Clinical resource reservation method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a clinical resource reservation method and device, equipment and a storage medium. The method comprises the following steps: constructing a diagnosis and treatment portrait of any patient according to main diagnosis information of the patient; according to the historical occupation time sequence information of each clinical resource, predicting target occupation time sequence information of the clinical resource in a future time period; according to the diagnosis and treatment portrait of the patient and the target occupation time sequence information of each clinical resource, a corresponding resource reservation path is generated for the patient, and the resource reservation path comprises the optimal diagnosis and treatment action of the patient in each time step, the clinical resource occupied by the optimal diagnosis and treatment action and the resource reservation time. According to the embodiment of the invention, the method can achieve the efficient and reasonable reservation of clinical resources, gives consideration to the maximum utilization of the clinical resources and the minimum waiting time of the patient, guarantees the full and effective utilization of the clinical resources, and improves the medical treatment efficiency of the patient.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing technology, and specifically to a clinical resource reservation method, device, equipment and storage medium. Background Art

[0002] As medical needs continue to grow, clinical resources in hospitals (such as beds, operating rooms, and examination equipment) are becoming increasingly scarce. Usually, the directors of each department need to make appointments for each patient based on the clinical resource usage of their department.

[0003] However, due to the limited clinical resources within the hospital, there is often a problem of uneven distribution of clinical resources, and the clinical resource information of each department is not interoperable, resulting in inefficient clinical resource appointments and waste of resources, greatly reducing the efficiency of patients' medical treatment. Summary of the invention

[0004] The embodiments of the present application provide a clinical resource reservation method, device, equipment and storage medium to achieve efficient and reasonable reservation of clinical resources, taking into account both maximizing the utilization of clinical resources and minimizing the waiting time of patients, ensuring the full and effective utilization of clinical resources, and improving the efficiency of patients' medical treatment.

[0005] In a first aspect, an embodiment of the present application provides a clinical resource reservation method, the method comprising:

[0006] Based on the main diagnosis information of any patient, construct a diagnosis and treatment profile of the patient;

[0007] Predicting target occupancy time series information of each clinical resource in a future time period based on historical occupancy time series information of the clinical resource;

[0008] Based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource, a corresponding resource reservation path is generated for the patient. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0009] In a second aspect, an embodiment of the present application provides a clinical resource reservation device, the device comprising:

[0010] A patient portrait construction module is used to construct a diagnosis and treatment portrait of any patient based on the primary diagnosis information of the patient;

[0011] A resource occupancy prediction module, used to predict the target occupancy time series information of each clinical resource in a future time period based on the historical occupancy time series information of the clinical resource;

[0012] A resource reservation module is used to generate a corresponding resource reservation path for the patient based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0014] A processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the clinical resource reservation method provided in the first aspect of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program enables a computer to execute the clinical resource reservation method provided in the first aspect of the present application.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the clinical resource reservation method provided in the first aspect of the present application.

[0017] The embodiment of the present application provides a clinical resource reservation method, device, equipment and storage medium. First, according to the main diagnosis information of any patient, a diagnosis and treatment portrait of the patient is constructed. Moreover, by analyzing the historical occupancy time series information of each clinical resource, the target occupancy time series information of each clinical resource in the future time period can be predicted. Thus, by comprehensively analyzing the diagnosis and treatment portrait of the patient and the target occupancy time series information of each clinical resource, the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are determined, so as to generate a corresponding resource reservation path for the patient, realize efficient and reasonable reservation of clinical resources, take into account the maximum utilization of clinical resources and the minimum waiting time of patients, avoid idle waste of clinical resources, and ensure the full and effective utilization of clinical resources, so that patients can make appointments with available clinical resources in time when they see a doctor, to provide patients with more convenient and efficient medical treatment services, and improve the efficiency of medical treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 A flowchart of a clinical resource reservation method shown in an embodiment of the present application;

[0020] Figure 2 A flowchart of another clinical resource reservation method shown in an embodiment of the present application;

[0021] Figure 3 A principle block diagram of a clinical resource reservation device shown in an embodiment of the present application;

[0022] Figure 4 A schematic block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In order to solve the problem of uneven distribution of clinical resources in medical institutions, which leads to low efficiency in appointment and waste of clinical resources, the embodiment of the present application designs a new clinical resource appointment scheme. This scheme takes the patient as the core and the patient's primary diagnosis information as the basis. By analyzing the historical occupancy time series information of each clinical resource in the medical institution, the available clinical resources in the entire medical treatment process are intelligently allocated and reserved for the patient, thereby realizing efficient and reasonable appointment of clinical resources, taking into account the maximum utilization of clinical resources and minimizing the waiting time of patients, ensuring the full and effective utilization of clinical resources, and improving the efficiency of patients' medical treatment.

[0026] Figure 1 This is a flow chart of a clinical resource reservation method shown in an embodiment of the present application. Figure 1, the method may include the following steps:

[0027] S110, constructing a diagnosis and treatment profile of any patient based on the primary diagnosis information of the patient.

[0028] When any patient visits a hospital, he or she usually needs to undergo various medical examinations with the assistance of a doctor in order to obtain the results of the various medical examinations of the patient. Moreover, when any patient undergoes various medical examinations under the advice of a doctor, he or she usually needs to use the corresponding clinical resources in the hospital. Among them, the clinical resources in this application may include but are not limited to the examination equipment, beds, operating rooms, etc. used by patients when performing corresponding medical examinations. It can be seen that patients need to undergo different examinations under different symptoms, which requires the use of different clinical resources, and there can be multiple clinical resources of the same kind.

