Travel chain supplementing method and device based on user riding data

Abstract

The invention relates to the technical field of data analysis, and discloses a trip chain supplement method and device based on user riding data, and the method comprises the steps: obtaining the riding data corresponding to a user; judging whether a to-be-supplemented riding record in the riding data meets a combined travel mode condition or not; when it is judged that the to-be-supplemented riding record meets the combined travel mode condition, determining a target combined travel mode matched with the to-be-supplemented riding record according to a mode classification condition; based on a trip chain supplement formula corresponding to the target combined trip mode, analyzing the riding data to obtain first supplement information; when it is judged that the to-be-supplemented riding record does not meet the combined trip mode condition or the trip chain supplement formula has no solution, the riding data are analyzed based on a trip chain prediction algorithm, and second supplement information is obtained; and supplementing the trip chain according to the trip chain supplement information. Therefore, by implementing the method, the supplement accuracy of the trip chain can be improved, so that the accuracy and the reliability of the trip chain are improved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a travel chain supplementation method and device based on user riding data. Background Art

[0002] With the acceleration of urban intelligence and the advancement of information technology, residents' travel methods are becoming more and more diverse, generating a large amount of travel behavior data. These travel behavior data can serve as the data basis for analyzing residents' travel chains, helping to use residents' travel chains to more accurately implement urban traffic planning.

[0003] However, in practice, it's been found that many residents don't travel every day, or it's impossible to fully collect their travel data, resulting in incomplete travel chains. Existing technologies can identify and supplement resident travel chains by fusing and analyzing multiple sources of data, such as positioning data and mobile phone signaling data. However, this approach requires collecting a wide variety of data, and the data fusion process is complex, prone to data loss and other issues. Consequently, the accuracy of the constructed travel chains still needs to be improved.

[0004] Therefore, it is particularly important to propose a technical solution that can improve the accuracy of trip chain supplementation, thereby improving the accuracy and reliability of the trip chain, and providing a more accurate data basis for urban transportation planning. Summary of the Invention

[0005] The present invention provides a method and device for supplementing a travel chain based on user riding data, which can improve the accuracy of supplementing the travel chain, thereby improving the accuracy and reliability of the travel chain, and is conducive to providing a more accurate data basis for urban traffic planning.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses a trip chain supplement method based on user travel data, the method comprising:

[0007] Obtaining ride data corresponding to the user; the ride data includes at least one single-day ride data, and each single-day ride data includes at least one ride record; each ride record is a bus ride record or a subway ride record;

[0008] Determining whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition;

[0009] When it is determined that the ride record to be supplemented meets the combined travel mode condition, determining a target combined travel mode that matches the ride record to be supplemented based on a pre-set mode classification condition; analyzing the ride data based on a travel chain supplement formula corresponding to the target combined travel mode to obtain first supplementary information for the ride record to be supplemented;

[0010] When it is determined that the ride record to be supplemented does not satisfy the combined travel mode condition or the first supplementary information indicates that the trip chain supplementation formula has no solution, analyzing the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented;

[0011] The travel chain corresponding to the riding data is supplemented according to the determined travel chain supplementary information; the travel chain supplementary information is the first supplementary information or the second supplementary information.

[0012] As an optional implementation, in the first aspect of the present invention, the determining whether the ride record to be supplemented in the ride data satisfies a preset combined travel mode condition includes:

[0013] Determining the single-day travel data containing the travel record to be supplemented in the travel data as the target single-day travel data;

[0014] Determining whether the target single-day ride data belongs to preset single-day ride data; wherein the preset single-day ride data only includes one ride record and no new single-day ride data exists within a preset number of days after the ride record;

[0015] When it is determined that the target single-day ride data belongs to the preset single-day ride data, determining that the ride record to be supplemented does not meet the preset combined travel mode condition;

[0016] When it is determined that the target single-day ride data does not belong to the preset single-day ride data, it is determined that the ride record to be supplemented meets a preset combined travel mode condition.

[0017] As an optional embodiment, in the first aspect of the present invention, determining the target combined travel mode that matches the ride record to be supplemented based on a preset mode classification condition includes:

[0018] When the target single-day ride data includes multiple ride records and the multiple ride records are of the same type, determining the target combined travel mode that matches the ride record to be supplemented as the first combined travel mode;

[0019] When the target single-day ride data includes multiple ride records and the first ride record in the target single-day ride data is the bus ride record and the second ride record is the subway ride record, determining that the target combined travel mode that matches the ride record to be supplemented is the second combined travel mode; wherein the first ride record and the second ride record are two adjacent ride records in the target single-day ride data;

[0020] When the target single-day ride data includes at least one ride record and there is newly added single-day ride data within the preset number of days after the target single-day ride data, if the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data do not belong to the same type of ride record, then determining that the target combined travel mode that matches the ride record to be supplemented is the third combined travel mode;

[0021] If the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data belong to the same type of ride record, then the target combined travel mode that matches the ride record to be supplemented is determined to be the fourth combined travel mode.

[0022] As an optional implementation, in the first aspect of the present invention, the travel chain supplement formula corresponding to the target combined travel mode is provided with a maximum transfer distance that the user can bear;

[0023] The method of analyzing the ride data based on the travel chain supplement formula corresponding to the target combined travel mode to obtain the first supplementary information for the ride record to be supplemented includes:

[0024] When the target combined travel mode is the first combined travel mode, analyzing the target single-day travel data based on the first supplementary formula to obtain a first calculation result corresponding to the first supplementary formula;

[0025] When the target combined travel mode is the second combined travel mode, analyzing the target single-day travel data based on the second supplementary formula to obtain a second calculation result corresponding to the second supplementary formula;

[0026] When the target combined travel mode is the third combined travel mode or the fourth combined travel mode, determining a target supplementary formula corresponding to the target combined travel mode from the first supplementary formula and the second supplementary formula based on a preset formula selection condition, and analyzing the target single-day ride data and the newly added single-day ride data based on the target supplementary formula to obtain a third calculation result corresponding to the target supplementary formula;

[0027] The first supplementary information for the ride record to be supplemented is one of the first calculation result, the second calculation result and the third calculation result.

[0028] As an optional embodiment, in the first aspect of the present invention, the analyzing the ride data based on the determined trip chain prediction algorithm to obtain the second supplementary information for the ride record to be supplemented includes:

[0029] Based on the improved DBSCAN algorithm, a clustering operation is performed on the ride data to obtain a travel clustering result; wherein the ride data used for performing the clustering operation includes outlier data and / or noise data; the travel clustering result includes at least one cluster, each of the clusters includes a plurality of sample points, and each of the sample points is one of the boarding / alighting stations or one of the entry / exit stations included in the ride data;

[0030] Calculating the weighted geometric center corresponding to each of the clusters based on the determined weighted geometric center calculation formula; wherein the weighted geometric center calculation formula is provided with a weight factor based on the number of rides;

[0031] Substituting the weighted geometric center corresponding to each cluster into a preset optimization problem to obtain a calculation result corresponding to the optimization problem;

[0032] When the calculation result indicates that the optimization problem has a solution, the weighted geometric center corresponding to the best cluster of the optimization problem is determined as the second supplementary information for the ride record to be supplemented.

[0033] As an optional implementation, in the first aspect of the present invention, the weighted geometric center calculation formula is further provided with a center point calculation coefficient;

[0034] The step of calculating the weighted geometric center corresponding to each cluster based on the determined weighted geometric center calculation formula includes:

[0035] For each of the clusters, calculating the ratio of the weight factor corresponding to each of the sample points in the cluster to the total number of rides corresponding to the cluster, as the ratio of the number of rides corresponding to the sample point;

[0036] When the proportion of the number of rides corresponding to any of the sample points is less than or equal to the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the first value;

[0037] When the proportion of the number of rides corresponding to any of the sample points is greater than the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the second value;

[0038] Based on the center point calculation coefficient corresponding to each of the sample points and the determined weighted geometric center calculation formula, the weighted geometric center corresponding to the cluster is calculated.

