CN113823394A - Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm - Google Patents
Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm Download PDFInfo
- Publication number
- CN113823394A CN113823394A CN202111383003.4A CN202111383003A CN113823394A CN 113823394 A CN113823394 A CN 113823394A CN 202111383003 A CN202111383003 A CN 202111383003A CN 113823394 A CN113823394 A CN 113823394A
- Authority
- CN
- China
- Prior art keywords
- department
- ant
- determining
- departments
- pheromone
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003745 diagnosis Methods 0.000 title claims abstract description 50
- 239000003016 pheromone Substances 0.000 claims abstract description 82
- 241000257303 Hymenoptera Species 0.000 claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000004364 calculation method Methods 0.000 claims description 23
- 230000007704 transition Effects 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 239000000126 substance Substances 0.000 claims description 8
- 230000001186 cumulative effect Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 5
- 238000011144 upstream manufacturing Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
Images
Classifications
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Public Health (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent diagnosis guiding method, system, equipment and medium based on an ant colony algorithm, wherein the method comprises the following steps: acquiring department information; initializing pheromone intensity and ant colony; determining an optimal path by adopting an ant colony algorithm, and taking the determined optimal path as the department sequence with the least total time consumption of the medical staff to realize diagnosis guide: determining the expected degree of transfer among ant departments; determining the transfer probability among ant departments; determining paths of ants to all departments by adopting roulette; determining the total time consumption of each ant reaching all departments; determining an optimal path by taking the minimum total time consumption as an optimization target; updating pheromone intensity; judging whether iteration ending conditions are met, if so, using the determined optimal path as the department sequence with the least total time consumption of the staff for seeing a doctor to realize diagnosis guide; if not, the ant colony algorithm after the intensity of the pheromone is updated is continuously adopted to determine the optimal path. The invention is based on the ant colony algorithm, aims at the minimum time consumption, reasonably leads the doctor and improves the diagnosis efficiency.
Description
Technical Field
The present invention relates to the field of intelligent medical treatment, and more particularly, to an ant colony algorithm-based intelligent diagnosis guiding method, system, device, and medium.
Background
The prior informatization management system of the medical service organization focuses on the informatization management of the organization, ignores the subjective diagnosis experience of the diagnosis personnel, moreover, the system is disjointed to a certain extent from the latest artificial intelligence technology, the intelligence level of information management is low, for example, for the doctor notification of the waiting staff, the existing medical service institution generally displays the name of the waiting staff through manual number calling or an LED display screen, and the doctor often does not know the position distance of each department in the hospital, or the reason that the number of the patients waiting for a doctor in real time in each department is unclear, the doctor journey cannot be reasonably planned, the patients are often discharged out of the department with a large number of the patients waiting for a doctor for a long time, and under the condition that no one exists outside other departments, the queuing efficiency is low, a large amount of time is wasted, the treatment experience of the treatment personnel is influenced, and the waste of medical manpower or material resources is caused at the same time.
Disclosure of Invention
The invention aims to overcome at least one defect (deficiency) of the prior art, and provides an ant colony algorithm-based intelligent diagnosis guiding method, system, equipment and medium, which are used for solving the problems that the diagnosis staff cannot reasonably plan the diagnosis journey and the diagnosis experience is poor.
