises a robot shell, a microphone, a camera, a loudspeaker, a driving structure, a control structure, a touch screen and a controller, wherein the microphone, the camera, the loudspeaker, the driving structure, the control structure, the touch screen and the controller are arranged in the robot shell, the controller is respectively electrically connected with the microphone, the camera, the loudspeaker, the driving structure, the control structure, the touch screen and the controller, the robot shell is of a humanoid structure, the top of the robot shell is arranged to be spherical and used as the head of the robot shell, the middle of the robot shell is a cylinder and extends to the bottom surface of the robot shell to be used as the body of the robot shell, two sides of the body of the robot shell are respectively provided with an arm which can only move up and down, the microphone is provided with a plurality of arms which are respectively arranged towards the front of. To accurately point out the drugs appropriate for the user.

Description

Safe medicine purchasing robot and control method thereof
Technical Field
The invention relates to a robot for safely purchasing medicine, in particular to a robot for safely purchasing medicine and a control method thereof.
Background
In fact, in spite of the current situation, convenient and fast medicine purchasing service and safe and reasonable medication mechanism constitute a contradiction community which restricts development of each other, seriously hampers the development process of the internet plus on medicine improvement, and solves the contradiction, which becomes an urgent requirement. Meanwhile, with the development of intelligent robots and the continuous release of new drugs, the demand of people on personalized and customized services is continuously strengthened, and the service robot is required to serve as a mechanical task executor in an intelligent space only and is required to serve as a customized information decision maker.
With the development of electronic commerce, more and more people prefer to purchase medicines on the internet for convenience. However, there is no necessary medication guide and blindly purchasing medication is a serious problem.
Disclosure of Invention
The invention aims to provide a safe medicine purchasing robot and a control method thereof, which are used for accurately indicating medicines suitable for users.
Therefore, the robot for safely purchasing the medicine comprises a robot shell, a microphone, a camera, a loudspeaker, a touch screen, a controller, a navigation structure and a mobile structure, wherein the microphone, the camera, the touch screen, the controller, the navigation structure and the mobile structure are arranged in the robot shell, the controller is respectively electrically connected with the microphone, the camera, the loudspeaker, the touch screen, the navigation structure and the mobile structure, the robot shell is of a humanoid structure, the top of the robot shell is of a spherical structure and is used as the head of the robot shell, the body part of the robot shell is of a cylinder structure with the diameter increasing downwards, the top surface of the cylinder structure is fixedly connected with the spherical structure, two sides of the cylinder structure are respectively provided with a movable mechanical arm, the mechanical arms are provided with pointing ends pointing out directions, the camera is arranged on the front side of the spherical structure to collect images from top to bottom, the microphones are respectively arranged on the front side of, the loudspeaker and the touch screen are respectively arranged on the front side face of the cylinder structure, the touch screen displays the result of tensor decomposition of the medicine by the controller, the moving structure is arranged on the bottom face of the cylinder structure to drive the cylinder structure to move, the navigation structure is arranged in the cylinder structure and used for outputting a navigation instruction to the controller, and the controller drives the moving structure to move.
Furthermore, the cylinder structure has a cavity, two movable cylinders which are electrically connected with the controller respectively are arranged in the cavity, a movable rod is fixedly connected to the middle of each mechanical arm, the telescopic end of each movable cylinder is connected with the end of each mechanical arm movable rod respectively, and the other end of each movable cylinder is fixed on the bottom surface of the cylinder structure cavity to realize the up-and-down movement of each arm.
Furthermore, the moving structure is a balance chassis, the diameter of the balance chassis is larger than the bottom surface of the column structure and is fixed on the bottom surface of the column structure, the bottom surface of the balance chassis is provided with a plurality of slidable wheels, and a driving shaft of each wheel is respectively connected with a servo motor electrically connected with the controller.
Furthermore, a projection display screen is arranged and is arranged on the front side surface of the spherical structure and is aligned with the front side surface of the spherical structure for projection.
Further, the navigation structure comprises a SLAM navigator and a laser radar which are respectively electrically connected with the controller.
The control method applied to the safe medicine purchasing robot runs the following steps 1 to 6, and is used for accurately indicating the medicine similar to the medicine input by the user:
step 1, collecting drug data to construct a drug library;
step 2, inputting the expected medicine purchase of the user;
step 3, calculating J medicines with similarity similar to that of the medicines expected to be purchased by the user according to the medicine types based on a recommendation model of a project collaborative filtering algorithm;