[0039] As an optional embodiment, in the first aspect of the present invention, analyzing the ride data based on the determined trip chain prediction algorithm to obtain the second supplementary information for the ride record to be supplemented further includes:

[0040] When the calculation result indicates that the optimization problem has no solution, determining whether there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented;

[0041] When it is determined that there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, calculating a first maximum alighting probability site corresponding to the ride record to be supplemented based on a first site prediction formula and the matching ride data;

[0042] When it is determined that there is no matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, obtaining passenger flow data corresponding to the ride schedule of the ride record to be supplemented, and calculating the second maximum alighting probability station corresponding to the ride record to be supplemented based on a second station prediction formula and the passenger flow data;

[0043] The first maximum alighting probability site or the second maximum alighting probability site is determined as the second supplementary information for the ride record to be supplemented.

[0044] A second aspect of the present invention discloses a travel chain supplement device based on user travel data, the device comprising:

[0045] An acquisition module is used to acquire the user's corresponding travel data; the travel data includes at least one single-day travel data, and each single-day travel data includes at least one travel record; each travel record is a bus travel record or a subway travel record;

[0046] A judgment module, configured to judge whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition;

[0047] a determination module configured to determine, when the determination module determines that the ride record to be supplemented meets the combined travel mode condition, a target combined travel mode that matches the ride record to be supplemented according to a preset mode classification condition;

[0048] an analysis module, configured to analyze the ride data based on a travel chain supplementation formula corresponding to the target combined travel mode, and obtain first supplementary information for the ride record to be supplemented;

[0049] The analysis module is further configured to, when the judgment module determines that the ride record to be supplemented does not meet the combined travel mode condition or the first supplementary information indicates that the trip chain supplementation formula has no solution, analyze the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented;

[0050] The supplementing module is used to supplement the travel chain corresponding to the riding data according to the determined travel chain supplementing information; the travel chain supplementing information is the first supplementing information or the second supplementing information.

[0051] As an optional implementation, in the second aspect of the present invention, the specific manner in which the judgment module judges whether the ride record to be supplemented in the ride data satisfies a preset combined travel mode condition includes:

[0052] Determining the single-day travel data containing the travel record to be supplemented in the travel data as the target single-day travel data;

[0053] Determining whether the target single-day ride data belongs to preset single-day ride data; wherein the preset single-day ride data only includes one ride record and no new single-day ride data exists within a preset number of days after the ride record;

[0054] When it is determined that the target single-day ride data belongs to the preset single-day ride data, determining that the ride record to be supplemented does not meet the preset combined travel mode condition;

[0055] When it is determined that the target single-day ride data does not belong to the preset single-day ride data, it is determined that the ride record to be supplemented meets a preset combined travel mode condition.

[0056] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the determination module determines the target combined travel mode that matches the ride record to be supplemented based on a preset mode classification condition includes:

[0057] When the target single-day ride data includes multiple ride records and the multiple ride records are of the same type, determining the target combined travel mode that matches the ride record to be supplemented as the first combined travel mode;

[0058] When the target single-day ride data includes multiple ride records and the first ride record in the target single-day ride data is the bus ride record and the second ride record is the subway ride record, determining that the target combined travel mode that matches the ride record to be supplemented is the second combined travel mode; wherein the first ride record and the second ride record are two adjacent ride records in the target single-day ride data;

[0059] When the target single-day ride data includes at least one ride record and there is newly added single-day ride data within the preset number of days after the target single-day ride data, if the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data do not belong to the same type of ride record, then determining that the target combined travel mode that matches the ride record to be supplemented is the third combined travel mode;

[0060] If the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data belong to the same type of ride record, then the target combined travel mode that matches the ride record to be supplemented is determined to be the fourth combined travel mode.

[0061] As an optional implementation, in the second aspect of the present invention, the travel chain supplement formula corresponding to the target combined travel mode is provided with a maximum transfer distance that the user can bear;

[0062] The specific method of the analysis module analyzing the ride data based on the travel chain supplement formula corresponding to the target combined travel mode to obtain the first supplementary information for the ride record to be supplemented includes:

[0063] When the target combined travel mode is the first combined travel mode, analyzing the target single-day travel data based on the first supplementary formula to obtain a first calculation result corresponding to the first supplementary formula;

[0064] When the target combined travel mode is the second combined travel mode, analyzing the target single-day travel data based on the second supplementary formula to obtain a second calculation result corresponding to the second supplementary formula;

[0065] When the target combined travel mode is the third combined travel mode or the fourth combined travel mode, determining a target supplementary formula corresponding to the target combined travel mode from the first supplementary formula and the second supplementary formula based on a preset formula selection condition, and analyzing the target single-day ride data and the newly added single-day ride data based on the target supplementary formula to obtain a third calculation result corresponding to the target supplementary formula;

[0066] The first supplementary information for the ride record to be supplemented is one of the first calculation result, the second calculation result and the third calculation result.

[0067] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the ride data based on the determined trip chain prediction algorithm and obtains the second supplementary information for the ride record to be supplemented includes:

[0068] Based on the improved DBSCAN algorithm, a clustering operation is performed on the ride data to obtain a travel clustering result; wherein the ride data used for performing the clustering operation includes outlier data and / or noise data; the travel clustering result includes at least one cluster, each of the clusters includes a plurality of sample points, and each of the sample points is one of the boarding / alighting stations or one of the entry / exit stations included in the ride data;

[0069] Calculating the weighted geometric center corresponding to each of the clusters based on the determined weighted geometric center calculation formula; wherein the weighted geometric center calculation formula is provided with a weight factor based on the number of rides;

[0070] Substituting the weighted geometric center corresponding to each cluster into a preset optimization problem to obtain a calculation result corresponding to the optimization problem;

[0071] When the calculation result indicates that the optimization problem has a solution, the weighted geometric center corresponding to the best cluster of the optimization problem is determined as the second supplementary information for the ride record to be supplemented.

[0072] As an optional implementation, in the second aspect of the present invention, the weighted geometric center calculation formula is further provided with a center point calculation coefficient;

[0073] The specific method of calculating the weighted geometric center corresponding to each cluster by the analysis module based on the determined weighted geometric center calculation formula includes:

[0074] For each of the clusters, calculating the ratio of the weight factor corresponding to each of the sample points in the cluster to the total number of rides corresponding to the cluster, as the ratio of the number of rides corresponding to the sample point;

[0075] When the proportion of the number of rides corresponding to any of the sample points is less than or equal to the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the first value;

[0076] When the proportion of the number of rides corresponding to any of the sample points is greater than the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the second value;

[0077] Based on the center point calculation coefficient corresponding to each of the sample points and the determined weighted geometric center calculation formula, the weighted geometric center corresponding to the cluster is calculated.

[0078] As an optional embodiment, in the second aspect of the present invention, the specific method of the analysis module analyzing the ride data based on the determined trip chain prediction algorithm to obtain the second supplementary information for the ride record to be supplemented further includes:

[0079] When the calculation result indicates that the optimization problem has no solution, determining whether there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented;

[0080] When it is determined that there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, calculating a first maximum alighting probability site corresponding to the ride record to be supplemented based on a first site prediction formula and the matching ride data;

[0081] When it is determined that there is no matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, obtaining passenger flow data corresponding to the ride schedule of the ride record to be supplemented, and calculating the second maximum alighting probability station corresponding to the ride record to be supplemented based on a second station prediction formula and the passenger flow data;

[0082] The first maximum alighting probability site or the second maximum alighting probability site is determined as the second supplementary information for the ride record to be supplemented.

[0083] A third aspect of the present invention discloses another device for supplementing a travel chain based on user travel data, the device comprising:

[0084] a memory storing executable program code;

[0085] a processor coupled to the memory;

[0086] The processor calls the executable program code stored in the memory to execute part or all of the steps of the travel chain supplement method based on user riding data disclosed in the first aspect of the present invention.

[0087] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps of the XXX method disclosed in the first aspect of the present invention.