The invention adopts the technical scheme that an intelligent diagnosis guiding method based on an ant colony algorithm comprises the following steps:
acquiring department information which comprises the average single-time completion visit time of each departmentDepartment room transfer matrixDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentWherein i and j represent department numbers, i =1,2, …, N, j =1,2, …, N represents the number of departments, t represents time t,indicating the possibility of transfer to department j after the visit to department i is completed,represents the distance between department i and department j;
initializing pheromone intensity and ant colony in the ant colony algorithm;
determining an optimal path using the ant colony algorithmDetermining the optimal pathAs the sequencing of the departments with the least total time consumption of the staff for seeing a doctor, the method realizes the diagnosis guide:
according to the average time of single visit of each departmentDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
According to the expected degree of transferring each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department j;
According to the transfer probability of each ant from department i to department jDetermining paths of ants to reach all departments by roulette;
According to the expected degree of transferring each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
Completing the path from each ant to all departments with the minimum total time consumption as the optimization targetTo determine the optimal path;
judging whether the iteration end condition is met or not,
if yes, determining the optimal pathThe medical staff is used as the department sequencing with the least total time consumption to realize the diagnosis guidance;
if not, the ant colony algorithm after the pheromone intensity is updated is continuously adopted to determine the optimal path。
The traditional ant colony algorithm is a probabilistic algorithm for searching an optimized path, each ant in an ant colony releases corresponding pheromone in the passing path, the moving direction of the ant is guided by sensing the existence and the strength of the pheromone on the path, the ant walks along the path with higher pheromone concentration, the amount of the pheromone released by the ant with shorter path is more, the pheromone concentration accumulated on the shorter path is gradually increased along with the advance of time, the number of the ants selecting the path is more and more, and finally, the whole ant is concentrated on the shortest path under the action of positive feedback. In the invention, the distance minimization target in the traditional ant colony algorithm is converted into the total time consumption minimization target by adaptively modifying the medical scene of the traditional ant colony algorithm, the whole diagnosis process is intelligently calculated by combining the clinic information of the diagnosis of the patient, such as the average single completion diagnosis time of each clinic, the upstream and downstream relation of the diagnosis process, the distance, the number of real-time waiting patients and other factors, the total time consumption of the whole diagnosis process is sorted by the clinic, the diagnosis of the patient is guided by the calculated clinic sorting, the diagnosis process of the patient is reasonably planned, the time consumption of the patient is saved, the queuing efficiency and the experience of the patient are improved, the intellectualization of the medical system data application of the medical service institution is realized, and the informatization management level of the medical service institution is improved. Meanwhile, the department ranking result obtained through the ant colony optimization calculation can be dynamically updated according to the real-time queuing condition of the medical staff or the departments, and the reasonability and the reliability of the obtained department ranking are further improved.
Further, according to the average time of single visit of each departmentDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department jThe method specifically comprises the following steps:
determining the expected degree of transfer of each ant in the ant colony from department i to department j by using the following calculation formula:
In the present invention, the desired degree of transferThe method is not only related to the distance between departments, but also related to the average single-time completion visit time and the number of real-time waiting persons of each department, so that the ant colony algorithm is suitable for modification in a medical treatment guide scene, and various parameters related to the total time consumption of the visit are brought into a calculation consideration range, so that the final optimization result is more accurate and reliable, and the purpose of intelligently planning the visit process with the minimum total time consumption as a target is achieved.
Further, according to the expected degree of transferring each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department jThe method specifically comprises the following steps:
determining the transition probability of each ant from department i to department j by adopting the following calculation formula:
Wherein the content of the first and second substances,representing the probability of the transfer of an ant k from department i to department j in the ant colony at time t, k =1,2, … …, M representing the number of ants,
representing the set of departments in the ant colony that ant k has not reached, as the algorithm proceeds,the set is continually getting smaller, until empty,
is an important process factor for the pheromone,the importance factor of the expected degree of transfer between departments determines which factor of pheromone and the expected degree of transfer between departments plays a greater role.
Further, according to the expected degree of transferring each ant from department i to department jDetermining the total time spent by each ant to reach all departmentsThe method specifically comprises the following steps:
determining the total time spent by each ant to reach all departments by adopting the following calculation formula:
Further, with the minimum total time consumption as an optimization target, completing the path from each ant to all departmentsTo determine the optimal pathThe method specifically comprises the following steps:
the following calculation formula is adopted to find the leechesWhen ants complete the total consumption to all departmentsAnd obtains the corresponding ant number:
According to the obtained ant numberOn each ant completing the path to all departmentsIn determining the optimal path。
Further, the optimal path is determinedAnd then, updating the intensity of the pheromone, which specifically comprises the following steps:
the pheromone intensity is updated using the following calculation:
wherein the content of the first and second substances,indicates the intensity of the pheromone for department j at time t,an empirical coefficient representing the range (0,1),show departmentPheromone increments.
Further, the iteration end condition includes: and the iteration times reach the maximum iteration times or the pheromone intensity reaches the pheromone intensity threshold, wherein the iteration times are the updating times of the pheromone intensity.
In the invention, the iteration ending condition of the ant colony algorithm is set, so that the waste of computing resources and time caused by continuous computation of the ant colony algorithm is avoided, the computing burden of a system is increased, the complexity of the algorithm is effectively reduced, the diagnosis guiding rate is accelerated, and the diagnosis experience of the diagnosis personnel is improved.