step 4, classifying the J medicines according to the disease types cured by the J medicines;
step 5, feeding back the classified result to the client;
and 6, asking the user to select any medicine to generate a selection instruction, driving the robot shell to move to a position corresponding to the medicine selected by the user according to the selection instruction, and driving the pointing end of the mechanical arm to point out the medicine.
Further, step 3 specifically includes:
(1) constructing a user-medicine scoring matrix R according to the scoring value of the medicine by the user; calculating the similarity between each medicine in the user-medicine scoring matrix R and the medicine which the user desires to purchase through a Pearson correlation coefficient formula; selecting a plurality of medicines with similarity close to the medicine expected to be purchased by the user to form a neighbor point set Nu；
(2) According to an algorithm
Figure BDA0002929657820000021
To calculate preference values p for the score values of the individual drugs in the user-drug scoring matrix Ru，tRespective preference values p obtained by calculationu，tTo form a user preference matrix UP; calculating the similarity between each medicine in the user preference matrix UP and the medicine which the user expects to purchase through a Pearson correlation coefficient formula; selecting a plurality of medicines with similarity close to that of the medicine expected to be purchased by the user to form a new neighbor point set Nu，
Wherein t represents the drug attributes of different classes, and if the drug i contains the drug attribute t, the preference value pu，tNote 1, otherwise preference value pu，tScore 0, sum (u) represents the sum of the user u's scores for a plurality of drugs i, Pu，tAn interest preference value, I, representing user u on drug attribute tu，vSet representing all drugs i evaluated by user u with drug attribute t，ru，iRepresents the user u's score for drug i;
(3) by algorithm
Figure BDA0002929657820000031
To obtain a time weight factor, and to combine the time weight factor into a scoring prediction formula, wherein the combined specific algorithm is
Figure BDA0002929657820000032
At a new set of neighbor points NuThe J medicines most similar to the medicine name input by the user u are selected.
Further, step 3 is specifically to calculate the similarity in the user-drug scoring matrix R by using a pearson correlation coefficient formula, which is as follows:
Figure BDA0002929657820000033
wherein, simR(u, v) represents the similarity of user u and user v, ruiRepresents the value of the target user u's score, r, for the target drug iviThe value of the target item i is rated on behalf of the user v.
Figure BDA0002929657820000034
And
Figure BDA0002929657820000035
representing the average values of credit, C, for user u and user v, respectivelyuvRepresenting a common set of scoring items for users u and v.
Further, a plurality of sim are obtained according to the calculationR(u, v), selecting a plurality of neighbor points which are closest to the medicine expected to be purchased by the user, and putting the neighbor points into a score value prediction formula in sequence
Figure BDA0002929657820000036
In (b) obtaining a plurality of pu，iScoring value, selecting N medicines to form a neighbor point set Nu。
Further, step 3 specifically calculates the similarity in the user preference matrix UP through the pearson correlation coefficient:
according to an algorithm
Figure BDA0002929657820000037
To find the similarity sim in the user preference matrix UPup(u, v) in neighbor set NuTo select the similarity sim with the user preference matrix UPup(u, v) the more similar K neighbor points as the new set of neighbor points NuAnd the process is carried out to the next step,
wherein,
Figure BDA0002929657820000038
and
Figure BDA0002929657820000039
representing the average value of the preference of user u and the average value of the preference of user v, CuvRepresenting a common set of scoring items for users u and v.
Has the advantages that:
the invention provides a safe medicine purchasing robot, which points out the position of a medicine to be purchased by a user through arms which are arranged at two sides of the body of a robot shell and can move up and down so as to accurately point out the medicine suitable for the user.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic structural diagram of a safe medicine purchasing robot;
FIG. 2 is a flow chart of a control method of a safe medicine purchasing robot;
FIG. 3 is a schematic structural diagram of an electronic device according to the present invention;
fig. 4 is a schematic structural diagram of a computer-readable storage medium according to the present invention.
Description of reference numerals: 1-a microphone; 2-a cylindrical structure; 3-a spherical structure; 4-touch screen; 5-arm; 6-balancing the chassis; 21-a processor; 22-a memory; 23-storage space; 24-program code; 31-program code.
Detailed Description
The invention is further described with reference to the following examples.
See fig. 1, the safe medicine purchasing robot of this embodiment, including robot housing and microphone, DLP projection display screen, camera, speaker, actuating system, control system, SLAM navigator, lidar, touch screen, the controller of setting in robot housing, the controller respectively with microphone, DLP projection display screen, camera, speaker, servo motor, SLAM navigator, lidar, touch screen electricity be connected.
The robot shell is of a humanoid structure, the top of the robot shell is spherical and serves as the head of the robot shell, the middle of the robot shell is a cylinder and extends to the bottom surface of the robot shell to serve as the body of the robot shell, two sides of the body of the robot shell are respectively provided with an arm which can only move up and down, the head of the robot shell is provided with a plurality of microphones, and the microphones face the front of the robot shell respectively so as to ensure that the robot can collect the sound of a user.
