Fire truck travel time prediction method based on multidimensional expansion of small sample data driven by deep learning

Abstract

This application proposes a deep learning-driven fire truck travel time prediction method using multi-dimensional expansion of small sample data, relating to the field of emergency management technology. The method includes: combining fire station information and historical rescue travel time information to construct a fire rescue travel time data set; utilizing similar historical data between fire stations and social vehicle travel time information to expand the fire rescue travel time data set to obtain a training sample set; constructing a fire truck travel time prediction model based on multi-graph convolution, and training the model based on the training samples; and predicting fire truck travel time based on the trained fire truck travel time prediction model. By combining fire station and historical rescue information, and utilizing the fire truck historical data itself and social vehicle data to expand the training set, accurate prediction of fire truck travel time is achieved, avoiding errors caused by insufficient data, and improving prediction accuracy and emergency response efficiency.

Description

Technical Field

[0001] The present application relates to the fields of emergency management and traffic forecasting technology, and in particular to a fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning. Background Art

[0002] Fire trucks, as vehicles with right-of-way, are exempt from standard traffic regulations during emergency rescue operations and can reach the scene at the fastest speed. The travel time of fire trucks can be used as an indicator to evaluate emergency rescue capabilities and is also the basis for fire stations to dispatch vehicles for rescue operations, making it of great significance. Accurately predicting fire truck travel time is crucial for both the effectiveness and timeliness of emergency rescue efforts.

[0003] However, the travel time prediction of fire trucks has the following difficulties: (1) Although fire trucks have the right of way, they are still inevitably affected by special circumstances such as road congestion and intersection queues. The speed of fire trucks under complex traffic conditions is not the free flow speed, which makes it difficult to predict the travel time of fire trucks. (2) Existing mature vehicle travel time prediction, such as taxis, private cars, and buses, can support the travel time prediction of these ordinary social vehicles due to their extremely high sampling rate and large scale of historical sample data. However, the number of fire trucks dispatching is limited, with each fire station only dispatching 1-2 times a day, resulting in an extremely small scale of historical sample data, which makes it difficult to support the research of fire truck travel time prediction methods. Summary of the Invention

[0004] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, the first purpose of this application is to propose a fire truck travel time prediction method with multi-dimensional expansion of small sample data driven by deep learning.

[0006] The second object of this application is to provide a device.

[0007] The third objective of this application is to provide an electronic device.

[0008] The fourth object of this application is to provide a computer-readable storage medium.

[0009] A fifth object of this application is to provide a computer program product.

[0010] To achieve the above objectives, the first embodiment of the present application proposes a fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning, including:

[0011] Combining fire station information and historical rescue travel time information, a fire rescue travel time data set is constructed;

[0012] Filling the fire rescue travel time data set according to historical fire rescue data information, and expanding the fire rescue travel time data set by using similar historical data between fire stations and social vehicle travel time information to obtain a training sample set;

[0013] Constructing a fire truck travel time prediction model based on multi-graph convolution, and training the fire truck travel time prediction model according to the training samples;

[0014] The fire truck travel time is predicted based on the trained fire truck travel time prediction model.

[0015] Optionally, the fire station information and historical rescue travel time information are combined to construct a fire rescue travel time data set, including:

[0016] Defines the set of fire stations that can dispatch fire trucks within a specific city. for:

[0017]

[0018] Where, Indicates fire stations, and the subscripts are the numbers of the fire stations;

[0019] For each fire station , defined in a specific period of time The feature set for:

[0020]

[0021] in, From the fire station The travel time to rescue locations at different distances corresponds to the rescue distances: ;

[0022] According to the fire station During a specific period of time The feature set , the fire station In various periods of history ~ Different distance ranges within All the features of are expressed as follows matrix :

[0023]

[0024] Among them, the limit A time point between 0:00 and 1:00 on any natural day;

[0025] For all fire station collections , all time periods and all distance ranges travel time, establish a The tensor feature library is used as the fire rescue travel time data set.

