Hospital logistics plan generation method and system and storage medium

By sorting out and utilizing the characteristic parameters obtained by the Internet of Things, calculating behavioral returns and expectations, and selecting the plan with the highest behavioral potential, the problem that the hospital emergency plan generation system cannot handle the differences in characteristics of emergencies is solved, and a fast and accurate emergency response is achieved .

CN119092081APending Publication Date: 2024-12-06GUANGXIN INTELLIGENT CONSTR RES INST CO LTD
View PDF 9 Cites 0 Cited by

Patent Information

Application Number
CN202411586973.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-08
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The existing hospital emergency plan generation system cannot effectively handle the specific characteristics of emergencies, resulting in inconsistent emergency response results, making it difficult for command personnel to make correct decisions quickly.

Method used

By sorting out the characteristic parameters and emergency countermeasures in the plan database, using the Internet of Things to obtain the characteristic parameters of emergencies, calculate behavioral returns and behavior expectations, select the plan with the highest behavioral potential and implement corresponding implementation behaviors, and achieve accurate results for emergencies response.

Benefits of technology

It improves the generation effect of emergency plans, quickly finds appropriate plans and takes emergency measures, reduces the need for on-site configuration and planning of command personnel, and improves the efficiency and accuracy of emergency response.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119092081A_ABST
    Figure CN119092081A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of medical emergency response, in particular to a hospital logistics plan generation method and system and a storage medium, and the method comprises the steps: combing existing plans in a plan library, obtaining a plurality of feature parameters and emergency countermeasures in each existing plan, and splitting the emergency countermeasures into implementation behaviors; acquiring an emergency with the emergency type tag and a corresponding characteristic parameter; obtaining rewards of all characteristic parameters in the existing plans, and calculating behavior returns brought by the emergencies under the emergency countermeasures corresponding to all the existing plans; selecting a plurality of existing plans meeting the expectation evaluation requirements from the plan library, and calculating the behavior expectation of the emergencies under the emergency countermeasures corresponding to the existing plans; calculating a behavior potential based on the behavior return and the behavior expectation; and selecting the existing plan with the highest behavior potential as a preferable plan, and performing behaviors corresponding to the preferable plan through the Internet of Things. The method and the device are used for improving the plan generation effect when an emergency event occurs in a hospital.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of medical emergency response, and in particular to a hospital logistics plan generation method, system and storage medium. Background Art

[0002] In the daily operation of the hospital, we will encounter a series of sudden, complex and changeable emergency events.

[0003] Currently, hospitals obtain emergency plans mainly by recording and managing the emergency countermeasures and handling results corresponding to historical emergency events. When the number of emergency plans in the plan library reaches a certain number, when subsequent emergencies occur, appropriate plans are manually selected from the plan library based on the type and scale of the emergency, and emergency countermeasures are generated based on the selected plans.

[0004] There are some problems with the above method. It can only be limited to selecting corresponding plans based on general information such as the type and scale of the emergency. However, the specific characteristics of events of the same type are often different. For example, when the medical system is paralyzed, the type, quantity, time, number of patients corresponding to the system and other specific details of the paralyzed system are all different. If only the same plan can be selected for events with different characteristics, the final emergency response results will be completely different. In addition, a large number of decision-making behaviors based only on experience and unable to predict the actual consequences will often be added when the emergency countermeasures corresponding to the actual operation plan are actually implemented. This makes the current plan generation system in the medical system still have major problems, resulting in the hospital commanders being unable to quickly make correct plans when sudden risks occur. Summary of the invention

[0005] In order to improve the effect of emergency plan generation when emergency events occur in hospitals, the present application provides a hospital logistics plan generation method, system and storage medium.

[0006] In the first aspect, the present application provides a method for generating a hospital logistics plan, which adopts the following technical solution: A method for generating a hospital logistics plan comprises the following steps: Combing the existing plans in the plan library, obtaining several characteristic parameters and emergency countermeasures in each of the existing plans, and splitting the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters, wherein each of the existing plans corresponds to an emergency event type label; Acquire an emergency event with the emergency event type label, and acquire the characteristic parameters corresponding to the emergency event based on the Internet of Things, put the characteristic parameters corresponding to the emergency event into the plan library and compare and predict with the existing plans of the same type; Obtain rewards corresponding to each of the characteristic parameters and one or more of the corresponding implementation behaviors in the existing plans, and calculate the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the rewards, wherein the behavioral rewards are characterized by the size of the positive value brought about by a certain behavior; Selecting a number of the existing plans that meet the expected evaluation requirements from the plan library, and calculating the behavioral expectations brought about by the emergency event under the emergency countermeasures corresponding to the selected existing plans, wherein the behavioral expectations are characterized by the possibility that selecting a certain behavior can bring positive value; Calculating the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation, wherein the behavior potential is characterized by the possibility of the plan being selected in a specific scenario; The existing plan with the highest behavior potential is selected as the preferred plan, and each implementation behavior corresponding to the preferred plan is sent to the corresponding Internet of Things device for execution through the Internet of Things.

[0007] In some of the embodiments, the reward is preset manually, and the larger the reward corresponding to the implementation behavior, the greater the positive correlation effect of the characteristic parameter corresponding to the implementation behavior; Specifically, the rewards include regular rewards and special rewards; The conventional reward is characterized as a reward corresponding to the implementation behavior existing in each of the existing plans in the same emergency event type label; The specific reward is characterized as a reward corresponding to the implementation behaviors that are different in the existing plans with the same emergency event type label; The minimum value of the special reward is greater than the maximum value of the regular reward, wherein, when the special reward exists, the characteristic parameters corresponding to the different implementation behaviors are defined as difference characteristic parameters.

[0008] In some embodiments, calculating the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the reward includes the following steps: Acquire the emergency event type label corresponding to the emergency event, and acquire all the existing plans that match the emergency event type label in the plan library; Screening out a number of the characteristic parameters that match the characteristic parameters of the emergency event and the corresponding implementation behaviors from each of the existing emergency plans; The sum of the rewards for the several implementation behaviors selected from each of the existing plans is calculated to obtain the behavioral rewards brought by each of the existing plans.

[0009] In some of the embodiments, selecting a number of the existing plans that meet the expected evaluation requirements from the plan library includes the following steps: Selecting several typical plans from the existing plans corresponding to the emergency event type label matching the emergency event, wherein the typical plans are plans with good emergency response results or with high universality of the characteristic parameters pre-marked by the user; The feature similarity between each of the existing plans and the emergency event is calculated, and a preset number of the existing plans with higher feature similarity are selected as high-matching plans, wherein the feature similarity is characterized by the degree of similarity between the feature parameters in the existing plans and the feature parameters in the emergency event.

[0010] In some embodiments, calculating the behavior expectation of the emergency event under the emergency countermeasures corresponding to each selected existing plan includes the following steps: In each of the typical plans, the existence ratio of the implementation behaviors that match the characteristic parameters corresponding to the emergency events is calculated and defined as the generalized expectation; In each of the high-matching plans, the existence ratio of the implementation behaviors that match the characteristic parameters corresponding to the emergency events is calculated and defined as a special expectation; The behavior expectations corresponding to each of the existing plans are calculated according to the generalized expectations and the special expectations.

[0011] In some embodiments, calculating the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation includes the following steps: The behavioral potential is calculated based on the following formula: Px(sn,R)=f(Ex|sn,Rvx|sn), Among them, Px represents the behavioral potential, sn represents the scenario of the nth emergency event based on the emergency event type label, R represents the possibility of resolving the emergency event, Ex represents the behavioral expectation, Rvx represents the behavioral reward, and f(x) is a functional relationship.

[0012] In some of the embodiments, the following steps are also included: Each characteristic parameter in the existing plan and the emergency event corresponds to a control point, wherein the control point includes an internal control point and an external control point; In the existing plan, it is determined whether the behavior reward corresponding to each implementation behavior is strongly correlated with the action of the implementation behavior itself, and the strong correlation is characterized by that the reward of a behavior is determined by the behavior itself; If it exists, the characteristic parameter corresponding to the implementation behavior corresponds to the internal control point; if it does not exist, the characteristic parameter corresponding to the implementation behavior corresponds to the external control point; In the emergency event, each of the characteristic parameters is compared with the characteristic parameters in the existing plan. If the same characteristic parameters exist, the control point that is the same as the characteristic parameter in the existing plan is added to the characteristic parameters; if the same characteristic parameters do not exist, the characteristic parameters correspond to the external control points.

[0013] In some of the embodiments, after selecting the existing plan with the highest behavior potential as the preferred plan, the following steps are also included: Calculating control point tendency information based on the quantity ratio of the internal control points and the external control points corresponding to each of the characteristic parameters in the emergency, and generating achievement motivation based on the control point tendency information to determine whether to perform intelligent adjustment on the preferred plan, wherein the achievement motivation is characterized as the willingness motivation of the system to perform intelligent adjustment on the preferred plan, and the intelligent adjustment includes adding the implementation behavior and / or deleting the implementation behavior; The control point tendency includes the internal control tendency and the external control tendency, and the achievement motivation corresponding to the internal control tendency is greater than the achievement motivation corresponding to the external control tendency.

[0014] In the second aspect, the present application provides a hospital logistics plan generation system, which adopts the following technical solution: A hospital logistics plan generation system, comprising: Plan library, used to store several existing plans; A plan combing module is used to comb the existing plans in the plan library, obtain several characteristic parameters and emergency countermeasures in each of the existing plans, and split the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters, wherein each of the existing plans corresponds to an emergency event type label; An emergency event acquisition module is used to acquire an emergency event with the emergency event type label, and acquire the characteristic parameters corresponding to the emergency event based on the Internet of Things module, put the characteristic parameters corresponding to the emergency event into the plan library and compare and predict with the existing plans of the same type; A behavior reward calculation module is used to obtain the rewards corresponding to each of the characteristic parameters and one or more of the corresponding implementation behaviors in the existing plan, and calculate the behavior rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the rewards, wherein the behavior rewards are represented by the size of the positive value brought about by a certain behavior; A behavior expectation calculation module is used to select a number of existing plans that meet the expected evaluation requirements from the plan library, and calculate the behavior expectations brought about by the emergency event under the emergency countermeasures corresponding to each of the selected existing plans, wherein the behavior expectation is characterized by the possibility that selecting a certain behavior can bring positive value; A plan generation module is used to calculate the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation, wherein the behavior potential is characterized by the possibility of the plan being selected in a specific scenario, and select the existing plan with the highest behavior potential as the preferred plan; A plan execution module, used to send each implementation behavior corresponding to the preferred plan to a corresponding object for execution through the Internet of Things module; The Internet of Things module is used to obtain the characteristic parameters corresponding to the emergency event and control the networked Internet of Things devices to execute the implementation behaviors corresponding to the preferred plan.

[0015] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and execute the above method.

[0016] The technical solution provided by the embodiments of the present application has the following technical effects: Through behavior prediction, by analyzing the returns that each existing plan can bring and the possibility that the implementation of the plan can bring corresponding returns, the degree of adaptability of an existing plan to the scenario corresponding to the emergency event can be calculated, and the implementation behavior corresponding to the optimal existing plan can be selected to control the corresponding IoT devices and personnel to perform emergency actions. When an emergency occurs, behavior prediction can be used to solve new problems by solving old problems, so as to quickly find a suitable plan and take emergency measures, without the need for commanders to configure and plan plans on site. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the steps of the hospital logistics plan generation method provided in the embodiment of the present application.

[0018] Figure 2 It is a module connection diagram of the hospital logistics plan generation system provided in the embodiment of the present application. DETAILED DESCRIPTION

[0019] To more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. However, it should be understood by those of ordinary skill in the art that the present application can be implemented without these details. In some cases, in order to avoid unnecessary descriptions that make various aspects of the present application obscure, well-known methods, processes, systems, components and / or circuits that have been described at a higher level will not be described in detail. For those of ordinary skill in the art, it is obvious that various changes can be made to the embodiments disclosed in the present application, and without departing from the principles and scope of the present application, the general principles defined in the present application can be applied to other embodiments and application scenarios. Therefore, the present application is not limited to the embodiments shown, but conforms to the broadest scope consistent with the scope claimed for protection of the present application.

[0020] It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in each embodiment of the present invention described below can be combined with each other as long as there is no conflict between them.

[0021] In the description of this application, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed", etc. are understood to exclude the number itself, and "above", "below", "within", etc. are understood to include the number itself. If there is a description of "first" or "second", it is only used to distinguish the technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0022] In the description of the present application, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples.

[0023] The embodiment of the present application discloses a method for generating a hospital logistics plan.

[0024] like Figure 1 As shown, a method for generating a hospital logistics plan includes the following steps: S100, sorting out the existing plans in the plan library, obtaining several characteristic parameters and emergency countermeasures in each existing plan, splitting the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters, and each existing plan corresponds to an emergency event type label.

[0025] The hospital summarizes the content, handling process, and results of historical emergencies to obtain emergency plans. At the same time, it obtains relevant plans from other hospitals through data networking, saves them in the plan library, and sorts out the existing plans.

[0026] Each existing plan corresponds to a different emergency event type label, which is used to indicate the event type corresponding to the existing plan. The emergency event types designed by the hospital are mainly the following: 1. Public health event emergency plan; 2. Natural disaster emergency plan; 3. Medical safety accident emergency plan; 4. Information emergency plan; 5. Mass casualty incident emergency plan; 6. Logistics plan.

[0027] Setting and accurately selecting an emergency event type label corresponding to an existing plan can generate emergency countermeasures that better match the actual emergency when selecting plans later, allowing commanders to quickly make correct plans.

[0028] The characteristic parameters are characterized by the quantifiable specific numerical content corresponding to each emergency event, such as poisons, disaster types, types of drugs with adverse reactions, the distance between the accident site and the hospital, the current number of isolation rooms in the hospital, etc. Each characteristic parameter corresponds to the corresponding performance content of the event. When selecting characteristic parameters, select 4-8 characteristic parameters in one event.

[0029] Among them, some of the selected characteristic parameters may be non-quantifiable indicators. For such characteristic parameters, a variety of methods can be used to quantify them: The refinement or behavioral approach breaks down non-quantifiable indicators into more specific behaviors or steps to make them observable or measurable; The clarification method makes vague indicators concrete and measurable by clarifying their definitions and evaluation criteria; The hierarchical quantitative method divides the indicators into several levels according to the different degrees of things and the corresponding degree range; ‌ Setting formulas for quantification methods. For some indicators that are difficult to quantify directly, they can be quantified by setting mathematical formulas.

[0030] Emergency countermeasures are a holistic description of all behavioral decisions that need to be made for a specific emergency behavior. They can be broken down into individual specific implementation behaviors. Each implementation behavior corresponds to a specific action of a person or IoT device, such as controlling the opening of a rolling door, opening access control, turning on a disinfection system, etc.

[0031] S200, obtaining an emergency event with an emergency event type label, and obtaining characteristic parameters corresponding to the emergency event based on the Internet of Things, putting the characteristic parameters corresponding to the emergency event into a plan library and performing comparison and prediction on existing plans of the same type.

[0032] When an emergency occurs in the hospital, the staff manually selects the emergency event type label corresponding to the emergency in the system, and obtains the corresponding status of each IoT device in real time through the IoT module to obtain several characteristic parameters. The characteristic parameters of the emergency are added to the plan library for plan comparison to predict and select the optimal plan with the best emergency implementation effect for the plan.

[0033] The parameters obtained by the IoT module include but are not limited to: equipment alarm data, equipment operation data, personnel and vehicle traffic data, and hospital material data.

[0034] S300, obtaining rewards corresponding to each characteristic parameter in the existing plan and one or more corresponding implementation behaviors, and calculating the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each existing plan based on the rewards.

[0035] Behavioral rewards are characterized by the size of the positive value brought by a certain behavior, which is specifically expressed as the relative value of the result brought about by a certain behavior as believed by the actor or intelligent agent. The same behavior has different relative values ​​in different scenarios, that is, in emergencies corresponding to different emergency event labels.

[0036] The greater the behavioral reward, the greater the system believes that the benefit of a behavior is to the actor or agent. In this application, it is characterized by the better the emergency response to the emergency event will be through this behavior.

[0037] By pre-comparing the behavioral rewards for the corresponding characteristic parameters of each implementation behavior in the existing plan, the characteristic parameters of the emergency event are compared with the characteristic parameters in the existing plan to obtain the overall emergency response effect of each existing plan on the emergency event.

[0038] S400, selecting a number of existing plans that meet the expected evaluation requirements in the plan library, and calculating the behavioral expectations brought about by the emergency event under the emergency countermeasures corresponding to the selected existing plans.

[0039] Behavioral expectation is characterized by the possibility that choosing a certain behavior can bring positive value. Specifically, it is manifested as the possibility that the actor or agent chooses a certain behavior and this behavior can bring beneficial results, that is, the system believes that taking this behavior in this scenario will achieve the expected effect.

[0040] By selecting some specific plans that meet the requirements in the plan library and comparing them with emergencies, these specific plans are representative or have high reference value, so as to make expectations on the behavior of emergencies under the emergency response measures corresponding to each existing plan.

[0041] S500, calculating the behavior potential corresponding to each existing plan based on the behavior reward and the behavior expectation.

[0042] Behavior potential is represented by the probability of the plan being selected in a specific scenario. The greater the behavior potential, the greater the probability that the plan will be selected in this emergency. In an emergency in a specific scenario, each of the multiple feasible behaviors has the possibility of occurring, that is, they all have behavior potential, but some behaviors have higher behavior potential, while others have lower behavior potential.

[0043] S600, selecting an existing plan with the highest behavior potential as a preferred plan, and sending each implementation behavior corresponding to the preferred plan to a corresponding IoT device through the IoT for execution.

[0044] The existing plan corresponding to the highest behavioral potential is selected as the preferred plan, and the corresponding people or IoT devices are controlled to execute the various implementation behaviors decomposed from the emergency countermeasures in the preferred plan, such as controlling certain devices to turn on or off, and notifying personnel in different parts to carry out corresponding commands. At the same time, the commander can modify the specific implementation behaviors in the selected preferred plan.

[0045] IoT devices include but are not limited to access control, fire shutter doors, and broadcasting.

[0046] Through the above steps: through behavior prediction, by analyzing how much return each existing plan can bring and the possibility that the implementation of the plan can bring corresponding returns, the adaptability of an existing plan to the scenario corresponding to the emergency event can be calculated, and the implementation behavior corresponding to the optimal existing plan can be selected to control the corresponding IoT devices and personnel to perform emergency actions. When an emergency occurs, behavior prediction can be used to solve new problems by solving old problems, so as to quickly find a suitable plan and take emergency measures, without the need for commanders to configure and plan plans on site.

[0047] In other embodiments, the reward is preset manually, and the larger the reward corresponding to an implementation behavior, the greater the positive correlation effect of the characteristic parameter corresponding to the implementation behavior.

[0048] Each implementation behavior corresponds to one or more characteristic parameters, and each implementation behavior will have an impact on a characteristic parameter. For example, if the characteristic parameter is infectious disease isolation, then closing doors and windows, turning off ventilation, turning on the disinfection system, etc. are all positive correlation effects on the characteristic parameter, while turning off power supply, turning off water supply, etc. have no effect on the characteristic parameter, and there is no reward at this time.

[0049] The rewards include regular rewards, which are represented by rewards corresponding to implementation behaviors that exist in all existing plans with the same emergency event type label.

[0050] For example, in the label of a major traffic accident, regardless of whether the characteristic parameters such as the number of casualties, the type of casualties, and the distance between the accident site and the hospital are the same, the various plans in the label all include implementation actions such as opening emergency channels and reporting to the blood bank. These actions are then represented as actions that need to be taken in a type of emergency. There are rewards for such actions, but because they cannot distinguish and classify the specific scenarios of the emergency, the reward value is relatively small.

[0051] Rewards also include special rewards, which are represented by rewards corresponding to different implementation behaviors in various existing plans with the same emergency event type label.

[0052] For example, in the labels of major traffic accidents, the types of casualties are different, and there are differences in the implementation behaviors of doctors in the notified departments in various existing plans. The specific differences are reflected in the different types of departments notified. This difference in implementation behavior is due to the different specific actual scenarios in each existing plan. The difference can reflect the reason why the existing plan is different from other existing plans, which will help to more accurately select the preferred existing plan according to the specific scenarios of the emergency. Therefore, the minimum value of the specific reward is greater than the maximum value of the regular reward.

[0053] When there is a specific reward, the characteristic parameters corresponding to the different implementation behaviors are defined as differential characteristic parameters.

[0054] In some other embodiments, the reward-based calculation of the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each existing plan includes the following steps: S310, obtaining an emergency event type label corresponding to the emergency event, and obtaining all existing plans that match the emergency event type label in the plan library.

[0055] First, based on the emergency event type label corresponding to the emergency event, an existing plan that meets the same event type is selected from the plan library.

[0056] Because the same behavior has different positive values ​​for the same characteristic parameters of the event in different scenarios, in order to improve the accuracy of plan selection, the generation of all plans needs to be ensured to be based on the same major category.

[0057] S320, screening out several characteristic parameters and corresponding implementation behaviors that match the characteristic parameters of the emergency event from each existing emergency plan.

[0058] A screening operation is performed on each existing emergency plan, and the screening content is the characteristic parameters in each existing emergency plan that are the same as the emergency event and the corresponding implementation behaviors.

[0059] S330, calculating the sum of rewards for a number of implementation behaviors selected from each existing plan to obtain the behavior rewards brought by each existing plan.

[0060] The sum of the rewards for the selected implementation behaviors in each existing plan is calculated as the behavioral reward corresponding to each existing plan. The same characteristic parameters in the existing plan and the emergency event represent the similarities between the emergency event scenario and the existing plan scenario. In similar situations, the same implementation behaviors can often be used to carry out emergency actions. Therefore, these implementation behaviors are selected and the rewards are calculated. The larger the reward, the better the effect of the emergency response to the emergency through the existing plan.

[0061] In some other embodiments, selecting a number of existing plans that meet the expected evaluation requirements from the plan library includes the following steps: S410: Select several typical plans from existing plans corresponding to emergency event type labels matching the emergency event.

[0062] A typical plan is a plan that is pre-marked by the user with good emergency response results or with high commonality of characteristic parameters.

[0063] Because the feature parameters selected in each existing case are different and the specific values ​​of the feature parameters are also different, in order to reduce the impact of some special or low-probability feature parameters in the existing cases on the overall behavior expectation calculation results in the subsequent behavior expectation calculation, the typical plans corresponding to each emergency event type label are first selected in the plan library. Typical plans are generally excellent plans or model plans marked by the hospital when uploading, or the hospital believes that the feature parameters selected in a case have high universality and reference value.

[0064] S411, calculating the feature similarity between each existing plan and the emergency event, and selecting a preset number of existing plans with higher feature similarity as high matching plans.

[0065] Feature similarity is characterized by the degree of similarity between the feature parameters in the existing plan and the feature parameters in the emergency.

[0066] The higher the similarity between the characteristic parameters of an emergency event and an existing plan, the more confident and sure the system is in calculating the possibility of an existing plan resolving an emergency event. In this case, an existing plan with high characteristic similarity can be used as a high-value reference plan that matches the particularity and uniqueness of a real-time emergency event.

[0067] In other embodiments, calculating the behavior expectations of an emergency event under the emergency countermeasures corresponding to each selected existing plan includes the following steps: S420, calculating the existence ratio of implementation behaviors that match the characteristic parameters corresponding to the emergency events in each typical plan, and defining it as the generalized expectation.

[0068] Generalized expectations refer to people or IoT devices' expectations that they will successfully obtain positive value by performing certain behaviors in general, relevant or similar typical scenarios. They are the accumulation of people's or IoT devices' experiences in several typical and standardized scenarios.

[0069] Therefore, we first calculate the generalized expectation through typical plans. Specifically, we calculate the existence ratio of the implementation behaviors that match the characteristic parameters in each typical plan with the characteristic parameters of the emergency. For example, among the 8 characteristic parameters of the emergency, 6 appear in a typical plan, so the existence ratio is 6 / 8.

[0070] S421, calculating the existence ratio of implementation behaviors that match the characteristic parameters corresponding to the emergency events in each high-matching plan, and defining it as a special expectation.

[0071] Special expectations refer to people's or IoT devices' expectations of successfully obtaining positive value by performing certain actions in a certain special situation. Special expectations are formed based on the many experiences of people or IoT devices in certain special situations that are specified or in accordance with their own specific conditions.

[0072] Therefore, it is also necessary to calculate the special expectations through high-matching plans, specifically by calculating the existence ratio of implementation behaviors that match the characteristic parameters in each high-matching plan with the characteristic parameters of the emergency event.

[0073] S422, calculating the behavior expectations corresponding to each existing plan based on the generalized expectations and the special expectations.

[0074] The expectation of a person or IoT device performing a certain action in a certain scenario is jointly determined by the specific expectation and the generalized expectation. In this way, the corresponding behavioral expectations of an emergency event in different types of plans can be comprehensively judged. After a certain amount of training, when faced with an existing plan, the actual behavioral expectations corresponding to an existing plan can be inferred based on the specific values ​​of the generalized expectation and the special expectation corresponding to the plan, making the subsequent calculation process more accurate.

[0075] In some other embodiments, the behavior potential corresponding to each existing plan is calculated based on the behavior reward and the behavior expectation, including the following steps: S510, calculating the behavior potential based on the following formula: Px(sn,R)=f(Ex|sn,Rvx|sn), Among them, Px represents the behavioral potential, sn represents the scenario of the nth emergency based on the emergency type label, R represents the possibility of resolving the emergency, Ex represents the behavioral expectation, Rvx represents the behavioral reward, and f(x) is the functional relationship.

[0076] In this application, since the emergency response measures of each existing plan are decomposed into independent implementation behaviors, the possibility of each behavior being selected depends on how much reward the system believes the implementation behavior can bring and the possibility of the implementation behavior bringing rewards. In the above formula, Px (sn, R) represents the possibility of implementation behavior x being selected under the condition that it can bring rewards in the scenario corresponding to the nth emergency, Ex | sn represents the possibility that implementation behavior x can bring rewards in the scenario corresponding to the nth emergency, and Rvx | sn represents the possibility that implementation behavior x can bring rewards in the scenario corresponding to the nth emergency.

[0077] In some other embodiments, it also includes: S700, each characteristic parameter in the existing plan and the emergency event corresponds to a control point, wherein the control point includes an internal control point and an external control point.

[0078] The control point is explained as the attribution method that the system believes a behavior corresponds to a result. Specifically, the internal control point means that the result of the characteristic parameter is determined by its corresponding implementation behavior, that is, the hospital can control itself through actual behavior or decision-making. The external control point is characterized by the fact that the result of the characteristic parameter is determined by external factors, such as the environment, the behavior of others, luck, etc. On the other hand, it also means that the result of a characteristic parameter cannot be determined by a certain behavior and there is no influence association.

[0079] The methods for determining the control point type corresponding to each characteristic parameter in existing plans and emergencies are completely different S710, in the existing plan, determine whether the behavior reward corresponding to each implementation behavior is strongly correlated with the action of the implementation behavior itself.

[0080] A strong association is one in which the reward for an action is determined by the action itself.

[0081] For example, in the event of a major traffic accident, actions such as opening emergency channels and preparing a corresponding number of operating rooms can all receive corresponding rewards in the emergency. That is, these actions are determined to have a beneficial effect on the final outcome of the emergency. This is a behavioral measure that the hospital can achieve on its own, which shows that there is a strong correlation between the behavioral rewards for implementing the behavior and the action itself.

[0082] However, the above-mentioned implementation behaviors cannot improve the speed of transporting patients from the accident site to the hospital in an emergency, because the transportation speed depends on external factors such as the location of the accident site, the road conditions at the time, and the weather. Therefore, there is no direct correlation between these implementation behaviors and the ideal behavior returns corresponding to the characteristic parameters. At this time, it is believed that there is no strong correlation.

[0083] S720, if it exists, the characteristic parameter corresponding to the implementation behavior corresponds to the internal control point; if it does not exist, the characteristic parameter corresponding to the implementation behavior corresponds to the external control point.

[0084] Internal control points are placed in the feature parameters corresponding to strong correlations, and external control points are placed in the feature parameters where there are no strong correlations.

[0085] Among them, the control point type in the existing plan can be manually added by the user when uploading the plan, or it can be determined by the system itself after certain machine learning training.

[0086] S730, in an emergency event, each characteristic parameter is compared with the characteristic parameters in the existing plan. If there are identical characteristic parameters, a control point identical to the characteristic parameter in the existing plan is added to the characteristic parameter. If there are no identical characteristic parameters, the characteristic parameter corresponds to an external control point.

[0087] In an emergency, it is determined whether the characteristic parameters of the emergency can be found in the existing plans. If there are the same characteristic parameters, the corresponding control point type is selected for the characteristic parameters. If it does not exist, an external control point is added directly. When comparing the characteristic parameters, the emergency cannot find the corresponding characteristic parameters from the existing plans, so the method of obtaining behavioral rewards for the characteristic parameters cannot be accurately obtained. Such unknown characteristic parameters are defined as external control points.

[0088] In some other embodiments, after selecting the existing plan with the highest behavior potential as the preferred plan, the following steps are also included: S800, calculating control point tendency information based on the quantity ratio of internal control points and external control points corresponding to each characteristic parameter in the emergency, and generating achievement motivation based on the control point tendency information to determine whether to perform intelligent adjustment on the preferred plan.

[0089] Achievement motivation is characterized by the system's willingness to make intelligent adjustments to the preferred plan. The greater the achievement motivation, the more willing the system is to actively make intelligent adjustments to some of the implementation behaviors in the preferred plan. The smaller the achievement motivation, the less willing the system is to actively make intelligent adjustments to some of the implementation behaviors in the preferred plan. Intelligent adjustments include adding implementation behaviors and / or deleting implementation behaviors.

[0090] The control point tendency includes internal control tendency and external control tendency. When the number of internal control points in an emergency is greater than the number of external control points, it manifests as an internal control tendency, otherwise, it manifests as an external control tendency. The internal control tendency means that the system is more inclined to improve the final result through its own active behavior changes, updates, or active decisions. The external control tendency is characterized by the system's tendency to believe that it cannot change the final result through its own active behavior, and wait for external instructions or external actions to change its own state results. Therefore, the achievement motivation corresponding to the internal control tendency is greater than the achievement motivation corresponding to the external control tendency.

[0091] If there are more internal control points in an emergency that can obtain behavioral rewards corresponding to the implementation behavior through existing plans, then the successful experience of self-intelligent adjustment based on a considerable number of internal control points will be higher, which can improve the system's ambition level, so it will be more willing to actively improve the preferred plan. On the contrary, if the proportion of external control points is better, the reference for self-intelligent adjustment will be fewer, and the behavioral rewards determined by external factors will be more, so the failure experience of self-intelligent adjustment will be higher, its ambition level will decrease, and it will be unwilling to actively improve the preferred plan.

[0092] like Figure 2 As shown, the present application also discloses a hospital logistics plan generation system, including: The plan library is used to store several existing plans.

[0093] The plan sorting module is used to sort out the existing plans in the plan library, obtain several characteristic parameters and emergency countermeasures in each existing plan, and split the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters. Among them, each existing plan corresponds to an emergency event type label.

[0094] The emergency event acquisition module is used to obtain emergency events with emergency event type labels, and obtain the characteristic parameters corresponding to the emergency events based on the Internet of Things module, put the characteristic parameters corresponding to the emergency events into the plan library and compare and predict with the existing plans of the same type.

[0095] The behavior reward calculation module is used to obtain the rewards corresponding to each characteristic parameter in the existing plan and one or more corresponding implementation behaviors, and calculate the behavior rewards brought about by the emergency events under the emergency countermeasures corresponding to each existing plan based on the rewards. The behavior reward is represented by the size of the positive value brought about by a certain behavior.

[0096] The behavior expectation calculation module is used to select several existing plans that meet the expected evaluation requirements in the plan library, and calculate the behavior expectations brought about by the emergency events under the emergency countermeasures corresponding to the selected existing plans. The behavior expectation is characterized by the possibility that choosing a certain behavior can bring positive value.

[0097] The plan generation module is used to calculate the behavior potential corresponding to each existing plan based on the behavior reward and behavior expectation. The behavior potential is represented by the probability of the plan being selected in a specific scenario, and the existing plan with the highest behavior potential is selected as the preferred plan; The plan execution module is used to send the implementation behaviors corresponding to the preferred plan to the corresponding objects for execution through the Internet of Things module.

[0098] The Internet of Things module is used to obtain the characteristic parameters corresponding to the emergency event and control the networked Internet of Things devices to execute the various implementation behaviors corresponding to the preferred plan.

[0099] The present application also discloses a computer-readable storage medium, characterized in that it stores a computer program that can be loaded by a processor and execute the above method.

[0100] The implementation principle is: Through behavior prediction, by analyzing the returns that each existing plan can bring and the possibility that the implementation of the plan can bring corresponding returns, the degree of adaptability of an existing plan to the scenario corresponding to the emergency event can be calculated, and the implementation behavior corresponding to the optimal existing plan can be selected to control the corresponding IoT devices and personnel to perform emergency actions. When an emergency occurs, behavior prediction can be used to solve new problems by solving old problems, so as to quickly find a suitable plan and take emergency measures, without the need for commanders to configure and plan plans on site.

[0101] It should be understood that although the steps in the flowchart of the accompanying drawings are shown in sequence according to the instructions of the arrows, these steps are not necessarily performed in the order indicated by the arrows. Unless otherwise clearly stated in this document, the execution of these steps is not strictly limited in order and can be performed in other orders.

[0102] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for generating a hospital logistics plan, characterized in that: The following steps are involved: Combing the existing plans in the plan library, obtaining several characteristic parameters and emergency countermeasures in each of the existing plans, and splitting the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters, wherein each of the existing plans corresponds to an emergency event type label; Acquire an emergency event with the emergency event type label, and acquire the characteristic parameters corresponding to the emergency event based on the Internet of Things, put the characteristic parameters corresponding to the emergency event into the plan library and compare and predict with the existing plans of the same type; Obtain rewards corresponding to each of the characteristic parameters and one or more of the corresponding implementation behaviors in the existing plans, and calculate the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the rewards, wherein the behavioral rewards are characterized by the size of the positive value brought about by a certain behavior; Selecting a number of the existing plans that meet the expected evaluation requirements from the plan library, and calculating the behavioral expectations brought about by the emergency event under the emergency countermeasures corresponding to the selected existing plans, wherein the behavioral expectations are characterized by the possibility that selecting a certain behavior can bring positive value; Calculating the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation, wherein the behavior potential is characterized by the possibility of the plan being selected in a specific scenario; The existing plan with the highest behavior potential is selected as the preferred plan, and each implementation behavior corresponding to the preferred plan is sent to the corresponding Internet of Things device for execution through the Internet of Things.

2. The method for generating a hospital logistics plan according to claim 1, characterized in that: The reward is preset manually, and the larger the reward corresponding to an implementation behavior, the greater the positive correlation influence of the feature parameter corresponding to the implementation behavior; Specifically, the rewards include regular rewards and special rewards; The conventional reward is characterized as a reward corresponding to the implementation behavior existing in each of the existing plans in the same emergency event type label; The specific reward is characterized as a reward corresponding to the implementation behaviors that are different in the existing plans with the same emergency event type label; The minimum value of the special reward is greater than the maximum value of the regular reward, wherein, when the special reward exists, the characteristic parameters corresponding to the different implementation behaviors are defined as difference characteristic parameters.

3. The method for generating a hospital logistics plan according to claim 2, characterized in that: Calculating the behavioral rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the reward includes the following steps: Acquire the emergency event type label corresponding to the emergency event, and acquire all the existing plans that match the emergency event type label in the plan library; Screening out a number of the characteristic parameters that match the characteristic parameters of the emergency event and the corresponding implementation behaviors from each of the existing emergency plans; The sum of the rewards for the several implementation behaviors selected from each of the existing plans is calculated to obtain the behavioral rewards brought by each of the existing plans.

4. The method for generating a hospital logistics plan according to claim 1, characterized in that: Selecting a number of the existing plans that meet the expected evaluation requirements from the plan library includes the following steps: Selecting several typical plans from the existing plans corresponding to the emergency event type label matching the emergency event, wherein the typical plans are plans with good emergency response results or with high universality of the characteristic parameters marked in advance by the user; The feature similarity between each of the existing plans and the emergency event is calculated, and a preset number of the existing plans with higher feature similarity are selected as high-matching plans, wherein the feature similarity is characterized by the degree of similarity between the feature parameters in the existing plans and the feature parameters in the emergency event.

5. The method for generating a hospital logistics plan according to claim 4, characterized in that: Calculating the behavior expectations brought about by the emergency event under the emergency countermeasures corresponding to each of the selected existing plans includes the following steps: In each of the typical plans, the existence ratio of the implementation behaviors that match the characteristic parameters corresponding to the emergency events is calculated and defined as the generalized expectation; In each of the high-matching plans, the existence ratio of the implementation behaviors that match the characteristic parameters corresponding to the emergency events is calculated and defined as a special expectation; The behavior expectations corresponding to each of the existing plans are calculated according to the generalized expectations and the special expectations.

6. The method for generating a hospital logistics plan according to claim 1, characterized in that: Calculating the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation includes the following steps: The behavioral potential is calculated based on the following formula: Px(sn,R)=f(Ex|sn,Rvx|sn), Among them, Px represents the behavioral potential, sn represents the scenario obtained by the nth emergency based on the emergency event type label, R represents the possibility of resolving the emergency, Ex represents the behavioral expectation, Rvx represents the behavioral reward, and f(x) is a functional relationship.

7. The method for generating a hospital logistics plan according to claim 1, characterized in that: The following steps are also included: Each characteristic parameter in the existing plan and the emergency event corresponds to a control point, wherein the control point includes an internal control point and an external control point; In the existing plan, it is determined whether the behavior reward corresponding to each implementation behavior is strongly correlated with the action of the implementation behavior itself, and the strong correlation is characterized by the reward of a behavior being determined by the behavior itself; If it exists, the characteristic parameter corresponding to the implementation behavior corresponds to the internal control point; if it does not exist, the characteristic parameter corresponding to the implementation behavior corresponds to the external control point; In the emergency event, each of the characteristic parameters is compared with the characteristic parameters in the existing plan. If the same characteristic parameters exist, the control point that is the same as the characteristic parameter in the existing plan is added to the characteristic parameters; if the same characteristic parameters do not exist, the characteristic parameters correspond to the external control points.

8. The method for generating a hospital logistics plan according to claim 7, characterized in that: After selecting the existing plan with the highest behavior potential as the preferred plan, the following steps are also included: Calculating control point tendency information based on the quantity ratio of the internal control points and the external control points corresponding to each of the characteristic parameters in the emergency, and generating achievement motivation based on the control point tendency information to determine whether to perform intelligent adjustment on the preferred plan, wherein the achievement motivation is characterized as the willingness motivation of the system to perform intelligent adjustment on the preferred plan, and the intelligent adjustment includes adding the implementation behavior and / or deleting the implementation behavior; The control point tendency includes the internal control tendency and the external control tendency, and the achievement motivation corresponding to the internal control tendency is greater than the achievement motivation corresponding to the external control tendency.

9. A hospital logistics plan generation system, characterized in that: include: Plan library, used to store several existing plans; A plan combing module is used to comb the existing plans in the plan library, obtain several characteristic parameters and emergency countermeasures in each of the existing plans, and split the emergency countermeasures into implementation behaviors corresponding to the characteristic parameters, wherein each of the existing plans corresponds to an emergency event type label; An emergency event acquisition module is used to acquire an emergency event with the emergency event type label, and acquire the characteristic parameters corresponding to the emergency event based on the Internet of Things module, put the characteristic parameters corresponding to the emergency event into the plan library and compare and predict with the existing plans of the same type; A behavior reward calculation module is used to obtain the rewards corresponding to each of the characteristic parameters and one or more of the corresponding implementation behaviors in the existing plan, and calculate the behavior rewards brought about by the emergency event under the emergency countermeasures corresponding to each of the existing plans based on the rewards, wherein the behavior rewards are represented by the size of the positive value brought about by a certain behavior; A behavior expectation calculation module is used to select a number of existing plans that meet the expected evaluation requirements from the plan library, and calculate the behavior expectations brought about by the emergency event under the emergency countermeasures corresponding to each of the selected existing plans, wherein the behavior expectation is characterized by the possibility that selecting a certain behavior can bring positive value; A plan generation module is used to calculate the behavior potential corresponding to each of the existing plans based on the behavior reward and the behavior expectation, wherein the behavior potential is characterized by the possibility of the plan being selected in a specific scenario, and select the existing plan with the highest behavior potential as the preferred plan; A plan execution module, used to send each implementation behavior corresponding to the preferred plan to a corresponding object for execution through the Internet of Things module; The Internet of Things module is used to obtain the characteristic parameters corresponding to the emergency event and control the networked Internet of Things devices to execute the implementation behaviors corresponding to the preferred plan.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 8.

Citation Information

Patent Citations

  • Automatic generation method for digital emergency plan

    CN102509164A

  • Emergency plan digitization generation method

    CN103886507A

  • Digital parameter design method and system for safety emergency plan, storage medium and computer equipment

    CN111310330A

  • Platform for digitally decomposing, managing and applying flood prevention and emergency rescue technical scheme

    CN112785164A

  • Hydro-junction operation risk real-time control system and method

    CN115330127A