CN116013541A - Resource allocation method and system for tuberculosis detection - Google Patents
Resource allocation method and system for tuberculosis detection Download PDFInfo
- Publication number
- CN116013541A CN116013541A CN202310002583.0A CN202310002583A CN116013541A CN 116013541 A CN116013541 A CN 116013541A CN 202310002583 A CN202310002583 A CN 202310002583A CN 116013541 A CN116013541 A CN 116013541A
- Authority
- CN
- China
- Prior art keywords
- target
- target area
- circulation
- personnel
- areas
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 201000008827 tuberculosis Diseases 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013468 resource allocation Methods 0.000 title claims abstract description 24
- 230000006978 adaptation Effects 0.000 claims abstract description 28
- 238000003745 diagnosis Methods 0.000 claims abstract description 26
- 239000003153 chemical reaction reagent Substances 0.000 claims abstract description 12
- 238000010586 diagram Methods 0.000 claims description 19
- 230000008901 benefit Effects 0.000 claims description 12
- 230000002457 bidirectional effect Effects 0.000 claims description 10
- 230000000875 corresponding effect Effects 0.000 description 32
- 238000012549 training Methods 0.000 description 13
- 230000008569 process Effects 0.000 description 9
- 238000002156 mixing Methods 0.000 description 8
- 238000012986 modification Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 8
- 239000013598 vector Substances 0.000 description 7
- 238000003062 neural network model Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 3
- 239000012678 infectious agent Substances 0.000 description 3
- 208000015181 infectious disease Diseases 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 208000035473 Communicable disease Diseases 0.000 description 2
- 206010011224 Cough Diseases 0.000 description 2
- 241000701806 Human papillomavirus Species 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 208000024891 symptom Diseases 0.000 description 2
- 102000009016 Cholera Toxin Human genes 0.000 description 1
- 108010049048 Cholera Toxin Proteins 0.000 description 1
- 208000017667 Chronic Disease Diseases 0.000 description 1
- 241000590002 Helicobacter pylori Species 0.000 description 1
- 241000700721 Hepatitis B virus Species 0.000 description 1
- 241000700605 Viruses Species 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 229940037467 helicobacter pylori Drugs 0.000 description 1
- 230000002458 infectious effect Effects 0.000 description 1
- 206010022000 influenza Diseases 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000003607 modifier Substances 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 206010041232 sneezing Diseases 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 241000712461 unidentified influenza virus Species 0.000 description 1
Images
Classifications
-
- 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
Abstract
The embodiment of the specification provides a resource allocation method and a system for tuberculosis detection, wherein the method comprises the steps of acquiring area characteristics and diagnosis information of a plurality of target areas; predicting epidemic risk values of a plurality of target areas at future time based on the area characteristics and the diagnosis confirming information; acquiring a resource reserve of each target area in a plurality of target areas; determining the fitness of each target area in the plurality of target areas based on the epidemic risk value and the resource reserve; determining a target allocation instruction based on the adaptation degree of each target area in the plurality of areas; and configuring resources in the plurality of target areas based on the target deployment instructions, wherein the resources include at least a detection reagent for tuberculosis detection.
Description
Technical Field
The present disclosure relates to the field of infectious disease detection management based on big data processing, and in particular, to a resource allocation method and system for tuberculosis detection.
Background
Tuberculosis is a very contagious disease, and patients can spread viruses through talking, coughing, sneezing droplets and used tableware, and eating the remaining food. In areas where tuberculosis patients occur, it is important to conduct tuberculosis detection. At present, certain resources such as a detection reagent and a detection device for tuberculosis detection are usually configured in advance in each area, but certain areas have larger demands on the resources, and the resources configured in advance often do not meet the demands of the areas, so that partial personnel in the areas cannot be detected in time, and the prevention and control of epidemic situations are delayed.
CN102713914B discloses an integrated health detection and monitoring system. The system can be used for monitoring infectious and chronic diseases. When faced with outbreaks of infectious agents such as influenza virus, the system can identify active cases by actively sampling at high risk locations such as schools or crowded commercial areas. When an event is detected, the system may allow for active management of the possible outbreaks by appropriate mechanisms, as well as predicting the best countermeasures to deploy the scarce resources. The resource allocation in the prior art is mainly based on financial conditions, basic information provided by a modeling component is provided, and then the resource allocation depends on the economic benefit of the region.
That is, the prior art has the following technical problems: the corresponding number relation of detection crowd and resources is not considered in resource allocation, and the situation that the people cannot detect in time and the situation that the resources overflow are likely to exist due to the lack of resources is reduced.
It is therefore desirable to provide a resource allocation method and system for tuberculosis detection that enables reasonable resource allocation based on regional reality.
Disclosure of Invention
One or more embodiments of the present specification provide a resource allocation method for tuberculosis detection, the method comprising: acquiring area characteristics and diagnosis information of a plurality of target areas; predicting epidemic risk values of a plurality of target areas at future time based on the area characteristics and the diagnosis confirming information; acquiring a resource reserve of each target area in a plurality of target areas; determining the fitness of each target area in the plurality of target areas based on the epidemic risk value and the resource reserve; determining a target allocation instruction based on the adaptation degree of each target area in the plurality of areas; and configuring resources in the plurality of target areas based on the target deployment instructions, the resources including at least a detection reagent for tuberculosis detection.
One or more embodiments of the present specification provide a resource allocation system for tuberculosis detection, the system comprising: the first acquisition module is used for acquiring the regional characteristics and the diagnosis confirming information of a plurality of target regions; the prediction module is used for predicting epidemic situation risk values of a plurality of target areas at future time based on the area characteristics and the diagnosis information; the second acquisition module is used for acquiring the resource reserve of each target area in the plurality of target areas; the determining module is used for determining the adaptation degree of each target area in the plurality of target areas based on the epidemic situation risk value and the resource reserve; the configuration module is used for determining a target allocation instruction based on the adaptation degree of each target area in the plurality of areas; and configuring resources in the plurality of target areas based on the target deployment instructions, the resources including at least a detection reagent for tuberculosis detection.
One or more embodiments of the present specification provide a resource allocation apparatus for tuberculosis detection, the apparatus comprising a processor for performing the resource allocation method for tuberculosis detection of any of the above embodiments.
One or more embodiments of the present specification provide a computer-readable storage medium storing computer instructions that, when read by a computer in the storage medium, perform a resource allocation method for tuberculosis detection as in any of the above embodiments.