[0026] Optionally, filling the fire rescue travel time data set according to historical fire rescue data information includes:

[0027] Obtain historical fire rescue data information , Refers to a recorded rescue incident;

[0028] According to the historical fire rescue data information , get each rescue event The latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time , Arrival time ;

[0029] According to the latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time , Arrival time , calculate each rescue event Travel time and travel distance , the expression is:

[0030]

[0031]

[0032] in, and The Euclidean distance and Manhattan distance are calculated based on the latitude and longitude of the departure point and the longitude and longitude of the rescue point respectively;

[0033] According to the dispatch time Time of day and distance traveled The corresponding distance range, travel time Fill in the tensor feature library.

[0034] Optionally, the process of expanding the fire rescue travel time data set by using similar historical data between fire stations includes:

[0035] For a given fire station and , according to their respective historical characteristic datasets and , calculate the similarity of historical data between the two fire stations;

[0036] The fire rescue travel time data set is expanded according to the similarity of historical data between the two fire stations.

[0037] Optionally, for a given fire station and , according to their respective historical characteristic datasets and , calculate the similarity of historical data between the two fire stations, including:

[0038] Historical feature dataset and Respectively reduced to and , that is, The data of 0 periods is reduced to 24 periods, and the formula for the travel time value of period 0 to 1 is as follows:

[0039]

[0040] That is, the travel time value in the period 0 to 1 is equal to the average value of the period 0:00 to 1:00 of each natural day in the historical period, and for The number of non-zero values ​​in the set, the remaining 23 periods The calculation method is similar to this, and so on, we get the fire station and Feature matrix after dimensionality reduction and ;

[0041] According to the feature matrix after dimensionality reduction and , calculate the similarity of historical data between two fire stations , the expression is:

[0042]

[0043] in, 、 and The calculation methods are as follows:

[0044]

[0045] in, is a matrix The average of all non-zero values ​​in , is a matrix The average of all non-zero values ​​in ;

[0046]

[0047] in, is a matrix The standard deviation of all non-zero values ​​in , is a matrix The standard deviation of all non-zero values ​​in ;

[0048]

[0049] in, is the Pearson correlation coefficient between two vectors, is a matrix Vector data flattened by rows and columns, is a matrix Vector data flattened by rows and columns.

[0050] Optionally, the expanding the fire rescue travel time data set according to the similarity of historical data between the two fire stations includes:

[0051] S1. Traverse the fire station set , take out any fire station and its characteristic matrix , marked as visited. If there is no unvisited fire station, go to step S4;

[0052] S2. If there are other fire stations With fire station The similarity satisfies , is the similarity threshold, go to step S3, otherwise go to step S1;

[0053] S3, Reservation and Fire Station The most similar fire station , and to the fire station The characteristic matrix To supplement, the expression is:

[0054]

[0055] S4. End of loop, output the characteristic matrix of all fire stations .

[0056] Optionally, the process of expanding the fire rescue travel time data set using social vehicle travel time information includes:

[0057] Collect GPS positioning points of all social vehicles in the same city ;

[0058] Meet at the GPS location Screening and Fire Station The set of all GPS positioning points belonging to the same administrative division ;

[0059] Meet at the GPS location , filter for a specific time period A collection of all GPS positioning points ;

[0060] According to GPS positioning point collection , calculate this period Fire station inside Travel time for different distance ranges , the expression is:

[0061]

[0062] in, Different distance ranges The median value of is a collection The average value of the instantaneous velocity of all the positioning points in;

[0063] If there is no fire truck historical data that meets the calculation requirements in the tensor feature library ,Will Fill in the corresponding position in the tensor feature library, where is the corresponding attenuation factor;

[0064] Repeat the above screening steps, calculation steps, and filling steps until all fire stations are gathered. , all time periods The elements in have been traversed.