[0029] Therefore, when any patient visits a doctor, in order to ensure the rational allocation of various clinical resources to the patient, this application first needs to analyze the various medical examination information performed by the patient under the advice of the attending physician, and determine the patient's specific medical diagnosis results as the patient's primary diagnostic information to describe the main medical diagnosis results obtained by the attending physician after a preliminary diagnosis of the patient, so as to subsequently accurately analyze the availability of various clinical resources for patients with this condition.

[0030] It is understandable that after the attending doctor makes a preliminary diagnosis of any patient, he or she will usually record the relevant disease diagnosis results after the preliminary diagnosis in the patient's admission record form for subsequent review. Therefore, for any patient, this application can extract the corresponding recorded content from the patient's admission record form and perform corresponding diagnostic analysis on it to determine the patient's main diagnostic information.

[0031] Then, in order to comprehensively and intuitively describe the specific diagnosis results of any patient's condition and accurately allocate various clinical resources for patients with such conditions, the present application can analyze the specific content used to describe each condition in the patient's main diagnostic information to determine key information such as the patient's disease type, disease diagnosis and treatment status, disease severity and potential disease risks, thereby constructing a diagnosis and treatment portrait of the patient to comprehensively and intuitively describe the patient's specific disease diagnosis and treatment status, so as to subsequently accurately analyze which clinical resources are suitable for patients with such conditions during the entire medical treatment process and realize reasonable reservation of clinical resources.

[0032] S120, predicting target occupancy time series information of each clinical resource in a future time period based on the historical occupancy time series information of the clinical resource.

[0033] Considering that when any patient visits a hospital, the clinical resources that the patient needs to use when performing various examinations and tests during the entire consultation process are usually analyzed in advance, that is, reservations are made in advance for the clinical resources that the patient may use when performing various examinations and tests in the future. Then, in order to ensure the accurate reservation of clinical resources, this application can analyze the historical usage of each clinical resource in the medical structure for a large number of patients to determine the usage pattern of each clinical resource, so as to accurately analyze which clinical resources any patient can use when performing corresponding examinations and tests in the future.

[0034] However, since different departments of medical institutions are equipped with corresponding clinical resources, and the use of clinical resources between different departments is not transparent, it leads to the problem of being unable to collaborate across departments. So, in order to avoid the situation where the clinical resources of one department are insufficient while the clinical resources of another department are idle and wasted, this application can use the Internet of Things technology to configure a corresponding data sharing mechanism for the use and idleness of clinical resources in each department of the medical institution, so that this application can monitor the use and idle status of each clinical resource in each department in real time.

[0035] In some achievable methods, the present application can set a corresponding Internet of Things sensor on each clinical resource in each department to collect relevant sensor data used to determine whether the clinical resource is used by the patient in real time, so as to determine the occupation and idle state of the clinical resource. Then, the Internet of Things sensor set on each clinical resource can transmit the collected relevant sensor data to the data center through a wireless network, and the data center determines whether each clinical resource is used by the patient based on this to determine the real-time occupation and idle state of the clinical resource, so as to centrally store and uniformly manage the real-time occupation and idle state data of the clinical resources in each department to support cross-department data sharing. Using the above method, the phenomenon of information islands existing in the management of clinical resource occupation and idle state between multiple departments can be broken, and the multi-dimensional clinical resource management between multiple departments can be horizontally combined to realize the transparency and visualization of clinical resources between different departments. Thus, by real-time monitoring of the occupation and idle state of each clinical resource in each department to timely update and share clinical resource information, to quickly respond to data queries on the occupation and idle state of clinical resources, so as to intelligently allocate and reserve each clinical resource for each patient.

[0036] In this application, in order to accurately analyze which clinical resources any patient can use when performing corresponding inspection and testing operations during the medical consultation process, this application first needs to analyze the usage rules of each clinical resource in each department. Therefore, for each clinical resource, this application can obtain a large amount of relevant sensor data collected by the clinical resource in the historical process from the data center, and judge the historical time period information of the clinical resource in the occupied state and the historical time period information in the idle state in the historical process, thereby forming the historical occupancy time series information of the clinical resource. Among them, the historical occupancy time series information of each clinical resource can clearly indicate the entire state change of the clinical resource in the occupied and idle states over time in the historical process.

[0037] In the same manner as above, the historical occupancy time series information of each clinical resource in each department can be determined. Then, by analyzing the entire state change of the clinical resource in the occupied and idle states in the historical process as time changes, the time dependence of the clinical resource when it changes between the occupied state and the idle state is determined, so as to determine the specific change law of the clinical resource between the occupied state and the idle state as time changes. Furthermore, according to the specific change law of each clinical resource between the occupied state and the idle state as time changes, the present application can predict the entire state change of the clinical resource between the occupied state and the idle state in the future period of time, so as to generate the target occupancy time series information of the clinical resource in the future period. Among them, the target occupancy time series information of each clinical resource can clearly indicate which time periods in the future period of time the clinical resource may be in the occupied state and which time periods it may be in the idle state.

[0038] It is understandable that the length of time required for patients with different symptoms to see a doctor in a hospital will also be different. Therefore, in order to make advance reservations for the clinical resources that any patient needs to use during the entire medical treatment process, this application can determine the length of time that the patient may need to see a doctor by analyzing the specific condition of any patient, thereby determining the patient's future time period. In other words, when making reservations for each clinical resource for any patient, a future time period can be set in advance for the patient to analyze the target occupancy timing information of each clinical resource in the future time period.