Drawings
The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:
FIG. 1 is an exemplary block diagram of a resource allocation system for tuberculosis detection according to some embodiments of the present description;
FIG. 2 is an exemplary flow chart of a resource allocation method for tuberculosis detection according to some embodiments of the present description;
FIG. 3 is an exemplary flow chart for determining epidemic risk values, according to some embodiments of the present description;
FIG. 4 is an exemplary schematic diagram illustrating the determination of epidemic risk values, according to some embodiments of the present description;
FIG. 5A is an exemplary schematic diagram of a target area map shown in accordance with some embodiments of the present description;
fig. 5B is an exemplary schematic diagram of a personnel flow chart according to some embodiments of the present description.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.
It will be appreciated that "system," "apparatus," "unit" and/or "module" as used herein is one method for distinguishing between different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.
As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.
FIG. 1 is an exemplary block diagram of a resource allocation system for tuberculosis detection according to some embodiments of the present description. In some embodiments, the resource configuration system 100 for tuberculosis detection may include a first acquisition module 110, a prediction module 120, a second acquisition module 130, a determination module 140, and a configuration module 150.
The first acquisition module 110 may be configured to acquire region characteristics and definitive information for a plurality of target regions. For more details on regional characteristics and diagnostic information see fig. 2 and its associated description.
The prediction module 120 may be configured to predict epidemic risk values for a plurality of target areas at future times based on the area characteristics and the diagnostic information.
In some embodiments, to predict epidemic risk values for a plurality of target areas at future times based on the area characteristics and the diagnostic information, the prediction module may be configured to: predicting, for each of a plurality of target areas, a person circulation of each target area based on the area characteristics; and determining epidemic risk values of each target area at future time based on the personnel circulation degree and the diagnosis information.
In some embodiments, to determine the epidemic risk value for the each target area at the future time based on the personnel circulation and the diagnostic information, a prediction module may be configured to: constructing a target area diagram based on first information related to a plurality of target areas, wherein each first node in the target area diagram corresponds to one target area, the first node characteristics of the first nodes at least comprise personnel circulation degrees corresponding to the target areas, each first side in the target area diagram corresponds to at least one circulation route between the target areas corresponding to the two nodes respectively, and the first side characteristics of the first sides at least comprise circulation convenience degrees corresponding to the circulation routes; determining, based on the target area map, bidirectional personnel traffic of at least one of the flow routes at a future time by means of a first predictive model; constructing a personnel flow chart based on second information related to a plurality of target areas, wherein each second node in the personnel flow chart corresponds to one target area, the second node characteristics of the second nodes at least comprise diagnosis information of the target areas, each second side of the personnel flow chart corresponds to at least one flow route between the target areas corresponding to the two nodes respectively, and the second side characteristics of the second sides at least comprise bidirectional personnel flow corresponding to the flow route; and determining epidemic risk values of each target area at future moments through a second prediction model based on the personnel flow diagrams.
For more details on determining epidemic risk values see fig. 3, 4, 5 and their associated description.
The second acquisition module 130 may be configured to acquire a resource reserve for each of a plurality of target areas. For more details on resource reserves see FIG. 2 and its associated description.
The determination module 140 may be configured to determine a fitness of each of the plurality of target areas based on the epidemic risk value and the resource reserves. For more details on the adaptation of the target area, see fig. 2 and its related description.
The configuration module 150 may be configured to determine a target deployment instruction based on the fitness of each target region of the plurality of regions; and configuring resources in the plurality of target areas based on the target deployment instructions, the resources including at least a detection reagent for tuberculosis detection.
In some embodiments, to determine the target deployment instruction based on the fitness of each of the plurality of target areas, the configuration module may be to: generating a plurality of candidate allocation instructions based on the adaptation degree of each target area; determining a blending yield value of each candidate blending instruction, wherein the blending yield value is related to the adaptation degree; and determining a target allocation instruction based on the allocation profit value. For more details on determining a target deployment instruction, see FIG. 2 and its associated description.
It should be noted that the above description of the resource allocation system for tuberculosis detection and its modules is for convenience of description only, and is not intended to limit the present description to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. In some embodiments, the first acquisition module 110, the prediction module 120, the second acquisition module 130, the determination module 140, and the configuration module 150 disclosed in fig. 1 may be different modules in one system, or may be one module to implement the functions of two or more modules described above. For example, each module may share one memory module, or each module may have a respective memory module. Such variations are within the scope of the present description.
Fig. 2 is an exemplary flow chart of a resource allocation method for tuberculosis detection according to some embodiments of the present description. In some embodiments, the process 200 may be performed by the resource allocation system 100 for tuberculosis detection. As shown in fig. 2, the process 200 includes the steps of:
At step 210, regional characteristics and definitive diagnosis information for a plurality of target regions are obtained.
The target area may be an area where detection of tuberculosis cases is required. For example, the target area may include a certain province, a certain urban area, or the like, or may be each administrative area, cell, or the like in a certain urban area.
The region features may be features that are pre-correlated to the target region. For example, the regional characteristics may include resident demographics, public transportation characteristics, public road characteristics, recent population flow characteristics, and the like for the region.
The regional characteristics may be obtained in a variety of ways. For example, the resident demographics, public transportation features, public road features, etc. of the target area may be obtained by database queries. For another example, the recent population flow characteristics may be determined by counting recent population flow conditions.
The diagnosis information may be information about a person who has been infected with tuberculosis in the target area (hereinafter simply referred to as a diagnosis person). For example, the diagnostic information may include the number of diagnostic personnel in the area, the number of diagnostic personnel recently (e.g., day, week, etc.) continuously increasing, the diagnostic population characteristics, etc. Among other things, diagnostic population characteristics may include condition characteristics and flow characteristics of diagnostic personnel. The condition characteristics may include clinical symptoms manifestations of the diagnostician, such as the severity of cough, etc. The flow characteristics may include a range of life trajectories for the diagnostician, the greater the range of life trajectories the greater the likelihood of infecting others.
The diagnostic information may be determined in a number of ways. For example, diagnostic information may be obtained based on historical infection records. The historical infection record may be information about the diagnostician that was recorded when the diagnostician was detected. For example, the history may include basic information (name, age, etc.), date of diagnosis, clinical symptoms, life track range, etc. of the diagnosed person.