[0088] Compared with the prior art, the present invention has the following beneficial effects:

[0089] In the present invention, the riding data corresponding to the user is obtained; the riding data includes at least one single-day riding data, and each single-day riding data includes at least one riding record; each riding record is a bus riding record or a subway riding record; it is judged whether the riding record to be supplemented in the riding data meets the pre-set combined travel mode condition; when it is judged that the riding record to be supplemented meets the combined travel mode condition, the target combined travel mode that matches the riding record to be supplemented is determined according to the pre-set mode classification condition; based on the travel chain supplement formula corresponding to the target combined travel mode, the riding data is analyzed to obtain the first supplementary information for the riding record to be supplemented; when it is judged that the riding record to be supplemented does not meet the combined travel mode condition or the first supplementary information is used to indicate that the travel chain supplement formula has no solution, based on the determined travel chain prediction algorithm, the riding data is analyzed to obtain the second supplementary information for the riding record to be supplemented; according to the determined travel chain supplementary information, the travel chain corresponding to the riding data is supplemented; the travel chain supplementary information is the first supplementary information or the second supplementary information. It can be seen that the implementation of the present invention can determine whether the ride record to be supplemented in the user's corresponding ride data meets the combined travel mode conditions. If the judgment result is yes, the target combined travel mode that matches the ride record to be supplemented can be determined based on the pre-set mode classification conditions, and the ride data can be analyzed based on the corresponding travel chain supplement formula to obtain the first supplementary information for the ride record to be supplemented. If the judgment result is no or the above-mentioned travel chain supplement formula has no solution, the ride data can be analyzed based on the travel chain prediction algorithm to obtain the corresponding second supplementary information. Then, the travel chain is supplemented based on the first supplementary information or the second supplementary information. It can realize intelligent analysis and supplementation of the user's travel chain based only on bus and / or subway ride data, thereby making the travel chain supplementation method easier to implement. At the same time, it can improve the flexibility and accuracy of the selection of the travel chain supplementation method on the basis of improving the analysis flexibility and accuracy of the ride data, thereby improving the flexibility and accuracy of the supplementation of the travel chain, thereby facilitating the improvement of the accuracy and reliability of the supplemented travel chain, and thereby facilitating the provision of a more accurate data basis for urban transportation planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0091] Figure 1 This is a flow chart of a method for supplementing a travel chain based on user travel data disclosed in an embodiment of the present invention;

[0092] Figure 2 1 is a flow chart of another method for supplementing a travel chain based on user travel data disclosed in an embodiment of the present invention;

[0093] Figure 3 This is a classification diagram of a combined travel mode disclosed in an embodiment of the present invention;

[0094] Figure 4 is a schematic diagram of a travel clustering result disclosed in an embodiment of the present invention;

[0095] Figure 5 1 is a schematic structural diagram of a travel chain supplement device based on user travel data disclosed in an embodiment of the present invention;

[0096] Figure 6 It is a structural schematic diagram of another travel chain supplement device based on user riding data disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0097] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0098] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

[0099] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0100] The present invention discloses a method and device for supplementing a travel chain based on user travel data. The method can determine whether the ride record to be supplemented in the user's corresponding travel data meets the conditions of a combined travel mode. If the judgment result is yes, the method can determine a target combined travel mode that matches the ride record to be supplemented based on a pre-set mode classification condition, and analyze the ride data based on a corresponding travel chain supplement formula to obtain first supplementary information for the ride record to be supplemented. If the judgment result is no or the above-mentioned travel chain supplement formula has no solution, the method can analyze the ride data based on a travel chain prediction algorithm to obtain corresponding second supplementary information. Then, the trip chain is supplemented based on the first supplementary information or the second supplementary information. The method can realize intelligent analysis and supplementation of user travel chains based only on bus and / or subway travel data, thereby making the travel chain supplementation method easier to implement. At the same time, the method can improve the flexibility and accuracy of selecting travel chain supplementation methods on the basis of improving the analysis flexibility and accuracy of travel data, thereby improving the flexibility and accuracy of supplementation of travel chains, thereby improving the accuracy and reliability of the supplemented travel chain, and thus providing a more accurate data foundation for urban transportation planning. The following are detailed descriptions.

[0101] Example 1

[0102] See also Figure 1 , Figure 1 This is a flow chart of a travel chain supplement method based on user travel data disclosed in an embodiment of the present invention. Figure 1 The described method for supplementing a trip chain based on user travel data can be applied to a device for supplementing a trip chain based on user travel data, which may include one of a smart device, a smart terminal, a smart system, and a server, wherein the server may be a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 1 As shown, the travel chain supplement method based on user riding data may include the following operations:

[0103] 101. Obtain the user’s corresponding ride data.

[0104] In an embodiment of the present invention, optionally, the user's corresponding travel data can be obtained from the transaction record corresponding to the transportation transaction method used by the user, which is not limited in the embodiment of the present invention; further optionally, the above-mentioned transportation transaction method includes a transportation card and / or a ride transaction QR code, and may also include other transaction methods, which is not limited in the embodiment of the present invention; among them, exemplarily, the transportation card can be a Yangchengtong card, or it can be other types of transportation cards, which is not limited in the embodiment of the present invention.

[0105] In an embodiment of the present invention, the riding data may include at least one single-day riding data, and each single-day riding data may include at least one riding record; each riding record may be a bus riding record or a subway riding record; wherein, optionally, each bus riding record may include a combination of one or more of the logical card number corresponding to the transportation transaction method used by the user, the vehicle information corresponding to the bus currently ridden by the user, and the bus boarding information, which is not limited in the embodiment of the present invention; further optionally, the above-mentioned vehicle information may include a combination of one or more of the bus license plate number, bus schedule and bus route identification, which is not limited in the embodiment of the present invention; the bus boarding information may include a combination of one or more of the boarding station identification, boarding station location information and boarding time, which is not limited in the embodiment of the present invention; wherein, exemplarily, the location information may be latitude and longitude information, or other types of location information, which is not limited in the embodiment of the present invention; further optionally, the boarding station identification may include The information may include the name of the boarding station and / or the code of the boarding station, which is not limited in the embodiment of the present invention; optionally, each subway ride record may include a combination of one or more of the logical card number, subway entry information, subway exit information and subway transfer information corresponding to the transportation transaction method used by the user, which is not limited in the embodiment of the present invention; further optionally, the subway entry information may include a combination of one or more of the entry station identification, entry station location information, entry gate information and entry time, which is not limited in the embodiment of the present invention; further optionally, the subway exit information may include a combination of one or more of the exit station identification, exit station location information, exit gate information and exit time, which is not limited in the embodiment of the present invention; further optionally, the subway transfer information may include relevant information that the user needs to transfer outside the station or needs to swipe the card to transfer during the subway ride, and may, for example, include at least one of the transfer station identification, transfer station location information and transfer time, which is not limited in the embodiment of the present invention.

[0106] In an embodiment of the present invention, further optionally, step 101 may also include: obtaining bus entry and exit data and / or bus route information, which is not limited in the embodiment of the present invention; wherein the bus entry and exit data includes data of each entry / exit of each bus and bus schedule data, and further optionally, the bus schedule data can be divided into schedules by setting dispatch numbers for the buses, which is not limited in the embodiment of the present invention; further, there is a corresponding relationship between the bus schedules included in the bus riding record and the bus entry and exit data; wherein the bus route information may include the stations included in the bus route and the location information corresponding to each station; wherein the bus route includes an up bus route and / or a down bus route, which is not limited in the embodiment of the present invention.

[0107] In an embodiment of the present invention, further optionally, the method may also include the following operations: preprocessing the acquired riding data, wherein the preprocessing may include a combination of one or more of data deduplication, data cleaning, and matching bus and subway data, which is not limited in the embodiment of the present invention.

[0108] 102. Determine whether the ride record to be supplemented in the ride data meets a pre-set combined travel mode condition.

[0109] In an embodiment of the present invention, the riding record to be supplemented in the riding data can be any riding record that lacks get-off information. For example, the riding record to be supplemented can be a bus riding record or a subway riding record that lacks exit information. This embodiment of the present invention does not limit this.

[0110] In an embodiment of the present invention, when step 102 determines that the ride record to be supplemented meets the conditions of the combined travel mode, that is, when the judgment result of step 102 is yes, the operations of step 103-step 104 are executed; when step 102 determines that the ride record to be supplemented does not meet the conditions of the combined travel mode, that is, when the judgment result of step 102 is no, the operation of step 105 is executed.

[0111] 103. Based on pre-set mode classification conditions, determine the target combined travel mode that matches the ride record to be supplemented.