[0039] S130, based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource, a corresponding resource reservation path is generated for the patient. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0040] In order to achieve accurate reservation of clinical resources when any patient visits the hospital, the present application may first analyze the patient's specific medical condition and treatment conditions described in the patient's medical portrait to determine key information such as the patient's disease type, medical condition, severity of disease, and potential disease risks. In this way, the various medical treatment actions that need to be performed in sequence when the patient visits the hospital can be preliminarily determined as the optimal medical treatment actions for the patient at each time step.

[0041] The diagnosis and treatment actions in this application can be various diagnosis and treatment operations that any patient may perform when visiting a hospital, such as various inspection and testing operations, surgical operations, hospitalization operations, rehabilitation training operations, etc. Moreover, the time step changes are used to indicate the timing changes of various diagnosis and treatment actions that need to be performed when the patient visits a hospital.

[0042] Then, for the optimal diagnosis and treatment action of the patient at each time step, the present application can determine which type of clinical resources the patient needs to use when performing the optimal diagnosis and treatment action, and determine the target occupation timing information of each clinical resource under this type in the future time period. Then, by analyzing the target occupation timing information of each clinical resource under this type, it can be determined which time periods of the clinical resource in the future time period may be occupied, and which time periods may be idle. Thus, from each clinical resource under this type, a most suitable clinical resource can be determined for the optimal diagnosis and treatment action as the clinical resource occupied by the optimal diagnosis and treatment action, so that the clinical resource occupied by the optimal diagnosis and treatment action can support the patient to wait for the shortest time when executing the optimal diagnosis and treatment action under the corresponding time step, thereby taking into account the maximum utilization of clinical resources and the patient's minimum waiting time. Moreover, by analyzing which time period of the clinical resources occupied by the optimal diagnosis and treatment action in the idle state can support the patient to wait for the shortest time, the resource reservation time corresponding to the clinical resources occupied by the optimal diagnosis and treatment action is determined.

[0043] Finally, by connecting in series the optimal diagnosis and treatment actions that need to be performed in sequence when the patient visits the hospital, a corresponding resource reservation path can be generated for the patient. In this resource reservation path, the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action at each time step can be configured to achieve reasonable reservation of clinical resources, ensure full and effective utilization of clinical resources, and improve the efficiency of patients' medical treatment.

[0044] In addition, in order to ensure the accuracy of clinical resource reservations for any patient, the present application can also use the doctor's scheduling information to analyze the target occupancy timing information of each clinical resource of the corresponding type required for the patient's optimal diagnosis and treatment action at each time step, so as to determine the most suitable clinical resource for the optimal diagnosis and treatment action. The clinical resources occupied by the optimal diagnosis and treatment action can not only support the patient's waiting time to be minimized when executing the optimal diagnosis and treatment action at the corresponding time step, but also ensure that the patient can perform the optimal diagnosis and treatment action with the assistance of a doctor, thereby further improving the patient's diagnosis and treatment quality.

[0045] Furthermore, in order to ensure the accuracy of clinical resource reservations, for any patient's resource reservation path, the present application can present the resource reservation path to the patient's attending physician to optimize the resource reservation path.

[0046] That is to say, by presenting the patient's resource reservation path to the patient's doctor, the doctor will judge the optimal diagnosis and treatment actions that need to be performed when the patient sees the doctor, the clinical resources occupied by the optimal diagnosis and treatment actions, and the resource reservation time based on the patient's specific diagnosis and the latest clinical resource changes, so as to make corresponding adjustments to the inappropriate parts of the resource reservation path, optimize the resource reservation path, and ensure the reasonable reservation of clinical resources. Moreover, the doctor can notify the patient of the final resource reservation path through SMS, phone calls, or message push, so that the patient can understand the precautions when seeing the doctor in advance.

[0047] The technical solution provided in the embodiment of the present application first constructs the diagnosis and treatment portrait of any patient based on the main diagnosis information of the patient. Moreover, by analyzing the historical occupancy time series information of each clinical resource, the target occupancy time series information of each clinical resource in the future time period can be predicted. Thus, by comprehensively analyzing the diagnosis and treatment portrait of the patient and the target occupancy time series information of each clinical resource, the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are determined, so as to generate a corresponding resource reservation path for the patient, realize efficient and reasonable reservation of clinical resources, take into account the maximum utilization of clinical resources and the minimization of waiting time for patients, avoid idle waste of clinical resources, and ensure the full and effective utilization of clinical resources, so that patients can make appointments with available clinical resources in time when they see a doctor, to provide patients with more convenient and efficient medical treatment services, and improve the efficiency of medical treatment for patients.

[0048] As an optional implementation scheme in the present application, in order to ensure efficient and reasonable reservation of clinical resources, the present application can provide detailed explanations on the specific steps of constructing the diagnosis and treatment profile of any patient, the steps of predicting the specific occupancy and idle status of clinical resources in future time periods, and the specific steps of generating the resource reservation path.

[0049] Figure 2 FIG. 1 is a flow chart of another clinical resource reservation method shown in an embodiment of the present application. Figure 2 As shown, the method may include the following steps:

[0050] S210, determining the main diagnostic features of the patient's disease according to the main diagnostic information of any patient.

