Method and device for predicting arrival of public transport vehicle and electronic equipment

Abstract

The invention discloses an arrival prediction method and device of a public transport vehicle and electronic equipment. The method is applied to a first user terminal, and comprises the following steps: in response to a current query instruction acting on an operation interface, obtaining current operation condition information of a target public transport vehicle corresponding to the current query instruction and a historical number of query instructions sent by at least one second terminal in a historical time period; based on the current query instruction, the historical number and the current operation condition information, a current query result of the target public transport vehicle is determined, and the current query result at least comprises the predicted arrival time when the target public transport vehicle arrives at a current query station corresponding to the current query instruction and the predicted riding congestion degree. According to the method and the device, the technical problems of relatively large operation workload, relatively high system deployment cost and relatively single prediction result of the system during arrival prediction of the public transport vehicle in related technologies are solved.

Description

Technical Field

[0001] The present invention relates to the field of public transportation data processing, and in particular to a method, device and electronic equipment for predicting the arrival of a public transportation vehicle. Background Art

[0002] At transportation hubs such as airports, users have travel or transfer needs for public transportation vehicles such as buses, subways, and airport shuttles. By predicting the arrival of public transportation vehicles, users can know the arrival time of the vehicle in advance, which is convenient for users to reasonably arrange travel time and reduce waiting time, thereby improving users' travel experience.

[0003] At present, the data processing process of public transportation vehicle arrival prediction in related technologies is usually executed on the server side. When users have query needs, they can directly obtain data calculation results from the server side. However, to ensure the real-time nature of user data, the server side needs to perform vehicle arrival prediction in real time, which easily causes a heavy computing burden on the server side, and the overall cost of deploying and upgrading the public transportation vehicle arrival prediction system is high; and the arrival prediction of public transportation vehicles in related technologies is mostly to predict the arrival time of the vehicle, and the diversity of prediction results is poor, making it difficult to provide satisfactory reference information for users' travel. In summary, when performing public transportation vehicle arrival prediction in related technologies, the system needs to perform a large amount of computing workload, the system deployment cost is high, and the prediction results are relatively simple.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method, device and electronic device for predicting the arrival of a public transportation vehicle, so as to at least solve the technical problems in the related art that when predicting the arrival of a public transportation vehicle, the system needs to perform a large amount of calculation workload, the system deployment cost is high and the prediction result is relatively single.

[0006] According to one aspect of an embodiment of the present application, a method for predicting the arrival of a public transportation vehicle is provided, which is applied to a first user terminal, and the method comprises: in response to a current query instruction acting on an operation interface, obtaining current operating status information of a target public transportation vehicle corresponding to the current query instruction, and a historical number of query instructions sent by at least one second terminal within a historical time period, wherein the current operating status information includes at least the current vehicle position, the current vehicle speed and the current number of passengers that can be taken by the vehicle, and the current number of passengers that can be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle; based on the current query instruction, the historical number and the current operating status information, determining a current query result for the target public transportation vehicle, wherein the current query result includes at least an estimated arrival time and an estimated degree of congestion of the target public transportation vehicle at a current query station corresponding to the current query instruction.

[0007] Optionally, based on the current query instruction, historical quantity and current operating status information, the current query result of the target public transportation vehicle is determined, including: determining the estimated arrival time based on the current query site, current vehicle position and current vehicle speed corresponding to the current query instruction; determining the estimated degree of congestion based on the historical quantity and the current number of passengers that the vehicle can take; determining the current query result based on the estimated arrival time and the estimated degree of congestion.

[0008] Optionally, after determining the current query result of the target public transportation vehicle based on the current query instruction, historical quantity and current operating status information, the method also includes: marking the current query instruction as a historical query instruction, and marking the current query result as a historical query result; constructing a historical query data pair based on the historical query instruction and the historical query result; uploading the historical query data pair to the cloud server to generate historical query information, wherein the historical query information uses the target data pair as index information, and the target data pair is composed of the historical instruction query time, historical instruction query station and historical query train number in the historical query instruction.

[0009] Optionally, based on the current query instruction, historical quantity and current operating status information, determining the current query result of the target public transportation vehicle includes: obtaining historical query information, wherein the historical query information is used to represent query information corresponding to the query instruction sent by at least one second terminal within a historical time period; based on the historical query information, the current query instruction, historical quantity and current operating status information, determining the current query result.

[0010] Optionally, based on historical query information, current query instructions, historical quantities and current operating status information, the current query result is determined, including: matching the current query instruction with the index information of the historical query information to obtain a matching result, wherein the matching result is used to characterize the degree of similarity between the current query instruction and the index information; determining a first weight parameter of the historical query results in the historical query information and a second weight parameter of the current operating status information based on the matching result; determining the current query result based on the current query instruction, historical quantities, historical query results, the first weight parameter, the current operating status information and the second weight parameter.

[0011] Optionally, the current query instruction is matched with the index information of the historical query information to obtain a matching result, including: obtaining the current instruction query time, current instruction query site and current query train number of the current query instruction; matching the current instruction query time, current instruction query site and current query train number with the historical instruction query time, historical instruction query site and historical query train number in the index information to obtain a matching result.

[0012] According to another aspect of an embodiment of the present invention, there is also provided an arrival prediction device for a public transportation vehicle, which is applied to a first user terminal, and the device comprises: an acquisition module, which is used to respond to a current query instruction acting on an operation interface, obtain current operating status information of a target public transportation vehicle corresponding to the current query instruction, and a historical number of query instructions sent by at least one second terminal within a historical time period, wherein the current operating status information at least includes the current vehicle position, current vehicle speed and the current number of passengers that can be taken by the vehicle, and the current number of passengers that can be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle; a determination module, which is used to determine a current query result of the target public transportation vehicle based on the current query instruction, the historical number and the current operating status information, wherein the current query result at least includes an estimated arrival time and an estimated degree of congestion of the target public transportation vehicle at a current query station corresponding to the current query instruction.