[0112] In the embodiment of the present invention, the target combined travel mode is one of several combined travel modes corresponding to a preset mode classification condition.

[0113] 104. Based on the travel chain supplement formula corresponding to the target combined travel mode, analyze the ride data to obtain first supplementary information for the ride record to be supplemented.

[0114] In the embodiment of the present invention, when the first supplementary information is used to indicate that the line chain supplementary formula has no solution, the operation of step 105 is performed; when the first supplementary information is used to indicate that the line chain supplementary formula has a solution, the operation of step 106 is performed.

[0115] 105. Based on the determined travel chain prediction algorithm, analyze the ride data to obtain second supplementary information for the ride record to be supplemented.

[0116] 106. Supplement the travel chain corresponding to the ride data based on the determined travel chain supplementary information.

[0117] In an embodiment of the present invention, the trip chain supplementary information may be the first supplementary information or the second supplementary information. For example, when the first supplementary information indicates that the trip chain supplementation formula has a solution, the trip chain may be supplemented based on the first supplementary information. When the second supplementary information exists, the trip chain may be supplemented based on the second supplementary information. This is not limited in this embodiment of the present invention. Optionally, the trip chain supplementary information may include supplementary disembarkation information. Further, the supplementary disembarkation information may be bus disembarkation information or subway exit information. This is not limited in this embodiment of the present invention. Further, the supplementary disembarkation information may include at least the disembarkation station corresponding to the ride record to be supplemented.

[0118] It can be seen that the method described in the embodiment of the present invention can determine whether the ride record to be supplemented in the user's corresponding ride data meets the combined travel mode conditions. If the judgment result is yes, the target combined travel mode that matches the ride record to be supplemented can be determined based on the pre-set mode classification conditions, and the ride data can be analyzed based on the corresponding travel chain supplement formula to obtain first supplementary information for the ride record to be supplemented. If the judgment result is no or the above-mentioned travel chain supplement formula has no solution, the ride data can be analyzed based on the travel chain prediction algorithm to obtain corresponding second supplementary information. Then, the travel chain is supplemented based on the first supplementary information or the second supplementary information. It can realize intelligent analysis and supplementation of user travel chains based only on bus and / or subway ride data, thereby making the travel chain supplementation method easier to implement. At the same time, it can improve the flexibility and accuracy of the selection of travel chain supplementation methods on the basis of improving the analysis flexibility and accuracy of ride data, thereby improving the flexibility and accuracy of travel chain supplementation, thereby improving the accuracy and reliability of the travel chain obtained after supplementation, and thus providing a more accurate data foundation for urban transportation planning.

[0119] In an optional embodiment, determining whether the ride record to be supplemented in the ride data satisfies a preset combined travel mode condition may include the following operations:

[0120] Determine the single-day ride data containing the ride record to be supplemented in the ride data as the target single-day ride data;

[0121] Determine whether the target single-day ride data belongs to the preset single-day ride data; wherein the preset single-day ride data only includes one ride record and there is no new single-day ride data within a preset number of days after the ride record;

[0122] When it is determined that the target single-day ride data belongs to the preset single-day ride data, determining that the ride record to be supplemented does not meet the preset combined travel mode condition;

[0123] When it is determined that the target single-day ride data does not belong to the preset single-day ride data, it is determined that the ride record to be supplemented meets the preset combined travel mode condition.

[0124] Among them, optionally, the above-mentioned preset number of days can be the number of holiday days determined based on the date corresponding to the target single day. For example, the holiday can include one of the weekend, statutory holidays and other holidays, which is not limited in the embodiment of the present invention.

[0125] It can be seen that this optional embodiment can determine whether the target single-day ride data of the ride record to be supplemented belongs to the preset single-day ride data. If the judgment result is yes, it is determined that the ride record to be supplemented does not meet the conditions of the combined travel mode. If the judgment result is no, it is determined that the ride record to be supplemented meets the conditions of the combined travel mode. By analyzing the target single-day ride data and related ride data, the target single-day ride data can be preliminarily classified, thereby improving the accuracy of the judgment on whether the ride record to be supplemented meets the conditions of the combined travel mode, which is conducive to improving the flexibility and accuracy of the selection of travel chain supplement methods.

[0126] In this optional embodiment, optionally, determining the target combined travel mode that matches the ride record to be supplemented based on a pre-set mode classification condition may include the following operations:

[0127] When the target single-day ride data includes multiple ride records and the multiple ride records are all of the same type, determining the target combined travel mode that matches the ride record to be supplemented as the first combined travel mode;

[0128] When the target single-day ride data includes multiple ride records and the first ride record in the target single-day ride data is a bus ride record and the second ride record is a subway ride record, determining that the target combined travel mode that matches the ride record to be supplemented is the second combined travel mode; wherein the first ride record and the second ride record are two adjacent ride records in the target single-day ride data;

[0129] When the target single-day ride data includes at least one ride record and there is new single-day ride data within a preset number of days after the target single-day ride data, if the last ride record included in the target single-day ride data and the first ride record included in the new single-day ride data do not belong to the same type of ride record, then the target combined travel mode that matches the ride record to be supplemented is determined to be the third combined travel mode;

[0130] If the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data belong to the same type of ride records, the target combined travel mode that matches the ride record to be supplemented is determined to be the fourth combined travel mode.

[0131] Exemplarily, when the target single-day ride data includes multiple ride records and all of the multiple ride records are bus ride records, the target combined travel mode is determined to be the first combined travel mode.

[0132] For example, the first ride record may be a ride record to be supplemented, and the first ride record may be a ride record that is adjacent to and precedes the second ride record, which is not limited in this embodiment of the present invention.

[0133] Among them, illustratively, the last ride record included in the target single-day ride data corresponding to the third combined travel mode or the fourth combined travel mode may be the ride record to be supplemented, which is not limited in the embodiment of the present invention.

[0134] For example, see Figure 3 , Figure 3 is a classification diagram of a combined travel mode disclosed in an embodiment of the present invention; Figure 3 As shown, Figure 3 The type one shown (i.e., the first combined travel mode mentioned above) can be a combined travel mode that includes at least K bus ride records in the single-day ride data; type two (i.e., the second combined travel mode mentioned above) can be a combined travel mode that includes at least j+1 ride records in the single-day ride data, wherein the jth record is a bus ride record and the j+1th record is a subway ride record; type three (i.e., the third combined travel mode mentioned above) can be a combined travel mode in which the last ride record in the single-day ride data on the nth day is a bus ride record and the first ride record in the single-day ride data on the n+1th day is a subway ride record; type four (i.e., the fourth combined travel mode mentioned above) can be a combined travel mode in which the last ride record in the single-day ride data on the nth day is a bus ride record and the first ride record in the single-day ride data on the n+1th day is a bus ride record, which is not limited in the embodiments of the present invention.

[0135] It can be seen that this optional embodiment can also classify the combined travel modes corresponding to the ride records to be supplemented according to the number and type of ride records included in the target single-day ride data and the newly added ride data related to the target single-day ride data after determining that the ride records to be supplemented meet the combined travel mode conditions, so as to determine the target combined travel mode that matches the ride records to be supplemented, which can further improve the analysis accuracy and classification accuracy of the ride data, thereby further improving the accuracy of determining the target combined travel mode, and further helping to improve the accuracy of selecting the travel chain supplement method that matches the target combined travel mode in subsequent steps, and further helping to improve the supplement flexibility and accuracy of the travel chain.

[0136] In this optional embodiment, optionally, the travel chain supplement formula corresponding to the target combined travel mode is provided with a maximum transfer distance that the user can bear;

[0137] Optionally, based on the travel chain supplementation formula corresponding to the target combined travel mode, analyzing the ride data to obtain the first supplementary information for the ride record to be supplemented may include the following operations:

[0138] When the target combined travel mode is the first combined travel mode, the target single-day travel data is analyzed based on the first supplementary formula to obtain a first calculation result corresponding to the first supplementary formula;

[0139] When the target combined travel mode is the second combined travel mode, the target single-day travel data is analyzed based on the second supplementary formula to obtain a second calculation result corresponding to the second supplementary formula;

[0140] When the target combined travel mode is the third combined travel mode or the fourth combined travel mode, determining a target supplementary formula corresponding to the target combined travel mode from the first supplementary formula and the second supplementary formula based on a pre-set formula selection condition, and analyzing the target single-day ride data and the newly added single-day ride data based on the target supplementary formula to obtain a third calculation result corresponding to the target supplementary formula;

[0141] The first supplementary information for the ride record to be supplemented is one of the first calculation result, the second calculation result and the third calculation result.