On the other hand, another technical scheme adopted by the invention is that an intelligent diagnosis guide system based on an ant colony algorithm comprises:
a department information acquisition module for acquiring department information including average single visit time of each departmentDepartment room transfer matrixDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentWherein i and j represent department numbers, i =1,2, …, N, j =1,2, …, N represents the number of departments, t represents time t,indicating the possibility of transfer to department j after the visit to department i is completed,represents the distance between department i and department j;
the initialization module is used for initializing pheromone intensity and ant colony in the ant colony algorithm;
an optimized path determining module for determining an optimal path by using the ant colony algorithmDetermining the optimal pathThe medical staff is used as the department sequencing with the least total time consumption to realize the diagnosis guidance;
the optimized path determining module specifically includes:
a transfer expectation degree determining module for determining the average single visit time according to the departmentsDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
A transfer probability determining module for determining transfer expectation degree of each ant from department i to department jPheromoneIntensity and transfer matrix for each departmentDetermining the transition probability of each ant from department i to department j;
A path determining module for determining the transfer probability of each ant from department i to department jDetermining paths of ants to reach all departments by roulette;
A total time consumption determining module for determining the expected degree of transfer of each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
An optimal path determining module for completing the paths from the ants to all departments with the minimum total time consumption as the optimization targetTo determine the optimal path;
A pheromone intensity updating module for determining the optimal pathThen, updating the intensity of the pheromone;
an iteration ending condition judging module for judging whether the current time is fullIf the iteration is enough to finish the condition, determining the determined optimal pathThe department ranking with the least total time consumption of the personnel in the clinic is used for realizing the diagnosis guide, if not, the ant colony algorithm after the pheromone intensity is updated is continuously adopted to determine the optimal path。
On the other hand, another technical solution adopted by the present invention is that a computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above-mentioned ant colony algorithm-based intelligent diagnosis guiding method when executing the computer program.
On the other hand, another technical solution adopted by the present invention is a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-mentioned intelligent diagnosis guiding method based on ant colony algorithm.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, through adaptive modification of medical scenes of a traditional ant colony algorithm, the distance minimized target in the traditional ant colony algorithm is converted into a total time consumption minimized target, and by combining the department information of the visit staff, such as the average single visit time of each department, the upstream and downstream relation, the distance, the number of real-time waiting people and other factors, the whole visit flow of the visit staff is intelligently calculated, the total time consumption is minimum, the department sequence is calculated, the visit staff is guided through the calculated department sequence, the visit journey of the visit staff is reasonably planned, the visit time consumption of the visit staff is favorably saved, the queuing efficiency and the experience of the visit staff are improved, the intellectualization of the data application of a medical system is realized, and the informatization management level of a medical service mechanism is improved; meanwhile, the department ranking result obtained by the ant colony algorithm optimization calculation can be dynamically updated according to the real-time queuing condition of the medical staff or departments, and the reasonability and reliability of the obtained department ranking are further improved.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a flowchart of step S3 of the method of the present invention.
FIG. 3 is a block diagram of the system of the present invention.
Description of reference numerals: the system comprises a department information acquisition module 100, an initialization module 200, an optimized path determination module 300, a transfer expectation degree determination module 310, a transfer probability determination module 320, a path determination module 330, a total time consumption determination module 340, an optimal path determination module 350, a pheromone intensity updating module 400 and an iteration ending condition judgment module 500.