[0065] Optionally, the constructing of a fire truck travel time prediction model based on multi-graph convolution includes:

[0066] The structure of the model is determined as follows: fire stations are used as graph nodes and the relationships between stations are used as edges to construct a graph structure model;

[0067] Confirm that the output of the model is: All fire stations During the forecast period At a specific rescue distance Travel time ,total nodes;

[0068] Confirm that the input to the model is:

[0069]

[0070] Among them, the for dimensional matrix, Including: front Time period , all fire stations At a specific rescue distance The travel time on dimensional matrix; and the forecast period Same front Natural day period , all fire stations At a specific rescue distance The travel time on dimensional matrix;

[0071] Confirm that the first graph convolution output of the model is:

[0072]

[0073] Among them, the Still dimensional matrix, yes dimensional matrix, representing the adjacency relationship between fire stations. and The spatial distance is less than or equal to the preset spatial distance , then in the adjacency matrix middle , otherwise it is 0; is the identity matrix, is the degree matrix, is the activation function, are all the parameters involved in the first layer of graph convolution;

[0074] Confirm that the second graph convolution output of the model is:

[0075]

[0076] Among them, the Still dimensional matrix, yes dimensional matrix, representing the correlation between fire stations, are all the parameters involved in the second layer of graph convolution, in the matrix Any position The values ​​are:

[0077]

[0078] in, is the Pearson correlation coefficient of the two vectors;

[0079] Determine the fully connected layer of the model, which is used to establish and The fully connected mapping is established.

[0080] Optionally, the training of the fire truck travel time prediction model according to the training samples includes:

[0081] Continuously calculate the training sample set, when entering the period After that, use immediately The fire truck travel time prediction model is trained by using the training sample set of all previous time periods until the model converges, and a trained fire truck travel time prediction model is obtained, wherein each distance range corresponds to a model, and a total of A trained fire truck travel time prediction model.

[0082] Optionally, the prediction of the fire truck travel time based on the trained fire truck travel time prediction model includes:

[0083] according to The trained fire truck travel time prediction models calculate the travel time data for the next period , get each fire station During the time period, reach different distance ranges The travel time, the prediction matrix of travel time is:

[0084]

[0085] When An actual demand point is generated during the time period, the distance between the fire station and the demand point is automatically calculated, and the corresponding travel time is selected from the travel time prediction matrix to realize the prediction of the travel time from the fire truck to the demand point.

[0086] To achieve the above objectives, the second embodiment of the present application proposes a fire truck travel time prediction device based on multi-dimensional expansion of small sample data driven by deep learning, comprising:

[0087] A travel time data set construction module is used to combine fire station information and historical rescue travel time information to construct a fire rescue travel time data set;

[0088] an expansion module, configured to fill the fire rescue travel time data set according to historical fire rescue data information, and to expand the fire rescue travel time data set by utilizing similar historical data between fire stations and social vehicle travel time information to obtain a training sample set;

[0089] A model building and training module, configured to build a fire truck travel time prediction model based on multi-graph convolution, and train the fire truck travel time prediction model according to the training samples;

[0090] The prediction module is used to predict the travel time of fire trucks based on the trained fire truck travel time prediction model.

[0091] To achieve the above-mentioned purpose, a third embodiment of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor;

[0092] The memory stores computer-executable instructions;

[0093] The processor executes the computer-executable instructions stored in the memory to implement the method as described in any one of the first aspects.

[0094] To achieve the above-mentioned purpose, the fourth embodiment of the present application proposes a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the method as described in any one of the first aspects.

[0095] To achieve the above-mentioned objectives, the fifth embodiment of the present application proposes a computer program product, which implements any one of the methods in the first aspect when executed by a processor.

[0096] The present application provides a deep learning-driven fire truck travel time prediction method, device, electronic device and storage medium for multi-dimensional expansion of small sample data. By combining fire station information and historical rescue travel time information, and using data from similar fire stations and social vehicle travel time information to expand historical fire rescue small samples, the fire rescue travel time data is enriched and diversified, and the travel time data of specific time periods, specific distances, and specific fire stations are expanded, so that the data set can meet the requirements of deep learning calculations, avoid the problem of poor model generalization ability caused by insufficient data volume, and improve the accuracy and reliability of the model; by constructing a fire truck travel time prediction model based on multi-graph convolution, two graph structures, an adjacency graph and a feature similarity measure, are designed in the model for the fire truck travel time features. The two graph structures are used to describe the connections between different fire stations, respectively. The spatial features of the fire truck travel time information are mined through multi-graph convolution, and the model is trained using the expanded training samples, thereby achieving accurate prediction of the fire truck travel time, avoiding the inaccuracy of traditional prediction methods under complex traffic conditions, and improving the efficiency and effectiveness of emergency response. Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0098] Figure 1 A flowchart of a fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning provided in an embodiment of the present application;

