CN116934060A - Hospital call intelligent queuing method and system - Google Patents
Hospital call intelligent queuing method and system Download PDFInfo
- Publication number
- CN116934060A CN116934060A CN202311198542.XA CN202311198542A CN116934060A CN 116934060 A CN116934060 A CN 116934060A CN 202311198542 A CN202311198542 A CN 202311198542A CN 116934060 A CN116934060 A CN 116934060A
- Authority
- CN
- China
- Prior art keywords
- case
- split
- cluster
- clusters
- cases
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 79
- 238000003745 diagnosis Methods 0.000 claims abstract description 54
- 230000008569 process Effects 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 34
- 238000003064 k means clustering Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 30
- 208000024891 symptom Diseases 0.000 description 7
- 238000012804 iterative process Methods 0.000 description 6
- 230000003111 delayed effect Effects 0.000 description 3
- 238000012417 linear regression Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 229910001006 Constantan Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/02—Reservations, e.g. for tickets, services or events
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work or social welfare, e.g. community support activities or counselling services
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C11/00—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
- G07C2011/04—Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere related to queuing systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Primary Health Care (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Child & Adolescent Psychology (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Game Theory and Decision Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an intelligent queuing method and system for hospital calls, comprising the following steps: obtaining case information and all cases of registered patients; dividing all cases into a plurality of initial clusters, obtaining a case sequence according to the treatment time length of all cases, dividing the case sequence into a plurality of split clusters through different split cluster dividing modes, constructing an objective function of each split cluster dividing mode according to the characteristic parameters of all initial clusters and all cases, and dividing the case sequence into a plurality of optimal split clusters according to the split cluster dividing mode corresponding to the maximum value of the objective function; and obtaining a diagnosis time length prediction equation according to all the optimal split clusters, predicting the diagnosis time length of the registered patient according to the diagnosis time length prediction equation, and further intelligently adjusting the calling sequence. The invention saves the time wasted by the factors of disordered order, poor time concept and the like, improves the number calling efficiency and saves the consumption of invalid waiting time in the queuing process of patients.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an intelligent queuing method and system for hospital calls.
Background
The increased throughput of hospital visits, long patient queuing waiting times and crowding of waiting areas are common problems. The hospital queuing and calling system is a system for managing the hospital outpatient service flow, solves the problems of confusion, disorder, queue insertion, crowding and other sites existing in the management of the hospital queuing process, ensures that the patients are equal, orderly and orderly, creates a good working environment for medical staff, ensures that the hospitals can better cope with the increasing treatment flow, and provides more efficient and convenient medical services for the patients.
The hospital triage number calling system is a subdivision extension of the queuing number calling system and is mainly used in a complex scene of a hospital. The triage number calling system can reasonably allocate hospital resources by monitoring, collecting and analyzing hospital visit data in real time, including information such as flow rates of different clinics, average visit time, patient waiting time and the like, and optimize the queuing system so as to shorten the patient waiting time. However, the appointment patient has high appointment priority in the actual appointment process, and the appointment patient can always visit the appointment to a certain extent, and the follow-up appointment inquiry is disturbed in the number calling sequence, so that the end node of the consulting room needs to be predicted, whether the appointment patient arrives at the hospital before the current patient visit is ended or not is judged in advance, and then the number calling sequence is quickly adjusted, so that the follow-up patient visit is not delayed.
Disclosure of Invention
In order to solve the problems, the invention provides an intelligent queuing method and system for hospital calls.
The invention relates to an intelligent queuing method and system for hospital calls, which adopts the following technical scheme:
the invention provides an intelligent queuing method for hospital calls, which comprises the following steps:
obtaining case information of registered patients and all cases in a database;
obtaining a word vector of each case, and dividing all cases into a plurality of initial clusters according to the similarity of the word vectors;
obtaining a case sequence according to the treatment duration of all cases; calculating characteristic parameters of each case in the case sequence according to the initial cluster; dividing the case sequence into a plurality of split clusters according to the characteristic parameters of the case by different split cluster dividing modes; calculating expected factors of each initial cluster, constructing an objective function of each split cluster dividing mode according to the expected factors of all the initial clusters and characteristic parameters of all cases, and dividing a case sequence into a plurality of optimal split clusters according to the split cluster dividing modes corresponding to the maximum value of the objective function;
and obtaining a diagnosis time length prediction equation according to all the optimal split clusters, predicting the diagnosis time length of the registered patient according to the diagnosis time length prediction equation, and further intelligently adjusting the calling sequence.
Further, the calculating the characteristic parameters of each case in the case sequence according to the initial cluster comprises the following specific steps:
presetting a length L, obtaining a window which takes each case in the case sequence as a center and has the length equal to the preset length L, and recording the window as the window of each case; according to the window of each case, calculating the characteristic parameters of each case, wherein the specific calculation formula is as follows:
in the method, in the process of the invention,representing the sequence of casesCharacteristic parameters of the v-th case, +.>The number of cases belonging to the same initial cluster as the v-th case in the window representing the v-th case in the case sequence, L represents a preset length, +.>Mean cosine similarity representing the v-th case in the case sequence,/->Maximum value representing the average cosine similarity of all cases in a sequence of cases,/->The cosine similarity between the v-th case and the r-th case excluding the v-th case in the case sequence is represented, and M represents the number of all cases.
Further, the calculating the expected factor of each initial cluster includes the following specific steps:
in the method, in the process of the invention,a desirability factor representing the s-th initial cluster, < >>Represents the number of cases in the s-th initial cluster,/->Representing the length of the visit for the v-th case in the s-th initial cluster,/for the treatment of the v-th case>Mean value representing the duration of the visit for all cases in the s-th initial cluster,/for all cases>Expressed as natural constantAn exponential function of the bottom.