[0142] Optionally, based on the first supplementary formula, the target single-day ride data is analyzed to obtain a first calculation result corresponding to the first supplementary formula, which can be specifically:

[0143] Determine first boarding data corresponding to the ride record to be supplemented and second boarding data corresponding to the next ride record of the ride record to be supplemented; wherein the first boarding data includes a bus schedule, a boarding stop, a boarding time, and a boarding direction, and the second boarding data includes a bus schedule, a boarding stop, and a boarding time;

[0144] Based on the first boarding data and the second boarding data, analyze whether there is a solution that meets the corresponding conditions of the first supplementary formula. If the first supplementary formula has a solution, the solution is determined as the first calculation result; wherein, the first calculation result includes the alighting station information corresponding to the ride record to be supplemented.

[0145] Further optionally, the first supplementary formula may be as follows:

[0146]

[0147] B in formula (1) k+1 It is used to indicate the station location corresponding to the k+1th ride record. Further, It is used to represent the location of the b+i station in the k-th ride record, where b is used to represent that the user boarded the bus at the b-th station on the bus line in the k-th ride record, M is used to represent the total number of stops on the bus line in the k-th ride record, and d is used to represent the maximum transfer distance that the user can bear. When formula (1) has a solution When , the alighting station of the kth ride record is the nearest station b+i associated with the boarding station of the k+1th ride record * .

[0148] The kth ride record is the ride record to be supplemented, the k+1th ride record is the next ride record after the ride record to be supplemented, and the solution of formula (1) is the first calculation result.

[0149] Optionally, based on the second supplementary formula, the target single-day ride data is analyzed to obtain a second calculation result corresponding to the second supplementary formula, which can be specifically:

[0150] Determine first boarding data corresponding to the ride record to be supplemented and second boarding data corresponding to the next ride record of the ride record to be supplemented; wherein the first boarding data includes bus schedule, boarding station, boarding time, and boarding direction, and the second boarding data includes entry station and entry gate information; wherein the ride record to be supplemented is the first ride record and the next ride record of the ride record to be supplemented is the second ride record;

[0151] Determine the nearest entrance gate corresponding to the entrance gate information in the second boarding data as the entrance gate corresponding to the next boarding record to be supplemented, and determine the location information corresponding to the entrance gate;

[0152] Based on the first boarding data, the second boarding data and the location information corresponding to the station entrance, analyze whether there is a solution that meets the corresponding conditions of the second supplementary formula. If the second supplementary formula has a solution, the solution is determined as the second calculation result; wherein, the second calculation result includes the alighting station information corresponding to the ride record to be supplemented.

[0153] Further optionally, the second supplementary formula may be as follows:

[0154]

[0155] S in formula (2) k+1 Used to indicate the entrance location corresponding to the k+1th ride record, It is used to represent the location of the b+i station in the k-th ride record, where b is used to represent that the user boarded the bus at the b-th station on the bus line in the k-th ride record, M is used to represent the total number of stops on the bus line in the k-th ride record, and d is used to represent the maximum transfer distance that the user can bear. When there is a solution to formula (2) When , the alighting station of the kth ride record is the nearest bus stop b+i associated with the subway entry station of the k+1th ride record * .

[0156] Optionally, based on a pre-set formula selection condition, a target supplementary formula corresponding to the target combined travel mode is determined from the first supplementary formula and the second supplementary formula, and based on the target supplementary formula, the target single-day ride data and the newly added single-day ride data are analyzed to obtain a third calculation result corresponding to the target supplementary formula, which can be specifically as follows:

[0157]

[0158] In formula (3), when the k+1th ride record is a bus ride record, α is 1, and when α is 1, the target supplementary formula can be the second supplementary formula; when the k+1th ride record is a subway ride record, α is 0, and when α is 0, the target supplementary formula can be the first supplementary formula; where B k+1,n+j It is used to indicate the location of the bus stop in the k+1th ride record, j days after the kth ride record; S k+1,n+j It is used to indicate the spatial location of the subway entrance for the k+1th trip after an interval of j days; It is used to represent the location of the b+i stop in the last ride record on the nth day, b is used to represent that the user boarded the bus at the bth stop on the bus line in the kth ride record, M is used to represent the total number of stops on the bus line in the kth ride record; d is used to represent the maximum transfer distance that the user can bear. When formula (3) has a solution When , the alighting station of the kth ride record is the nearest station b+i associated with the boarding station / subway entry station of the k+1th ride record * .

[0159] It can be seen that this optional embodiment can also select different travel chain supplement formulas for different combined travel modes to calculate and analyze the target single-day ride data, and obtain the first supplement information for the ride record to be supplemented. On the basis of improving the selection accuracy of the travel chain supplement formula, it can improve the calculation flexibility and accuracy of the travel chain supplement information, which is conducive to improving the supplement flexibility and accuracy of the travel chain; further, it can also screen out the closest station as the get-off station for the ride record to be supplemented based on the boarding station of the adjacent ride record to be supplemented (such as the next ride record). On the basis of improving the accuracy of determining the boarding station as the prediction reference station, it can improve the accuracy of determining the get-off station for the ride record to be supplemented, thereby improving the accuracy of supplementation of the travel chain, and then helping to improve the accuracy of the travel chain.

[0160] Example 2

[0161] See also Figure 2 , Figure 2 This is a flow chart of a method for supplementing a travel chain based on user travel data disclosed in an embodiment of the present invention. Figure 2 The described method for supplementing a trip chain based on user travel data can be applied to a device for supplementing a trip chain based on user travel data, which may include one of a smart device, a smart terminal, a smart system, and a server, wherein the server may be a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 2 As shown, the travel chain supplement method based on user riding data may include the following operations:

[0162] 201. Obtain the user's corresponding ride data.

[0163] In the embodiment of the present invention, the riding data includes at least one single-day riding data, and each single-day riding data includes at least one riding record; each riding record is a bus riding record or a subway riding record.

[0164] 202. Determine whether the ride record to be supplemented in the ride data meets a pre-set combined travel mode condition.

[0165] In an embodiment of the present invention, when step 202 determines that the ride record to be supplemented meets the conditions of the combined travel mode, that is, when the judgment result of step 202 is yes, the operations of steps 203 to 204 are executed; when step 202 determines that the ride record to be supplemented does not meet the conditions of the combined travel mode, that is, when the judgment result of step 202 is no, the operations of steps 205 to 208 are executed.

[0166] 203. According to the pre-set mode classification conditions, determine the target combined travel mode that matches the ride record to be supplemented.

[0167] 204. Based on the travel chain supplement formula corresponding to the target combined travel mode, analyze the ride data to obtain first supplementary information for the ride record to be supplemented.

[0168] In the embodiment of the present invention, when the first supplementary information is used to indicate that the line chain supplementary formula has no solution, the operations of steps 205 to 208 are performed; when the first supplementary information is used to indicate that the line chain supplementary formula has a solution, the operation of step 209 is performed.

[0169] 205. Based on the improved DBSCAN algorithm, clustering operation is performed on the ride data to obtain the travel clustering results.

[0170] In an embodiment of the present invention, the riding data used to perform clustering operations include outlier data and / or noise data; it should be noted that the traditional DBSCAN algorithm tends to exclude noise points and outliers, but in the scenario of public transportation, the behavioral characteristics of residents taking public transportation usually have specific reasons and will not occur without reason, so these data that are regarded as abnormal or noise may actually constitute an important link in the travel chain, and therefore these data need to be retained in the improved DBSCAN algorithm.

[0171] In the embodiment of the present invention, the travel clustering result includes at least one cluster, each cluster includes multiple sample points, and each sample point is one of the boarding / alighting stations or one of the entry / exit stations included in the ride data.