[0099] Figure 2 A schematic structural diagram of a fire truck travel time prediction device with multi-dimensional expansion of small sample data driven by deep learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0100] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0101] Predicting the travel time of a fire truck has the following difficulties:

[0102] (1) Although fire trucks have the right of way, they are inevitably affected in special circumstances such as road congestion and intersection queues. The speed of fire trucks in complex traffic conditions is not the free flow speed, which makes the travel time of fire trucks difficult to predict.

[0103] (2) Existing mature vehicle travel time prediction methods, such as taxis, private cars, and buses, can support travel time prediction for these common vehicles due to their extremely high sampling rates and large historical sample data. However, fire trucks are limited in the number of dispatches, with each fire station only responding 1-2 times a day. This results in an extremely small historical sample data size, making it difficult to support research on fire truck travel time prediction methods.

[0104] To address this issue, the present invention provides a fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning. Figure 1 This is a flow chart of a fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning provided in an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0105] Step 101: Combine fire station information and historical rescue travel time information to construct a fire rescue travel time data set.

[0106] This application is based on a deep learning model, so a complete training dataset needs to be established.

[0107] In this embodiment of the present application, within a specific city, a set of fire stations that can dispatch fire trucks is defined. for:

[0108]

[0109] Where, Indicates fire stations, and the subscripts are the numbers of the fire stations;

[0110] For each fire station , defined in a specific period of time The set of features (i.e. travel time for different distance ranges) for:

[0111]

[0112] in, Fire Station As the starting point, the time consumed to reach the rescue location at different distances, and the corresponding rescue distances are: .

[0113] It should be noted that A range value, for example, 100 meters to 500 meters.

[0114] In one possible embodiment, a specific period of time It will be from 8:00 to 9:00 on December 23, 2023.

[0115] Therefore, according to the above definition, according to the fire station During a specific period of time The feature set , the fire station In various periods of history ~ Different distance ranges within All the features of are expressed as follows matrix :

[0116]

[0117] Among them, the limit A time point between 0:00 and 1:00 on any natural day.

[0118] Then, for all fire stations , all time periods and all distance ranges travel time, can establish a The tensor feature library is used as the fire rescue travel time data set, which is the data basis of the deep learning model of this application.

[0119] Step 102, fill the fire rescue travel time data set according to historical fire rescue data information, and use similar historical data between fire stations and social vehicle travel time information to expand the fire rescue travel time data set to obtain a training sample set.

[0120] Furthermore, in an embodiment of the present application, the tensor feature library obtained in step 102 is filled with historical fire rescue data information.

[0121] In the embodiment of the present application, first obtain historical fire rescue data information , Refers to a recorded rescue incident; then based on historical fire rescue data information , get each rescue event The latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time (e.g. October 23, 2023, 12:10 PM), arrival time (such as 12:20 on October 23, 2023), and based on the latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time , Arrival time , calculate each rescue event Travel time and the duration of this journey Corresponding travel distance ; Finally, according to the time of police dispatch Time of day and distance traveled The corresponding distance range, travel time Fill in the tensor feature library constructed in step 101.

[0122] Each rescue incident Travel time and the duration of this journey Corresponding travel distance The calculation expression is:

[0123] The expression is:

[0124]

[0125]

[0126] Where, and The Euclidean distance and the Manhattan distance are calculated based on the longitude and latitude of the starting point and the longitude and latitude of the rescue point, respectively. The calculation formulas of these two distances have been widely disclosed and are conventional technical contents in this field. This application does not describe or limit them.

[0127] In one possible embodiment, historical fire rescue data information is obtained from the fire brigade .