[0013] According to another aspect of an embodiment of the present invention, there is further provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the method in each embodiment of the present invention is executed when the program is running.

[0014] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0015] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0016] According to another aspect of an embodiment of the present invention, a computer program product is provided, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0017] According to another aspect of the embodiments of the present invention, a computer program is further provided. When the computer program is executed by a processor, the methods in the embodiments of the present invention are implemented.

[0018] In an embodiment of the present invention, a method for predicting the arrival of a public transportation vehicle is provided, which is applied to a first user terminal. The specific process includes: first, responding to the current query instruction of the operation interface, obtaining the current operating status information of the target public transportation vehicle corresponding to the current query instruction, and the historical number of query instructions sent by at least one second terminal within a historical time period. The current operating status information includes the current vehicle position, current vehicle speed and the current number of passengers that can be taken by the vehicle of the target public transportation vehicle. Then, based on the current query instruction, the historical number and the current operating status information, the current query result of the target public transportation vehicle is determined. The current query result includes at least the estimated arrival time and the estimated degree of congestion of the target public transportation vehicle at the current query station corresponding to the current query instruction. It is easy to notice that in the technical solution proposed in this application, the data processing process is performed on the first user terminal during the public transportation vehicle arrival prediction process. By performing data processing on the user terminal device, the burden on the server can be reduced, and the deployment and maintenance costs of the public transportation vehicle arrival prediction system can be effectively reduced. Moreover, the calculation is performed only in response to the user's query needs, and there is no need for the server to perform real-time prediction to obtain the prediction results. The user can view the expected arrival time and the degree of congestion of the target vehicle. The rich and diverse current query results facilitate the user to make corresponding travel choices, and facilitate the user to adjust the travel mode in advance, thereby improving the user's travel experience. This solves the technical problems in the related technology that when predicting the arrival of public transportation vehicles, the system needs to perform a large amount of calculation workload, the system deployment cost is high, and the prediction results are relatively single. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0020] Figure 1is a flow chart of a method for predicting the arrival of a public transportation vehicle according to an embodiment of the present invention;

[0021] Figure 2 is a schematic diagram of an optional current state judgment of a vehicle according to an embodiment of the present invention;

[0022] Figure 3 2 is a schematic diagram of a public transportation vehicle arrival prediction device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0024] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention 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 interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] According to an embodiment of the present invention, an embodiment of a method for predicting the arrival of a public transportation vehicle is provided. It can be explained that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a flow chart of a method for predicting the arrival of a public transportation vehicle according to an embodiment of the present invention, the method being applied to a first user terminal, such as Figure 1 As shown, the method comprises the following steps:

[0027] Step S102, in response to the current query instruction acting on the operation interface, obtain the current operation status information of the target public transportation vehicle corresponding to the current query instruction, and the historical number of query instructions sent by at least one second terminal within the historical time period.

[0028] The current operation status information includes at least the current vehicle position, current vehicle speed and the number of passengers that can currently be taken by the target public transportation vehicle. The number of passengers that can currently be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle.

[0029] The above-mentioned first user terminal may refer to a terminal device used by a user to query the arrival of a public transportation vehicle, which may be a user's smart phone, tablet, portable computer, smart watch, etc. The first user terminal may be determined according to actual needs and is not limited here.

[0030] The above-mentioned current query instruction may refer to an instruction issued by a user to query the arrival of a public transportation vehicle. The current query instruction may include the user's diverse and optional query requirements, and may include the user's expected arrival time, expected congestion level and other demand information for public transportation vehicles. The specific query requirements that the current query instruction may include may be determined based on actual conditions and are not limited here.

[0031] The above-mentioned target public transportation vehicle may refer to the public transportation vehicle corresponding to the current query instruction. The public transportation vehicle may include but is not limited to buses, long-distance and short-distance buses, subways, trams, airport shuttles, etc., which can be determined according to actual conditions and are not limited here.

[0032] The above-mentioned current operating status information may refer to information related to the current operating status of the target public transportation vehicle, which may include but is not limited to the current vehicle position of the target public transportation vehicle, the current vehicle speed, the current number of passengers that the vehicle can take, whether the vehicle is currently operating normally, the degree of road congestion around the vehicle, etc. The current operating status information can be determined based on actual conditions and is not limited here.

[0033] The above-mentioned historical time period may refer to a preset time period before the current moment, for example, 5 minutes before the current moment, 10 minutes before the current moment, etc. The historical time period may be determined according to actual conditions and is not limited here.

[0034] The above-mentioned historical quantity can represent the number of query instructions initiated by other users to query the target public transportation vehicle within the preset time period before the current moment, that is, within the historical time period. The historical quantity can represent the number of ride demands of other users for the target public transportation vehicle within the preset time period before the current moment.

[0035] The second terminal mentioned above may refer to a terminal device used by other users to query the arrival of a target public transportation vehicle. The second terminal may be determined according to actual conditions and is not limited here.