The future time may be some point in time or period of time in the future. For example, the future time may be one week in the future, or 10 points in the tomorrow.
The epidemic risk value may be a value representing the severity of the epidemic of the target area at a future time. For example, the epidemic risk value can be represented by a value of 0 to 10, and the greater the value, the higher the severity of the epidemic in the area.
In some embodiments, the epidemic situation of the target area can be analyzed by an expert through counting the information of the existing patient number, the personnel flow situation and the like of the target area so as to predict the epidemic risk value of the target area at the future moment.
In some embodiments, for each of the plurality of target areas, the prediction module 120 may predict a personal circulation of each target area based on the area characteristics of each target area and determine an epidemic risk value for each target area at a future time based on the personal circulation and the diagnostic information. For more details on determining epidemic risk values, see fig. 3, fig. 4 and their associated descriptions.
In some embodiments, the resource may include a detection reagent or detection device for tuberculosis detection, or the like. In some embodiments, the resource reserve may be a reserve of detection reagent and/or detection device for tuberculosis detection within the target area. For example, the resource reserve may be 1 ten thousand test reagents.
In some embodiments, the resource may also be a detection reagent or detection device for other infectious agents. Exemplary other infectious agents may include, but are not limited to, influenza, HIV, cholera toxin, helicobacter pylori, hepatitis B Virus (HBV), human Papilloma Virus (HPV), and the like.
Resource reserves can be obtained in a number of ways. For example, the resource reserves may be determined based on historical total reserves of resources, used amounts, and replenishment amounts in the database, and so forth.
The fitness of the target area may refer to the fitness of the epidemic risk value and the resource reserve. In some embodiments, the fitness may be represented by a value between 0-1, with higher values representing higher fitness.
The adaptation degree can indicate whether the resource reserves of the target area are suitable or not under the corresponding epidemic risk values. For example, when epidemic risk values are higher and resource reserves are smaller, the adaptation degree is lower; when the epidemic situation risk value is higher and the resource reserves are more, the adaptation degree is higher; when the epidemic situation risk value is low and the resource reserves are more, the adaptation degree is low; and when the epidemic risk value is low and the resource reserves are less, the adaptation degree is high.
The degree of adaptation may be determined in a number of ways. For example, the determination module 140 may determine a historical epidemic risk value that is similar or similar to the current epidemic risk value, and determine the fitness based on a ratio of historical resources reserves used at the historical epidemic risk value to the current resources reserves. As an example, assuming that the historical epidemic risk value of the target area a is 6, the corresponding used historical resource reserve is 9000 parts, the resource reserve of the target area B is 5500 parts, and when the current epidemic risk value (for example, 6.2) of the target area B is close to the historical epidemic risk value of the target area a, it may be determined that the fitness of the target area B is 5500/9000=0.61.
The target allocation instruction may be an instruction set that allocates resources between different target regions. The target allocation instruction may be comprised of a plurality of sub-allocation instructions. For example, a target deployment instruction may include region A transporting X1 units of resources to region B; region C transmits a plurality of child allocation instructions such as X2 units of resources to region D.
In some embodiments, the configuration module 150 may determine the deployment instructions based on the fitness of each target area, the epidemic risk value and the resource reserves of the respective target area. For example, the configuration module 150 may take as the target allocation instruction an instruction to allocate resources preferentially from a target area with low adaptation and high resource storage to a target area with low adaptation and low resource storage.
In some embodiments, the configuration module 150 may generate a plurality of candidate deployment instructions based on the fitness of each of the plurality of target regions; determining a blending yield value of each candidate blending instruction; and determining a target allocation instruction based on the allocation profit value.
The candidate allocation instructions may be candidate instructions to allocate resources between different target regions. For example, the candidate allocation instruction may be an instruction to allocate 1000 resources of target area a to target area B.
The candidate blend instruction may be determined in the same manner as the target blend instruction. For example, the candidate deployment instructions may be determined based on the fitness of each target area, the epidemic risk value of each target area, and the resource reserves, which are not described in detail herein.
The deployment yield value may be used to reflect a contribution value to the fitness of the target region after the candidate deployment instruction is implemented. For example, a certain candidate allocation instruction allocates 1000 resources of the target area a to the target area B, where the adaptation degree of the target area a is 0.4, the adaptation degree of the target area B is 0.5, after the candidate allocation instruction is implemented, the adaptation degree of the target area a is increased to 0.8, and the adaptation degree of the target area B is increased to 0.9, so that it can be determined that the allocation profit value of the candidate allocation instruction is higher.
In some embodiments, the deployment benefit value may also be related to circulation convenience. For example, the higher the circulation convenience between two target areas, the higher the allocation benefit value of the candidate allocation instruction for allocating the resources of the two target areas. The circulation convenience can reflect the transportation difficulty of the two target areas. For further description of the convenience of circulation, see fig. 4 and its associated description.
In some embodiments, the configuration module 150 may determine the blending yield value of the candidate blending instruction based on the circulation convenience between the two target areas and the total added value of the adaptation degree of the two target areas after the candidate blending instruction is implemented through a preset algorithm. An exemplary preset algorithm is shown in the following equation (1):
K＝m*Δh i -n*j (1)
wherein, the allocation profit value of the K candidate allocation instruction, m and n are coefficients, and delta h i And j represents the circulation convenience between the two target areas in the candidate allocation instruction.
In some embodiments of the present disclosure, by introducing circulation convenience to determine the allocation benefit value, the influence of transportation convenience on the allocation benefit value can be fully considered, so that accuracy of the allocation benefit value is improved, and a target allocation instruction which is more in line with actual conditions and has higher benefit is determined.
In some embodiments, after allocating the benefit value of each candidate allocation instruction obtained in the above manner, the allocation module 150 may select, as the target allocation instruction, a candidate allocation instruction in which the allocation benefit value satisfies the benefit threshold and does not conflict with each other. Wherein, the non-conflict may mean that the two target areas contained in the candidate allocation instruction are different.
In some embodiments of the present disclosure, by selecting one or more candidate allocation instructions with the highest allocation profit value as a target allocation instruction and allocating resources of each target area, the cost of transporting resources can be saved to the greatest extent, and meanwhile, the transportation efficiency is improved, so that the allocation scheme is more practical, and the adaptation degree of multiple target areas is improved.