[0128] However, due to the limited number of fire trucks dispatching, each fire station only responds once or twice a day, resulting in an extremely small historical sample data size. The tensor feature library cannot be effectively filled with historical dispatch data, so it needs to be expanded.

[0129] In an embodiment of the present application, the historical data of the fire truck itself and the GPS data of social vehicles (such as taxis, online ride-hailing vehicles, and private cars, and the data must include instantaneous speed data for each sampling) are further used to fill in the missing features in the tensor feature library, as explained below.

[0130] (1) Using the fire truck historical data to expand the small sample

[0131] In some embodiments of the present application, the process of using the fire truck historical data to expand the fire rescue travel time data set is based on the following principle: first, measure the similarity of historical data between different fire stations, and then use the data of fire stations with close similarity to fill in the gaps of fire stations that lack rescue data. Specifically, the following steps are included: for a given fire station, and , according to their respective historical characteristic datasets and , calculate the similarity of historical data between the two fire stations; and expand the fire rescue travel time data set based on the similarity of historical data between the two fire stations.

[0132] In the embodiment of the present application, for a given fire station and , according to their respective historical characteristic datasets and ,The steps to calculate the similarity of historical data between two fire stations are:

[0133] Historical feature dataset and Respectively reduced to and , that is, The data of 1 period is reduced to 24 periods. These 24 periods are 0:00~1:00, 1:00~2:00, 2:00~3:00,…, 22:00~23:00, 23:00~24:00. The formula for the travel time value of period 0~1 is as follows:

[0134]

[0135] That is, the travel time value in the period 0 to 1 is equal to the average value of the period 0:00 to 1:00 of each natural day in the historical period, and for The number of non-zero values ​​in the set, the remaining 23 periods The calculation method is similar to this, and by analogy, we can get the fire station and Feature matrix after dimensionality reduction and .

[0136] Then, according to the feature matrix after dimensionality reduction and , calculate the similarity of historical data between two fire stations , the expression is:

[0137]

[0138] in, 、 and The calculation methods are as follows:

[0139]

[0140] in, is a matrix The average of all non-zero values ​​in , is a matrix The average of all non-zero values ​​in ;

[0141]

[0142] in, is a matrix The standard deviation of all non-zero values ​​in , is a matrix The standard deviation of all non-zero values ​​in ;

[0143]

[0144] in, is the Pearson correlation coefficient between two vectors, is a matrix Vector data flattened by rows and columns, is a matrix Vector data flattened by rows and columns.

[0145] It should be noted that according to the above steps, the similarity between any two fire stations can be obtained , determine if , then the two fire stations are considered to be very similar ( is the similarity threshold, usually set to 0.8. The larger the value, the greater the similarity between the two). The data are shared and supplemented with each other in the following ways:

[0146] S1. Traverse the fire station set , take out any fire station and its characteristic matrix , marked as visited. If there is no unvisited fire station, go to step S4;

[0147] S2. If there are other fire stations With fire station The similarity satisfies , is the similarity threshold, go to step S3, otherwise go to step S1;

[0148] S3, Reservation and Fire Station The most similar fire station , and to the fire station The characteristic matrix To supplement, the expression is:

[0149]

[0150] S4. End of loop, output the characteristic matrix of all fire stations .

[0151] Finally, according to the characteristic matrix of all fire stations Expand the tensor database.

[0152] (2) Using social vehicle travel time information to expand small samples

[0153] 1) Collect GPS positioning points of all vehicles in the same city .

[0154] 2) Meet at the GPS location Screening and Fire Station The set of all GPS positioning points belonging to the same administrative division .

[0155] 3) Meet at the GPS location , filter for a specific time period A collection of all GPS positioning points .

[0156] 4) According to GPS positioning point collection , calculate this period Fire station inside Travel time for different distance ranges , the expression is:

[0157]

[0158] in, Different distance ranges The median value (e.g., for a range of 100 to 500 meters, the median value is 300 meters), is a collection The average instantaneous velocity of all the positioning points in .