[0051] For any patient, in order to ensure the rational allocation of various clinical resources to the patient, this application will first analyze the various medical examination information performed by the patient under the advice of the attending physician, and determine the patient's specific medical diagnosis results as the patient's primary diagnostic information, thereby describing the main medical diagnosis results obtained by the attending physician after a preliminary diagnosis of the patient.

[0052] Then, in order to ensure the accurate construction of the patient's diagnosis and treatment portrait, the present application can perform corresponding data cleaning, standardization and other operations on the patient's main diagnosis information and basic information to obtain the patient's relevant medical record data. Moreover, using the recursive feature elimination (RFE) algorithm, the relevant medical record data of the patient after the above processing can be subjected to feature extraction operations related to the patient's symptom description to obtain the patient's main diagnosis feature of the symptom.

[0053] S220, constructing a diagnosis and treatment profile of the patient based on the main diagnostic features of the disease.

[0054] By conducting corresponding diagnostic analysis on the content used to describe the patient's specific condition in the patient's main diagnostic characteristics, we can determine key information such as the patient's disease type, disease diagnosis and treatment, disease severity, and potential disease risks, thereby constructing a diagnostic and treatment profile of the patient to comprehensively and intuitively describe the patient's specific disease diagnosis and treatment.

[0055] In some possible implementations, in order to ensure the accurate construction of a patient's diagnosis and treatment profile, the present application may pre-construct a disease classification model for accurately analyzing the type of disease suffered by any patient so as to accurately construct a diagnosis and treatment profile for the patient.

[0056] Specifically, the disease classification model can be trained in the following way:

[0057] 1) Data preprocessing: Collect a large amount of basic information and main diagnosis information of patients, and perform corresponding data cleaning, standardization and other operations on them to obtain relevant medical record data of a large number of patients, so that the numerical range of medical record data under different attributes can be on the same scale to ensure the accuracy of subsequent medical record data processing.

[0058] 2) Feature extraction: Use the RFE algorithm to perform feature extraction operations related to the patient's symptom description on a large number of patients' relevant medical record data after preprocessing to obtain the main diagnostic features of each patient's symptom.

[0059] 3) Disease classification: The main diagnostic features of a large number of patients' diseases after the above processing are used as training samples, and the corresponding disease category labels are marked on them as the corresponding sample labels. In addition, the support vector machine (SVM) algorithm is used to construct the corresponding SVM model as the initial disease classification model.

[0060] 4) Model training: Select the radial basis function (RBF) of the nonlinear kernel as the kernel function of the SVM model, as shown below:

[0061] K(x i ,x j )=exp(-γx i -x j 2 )

[0062] Among them, γ is the parameter of RBF kernel, ||x i -x j || is the i-th training sample x i With the jth training sample x j The Euclidean distance between .

[0063] The objective function of the SVM model can be:

[0064] Where w is the normal vector of the hyperplane, ξ i is a slack variable used to deal with the situation where the linear equations are inseparable, and c is a regularization parameter.

[0065] Therefore, by using the above training samples and sample labels to train the SVM model, the optimal hyperplane can be determined to separate the training samples of different categories as accurately as possible and maximize the distance between the two types of training samples and the hyperplane, so as to achieve accurate classification of training samples under different categories. Then, the trained SVM model is used as the disease classification model in this application.

[0066] 5) The performance of the trained disease classification model can be evaluated using indicators such as cross-validation, accuracy, and recall. The network parameters of the disease classification model (such as C parameters, kernel function type, etc.) are adjusted according to the evaluation results to optimize the model performance.

[0067] Then, for any patient's diagnosis and treatment profile, the present application can be constructed in the following manner: input the main diagnostic features of the disease into a pre-constructed disease classification model to obtain the patient's disease category; and construct the patient's diagnosis and treatment profile based on the patient's disease category.

[0068] That is to say, for any patient, after determining the main diagnostic features of the patient's disease, the present application can input the main diagnostic features of the patient's disease into a trained disease classification model, and perform corresponding feature processing on the above-mentioned main diagnostic features of the disease through the disease classification model to determine key information such as the patient's disease type, disease diagnosis and treatment status, disease severity and potential disease risks, thereby determining the patient's disease category.

[0069] It can be understood that by analyzing the patient's disease category, key information such as the patient's disease type, disease diagnosis and treatment, disease severity and potential disease risks can be obtained, thereby constructing a diagnosis and treatment profile of the patient.

[0070] S230: For each clinical resource, obtain historical occupancy time series information of the clinical resource.

[0071] In order to accurately analyze which clinical resources any patient can use when performing corresponding examination and testing operations during the medical consultation process, this application first needs to analyze the usage patterns of each clinical resource in each department.

[0072] Therefore, for each clinical resource, the present application can obtain a large amount of relevant sensor data collected by the clinical resource in the historical process from the data center that supports the sharing of relevant sensor data of each clinical resource, and judge the historical time period information of the clinical resource in the occupied state and the historical time period information of the clinical resource in the historical process, thereby forming the historical occupancy time series information of the clinical resource. Among them, the historical occupancy time series information of each clinical resource can clearly indicate the entire state change of the clinical resource in the occupied and idle states over time in the historical process.

[0073] S240, inputting the historical occupancy time series information of the clinical resource into a pre-built time series prediction model to predict the target occupancy time series information of the clinical resource in a future time period.

[0074] In order to accurately analyze the usage of each clinical resource in future time periods, the present application can pre-construct a time series prediction model to analyze the historical time series of each clinical resource in the occupied and idle states in the historical process, to predict the time series of the clinical resource in the occupied and idle states in future time periods, to describe which time periods in the future time periods the clinical resource may be occupied and which time periods it may be idle.