In order to realize reciprocating of arm, all be provided with the removal post in each arm, the removal post sets up at the middle part of arm and with arm integrated into one piece, the one end of each arm embedding robot shells inner wall is connected with a telescopic link that removes the cylinder respectively, the other end of each removes the cylinder and all fixes the inside of robot shells and guarantees that the telescopic link that removes the cylinder can vertical removal, each removes the cylinder and is connected with the controller electricity respectively, each removes the cylinder and is used for guaranteeing that each arm can realize reciprocating, point out the position that the user waited the medicine of purchasing to be located.
In order to ensure that the robot is not easy to be pushed down, a balance chassis is arranged at the bottom of the robot shell, a plurality of slidable wheels are arranged on the bottom surface of the balance chassis, each wheel is connected with a servo motor, and the SLAM navigator and the laser radar are used for controlling the robot to move to the position where a medicine to be purchased by a user is located.
DLP projection display screen is used for projecting the pattern of imitative people's face with one side of robot head orientation touch-control screen for improve user's use and experience.
Referring to fig. 2, based on the above-mentioned safe medicine purchasing robot structure, the following steps 1 to 6 are performed to accurately analyze the medicine of the appropriate user:
step 1, collecting data and building a database;
specifically, the operation of collecting data and establishing a database comprises the following steps:
(1) data are collected, a data source mainly obtains a Chinese health industry big data service platform medicine intelligent online purchasing database, sales records of cooperative medicine enterprises and the like in a cooperative or purchasing mode, so that detailed information of various medicines is collected, information classification such as product effective date, main treatment function, specific taking method, use contraindication, adverse reaction and the like is carried out on the collected medicine purchasing information, the collection of the traditional Chinese medicine information comprises classification of main medicine taste characters, storage environment, pharmacological action and the like of the traditional Chinese medicine, and all the collected medicine information is stored in a collection server;
(2) and (4) data preprocessing operation, namely performing clustering operation on the medicines in the cleaning acquisition server according to the characteristics of the medicines, the indications and the like in the medicine information.
Step 2, the user inputs the name of the medicine expected to be purchased;
specifically, the user inputs the name of the drug to be retrieved through the voice collector or the touch screen, and defines the user who inputs the name of the drug as the user u.
Step 3, establishing a recommendation model based on a project collaborative filtering algorithm;
specifically, the recommendation model based on the project collaborative filtering algorithm is established through the following steps:
(1) constructing a user-drug scoring matrix R according to the sales records and the drug information in the acquisition server and calculating the drug similarity;
the user-drug scoring matrix R is shown in the following formula,
Figure BDA0002929657820000051
wherein m represents the number of users, n represents the number of items, Rmn represents the value of the medicines n scored by the user m, and the value of the scoring represents the interest degree of the user in the items.
Calculating the similarity in the user-medicine scoring matrix R through a Pearson correlation coefficient formula, wherein the specific formula is as follows:
Figure BDA0002929657820000061
wherein, simR(u, v) represents the similarity of user u and user v, ruiRepresents the value of the target user u's score, r, for the target drug iviThe value of the target item i is rated on behalf of the user v.
Figure BDA0002929657820000062
And
Figure BDA0002929657820000063
representing the average values of credit, C, for user u and user v, respectivelyuvRepresenting a common set of scoring items for users u and v.
Then, a plurality of sim (u, v) which are obtained by calculation and are closest to the medicine expected to be purchased by the user are taken as neighbor points, and all the neighbor points are sequentially put into a score value prediction formula
Figure BDA0002929657820000064
In (b) obtaining a plurality of pu，iScoring value, selecting N medicines as recommendation results, wherein N isuA set of neighbor points representing user u.
(2) Constructing a user preference matrix UP and calculating the drug similarity, wherein the drug similarity is used for reflecting drug i attribute information;
a plurality of base algorithms are arranged in the user preference matrix UP
Figure BDA0002929657820000065
Calculated preference value pu，tWherein t represents the drug attribute of different classes, and if the drug i contains the drug attribute t, the preference value pu，tNote 1, otherwise preference value pu，tScore 0, sum (u) represents the sum of the user u's scores for a plurality of drugs i, Pu，tIndicates the interest preference value, I, of user u on the drug attribute tu，vRepresents a set of drug attributes t, r, among all drugs i that user u has evaluatedu，iRepresents the user u's score for drug i, matrix N.
Calculating the similarity in a user preference matrix UP through a Pearson correlation coefficient;
in particular, according to an algorithm