[0036] In an optional embodiment, the first user terminal can obtain the current operation status information of the target public transportation vehicle in response to the current query instruction, as well as the historical number of query instructions sent by the second terminal in the historical time period, so as to achieve more accurate prediction and help users plan their riding behavior in advance. Specifically, in response to the user inputting the current query instruction on the terminal device, such as the destination and other information. The first user terminal can parse the current query instruction, and can determine the user's current query site based on the current user location information in the current query instruction. The user's current query site can also be manually input by the user. In combination with the destination input by the user, the target public transportation vehicle can be determined, which can be one or more vehicles that are about to arrive at the current query site; the user can also directly enter the line number of the target public transportation vehicle. For example, the user enters the query for bus route 8, so that the line number of the target public transportation vehicle included in the current query instruction can directly determine the corresponding target public transportation vehicle. Then, the current operation status information of the target public transportation vehicle can be determined, and the current operation status information of the target public transportation vehicle can be queried according to the instruction content, which can include information such as the current vehicle position, the current vehicle speed, and the number of people currently available for the vehicle. This information can be obtained through devices such as vehicle-mounted positioning systems and vehicle-mounted sensors, and updated to the cloud server in real time. At the same time, the cloud server will also count the number of query instructions sent by the second terminal within the historical time period. These historical data can be used to analyze information such as passenger demand of public transportation vehicles, so as to more accurately predict arrival time and congestion level, so as to help users reasonably arrange travel time and choose riding strategies. Users can obtain current operating status information and historical quantities in real time, respond to the current query instruction acting on the operation interface, obtain the current operating status information of the target public transportation vehicle corresponding to the current query instruction, and count the historical quantity, which can bring more accurate, intelligent and diversified public transportation arrival prediction services, improve user experience and traffic management efficiency.

[0037] Step S104, determining the current query result of the target public transportation vehicle based on the current query instruction, the historical quantity and the current operation status information.

[0038] The current query result at least includes the estimated arrival time of the target public transportation vehicle at the current query station corresponding to the current query instruction and the estimated riding congestion level.

[0039] The above-mentioned predicted degree of crowdedness can display different degrees of crowdedness for users, for example, it may include sparse, suitable, relatively crowded and very crowded, and may also include information such as seats available and no seats available, so as to display riding experience information to users in advance, which is especially friendly to people such as the elderly who carry a lot of luggage and need seats to travel.

[0040] The above-mentioned current query results may correspond to the information required by the user in the current query instruction, and may also include default information not mentioned in the current query instruction. The current query results may include but are not limited to estimated arrival time, estimated congestion level, estimated time for the vehicle to arrive at the user's destination, temperature inside the vehicle and other information. The current query results can be determined based on actual needs and are not limited here.

[0041] In an optional embodiment, the technical solution proposed in the present application is executed on the first user terminal during the public transportation vehicle arrival prediction process. By executing data processing on the user terminal device, the burden on the server can be reduced, and the deployment and maintenance costs of the public transportation vehicle arrival prediction system can be effectively reduced. In addition, the calculation is performed only in response to the user's query needs, and there is no need for the server to perform real-time prediction to obtain the prediction results. Specifically, in response to the user inputting a query instruction on the terminal device, the terminal device is connected to the real-time information system of the public transportation vehicle through the network to obtain the historical quantity and current operating status information, including the real-time location, speed, traffic conditions, etc. of the vehicle. The terminal device determines the current query result of the target public transportation vehicle based on the query instruction and the acquired historical quantity and current operating status information. The current query result may include information such as the estimated arrival time and the estimated degree of congestion of the target public transportation vehicle at the current query station. The current query result can be displayed on the user terminal device, and the user can view the estimated arrival time and degree of congestion of the target vehicle. The rich and diverse current query results provide users with richer vehicle arrival query information results, so that users can make corresponding travel choices, adjust their travel methods in advance, and improve their travel experience.

[0042] In an embodiment of the present invention, a method for predicting the arrival of a public transportation vehicle is provided, which is applied to a first user terminal. The specific process includes: first, responding to the current query instruction of the operation interface, obtaining the current operating status information of the target public transportation vehicle corresponding to the current query instruction, and the historical number of query instructions sent by at least one second terminal within a historical time period. The current operating status information includes the current vehicle position, current vehicle speed and the current number of passengers that can be taken by the vehicle of the target public transportation vehicle. Then, based on the current query instruction, the historical number and the current operating status information, the current query result of the target public transportation vehicle is determined. The current query result includes at least the estimated arrival time and the estimated degree of congestion of the target public transportation vehicle at the current query station corresponding to the current query instruction. It is easy to notice that in the technical solution proposed in this application, the data processing process is performed on the first user terminal during the public transportation vehicle arrival prediction process. By performing data processing on the user terminal device, the burden on the server can be reduced, and the deployment and maintenance costs of the public transportation vehicle arrival prediction system can be effectively reduced. Moreover, the calculation is performed only in response to the user's query needs, and there is no need for the server to perform real-time prediction to obtain the prediction results. The user can view the expected arrival time and the degree of congestion of the target vehicle. The rich and diverse current query results facilitate the user to make corresponding travel choices, and facilitate the user to adjust the travel mode in advance, thereby improving the user's travel experience. This solves the technical problems in the related technology that when predicting the arrival of public transportation vehicles, the system needs to perform a large amount of calculation workload, the system deployment cost is high, and the prediction results are relatively single.

[0043] Optionally, based on the current query instruction, historical quantity and current operating status information, the current query result of the target public transportation vehicle is determined, including: determining the estimated arrival time based on the current query site, current vehicle position and current vehicle speed corresponding to the current query instruction; determining the estimated degree of congestion based on the historical quantity and the current number of passengers that the vehicle can take; determining the current query result based on the estimated arrival time and the estimated degree of congestion.