[0075] In this application, the time series prediction model in this application can be trained in the following way:

[0076] 1) Data collection: Obtain the relevant state change time series data of each clinical resource in each department of the medical institution in the occupied and idle states in the historical process from the data center or other similar information systems, and process the missing values ​​and abnormal values ​​in the collected data to ensure the integrity, accuracy and consistency of the data.

[0077] 2) Data preprocessing: According to data business requirements, data features related to predicting the occupation and idle status of clinical resources in future time periods can be extracted from the above collected data, including but not limited to the timestamps of the occupied and idle states of each clinical resource, department information, resource type, whether it is occupied or idle at the corresponding timestamp, occupation duration, etc.

[0078] Moreover, by encoding the above corresponding data features (such as timestamps), date and time features (such as year, month, day, hour, minute, etc.) or time steps (such as a continuous integer sequence in hours) are usually used to support computational readability. The above data features can also be normalized or standardized to improve the convergence speed and performance of the model. Among them, normalization can use Min-Max Scaling, and standardization can use Z-Score Normalization.

[0079] Therefore, the historical time series data related to a large number of clinical resources being occupied or idle can be used as training samples for the time series prediction model, and the training samples can be divided into training set, validation set and test set, with the ratios of 70%, 15% and 15%. Moreover, according to the time window represented by the future period that the clinical resources need to be predicted, the training samples can be divided into input sequence and target sequence. Among them, the input sequence can be training data, and the target sequence can be sample labels.

[0080] 3) Model construction: The Long Short-Term Memory Networks (LSTM) model is used as the initial time series prediction model.

[0081] Specifically, the design architecture of the LSTM model may include an input layer, an LSTM layer, a fully connected layer (Dense layer), and an output layer. The input layer may receive an input sequence in a preprocessed time series. The LSTM layer captures the temporal dependencies and patterns in the input sequence data, and adds a Dropout layer to prevent data overfitting. The fully connected layer converts the output of the LSTM layer into the final prediction result. The output layer selects a linear activation function using the target sequence as the prediction target (e.g., resource occupancy, idle time, etc.).

[0082] For example, the number of LSTM layers can be 2, the number of neurons / layer can be 100, and the Dropout rate can be 0.2 to prevent data overfitting.

[0083] Therefore, the above input sequence can be continuously input into the LSTM model, and the target sequence can be used to train it, so that the trained LSTM model can be used as the time series prediction model in this application to predict the resource demand trend of various clinical resources in the future.

[0084] Then, after obtaining the historical occupancy time series information of each clinical resource, the present application can input the historical occupancy time series information of each clinical resource into a trained time series prediction model, and analyze the historical occupancy time series information of each clinical resource through the time series prediction model to determine the time dependence of the clinical resource when it changes continuously between the occupied state and the idle state, so as to determine the specific change law of the clinical resource between the occupied state and the idle state over time, and based on this law, predict the overall state change of the clinical resource between the occupied state and the idle state in the future period of time, so as to output the target occupancy time series information of the clinical resource in the future time period, so as to clearly indicate which time periods in the future time period the clinical resource may be in the occupied state and which time periods it may be in the idle state.

[0085] S250, constructing the current status characteristics of the patient for each clinical resource based on the diagnosis and treatment profile of the patient and the target occupancy time series information of each clinical resource.

[0086] Since the specific diagnosis information of any patient and the occupation and idle status of each clinical resource will affect the clinical resource reservation result when the patient visits the doctor. Therefore, in order to ensure the efficient and reasonable reservation of clinical resources, this application can perform feature extraction on the patient's diagnosis and treatment portrait to obtain the corresponding patient diagnosis and treatment characteristics. Moreover, by performing corresponding feature analysis on the target occupancy timing information of each clinical resource, it is possible to determine which time periods in the future may be occupied and which time periods may be idle for each clinical resource, thereby obtaining the timing state characteristics of each clinical resource.

[0087] Therefore, by combining the above-mentioned patient diagnosis and treatment characteristics with the time series status characteristics of each clinical resource, the current status characteristics of the patient for each clinical resource can be constructed, so as to accurately analyze the specific appointment status of the patient for each clinical resource when visiting the hospital.

[0088] In one case, the expertise and scheduling of the patient's doctor may also affect the patient's accurate reservation of various clinical resources when visiting. Therefore, when constructing the current status characteristics of the patient facing various clinical resources, based on the above-mentioned patient diagnosis and treatment characteristics and the time series status characteristics of various clinical resources, this application can further combine the expertise information and scheduling information of the doctor to ensure the comprehensiveness of the current status characteristics of the patient facing various clinical resources.

[0089] S260, input the current state characteristics into the pre-built resource reservation model to obtain the optimal diagnosis and treatment action for the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action, so as to form the resource reservation path corresponding to the patient.

[0090] In order to achieve efficient and reasonable reservation of various clinical resources when any patient visits the hospital, the present application can pre-build a resource reservation model to analyze the current status characteristics of any patient facing various clinical resources, so as to make reservations in advance for the patient for the clinical resources needed to perform various diagnosis and treatment actions.

[0091] In this application, the resource reservation model in this application can be trained in the following ways:

[0092] 1) Model construction: Considering that any patient usually performs multiple diagnosis and treatment actions when visiting a doctor, in order to achieve efficient diagnosis and treatment of the patient, when the patient visits a doctor, it is necessary to reserve a suitable clinical resource in advance for each diagnosis and treatment action to be performed, so that the resource reservation model can support the reservation of clinical resources for each diagnosis and treatment action performed by the patient in sequence.