Detailed Description
The drawings are only for purposes of illustration and are not to be construed as limiting the invention. For a better understanding of the following embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
Example 1
As shown in fig. 1, the present embodiment provides an intelligent diagnosis guiding method based on ant colony algorithm, including the following steps:
s1: acquiring department information;
specifically, in the present embodiment, department numbers i and j are represented, i =1,2, …, N, j =1,2, …, N represents the number of departments, and the department information includes:
(1) the position coordinates of each department position database are as follows:
(2) the average single visit time of each department:
(3) the transfer matrix of each department mainly reflects the upstream and downstream relationship of each department in the treatment process:
to be provided withThe elements of the matrix, i.e. the possibility of transfer to department j after the end of the visit at department i, are in particular:
(4) each family room distance matrix:
to be provided withRepresenting the distance between the elements in the matrix, i.e. department i to department j;
(5) the number of people waiting for the department at the current moment t:
specifically, the real-time waiting number of people in each department can be counted by using a target detection technology based on computer vision, specifically, a camera near each department is accessed to a background server in a real-time picture, the number of people in the real-time picture is analyzed and discriminated by using a computer vision algorithm, and the real waiting number of people is counted;
s2, initializing pheromone intensity and ant colony in the ant colony algorithm;
specifically, in the present embodiment,
initializing pheromone intensities to assign a dimensionless one unit intensity to each departmentThe pheromone of degree, i.e. the pheromone intensity array, is specifically:the length of the array is the number N of departments;
and initializing an ant colony, setting an ant colony scale M,randomly distributing a path starting department for each ant in the ant colony;
in addition, in this embodiment, initializing the ant colony further includes initializing a maximum number of iterations;
Specifically, as shown in fig. 2, step S3 includes:
s301, according to the average single visit time of each departmentDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
Further, step S301 specifically includes:
determining the expected degree of transfer of each ant in the ant colony from department i to department j by using the following calculation formula:
S302, according to the expected degree of transferring each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department j;
Further, step S302 specifically includes:
determining the transition probability of each ant from department i to department j by adopting the following calculation formula:
Wherein the content of the first and second substances,representing the probability of the transfer of an ant k from department i to department j in the ant colony at time t, k =1,2, … …, M representing the number of ants,
representing the set of departments in the ant colony that ant k has not reached, as the algorithm proceeds,the set is continually getting smaller, until empty,
is an important process factor for the pheromone,the importance factor of the expected degree of transfer between departments determines which factor of pheromone and the expected degree of transfer between departments plays a greater role.
S303, according to the transfer probability of each ant from department i to department jDetermining paths of ants to reach all departments by roulette;
Specifically, in step S303, a roulette method is used to determine the path of each ant to reach all departmentsThe method comprises the following steps:
calculating the sum of the transfer probabilities of each ant moving to other departments not reached yet in the current department:
calculating the proportion probability of each transition probability:
calculating the cumulative percentage probability of each transition probability:
wherein each term in the cumulative percentage probability is the sum of all terms before the term in the percentage probability, which may be, for example: when the ratio probability sequence isThe cumulative percentage probability of which is;
Taking a random number with a value range between (0,1)Finding the first one greater than the cumulative ratio probability sequenceAnd returning the index, namely the next target department to be visited by the ant, and updating the department in the pathPerforming the following steps;
S304, according to the expected degree of transferring each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
Further, step S304 specifically includes: determining the total time spent by each ant to reach all departments by adopting the following calculation formula:
S305, with the minimum total time consumption as an optimization target, completing the path from each ant to all departmentsTo determine the optimal path;
Further, step S305 specifically includes:
the following calculation formula is adopted to find the total time spent by each ant to reach all departmentsAnd obtains the corresponding ant number:
According to the obtained ant numberOn each ant completing the path to all departmentsIn determining the optimal path。
further, step S4 specifically includes:
the pheromone intensity is updated using the following calculation:
wherein the content of the first and second substances,indicates the intensity of the pheromone for department j at time t,an empirical coefficient representing the range (0,1),representing department j pheromone increments.
S5, judging whether the iteration end condition is met, if yes, executing a step S6, and if not, returning to the step S3;
in this embodiment, the iteration ending condition is specifically that the iteration number reaches the maximum iteration number, and the iteration number is the update number of the pheromone intensity;
s6, determining the optimal pathThe medical guidance is realized as the sequencing of the departments with the least total time consumption of the medical staff.
Example 2
The embodiment provides an intelligent diagnosis guiding method based on an ant colony algorithm, which includes the steps that the specific steps are basically the same as those in embodiment 1, except that in this embodiment, initializing an ant colony further includes initializing an pheromone intensity threshold instead of initializing the maximum iteration number, and an iteration ending condition specifically includes that the pheromone intensity reaches the pheromone intensity threshold, but not the iteration number reaches the maximum iteration number.
