Pre-hospital emergency flow prediction method and system based on spatio-temporal data

Abstract

The invention belongs to the technical field of data processing. The invention provides a pre-hospital emergency flow prediction method and system based on spatio-temporal data. The method comprises the following steps: acquiring historical emergency spatio-temporal data of each minimum space area; performing spatial feature extraction on the historical first-aid spatio-temporal data, and learning time evolution in a spatial dimension according to the extracted spatial features to obtain spatio-temporal features corresponding to the historical first-aid spatio-temporal data; performing linear layer embedding on the spatiotemporal features to obtain emergency spatiotemporal data traffic corresponding to each minimum space region in a certain time period in the future; according to the method, a city is divided into irregular minimum space areas for data mapping according to community attributes, spatial features are extracted from space-time image data after mapping, time evolution information is learned, and accurate prediction of emergency flow distribution of each minimum space area is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for predicting pre-hospital emergency flow based on spatiotemporal data. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] In recent years, the total amount of pre-hospital emergency care has continued to increase. Accurately predicting the demand for pre-hospital emergency care is one of the important aspects of pre-hospital emergency care management. Successfully predicting the distribution of critically ill patients in a certain area in the future is of great significance to improving the emergency care system. Pre-hospital emergency care has a strong timeliness. For example, for patients with out-of-hospital cardiac arrest, the survival rate of the patient will decrease for every 1 minute of delay. In this case, early intervention may lead to successful resuscitation. By accurately predicting the daily vehicle volume, rationally allocating pre-hospital emergency care resources, and transforming passive emergency care into active emergency care mode, the efficiency of emergency care and the survival rate of patients can be effectively improved.

[0004] However, although some researchers have proposed relevant prediction methods to promote emergency medical care, there is still no relevant research on the spatiotemporal prediction of community emergency needs. Previous research on pre-hospital emergency care only stayed at the analysis of time series data, discarding the location attributes of the information, causing the model to ignore the impact of community dependence on patient onset, which greatly limits the full play of the role of emergency data. Summary of the invention

[0005] In order to address the shortcomings of the prior art, the present invention provides a method and system for predicting pre-hospital emergency flow based on spatiotemporal data. The city is divided into irregular minimum spatial areas according to community attributes for data mapping, spatial features are extracted from the mapped spatiotemporal image data, and time evolution information is learned, thereby achieving accurate prediction of the emergency flow distribution in each minimum spatial area.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for predicting pre-hospital emergency flow based on spatiotemporal data.

[0007] A method for predicting pre-hospital emergency flow based on spatiotemporal data includes the following processes: Obtain historical emergency spatiotemporal data for each minimum spatial area; Extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; After embedding the spatiotemporal features in a linear layer, the emergency spatiotemporal data flow of a certain time period in the future corresponding to each minimum spatial area is obtained.

[0008] As a further limitation of the first aspect of the present invention, the division of the minimum spatial area includes: dividing the entire area into a plurality of irregular areas as the minimum spatial area according to community attributes.

[0009] As a further limitation of the first aspect of the present invention, the historical emergency spatiotemporal data of the entire region are analyzed for relationship to generate a distribution matrix from the region to the irregular grid, the city is divided into N grid cells, and the distribution matrix from each grid cell to the entire region is used Indicates that N is the number of divided regions and L is the feature dimension in each region.

[0010] As a further limitation of the first aspect of the present invention, the correlation between any minimum spatial region and other minimum spatial regions in the entire region is for: ; in, Is and The minimum number of spatial regions to index, It is i spatial variables, is the mean of all minimum spatial region attributes, represents the space matrix, It is j A spatial variable.

[0011] As a further limitation of the first aspect of the present invention, performing spatial feature extraction on the historical emergency spatiotemporal data includes: Hidden modules are stacked to extract spatial features. The hidden modules are composed of a stack of two-dimensional convolutional layers, group normalization layers, and activation function layers.

[0012] As a further limitation of the first aspect of the present invention, the output of the hidden module is , learn the time evolution in the spatial dimension according to the extracted spatial features, use the stacked inception module to learn the time evolution in the spatial dimension, and obtain the spatiotemporal features corresponding to the historical emergency spatiotemporal data : ; in, represents a 2D convolution with a kernel of 3, represents a 2D convolution with a kernel of 5, represents a 2D convolution with a kernel of 7, and S represents the number of stacking times.

[0013] In a second aspect, the present invention provides a pre-hospital emergency flow prediction system based on spatiotemporal data.

[0014] A pre-hospital emergency flow prediction system based on spatiotemporal data, comprising: The data acquisition unit is configured to: acquire historical emergency spatiotemporal data of each minimum spatial area; The spatiotemporal feature extraction unit is configured to: extract spatial features from the historical emergency spatiotemporal data, learn the time evolution in the spatial dimension according to the extracted spatial features, and obtain the spatiotemporal features corresponding to the historical emergency spatiotemporal data; The emergency traffic prediction unit is configured to: embed the spatiotemporal features in a linear layer to obtain the emergency spatiotemporal data traffic of a certain time period in the future corresponding to each minimum spatial area.

[0015] In a third aspect, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the pre-hospital emergency flow prediction based on spatiotemporal data as described in the first aspect of the present invention is implemented.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the pre-hospital emergency flow prediction based on spatiotemporal data as described in the first aspect of the present invention.

[0017] In a fifth aspect, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the pre-hospital emergency flow prediction based on spatiotemporal data as described in the first aspect of the present invention.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention innovatively provides a pre-hospital emergency flow prediction strategy based on spatiotemporal data. It divides the city into irregular minimum spatial areas according to community attributes for data mapping, extracts spatial features from the mapped spatiotemporal image data, and learns the time evolution information, thereby achieving accurate prediction of the emergency flow distribution in each minimum spatial area.

[0019] 2. The present invention innovatively proposes a model for predicting the demand for emergency treatment in urban areas, which can simulate the changes in urban emergency treatment in advance, so that relevant units can arrange emergency treatment resources in advance and transform the passive emergency treatment mode into active emergency treatment, thereby making more rational use of emergency treatment resources and improving emergency treatment efficiency.

[0020] 3. The present invention provides an end-to-end urban pre-hospital emergency distribution prediction method. By reading historical emergency data, the read data is used as a model input, and after combining it with a deep learning method for mining and analysis, the emergency demand situation in the urban area in the future period is output, which can more reasonably utilize emergency resources, improve emergency efficiency, and increase the survival rate of patients.

[0021] 4. The present invention proposes a minimum area division method that combines spatial attribute characteristics, performs spatial correlation analysis on pre-hospital emergency data, generates an allocation matrix from regions to irregular grids, divides the city into N grid units, and the division of community attributes has a higher semantic level and is easier to convey overall regional semantic messages that change over time.

[0022] 5. The present invention fully exploits the excellent representation ability of convolutional neural networks in image feature extraction, and uses stacked hidden modules to extract preliminary spatial features. Each hidden module is composed of a stack of convolutional layers, normalization layers, and activation layers. Spatial and channel attention calculations are implemented before the hidden modules to cope with the spatial clustering characteristics of emergency distribution. This module is lightweight and can achieve better prediction accuracy at a lower computing cost.

[0023] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0025] Figure 1 A schematic diagram of a flow chart of a method for predicting pre-hospital emergency flow based on spatiotemporal data provided in Example 1 of the present invention; Figure 2 A schematic diagram of the principle of a method for predicting pre-hospital emergency flow based on spatiotemporal data provided in Example 1 of the present invention; Figure 3 A probability distribution diagram provided in Example 1 of the present invention; wherein the horizontal axis represents the significance level, and the vertical axis represents the probability density, both of which are expressed in specific numerical values ​​without specific units; Figure 4 A scatter plot provided in Example 1 of the present invention; wherein the horizontal axis represents the standard value of the significance level, and the vertical axis represents the lag value of the significance level, both of which are expressed in specific numerical values ​​without specific units; Figure 5 A diagram of a hidden module provided in Embodiment 1 of the present invention; Figure 6 A schematic diagram of a pre-hospital emergency flow prediction system based on spatiotemporal data provided in Example 2 of the present invention; Figure 7 This is a schematic diagram of an electronic device provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0026] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0027] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0028] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0029] Embodiment 1: This implementation proposes a pre-hospital emergency flow prediction method based on spatiotemporal data, such as Figure 1 As shown, the following process is included: S1: Obtain historical emergency spatiotemporal data of each minimum spatial area; S2: extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; S3: After embedding the spatiotemporal features in a linear layer, the spatiotemporal data flow of emergency rescue in a certain time period in the future corresponding to each minimum spatial area is obtained.

[0030] In step S1 of this implementation, a spatial correlation analysis is performed on the existing pre-hospital emergency data to provide a theoretical basis for spatiotemporal data conversion, and the average correlation degree of the minimum spatial area with the surrounding areas in the entire region is constructed, and the correlation between any minimum spatial area and other minimum spatial areas in the entire region is constructed. for: (1); in, Is and The minimum number of spatial regions to index, It is i spatial variables, is the mean of all minimum spatial region attributes, represents the space matrix, It is j A spatial variable.

[0031] like Figure 2As shown, correlation analysis is performed on pre-hospital emergency data to obtain the minimum spatial area, the emergency flow is determined according to the block and the condition, and then the spatiotemporal data is determined, and the spatiotemporal data is analyzed and displayed; at the same time, feature extraction and prediction output are performed on time and space, and the prediction results are fed back and analyzed based on the spatiotemporal data and prediction output, and fed back to the feature extraction module, and the prediction results are predicted and displayed.

[0032] from Figure 3 and Figure 4 From the probability distribution diagram and scatter plot in , we can see that the value of the correlation index corresponding to the scatter plot is much larger than the expected value of the normal distribution, indicating that the distribution is not random, and the scatter plot shows a linear distribution trend, with the values ​​surrounding the red baseline, which proves the spatial dependence between the data.

[0033] Specifically, the division method of each minimum spatial area includes: the specific goal of the division is to generate an allocation matrix from the area to the irregular grid, dividing the city into The division of community attributes has a higher semantic level and is easier to convey the overall regional semantic information that changes over time. The grid-to-region allocation matrix can be used express, is the minimum number of spatial regions to be divided, is the feature dimension in each region.

[0034] More specifically, in this implementation, the minimum space is defined by relying on the street division method. A street belongs to a community and involves population, transportation, medical care, etc., so it has its own attributes. The number of emergency calls occurring within the geographical scope of a street is defined as the emergency flow rate in a minimum space. This division method has a higher semantic level than grid division, so it is easier to convey regional semantic information.

[0035] In step S2 of this implementation, in order to reduce the amount of model calculation and effectively capture global features, the present invention does not introduce additional techniques and complex strategies. Convolutional neural networks have excellent representation capabilities in image feature extraction. Therefore, the present invention proposes to adopt Figure 5 The hidden modules in the network are stacked to extract preliminary spatial features. Each hidden module is composed of a stack of two-dimensional convolution, group normalization, and activation functions. In the hidden module, only the two-dimensional convolution operation will change the shape of the feature map.

[0036] In step S2 of this implementation, learning the spatial relationship in the temporal evolution process is far more important than exploring complex semantic information. Therefore, the depth of the convolutional network is not required here. The Inception module uses convolution kernels of different sizes to enrich the information of each layer. Inspired by this, the spatiotemporal feature encoder uses stacked Inception modules to convolve in the spatial dimension. channel to learn the time evolution, } represents the output of the hidden module, and then the output of the stacked Inception module can be expressed as formula (2), Indicates time, represents the number of channels of the feature map before hidden module processing, and represents the height and width of the feature map before hidden module processing, Represents the number of channels of the feature map after processing by the hidden module, and Represents the height and width of the feature map after processing by the hidden module.

[0037] (2); in, represents a 2D convolution with a kernel of 3, represents a 2D convolution with a kernel of 5, represents a 2D convolution with a kernel of 7, S represents the number of stacking times, , Indicates the number of channels of the feature map processed by the Inception module, and Represents the height and width of the feature map processed by the Inception module.

[0038] In step S3 of this implementation, the feature map is then embedded through a linear layer to map it to , Represents the number of segmentations of irregular regions. The linear layer embedding here is implemented with a full connection, converting the feature dimension to the same as the number of minimum spaces; for example, if there are 100 minimum spaces, the number of features is converted to 100. The final network mapping output is It is the predicted number of emergency traffic in each minimum spatial area in a certain period of time in the future.

[0039] Embodiment 2: This implementation provides a pre-hospital emergency flow prediction system based on spatiotemporal data, such as Figure 6 As shown, including: The data acquisition unit is configured to: acquire the historical emergency spatiotemporal data of each minimum spatial area; the specific working method of this unit is the same as the process of step S1 provided in Example 1, and will not be repeated here; The spatiotemporal feature extraction unit is configured to: extract spatial features from the historical emergency spatiotemporal data, learn the time evolution in the spatial dimension according to the extracted spatial features, and obtain the spatiotemporal features corresponding to the historical emergency spatiotemporal data; the specific working method of this unit is the same as the process of step S2 provided in Example 1, and will not be repeated here; The emergency traffic prediction unit is configured to: embed the spatiotemporal features in a linear layer to obtain the emergency spatiotemporal data traffic of a certain time period in the future corresponding to each minimum spatial area; the specific working method of this unit is the same as the process of step S3 provided in Example 1, and will not be repeated here.

[0040] It is understandable that the above-mentioned modules can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the prediction can also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0041] According to another embodiment of the present application, the system described in this embodiment can be constructed and the prediction method of the embodiment of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0042] Embodiment 3: like Figure 7 As shown, this implementation provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0043] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0044] The processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0045] The processor 1001 is configured to execute the following process: Obtain the historical emergency spatiotemporal data of each minimum spatial area; the specific working method is the same as the process of step S1 provided in Example 1, and will not be repeated here; Extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; the specific working method is the same as the process of step S2 provided in Example 1, and will not be repeated here; After embedding the spatiotemporal features in a linear layer, the emergency spatiotemporal data flow of a certain time period in the future corresponding to each minimum spatial area is obtained; the specific working method is the same as the process of step S3 provided in Example 1, and will not be repeated here.

[0046] Embodiment 4: This implementation provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0047] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor, and these instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it may also be at least one computer-readable storage medium located away from the aforementioned processor.

[0048] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process: Obtain the historical emergency spatiotemporal data of each minimum spatial area; the specific working method is the same as the process of step S1 provided in Example 1, and will not be repeated here; Extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; the specific working method is the same as the process of step S2 provided in Example 1, and will not be repeated here; After embedding the spatiotemporal features in a linear layer, the emergency spatiotemporal data flow of a certain time period in the future corresponding to each minimum spatial area is obtained; the specific working method is the same as the process of step S3 provided in Example 1, and will not be repeated here.

[0049] Embodiment 5: The present implementation provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the following process: Obtain the historical emergency spatiotemporal data of each minimum spatial area; the specific working method is the same as the process of step S1 provided in Example 1, and will not be repeated here; Extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; the specific working method is the same as the process of step S2 provided in Example 1, and will not be repeated here; After embedding the spatiotemporal features in a linear layer, the emergency spatiotemporal data flow of a certain time period in the future corresponding to each minimum spatial area is obtained; the specific working method is the same as the process of step S3 provided in Example 1, and will not be repeated here.

[0050] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application 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. A person skilled in the art 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.

[0051] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, 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 the 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 through a computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server or a data center to another website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server, a data center, etc. that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting pre-hospital emergency flow based on spatiotemporal data, characterized in that: The process includes: Obtain historical emergency spatiotemporal data for each minimum spatial area; Extracting spatial features from the historical emergency spatiotemporal data, learning the time evolution in the spatial dimension according to the extracted spatial features, and obtaining the spatiotemporal features corresponding to the historical emergency spatiotemporal data; After embedding the spatiotemporal features in a linear layer, the emergency spatiotemporal data flow of a certain time period in the future corresponding to each minimum spatial area is obtained.

2. The pre-hospital emergency flow prediction method based on spatiotemporal data according to claim 1, characterized in that: The division of the minimum spatial area includes: dividing the entire area into a plurality of irregular areas as the minimum spatial area according to community attributes.

3. The pre-hospital emergency flow prediction method based on spatiotemporal data as claimed in claim 2, characterized in that: The historical emergency spatiotemporal data of the entire region are analyzed to generate a distribution matrix from the region to the irregular grid. The city is divided into N grid cells, and the distribution matrix from each grid cell to the entire region is used Indicates that N is the number of divided regions, and L is the feature dimension in each region.

4. The pre-hospital emergency flow prediction method based on spatiotemporal data as claimed in claim 3, characterized in that: The correlation between any minimum spatial region and other minimum spatial regions in the entire region for: ； in, Is and The minimum number of spatial regions to index, It is i spatial variables, is the mean of all minimum spatial region attributes, represents the space matrix, It is j A spatial variable.

5. The pre-hospital emergency flow prediction method based on spatiotemporal data according to any one of claims 1 to 3, characterized in that: Extracting spatial features from the historical emergency spatiotemporal data includes: Hidden modules are stacked to extract spatial features. The hidden modules are composed of a stack of two-dimensional convolutional layers, group normalization layers, and activation function layers.

6. The method for predicting pre-hospital emergency flow based on spatiotemporal data according to claim 5, characterized in that: The output of the hidden module is , learn the time evolution in the spatial dimension according to the extracted spatial features, use the stacked inception module to learn the time evolution in the spatial dimension, and obtain the spatiotemporal features F corresponding to the historical emergency spatiotemporal data: ； in, represents a 2D convolution with a kernel of 3, represents a 2D convolution with a kernel of 5, represents a 2D convolution with a kernel of 7, and S represents the number of stacking times.

7. A pre-hospital emergency flow prediction system based on spatiotemporal data, characterized in that: include: The data acquisition unit is configured to: acquire historical emergency spatiotemporal data of each minimum spatial area; The spatiotemporal feature extraction unit is configured to: extract spatial features from the historical emergency spatiotemporal data, learn the time evolution in the spatial dimension according to the extracted spatial features, and obtain the spatiotemporal features corresponding to the historical emergency spatiotemporal data; The emergency traffic prediction unit is configured to: embed the spatiotemporal features in a linear layer to obtain the emergency spatiotemporal data traffic of a certain time period in the future corresponding to each minimum spatial area.

8. A computer device, characterized in that: include: A processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the method for predicting pre-hospital emergency flow based on spatiotemporal data as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the pre-hospital emergency flow prediction method based on spatiotemporal data as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method for predicting pre-hospital emergency flow based on spatiotemporal data as claimed in any one of claims 1 to 6 is implemented.

Images