[0159] 5) If there is no fire truck historical data that meets the calculation requirements in the tensor feature library ,Will Fill in the corresponding position in the tensor feature library. Among them, is the corresponding attenuation factor.

[0160] 6) Repeat steps 2)-5) above until all fire stations gather. , all time periods The elements in have been traversed.

[0161] Step 103: construct a fire truck travel time prediction model based on multi-graph convolution, and train the fire truck travel time prediction model based on training samples.

[0162] In the embodiment of the present application, a graph structure model is constructed with fire stations as graph nodes and the relationships between stations as edges, and feature mining is performed based on a graph convolutional neural network model to establish a mapping between historical travel time and future travel time.

[0163] Specifically, the output of the confirmation model is: all fire stations During the forecast period At a specific rescue distance Travel time ,total nodes.

[0164] Confirm that the input to the model is:

[0165]

[0166] in, for dimensional matrix, Including: front Time period , all fire stations At a specific rescue distance The travel time on dimensional matrix; and the forecast period Same front Natural day period , all fire stations At a specific rescue distance The travel time on dimensional matrix.

[0167] Confirm that the first graph convolution output of the model is:

[0168]

[0169] in, Still dimensional matrix, yes dimensional matrix, representing the adjacency relationship between fire stations. and The spatial distance is less than or equal to the preset spatial distance , then in the adjacency matrix middle , otherwise it is 0; is the identity matrix, is the degree matrix, is the activation function, are all the parameters involved in the first layer of graph convolution.

[0170] After the first graph convolution, the output is obtained , still dimensional matrix.

[0171] Confirm that the second graph convolution output of the model is:

[0172]

[0173] in, Still dimensional matrix, yes dimensional matrix, representing the correlation between fire stations, are all the parameters involved in the second layer of graph convolution, in the matrix Any position The values ​​are:

[0174]

[0175] in, is the Pearson correlation coefficient of the two vectors. The calculation formula of the correlation coefficient has been made public and is a conventional technical content in this field. This application does not describe or limit it.

[0176] After the second graph convolution, the output is obtained , still dimensional matrix.

[0177] Determine the fully connected layer of the model, which is used to establish and The fully connected mapping is established.

[0178] It should be noted that in order to respond to fire needs in a timely manner, model training should be carried out on a rolling basis during actual application.

[0179] In the embodiment of the present application, after the fire truck travel time prediction model is established, the training sample set in step 102 is continuously calculated, and a new round of training can be carried out when the time period is switched, such as when entering the time period After that, use immediately The fire truck travel time prediction model is trained with the training sample set of all previous time periods until the model converges, and the trained fire truck travel time prediction model is obtained, where each distance range corresponds to a model, and a total of A trained fire truck travel time prediction model.

[0180] Step 104 : Predicting the fire truck travel time based on the trained fire truck travel time prediction model.

[0181] In the embodiment of this application, according to The trained fire truck travel time prediction models calculate the travel time data for the next period , that is, to obtain the During the time period, reach different distance ranges The travel time prediction matrix is ​​as follows:

[0182]

[0183] When When actual demand points (such as fire points) are generated during a time period, the distance between the fire station and the demand point can be automatically calculated. Then, the travel time corresponding to the corresponding distance is selected from the travel time prediction matrix diagram as the prediction result, thereby realizing the prediction of the travel time from the fire truck to the demand point.

[0184] In order to implement the above embodiments, the present application also proposes a fire truck travel time prediction device with multi-dimensional expansion of small sample data driven by deep learning. Figure 2 This is a structural diagram of a fire truck travel time prediction device 10 based on multi-dimensional expansion of small sample data driven by deep learning provided in an embodiment of the present application. Figure 2 As shown, the device includes:

[0185] The travel time data set construction module 100 is used to construct a fire rescue travel time data set by combining fire station information and historical rescue travel time information;

[0186] An expansion module 200 is configured to fill the fire rescue travel time data set based on historical fire rescue data information, and to expand the fire rescue travel time data set using similar historical data between fire stations and social vehicle travel time information to obtain a training sample set;

[0187] A model building and training module 300 is used to build a fire truck travel time prediction model based on multi-graph convolution and train the fire truck travel time prediction model based on training samples;

[0188] The prediction module 400 is used to predict the travel time of a fire truck based on the trained fire truck travel time prediction model.