Example 3
As shown in fig. 3, the present embodiment provides an intelligent diagnosis guiding system based on ant colony algorithm, including:
a department information obtaining module 100 for obtaining department information,
specifically, in this embodiment, department numbers i and j are represented, where i =1,2, …, N, j =1,2, …, N, and N represent the number of departments, and the obtained department information includes:
(1) the position coordinates of each department position database are as follows:
(2) the average single visit time of each department:
(3) the transfer matrix of each department mainly reflects the upstream and downstream relationship of each department in the treatment process:
to be provided withThe elements of the matrix, i.e. the possibility of transfer to department j after the end of the visit at department i, are in particular:
(4) each family room distance matrix:
to be provided withRepresenting the distance between the elements in the matrix, i.e. department i to department j;
(5) the number of people waiting for the department at the current moment t:
specifically, the real-time waiting number of people in each department can be counted by using an AI counting module based on a computer vision target detection technology, specifically, a camera near each department is accessed to a background server in real time, the number of people in the real-time picture is analyzed and distinguished by using a computer vision algorithm, and the real waiting number of people is counted;
an initialization module 200, configured to initialize pheromone intensities and ant colonies in an ant colony algorithm;
specifically, in the present embodiment,
initializing pheromone intensity, and distributing dimensionless pheromones with one unit intensity to each department, namely the pheromone intensity array specifically comprises the following steps:the length of the array is the number N of departments;
and initializing an ant colony, setting an ant colony scale M,randomly distributing a path starting department for each ant in the ant colony;
in addition, in this embodiment, initializing the ant colony further includes initializing a maximum number of iterations;
an optimized path determination module 300 for determining an optimal path using the ant colony algorithmDetermining the optimal pathThe medical staff is used as the department sequencing with the least total time consumption to realize the diagnosis guidance;
the optimized path determining module 300 specifically includes:
a transfer expectation degree determination module 310 for determining the average single visit time according to the departmentsDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
Further, the transfer expectation determining module 310 specifically determines the transfer expectation of each ant in the ant colony from department i to department j by using the following calculation formula:
A transfer probability determining module 320 for determining the expected degree of transfer of each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department j;
Further, the transition probability determining module 320 specifically determines the transition probability of each ant from department i to department j by using the following calculation formula:
Wherein the content of the first and second substances,representing the probability of the transfer of an ant k from department i to department j in the ant colony at time t, k =1,2, … …, M representing the number of ants,
representing the set of departments in the ant colony that ant k has not reached, as the algorithm proceeds,the set is continually getting smaller, until empty,
is an important process factor for the pheromone,the importance factor of the expected degree of transfer between departments determines which factor of pheromone and the expected degree of transfer between departments plays a greater role.
A path determining module 330, configured to determine a transition probability of each ant from department i to department j according to the determined transition probabilityDetermining paths of ants to reach all departments by roulette;
Specifically, the path determining module 330 determines paths of ants to reach all departments by using a roulette methodThe method comprises the following steps:
calculating the sum of the transfer probabilities of each ant moving to other departments not reached yet in the current department:
calculating the proportion probability of each transition probability:
calculating the cumulative percentage probability of each transition probability:
wherein each term in the cumulative percentage probability is the sum of all terms before the term in the percentage probability, which may be, for example: when the ratio probability sequence isThe cumulative percentage probability of which is;
Taking a random number with a value range between (0,1)Finding the first one greater than the cumulative ratio probability sequenceAnd returning the index, namely the next target department to be visited by the ant, and updating the department in the pathPerforming the following steps;
A total time consumption determining module 340 for determining the expected degree of transferring each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
Further, the total time consumption determining module 340 specifically determines the total time consumption of each ant reaching all departments by using the following calculation formula:
An optimal path determining module 350, configured to complete paths from the ants to all departments with minimum total time consumption as an optimization goalTo determine the optimal path;
Further, the optimal path determination module 350 determines the optimal pathThe method specifically comprises the following steps:
the following calculation formula is adopted to find the total time spent by each ant to reach all departmentsAnd obtains the corresponding ant number:
According to the obtained ant numberOn each ant completing the path to all departmentsIn determining the optimal path。
A pheromone intensity update module 400 for determining the optimal pathThen, updating the intensity of the pheromone;
further, the pheromone intensity updating module 400 specifically updates the pheromone intensity by using the following calculation formula:
wherein the content of the first and second substances,indicates the intensity of the pheromone for department j at time t,an empirical coefficient representing the range (0,1),representing department j pheromone increments.
An iteration end condition determining module 500, configured to determine whether an iteration end condition is met, and if yes, determine the determined optimal pathThe department sequence with the least total time consumption of the medical personnel is used for guiding the medical treatment, if not, the optimal path is determined by the optimal path determining module 300 by adopting the ant colony algorithm after the pheromone intensity is updated。
In this embodiment, the iteration ending condition is specifically that the iteration number reaches the maximum iteration number, and the iteration number is the update number of the pheromone strength.