Further, the construction of the objective function of each split cluster division mode comprises the following specific steps:
where W represents an objective function of the split cluster division scheme,characteristic parameters representing the center of the d-th split cluster in the s-th initial cluster, +.>Represents the number of split clusters in the s-th initial cluster,/->A desirability factor representing the s-th initial cluster, < >>Representing the proportionality coefficient>Represents the number of cases in the s-th initial cluster, K represents the optimal cluster number, +.>Representing the length of the visit at the center of the ith split cluster in all split clusters of all initial clusters,/for all split clusters>Mean value of the time duration of the visit at the center of all split clusters representing all initial clusters,/for each cluster>Representing the local density of the ith split cluster in all split clusters of all initial clusters, +.>Mean value of local densities of all split clusters representing all initial clusters, +.>The standard deviation of the time spent on the diagnosis of all split cluster centers of all initial clusters is represented,the standard deviation of the local densities of all the split clusters of all the initial clusters, G, represents the number of all the split clusters of all the initial clusters.
Further, the case sequence is divided into a plurality of split clusters according to the characteristic parameters of the case by different split cluster division modes, and the method comprises the following specific steps:
the method comprises the steps of presetting quantity S, clustering case sequences through a DBSCAN algorithm, and dividing the case sequences into a plurality of split clusters, wherein all cases in each split cluster belong to the same initial cluster; the minimum sample number minPts of parameters in the DBSCAN algorithm is equal to the preset number S, and the size of a parameter window in the DBSCAN algorithm is equal to the preset length L;
the specific clustering process is as follows: randomly selecting a case belonging to a core point as a split cluster center, wherein the case belonging to the core point means that at least the minimum sample number minPts of cases belonging to the same initial cluster as the case belonging to the core point exists in a window of the case belonging to the core point; evaluating each case belonging to the same initial cluster as the case belonging to the split cluster center in the window of the case belonging to the split cluster center, and judging whether the case belongs to a core point or a boundary point, wherein the case belongs to the boundary point means that the number of cases belonging to the same initial cluster as the case belonging to the boundary point in the window of the case belonging to the boundary point is smaller than the minimum sample number minPts; when a cluster is surrounded by boundary points, this split cluster has been searched for completion; randomly selecting a new split cluster center and repeatedly searching for the next split cluster; and continuously and iteratively searching the next split cluster until all cases in the case sequence are divided into corresponding split clusters, and obtaining all the split clusters.
Further, the method for obtaining the prediction equation of the treatment duration according to all the optimal split clusters comprises the following specific steps:
fitting the diagnosis time length of the split cluster centers of all the optimal split clusters by using a least square method to obtain a diagnosis time length prediction equation, and taking a fitting value corresponding to the split cluster center of each optimal split cluster on the diagnosis time length prediction equation as the fitting diagnosis time length of each optimal split cluster.
Further, the step of obtaining the word vector of each case, and dividing all cases into a plurality of initial clusters according to the similarity of the word vectors comprises the following specific steps:
extracting keywords of each case, and converting the keywords into word vectors serving as the word vectors of each case;
taking cosine similarity of word vectors of any two cases as the distance between any two cases, clustering all cases by a K-Means clustering algorithm, searching an optimal clustering number K by using an elbow method in the K-Means clustering algorithm, and dividing all cases into K initial clusters.
Further, the case sequence is obtained according to the treatment duration of all cases, and the method comprises the following specific steps:
and arranging all cases according to the order of the treatment duration from small to large, and if the treatment duration is the same, arranging according to the generation time of the cases to obtain a case sequence.
Further, the predicting the diagnosis duration of the registered patient according to the diagnosis duration prediction equation includes the following specific steps:
acquiring word vectors of registered patients according to case information of the registered patients, calculating cosine similarity between the word vectors of the registered patients and word vectors at the center of each optimal split cluster, and taking fitting treatment time length of the optimal split cluster corresponding to the minimum value of the cosine similarity as prediction treatment time length of the registered patients;
the method comprises the steps of evaluating the ending time of the current visit according to the predicted visit duration of a registered patient currently in visit, informing the next appointment registered patient to arrive at a hospital consulting room as soon as possible or not to walk at will by the next appointment registered patient who arrives at the hospital consulting room before the ending time of the current visit, preparing for the visit, and calling the next appointment registered patient to make a visit preparation immediately if the next appointment registered patient does not arrive at the hospital 5 minutes before the visit of the registered patient currently in visit is ended, so as to realize intelligent adjustment of the order of the call.
The invention further provides a hospital call intelligent queuing system, which comprises a registration module, a database, a case clustering module and a prediction adjustment module; the registration module obtains case information of registered patients; the database stores the cases; the case clustering module obtains a word vector of each case, divides all cases into a plurality of initial clusters according to the similarity of the word vector, obtains a case sequence according to the treatment time of all cases, calculates the characteristic parameters of each case in the case sequence according to the initial clusters, divides the case sequence into a plurality of split clusters according to the characteristic parameters of the cases in different split cluster division modes, calculates the expected factors of each initial cluster, constructs an objective function of each split cluster division mode according to the expected factors of all the initial clusters and the characteristic parameters of all the cases, and divides the case sequence into a plurality of optimal split clusters according to the split cluster division mode corresponding to the maximum value of the objective function; the prediction adjustment module obtains a diagnosis time prediction equation according to all the optimal split clusters, predicts the diagnosis time of the registered patient according to the diagnosis time prediction equation, and further intelligently adjusts the calling sequence.