[0044] In an optional embodiment, in the process of predicting the arrival of a public transportation vehicle, by combining the current query instruction, the historical number and the current operating status information, a more accurate and real-time prediction result can be provided to the user. Specifically, the estimated arrival time can be determined based on the current query site, the current vehicle position and the current vehicle speed corresponding to the current query instruction. First, the query site where the user is located can be determined according to the query instruction input by the user. Then, the position and speed information of the current vehicle are obtained through the vehicle real-time positioning system, and the estimated arrival time of the vehicle at the site is calculated in combination with the real-time running route and traffic conditions of the vehicle, so as to provide the user with an accurate arrival time and help the user to better plan the travel. And the estimated riding congestion degree can be determined based on the historical number and the current number of passengers available in the vehicle. By recording the number of inquiries made by other users on the target public transportation vehicle in the historical time period, the riding demand of other users on the target public transportation vehicle in the preset time period before the current moment can be understood. Combined with the number of passengers available in the current vehicle, the current congestion degree of the vehicle can be predicted. In this way, the user can understand the congestion of the vehicle in advance and choose a suitable travel mode. Finally, the current query result can be determined based on the estimated arrival time and the expected degree of congestion, that is, the current query result can be determined by combining the estimated arrival time and the expected degree of congestion. Users can see the estimated arrival time and the degree of congestion of the vehicle in the query results, providing users with comprehensive travel information. Through the above process, users can be provided with more accurate and real-time public transportation vehicle arrival prediction results to help users better plan their travel. At the same time, through the analysis of historical quantities and the current number of people that can be taken by the vehicle, the congestion of the vehicle can be predicted in advance, helping users avoid peak hours, reducing waiting time and congestion, improving user experience, enhancing the intelligence level of the public transportation system, and providing strong support for urban traffic management and planning.

[0045] Optionally, after determining the current query result of the target public transportation vehicle based on the current query instruction, historical quantity and current operating status information, the method also includes: marking the current query instruction as a historical query instruction, and marking the current query result as a historical query result; constructing a historical query data pair based on the historical query instruction and the historical query result; uploading the historical query data pair to the cloud server to generate historical query information, wherein the historical query information uses the target data pair as index information, and the target data pair is composed of the historical instruction query time, historical instruction query station and historical query train number in the historical query instruction.

[0046] In an optional embodiment, after determining the current query result of the target public transportation vehicle, the current query instruction can be marked as a historical query instruction, and the current query result can be marked as a historical query result, and a historical query data pair can be constructed and uploaded to the cloud server to generate historical query information, which can provide convenience for subsequent queries, so that other users who conduct subsequent queries can use the historical query information as an intermediate result, so that there is no need to recalculate various parameters, and the amount of data processed when predicting data processing is reduced. Specifically, after determining the current query result, the current query instruction can be marked as a historical query instruction, and the current query result can be marked as a historical query result. Based on the historical query instruction and the historical query result, a historical query data pair can be constructed, such as the corresponding relationship between the query time, query station and query train number in the historical query instruction and the query result. The historical query data pair can also be uploaded to the cloud server to generate historical query information, with the target data pair as index information, which is convenient for subsequent queries. Through the above process, other users who conduct subsequent queries can use the historical query information as an intermediate result, without recalculating various parameters, reducing the amount of data processed when predicting data processing, thereby improving the query response speed. Historical query information can be used as a reference to help the system more accurately predict the arrival time, congestion level and other information of public transportation vehicles, improve prediction accuracy, reduce the prediction calculation burden of user terminal devices, optimize system performance, and improve user experience. This can in turn improve the efficiency and accuracy of the public transportation vehicle arrival prediction system and provide users with a better travel service experience.

[0047] Optionally, based on the current query instruction, historical quantity and current operating status information, determining the current query result of the target public transportation vehicle includes: obtaining historical query information, wherein the historical query information is used to represent query information corresponding to the query instruction sent by at least one second terminal within a historical time period; based on the historical query information, the current query instruction, historical quantity and current operating status information, determining the current query result.

[0048] In an optional embodiment, the first user terminal can obtain historical query information from the cloud server, that is, query information corresponding to the query instruction sent by at least one second terminal in the historical time period. The historical query information may include relevant data such as query time, target vehicle, estimated arrival time, and riding congestion. When the user enters a query instruction on the terminal device, the first user terminal can parse the current query instruction, determine the current query result based on the historical query information, the current query instruction, the historical quantity, and the current operating status information, and determine the current query result of the target vehicle according to the data related to the current query instruction in the historical query information, combined with the current query instruction, the historical quantity, and the current operating status information. Specifically, the data related to the target public transportation vehicle and the query time of the current query instruction can be screened out in the historical query information. Comprehensively consider the data such as the estimated arrival time and riding congestion in the historical query information, combined with the current operating status information, and perform data analysis and calculation. According to the relevant data in the historical query information and the current operating status information, the current query result of the target public transportation vehicle is determined, including the predicted data such as the estimated arrival time and riding congestion. Through the above steps, historical query information can be used as an intermediate result, and there is no need to recalculate various parameters, thereby reducing the amount of data required for processing the prediction data. By using historical query information as an intermediate result, the system can determine the current query result of the target vehicle more quickly, improving the query efficiency. The first user terminal of the user who conducts subsequent inquiries does not need to repeatedly calculate the historical data, which can reduce the calculation burden of the system and the amount of data required for processing. The current query result of the target public transportation vehicle is determined based on the current query instruction, historical quantity and current operating status information. By using historical query information as an intermediate result, it can bring better technical effects and improve the query efficiency and user experience of the system.