In step 260, resources in the plurality of target areas are configured based on the target deployment instruction.
In some embodiments, provisioning module 150 may configure resources in multiple target areas according to target provisioning instructions. For example, assuming that a certain target allocation instruction includes allocating 1000 resources from target area a to target area B and 500 resources from target area C to target area D, allocation module 150 may allocate resources of target area a, target area B, target area C, and target area D according to the target allocation instruction.
In some embodiments, the provisioning module 150 may select an appropriate vehicle to configure resources in multiple target areas based on the target provisioning instructions and the cost of transportation for each traffic route between the two target areas. For example, for the target allocation instruction in the foregoing example, the traffic route for allocating the resource from the target area a to the target area B includes 2 routes, one is a train route and one is a truck route, and when the transportation cost corresponding to the truck route is low, the truck may be selected to allocate the resource from the target area a to the target area B.
In some embodiments of the specification, the resources are configured by a resource configuration method of tuberculosis detection. The resource allocation efficiency can be greatly improved, the allocation scheme is more in accordance with the actual situation, and each target area can obtain enough detection reagent as soon as possible, so that the epidemic prevention difficulty is greatly reduced.
FIG. 3 is an exemplary flow chart for determining epidemic risk values, according to some embodiments of the present description. In some embodiments, the process 300 may be performed by the prediction module 120. The process 300 may be performed for each of a plurality of target areas. As shown in fig. 3, the process 300 includes the steps of:
The personnel circulation degree refers to an index for measuring the personnel circulation condition between a plurality of target areas. In some embodiments, the popularity of a target area may be represented by an additive summation of the number of people entering/exiting the target area. For example, the number of people entering the target area a is 1000, and the number of people exiting the target area a is 1200, and the circulation of people in the target area a is 2200. In some embodiments, the popularity of a target area may be represented by the number of people entering/exiting the target area, respectively. For example, the number of people entering the target area A is 1000, and the number of people exiting the target area A is 1200, and the circulation degree of people in the target area A is +1000 and-1200.
In some embodiments, the personal communication may include a plurality of dimensions of personal communication. Wherein the plurality of dimensions corresponds to a plurality of ways of going and going between the target areas. For example, the various means of arrival and departure may include, but are not limited to, public transportation (e.g., subways, buses, etc.), long distance traffic (e.g., trains, planes, etc.), motor vehicle self-driving, walking, etc. Accordingly, the personnel circulation may include personnel conditions circulated between the target areas by various means of passing.
In some embodiments of the present disclosure, the personnel circulation degree is divided into personnel circulation degrees with multiple dimensions, so that the personnel circulation conditions between multiple target areas can be reflected more accurately.
In some embodiments, the prediction module 120 may predict the personal circulation by a variety of means. For example, the prediction module 120 may obtain the number of people entering/exiting the target area through a card swiping record, road monitoring, mobile phone positioning, or any combination thereof, so as to predict the circulation of people in the target area.
In some embodiments, the prediction module 120 may predict the popularity of each target region by a popularity model based on the region characteristics.
The people traffic model may be a machine learning model for predicting people traffic of the target area. For example, the personal mobility model may include one of a Neural Network (NN) model, a convolutional Neural network (Convolutional Neural Networks, CNN) model, or the like, or any combination thereof.
In some embodiments, the input of the people traffic model may include regional characteristics of a plurality of target regions. For example, the input of the people traffic model may include the regional characteristics of the target region a, the regional characteristics of the target region B, and the like. For more details regarding regional features, see step 210 and its associated description.
In some embodiments, the output of the people traffic model may include people traffic for a plurality of target areas. For example, the output of the people traffic model may include the people traffic of the target area a, the people traffic of the target area B, and so on.
In some embodiments, the people traffic model may be composed of a feature embedding layer and a determination layer.
The feature embedding layer may be a machine learning model for acquiring feature vectors corresponding to region features of a plurality of target regions. For example, the feature embedding layer may include CNN, DNN, and the like. In some embodiments, the input of the feature embedding layer may include region features of a plurality of target regions. For example, the input of the feature embedding layer may include the region features of the target region a, the region features of the target region B, and the like. The output of the feature embedding layer may include feature vectors corresponding to the region features of the plurality of target regions. For example, the output of the feature embedding layer may include a feature vector corresponding to the region feature of the target region a, a feature vector corresponding to the region feature of the target region B, and the like.
The determination layer may be a machine learning model for determining the popularity of persons for a plurality of target areas. For example, the determination layer may include CNN, DNN, and the like. In some embodiments, the input of the determination layer may include the output of the feature extraction layer, i.e., the feature vectors corresponding to the region features of the plurality of target regions. For example, the input of the determination layer may include a feature vector corresponding to the region feature of the target region a, a feature vector corresponding to the region feature of the target region B, and the like. The output of the determination layer may include the personal circulation of the plurality of target areas. For example, the output of the feature embedding layer may include the person's circulation of the target area a, the person's circulation of the target area B, and so on.
In some embodiments, the personal mobility model may be obtained by training a plurality of first training samples with first tags. For example, a plurality of first training data with first labels may be input into the initial personnel circulation model, a loss function is constructed through the results of the first labels and the initial personnel circulation model, and parameters of the initial personnel circulation model are iteratively updated based on the loss function. When the loss function of the initial personnel circulation model meets the preset condition, model training is completed, and a trained personnel circulation model is obtained. The preset condition may be that the loss function converges, the number of iterations reaches a threshold value, etc.
In some embodiments, the first training sample of the personal mobility model may include sample region features of a plurality of sample target regions; the first tag may include actual personnel circulation corresponding to each sample target area. The actual personnel circulation degree of the target area can be determined through manual labeling based on the historical personnel circulation condition of the target area.
In some embodiments of the present disclosure, the area features of each target area are processed through the personnel circulation model, so as to determine the personnel circulation degree of the target area, thereby improving the efficiency and accuracy of determining the personnel circulation degree of each target area.
In some embodiments, the prediction module 120 may determine the epidemic risk value for the target area at a future time in a variety of ways. For example, the prediction module 120 may determine whether the personnel circulation and the diagnosis information of the target area meet a preset condition, and if the preset condition is met, the epidemic risk value of the target area at a future time is greater than a risk value threshold. The preset conditions and the risk value threshold values can be preset in advance, default in a system, manually set based on experience, and the like or any combination thereof. For example, the preset condition may be that the circulation of people in the target area is greater than 1000 people, and the number of confirmed diagnoses and the number of consecutive new increases are greater than 200 people and 50 people, respectively.
In some embodiments, the prediction module 120 may also determine an epidemic risk value for each of the plurality of target areas at a future time by constructing a target area map and a personnel flow map, and processing the target area map by the first prediction model and the personnel flow map by the second prediction model, respectively. For more details on determining epidemic risk values see fig. 4 and its associated description.
In some embodiments of the present disclosure, the circulation of people in each of a plurality of target areas is predicted by the area features, and then the epidemic risk value of the target area at a future time is determined based on the circulation of people and the diagnosis confirmation information, so that the circulation of people and the diagnosis confirmation information of the target area are considered, and the reliability of the finally determined epidemic risk value is higher.
It should be noted that the above description of the flow 200 and the flow 300 is for illustration and description only, and is not intended to limit the scope of applicability of the present description. Various modifications and changes to flow 200 and flow 300 may be made by those skilled in the art under the guidance of this specification. However, such modifications and variations are still within the scope of the present description.
FIG. 4 is an exemplary schematic diagram illustrating the determination of epidemic risk values according to some embodiments of the present description.
In some embodiments, the prediction module 120 may construct a target region map based on first information related to a plurality of target regions; determining, based on the target area map, bidirectional personnel traffic of at least one of the flow routes at a future time by means of a first predictive model; constructing a personnel flow graph based on second information related to the plurality of target areas; and determining epidemic risk values of each target area at future moments through a second prediction model based on the personnel flow diagrams.
In some embodiments, as shown in fig. 4, the prediction module 120 may construct the target region map 420 based on the first information 410 related to the plurality of target regions. The target area graph is a data structure composed of nodes and edges, the edges are connected with the nodes, and the nodes and the edges can have attributes.
In some embodiments, as shown in FIG. 4, the first information 410 may include a plurality of target areas 410-1, area features 410-2, flow routes 410-3 between the target areas, personnel flow 410-4 of the target areas, and distances 410-5 between the target areas. For more details regarding the target area, the area characteristics, see step 210 and the description thereof. For more details regarding the circulation of persons in the target area, see step 310 and its associated description.
The flow route between the target areas may refer to a traffic route between a plurality of target areas. For example, the flow route between the target areas may include a highway traffic route 1, a highway traffic route 2, a railway traffic route 1, an aircraft traffic route 1, and the like.
In some embodiments, the prediction module 120 may obtain the flow path between the target regions in a variety of ways. For example, the prediction module 120 may obtain the flow path between the target areas from the platform data.
In some embodiments, as shown in FIG. 4, the prediction module 120 may construct a target zone map based on the plurality of target zones 410-1 in the first information 410, the zone characteristics 420-2 of each target zone, the flow paths 410-3 between target zones, the person flow 410-4 of the target zone, and the distance 410-5 between target zones.
The target area map is a map for reflecting knowledge about the target area. As shown in FIG. 4, the target area graph 420 is composed of a plurality of first nodes 420-1 and a plurality of first edges 420-3, the first nodes 420-1 corresponding to have first node features 420-2, and the first edges 420-3 corresponding to have first edge features 420-4.
In some embodiments, each first node corresponds to a target area in the target area map. For example, as shown in fig. 5A, the target area graph 420 may include a plurality of first nodes such as "target area a", "target area B", "target area C", and "target area D".
The first node characteristic of the first node may reflect a relevant characteristic of the corresponding target region. In some embodiments, the first node characteristic includes at least a personal circulation of the target area. For more details regarding people circulation, see step 310 and its associated description. In some embodiments, the first node characteristic may further comprise a region characteristic of the target region. For more details regarding regional features, see step 210 and its associated description.
The plurality of first nodes may be connected by a first edge, and the first edge feature may reflect a relationship between the first nodes, which may include a flow path between the target areas. When there is a relationship between two first nodes, then the first nodes are connected as first edges.
In some embodiments, in the target area graph, each first edge corresponds to a flow path between the target areas to which the two first nodes respectively correspond. In some embodiments, one or more flow paths may be included between two first nodes, each flow path corresponding to a first edge. The first side is a bi-directional side, indicating that the flow path between the target areas is bi-directional. For example, as shown in fig. 5A, a first edge between the target area a and the target area B may include c1, c2, c3; the first side between the target area B and the target area C may include a1, a2, a3; the first edge between the target area B and the target area D may include B1, B2; the first edge between the target area a and the target area D may include D.
The first edge feature of the first edge may reflect a relevant feature of the corresponding flow path. In some embodiments, the first edge feature may include a corresponding circulation convenience for each circulation route. For more details regarding the convenience of circulation, see step 250 and its associated description.
In some embodiments, the circulation convenience may be determined based at least on the distance of the two target areas. For example, the closer the distance between two target areas, the higher the circulation convenience.
In some embodiments, the prediction module 120 may obtain the distance between two target regions in a variety of ways. For example, the prediction module 120 obtains the distance between two target areas from the map platform data.
In some embodiments, the circulation convenience may be further determined comprehensively based on the distance between the two target areas, the number of circulation routes, the circulation of people, and the circulation duration. For example, the shorter the distance between two target areas, the greater the number of circulation routes, the greater the person circulation, the shorter the circulation duration, the greater the circulation convenience between the two target areas. For more explanation of the circulation of people, see fig. 3 and the description thereof.
The circulation duration may refer to the time that is required for a certain target area to reach another target area on average via one circulation route. For example, the circulation time period may be a time period required for the target area a to reach the target area B via the circulation route 1 is 1h.
In some embodiments, each circulation route may correspond to a circulation duration, and the circulation duration between the two corresponding target areas may include a plurality of circulation durations, and each circulation route may correspond to a circulation convenience. An exemplary algorithm for calculating the convenience of circulation is shown in equation (2) below:
j＝r*s/(L*t) (2)
wherein j is the circulation convenience, L is the distance between two target areas, r is the number of circulation routes, s is the circulation of people, and t is the average circulation time. For example, the distance between the target area a and the target area B is 25km, the circulation route is 2, the person circulation is 1000 persons, and the average circulation time length is 1h, the circulation convenience between the two target areas is 80.
In some embodiments of the present disclosure, when determining the circulation convenience between the target areas, the influence of the distance between the target areas, the number of circulation routes, the circulation degree of the personnel, and the circulation duration is considered, so that whether the personnel flow between the target areas is convenient or not can be determined from multiple aspects, and the accuracy of the finally obtained circulation convenience is higher.
In some embodiments, as shown in FIG. 4, the prediction module 120 may determine the bi-directional personnel traffic 440-1 of the at least one flow route at a future time by a first prediction model 430 based on the target area map 420.
The first predictive model may be used to process the target area map to determine bi-directional personnel traffic for the at least one flow path at a future time. Wherein, the bidirectional personnel traffic refers to the circulation condition of all people going and going between two target areas. For example, the bidirectional personnel traffic may be 1000 persons for target area a to target area B and 1200 persons for target area B to target area a.
In some embodiments, the first predictive model may be a graph neural network model (Graph Neural Network, GNN). The first predictive model input may be a target area graph and the output may be bi-directional personnel traffic for at least one flow path in the target area, where the edge in the GNN outputs bi-directional personnel traffic for the corresponding flow path.
The first predictive model may also be other graph models, such as a graph roll-up neural network model (GCNN), or may add other processing layers to the graph neural network model, modify its processing methods, etc.
The first predictive model is trained by the same or a different processing device based on the second training data. The second training data includes a second training sample and a second label. For example, the second training sample may be a historical target area graph determined based on historical data, and the nodes and features, edges and features of the historical target area graph may be similar to those described above, and the second label may be historical bidirectional personnel traffic corresponding to each second edge in the historical target area graph.
In some embodiments, as shown in FIG. 4, the second information 440 may include a plurality of target areas 410-1, flow routes 410-3 between the target areas, bi-directional personnel traffic 440-1, and diagnostic information 440-2. Where bi-directional personnel traffic 440-1 is output by first predictive model 430. For more information about the target area, definitive diagnosis information, see step 210 and its associated description.
The personnel flow chart refers to a knowledge graph for reflecting personnel flow conditions between each target area, as shown in fig. 4, the personnel flow chart 450 is composed of a plurality of second nodes 450-1 and a plurality of second edges 450-3, the second nodes 450-1 correspondingly have second node features 450-2, and the second edges 450-3 correspondingly have second edge features 450-4.
In some embodiments, each of the second nodes corresponds to a target area in the personnel flow graph. For example, as shown in fig. 5B, the people flow graph 450 may include a plurality of second nodes such as "target area a", "target area B", "target area C", and "target area D".
The second node characteristics of the second node reflect the relevant characteristics of the corresponding target region. In some embodiments, the second node characteristic includes at least definitive information for each target area. For more information about the corroborative information, see step 210 and its associated description.
The plurality of second nodes may be connected by a second edge, and the second edge feature may reflect a relationship between the second nodes, which may include a flow path between the target areas. When there is a relationship between the two second nodes, the second nodes are connected into a second edge.
In some embodiments, in the personnel flow graph, each second edge corresponds to a flow path between the target areas to which the two second nodes respectively correspond. In some embodiments, one or more flow paths may be included between two second nodes, each flow path corresponding to one of the second edges. The second side is a bi-directional side, indicating that the flow path between the target areas is bi-directional. For example, as shown in fig. 5B, the second edge between the target area a and the target area B may include c1, c2, c3; the second side between the target area B and the target area C may include a1, a2, a3; the second edge between the target area B and the target area D may include B1, B2; the second edge between the target area a and the target area D may include D.
The second feature of the second side may reflect a related feature of the corresponding flow path. In some embodiments, the second edge feature may include a bi-directional personal circulation corresponding to each circulation route. Bi-directional personnel flow may refer to an indicator that measures personnel flow between multiple target areas. In some embodiments, the bi-directional personal communication between the target areas may be represented by the number of people coming and going between the target areas. For example, when 1200 persons enter the target area B from the target area a and 1000 persons enter the target area a from the target area B, the bi-directional personal communication between the target area a and the target area B is ([ a→b,1200], [ b→a,1000 ]).
In some embodiments, the first node feature of the target area graph and the second node feature of the personnel flow graph may further comprise weather features.
Weather features refer to weather-related features. For example, weather features may include, but are not limited to, features such as air temperature, precipitation, wind, humidity, and the like.
Weather characteristics may be obtained in a variety of ways. For example, weather features may be obtained through a weather monitoring platform database.
In some embodiments of the present disclosure, weather features are used as a first node feature of a target area diagram and a second node feature of a personnel circulation diagram, and an influence of the weather features on personnel circulation and an influence on epidemic propagation are considered, so that accuracy of an finally obtained epidemic risk value at a future time is higher.
In some embodiments, as shown in fig. 4, the prediction module 120 may determine an epidemic risk value 470 for each target area at a future time based on the personnel flow graph 450 via a second prediction model 460.
The second prediction model may be used to process the personnel flow graph to determine an epidemic risk value for each target area at a future time.
In some embodiments, the second predictive model may be a graph neural network model (Graph Neural Network, GNN). The second predictive model input may be a personnel flow graph and the output may be an epidemic risk value for the target area at a future time. Wherein, the nodes in the GNN output epidemic risk values of the corresponding target areas at future time.
The second predictive model may also be other graph models, such as a graph roll-up neural network model (GCNN), or may add other processing layers to the graph neural network model, modify its processing methods, etc.
The second predictive model is trained by the same or a different processing device based on the third training data. The third training data includes a third training sample and a third label. For example, the third training sample may be a historical staff circulation chart determined based on historical data, the nodes and features, edges and features of the historical staff circulation chart are similar to those described above, and the third label may be a historical epidemic risk value corresponding to each target area in the historical staff circulation chart.
In some embodiments of the present disclosure, a target area map and a personnel circulation map are respectively constructed based on first information and second information of a target area, and then an epidemic risk value of the target area at a future time is determined through a first prediction model and a second prediction model, so that the reliability of the finally obtained epidemic risk value is higher by combining the calculation of multiple information of the target area.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.
Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.
Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.
In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.
Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.
Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.
Claims (10)
1. A resource allocation method for tuberculosis detection, the method comprising:
acquiring area characteristics and diagnosis information of a plurality of target areas;
predicting epidemic risk values of the plurality of target areas at future time points based on the area characteristics and the diagnosis information;
acquiring resource reserves of each target area in the plurality of target areas;
determining a fitness of each of the plurality of target areas based on the epidemic risk value and the resource reserve;
determining a target allocation instruction based on the adaptation degree of each target area in the plurality of areas; and
and configuring resources in the plurality of target areas based on the target allocation instructions, wherein the resources at least comprise detection reagents for tuberculosis detection.
2. The method of claim 1, wherein predicting epidemic risk values for the plurality of target areas at future times based on the regional characteristics and the diagnostic information comprises:
for each of the plurality of target areas,
predicting the personnel circulation degree of each target area based on the area characteristics;
and determining the epidemic risk value of each target area at the future time based on the personnel circulation degree and the diagnosis information.
3. The method of claim 2, wherein the determining the epidemic risk value for each target area at the future time based on the personnel circulation and the diagnostic information comprises:
constructing a target area diagram based on first information related to the target areas, wherein each first node in the target area diagram corresponds to one target area, the first node characteristics of the first nodes at least comprise personnel circulation degrees of the target areas, each first side in the target area diagram corresponds to at least one circulation route between the target areas respectively corresponding to two first nodes, and the first side characteristics of the first sides at least comprise circulation convenience degrees of the circulation routes;
Determining, based on the target area map, a bidirectional personnel traffic of at least one flow route at the future time by a first predictive model;
constructing a personnel flow graph based on second information related to the plurality of target areas, wherein each second node in the personnel flow graph corresponds to one target area, the second node characteristics of the second nodes at least comprise diagnosis information of the target areas, each second side of the personnel flow graph corresponds to at least one flow route between the target areas respectively corresponding to the two second nodes, and the second side characteristics of the second sides at least comprise bidirectional personnel flow of the flow route;
and determining the epidemic risk value of each target area at the future time by a second prediction model based on the personnel flow chart.
4. The method of claim 1, wherein the determining the target deployment instruction based on the fitness of each of the plurality of target areas comprises:
generating a plurality of candidate allocation instructions based on the adaptation degree of each target area;
determining a deployment yield value of each candidate deployment instruction, wherein the deployment yield value is related to the adaptation degree;
And determining the target allocation instruction based on the allocation benefit value.
5. A resource allocation system for tuberculosis detection, the system comprising:
the first acquisition module is used for acquiring the regional characteristics and the diagnosis confirming information of a plurality of target regions;
the prediction module is used for predicting epidemic risk values of the target areas at future moments based on the area characteristics and the diagnosis information;
a second acquisition module configured to acquire a resource reserve of each of the plurality of target areas;
the determining module is used for determining the fitness of each target area in the plurality of target areas based on the epidemic situation risk value and the resource reserve;
a configuration module for
Determining a target allocation instruction based on the adaptation degree of each target area in the plurality of areas; and
and configuring resources in the plurality of target areas based on the target allocation instructions, wherein the resources at least comprise detection reagents for tuberculosis detection.
6. The system of claim 5, wherein to predict epidemic risk values for the plurality of target areas at future times based on the area characteristics and the diagnostic information, the prediction module is to:
For each of the plurality of target areas,
predicting the personnel circulation degree of each target area based on the area characteristics;
and determining the epidemic risk value of each target area at the future time based on the personnel circulation degree and the diagnosis information.
7. The system of claim 6, wherein to determine the epidemic risk value for each target area at the future time based on the personnel circulation and the diagnostic information, the prediction module is to:
constructing a target area diagram based on first information related to the target areas, wherein each first node in the target area diagram corresponds to one target area, the first node characteristics of the first nodes at least comprise personnel circulation degrees of the target areas, each first side in the target area diagram corresponds to at least one circulation route between the target areas respectively corresponding to two first nodes, and the first side characteristics of the first sides at least comprise circulation convenience degrees of the circulation routes;
determining, based on the target area map, a bidirectional personnel traffic of at least one flow route at the future time by a first predictive model;
Constructing a personnel flow graph based on second information related to the plurality of target areas, wherein each second node in the personnel flow graph corresponds to one target area, the second node characteristics of the second nodes at least comprise diagnosis information of the target areas, each second side of the personnel flow graph corresponds to at least one flow route between the target areas respectively corresponding to the two second nodes, and the second side characteristics of the second sides at least comprise bidirectional personnel flow of the flow route;
and determining the epidemic risk value of each target area at the future time by a second prediction model based on the personnel flow chart.
8. The system of claim 5, wherein to determine the target deployment instruction based on the fitness of each of the plurality of target areas, the configuration module is to:
generating a plurality of candidate allocation instructions based on the adaptation degree of each target area;
determining a deployment yield value of each candidate deployment instruction, wherein the deployment yield value is related to the adaptation degree;
and determining the target allocation instruction based on the allocation benefit value.
9. A resource allocation device for tuberculosis detection, the device comprising at least one processor and at least one memory;
The at least one memory is configured to store computer instructions;
the at least one processor is configured to execute at least some of the computer instructions to implement the method of any one of claims 1-4.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, implement a method as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310002583.0A CN116013541A (en) | 2023-01-03 | 2023-01-03 | Resource allocation method and system for tuberculosis detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310002583.0A CN116013541A (en) | 2023-01-03 | 2023-01-03 | Resource allocation method and system for tuberculosis detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116013541A true CN116013541A (en) | 2023-04-25 |
Family
ID=86029615
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310002583.0A Pending CN116013541A (en) | 2023-01-03 | 2023-01-03 | Resource allocation method and system for tuberculosis detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116013541A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110993119A (en) * | 2020-03-04 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method and device based on population migration, electronic equipment and medium |
| CN112163705A (en) * | 2020-09-29 | 2021-01-01 | 重庆邮电大学 | Epidemic situation prediction and early warning method based on CNN + SEIR and LSTM |
| CN112270998A (en) * | 2020-09-23 | 2021-01-26 | 清华大学 | Method and device for evaluating distribution of infected persons in region |
| CN113035368A (en) * | 2021-04-13 | 2021-06-25 | 桂林电子科技大学 | Disease propagation prediction method based on differential migration diagram neural network |
| CN113096785A (en) * | 2021-04-09 | 2021-07-09 | 中南林业科技大学 | Epidemic situation period medical resource allocation method |
| CN113096787A (en) * | 2021-04-19 | 2021-07-09 | 大连理工大学 | Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation |
| CN113517076A (en) * | 2021-07-30 | 2021-10-19 | 齐鲁工业大学 | Disease case number prediction method and system based on graph neural network and transfer learning |
| CN113517075A (en) * | 2021-06-25 | 2021-10-19 | 联通(广东)产业互联网有限公司 | Infectious disease dynamics-based infectious disease prediction method, system and medium |
| CN113793690A (en) * | 2021-08-31 | 2021-12-14 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for evaluating regional risk of infectious disease |
| US20220102012A1 (en) * | 2020-09-30 | 2022-03-31 | Arizona Board Of Regents On Behalf Of The University Of Arizona | Systems and methods for predictive modeling of people movement and disease spread under covid and pandemic situations |
| US11504011B1 (en) * | 2020-08-05 | 2022-11-22 | Vignet Incorporated | Early detection and prevention of infectious disease transmission using location data and geofencing |
| CN115394455A (en) * | 2022-05-31 | 2022-11-25 | 北京乾图科技有限公司 | Infectious disease time-space diffusion prediction method and device based on spatial clustering discrete grid |
| CN115424710A (en) * | 2022-08-22 | 2022-12-02 | 东南大学 | Infectious disease medical material distribution method |
| CN115547465A (en) * | 2022-05-15 | 2022-12-30 | 兰州大学 | Vaccine distribution system based on regional epidemic spread risk classification |
-
2023
- 2023-01-03 CN CN202310002583.0A patent/CN116013541A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110993119A (en) * | 2020-03-04 | 2020-04-10 | 同盾控股有限公司 | Epidemic situation prediction method and device based on population migration, electronic equipment and medium |
| US11504011B1 (en) * | 2020-08-05 | 2022-11-22 | Vignet Incorporated | Early detection and prevention of infectious disease transmission using location data and geofencing |
| CN112270998A (en) * | 2020-09-23 | 2021-01-26 | 清华大学 | Method and device for evaluating distribution of infected persons in region |
| CN112163705A (en) * | 2020-09-29 | 2021-01-01 | 重庆邮电大学 | Epidemic situation prediction and early warning method based on CNN + SEIR and LSTM |
| US20220102012A1 (en) * | 2020-09-30 | 2022-03-31 | Arizona Board Of Regents On Behalf Of The University Of Arizona | Systems and methods for predictive modeling of people movement and disease spread under covid and pandemic situations |
| CN113096785A (en) * | 2021-04-09 | 2021-07-09 | 中南林业科技大学 | Epidemic situation period medical resource allocation method |
| CN113035368A (en) * | 2021-04-13 | 2021-06-25 | 桂林电子科技大学 | Disease propagation prediction method based on differential migration diagram neural network |
| CN113096787A (en) * | 2021-04-19 | 2021-07-09 | 大连理工大学 | Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation |
| CN113517075A (en) * | 2021-06-25 | 2021-10-19 | 联通(广东)产业互联网有限公司 | Infectious disease dynamics-based infectious disease prediction method, system and medium |
| CN113517076A (en) * | 2021-07-30 | 2021-10-19 | 齐鲁工业大学 | Disease case number prediction method and system based on graph neural network and transfer learning |
| CN113793690A (en) * | 2021-08-31 | 2021-12-14 | 医渡云（北京）技术有限公司 | Method, device, storage medium and equipment for evaluating regional risk of infectious disease |
| CN115547465A (en) * | 2022-05-15 | 2022-12-30 | 兰州大学 | Vaccine distribution system based on regional epidemic spread risk classification |
| CN115394455A (en) * | 2022-05-31 | 2022-11-25 | 北京乾图科技有限公司 | Infectious disease time-space diffusion prediction method and device based on spatial clustering discrete grid |
| CN115424710A (en) * | 2022-08-22 | 2022-12-02 | 东南大学 | Infectious disease medical material distribution method |
Non-Patent Citations (1)
| Title |
|---|
| 陈长坤;童蕴贺;: "基于元胞自动机的传染病跨区域传播模型研究", 武汉理工大学学报(信息与管理工程版), no. 04 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sullivan | Understanding from machine learning models | |
| CN108446470B (en) | Medical facility accessibility analysis method based on vehicle trajectory data and population distribution | |
| CN110366759B (en) | System for diagnosing disease using neural network and method thereof | |
| Djanatliev et al. | Prospective healthcare decision-making by combined system dynamics, discrete-event and agent-based simulation | |
| CN110931112B (en) | Brain medical image analysis method based on multi-dimensional information fusion and deep learning | |
| CN106960568A (en) | Produce method, medium and system based on probabilistic traffic congestion index | |
| BR112013017447B1 (en) | travel process forecasting system and apparatus and a medium storing a method | |
| WO2020092150A1 (en) | Clustering, explainability, and automated decisions in computer-based reasoning systems | |
| CN107610282A (en) | A kind of bus passenger flow statistical system | |
| Nasir et al. | Quantitative thresholds based decision support approach for the home health care scheduling and routing problem | |
| JP7389787B2 (en) | Domain adaptive object detection device and method based on multi-level transition region | |
| US20240119317A1 (en) | Clustering, explainability, and automated decisions in computer-based reasoning systems | |
| CN106164896A (en) | For finding multidimensional recursive learning process and the system of complicated two analogues or many analogues relation | |
| CN110175654A (en) | A kind of update method and system of track road sign | |
| CN115187566A (en) | Intracranial aneurysm detection method and device based on MRA image | |
| CN112634889A (en) | Electronic case logging method, device, terminal and medium based on artificial intelligence | |
| Ata et al. | Structural Estimation of Kidney Transplant Candidates' Quality of Life Scores: Improving National Kidney Allocation Policy Under Endogenous Patient Choice and Geographical Sharing | |
| US10890460B2 (en) | Navigation and location validation for optimizing vehicle-based transit systems | |
| CN109886338A (en) | A kind of intelligent automobile test image mask method, device, system and storage medium | |
| CN116013541A (en) | Resource allocation method and system for tuberculosis detection | |
| CN110751395A (en) | Passenger travel state determination method, device and server | |
| CN116964588A (en) | Target detection method, target detection model training method and device | |
| Ghanim et al. | An artificial intelligence approach to estimate travel time along public transportation bus lines | |
| CN113868220A (en) | Construction method and device of epidemic situation research platform | |
| Sinwar et al. | Artificial intelligence and deep learning assisted rapid diagnosis of COVID-19 from chest radiographical images: A survey |
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 |