The technical scheme of the invention has the beneficial effects that: aiming at the problem that when a patient leaves or reserves the patient to be not in the time of calling in a hospital number-dividing and calling system, the follow-up enqueuing and disturbing the number-calling sequence needs to be predicted at the end node of a consulting room, and the traditional prediction method is too coarse, the invention obtains an initial cluster by clustering similarity of historical cases of the hospital, then arranges the cases according to the consultation time to obtain a case sequence, carries out fine clustering on the case sequence based on the initial cluster by a DBSCAN algorithm, iteratively screens a center of the split cluster, extracts characteristic parameters of the center case of the split cluster, sets expected factor punishment times, constructs an objective function together with the correlation coefficient of the center case of the split cluster and the consultation time, carries out split cluster iteration on each initial cluster until the objective function converges to obtain an optimal split cluster center, and is limited by the objective function, the optimal splitting cluster center has the characteristic of higher characteristic parameters, the splitting result is ensured not to cause clustering distortion of the same case by limiting the number of the splitting clusters, and the optimal splitting cluster center has higher linear correlation with the time of the doctor, the doctor's time prediction equation is obtained by carrying out linear fitting on the doctor's time of the optimal splitting cluster center, the doctor's time of a registered patient is further predicted, the next queuing patient is informed in advance, the patient is prevented from being absent when the doctor calls, or the ordering order of the patient with the reservation not arrived is adjusted, the time wasted by the factors of disordered order, poor time concept and the like is saved, the efficiency of the doctor calls is improved, the cost of invalid waiting time of the queuing process of the patient is saved, the patient is smooth, the order is orderly, a good working environment is created for medical staff, effectively improving the service image of the hospital.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of steps of a method for intelligent queuing of hospital calls according to the present invention;
fig. 2 is a system block diagram of a hospital call intelligent queuing system of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description is given below of a hospital call intelligent queuing method and system according to the invention, and the detailed implementation, structure, characteristics and effects thereof are as follows. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a hospital call intelligent queuing method and a system specific scheme by combining the drawings.
Referring to fig. 1, a flowchart of steps of a method for intelligent queuing of hospital calls according to an embodiment of the present invention is shown, the method includes the steps of:
s001, obtaining case information of registered patients and all cases in a database.
It should be noted that, in the actual treatment process, the treatment priority of the reserved patient is very high, although the treatment process can be simplified to a certain extent, the reserved patient can often go out of order, and the subsequent enqueue inquiry disturbs the number calling sequence, so that the end node of the consulting room needs to be predicted, whether the reserved patient arrives at the hospital before the current patient treatment is ended is judged in advance, and then the number calling sequence is quickly adjusted, so that the subsequent patient treatment is not delayed.
For patients, after the patients arrive at a hospital, a front medical staff registers information of the patients as patients for treatment by entering the information into a system, and a unique registration number is allocated; if the patient has made an appointment via the appointment system, they can go directly to the office at the front office and assign a unique registration number. After registration, the patient receives a ticket or displays his or her number, typically including department information and queuing order, through an electronic screen. The patient waits in the order of the number calling. Hospitals typically set up electronic screens in the lobby or waiting area to display the current number and corresponding department window.
Specifically, for a patient who makes a first visit, registration is required first when registering, basic information and a symptom description of the present visit are input into the system, and the symptom description of the present visit is recorded as case information of the registered patient; for the patients with non-primary visit, the symptom description of the patient at the present visit needs to be recorded into the system during registration, meanwhile, the history cases of the patient at each visit are searched in the system according to the personal information of the patient, and the history cases of the patient at each visit and the symptom description of the patient at the present visit are recorded as the case information of the registered patient.
Further, obtaining all cases in a database of a hospital, one case being visit data at one visit of one patient, comprising: condition description, physical examination results, diagnostic records including the duration of the visit.
S002, dividing all cases into a plurality of initial clusters, obtaining a case sequence according to the treatment time length of all cases, dividing the case sequence into a plurality of split clusters through different split cluster dividing modes, constructing an objective function of each split cluster dividing mode according to the characteristic parameters of all initial clusters and all cases, and dividing the case sequence into a plurality of optimal split clusters according to the split cluster dividing mode corresponding to the maximum value of the objective function.
It should be noted that, in the actual treatment process, the treatment priority of the reserved patient is very high, although the treatment process can be simplified to a certain extent, the reserved patient can often go out of order, and the subsequent enqueue inquiry disturbs the number calling sequence, so that the end node of the consulting room needs to be predicted, whether the reserved patient arrives at the hospital before the current patient treatment is ended is judged in advance, and then the number calling sequence is quickly adjusted, so that the subsequent patient treatment is not delayed. In order to predict the end node of a consulting room, it is necessary to predict the duration of a registered patient visit from all cases in the hospital's database and the case information of registered patients.
1. All cases are divided into several initial clusters.
When the diagnosis time of the registered patient is predicted according to all cases in the database of the hospital and the case information of the registered patient, the accuracy of predicting the diagnosis time of the registered patient according to the diagnosis record of the case with higher similarity with the case information of the registered patient is higher. Calculating the similarity between cases based on text similarity is a common task in the medical field, a word vector of each case is obtained, cosine similarity of the word vector represents case difference, all cases are clustered by using the cosine similarity of the word vector as a clustering distance, symptom similar cases are divided into an initial cluster, and then the initial cluster most similar to symptoms of registered patients can be obtained according to the similarity between case information of the registered patients and each initial cluster, and further the treatment duration of the registered patients is predicted according to the treatment time of the initial cluster.
Specifically, extracting keywords in the condition description, physical examination result and diagnosis record of each case by a keyword extraction method TF-IDF based on statistical characteristics; in the natural language field, a dictionary and a corpus such as WordNet are utilized to merge synonyms and paraphrasing words, and keywords are converted into word vectors which are used as the word vectors of each case; the method for extracting keywords by using the statistical feature-based keyword extraction method TF-IDF and converting keywords into word vectors by using a dictionary and a corpus are known techniques, and will not be described here.