[0049] Optionally, based on historical query information, current query instructions, historical quantities and current operating status information, the current query result is determined, including: matching the current query instruction with the index information of the historical query information to obtain a matching result, wherein the matching result is used to characterize the degree of similarity between the current query instruction and the index information; determining a first weight parameter of the historical query results in the historical query information and a second weight parameter of the current operating status information based on the matching result; determining the current query result based on the current query instruction, historical quantities, historical query results, the first weight parameter, the current operating status information and the second weight parameter.

[0050] In an optional embodiment, the present application can provide diversified prediction information through a user terminal device, including an estimated arrival time, an estimated degree of crowdedness, etc. Specifically, the current query instruction and the index information of the historical query information can be matched to obtain a matching result. This can be achieved by calculating the similarity between the two, for example, using a text similarity algorithm or a method based on a vector space model. The matching result can be used to characterize the similarity matching degree between the current query instruction and the index information. Then, the first weight parameter of the historical query result in the historical query information and the second weight parameter of the current operating status information can be determined based on the matching result. The weight parameter can be determined according to the size of the matching result. For example, the higher the matching result, the larger the weight parameter of the historical query result can be, and the smaller the weight parameter of the current operating status information can be, that is, the historical query result has a strong reference to the current query result. At this time, there is no need to perform too much calculation on the current operating status information to obtain a more accurate current query result, which can effectively save the computing resources of the first user terminal; the lower the matching result, the lower the weight parameter of the historical query result can be, and the larger the weight parameter of the current operating status information can be, that is, the historical query result has a weaker reference to the current query result, and it is necessary to rely more on the current operating status information to ensure the accuracy of the prediction. Finally, the current query result can be determined based on the current query instruction, the historical quantity, the historical query result, the first weight parameter, the current operating status information and the second weight parameter. The historical query result can be multiplied by the first weight parameter, and the current operating status information can be multiplied by the second weight parameter, that is, the weighted sum operation. This process can be implemented by a machine learning algorithm or a rule engine. Through the above steps, the current query result can be determined based on the historical query information, the current query instruction and the current operating status information. The historical query information can be used as an intermediate result without recalculating each parameter, thereby reducing the amount of data processed during the prediction data processing. This can improve the accuracy and efficiency of the prediction, and provide faster services for other users who perform subsequent queries. When there are many users who perform vehicle arrival inquiries, the historical query results have a strong reference to the current query results, so as to realize the sharing of the query results of each user, which can effectively save the computing resources of the first user terminal.

[0051] Optionally, the current query instruction is matched with the index information of the historical query information to obtain a matching result, including: obtaining the current instruction query time, current instruction query site and current query train number of the current query instruction; matching the current instruction query time, current instruction query site and current query train number with the historical instruction query time, historical instruction query site and historical query train number in the index information to obtain a matching result.

[0052] In an optional embodiment, the user terminal device can obtain the estimated arrival time, estimated riding congestion and other information of the current public transport through the query instruction, and can match the index information of the current query instruction and the historical query information to obtain the matching result. Specifically, the current instruction query time, the current instruction query site and the current query train number of the current query instruction can be obtained. The historical instruction query time, the historical instruction query site and the historical query train number are obtained from the historical query information. The parameters of the current query instruction and the historical query information are matched to obtain the matching result. For example, when the current query train number is the same as the historical query train number, the current instruction query site is the same as the historical instruction query site, and the current instruction query time and the historical instruction query time are similar, the matching result can be higher, and the matching can adopt a certain algorithm, such as cosine similarity or Euclidean distance. According to the matching result, the reference of the historical query information to the current query result is determined, that is, the degree of influence of the historical query information on the current query result. In the above process, by matching the current query instruction and the historical query information, a more accurate prediction result can be obtained. The historical query information can be used as a reference to help improve the prediction accuracy of the current query. Using historical query information as an intermediate result can reduce the recalculation of various parameters. This can reduce the amount of data to be processed when predicting data and improve computing efficiency. By matching the current query instruction with historical query information, the prediction accuracy can be improved, the computing cost can be reduced, and the user experience can be improved. Such a setting can effectively utilize historical query information and provide better services to users.

[0053] The technical solution proposed in this application is described below in combination with an optional embodiment. This application proposes a simple method for predicting the arrival of public transportation vehicles. Accurate prediction of the arrival status of public transportation vehicles can improve passengers' travel experience, increase travel certainty, and encourage more passengers to choose public transportation for green travel. After obtaining accurate public transportation vehicle arrival status, passengers can better plan their trips and improve travel efficiency. This application predicts the real-time arrival status of public transportation vehicles based on fractal theory, historical travel data and real-time location information of public transportation vehicles.

[0054] The present application proposes a fractal-based real-time prediction method for public transport vehicle arrivals, and provides a low-cost, multi-mode, and easy-to-deploy real-time prediction system for public transport vehicle arrivals, which can at least be used to solve the real-time prediction problem of public transport vehicle arrivals for small and medium-sized public transport enterprises and public transport vehicles on scheduled routes in remote areas, and meet users' demand for real-time prediction services for scheduled vehicle arrivals. This method can be implemented based on a mobile phone application or an on-board edge computing device. The fractal-based real-time prediction method for public transport vehicle arrivals collects real-time vehicle operation status data, such as location, route, vehicle, time, and other information, and combines the historical driving status data of public transport vehicles for calculation to make real-time predictions of the vehicle's arrival at the next station. Since the fractal algorithm uses a step-by-step matrix calculation method, when the position of the vehicle changes during driving, it only needs to calculate the difference between the current time and position data and the time and position data at the last calculation to update the time when the vehicle arrives at the next station, without the need to recalculate all parameters. Compared with traditional vehicle arrival time prediction algorithms based on overall modeling such as traffic flow simulation, fluid mechanics, and cellular automata, the fractal-based real-time prediction method for public transport vehicle arrival time has the advantages of fast update speed, high update frequency, and low demand for computing power. It is easy to deploy at low cost in small and medium-sized public transport enterprises and remote areas.