Example 4
The embodiment provides an intelligent diagnosis guiding system based on an ant colony algorithm, which has a similar structure to that of embodiment 3, except that in this embodiment, the initialization ant colony of the ant colony algorithm initialization module 200 further includes an initialization pheromone intensity threshold instead of the initialization maximum iteration number, and the iteration ending condition determined by the iteration ending condition determination module 500 is specifically that the pheromone intensity reaches the pheromone intensity threshold, but not the iteration number reaches the maximum iteration number.
Example 5
The present embodiment provides a computer device, which includes a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the ant colony algorithm-based intelligent diagnosis guiding method in embodiment 1 described above when executing the computer program.
Example 6
The present embodiment provides a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the above-mentioned ant colony algorithm-based intelligent diagnosis guiding method.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the technical solutions of the present invention, and are not intended to limit the specific embodiments of the present invention. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention claims should be included in the protection scope of the present invention claims.
Claims (10)
1. An intelligent diagnosis guiding method based on an ant colony algorithm is characterized by comprising the following steps:
acquiring department information which comprises the average single-time completion visit time of each departmentDepartment room transfer matrixDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentWherein i and j represent department numbers, i =1,2, …, N, j =1,2, …, N represents the number of departments, t represents time t,indicating the possibility of transfer to department j after the visit to department i is completed,represents the distance between department i and department j;
initializing pheromone intensity and ant colony in the ant colony algorithm;
determining an optimal path using the ant colony algorithmDetermining the optimal pathAs the sequencing of the departments with the least total time consumption of the staff for seeing a doctor, the method for realizing the diagnosis guide specifically comprises the following steps:
according to the average time of single visit of each departmentDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
According to the expected degree of transferring each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department j;
According to the transfer probability of each ant from department i to department jDetermining paths of ants to reach all departments by roulette;
According to the expected degree of transferring each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
Completing the path from each ant to all departments with the minimum total time consumption as the optimization targetTo determine the optimal path;
judging whether the iteration end condition is met or not,
if yes, determining the optimal pathThe medical staff is used as the department sequencing with the least total time consumption to realize the diagnosis guidance;
2. The ant colony algorithm-based intelligent diagnosis guiding method according to claim 1, wherein the diagnosis time is determined according to the average single-time completion visit time of each departmentDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department jThe method specifically comprises the following steps:
determining the expected degree of transfer of each ant in the ant colony from department i to department j by using the following calculation formula:
3. The method as claimed in claim 1, wherein the ant colony algorithm-based intelligent diagnosis guidance method is implemented according to the expected degree of transfer of each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department jThe method specifically comprises the following steps:
determining the transition probability of each ant from department i to department j by adopting the following calculation formula:
Wherein the content of the first and second substances,represents the slave department of ant k in the ant colony at the time ti to department j, k =1,2, … …, M representing the number of ants,
representing the set of departments in the ant colony that ant k has not reached, as the algorithm proceeds,the set is continually getting smaller, until empty,
4. The method as claimed in claim 1, wherein the ant colony algorithm-based intelligent diagnosis guidance method is implemented according to the expected degree of transfer of each ant from department i to department jDetermining the total time spent by each ant to reach all departmentsThe method specifically comprises the following steps:
determining the total time spent by each ant to reach all departments by adopting the following calculation formula:
5. The method as claimed in claim 1, wherein the path from each ant to all departments is optimized with minimum total time consumptionTo determine the optimal pathThe method specifically comprises the following steps:
the following calculation formula is adopted to find the total time spent by each ant to reach all departmentsAnd obtains the corresponding ant number:
6. The ant colony algorithm-based intelligent diagnosis guiding method according to claim 1, wherein the optimal path is determinedAnd then, updating the intensity of the pheromone, which specifically comprises the following steps:
the pheromone intensity is updated using the following calculation:
7. The ant colony algorithm-based intelligent diagnosis guiding method according to claim 1, wherein the iteration end condition comprises: and the iteration times reach the maximum iteration times or the pheromone intensity reaches the pheromone intensity threshold, wherein the iteration times are the updating times of the pheromone intensity.