Further, taking cosine similarity of word vectors of any two cases as the distance between any two cases, and clustering all cases by a K-Means clustering algorithm, wherein the parameter clustering number of the K-Means clustering algorithm is larger than 1; searching an optimal clustering number K in a K-Means clustering algorithm by using an elbow method, and dividing all cases into K initial clusters; the K-Means clustering algorithm and the method of finding the best cluster number K by using the elbow method in the K-Means clustering algorithm are all known techniques, and will not be described herein.
2. Obtaining a case sequence according to the treatment duration of all cases, dividing the case sequence into a plurality of split clusters through different split cluster dividing modes, constructing an objective function of each split cluster dividing mode according to the characteristic parameters of all initial clusters and all cases, and dividing the case sequence into a plurality of optimal split clusters according to the split cluster dividing mode corresponding to the maximum value of the objective function.
It should be noted that, in the conventional method, the average treatment time length of all cases in the initial cluster most similar to the symptoms of the registered patient is used to predict the treatment time length of the registered patient, and is used as the reference treatment time length of the patient in the case, so as to estimate the waiting time of the subsequently queued patient.
It should be further noted that, since all cases are independent, after the diagnosis duration of all cases in each initial cluster is normalized, the fitting line from short to long along the diagnosis duration is actually a direct proportional relationship curve of the length of the diagnosis duration and the type of case. However, the case type is a general concept rather than a quantifiable characteristic index, so that a proper fitting point needs to be screened, and a linear regression model of different case characteristic indexes and the time length of treatment is re-fitted. The treatment time of the case data in the same initial cluster may be distributed discretely, so that a finer clustering method is to reselect a plurality of new cluster centers to obtain local split clusters according to the distribution condition of the treatment time of the cases in the same initial cluster, and the cluster centers of the classified clusters can be used as effective fitting points of the subsequent linear regression process. In summary, the split clusters need to be formed according to the local distribution density, and thus are suitable for the DBSCAN algorithm.
Specifically, a case sequence is obtained according to the treatment time of all cases, the case sequence is divided into a plurality of split clusters through different split cluster dividing modes, an objective function of each split cluster dividing mode is constructed according to the characteristic parameters of all initial clusters and all cases, and the case sequence is divided into a plurality of optimal split clusters according to the split cluster dividing mode corresponding to the maximum value of the objective function, wherein the specific process is as follows:
(1) And arranging all cases according to the order of the treatment duration from small to large, and if the treatment duration is the same, arranging according to the generation time of the cases to obtain a case sequence.
(2) A length L is preset, where the embodiment is described by taking l=11 as an example, and the embodiment is not specifically limited, and L is determined according to the specific implementation situation. Obtaining a window which takes each case in the case sequence as a center and has the length equal to the preset length L, and recording the window as the window of each case; according to the window of each case, calculating the characteristic parameters of each case, wherein the specific calculation formula is as follows:
in the method, in the process of the invention,characteristic parameters representing the v-th case in the case sequence,/->The number of cases belonging to the same initial cluster as the v-th case in the window representing the v-th case in the case sequence, L represents a preset length, +.>Mean cosine similarity representing the v-th case in the case sequence,/->Maximum value representing the average cosine similarity of all cases in a sequence of cases,/->The cosine similarity between the v-th case and the r-th case excluding the v-th case in the case sequence is represented, and M represents the number of all cases.
The larger the value is, the more the number of cases belonging to the same initial cluster as the v-th case in the window of the v-th case is, the more the v-th case is suitable for being used as a splitting cluster center in the subsequent fine clustering, and the larger the characteristic parameter of the v-th case is; />The larger the value is, the more the v case tends to the cluster center in the corresponding initial cluster, the more the v case is suitable as the cluster center for splitting in the subsequent fine clustering, and the larger the characteristic parameter of the v case is.
It should be noted that, the feature parameter of the case characterizes whether the case is suitable for being used as a splitting cluster center in the subsequent fine clustering, so that the splitting cluster center is iterated from the case with higher feature parameter and can be used as an effective fitting point for performing the subsequent linear regression on the time length of the doctor, and in order to ensure the accuracy of the fitting result of the time length of the doctor, an optimal splitting result needs to be obtained by combining a DBSCAN algorithm and constructing an objective function through repeated iterative clustering.
It should be further noted that, in the process of combining the DBSCAN algorithm to construct the objective function through multiple iterative clustering to obtain the optimal splitting result, the splitting cluster center in the DBSCAN algorithm is randomly selected, so that the number of splitting clusters in the iterative process needs to be constrained by setting a desired factor, the variance of the time of diagnosis in the initial cluster is taken as the desired factor, the larger the variance is, the larger the difference of the time of diagnosis caused by the problems of individual physique, complications and the like in the case is represented, and the clusters can be divided more finely.
(3) A number S is preset, where the present embodiment is described by taking s=2 as an example, and the present embodiment is not specifically limited, and S is determined according to the specific implementation situation.
Specifically, clustering a case sequence by a DBSCAN algorithm, and dividing the case sequence into a plurality of split clusters, wherein all cases in each split cluster belong to the same initial cluster; two parameters in the DBSCAN algorithm need to be set, namely a minimum sample number minPts and a maximum radius epsilon of a community, in this embodiment, the minimum sample number minPts of the parameters in the DBSCAN algorithm is equal to a preset number S, and because the one-dimensional case sequences are clustered in this embodiment, the maximum radius epsilon of the parameter community in the DBSCAN algorithm should be a window size, and in this embodiment, the parameter window size in the DBSCAN algorithm is equal to a preset length L.