[0055] The real-time prediction method for public transport vehicle arrival based on fractals mainly includes three modules: vehicle operation data collection, historical data processing, and real-time prediction. Among them, the vehicle operation data collection module can collect basic data such as the real-time location, route, station, vehicle, time information, and historical vehicle driving data of the operating vehicle. In the entire algorithm process, the correct collection of vehicle operation data can ensure the accuracy of the prediction results. When collecting line station data used to segment vehicle operation trip data, the data can be verified during the data collection process to eliminate the following errors: the station data does not match the line data to which it belongs; the station data does not match the line direction data; the station longitude and latitude are wrong, that is, it exceeds the city threshold; the station longitude and latitude deviation, that is, it deviates from the actual trajectory of the vehicle; the station sequence is wrong; the station sequence and longitude and latitude are wrong at the same time.

[0056] Due to the large number of stations, in the process of troubleshooting, the information of each station can be independently verified to find out the errors. After the above data errors are eliminated, the accuracy of the "vehicle-line-direction" correspondence can be guaranteed, and vehicles with data can be screened out. After that, for vehicles with data, their operating status is judged. Since according to the rules, the driver can reset the line number (ID) after the vehicle arrives at the terminal, it can be judged whether the line has been completed by whether the line number is reset. On this basis, it can be judged whether the vehicle is in operation based on whether the line number has changed and the values ​​before and after the change.

[0057] Figure 2 is a schematic diagram of an optional vehicle current state judgment according to an embodiment of the present invention, wherein the vehicle has data, vehicle operation and vehicle operation including the relationship as shown in FIG. Figure 2 As shown, vehicle data includes vehicle operation, and vehicle operation further includes vehicle operation.

[0058] The historical data processing module can model the historical driving data of the vehicle and establish a historical location-historical arrival time relationship model of the vehicle. The historical data processing process can include the preprocessing of the basic information of the historical data, based on the historical operation travel trajectory data and line station data, obtaining the historical time of arrival at each station during the vehicle operation process; establishing the historical location-historical arrival time relationship model of the vehicle, associating the historical operation travel trajectory data with the real-time operation travel data, analyzing the arrival time of each station, and establishing the historical location-arrival station schedule of the vehicle.

[0059] The real-time prediction module can use real-time travel data, which can include vehicle tags, time, location, line number, etc., to calculate fixed split point line intersections and station split points, and then predict the vehicle arrival time according to the average running speed, running speed time consistency, and running speed frequency function consistency. The real-time prediction process may include line station data adjustment, pre-processing of running data, real-time prediction using station line data, historical running travel trajectory data, real-time running travel data, predicting the arrival time of each station, and publishing the arrival time of each station.

[0060] The implementation process of the fractal-based real-time prediction of public transportation vehicle arrival time proposed in this application can mainly include steps such as vehicle operation data collection, historical data processing, and real-time prediction. Among them, vehicle operation data collection can collect basic data such as the real-time position, route, station, vehicle, time information and historical vehicle driving data of the operating vehicle. The basic data of the prediction program can include: historical operation travel trajectory data, which can include vehicle label, vehicle location, data time, vehicle route label; route site data can include route label, site location, site order within the route, site name, site label; real-time operation travel trajectory data can include vehicle label, vehicle location, data time, vehicle route label.

[0061] The historical data processing models the historical driving data of the vehicle and establishes a relationship model between the historical position and the historical arrival time of the vehicle. The historical data processing process may include preprocessing the basic information of the historical data, and obtaining the historical time of the vehicle arriving at each station during the operation process based on the historical operation travel trajectory data and the line station data. According to the vehicle label and the vehicle line label, the historical operation travel trajectory data is divided into the single trip operation data of the vehicle on the line label; according to the single trip operation data and the line station data, the time of arrival and departure of each station is divided. For example, the station departure and arrival judgment can be that the data within the radius of the station location (500m-300m) is the arrival, and the data outside is the departure; then, the time of arrival and departure of all vehicles on all lines can be obtained, and the historical data preprocessing results can be obtained. The relationship model between the historical position and the historical arrival time of the vehicle is established, and the historical operation travel trajectory data is associated with the real-time operation travel data, and the arrival time of each station is analyzed to establish the vehicle historical position-arrival station schedule. The list of stations on the route can be obtained based on the real-time data vehicle route labels; the vehicle operation data can be updated to determine whether the vehicle has arrived at the terminal: based on the available vehicle route labels in real-time data, the list of stations on the route can be obtained; based on the available vehicle route labels in real-time data and the list of stations on the route, it can be determined whether the vehicle has left and arrived at which station, and which stations have not been arrived at, etc. The vehicle operation status can be determined based on the preprocessing results and the vehicle operation status, and the corresponding prediction basic data can be obtained: based on the historical operation trip data, the historical arrival time of each station; based on the historical operation time rules, the binary query can be used to obtain the predicted operation time between adjacent stations that have not been arrived; whether the vehicle has arrived at the station: based on the vehicle position, the vehicle's historical position-arrival station timetable can be obtained; based on the historical operation time of the vehicle at the same position, the prediction result can be adjusted.

[0062] Real-time prediction can use real-time operation trip data, which can include vehicle labels, time, location, line number, etc., calculate fixed split point line intersections, station split points, and then predict vehicle arrival time according to average operation speed, operation speed time consistency, and operation speed frequency function consistency. The real-time prediction process can include line station data adjustment. Station location data is not allowed to be adjusted. The locations of the two line stations provided are all inaccurate, so manual methods can be used to adjust them one by one, that is, re-execute data acquisition. Station sequence adjustment. According to the position adjustment results and query related line operations, manual adjustments are made. Preprocessing operation data. Since the line label is inaccurate, the order of stations passed by a single vehicle can be divided according to the line station data to determine the vehicle operation trips; according to the single trip operation data and line station data, the time of arrival and departure from each station can be divided; then the time of arrival and departure of all vehicles on all lines can be obtained, and the operation data preprocessing results. Real-time prediction uses station line data, historical operation trip trajectory data, and real-time operation trip data to predict the arrival time of each station and announce the arrival time of each station.

[0063] The fractal-based real-time prediction method for public transportation vehicle arrival proposed in this application adopts a step-by-step matrix calculation method. Therefore, when the position of the vehicle changes during driving, it is only necessary to calculate the difference between the current time and position data and the time and position data at the last calculation to update the time when the vehicle arrives at the next station without recalculating all parameters. This technical solution has low computing power requirements, so it can be implemented entirely based on mobile phone applications or on-board edge computing devices. This application provides a low-cost, multi-mode, and easy-to-deploy real-time prediction system for public transportation vehicle arrivals, which is mainly used to solve the real-time prediction problem of public transportation vehicle arrivals for small and medium-sized public transportation enterprises and public transportation vehicles on scheduled routes in remote areas, and to meet users' demand for real-time prediction services for scheduled vehicle arrivals.

[0064] According to another aspect of an embodiment of the present application, a public transportation vehicle arrival prediction device is also provided, which is applied to a first user terminal. The device can execute the public transportation vehicle arrival prediction method of the above embodiment. The specific implementation method and preferred application scenario are the same as those of the above embodiment and will not be repeated here.

[0065] Figure 3 is a schematic diagram of a public transportation vehicle arrival prediction device according to an embodiment of the present application, such as Figure 3 As shown, the device includes the following: an acquisition module 302 and a determination module 304 .

[0066] Among them, the acquisition module is used to respond to the current query instruction acting on the operation interface, obtain the current operation status information of the target public transportation vehicle corresponding to the current query instruction, and the historical number of query instructions sent by at least one second terminal within the historical time period, wherein the current operation status information at least includes the current vehicle position, current vehicle speed and the current number of passengers that can be taken by the vehicle, and the current number of passengers that can be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle; the determination module is used to determine the current query result of the target public transportation vehicle based on the current query instruction, the historical number and the current operation status information, wherein the current query result at least includes the estimated arrival time and the estimated degree of congestion of the target public transportation vehicle at the current query station corresponding to the current query instruction.

[0067] Among them, the determination module is also used to determine the estimated arrival time based on the current query site, current vehicle position and current vehicle speed corresponding to the current query instruction; determine the estimated degree of congestion based on historical quantities and the current number of passengers that the vehicle can take; and determine the current query result based on the estimated arrival time and the estimated degree of congestion.

[0068] Among them, after determining the current query result of the target public transportation vehicle based on the current query instruction, historical quantity and current operating status information, the determination module is also used to mark the current query instruction as a historical query instruction, and mark the current query result as a historical query result; based on the historical query instruction and the historical query result, a historical query data pair is constructed; the historical query data pair is uploaded to the cloud server to generate historical query information, wherein the historical query information uses the target data pair as index information, and the target data pair is composed of the historical instruction query time, the historical instruction query station and the historical query train number in the historical query instruction.

[0069] Among them, the determination module is also used to obtain historical query information, wherein the historical query information is used to represent the query information corresponding to the query instruction sent by at least one second terminal within a historical time period; based on the historical query information, the current query instruction, the historical quantity and the current operating status information, the current query result is determined.

[0070] Among them, the determination module is also used to match the current query instruction with the index information of the historical query information to obtain a matching result, wherein the matching result is used to characterize the similarity matching degree between the current query instruction and the index information; based on the matching result, determine the first weight parameter of the historical query results in the historical query information, and the second weight parameter of the current operating status information; based on the current query instruction, historical quantity, historical query results, the first weight parameter, the current operating status information and the second weight parameter, determine the current query result.

[0071] Among them, the determination module is also used to obtain the current instruction query time, current instruction query site and current query train number of the current query instruction; the current instruction query time, current instruction query site and current query train number are matched with the historical instruction query time, historical instruction query site and historical query train number in the index information to obtain a matching result.

[0072] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods in various embodiments of the present invention when running.

[0073] The above-mentioned memory may refer to a device inside a computer for storing data and programs, and may include memory, hard disk, etc., wherein the memory may be used to temporarily store running programs and data, the hard disk may be used to store programs and data for a long time, and the memory may be used to enable the computer to read and write data, and execute programs; the above-mentioned processor may be responsible for executing instructions in computer programs and performing data processing, and may be responsible for controlling and executing various operations, including arithmetic operations, logical operations, data transmission, etc.

[0074] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0075] The above-mentioned computer storage medium may refer to a medium in a computer memory used to store certain discontinuous physical quantities. Computer storage media mainly include semiconductors, magnetic cores, magnetic drums, magnetic tapes, laser disks, etc.; the stored program included in the computer-readable storage medium may be a set of instructions that can be recognized and executed by a computer, running on an electronic computer, and is an information tool that meets certain needs of people.

[0076] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0077] The above-mentioned computer program product may refer to a software program that has been written, tested and released and can be run on a computer or other device. The computer program product may include an application, an operating system, tool software, etc., which is used to implement specific functions or solve specific problems.

[0078] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0079] The above-mentioned non-volatile computer-readable storage medium may refer to a medium for storing data. The non-volatile computer-readable storage medium can keep the data from being lost when the power is off, and can be used to store long-term data, such as operating systems, applications, and user files. The non-volatile storage medium may include hard disk drives, solid-state drives, optical disks, and flash memory storage devices, etc.

[0080] The embodiments of the present application further provide a computer program, which implements the methods in the above-mentioned embodiments of the present invention when executed by a processor.

[0081] The above-mentioned computer program may refer to a collection of instructions used to tell a computer to perform a specific task or operation. A computer program may be written by a programmer using a specific programming language and may include algorithms, data structures, logic, and control flows. A computer program may be used for a variety of purposes, including application software, operating systems, and the like.

[0082] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units 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 units or modules, which can be electrical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0085] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0086] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0087] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for predicting the arrival of a public transportation vehicle, characterized in that: Applied to a first user terminal, the method includes: In response to a current query instruction acting on the operation interface, current operation status information of a target public transportation vehicle corresponding to the current query instruction and a historical number of query instructions sent by at least one second terminal within a historical time period are obtained, wherein the current operation status information includes at least a current vehicle position, a current vehicle speed and a current number of passengers that can be taken by the vehicle, and the current number of passengers that can be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle; Based on the current query instruction, the historical quantity and the current operating status information, a current query result of the target public transportation vehicle is determined, wherein the current query result at least includes an estimated arrival time and an estimated degree of congestion of the target public transportation vehicle at the current query station corresponding to the current query instruction.

2. The method for predicting the arrival of a public transportation vehicle according to claim 1, characterized in that: Determining a current query result of the target public transportation vehicle based on the current query instruction, the historical quantity and the current operation status information includes: Determining the estimated arrival time based on the current query site, the current vehicle position, and the current vehicle speed corresponding to the current query instruction; Determining the expected riding congestion level based on the historical number and the number of people currently available for riding in the vehicle; The current query result is determined based on the estimated arrival time and the estimated riding congestion level.

3. The method for predicting the arrival of a public transportation vehicle according to claim 1, characterized in that: After determining the current query result of the target public transportation vehicle based on the current query instruction, the historical quantity and the current operation status information, the method further includes: Marking the current query instruction as a historical query instruction, and marking the current query result as a historical query result; Based on the historical query instruction and the historical query result, construct a historical query data pair; The historical query data pair is uploaded to a cloud server to generate historical query information, wherein the historical query information uses a target data pair as index information, and the target data pair is composed of the historical instruction query time, historical instruction query site and historical query train number in the historical query instruction.

4. The method for predicting the arrival of a public transportation vehicle according to claim 1, characterized in that: Determining a current query result of the target public transportation vehicle based on the current query instruction, the historical quantity and the current operation status information includes: Acquire historical query information, wherein the historical query information is used to represent query information corresponding to the query instruction sent by the at least one second terminal within the historical time period; The current query result is determined based on the historical query information, the current query instruction, the historical quantity and the current operating status information.

5. The method for predicting the arrival of a public transportation vehicle according to claim 4, characterized in that: Determining the current query result based on the historical query information, the current query instruction, the historical quantity, and the current operating status information includes: Matching the current query instruction with the index information of the historical query information to obtain a matching result, wherein the matching result is used to indicate the similarity matching degree between the current query instruction and the index information; Determine a first weight parameter of the historical query result in the historical query information and a second weight parameter of the current operation status information based on the matching result; The current query result is determined based on the current query instruction, the historical quantity, the historical query result, the first weight parameter, the current operating status information and the second weight parameter.

6. The method for predicting the arrival of a public transportation vehicle according to claim 5, characterized in that: The current query instruction is matched with the index information of the historical query information to obtain a matching result, including: Obtaining the current query time, the current query station and the current query train number of the current query instruction; The current instruction query time, the current instruction query site and the current query train number are matched with the historical instruction query time, the historical instruction query site and the historical query train number in the index information to obtain the matching result.

7. A public transportation vehicle arrival prediction device, characterized in that: Applied to a first user terminal, the device includes: an acquisition module, configured to respond to a current query instruction acting on an operation interface, and acquire current operation status information of a target public transportation vehicle corresponding to the current query instruction, and a historical number of query instructions sent by at least one second terminal within a historical time period, wherein the current operation status information includes at least a current vehicle position, a current vehicle speed, and a current number of passengers that can be taken by the vehicle, and the current number of passengers that can be taken by the vehicle is used to indicate the number of passengers that can currently be taken by the target public transportation vehicle; A determination module is used to determine a current query result of the target public transportation vehicle based on the current query instruction, the historical quantity and the current operation status information, wherein the current query result at least includes an estimated arrival time and an estimated riding congestion level of the target public transportation vehicle at the current query station corresponding to the current query instruction.

8. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the public transportation vehicle arrival prediction method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the storage medium is located is controlled to execute the arrival prediction method of a public transportation vehicle according to any one of claims 1 to 6.

10. A computer program product, characterized in that The invention comprises a computer program, which, when executed by a processor, implements the arrival prediction method of a public transportation vehicle according to any one of claims 1 to 6.

Images