Figure BDA0002929657820000066
To find the similarity sim in the user preference matrix UPup(u, v) wherein,
Figure BDA0002929657820000067
and
Figure BDA0002929657820000068
representing the average value of the preference of user u and the average value of the preference of user v, CuvRepresenting a common set of scoring items for users u and v.
At neighbor set NuTo select the similarity sim with the user preference matrix UPup(u, v) the more similar K neighbor points as the new set of neighbor points NuAnd proceeds to the next step.
(3) By algorithm
Figure BDA0002929657820000069
To obtain a time weight factor, and to combine the time weight factor into a scoring prediction formula, wherein the combined specific algorithm is
Figure BDA00029296578200000610
At a new set of neighbor points NuThe J medicines most similar to the medicine name input by the user u are selected.
Wherein, tviRepresenting the time of the user v's rating of item i, tvfRepresents the earliest time, f (t), that user v scored the projectvi)Representing temporal weighting factors in the prediction scores. As can be seen from the formula, the farther the user scoring time is from the current time, the smaller the time weighting factor and the lower the predicted scoring value. Therefore, the method is more suitable for the change of human interests, and therefore, the scoring of the medicine by the user can be more accurately predicted, so that the change of human interests can be simulated.
4, carrying out tensor decomposition on J medicines which are most similar to the medicine names input by the user u according to the cured disease symptoms;
specifically, the J drugs obtained in step 3 are clustered according to the treatment effect, so that the drugs are divided into different groups to group the J drugs.
Step 5, feeding J medicines subjected to tensor decomposition back to a client;
specifically, the recommendation server feeds the J drugs after tensor decomposition back to the user through a loudspeaker and a touch screen.
And 6, prompting the user to select any one of the J medicines, driving the robot shell to move to the position corresponding to the medicine selected by the user, and indicating the approximate position of the medicine for the user.
Has the advantages that: because the traditional collaborative filtering algorithm is usually started only according to the user scoring angle when the closest point is searched, the traditional user scoring is only effective for the same medicine, the traditional search method is also willing to accept the same type of medicine when users buy the same medicine in life, and the traditional collaborative filtering method does not have the capacity of distinguishing the same type of medicine. The problem that neighbor points are lost in the traditional collaborative filtering algorithm is caused, so that the traditional collaborative filtering algorithm cannot master potential interests among users, and pain points of long tail effect cannot be solved for medicine enterprises.
Compared with the traditional collaborative filtering algorithm, the recommendation model based on the project collaborative filtering algorithm established in the embodiment is added with the project type matrix N when the matrix is established, a plurality of preference values in the project type matrix N and the time weight added with the user score are added into a similarity calculation formula, and then the similarity reflected by the preference of the user to the project attribute type and the similarity reflected by the user to the project are fused according to the set weight, so that the comprehensiveness and the accuracy when the nearest neighbor point is searched are increased; meanwhile, the influence of the user scoring time on the predicted scoring value is comprehensively considered, a time function capable of reflecting the interest attenuation of the user is provided by combining a human memory forgetting curve, and the time function is integrated into a scoring prediction formula of a traditional collaborative filtering algorithm, so that the problem of loss of neighbor points is avoided.
It should be noted that:
the method used in this embodiment can be converted into program steps and devices that can be stored in a computer storage medium, and implemented by calling and executing by a controller.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus nor is the particular language used to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices other than the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the apparatus for detecting the wearing state of an electronic device according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
For example, fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the invention. The electronic device conventionally comprises a processor 21 and a memory 22 arranged to store computer executable instructions (program code). The memory 22 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 22 has a storage space 23 storing program code 24 for performing any of the method steps in the embodiments. For example, the memory space 23 for the program code may comprise respective program code 24 for implementing respective steps in the above method. The program code can be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 4. The computer readable storage medium may have memory segments, memory spaces, etc. arranged similarly to the memory 22 in the electronic device of fig. 3. The program code may be compressed, for example, in a suitable form. In general, the memory unit stores program code 31 for performing the steps of the method according to the invention, i.e. program code readable by a processor such as 21, which when run by an electronic device causes the electronic device to perform the steps of the method described above.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (10)