[0189] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0190] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0191] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0192] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0193] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0194] It is important to note that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold beyond these legitimate uses. Furthermore, such collection / sharing should be conducted only after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes the relevant user information before using the feature. Furthermore, any necessary steps must be taken to safeguard and secure access to such personal information and ensure that others with access to personal information comply with its privacy policy and procedures.

[0195] This application contemplates providing implementations that allow users to selectively block the use or access of personal information data. Specifically, this disclosure contemplates providing hardware and / or software to prevent or block access to such personal information data. Risks can be minimized by limiting data collection and deleting data once it is no longer needed. Furthermore, where applicable, such personal information can be de-identified to protect user privacy.

[0196] In the descriptions of the foregoing embodiments, the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and features of different embodiments or examples, unless they are mutually inconsistent.

[0197] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0198] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0199] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" is any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (not exhaustive) of computer-readable media include: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0200] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having logic gate circuits for implementing logical functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0201] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0202] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0203] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A fire truck travel time prediction method based on multi-dimensional expansion of small sample data driven by deep learning, characterized by: The following steps are involved: Combine fire station information and historical rescue travel time information to build a fire rescue travel time data set, including: defining the set of all fire stations that can dispatch fire trucks within a specific city for: , where Indicates a fire station, and the subscript is the number of each fire station; for each fire station , defined in a specific period of time The feature set for: ,in, From the fire station The travel time to rescue locations at different distances corresponds to the rescue distances: According to the fire station During a specific period of time The feature set , the fire station In various periods of history ~ Different distance ranges within All the features of are expressed as follows matrix : , where the limit It is a time point between 0:00 and 1:00 on any natural day; for all fire stations , all time periods and all distance ranges travel time, establish a The tensor feature library is used as the fire rescue travel time data set; Filling the fire rescue travel time data set according to historical fire rescue data information, and expanding the fire rescue travel time data set by using similar historical data between fire stations and social vehicle travel time information to obtain a training sample set; Constructing a fire truck travel time prediction model based on multi-graph convolution, and training the fire truck travel time prediction model according to the training samples; The fire truck travel time is predicted based on the trained fire truck travel time prediction model; The process of expanding the fire rescue travel time data set by using similar historical data between the fire stations includes: for a given fire station and , according to their respective historical characteristic datasets and , calculating the similarity of historical data between the two fire stations; expanding the fire rescue travel time data set according to the similarity of historical data between the two fire stations; The process of expanding the fire rescue travel time data set using the social vehicle travel time information includes: Collect GPS positioning points of all social vehicles in the same city ; Meet at the GPS location Screening and Fire Station The set of all GPS positioning points belonging to the same administrative division ; Meet at the GPS location , filter for a specific time period A collection of all GPS positioning points ; According to the GPS positioning point set , calculate this period Fire Station Travel time for different distance ranges , the expression is: ,in, Different distance ranges The median value of is a collection The average value of the instantaneous velocity of all the positioning points in; If there is no fire truck historical data that meets the calculation requirements in the tensor feature library ,Will Fill in the corresponding position in the tensor feature library, where is the corresponding attenuation factor; Repeat the above screening steps, calculation steps, and filling steps until all fire stations are gathered. , all time periods The elements in have been traversed.

2. The method according to claim 1, characterized in that The filling of the fire rescue travel time data set according to historical fire rescue data information includes: Obtain historical fire rescue data information , Refers to a recorded rescue incident; According to the historical fire rescue data information , get each rescue event The latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time , Arrival time ; According to the latitude and longitude of the starting point , latitude and longitude of the rescue point , Police dispatch time , Arrival time , calculate each rescue event Travel time and travel distance , the expression is: in, and The Euclidean distance and Manhattan distance are calculated based on the latitude and longitude of the departure point and the longitude and longitude of the rescue point respectively; According to the dispatch time Time of day and distance traveled The corresponding distance range, travel time Fill in the tensor feature library.