[0172] In the embodiment of the present invention, optionally, the formula used by the improved DBSCAN algorithm may be as follows:

[0173] N ε (p)={q∈D,dist(p,q)≤ε} (4)

[0174] N ε (p)≥minPts (5)

[0175] (p, q) are two sample points in the ride data, and ε is the maximum correlation distance between the two sample points. The minimum value of minPts can be obtained from the dimension D of the ride data, i.e., minPts ≥ D + 1. For example, in this embodiment of the present invention, minPts = 3. ε can be determined based on the distribution distance between bus stops and subway stations. For example, in this embodiment of the present invention, ε = 500.

[0176] In the embodiment of the present invention, for example, please refer to Figure 4 , Figure 4Schematic diagram of a travel clustering result disclosed in an embodiment of the present invention; for example, the user's ride data within one year can be selected, duplicate ride records in the ride data are first removed, and then the improved DBSCAN algorithm is used for clustering. The obtained travel clustering result can be as follows: Figure 4 As shown, Figure 4 Sample points of the same color belong to the same cluster, and black sample points are noise data or abnormal data.

[0177] 206. Calculate the weighted geometric center corresponding to each cluster based on the determined weighted geometric center calculation formula.

[0178] In the embodiment of the present invention, the weighted geometric center calculation formula is provided with a weight factor based on the number of rides, wherein the weighted geometric center corresponding to each cluster is one of the sample points of the cluster.

[0179] 207. Substitute the weighted geometric center corresponding to each cluster into a preset optimization problem to obtain a calculation result corresponding to the optimization problem.

[0180] In the embodiment of the present invention, optionally, the optimization problem can be as follows:

[0181]

[0182] Formula (8) is a constraint condition, the purpose of which is to find all clusters that satisfy Formula (8); where Z is the number of clusters contained in the travel clustering result, is the weighted geometric center corresponding to cluster z.

[0183] Formula (7) is the optimal value of the solution set that satisfies the constraint (8), where T is the number of clusters that satisfy the constraint (T≤Z), n t is the number of sample points contained in cluster t, is the alighting station with the minimum distance from cluster t when formula (8) is satisfied. Where Ξ is a constant. By solving the optimization problem, the optimal cluster t can be obtained. * The weighted geometric center of So you can get the best alighting point

[0184] 208. When the calculation result indicates that the optimization problem has a solution, the weighted geometric center corresponding to the best cluster of the optimization problem is determined as the second supplementary information for the ride record to be supplemented.

[0185] In the embodiment of the present invention, specifically, step 208 may be: determining the station pointed to by the weighted geometric center corresponding to the best cluster of the optimization problem as the alighting station corresponding to the ride record to be supplemented.

[0186] 209. Supplement the travel chain corresponding to the ride data based on the determined travel chain supplementary information.

[0187] In the embodiment of the present invention, the travel chain supplementary information is the first supplementary information or the second supplementary information.

[0188] In the embodiment of the present invention, for other detailed descriptions of steps 201 to 204 and step 209, please refer to the detailed description of steps 101 to 104 and step 106 in the first embodiment, which will not be repeated in the embodiment of the present invention.

[0189] It can be seen that the method described in the embodiment of the present invention can determine whether the ride record to be supplemented in the user's corresponding ride data meets the combined travel mode conditions. If the judgment result is yes, the target combined travel mode that matches the ride record to be supplemented can be determined based on the pre-set mode classification conditions, and the ride data can be analyzed based on the corresponding travel chain supplement formula to obtain first supplementary information for the ride record to be supplemented. If the judgment result is no or the above-mentioned travel chain supplement formula has no solution, the ride data can be analyzed based on the travel chain prediction algorithm to obtain corresponding second supplementary information. Then, the travel chain is supplemented based on the first supplementary information or the second supplementary information. It can realize intelligent analysis and supplementation of user travel chains based only on bus and / or subway ride data, thereby making the travel chain supplementation method easier to implement. At the same time, it can improve the flexibility and accuracy of the selection of travel chain supplementation methods on the basis of improving the analysis flexibility and accuracy of ride data, thereby improving the flexibility and accuracy of travel chain supplementation, thereby improving the accuracy and reliability of the travel chain obtained after supplementation, and thus providing a more accurate data foundation for urban transportation planning. In addition, after determining that the ride record to be supplemented does not meet the conditions of the combined travel mode, the ride data can be clustered by the improved DBSCAN algorithm to obtain the travel clustering results, and based on the weighted geometric center calculation formula, the weighted geometric center corresponding to each cluster in the travel clustering results is calculated, and then the weighted geometric center of each cluster is substituted into the optimization problem. If the optimization problem has a solution, the weighted geometric center of the best cluster corresponding to the unlocking of the optimization problem is used as the supplemented get-off station, that is, determined as the second supplementary information. By adopting the improved DBSCAN algorithm, the ride data that is considered abnormal or noisy can be retained. The data of the sound can be used to perform more accurate clustering operations on the ride data, thereby improving the accuracy of the travel clustering results; and since the number of rides is an important factor in the travel chain, by using the weight factor based on the number of rides to calculate the weighted geometric center of each cluster, the weighted geometric center associated with the number of rides is calculated, which can make the calculated weighted geometric center more relevant to the user's travel and riding habits, thereby further improving the accuracy of the weighted geometric center, which is beneficial to improving the accuracy of solving the optimization problem, and further beneficial to improving the accuracy of determining the supplementary information of the travel chain, so as to further improve the supplementary accuracy of the travel chain.

[0190] In an optional embodiment, the weighted geometric center calculation formula is further provided with a center point calculation coefficient.

[0191] Optionally, based on the determined weighted geometric center calculation formula, the weighted geometric center corresponding to each cluster is calculated, including:

[0192] For each cluster, calculate the ratio of the weight factor corresponding to each sample point in the cluster to the total number of rides corresponding to the cluster, as the proportion of the number of rides corresponding to the sample point;

[0193] When the proportion of the number of rides corresponding to any sample point is less than or equal to the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the first value;

[0194] When the proportion of the number of rides corresponding to any sample point is greater than the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the second value;

[0195] Based on the center point calculation coefficient corresponding to each sample point and the determined weighted geometric center calculation formula, the weighted geometric center corresponding to the cluster is calculated.

[0196] The weight factor corresponding to each sample point is used to represent the number of rides a user has taken at the station corresponding to the sample point; further, the number of rides may be the number of boardings and / or the number of alightings, which is not limited in the embodiment of the present invention.

[0197] Optionally, the weighted geometric center calculation formula can be as follows:

[0198]

[0199] Among them, n is the number of samples in the cluster, w i is the weight factor of sample point i, (x i ,y i ) is the station location coordinate of sample point i. When the weight factor of sample i, that is, the proportion of the number of rides to the total number of sample rides in the cluster, When , the center point calculation coefficient is taken as Λ i =1, otherwise the center point calculation coefficient is Λ i =2.

[0200] Furthermore, when the proportion of rides corresponding to the sample point is less than or equal to the preset proportion (such as 1% above), that is, Λ i =1, the sample point can be determined as a boundary point; when the proportion of the number of rides corresponding to any sample point is greater than the preset proportion, that is, Λ i =2, the sample point can be determined as the core point, that is, the weighted geometric center of the cluster.

[0201] It can be seen that this optional embodiment can, for each cluster, if the proportion of the number of rides corresponding to each sample point in the total number of rides corresponding to the cluster is less than or equal to the preset proportion, then the value of the center point calculation coefficient corresponding to the sample point is determined as the first value; otherwise, the value of the center point calculation coefficient is determined as the second value, and then the weighted geometric center is calculated based on the corresponding center point calculation coefficient and the weighted geometric center calculation formula, which can improve the accuracy of the analysis of the number of rides of the user at each station, thereby improving the accuracy of the calculation of the weighted geometric center corresponding to each cluster, and thus helping to improve the accuracy of the subsequent solution to the optimization problem.