The specific clustering process is as follows: randomly selecting a case belonging to a core point as a split cluster center, wherein the case belonging to the core point means that at least the minimum sample number minPts of cases belonging to the same initial cluster as the case belonging to the core point exists in a window of the case belonging to the core point; evaluating each case belonging to the same initial cluster as the case belonging to the split cluster center in the window of the case belonging to the split cluster center, and judging whether the case belongs to a core point or a boundary point, wherein the case belongs to the boundary point means that the number of cases belonging to the same initial cluster as the case belonging to the boundary point in the window of the case belonging to the boundary point is smaller than the minimum sample number minPts; when a cluster is surrounded by boundary points, this split cluster has been searched for completion; randomly selecting a new split cluster center and repeatedly searching for the next split cluster; and continuously and iteratively searching the next split cluster until all cases in the case sequence are divided into corresponding split clusters, and obtaining all the split clusters.
(4) In the DBSCAN clustering process, the split clusters are formed along with the split cluster centers, and the selection of the split cluster centers is random, so that all cases in a case sequence are divided into different split clusters by the selection of different split cluster centers, all cases are divided into different split clusters by continuously changing the split cluster centers, an objective function of each split cluster division mode is constructed according to the characteristic parameters of each split cluster center and the expected factors of each split cluster in each split cluster division mode, all split clusters in the split cluster division mode corresponding to the maximum value of the objective function are used as optimal split clusters, and the final clustering result of fine clustering is achieved on all cases.
It should be noted that, by analyzing the influence of different case types represented by different split clusters on the diagnosis duration, namely, cases with higher occurrence frequency, the doctor diagnosis efficiency is higher, cases with lower frequency are diagnosed with lower efficiency, and we acquire the correlation between the case type frequency and the diagnosis time to construct an objective function.
Specifically, the objective function of each split cluster division mode is specifically:
where W represents an objective function of the split cluster division scheme,characteristic parameters representing the center of the d-th split cluster in the s-th initial cluster, +.>Represents the number of split clusters in the s-th initial cluster,/->A desirability factor representing the s-th initial cluster, < >>Representing the proportionality coefficient, the present embodiment is given by +.>The embodiment is not particularly limited, and is exemplified by =0.25, where +.>Depending on the specific implementation, the case may be->Represents the number of cases in the s-th initial cluster, K represents the optimal cluster number, and also represents the number of initial clusters, etc.>Representing the length of the visit at the center of the ith split cluster in all split clusters of all initial clusters,/for all split clusters>Mean value of the time duration of the visit at the center of all split clusters representing all initial clusters,/for each cluster>Representing the local density of the i-th cluster in all clusters of all initial clusters, in particular the ratio of the number of cases in the i-th cluster to the number of all cases in all clusters of all initial clusters,/->Mean value of local densities of all split clusters representing all initial clusters, +.>Standard deviation of the visit duration representing the centers of all split clusters of all initial clusters, +.>The standard deviation of the local densities of all the split clusters of all the initial clusters, G, represents the number of all the split clusters of all the initial clusters.
The average characteristic parameters of all the split cluster centers in the s-th initial cluster are represented, and the larger the characteristic parameters of the case are, the more suitable as the split cluster centers in the subsequent fine clustering, so that the larger the average characteristic parameters of the selected split cluster centers are, the better for the iterative process; />The larger the value representing the product of the total number of split clusters divided by the initial cluster case count and the scaling factor of the iterative process, the more the number of split clusters is represented, and as a penalty for the s-th initial cluster splitting process, i.e., the larger the average feature parameter is needed at the center of the iterative split cluster, and->Representing too many clusters to split is penalized by the hope factor +.>Limiting the number of split clusters in the iterative process, the desirability factor +.>The smaller the number of split clusters can be allowed to be larger, i.e. the desired factor +.>Multiplied by->The allowable number of the split clusters can be increased by shrinking the penalty term;covariance representing the duration of the visit and local density of the clusters, +.>Correlation coefficients representing the time duration of a visit of a split cluster and the local density, which are used to limit the obtained center of the split cluster to have a linear correlation with the time duration of a visit; therefore, will->When the objective function W takes the maximum value, the objective function converges, which means that the center of each initial cluster iterated in the time of the diagnosis in the split cluster dividing mode has higher characteristic parameters, and the number of the split clusters is limited to ensure that the split result cannot cause the cluster distortion of the same case and has higher linear correlation with the time of the diagnosis.
It should be noted that, the expected factor is used to constrain the number of split clusters in the iterative process, and the variance of the time of the diagnosis in the initial cluster is taken as the expected factor, and the larger the variance is, the larger the difference of the diagnosis time caused by the problems of individual physique, complications and the like in the cases is, the finer the cluster can be divided, i.e. the more the number of split clusters is.
Further, a specific calculation formula of the expected factor of the s-th initial cluster is as follows:
in the method, in the process of the invention,a desirability factor representing the s-th initial cluster, < >>Represents the number of cases in the s-th initial cluster,/->Representing the length of the visit for the v-th case in the s-th initial cluster,/for the treatment of the v-th case>Mean value representing the duration of the visit for all cases in the s-th initial cluster,/for all cases>An exponential function based on a natural constant is represented.
The variance of the time duration of the visit representing all cases in the initial cluster, the larger the value, the larger the number of split clusters in the initial cluster can be tolerated, by the inverse function +.>Make the expected factor->The smaller the utilization of the desired factor +.>Limiting the number of split clusters in the iterative process, the desirability factor +.>The smaller the number of split clusters can tolerate the larger.
S003, a diagnosis time length prediction equation is obtained according to all the optimal split clusters, and the diagnosis time length of the registered patient is predicted according to the diagnosis time length prediction equation, so that the calling sequence is intelligently adjusted.