[0093] Accordingly, the present application may use a deep Q network (DQN) to construct an initial resource reservation model. As a deep reinforcement learning algorithm, the DQN network may use a deep neural network to approximate the value function Q(s,a), where s represents the state and a represents the action. Then, the DQN network may learn a state-to-action mapping strategy through an agent interacting with the environment to maximize future cumulative rewards. That is, at each time step, the agent can select an executable action based on the current state, and the environment provides the next state and immediate reward based on this action, thereby learning a mapping strategy from state to action to maximize future cumulative rewards.

[0094] The DQN network can include an input layer, a convolutional layer (optional), a fully connected layer, an output layer, etc. The input layer is used to receive state features, and the output layer outputs the Q value (i.e. expected reward) of each action. Experience replay and target network are used to stabilize the training process.

[0095] 2) State definition: Based on the expected state time series characteristics represented by the target occupancy time series information of each clinical resource and the diagnosis and treatment characteristics of each patient involved in the diagnosis and treatment profile of any patient, the corresponding state dimensions can be pre-defined in the resource reservation model, which may include but are not limited to the type of disease, diagnosis and treatment of the disease, severity of the disease and potential disease risk of the patient, as well as the expected state change time series characteristics corresponding to which time periods of each clinical resource may be occupied and which time periods may be idle in the future. This application can use vectors or matrices to represent the state characteristics of the input.

[0096] 3) Action definition: By analyzing the various diagnostic and treatment actions that each patient may perform when visiting the hospital, this application can pre-define the corresponding diagnostic and treatment actions in the resource reservation model. The diagnostic and treatment actions may include but are not limited to selecting a department, various inspection and testing operations, surgical operations, hospitalization operations, rehabilitation training operations, etc.

[0097] It can be seen that the resource reservation model in the present application may have defined multiple diagnosis and treatment actions that support any patient to perform during the entire medical consultation process.

[0098] 4) Reward function design: Design a corresponding reward function in the resource reservation model to evaluate the quality of the optimal diagnosis and treatment action determined according to the current state at each time step. Among them, the reward function can consider multiple factors such as the precise matching of treatment plans, the efficient use of clinical resources, and the patient's satisfaction. Therefore, positive rewards are given to resource reservation paths that meet the goals; negative rewards are given to resource reservation paths that do not meet the goals or cause waste of clinical resources.

[0099] 5) Model training: A large number of historical state features constructed from the diagnosis and treatment portraits of a large number of patients in the historical treatment process and the target occupancy time series information of various clinical resources in the historical treatment process of patients are used to train the above-mentioned DQN network so that it can learn how to select the optimal diagnosis and treatment action based on the current state features.

[0100] During the training process, the ε-greedy strategy can be used for action selection to balance exploration and utilization. The parameters of the DQN network (such as learning rate, discount factor, network structure, etc.) are adjusted according to the performance of the validation set to obtain a trained resource reservation model.

[0101] Then, after obtaining the current state characteristics of the patient facing each clinical resource, the present application can input the current state characteristics into the above-mentioned trained resource reservation model, and analyze the patient's diagnosis and treatment characteristics in the current state characteristics through the resource reservation model to obtain the reward value (that is, the Q value) of each diagnosis and treatment action at each time step, and take the diagnosis and treatment action with the highest Q value at each time step as the optimal diagnosis and treatment actions that need to be performed in sequence when the patient visits the doctor, that is, the optimal diagnosis and treatment action for the patient at each time step.

[0102] Moreover, for the optimal diagnosis and treatment action at each time step, the resource reservation model is used to analyze the expected state change timing characteristics of each clinical resource in the current state characteristics, so as to determine which clinical resource is most suitable for the patient to occupy when performing the optimal diagnosis and treatment action, so that the clinical resources occupied by the optimal diagnosis and treatment action can support the patient's waiting time to be as short as possible when performing the optimal diagnosis and treatment action at the corresponding time step, thereby taking into account both the maximization of clinical resources and the minimization of patients' waiting time, thereby determining the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0103] In the same way as above, the optimal diagnosis and treatment action for the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action can be determined. Then, the optimal diagnosis and treatment actions that need to be performed in sequence when the patient visits the doctor are connected in series, and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action at each time step are configured, and the resource reservation path corresponding to the patient can be generated to achieve reasonable reservation of clinical resources.

[0104] In some implementable methods, in order to ensure efficient and reasonable reservation of clinical resources, the resource reservation path for the patient can be determined by the following method: input the current state characteristics into the pre-built resource reservation model to obtain the patient's optimal diagnosis and treatment action at the current time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time; update the current state characteristics according to the simulated execution state of the patient's optimal diagnosis and treatment action at the current time step to obtain the new current state characteristics corresponding to the next time step, and continue to obtain the patient's optimal diagnosis and treatment action at the next time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time through the resource reservation model until the patient's visit end action is obtained; generate a corresponding resource reservation path for the patient based on the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0105] Specifically, after obtaining the current state characteristics of the patient facing each clinical resource, the present application can input the current state characteristics into the trained resource reservation model, and the resource reservation model analyzes the current state characteristics and outputs a reward value (that is, Q value) for each defined diagnosis and treatment action. Then, a diagnosis and treatment action with the highest Q value is selected from each defined diagnosis and treatment action as the optimal diagnosis and treatment action for the patient at the current time step, indicating the first diagnosis and treatment action that needs to be performed when the patient is treated. Moreover, by analyzing which time periods of each clinical resource in the future time period may be occupied and which time periods may be idle, a clinical resource that is most suitable for occupation can be determined for the optimal diagnosis and treatment action, and by analyzing which time period of the clinical resources occupied by the optimal diagnosis and treatment action can support the patient to wait for the shortest time in the idle state, the resource reservation time corresponding to the clinical resources occupied by the optimal diagnosis and treatment action can be determined.