3. The method according to claim 2, characterized in that For a given fire station and , according to their respective historical characteristic datasets and , calculate the similarity of historical data between the two fire stations, including: Historical feature dataset and Respectively reduced to and , that is, The data of 0 periods is reduced to 24 periods, and the formula for the travel time value of period 0 to 1 is as follows: That is, the travel time value in the period 0 to 1 is equal to the average value of the period 0:00 to 1:00 of each natural day in the historical period, and for The number of non-zero values ​​in the set, the remaining 23 periods The calculation method is similar to this, and so on, we get the fire station and Feature matrix after dimensionality reduction and ; According to the feature matrix after dimensionality reduction and , calculate the similarity of historical data between two fire stations , the expression is: in, 、 and The calculation methods are as follows: in, is a matrix The average of all non-zero values ​​in , is a matrix The average of all non-zero values ​​in ; in, is a matrix The standard deviation of all non-zero values ​​in , is a matrix The standard deviation of all non-zero values ​​in ; in, is the Pearson correlation coefficient between two vectors, is a matrix Vector data flattened by rows and columns, is a matrix Vector data flattened by rows and columns.

4. The method according to claim 3, characterized in that The method of expanding the fire rescue travel time data set based on the similarity of historical data between the two fire stations includes: S1. Traverse the fire station set , take out any fire station and its characteristic matrix , marked as visited. If there is no unvisited fire station, go to step S4; S2. If there are other fire stations With fire station The similarity satisfies , is the similarity threshold, go to step S3, otherwise go to step S1; S3, Reservation and Fire Station The most similar fire station , and to the fire station The characteristic matrix To supplement, the expression is: S4. End of loop, output the characteristic matrix of all fire stations .

5. The method according to claim 1, characterized in that The method of constructing a fire truck travel time prediction model based on multi-graph convolution includes: The structure of the model is determined as follows: fire stations are used as graph nodes and the relationships between stations are used as edges to construct a graph structure model; Confirm that the output of the model is: All fire stations During the forecast period At a specific rescue distance Travel time ,total nodes; Confirm that the input to the model is: Among them, the for dimensional matrix, Including: front Time period , all fire stations At a specific rescue distance The travel time on dimensional matrix; and the forecast period Same front Natural day period , all fire stations At a specific rescue distance The travel time on dimensional matrix; Confirm that the first graph convolution output of the model is: Among them, the Still dimensional matrix, yes dimensional matrix, representing the adjacency relationship between fire stations. and The spatial distance is less than or equal to the preset spatial distance , then in the adjacency matrix middle , otherwise it is 0; is the identity matrix, is the degree matrix, is the activation function, are all the parameters involved in the first layer of graph convolution; Confirm that the second graph convolution output of the model is: Among them, the Still dimensional matrix, yes dimensional matrix, representing the correlation between fire stations, are all the parameters involved in the second layer of graph convolution, in the matrix Any position The values ​​are: in, is the Pearson correlation coefficient of the two vectors; Determine the fully connected layer of the model, which is used to establish and The fully connected mapping is established.

6. The method according to claim 5, characterized in that The training of the fire truck travel time prediction model according to the training samples includes: Continuously calculate the training sample set, when entering the period After, use immediately The fire truck travel time prediction model is trained by using the training sample set of all previous time periods until the model converges, and a trained fire truck travel time prediction model is obtained, wherein each distance range corresponds to a model, and a total of A trained fire truck travel time prediction model.

7. The method according to claim 6, characterized in that The method of predicting the fire truck travel time based on the trained fire truck travel time prediction model includes: according to The trained fire truck travel time prediction models calculate the travel time data for the next period respectively. , get each fire station During the time period, reach different distance ranges The travel time, the travel time prediction matrix is ​​as follows: When The actual demand point is generated during the time period, the distance between the fire station and the demand point is automatically calculated, and the corresponding travel time is selected from the travel time prediction matrix to realize the prediction of the travel time from the fire truck to the demand point.

Images