Specifically, fitting the diagnosis time length of the division cluster centers of all the optimal division clusters by using a least square method to obtain a diagnosis time length prediction equation, and taking a fitting value corresponding to the division cluster center of each optimal division cluster on the diagnosis time length prediction equation as the fitting diagnosis time length of each optimal division cluster; the least squares fit linear equation is a well known technique and will not be described in detail here.
Further, according to the case information of the registered patient, the word vector of the registered patient is obtained, the cosine similarity between the word vector of the registered patient and the word vector at the center of each optimal split cluster is calculated, and the fitting treatment time length of the optimal split cluster corresponding to the minimum value of the cosine similarity is used as the prediction treatment time length of the registered patient.
Further, the end time of the current visit is estimated according to the predicted visit duration of the registered patient currently in visit, the next appointment registered patient is informed to arrive at a hospital consulting room as soon as possible or the next appointment registered patient who arrives at the hospital consulting room does not need to walk at will before the end time of the current visit, the visit is prepared, and if the next appointment registered patient does not arrive at the hospital 5 minutes before the visit of the registered patient currently in visit is finished, the next appointment registered patient is immediately called to make a visit preparation, and the intelligent adjustment of the order of calling is realized.
The method has the advantages that the treatment time of registered patients is predicted through the treatment time prediction equation, the next queuing patient is notified in advance, the situation that the patient is not present when the patient is called is avoided, or the ordering sequence adjustment is carried out on the patient with the appointment not in place, the time wasted by the factors such as disordered order, poor time concept and the like is saved, the number calling efficiency is improved, the consumption of invalid waiting time in the queuing process of the patient is saved, the patients are equal, the order is orderly, a good working environment is created for medical staff, and the service image of a hospital is effectively improved.
Referring to fig. 2, a system block diagram of a hospital call intelligent queuing system according to an embodiment of the present invention is shown, where the system includes a registration module, a database, a case clustering module, and a prediction adjustment module, and specifically includes:
the registering module is used for realizing the step of the S001 method;
the database is used for storing cases, one case is the diagnosis data of one patient at one diagnosis, and the method comprises the following steps: condition description, physical examination result, diagnosis record, wherein the diagnosis record comprises the time of diagnosis;
the case clustering module is used for realizing the step of the S002 method;
the prediction adjustment module is used for implementing the step of the method S003.
Aiming at the problem that when a patient leaves or reserves the patient to be not in the time of calling in a hospital number-dividing and calling system, the follow-up enqueuing and disturbing the number-calling sequence needs to be predicted at the end node of a consulting room, and the traditional prediction method is too coarse, the invention obtains an initial cluster by clustering similarity of historical cases of the hospital, then arranges the cases according to the consultation time to obtain a case sequence, carries out fine clustering on the case sequence based on the initial cluster by a DBSCAN algorithm, iteratively screens a center of the split cluster, extracts characteristic parameters of the center case of the split cluster, sets expected factor punishment times, constructs an objective function together with the correlation coefficient of the center case of the split cluster and the consultation time, carries out split cluster iteration on each initial cluster until the objective function converges to obtain an optimal split cluster center, and is limited by the objective function, the optimal splitting cluster center has the characteristic of higher characteristic parameters, the splitting result is ensured not to cause clustering distortion of the same case by limiting the number of the splitting clusters, and the optimal splitting cluster center has higher linear correlation with the time of the doctor, the doctor's time prediction equation is obtained by carrying out linear fitting on the doctor's time of the optimal splitting cluster center, the doctor's time of a registered patient is further predicted, the next queuing patient is informed in advance, the patient is prevented from being absent when the doctor calls, or the ordering order of the patient with the reservation not arrived is adjusted, the time wasted by the factors of disordered order, poor time concept and the like is saved, the efficiency of the doctor calls is improved, the cost of invalid waiting time of the queuing process of the patient is saved, the patient is smooth, the order is orderly, a good working environment is created for medical staff, effectively improving the service image of the hospital.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. A method for intelligent queuing of hospital calls, said method comprising the steps of:
obtaining case information of registered patients and all cases in a database;
obtaining a word vector of each case, and dividing all cases into a plurality of initial clusters according to the similarity of the word vectors;
obtaining a case sequence according to the treatment duration of all cases; calculating characteristic parameters of each case in the case sequence according to the initial cluster; dividing the case sequence into a plurality of split clusters according to the characteristic parameters of the case by different split cluster dividing modes; calculating expected factors of each initial cluster, constructing an objective function of each split cluster dividing mode according to the expected factors of all the initial clusters and characteristic parameters of all cases, and dividing a case sequence into a plurality of optimal split clusters according to the split cluster dividing modes corresponding to the maximum value of the objective function;
and obtaining a diagnosis time length prediction equation according to all the optimal split clusters, predicting the diagnosis time length of the registered patient according to the diagnosis time length prediction equation, and further intelligently adjusting the calling sequence.
2. The intelligent queuing method for hospital calls according to claim 1, wherein said calculating characteristic parameters of each case in the case sequence according to the initial cluster comprises the specific steps of:
presetting a length L, obtaining a window which takes each case in the case sequence as a center and has the length equal to the preset length L, and recording the window as the window of each case; according to the window of each case, calculating the characteristic parameters of each case, wherein the specific calculation formula is as follows:
in the method, in the process of the invention,characteristic parameters representing the v-th case in the case sequence,/->The number of cases belonging to the same initial cluster as the v-th case in the window representing the v-th case in the case sequence, L represents a preset length, +.>Mean cosine similarity representing the v-th case in the case sequence,/->Maximum value representing the average cosine similarity of all cases in a sequence of cases,/->The cosine similarity between the v-th case and the r-th case excluding the v-th case in the case sequence is represented, and M represents the number of all cases.