[0106] Then, by simulating the optimal diagnosis and treatment action at the current time step, the state change of the optimal diagnosis and treatment action after the simulation execution can be determined, so as to update the current state characteristics and obtain the new current state characteristics corresponding to the next time step. Furthermore, the new current state characteristics corresponding to the next time step are input into the resource reservation model again, so that the resource reservation model performs the same processing operation as above, and the optimal diagnosis and treatment action of the patient at the next time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action can be obtained. The cycle is repeated until the optimal diagnosis and treatment action at a certain time step is the end action of the patient's visit, and the cycle can be ended to obtain the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action.

[0107] Furthermore, by connecting in series the various optimal diagnosis and treatment actions that need to be performed in sequence when the patient visits the doctor, a corresponding resource reservation path can be generated for the patient, and in the resource reservation path, the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action at each time step can be configured to achieve reasonable reservation of clinical resources, ensure full and effective utilization of clinical resources, and improve the efficiency of patients' medical treatment.

[0108] The technical solution provided in the embodiment of the present application first constructs the diagnosis and treatment portrait of any patient based on the main diagnosis information of the patient. Moreover, by analyzing the historical occupancy time series information of each clinical resource, the target occupancy time series information of each clinical resource in the future time period can be predicted. Thus, by comprehensively analyzing the diagnosis and treatment portrait of the patient and the target occupancy time series information of each clinical resource, the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are determined, so as to generate a corresponding resource reservation path for the patient, realize efficient and reasonable reservation of clinical resources, take into account the maximum utilization of clinical resources and the minimization of waiting time for patients, avoid idle waste of clinical resources, and ensure the full and effective utilization of clinical resources, so that patients can make appointments with available clinical resources in time when they see a doctor, to provide patients with more convenient and efficient medical treatment services, and improve the efficiency of medical treatment for patients.

[0109] Figure 3 This is a principle block diagram of a clinical resource reservation device shown in an embodiment of the present application. Figure 3 As shown, the device 300 may include:

[0110] A patient portrait construction module 310 is used to construct a diagnosis and treatment portrait of any patient based on the primary diagnosis information of the patient;

[0111] A resource occupancy prediction module 320, configured to predict target occupancy time series information of each clinical resource in a future time period based on the historical occupancy time series information of the clinical resource;

[0112] The resource reservation module 330 is used to generate a corresponding resource reservation path for the patient based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

[0113] In some implementations, the patient portrait building module 310 may include:

[0114] A feature extraction unit, used to determine the main diagnostic features of the disease of any patient according to the main diagnostic information of the patient;

[0115] The patient portrait construction unit is used to construct the diagnosis and treatment portrait of the patient according to the main diagnostic characteristics of the disease.

[0116] In some possible implementations, the patient portrait construction unit may be specifically used to:

[0117] Inputting the main diagnostic features of the disease into a pre-built disease classification model to obtain the disease category of the patient;

[0118] A diagnosis and treatment profile of the patient is constructed based on the patient's disease category.

[0119] In some implementations, the resource occupancy prediction module 320 may be specifically used to:

[0120] For each clinical resource, obtain the historical occupancy time series information of the clinical resource;

[0121] The historical occupancy time series information of the clinical resource is input into a pre-built time series prediction model to predict the target occupancy time series information of the clinical resource in a future time period.

[0122] In some implementations, the resource reservation module 330 may include:

[0123] A state feature construction unit, configured to construct a current state feature of the patient facing each of the clinical resources according to the diagnosis and treatment portrait of the patient and the target occupancy time series information of each of the clinical resources;

[0124] A resource reservation unit, used to input the current state feature into a pre-built resource reservation model, obtain the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action, so as to form a resource reservation path corresponding to the patient;

[0125] The resource reservation model has defined a plurality of diagnosis and treatment actions that can be performed by any patient during the entire medical consultation process.

[0126] In some possible implementations, the resource reservation unit may be specifically used to:

[0127] Inputting the current state feature into a pre-built resource reservation model to obtain the optimal diagnosis and treatment action for the patient at the current time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action;

[0128] The current state feature is updated according to the simulated execution state of the optimal diagnosis and treatment action of the patient at the current time step, and a new current state feature corresponding to the next time step is obtained, and the optimal diagnosis and treatment action of the patient at the next time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are continuously obtained through the resource reservation model until the patient's consultation end action is obtained;

[0129] A corresponding resource reservation path is generated for the patient according to the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action.

[0130] In some implementations, the clinical resource reservation device may further include a path presentation module. The path presentation module may be used to:

[0131] The resource reservation path is presented to the patient's attending physician to optimize the resource reservation path.