[0202] In this optional embodiment, optionally, based on the determined trip chain prediction algorithm, analyzing the ride data to obtain the second supplementary information for the ride record to be supplemented may further include the following operations:

[0203] When the calculation result indicates that the optimization problem has no solution, it is determined whether there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented;

[0204] When it is determined that there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, calculating the first maximum alighting probability site corresponding to the ride record to be supplemented based on the first site prediction formula and the matching ride data;

[0205] When it is determined that there is no matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, obtaining passenger flow data corresponding to the ride schedule of the ride record to be supplemented, and calculating the second maximum alighting probability station corresponding to the ride record to be supplemented based on the second station prediction formula and the passenger flow data;

[0206] The first maximum getting-off probability site or the second maximum getting-off probability site is determined as the second supplementary information for the ride record to be supplemented.

[0207] Optionally, the matching ride data that matches the ride schedule of the ride record to be supplemented may include ride records at other times that are the same as the ride schedule, which is not limited in this embodiment of the present invention.

[0208] Optionally, the passenger flow data may include boarding passenger flow data and / or alighting passenger flow data corresponding to each station in the route corresponding to the bus trip, which is not limited in the embodiment of the present invention.

[0209] It should be noted that the optimization problem may not be able to find a suitable solution because the fixed value of Ξ is too small.

[0210] Optionally, the first site prediction formula may be as follows:

[0211]

[0212] Here, b is used to indicate that the user boarded the bus at the bth stop on the bus route in the kth ride record, and M is used to indicate the total number of stops on the bus route taken by the user in the kth ride record. Used to indicate the number of times a user gets off at the downstream station b+i of station b on the route in the ride data. Used to indicate that the user is at downstream site b+i * The probability of getting off is the highest. is the location of the next stop, i.e. the downstream stop b+i * is the first station with the highest probability of getting off.

[0213] Optionally, the second site prediction formula may be as follows:

[0214]

[0215] in, It is used to represent all boarding passenger flows and existing passenger flows at the b-th station of the bus line taken by the user in the k-th riding record. It is used to represent the passenger flow getting off at the downstream station b+j of the b-th station, and the passenger flow getting off is only for The passenger flow getting off the bus has nothing to do with the passenger flow getting on the bus midway. Used to indicate that the user is at downstream site b+i * The probability of getting off is the highest. is the location of the next stop, i.e. the downstream stop b+i * It is the second highest probability station for getting off.

[0216] It can be seen that this optional embodiment can also calculate the first maximum get-off probability site based on the first site prediction formula and the matching ride data when there is no solution to the optimization problem. If it is determined that there is matching ride data in the ride data that matches the ride record to be supplemented, otherwise, the second maximum get-off probability site is calculated based on the second site prediction formula and the passenger flow data, so as to determine the site obtained by the above calculation as the second supplementary information. When the aforementioned method cannot estimate the user's get-off site at the ride record to be supplemented, the probability of the user getting off at each site can be estimated by analyzing the ride data of the same schedule or the passenger flow data in the ride data. On the basis of improving the flexibility of selecting the travel chain supplement method, the accuracy of estimating the user's get-off probability at the ride record to be supplemented can be improved, thereby improving the screening accuracy of the site with the maximum get-off probability, which is beneficial to improving the accuracy of determining the travel chain supplement information, and thus is beneficial to improving the supplement flexibility and accuracy of the travel chain.

[0217] In an embodiment of the present invention, for example, simulation tests show that the accuracy of the travel chain obtained by implementing the travel chain supplementation method based on user riding data disclosed in the present invention is improved by 10% and 6% respectively compared with the accuracy of the travel chain supplemented by the non-density clustering algorithm or the standard DBSCAN algorithm.

[0218] Example 3

[0219] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a travel chain supplement device based on user travel data disclosed in an embodiment of the present invention. Figure 5 The described travel chain supplement device based on user travel data may include one of a smart device, a smart terminal, a smart system and a server, wherein the server may be a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 5 As shown, the travel chain supplement device based on user riding data may include:

[0220] The acquisition module 301 is used to obtain the user's corresponding travel data; the travel data includes at least one single-day travel data, and each single-day travel data includes at least one travel record; each travel record is a bus travel record or a subway travel record;

[0221] The judgment module 302 is used to judge whether the ride record to be supplemented in the ride data meets the preset combined travel mode condition;

[0222] The determination module 303 is configured to determine a target combined travel mode that matches the ride record to be supplemented based on a preset mode classification condition when the determination module 302 determines that the ride record to be supplemented meets the combined travel mode condition;

[0223] An analysis module 304 is configured to analyze the ride data based on a travel chain supplementation formula corresponding to the target combined travel mode to obtain first supplementary information for the ride record to be supplemented;

[0224] The analysis module 304 is further configured to analyze the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented, when the judgment module 302 determines that the ride record to be supplemented does not meet the combined travel mode condition or the first supplementary information indicates that there is no solution to the trip chain supplementation formula;

[0225] The supplement module 305 is used to supplement the trip chain corresponding to the ride data according to the determined trip chain supplement information; the trip chain supplement information is the first supplement information or the second supplement information.

[0226] It can be seen that the device described in the embodiment of the present invention can determine whether the ride record to be supplemented in the ride data corresponding to the user meets the combined travel mode conditions. If the judgment result is yes, the target combined travel mode that matches the ride record to be supplemented can be determined based on the pre-set mode classification conditions, and the ride data can be analyzed based on the corresponding travel chain supplement formula to obtain first supplementary information for the ride record to be supplemented. If the judgment result is no or the above-mentioned travel chain supplement formula has no solution, the ride data can be analyzed based on the travel chain prediction algorithm to obtain corresponding second supplementary information. Then, the travel chain is supplemented based on the first supplementary information or the second supplementary information. It can realize intelligent analysis and supplementation of user travel chains based only on bus and / or subway ride data, thereby making the travel chain supplementation method easier to implement. At the same time, it can improve the flexibility and accuracy of the selection of travel chain supplementation methods on the basis of improving the analysis flexibility and accuracy of ride data, thereby improving the flexibility and accuracy of travel chain supplementation, thereby facilitating the improvement of the accuracy and reliability of the supplemented travel chain, and thereby facilitating the provision of a more accurate data basis for urban transportation planning.

[0227] In an optional embodiment, the specific manner in which the determination module 302 determines whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition may include:

[0228] Determine the single-day ride data containing the ride record to be supplemented in the ride data as the target single-day ride data;

[0229] Determine whether the target single-day ride data belongs to the preset single-day ride data; wherein the preset single-day ride data only includes one ride record and there is no new single-day ride data within a preset number of days after the ride record;

[0230] When it is determined that the target single-day ride data belongs to the preset single-day ride data, determining that the ride record to be supplemented does not meet the preset combined travel mode condition;

[0231] When it is determined that the target single-day ride data does not belong to the preset single-day ride data, it is determined that the ride record to be supplemented meets the preset combined travel mode condition.

[0232] It can be seen that the device described in the implementation of this optional embodiment is capable of determining whether the target single-day ride data in which the ride record to be supplemented is located belongs to the preset single-day ride data. If the judgment result is yes, it is determined that the ride record to be supplemented does not meet the conditions of the combined travel mode. If the judgment result is no, it is determined that the ride record to be supplemented meets the conditions of the combined travel mode. By analyzing the target single-day ride data and related ride data, the target single-day ride data can be preliminarily classified, thereby improving the accuracy of the judgment on whether the ride record to be supplemented meets the conditions of the combined travel mode, which is conducive to improving the flexibility and accuracy of the selection of travel chain supplement methods.

[0233] In this optional embodiment, the specific manner in which the determination module 303 determines the target combined travel mode that matches the ride record to be supplemented according to the pre-set mode classification condition may include:

[0234] When the target single-day ride data includes multiple ride records and the multiple ride records are all of the same type, determining the target combined travel mode that matches the ride record to be supplemented as the first combined travel mode;

[0235] When the target single-day ride data includes multiple ride records and the first ride record in the target single-day ride data is a bus ride record and the second ride record is a subway ride record, determining that the target combined travel mode that matches the ride record to be supplemented is the second combined travel mode; wherein the first ride record and the second ride record are two adjacent ride records in the target single-day ride data;

[0236] When the target single-day ride data includes at least one ride record and there is new single-day ride data within a preset number of days after the target single-day ride data, if the last ride record included in the target single-day ride data and the first ride record included in the new single-day ride data do not belong to the same type of ride record, then the target combined travel mode that matches the ride record to be supplemented is determined to be the third combined travel mode;

[0237] If the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data belong to the same type of ride records, the target combined travel mode that matches the ride record to be supplemented is determined to be the fourth combined travel mode.