3. The intelligent queuing method for hospital calls according to claim 1, wherein said calculating the desirability factor for each initial cluster comprises the steps of:
in the method, in the process of the invention,a desirability factor representing the s-th initial cluster, < >>Represents the number of cases in the s-th initial cluster,/->Representing the length of the visit for the v-th case in the s-th initial cluster,/for the treatment of the v-th case>Mean value representing the duration of the visit for all cases in the s-th initial cluster,/for all cases>An exponential function based on a natural constant is represented.
4. The intelligent queuing method for hospital calls according to claim 1, wherein said constructing an objective function for each split cluster partition mode comprises the following specific steps:
where W represents an objective function of the split cluster division scheme,characteristic parameters representing the center of the d-th split cluster in the s-th initial cluster, +.>Represents the number of split clusters in the s-th initial cluster,/->A desirability factor representing the s-th initial cluster, < >>Representing the proportionality coefficient>Represents the number of cases in the s-th initial cluster, K represents the optimal cluster number, +.>Representing the length of the visit at the center of the ith split cluster in all split clusters of all initial clusters,/for all split clusters>Mean value of the time duration of the visit at the center of all split clusters representing all initial clusters,/for each cluster>Representing the local density of the ith split cluster in all split clusters of all initial clusters, +.>Mean value of local densities of all split clusters representing all initial clusters, +.>Standard deviation of the visit duration representing the centers of all split clusters of all initial clusters, +.>The standard deviation of the local densities of all the split clusters of all the initial clusters, G, represents the number of all the split clusters of all the initial clusters.
5. The intelligent queuing method for hospital calls according to claim 2, wherein the case sequence is divided into a plurality of split clusters according to characteristic parameters of the cases by different split cluster division modes, comprising the following specific steps:
the method comprises the steps of presetting quantity S, clustering case sequences through a DBSCAN algorithm, and dividing the case sequences into a plurality of split clusters, wherein all cases in each split cluster belong to the same initial cluster; the minimum sample number minPts of parameters in the DBSCAN algorithm is equal to the preset number S, and the size of a parameter window in the DBSCAN algorithm is equal to the preset length L;
the specific clustering process is as follows: randomly selecting a case belonging to a core point as a split cluster center, wherein the case belonging to the core point means that at least the minimum sample number minPts of cases belonging to the same initial cluster as the case belonging to the core point exists in a window of the case belonging to the core point; evaluating each case belonging to the same initial cluster as the case belonging to the split cluster center in the window of the case belonging to the split cluster center, and judging whether the case belongs to a core point or a boundary point, wherein the case belongs to the boundary point means that the number of cases belonging to the same initial cluster as the case belonging to the boundary point in the window of the case belonging to the boundary point is smaller than the minimum sample number minPts; when a cluster is surrounded by boundary points, this split cluster has been searched for completion; randomly selecting a new split cluster center and repeatedly searching for the next split cluster; and continuously and iteratively searching the next split cluster until all cases in the case sequence are divided into corresponding split clusters, and obtaining all the split clusters.
6. The intelligent queuing method for hospital calls according to claim 1, wherein said obtaining the prediction equation of the time length of a visit according to all the optimal split clusters comprises the following specific steps:
fitting the diagnosis time length of the split cluster centers of all the optimal split clusters by using a least square method to obtain a diagnosis time length prediction equation, and taking a fitting value corresponding to the split cluster center of each optimal split cluster on the diagnosis time length prediction equation as the fitting diagnosis time length of each optimal split cluster.
7. The intelligent queuing method for hospital calls according to claim 1, wherein the steps of obtaining the word vector of each case, dividing all cases into a plurality of initial clusters according to the similarity of the word vectors, and comprises the following specific steps:
extracting keywords of each case, and converting the keywords into word vectors serving as the word vectors of each case;
taking cosine similarity of word vectors of any two cases as the distance between any two cases, clustering all cases by a K-Means clustering algorithm, searching an optimal clustering number K by using an elbow method in the K-Means clustering algorithm, and dividing all cases into K initial clusters.
8. The intelligent queuing method for hospital calls according to claim 1, wherein said obtaining a case sequence according to the duration of the visit of all cases comprises the following steps:
and arranging all cases according to the order of the treatment duration from small to large, and if the treatment duration is the same, arranging according to the generation time of the cases to obtain a case sequence.
9. The intelligent queuing method for hospital calls according to claim 1, wherein said predicting the time of a registered patient according to the time of a patient's visit prediction equation comprises the following steps:
acquiring word vectors of registered patients according to case information of the registered patients, calculating cosine similarity between the word vectors of the registered patients and word vectors at the center of each optimal split cluster, and taking fitting treatment time length of the optimal split cluster corresponding to the minimum value of the cosine similarity as prediction treatment time length of the registered patients;
the method comprises the steps of evaluating the ending time of the current visit according to the predicted visit duration of a registered patient currently in visit, informing the next appointment registered patient to arrive at a hospital consulting room as soon as possible or not to walk at will by the next appointment registered patient who arrives at the hospital consulting room before the ending time of the current visit, preparing for the visit, and calling the next appointment registered patient to make a visit preparation immediately if the next appointment registered patient does not arrive at the hospital 5 minutes before the visit of the registered patient currently in visit is ended, so as to realize intelligent adjustment of the order of the call.