[0132] In the embodiment of the present application, firstly, the diagnosis and treatment portrait of any patient is constructed according to the main diagnosis information of any patient. Moreover, by analyzing the historical occupancy time series information of each clinical resource, the target occupancy time series information of each clinical resource in the future time period can be predicted. Thus, by comprehensively analyzing the diagnosis and treatment portrait of the patient and the target occupancy time series information of each clinical resource, the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are determined, so as to generate a corresponding resource reservation path for the patient, realize efficient and reasonable reservation of clinical resources, take into account the maximum utilization of clinical resources and the minimization of waiting time for patients, avoid idle waste of clinical resources, and ensure the full and effective utilization of clinical resources, so that patients can make appointments with available clinical resources in time when they go to the hospital, to provide patients with more convenient and efficient medical treatment services, and improve the efficiency of medical treatment for patients.

[0133] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Figure 3 The device 300 shown can execute any method embodiment in the present application, and the aforementioned and other operations and / or functions of each module in the device 300 are respectively for implementing the corresponding processes in each method in the embodiment of the present application. For the sake of brevity, they will not be repeated here.

[0134] The above describes the device 300 of the embodiment of the present application from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0135] Figure 4 A schematic block diagram of an electronic device according to an embodiment of the present application.

[0136] like Figure 4 As shown, the electronic device 400 may include:

[0137] The memory 410 and the processor 420, the memory 410 is used to store the computer program and transmit the program code to the processor 420. In other words, the processor 420 can call and run the computer program from the memory 410 to implement the method in the embodiment of the present application.

[0138] For example, the processor 420 may be configured to execute the above method embodiments according to instructions in the computer program.

[0139] In some embodiments of the present application, the processor 420 may include but is not limited to:

[0140] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0141] In some embodiments of the present application, the memory 410 includes but is not limited to:

[0142] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0143] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 410 and executed by the processor 420 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0144] like Figure 4 As shown, the electronic device may also include:

[0145] The transceiver 430 may be connected to the processor 420 or the memory 410 .

[0146] The processor 420 may control the transceiver 430 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 430 may include a transmitter and a receiver. The transceiver 430 may further include an antenna, and the number of antennas may be one or more.

[0147] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0148] The present application also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.

[0149] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.

[0150] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0152] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0153] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A clinical resource reservation method, characterized in that: include: Based on the main diagnosis information of any patient, construct a diagnosis and treatment profile of the patient; Predicting target occupancy time series information of each clinical resource in a future time period based on historical occupancy time series information of the clinical resource; Based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource, a corresponding resource reservation path is generated for the patient. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

2. The method according to claim 1, characterized in that The step of constructing a diagnosis and treatment profile of any patient based on the primary diagnosis information of the patient includes: Determine the main diagnostic features of the patient's disease based on the main diagnostic information of any patient; A diagnosis and treatment profile of the patient is constructed based on the main diagnostic features of the disease.

3. The method according to claim 2, characterized in that The step of constructing a diagnosis and treatment profile of the patient according to the main diagnosis characteristics of the disease includes: Inputting the main diagnostic features of the disease into a pre-built disease classification model to obtain the disease category of the patient; A diagnosis and treatment profile of the patient is constructed based on the patient's disease category.

4. The method according to claim 1, characterized in that The step of predicting target occupancy time series information of each clinical resource in a future time period based on historical occupancy time series information of the clinical resource includes: For each clinical resource, obtain the historical occupancy time series information of the clinical resource; The historical occupancy time series information of the clinical resource is input into a pre-built time series prediction model to predict the target occupancy time series information of the clinical resource in a future time period.

5. The method according to claim 1, characterized in that Generating a corresponding resource reservation path for the patient according to the patient's diagnosis and treatment profile and the target occupancy time sequence information of each clinical resource includes: According to the diagnosis and treatment portrait of the patient and the target occupancy time series information of each of the clinical resources, construct the current state characteristics of the patient facing each of the clinical resources; Input the current state feature into a pre-built resource reservation model to obtain the optimal diagnosis and treatment action for the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action, so as to form a resource reservation path corresponding to the patient; The resource reservation model has defined a plurality of diagnosis and treatment actions that can be performed by any patient during the entire medical consultation process.

6. The method according to claim 5, characterized in that The inputting of the current state feature into a pre-built resource reservation model to obtain the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action to form a resource reservation path corresponding to the patient includes: Inputting the current state feature into a pre-built resource reservation model to obtain the optimal diagnosis and treatment action for the patient at the current time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action; The current state feature is updated according to the simulated execution state of the optimal diagnosis and treatment action of the patient at the current time step, and a new current state feature corresponding to the next time step is obtained, and the optimal diagnosis and treatment action of the patient at the next time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action are continuously obtained through the resource reservation model until the patient's consultation end action is obtained; A corresponding resource reservation path is generated for the patient according to the optimal diagnosis and treatment action of the patient at each time step and the clinical resources and resource reservation time occupied by the optimal diagnosis and treatment action.

7. The method according to claim 1, characterized in that The method further comprises: The resource reservation path is presented to the patient's attending physician to optimize the resource reservation path.

8. A clinical resource reservation device, characterized in that: include: A patient portrait construction module is used to construct a diagnosis and treatment portrait of any patient based on the primary diagnosis information of the patient; A resource occupancy prediction module, used to predict the target occupancy time series information of each clinical resource in a future time period based on the historical occupancy time series information of the clinical resource; A resource reservation module is used to generate a corresponding resource reservation path for the patient based on the patient's diagnosis and treatment profile and the target occupancy time series information of each clinical resource. The resource reservation path includes the patient's optimal diagnosis and treatment action at each time step and the clinical resources occupied by the optimal diagnosis and treatment action and the resource reservation time.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the clinical resource reservation method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program enables a computer to execute the clinical resource reservation method according to any one of claims 1 to 7.

Images