8. An intelligent diagnosis guide system based on an ant colony algorithm is characterized by comprising:
a department information acquisition module for acquiring department information including average single visit time of each departmentDepartment room transfer matrixDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentWherein i and j represent department numbers, i =1,2, …, N, j =1,2, …, N represents the number of departments, t represents time t,indicating the possibility of transfer to department j after the visit to department i is completed,represents the distance between department i and department j;
the initialization module is used for initializing pheromone intensity and ant colony in the ant colony algorithm;
an optimized path determining module for determining an optimal path by using the ant colony algorithmDetermining the optimal pathThe medical staff is used as the department sequencing with the least total time consumption to realize the diagnosis guidance;
the optimized path determining module specifically includes:
a transfer expectation degree determining module for determining the average single visit time according to the departmentsDistance matrix between departmentsAnd the number of people waiting for a doctor in each departmentDetermining the expected degree of transfer of each ant in the ant colony from department i to department j;
A transfer probability determining module for determining transfer expectation degree of each ant from department i to department jIntensity of pheromone and transfer matrix of each departmentDetermining the transition probability of each ant from department i to department j;
A path determining module for determining the transfer probability of each ant from department i to department jDetermining paths of ants to reach all departments by roulette;
A total time consumption determining module for determining the expected degree of transfer of each ant from department i to department jDetermining the total time spent by each ant to reach all departments;
An optimal path determining module for completing the paths from the ants to all departments with the minimum total time consumption as the optimization targetTo determine the optimal path;
A pheromone intensity updating module for determining the optimal pathThen, updating the intensity of the pheromone;
an iteration ending condition judging module for judging whether the iteration ending condition is satisfied, if so, the determined optimal pathThe department ranking with the least total time consumption of the personnel in the clinic is used for realizing the diagnosis guide, if not, the ant colony algorithm after the pheromone intensity is updated is continuously adopted to determine the optimal path。
9. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
10. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, realizing the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111383003.4A CN113823394B (en) | 2021-11-22 | 2021-11-22 | Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111383003.4A CN113823394B (en) | 2021-11-22 | 2021-11-22 | Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113823394A true CN113823394A (en) | 2021-12-21 |
CN113823394B CN113823394B (en) | 2022-04-05 |
Family
ID=78917989
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111383003.4A Active CN113823394B (en) | 2021-11-22 | 2021-11-22 | Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113823394B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116779087A (en) * | 2023-08-18 | 2023-09-19 | 江苏臻云技术有限公司 | Automatic data management system and method based on AI engine |
CN116895371A (en) * | 2023-09-08 | 2023-10-17 | 中国人民解放军空军特色医学中心 | Patient guiding method, system, terminal and storage medium based on general surgery |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080015824A1 (en) * | 2006-04-28 | 2008-01-17 | Caterpillar Inc. | Automatic hose and harness routing method and system |
US20080168704A1 (en) * | 2007-01-12 | 2008-07-17 | Mcdonald Ken | Fire ant colony killer |
CN103164616A (en) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | Intelligent hospital guide system and intelligent hospital guide method |
CN103246811A (en) * | 2013-04-25 | 2013-08-14 | 中山大学 | Medical system admission scheduling method based on ant colony optimization |
CN103327082A (en) * | 2013-06-07 | 2013-09-25 | 同济大学 | Multiple ant colony evacuation optimizing exchanging method |
US20150371135A1 (en) * | 2014-06-23 | 2015-12-24 | International Business Machines Corporation | Solving vehicle routing problems using evolutionary computing techniques |
CN106453224A (en) * | 2016-07-18 | 2017-02-22 | 北京交通大学 | Rapid convergence ant colony classification method based on adaptive dynamic pheromone |
CN110705742A (en) * | 2019-08-21 | 2020-01-17 | 浙江工业大学 | Logistics distribution method based on improved ant colony algorithm |
CN110989612A (en) * | 2019-12-17 | 2020-04-10 | 哈工大机器人(合肥)国际创新研究院 | Robot path planning method and device based on ant colony algorithm |