10. The intelligent queuing system for hospital calls is characterized by comprising a registration module, a database, a case clustering module and a prediction adjustment module; the registering module obtains case information of registered patients; the database stores the cases; the case clustering module obtains a word vector of each case, divides all cases into a plurality of initial clusters according to the similarity of the word vector, obtains a case sequence according to the treatment time of all cases, calculates characteristic parameters of each case in the case sequence according to the initial clusters, divides the case sequence into a plurality of split clusters according to the characteristic parameters of the cases in different split cluster division modes, calculates expected factors of each initial cluster, constructs an objective function of each split cluster division mode according to the expected factors of all the initial clusters and the characteristic parameters of all the cases, and divides the case sequence into a plurality of optimal split clusters according to the split cluster division mode corresponding to the maximum value of the objective function; the prediction adjustment module obtains a diagnosis time prediction equation according to all the optimal split clusters, predicts the diagnosis time of the registered patient according to the diagnosis time prediction equation, and further intelligently adjusts the calling sequence.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311198542.XA CN116934060B (en) | 2023-09-18 | 2023-09-18 | Hospital call intelligent queuing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311198542.XA CN116934060B (en) | 2023-09-18 | 2023-09-18 | Hospital call intelligent queuing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116934060A true CN116934060A (en) | 2023-10-24 |
| CN116934060B CN116934060B (en) | 2023-12-29 |
Family
ID=88382888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311198542.XA Active CN116934060B (en) | 2023-09-18 | 2023-09-18 | Hospital call intelligent queuing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116934060B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576822A (en) * | 2023-11-20 | 2024-02-20 | 上海徽视科技集团有限公司 | Queuing and number calling guiding system based on Internet platform |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147762A1 (en) * | 2015-11-24 | 2017-05-25 | Jonathan Vallee | Method for Finding the Optimal Schedule and Route in Contrained Home Healthcare Visit Scheduling |
| CN111242005A (en) * | 2020-01-10 | 2020-06-05 | 西华大学 | Heart sound classification method based on improved wolf colony algorithm optimization support vector machine |
| CN111951942A (en) * | 2020-08-25 | 2020-11-17 | 河北省科学院应用数学研究所 | Outpatient clinic pre-examination triage method, outpatient clinic pre-examination triage device, outpatient clinic pre-examination triage terminal and storage medium |
| US20220415469A1 (en) * | 2019-10-03 | 2022-12-29 | Rom Technologies, Inc. | System and method for using an artificial intelligence engine to optimize patient compliance |
| CN116364251A (en) * | 2023-03-08 | 2023-06-30 | 清华大学 | Waiting queuing optimization method, waiting queuing optimization device and storage medium |
-
2023
- 2023-09-18 CN CN202311198542.XA patent/CN116934060B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170147762A1 (en) * | 2015-11-24 | 2017-05-25 | Jonathan Vallee | Method for Finding the Optimal Schedule and Route in Contrained Home Healthcare Visit Scheduling |
| US20220415469A1 (en) * | 2019-10-03 | 2022-12-29 | Rom Technologies, Inc. | System and method for using an artificial intelligence engine to optimize patient compliance |
| CN111242005A (en) * | 2020-01-10 | 2020-06-05 | 西华大学 | Heart sound classification method based on improved wolf colony algorithm optimization support vector machine |
| CN111951942A (en) * | 2020-08-25 | 2020-11-17 | 河北省科学院应用数学研究所 | Outpatient clinic pre-examination triage method, outpatient clinic pre-examination triage device, outpatient clinic pre-examination triage terminal and storage medium |
| CN116364251A (en) * | 2023-03-08 | 2023-06-30 | 清华大学 | Waiting queuing optimization method, waiting queuing optimization device and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 周金海;耿玉良;: "基于遗传算法的模糊聚类在临床决策分析中的研究", 医学信息, no. 11, pages 1926 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576822A (en) * | 2023-11-20 | 2024-02-20 | 上海徽视科技集团有限公司 | Queuing and number calling guiding system based on Internet platform |
| CN117576822B (en) * | 2023-11-20 | 2024-04-30 | 上海徽视科技集团有限公司 | Queuing and number calling guiding system based on Internet platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116934060B (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113592345B (en) | Medical triage method, system, equipment and storage medium based on clustering model | |
| CN116934060B (en) | Hospital call intelligent queuing method and system | |
| US20160196398A1 (en) | Data analysis mechanism for generating statistics, reports and measurements for healthcare decisions | |
| CN108665148B (en) | Electronic resource quality evaluation method and device and storage medium | |
| CN106446575B (en) | The method and system of intelligently pushing medical resource | |
| CN108461130B (en) | Intelligent scheduling method and system for treatment tasks | |
| CN110909222A (en) | User portrait establishing method, device, medium and electronic equipment based on clustering | |
| CN112819054A (en) | Slice template configuration method and device | |
| CN113792920B (en) | Single-consulting-room-oriented hospital consultation sequence optimization method and device | |
| Dai et al. | Recent modeling and analytical advances in hospital inpatient flow management | |
| Thomas Schneider et al. | Allocating emergency beds improves the emergency admission flow | |
| CN110491475A (en) | A kind of menu recommendation process method and device | |
| CN109784848A (en) | Hotel's order processing method and Related product | |
| CN117594206A (en) | Patient integrated triage system and method based on medical interconnection platform | |
| CN116932906A (en) | Search term pushing method, device, equipment and storage medium | |
| JP2008158748A (en) | Variable selection device and method, and program | |
| WO2020192136A1 (en) | Queuing method and device enabling smart transfer | |
| Bertsimas et al. | Hospital-wide inpatient flow optimization | |
| Prokofyeva et al. | Clinical pathways analysis of patients in medical institutions based on hard and fuzzy clustering methods | |
| JP2021524112A (en) | Information processing equipment, control methods and non-temporary storage media | |
| Fan et al. | Appointment scheduling optimization with two stages diagnosis for clinic outpatient | |
| CN110162535B (en) | Search method, apparatus, device and storage medium for performing personalization | |
| CN113223677A (en) | Doctor matching method and device for patient | |
| Khaleghi et al. | A tree based approach for multi-class classification of surgical procedures using structured and unstructured data | |
| Izady et al. | Reconfiguration of inpatient services to reduce bed pressure in hospitals |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |