Prediction method, device, electronic equipment and storage medium for predicted time of arrival

Abstract

The present disclosure provides a prediction method, device and electronic equipment for predicting the time of arrival, relates to the technical field of computers, and particularly relates to the technical field of map navigation and intelligent traffic. The method comprises the following steps: receiving a prediction request for predicting the time of arrival; determining a requested path according to position information in the prediction request; and querying a travel time of the path in a corresponding time slice in mining data as a prediction result according to time information in the prediction request, wherein the mining data is obtained by mining historical travel times according to the sparsity of historical trajectory data in advance. The ETA is optimized based on the historical trajectory data in the technical solution of the present disclosure, which can improve the accuracy of the prediction result of the ETA, is particularly suitable for areas with sparse trajectories, and improves the user experience.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of map navigation and intelligent transportation technology. Background Technology

[0002] In existing map navigation scenarios, ETA (Estimated Time of Arrival) is a crucial function that helps users make pre-trip decisions, and its accuracy is a significant factor affecting user experience. Currently, for areas with dense tracking data, methods combining big data and machine learning can effectively predict ETA.

[0003] However, the above method is not applicable to areas with very sparse traffic patterns. Typically, static speed limits and traffic light rules are used to estimate the travel time for each route. The drawback of this approach is that the calculation results do not change with road capacity, and because the static speed limit is the maximum speed, the estimated travel time is much shorter than the actual time required, resulting in significant deviations in the ETA results and severely impacting the user experience. Summary of the Invention

[0004] This disclosure provides a method, apparatus, electronic device, storage medium, and computer program product for predicting estimated arrival times.

[0005] According to one aspect of this disclosure, a method for predicting estimated arrival time is provided, comprising:

[0006] Receive prediction requests for estimated arrival time;

[0007] The path of the request is determined based on the location information in the predicted request;

[0008] Based on the time information in the prediction request, the travel time of the path within the corresponding time slice is queried in the mined data as the prediction result;

[0009] The data being mined is obtained in advance by mining historical travel times based on the sparsity of historical trajectory data.

[0010] According to another aspect of this disclosure, a time-of-arrival prediction device is provided, comprising:

[0011] The determination module is used to determine the path of the request based on the location information in the predicted request;

[0012] The prediction module is used to query the travel time of the path within the corresponding time slice in the mined data based on the time information in the prediction request, and use this as the prediction result.

[0013] The data being mined is obtained in advance by mining historical travel times based on the sparsity of historical trajectory data.

[0014] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the methods in any embodiment of this disclosure.

[0018] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the methods of any embodiment of this disclosure.

[0019] According to another aspect of this disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the methods in any embodiment of this disclosure.

[0020] The technical solution of this disclosure optimizes ETA based on historical trajectory data, which can improve the accuracy of ETA prediction results. It is applicable not only to areas with dense trajectories but also to areas with sparse trajectories, making it more widely applicable and improving the user experience.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0022] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0023] Figure 1 This is a schematic diagram of a prediction method for estimated arrival time according to an embodiment of the present disclosure;

[0024] Figure 2 This is a schematic diagram of a prediction method for estimated arrival time according to an embodiment of the present disclosure;

[0025] Figure 3 This is a schematic diagram of a prediction method for estimated arrival time according to an embodiment of the present disclosure;

[0026] Figure 4 This is a schematic diagram of a data mining process according to an embodiment of the present disclosure;

[0027] Figure 5 This is a schematic diagram of the data mining process within a unit time slice of a path according to an embodiment of this disclosure;

[0028] Figure 6 This is a block diagram of a prediction device for estimated arrival time according to an embodiment of the present disclosure;

[0029] Figure 7 This is a block diagram of a prediction device for estimated arrival time according to an embodiment of the present disclosure;

[0030] Figure 8 This is a block diagram of an electronic device used to implement the estimated arrival time prediction method of the embodiments of this disclosure. Detailed Implementation

[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0032] The technical solutions of this disclosure are applied to ETA prediction scenarios, including but not limited to applications such as map navigation, intelligent transportation, and dispatch control. ETA prediction in this disclosure can be initiated by any electronic device, including but not limited to computers, mobile terminals, laptops, etc. ETA prediction estimates the travel time required for a route, typically referring to the time required to reach a destination from the current location. This travel time can be the travel time of a vehicle or other means of transportation, such as ships, aircraft, etc., and is not specifically limited. The route can include one or more links. In this disclosure, a link refers to the smallest unit of road in navigation or map applications. When the requested route includes multiple links, the ETA of each link can be predicted and then summed to obtain the ETA of the entire route. This disclosure optimizes ETA based on historical trajectory data, improving the accuracy of ETA prediction results. It is applicable not only to areas with dense trajectories but also to areas with sparse trajectories, thus broadening its application and enhancing the user experience.

[0033] Figure 1 This is a schematic diagram of a method for predicting the estimated arrival time in one embodiment of this disclosure. Figure 1 As shown, the method includes:

[0034] S101: Receive the prediction request for the estimated arrival time;

[0035] S102: Determine the requested path based on the location information in the predicted request;

[0036] S103: Based on the time information in the prediction request, query the travel time of the path within the corresponding time slice in the mined data as the prediction result; wherein, the mined data is obtained in advance by mining historical travel times based on the sparsity of historical trajectory data.

[0037] In this embodiment of the disclosure, the prediction request typically includes location information and time information. The location information includes, but is not limited to, the current location and the destination, and the time information includes, but is not limited to, the current time.

[0038] In this embodiment of the disclosure, the historical trajectory data is real historical passage data within a certain time range, including at least the historical passage time, and may further include at least one of the following: passage time, time slice, or link ID. The aforementioned time range can be set as needed, such as six months, eight months, or one year, etc., and is not specifically limited.

[0039] The technical solution of this disclosure is based on the sparsity of historical trajectory data to obtain mining data. The ETA is optimized based on the mining data, which can improve the accuracy of ETA prediction results. It can be applied not only to areas with dense trajectories, but also to areas with sparse trajectories, making it more widely applicable and improving the user experience.

[0040] In one implementation, S103 may include:

[0041] If there are multiple paths in the request, obtain the current time of the predicted request.

[0042] For the first path, the travel time of the first path within the corresponding time slice at the current moment is queried from the mined data and used as the prediction result for the first path;

[0043] For the remaining paths, the corresponding time slices are determined based on the current time and the obtained prediction results. The travel time of the remaining paths within the determined time slices is then queried from the mined data as the prediction results for the remaining paths.

[0044] In scenarios where there are multiple paths for the above ETA prediction request, except for the first path whose corresponding time slice is determined by the current time, the time slices for the remaining paths are determined by the current time and the obtained prediction results. This fully considers the impact of the travel time of the preceding paths on the prediction results of the subsequent paths, improves the accuracy of ETA prediction and the accuracy of the results, and enhances the user experience.

[0045] In one implementation, for the remaining paths, the corresponding time slices are determined based on the current time and the obtained prediction results. The travel time of the remaining paths within the determined time slices is queried from the mined data as the prediction results for the remaining paths, including:

[0046] Each of the remaining paths is taken as the current path in turn. The prediction results of the current time and all paths before the current path are summed. The time slice to which the summation result belongs is determined as the time slice of the current path. The travel time of the current path within the determined time slice is queried in the mined data and used as the prediction result of the current path.

[0047] This method, which determines the time slice for each subsequent path in a multi-path system by summing the prediction results of the current time and all previous paths, fully considers the impact of the travel time of the preceding paths on the prediction results of the subsequent paths. It can accurately obtain the current time of arrival at each path, thereby improving the accuracy of ETA prediction and the accuracy of the results, and enhancing the user experience.

[0048] In one implementation, S103 may include:

[0049] Based on the time information in the prediction request, query the travel time of the path within the corresponding time slice in the first mined data;

[0050] If the travel time is found, the travel time will be used as the prediction result.

[0051] If no travel time is found, the travel time of the path within the corresponding time slice is queried in the second mining data based on the time information in the prediction request, and this is used as the prediction result; wherein, the mining accuracy of the first mining data is higher than that of the second mining data.

[0052] The above implementation provides two types of mining data with different mining precision. The first mining data with higher precision can ensure the accuracy of ETA prediction results. The two types of mining data are used together to ensure more comprehensive data coverage and expand the scope of application.

[0053] In one embodiment, the above method may further include:

[0054] Retrieve historical trajectory data within a specified time range;

[0055] Based on a preset threshold and the number of historical trajectories in the historical trajectory data, the historical travel time in the historical trajectory data is mined to obtain mined data.

[0056] The above implementation method, based on the number of historical trajectories and a preset threshold, can determine the sparsity of historical trajectory data, thus ensuring that the mined data can reflect the sparsity of historical trajectory data. Therefore, the ETA prediction results can change with the changes in road capacity, thereby improving the accuracy of ETA prediction.

[0057] In one implementation, based on a preset threshold and the number of historical trajectories in the historical trajectory data, historical travel time in the historical trajectory data is mined to obtain mined data, including:

[0058] If the number of historical trajectories in the historical trajectory data meets the first threshold, the first mining data is obtained by mining the historical passage time in the historical trajectory data based on the time slices divided by the first passage rule.

[0059] If the number of historical trajectories in the historical trajectory data does not meet the first threshold, the historical travel time in the historical trajectory data is mined based on the time slices divided by the second travel rule to obtain the second mined data; wherein, the accuracy of the time slices divided by the first travel rule is higher than the accuracy of the time slices divided by the second travel rule.

[0060] In the above implementation, by dividing time slices with different precision using the first and second passage rules, relatively dense historical trajectory data can be finely mined, while relatively sparse historical trajectory data can be coarsely mined, thereby making the mined data more comprehensive and reliable, and thus improving the accuracy of ETA prediction.

[0061] In one embodiment, the above method may further include:

[0062] If the number of historical trajectories in the historical trajectory data does not meet the first threshold, historical predicted traffic data is obtained. Based on the time slices divided by the first traffic rule, the historical predicted traffic time in the historical predicted traffic data is mined to obtain the first mined data.

[0063] The above-mentioned method of mining based on historical predicted road condition data is a good supplement to historical trajectory data, expanding the sources of historical data, making data mining more comprehensive and the results more representative.

[0064] In one implementation, if the number of historical trajectories in the historical trajectory data meets a first threshold, the historical travel time in the historical trajectory data is mined based on time slices divided by a first travel rule to obtain first mined data, including:

[0065] Divide the time slices according to the first pass rule;

[0066] For each path in the historical trajectory data, within each time slice divided by the first passage rule, compare the number of historical trajectories in the current time slice with the first threshold.

[0067] If the number of historical trajectories exceeds the first threshold, all historical travel times of the current path within the current time slice are mined to obtain the travel time of the current path within the current time slice, which is then used as the first mining data.

[0068] In the above implementation, a value greater than the first threshold indicates that the sparsity of the historical trajectory data within the current time slice meets the conditions for fine data mining. This historical trajectory data is considered valid, as it can reflect historical patterns and can be used for fine data mining. Therefore, fine mining is performed to obtain the first mining data, which provides a reliable query basis for ETA prediction.

[0069] In one implementation, if the number of historical trajectories in the historical trajectory data does not meet a first threshold, second mined data is obtained by mining the historical travel times in the historical trajectory data based on time slices divided by a second travel rule, including:

[0070] If the number of historical trajectories is less than or equal to the first threshold, compare the number of historical trajectories with the second threshold.

[0071] If the number of historical trajectories exceeds the second threshold, time slices are divided according to the second passage rule. The new time slice corresponding to the current time slice in the second passage rule is determined. All historical passage times of the current path within the new time slice are mined to obtain the passage time of the current path within the current time slice, which is used as the second mining data.

[0072] In the above implementation, a value less than or equal to the first threshold and greater than the second threshold indicates that the sparsity of the historical trajectory data within the current time slice meets the conditions for coarse data mining. This historical trajectory data is considered valid and can reflect historical patterns, and can be used for coarse data mining. Therefore, coarse mining is performed to obtain the second mining data, which further enriches the data query basis for ETA prediction.

[0073] In one implementation, the first traffic rule divides the time slots according to the traffic patterns of the morning and evening peak hours, and the second traffic rule divides the time slots according to the traffic patterns of weekdays and weekends.

[0074] The first and second passage rules mentioned above reflect the passage patterns from different perspectives, making the division of time slices more reasonable and the division results more accurate and reliable.

[0075] Figure 2 This is a schematic diagram of a method for predicting the estimated arrival time in one embodiment of this disclosure. Figure 2 As shown, the method includes:

[0076] S201: Receive the prediction request for the estimated arrival time;

[0077] For example, the prediction request may include location information, such as current location and destination, and may also include time information, such as current time, and may further include path ID, etc., without limitation.

[0078] S202: Determine the requested path based on the location information in the predicted request;

[0079] In this embodiment of the disclosure, the path requested in the prediction request can be a single path, meaning the destination of the requested route is the endpoint of that path. In this scenario, predicting the ETA of that path is sufficient. In practical applications, the path requested in the prediction request is usually multiple, meaning the requested route from the current location to the destination includes multiple paths. In this scenario, it is necessary to predict the ETA of each of these paths to obtain the ETA of the entire route.

[0080] S203: When there are multiple paths in the request, obtain the current time of the predicted request;

[0081] S204: For the first path, query the travel time of the first path within the corresponding time slice at the current moment in the mined data as the prediction result for the first path;

[0082] The aforementioned data was mined in advance based on the sparsity of historical trajectory data, specifically by mining historical travel times. The aforementioned time slices were pre-divided according to travel rules, typically representing a time range. If the current time falls within this time range, then the time slice representing that time range is considered the time slice corresponding to the current time. For example, if the current time is 7:55, the corresponding time slice is 7:00-8:00.

[0083] S205: Take each of the remaining paths as the current path in turn, sum the prediction results of the current time and all paths before the current path, determine the time slice to which the time slice corresponding to the summation result belongs, and query the travel time of the current path in the determined time slice in the mined data as the prediction result of the current path.

[0084] For example, the first path is link1, with a current time of 7:55. The predicted ETA for this path is 10 minutes. The remaining paths are link2 and link3. When predicting link2, adding 10 minutes to 7:55 gives 8:05. Therefore, the time slot from 8:00 to 9:00, where 8:05 is located, is determined as the time slot corresponding to link2, and the ETA is found to be 25 minutes. Similarly, when predicting link3, based on 7:55, 10 minutes, and 25 minutes, the time is 8:30. Therefore, the time slot from 8:00 to 9:00 is again determined as the time slot corresponding to link3, and the travel time of link3 within this time slot is then obtained.

[0085] Figure 3 This is a schematic diagram of a method for predicting the estimated arrival time in one embodiment of this disclosure. Figure 3 As shown, the method includes:

[0086] S301: Receive a prediction request for the estimated arrival time;

[0087] S302: Determine the requested path based on the location information in the predicted request;

[0088] S303: Based on the time information in the prediction request, query the travel time of the path in the corresponding time slice in the first mining data;

[0089] S304: If the above passage time is found, use the passage time as the prediction result;

[0090] S305: If the above-mentioned travel time is not found, the travel time of the path in the corresponding time slice is queried in the second mining data according to the time information in the prediction request and used as the prediction result.

[0091] The first and second mining data were both obtained in advance by mining historical travel time based on the sparsity of historical trajectory data, and the mining accuracy of the first mining data was higher than that of the second mining data.

[0092] In the above embodiments, the requested path can be one or more. When multiple paths are requested, they can be selected according to... Figure 2 The implementation shown performs ETA prediction for these multiple paths, which will not be described in detail here.

[0093] In any of the embodiments of this disclosure above, if no query result is obtained by mining data to determine the travel time, the following method can be used for ETA prediction: The travel time of the requested path can be calculated using static speed limits and traffic light rules. The static speed limit is the maximum speed of the path. Based on the path distance and this maximum speed, the required travel time can be calculated. If the path passes through several traffic lights, the duration of the red light (e.g., 20 seconds or 30 seconds) can be added to the total travel time to obtain the ETA result for that path. Further details are omitted here.

[0094] Figure 4 This is a schematic diagram of a data mining process according to one embodiment of this disclosure. Figure 4 As shown, in one implementation, prior to employing the ETA prediction method provided in any of the above embodiments, data mining based on historical trajectory data may include the following steps:

[0095] S401: Obtain historical trajectory data within a specified time range;

[0096] S402: Divide the time slices according to the first passage rule;

[0097] S403: For each path in the historical trajectory data, within each time slice divided by the first passage rule, compare the number of historical trajectories in the current time slice with the first threshold.

[0098] S404: If the number of historical trajectories is greater than the first threshold, mine all historical travel times of the current path within the current time slice to obtain the travel time of the current path within the current time slice, and use it as the first mining data;

[0099] S405: If the number of historical trajectories is less than or equal to the first threshold, compare the number of historical trajectories with the second threshold.

[0100] For example, the above S405 may further include the following steps:

[0101] If the number of historical trajectories is no greater than the first threshold, historical predicted traffic data is obtained. Based on the time slices divided by the first traffic rule, the historical predicted traffic time in the historical predicted traffic data is mined to obtain the first mined data.

[0102] In this embodiment, the size of the first threshold can be set as needed, such as 20 or 30, etc., and the specific value is not limited. The size of the second threshold can also be set as needed, such as 5 or 8, etc., and the specific value is not limited. The first threshold simply needs to be greater than the second threshold.

[0103] S406: When the number of historical trajectories is greater than the second threshold, divide the time slices according to the second passage rule, determine the new time slice corresponding to the current time slice in the second passage rule, mine all the historical passage times of the current path in the new time slice, obtain the passage time of the current path in the current time slice, and use it as the second mining data.

[0104] The time slice precision of the first passage rule is higher than that of the time slice precision of the second passage rule.

[0105] In this embodiment of the disclosure, the first mining data can be stored in one file, the second mining data can be stored in another file, or the first mining data can be stored in a first database, the second mining data can be stored in a second database, etc. This disclosure does not make any specific limitations in this regard.

[0106] In any of the data mining steps described above, the mining may include calculating the average time taken for multiple historical travel times. Specifically, the following method may be used: denoising and averaging multiple historical travel times to obtain an optimized result. Of course, other implementation methods may also be used, and this disclosure does not make any specific limitations.

[0107] For example, the first traffic rule can divide time slots according to the traffic patterns of morning and evening peak hours. For instance, using the first traffic rule to finely divide the 24 hours of a day into time slots, the morning peak (7:00-10:00) and evening peak (17:00-21:00) have high traffic volume and relatively dense traffic patterns, so each 30-minute time slot can be used. Outside of morning and evening peak hours, traffic volume is low and traffic patterns are relatively sparse, so each hour can be used as a time slot.

[0108] For example, the second traffic rule can divide time slices according to the traffic patterns of weekdays and rest days, and this disclosure does not impose specific limitations. For instance, using the second traffic rule to roughly divide a week into time slices, Monday to Friday are weekdays and can be considered as one time slice, while Saturday and Sunday are rest days and can be considered as another time slice.

[0109] Any embodiment of this disclosure can be applied to areas with dense trajectories, and is especially suitable for areas with sparse trajectories. After online practical verification, the accuracy of ETA has been improved from 30% to over 70%.

[0110] Figure 5 This is a schematic diagram of the data mining process within a unit time slice of a path according to an embodiment of this disclosure. For example... Figure 5 As shown, after loading historical trajectory data and historical predicted traffic data, the process includes:

[0111] S501: Select the current time slice for the current path in the loaded historical trajectory data;

[0112] The current path can be any path in the loaded historical trajectory data. This process is applicable to every path in the historical trajectory data. In actual execution, each path in the historical trajectory data can be used as the current path to execute this process, which will not be elaborated here.

[0113] The current time slice is any one of the time slices divided using the first passage rule. In actual execution, this process can be executed sequentially for each time slice, starting from the first time slice, until all time slices have been executed, thus completing the data mining of the current path.

[0114] S502: Determine whether the number of historical trajectories in the current time slice is greater than the first threshold. If yes, execute 503; otherwise, execute 504.

[0115] S503: First, denoise all historical travel times of the current path within the current time slice, then take the average value. The result is used as the travel time of the current path within the current time slice. Then execute 506.

[0116] S504: Determine whether the number of historical predicted traffic conditions in the current time slice is greater than the first threshold. If yes, execute 505; otherwise, execute 507.

[0117] S505: First, denoise all historical predicted travel times of the current path within the current time slice, then take the average value. The result is used as the travel time of the current path within the current time slice. Then execute 506.

[0118] S506: Save the travel time of the current path within the current time slice as the first mining data for fine mining, and end the current mining;

[0119] S507: Redetermine the current time slice and determine whether the number of historical trajectories of the current path within the current time slice is greater than the second threshold. If yes, execute 508; otherwise, execute 509.

[0120] The re-determination step involves identifying the time slice corresponding to the original current time slice within the time slices allocated using the second passage rule, and then re-determining it as the current time slice. For example, if the original current time slice in the previous step was Wednesday from 12:00 to 13:00, this step determines its corresponding time slice from Monday to Friday according to the second passage rule. Therefore, the time slice from Monday to Friday is re-determined as the current time slice to continue executing subsequent steps.

[0121] S508: First, denoise all historical travel times of the current path within the current time slice, then take the average value. The result is used as the travel time of the current path within the current time slice. Then execute 511.

[0122] S509: Determine whether the number of historical predicted road conditions for the current path within the current time slice is greater than the second threshold. If yes, execute 510; otherwise, end the current mining.

[0123] S510: First, denoise all historical predicted travel times of the current path within the current time slice, then take the average value. The result is used as the travel time of the current path within the current time slice. Then execute 511.

[0124] S511: Save the travel time of the current path within the current time slice as the second mining data of the rough mining, and end the current mining.

[0125] Figure 6 This is a block diagram of a time-of-arrival prediction device according to an embodiment of the present disclosure. For example... Figure 6 As shown, the device includes:

[0126] The receiving module 601 is used to receive a prediction request for the estimated time of arrival;

[0127] The determination module 602 is used to determine the path of the request based on the location information in the prediction request;

[0128] Prediction module 603 is used to query the travel time of the path within the corresponding time slice in the mined data based on the time information in the prediction request, and use it as the prediction result.

[0129] The data mined was obtained in advance by mining historical travel times based on the sparsity of historical trajectory data.

[0130] In one implementation, the prediction module 603 includes:

[0131] The acquisition unit is used to obtain the current time contained in the predicted request when there are multiple request paths;

[0132] The first prediction unit is used to query the travel time of the first path in the corresponding time slice at the current moment in the mined data for the first path as the prediction result of the first path;

[0133] The second prediction unit is used to determine the corresponding time slice for the remaining paths based on the current time and the obtained prediction results, and to query the travel time of the remaining paths in the determined time slice in the mined data as the prediction result for the remaining paths.

[0134] In one implementation, the second prediction unit is used for:

[0135] Each of the remaining paths is taken as the current path in turn. The prediction results of the current time and all paths before the current path are summed. The time slice to which the summation result belongs is determined as the time slice of the current path. The travel time of the current path within the determined time slice is queried in the mined data and used as the prediction result of the current path.

[0136] In one implementation, the prediction module 603 is used for:

[0137] Based on the time information in the prediction request, query the travel time of the path within the corresponding time slice in the first mined data;

[0138] If the travel time is found, the travel time will be used as the prediction result.

[0139] If the passage time is not found, the passage time of the path within the corresponding time slice is queried in the second mining data based on the time information in the prediction request and used as the prediction result.

[0140] The mining accuracy of the first mining data is higher than that of the second mining data.

[0141] Figure 7 This is a block diagram of a time-of-arrival prediction device according to an embodiment of the present disclosure. For example... Figure 7 As shown, the device includes: a receiving module 701, a determining module 702, and a prediction module 703. The receiving module 701, determining module 702, and prediction module 703 have the same functions as the receiving module 601, determining module 602, and prediction module 603 in the above embodiments, and will not be described again here. In one embodiment, the above device may further include:

[0142] Module 704 is used to acquire historical trajectory data within a specified time range;

[0143] The mining module 705 is used to mine historical travel time data from historical trajectory data based on preset thresholds and the number of historical trajectories in historical trajectory data.

[0144] In one embodiment, the mining module 705 includes:

[0145] The first mining unit is used to mine the historical passage time in the historical trajectory data to obtain the first mining data, based on the time slices divided by the first passage rule, when the number of historical trajectories in the historical trajectory data meets the first threshold.

[0146] The second mining unit is used to mine the historical passage time in the historical trajectory data to obtain the second mining data when the number of historical trajectories in the historical trajectory data does not meet the first threshold, based on the time slices divided by the second passage rule.

[0147] The time slice precision of the first passage rule is higher than that of the time slice precision of the second passage rule.

[0148] In one embodiment, the second excavation unit is further configured to:

[0149] If the number of historical trajectories in the historical trajectory data does not meet the first threshold, historical predicted traffic data is obtained. Based on the time slices divided by the first traffic rule, the historical predicted traffic time in the historical predicted traffic data is mined to obtain the first mined data.

[0150] In one embodiment, the first excavation unit is used for:

[0151] Divide the time slices according to the first pass rule;

[0152] For each path in the historical trajectory data, within each time slice divided by the first passage rule, compare the number of historical trajectories in the current time slice with the first threshold.

[0153] If the number of historical trajectories exceeds the first threshold, all historical travel times of the current path within the current time slice are mined to obtain the travel time of the current path within the current time slice, which is then used as the first mining data.

[0154] In one embodiment, the second excavation unit is used for:

[0155] If the number of historical trajectories is less than or equal to the first threshold, compare the number of historical trajectories with the second threshold.

[0156] If the number of historical trajectories exceeds the second threshold, time slices are divided according to the second passage rule. The new time slice corresponding to the current time slice in the second passage rule is determined. All historical passage times of the current path within the new time slice are mined to obtain the passage time of the current path within the current time slice, which is used as the second mining data.

[0157] In this embodiment of the disclosure, the first traffic rule can divide the time slots according to the traffic patterns of the morning and evening peak hours, and the second traffic rule can divide the time slots according to the traffic patterns of weekdays and rest days.

[0158] The apparatus provided in this embodiment of the present disclosure obtains mining data based on the sparsity of historical trajectory data, and optimizes ETA based on the mining data, which can improve the accuracy of ETA prediction results. It is applicable not only to areas with dense trajectories, but also to areas with sparse trajectories, making it more widely applicable and improving the user experience.

[0159] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0160] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0161] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0162] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0163] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0164] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for predicting the estimated time of arrival. For example, in some embodiments, the method for predicting the estimated time of arrival may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the method for predicting the estimated time of arrival described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the method for predicting the estimated time of arrival by any other suitable means (e.g., by means of firmware).

[0165] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0166] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0167] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0168] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0169] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0170] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0171] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0172] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for predicting a predicted time of arrival, comprising: receiving a prediction request for a predicted time of arrival; determining a requested path according to location information in the prediction request; querying a travel time of the path in a corresponding time slice in mined data as a prediction result according to time information in the prediction request; wherein the mined data is obtained by mining historical travel times according to a sparsity of historical trajectory data, and wherein the mined data is obtained by mining historical travel times in the historical trajectory data based on a first travel rule to divide time slices when a number of historical trajectories in the historical trajectory data meets a first threshold, and by mining historical travel times in the historical trajectory data based on a second travel rule to divide time slices when the number of historical trajectories in the historical trajectory data does not meet the first threshold, and wherein a time slice precision of the first travel rule is higher than a time slice precision of the second travel rule.

2. The method of claim 1, wherein, The querying of the travel time of the path in the corresponding time slice in the mined data as the prediction result according to the time information in the prediction request comprises: when the requested path is multiple paths, obtaining a current time included in the prediction request; for a first path, querying a travel time of the first path in a time slice corresponding to the current time in the mined data as a prediction result of the first path; for the remaining paths, determining a corresponding time slice according to the current time and the obtained prediction results, and querying a travel time of the remaining paths in the determined time slice in the mined data as prediction results of the remaining paths.

3. The method of claim 2, wherein, The querying of the travel time of the remaining paths in the determined time slice in the mined data as the prediction results of the remaining paths according to the current time and the obtained prediction results comprises: taking each path in the remaining paths as a current path in turn, summing the current time and prediction results of all paths before the current path, determining a time slice to which a time corresponding to a summing result belongs as a time slice corresponding to the current path, and querying a travel time of the current path in the determined time slice in the mined data as a prediction result of the current path. 4.The method of claim 1, wherein the querying of the travel time of the path in the corresponding time slice in the mined data as the prediction result according to the time information in the prediction request comprises: querying the travel time of the path in the corresponding time slice in the first mined data according to the time information in the prediction request; when the travel time is queried, taking the travel time as the prediction result; when the travel time is not queried, querying a travel time of the path in the corresponding time slice in the second mined data as the prediction result according to the time information in the prediction request. The mining precision of the first mining data is higher than the mining precision of the second mining data.

5. The method of claim 1, further comprising: obtaining historical trajectory data in a specified time range.

6. The method of claim 1, further comprising: in a case where the number of historical trajectories in the historical trajectory data does not meet the first threshold, obtaining historical predicted traffic data, mining historical predicted travel times in the historical predicted traffic data based on time slices divided according to the first travel rule to obtain first mining data.

7. The method of claim 1, wherein, The mining of the historical travel times in the historical trajectory data based on the time slices divided according to the first travel rule to obtain the first mining data in the case where the number of historical trajectories in the historical trajectory data meets the first threshold comprises: dividing the time slices according to the first travel rule; for each path in the historical trajectory data, comparing the number of historical trajectories in a current time slice with the first threshold in the current time slice divided according to the first travel rule; in a case where the number of historical trajectories in the current time slice is greater than the first threshold, mining all historical travel times of the current path in the current time slice to obtain a travel time of the current path in the current time slice as the first mining data.

8. The method of claim 7, wherein, The mining of the historical travel times in the historical trajectory data based on the time slices divided according to the second travel rule to obtain the second mining data in the case where the number of historical trajectories in the historical trajectory data does not meet the first threshold comprises: in a case where the number of historical trajectories in the current time slice is less than or equal to the first threshold, comparing the number of historical trajectories with a second threshold; in a case where the number of historical trajectories in the current time slice is greater than the second threshold, dividing the time slices according to the second travel rule, determining a new time slice corresponding to the current time slice in the second travel rule, and mining all historical travel times of the current path in the new time slice to obtain a travel time of the current path in the new time slice as the second mining data.

9. The method of any one of claims 1-8, wherein, The first travel rule divides the time slices according to travel rules in morning peak and evening peak, and the second travel rule divides the time slices according to travel rules in weekdays and weekends.

10. A prediction device for predicted time of arrival, comprising: a receiving module configured to receive a prediction request for predicted time of arrival; a determining module configured to determine a requested path according to location information in the prediction request; a prediction module configured to query travel time of the path in a corresponding time slice in mining data as a prediction result according to time information in the prediction request; wherein the mining data is obtained by mining historical travel times according to sparsity of historical trajectory data in advance; and further comprising a mining module configured to mine the historical travel times in the historical trajectory data according to a preset threshold and the number of historical trajectories in the historical trajectory data to obtain the mining data. The mining module comprises: a first mining unit configured to mine historical travel time in the historical trajectory data to obtain first mining data, based on time slices divided according to a first travel rule, when the number of historical trajectories in the historical trajectory data meets a first threshold value; a second mining unit configured to mine historical travel time in the historical trajectory data to obtain second mining data, based on time slices divided according to a second travel rule, when the number of historical trajectories in the historical trajectory data does not meet the first threshold value; wherein the time slice divided according to the first travel rule has higher precision than the time slice divided according to the second travel rule.

11. The apparatus of claim 10, wherein, The prediction module comprises: an acquisition unit configured to acquire a current time included in the prediction request, when the requested path is multiple paths; a first prediction unit configured to, for a first path, query travel time of the first path in a time slice corresponding to the current time in the mining data as a prediction result of the first path; a second prediction unit configured to, for the remaining paths, determine a corresponding time slice according to the current time and the obtained prediction results, and query travel time of the remaining paths in the determined time slice in the mining data as a prediction result of the remaining paths.

12. The apparatus of claim 11, wherein, The second prediction unit is configured to: take each path in the remaining paths as a current path in turn, sum the current time and prediction results of all paths before the current path, determine a time slice to which a time corresponding to the sum result belongs as a time slice corresponding to the current path, and query travel time of the current path in the determined time slice in the mining data as a prediction result of the current path.

13. The apparatus according to claim 10, wherein the prediction module is configured to: query travel time of the path in a corresponding time slice in first mining data according to time information in the prediction request; in a case where the travel time is queried, take the travel time as a prediction result; in a case where the travel time is not queried, query travel time of the path in a corresponding time slice in second mining data according to time information in the prediction request as a prediction result; wherein the mining precision of the first mining data is higher than the mining precision of the second mining data.

14. The apparatus according to claim 10, further comprising: an acquisition module configured to acquire historical trajectory data in a specified time range.

15. The apparatus according to claim 10, wherein the second mining unit is further configured to: in a case where the number of historical trajectories in the historical trajectory data does not meet the first threshold value, acquire historical prediction road condition data, and mine historical prediction travel time in the historical prediction road condition data to obtain first mining data, based on time slices divided according to the first travel rule.

16. The apparatus of claim 10, wherein, The first mining unit is configured to: divide time slices according to a first travel rule; for each path in the historical trajectory data, compare the number of historical trajectories in a current time slice with a first threshold value in each time slice divided according to the first travel rule; In a case where the number of historical trajectories in the current time slice is greater than the first threshold, all historical travel times of the current path in the current time slice are mined to obtain the travel time of the current path in the current time slice as first mining data.

17. The apparatus of claim 16, wherein, The second mining unit is configured to: In a case where the number of historical trajectories in the current time slice is less than or equal to the first threshold, compare the number of historical trajectories with a second threshold; In a case where the number of historical trajectories in the current time slice is greater than the second threshold, divide time slices according to a second travel rule, determine a new time slice corresponding to the current time slice in the second travel rule, and mine all historical travel times of the current path in the new time slice to obtain the travel time of the current path in the new time slice as second mining data.

18. The apparatus of any one of claims 10-17, wherein, The first travel rule divides time slices according to travel rules of morning peak and evening peak, and the second travel rule divides time slices according to travel rules of weekdays and holidays. 19.An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

20. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are configured to enable the computer to perform the method of any one of claims 1-9. 21.A computer program product comprising computer programs / instructions which, when executed by a processor, implement the method of any one of claims 1-9.

Images