CN111709233A (en) * | 2020-05-27 | 2020-09-25 | 西安交通大学 | Intelligent diagnosis guiding method and system based on multi-attention convolutional neural network |
-
2021
- 2021-11-22 CN CN202111383003.4A patent/CN113823394B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080015824A1 (en) * | 2006-04-28 | 2008-01-17 | Caterpillar Inc. | Automatic hose and harness routing method and system |
US20080168704A1 (en) * | 2007-01-12 | 2008-07-17 | Mcdonald Ken | Fire ant colony killer |
CN103164616A (en) * | 2013-02-02 | 2013-06-19 | 杭州卓健信息科技有限公司 | Intelligent hospital guide system and intelligent hospital guide method |
CN103246811A (en) * | 2013-04-25 | 2013-08-14 | 中山大学 | Medical system admission scheduling method based on ant colony optimization |
CN103327082A (en) * | 2013-06-07 | 2013-09-25 | 同济大学 | Multiple ant colony evacuation optimizing exchanging method |
US20150371135A1 (en) * | 2014-06-23 | 2015-12-24 | International Business Machines Corporation | Solving vehicle routing problems using evolutionary computing techniques |
CN106453224A (en) * | 2016-07-18 | 2017-02-22 | 北京交通大学 | Rapid convergence ant colony classification method based on adaptive dynamic pheromone |
CN110705742A (en) * | 2019-08-21 | 2020-01-17 | 浙江工业大学 | Logistics distribution method based on improved ant colony algorithm |
CN110989612A (en) * | 2019-12-17 | 2020-04-10 | 哈工大机器人(合肥)国际创新研究院 | Robot path planning method and device based on ant colony algorithm |
CN111709233A (en) * | 2020-05-27 | 2020-09-25 | 西安交通大学 | Intelligent diagnosis guiding method and system based on multi-attention convolutional neural network |
Non-Patent Citations (1)
Title |
---|
LOKARE POOJA S. 等: "Solving Nurse Rostering Problem Using Ant Colony Optimization Approach", 《INTERNATIONAL JOURNAL OF MODERN TRENDS IN ENGINEERING AND RESEARCH (IJMTER)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116779087A (en) * | 2023-08-18 | 2023-09-19 | 江苏臻云技术有限公司 | Automatic data management system and method based on AI engine |
CN116779087B (en) * | 2023-08-18 | 2023-11-07 | 江苏臻云技术有限公司 | Automatic data management system and method based on AI engine |
CN116895371A (en) * | 2023-09-08 | 2023-10-17 | 中国人民解放军空军特色医学中心 | Patient guiding method, system, terminal and storage medium based on general surgery |
CN116895371B (en) * | 2023-09-08 | 2024-03-26 | 中国人民解放军空军特色医学中心 | Patient guiding method, system, terminal and storage medium based on general surgery |
Also Published As
Publication number | Publication date |
---|---|
CN113823394B (en) | 2022-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113823394B (en) | Intelligent diagnosis guiding method, system, equipment and medium based on ant colony algorithm | |
WO2021159742A1 (en) | Image segmentation method and apparatus, and storage medium | |
JP2022502112A (en) | Scheduling methods, devices, devices and computer programs for virtual objects in a virtual environment | |
KR102340984B1 (en) | An apparatus for wound management using machine learning and operations thereof | |
Ehinger et al. | When is it time to move to the next map? Optimal foraging in guided visual search | |
Alam Khan et al. | Optimal policy learning for disease prevention using reinforcement learning | |
US11393085B2 (en) | Image analysis using machine learning and human computation | |
Tang et al. | Clinician-in-the-loop decision making: Reinforcement learning with near-optimal set-valued policies | |
Memarzadeh et al. | Adaptive management of ecological systems under partial observability | |
US9256837B1 (en) | Data mining technique with shadow individuals | |
US9304895B1 (en) | Evolutionary technique with n-pool evolution | |
CN113096793A (en) | Remote medical diagnosis system based on medical images, algorithms and block chains | |
CN109871866B (en) | Model training method, device, equipment and medium for hospital infection prediction | |
EP3951795A1 (en) | Methods and apparatus for the application of reinforcement learning to animal medical diagnostics | |
Noroozi-Ghaleini et al. | Investigating the effect of vaccinated population on the COVID-19 prediction using FA and ABC-based feed-forward neural networks | |
CN116129988B (en) | Model construction method, device, equipment and medium | |
CN113257391B (en) | Course of disease management system of skin disease | |
McGahan et al. | 28 models later: model competition and the zombie apocalypse | |
CN113838573A (en) | Clinical assistant decision-making diagnosis self-learning method, device, equipment and storage medium | |
Phetrittikun et al. | Temporal Fusion Transformer for forecasting vital sign trajectories in intensive care patients | |
US10025700B1 (en) | Data mining technique with n-Pool evolution | |
Chen et al. | Reinforcement learning with potential functions trained to discriminate good and bad states | |
CN117474077B (en) | Auxiliary decision making method and device based on OAR model and reinforcement learning | |
Lane | Planning in fisheries-related systems | |
Agushaka et al. | Greater Cane Rat Algorithm (GCRA): A Nature-Inspired Metaheuristic for Optimization Problems |
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 |