1. A safe medicine purchasing robot is characterized by comprising a robot shell, a microphone, a camera, a loudspeaker, a touch screen, a controller, a navigation structure and a moving structure, wherein the microphone, the camera, the loudspeaker, the touch screen and the moving structure are arranged in the robot shell, the controller is respectively electrically connected with the microphone, the camera, the loudspeaker, the touch screen, the navigation structure and the moving structure, the robot shell is of a humanoid structure, the top of the robot shell is of a spherical structure and serves as the head of the robot shell, the body part of the robot shell is of a cylinder structure with the diameter increasing downwards, the top surface of the cylinder structure is fixedly connected with the spherical structure, two sides of the cylinder structure are respectively provided with a movable mechanical arm, the mechanical arms are provided with pointing ends pointing directions, the camera is arranged on the front side of the spherical structure to collect images from top to bottom, the microphones are provided with a plurality of mechanical arms and are respectively arranged on the, the loudspeaker and the touch screen are respectively arranged on the front side face of the cylinder structure, the touch screen displays the result of tensor decomposition of the medicine by the controller, the moving structure is arranged on the bottom face of the cylinder structure to drive the cylinder structure to move, the navigation structure is arranged in the cylinder structure and used for outputting a navigation instruction to the controller, and the controller drives the moving structure to move.
2. The safe medicine purchasing robot as claimed in claim 1, wherein the cylinder structure has a cavity, two movable cylinders are disposed in the cavity and electrically connected to the controller, a movable rod is fixedly connected to the middle of each mechanical arm, the telescopic end of each movable cylinder is connected to the end of the movable rod of each mechanical arm, and the other end of each movable cylinder is fixed to the bottom of the cavity of the cylinder structure to move the arms up and down.
3. The safe medicine purchasing robot as claimed in claim 1, wherein the moving structure is a balance chassis with a diameter greater than that of the bottom of the column structure and fixed to the bottom of the column structure, the balance chassis has a plurality of slidable wheels with respective drive shafts connected to a servo motor electrically connected to the controller.
4. The safe medicine purchasing robot as claimed in claim 1, further comprising a projection display screen, wherein the projection display screen is arranged on the front side of the spherical structure and is projected in alignment with the front side of the spherical structure.
5. The safe medicine purchasing robot as claimed in claim 1, wherein the navigation structure includes SLAM navigator and laser radar electrically connected to the controller.
6. A control method applied to the safe medicine purchasing robot of any one of claims 1 to 5, characterized by operating the following steps 1 to 6 to accurately indicate a medicine similar to a medicine input by a user:
step 1, collecting drug data to construct a drug library;
step 2, inputting the expected medicine purchase of the user;
step 3, calculating J medicines with similarity similar to that of the medicines expected to be purchased by the user according to the medicine types based on a recommendation model of a project collaborative filtering algorithm;
step 4, classifying the J medicines according to the disease types cured by the J medicines;
step 5, feeding back the classified result to the client;
and 6, asking the user to select any medicine to generate a selection instruction, driving the robot shell to move to a position corresponding to the medicine selected by the user according to the selection instruction, and driving the pointing end of the mechanical arm to point out the medicine.
7. The control method of the safe medicine purchasing robot according to claim 6, wherein the step 3 specifically comprises the following steps:
(1) constructing a user-medicine scoring matrix R according to the scoring value of the medicine by the user; calculating the similarity between each medicine in the user-medicine scoring matrix R and the medicine which the user desires to purchase through a Pearson correlation coefficient formula; selecting a plurality of medicines with similarity close to that of the medicine expected to be purchased by the user to form a neighbor point set Nu；
(2) According to an algorithm
Figure FDA0002929657810000021
To calculate preference values p for the score values of the individual drugs in the user-drug scoring matrix Ru，tRespective preference values p obtained by calculationu，tTo form a user preference matrix UP; calculating the similarity between each medicine in the user preference matrix UP and the medicine which the user desires to purchase through a Pearson correlation coefficient formula; selecting a plurality of medicines with similarity close to that of the medicine expected to be purchased by the user to form a new neighbor point set Nu，
Wherein t represents the drug attributes of different classes, and if the drug i contains the drug attribute t, the preference value pu，tNote 1, otherwise preference value pu，tScore 0, sum (u) represents the sum of the user u's scores for a plurality of drugs i, Pu，tIndicates the interest preference value, I, of user u on the drug attribute tu，vRepresents a set of drug attributes t, r, among all drugs i that user u has evaluatedu，iRepresents the user u's score for drug i;
(3) by algorithm
Figure FDA0002929657810000022
To obtain a time weight factor, and to combine the time weight factor into a scoring prediction formula, wherein the combined specific algorithm is
Figure FDA0002929657810000023
At a new set of neighbor points NuThe J medicines most similar to the medicine name input by the user u are selected.
8. The control method of the safe medicine purchasing robot according to claim 7, wherein the step 3 is specifically to calculate the similarity in the user-medicine scoring matrix R through a Pearson correlation coefficient formula, which is as follows:
Figure FDA0002929657810000024
wherein, simR(u, v) represents the similarity of user u and user v, ruiRepresents the value of the target user u's score, r, for the target drug iviThe value of the target item i is rated on behalf of the user v.
Figure FDA0002929657810000025
And
Figure FDA0002929657810000026
representing the average values of credit, C, for user u and user v, respectivelyuvRepresenting a common set of scoring items for users u and v.
9. The method for controlling the safe medicine purchasing robot according to claim 8, wherein the plurality of sim are obtained according to calculationR(u, v), selecting a plurality of neighbor points which are closest to the medicine expected to be purchased by the user, and putting the neighbor points into a score value prediction formula in sequence
Figure FDA0002929657810000027
In (b) obtaining a plurality of pu，iScoring value, selecting N medicines to form a neighbor point set Nu。
10. The method for controlling a safe medicine purchasing robot according to claim 7, wherein the step 3 is to calculate the similarity in the user preference matrix UP through the pearson correlation coefficient:
according to an algorithm
Figure FDA0002929657810000031
To find the similarity sim in the user preference matrix UPup(u, v) in neighbor set NuTo select the similarity sim with the user preference matrix UPup(u, v) the more similar K neighbor points as the new set of neighbor points NuAnd the process is carried out to the next step,
wherein,
Figure FDA0002929657810000032
and
Figure FDA0002929657810000033
representing the average value of the preference of user u and the average value of the preference of user v, CuvRepresenting a common set of scoring items for users u and v.
CN202110142829.5A 2021-02-02 2021-02-02 Safe medicine purchasing robot and control method thereof Pending CN112847376A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110142829.5A CN112847376A (en) 2021-02-02 2021-02-02 Safe medicine purchasing robot and control method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110142829.5A CN112847376A (en) 2021-02-02 2021-02-02 Safe medicine purchasing robot and control method thereof

Publications (1)

Publication Number Publication Date
CN112847376A true CN112847376A (en) 2021-05-28

Family

ID=75987705

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110142829.5A Pending CN112847376A (en) 2021-02-02 2021-02-02 Safe medicine purchasing robot and control method thereof

Country Status (1)

Country Link
CN (1) CN112847376A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113787531A (en) * 2021-10-27 2021-12-14 北京小乔机器人科技发展有限公司 Robot with medicine delivery, medicine administration management and medicine purchasing functions

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102254028A (en) * 2011-07-22 2011-11-23 青岛理工大学 Personalized commodity recommendation method and system integrating attributes and structural similarity
JP2013144354A (en) * 2012-01-13 2013-07-25 Toyota Motor Engineering & Manufacturing North America Inc Robot, computer program product, and method for trajectory plan optimization
CN105835071A (en) * 2016-06-07 2016-08-10 苏州全谱光电科技有限公司 Projection type humanoid robot
CN108818573A (en) * 2018-09-11 2018-11-16 中新智擎科技有限公司 A kind of Multifunctional service robot
CN109684538A (en) * 2018-12-03 2019-04-26 重庆邮电大学 A kind of recommended method and recommender system based on individual subscriber feature

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102254028A (en) * 2011-07-22 2011-11-23 青岛理工大学 Personalized commodity recommendation method and system integrating attributes and structural similarity
JP2013144354A (en) * 2012-01-13 2013-07-25 Toyota Motor Engineering & Manufacturing North America Inc Robot, computer program product, and method for trajectory plan optimization
CN105835071A (en) * 2016-06-07 2016-08-10 苏州全谱光电科技有限公司 Projection type humanoid robot
CN108818573A (en) * 2018-09-11 2018-11-16 中新智擎科技有限公司 A kind of Multifunctional service robot
CN109684538A (en) * 2018-12-03 2019-04-26 重庆邮电大学 A kind of recommended method and recommender system based on individual subscriber feature

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
周锡玲: "基于协同过滤的药品推荐算法研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 *
王永贵: "一种优化聚类的协同过滤推荐算法", 《计算机工程与应用》 *
邓爱林 等: "基于项目评分预测的协同过滤推荐算法", 《软件学报》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113787531A (en) * 2021-10-27 2021-12-14 北京小乔机器人科技发展有限公司 Robot with medicine delivery, medicine administration management and medicine purchasing functions

Similar Documents

Publication Publication Date Title
US20220375193A1 (en) Saliency-based object counting and localization
US10936632B2 (en) Enhanced search query suggestions
KR20180111979A (en) Semantic category classification
CN111177569A (en) Recommendation processing method, device and equipment based on artificial intelligence
JP2018533148A (en) Method and system for categorizing data
CN111295671A (en) Modular hierarchical vision system for autonomous personal companion
US20210397954A1 (en) Training device and training method
CN109409928A (en) A kind of material recommended method, device, storage medium, terminal
Willett et al. Pose2Pose: Pose selection and transfer for 2D character animation
US11775053B2 (en) Methods and systems for using artificial intelligence to analyze user activity data
US20200110778A1 (en) Search method and apparatus and non-temporary computer-readable storage medium
Artasanchez et al. Artificial Intelligence with Python: Your complete guide to building intelligent apps using Python 3. x
CN108388570A (en) The method, apparatus of classification and matching is carried out to video and selects engine
Abe et al. On the use of dance notation systems to generate movements in humanoid robots: The utility of Laban notation in robotics
US20210019358A1 (en) Methods and systems for providing an augmented reality interface for saving information for recognized objects
CN109472292A (en) A kind of sensibility classification method of image, storage medium and server
CN112847376A (en) Safe medicine purchasing robot and control method thereof
CN113240490A (en) Intelligent service transaction recommendation method and system based on graph neural network
WO2015153240A1 (en) Directed recommendations
JP6886651B2 (en) Action command generation system, response system and action command generation method
WO2022157973A1 (en) Information processing system, information processing method, and computer program
JP2012194691A (en) Re-learning method and program of discriminator, image recognition device
Naert et al. Per channel automatic annotation of sign language motion capture data
KR101655368B1 (en) Method and system to search and provide shopping postscript
CN115409579A (en) Meta-learning-based responsive recommendation method, system and equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210528