[0238] It can be seen that the device described in the implementation of this optional embodiment can also classify the combined travel modes corresponding to the ride records to be supplemented according to the number and type of ride records included in the target single-day ride data and the newly added ride data related to the target single-day ride data after determining that the ride records to be supplemented meet the combined travel mode conditions, thereby determining the target combined travel mode that matches the ride records to be supplemented, which can further improve the analysis accuracy and classification accuracy of the ride data, thereby further improving the accuracy of determining the target combined travel mode, and further helping to improve the accuracy of selecting the travel chain supplement method that matches the target combined travel mode in subsequent steps, and further helping to improve the supplement flexibility and accuracy of the travel chain.

[0239] In this optional embodiment, optionally, the travel chain supplement formula corresponding to the target combined travel mode is provided with a maximum transfer distance that the user can bear;

[0240] The specific method of the analysis module 304 analyzing the ride data based on the travel chain supplement formula corresponding to the target combined travel mode to obtain the first supplementary information for the ride record to be supplemented may include:

[0241] When the target combined travel mode is the first combined travel mode, the target single-day travel data is analyzed based on the first supplementary formula to obtain a first calculation result corresponding to the first supplementary formula;

[0242] When the target combined travel mode is the second combined travel mode, the target single-day travel data is analyzed based on the second supplementary formula to obtain a second calculation result corresponding to the second supplementary formula;

[0243] When the target combined travel mode is the third combined travel mode or the fourth combined travel mode, determining a target supplementary formula corresponding to the target combined travel mode from the first supplementary formula and the second supplementary formula based on a pre-set formula selection condition, and analyzing the target single-day ride data and the newly added single-day ride data based on the target supplementary formula to obtain a third calculation result corresponding to the target supplementary formula;

[0244] The first supplementary information for the ride record to be supplemented is one of the first calculation result, the second calculation result and the third calculation result.

[0245] It can be seen that the device described in the implementation of this optional embodiment can also select different travel chain supplement formulas for different combined travel modes to calculate and analyze the target single-day ride data, and obtain the first supplementary information for the ride record to be supplemented. On the basis of improving the selection accuracy of the travel chain supplement formula, it can improve the calculation flexibility and accuracy of the travel chain supplement information, which is conducive to improving the supplement flexibility and accuracy of the travel chain; further, it can also screen out the closest station as the alighting station of the ride record to be supplemented based on the boarding station of the adjacent ride record to be supplemented (such as the next ride record). On the basis of improving the accuracy of determining the boarding station as the prediction reference station, it can improve the accuracy of determining the alighting station of the ride record to be supplemented, thereby improving the supplement accuracy of the travel chain, and then helping to improve the accuracy of the travel chain.

[0246] In another optional embodiment, the analysis module 304 analyzes the ride data based on the determined trip chain prediction algorithm to obtain the second supplementary information for the ride record to be supplemented. The specific method may include:

[0247] Based on the improved DBSCAN algorithm, a clustering operation is performed on the ride data to obtain a trip clustering result; wherein the ride data used for performing the clustering operation includes outlier data and / or noise data; the trip clustering result includes at least one cluster, each cluster includes multiple sample points, and each sample point is one of the boarding / alighting stations or one of the entry / exit stations included in the ride data;

[0248] Calculate the weighted geometric center corresponding to each cluster based on the determined weighted geometric center calculation formula; wherein the weighted geometric center calculation formula is provided with a weight factor based on the number of rides;

[0249] Substitute the weighted geometric center corresponding to each cluster into the pre-set optimization problem to obtain the calculation result corresponding to the optimization problem;

[0250] When the calculation result is used to indicate that the optimization problem has a solution, the weighted geometric center corresponding to the best cluster of the optimization problem is determined as the second supplementary information for the ride record to be supplemented.

[0251] It can be seen that the device described in the implementation of this optional embodiment can, after determining that the ride record to be supplemented does not meet the conditions of the combined travel mode, cluster the ride data through the improved DBSCAN algorithm to obtain the travel clustering result, and calculate the weighted geometric center corresponding to each cluster in the travel clustering result based on the weighted geometric center calculation formula, and then substitute the weighted geometric center of each cluster into the optimization problem. If the optimization problem has a solution, the weighted geometric center of the best cluster corresponding to the unlocking of the optimization problem is used as the supplemented get-off site, that is, determined as the second supplementary information. By adopting the improved DBSCAN algorithm, the ride data can be retained. Data that is regarded as abnormal or noisy can be clustered more accurately, thereby improving the accuracy of travel clustering results; and, since the number of rides is an important factor in the travel chain, the weighted geometric center of each cluster is calculated by using a weight factor based on the number of rides, and the weighted geometric center associated with the number of rides is calculated. This can make the calculated weighted geometric center more relevant to the user's travel habits, thereby further improving the accuracy of the weighted geometric center, which is beneficial to improving the accuracy of solving the optimization problem, and further beneficial to improving the accuracy of determining the supplementary information of the travel chain, so as to further improve the supplementary accuracy of the travel chain.

[0252] In this optional embodiment, optionally, the weighted geometric center calculation formula is further provided with a center point calculation coefficient;

[0253] The specific method of calculating the weighted geometric center corresponding to each cluster by the analysis module 304 based on the determined weighted geometric center calculation formula may include:

[0254] For each cluster, calculate the ratio of the weight factor corresponding to each sample point in the cluster to the total number of rides corresponding to the cluster, as the proportion of the number of rides corresponding to the sample point;

[0255] When the proportion of the number of rides corresponding to any sample point is less than or equal to the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the first value;

[0256] When the proportion of the number of rides corresponding to any sample point is greater than the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the second value;

[0257] Based on the center point calculation coefficient corresponding to each sample point and the determined weighted geometric center calculation formula, the weighted geometric center corresponding to the cluster is calculated.

[0258] It can be seen that the device described in the implementation of this optional embodiment can also, for each cluster, if the proportion of the number of rides corresponding to each sample point in the total number of rides corresponding to the cluster is less than or equal to the preset proportion, then the value of the center point calculation coefficient corresponding to the sample point is determined as the first value; otherwise, the value of the center point calculation coefficient is determined as the second value, and then the weighted geometric center is calculated based on the corresponding center point calculation coefficient and the weighted geometric center calculation formula, which can improve the accuracy of the analysis of the number of rides of the user at each station, thereby improving the calculation accuracy of the weighted geometric center corresponding to each cluster, and thus helping to improve the accuracy of the subsequent solution to the optimization problem.

[0259] In this optional embodiment, the analysis module 304 may analyze the ride data based on the determined trip chain prediction algorithm to obtain the second supplementary information for the ride record to be supplemented. The specific method may also include:

[0260] When the calculation result indicates that the optimization problem has no solution, it is determined whether there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented;

[0261] When it is determined that there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, calculating the first maximum alighting probability site corresponding to the ride record to be supplemented based on the first site prediction formula and the matching ride data;

[0262] When it is determined that there is no matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, obtaining passenger flow data corresponding to the ride schedule of the ride record to be supplemented, and calculating the second maximum alighting probability station corresponding to the ride record to be supplemented based on the second station prediction formula and the passenger flow data;

[0263] The first maximum getting-off probability site or the second maximum getting-off probability site is determined as the second supplementary information for the ride record to be supplemented.

[0264] It can be seen that the device described in the implementation of this optional embodiment can also calculate the first maximum get-off probability site based on the first site prediction formula and the matching ride data when there is no solution to the optimization problem. If it is determined that there is matching ride data in the ride data that matches the ride record to be supplemented, otherwise, the second maximum get-off probability site is calculated based on the second site prediction formula and the passenger flow data, so as to determine the site obtained by the above calculation as the second supplementary information. When the aforementioned method cannot estimate the user's get-off site in the ride record to be supplemented, the user's get-off probability at each site can be estimated by analyzing the ride data of the same schedule or the passenger flow data in the ride data. On the basis of improving the flexibility of selecting the travel chain supplement method, the accuracy of estimating the user's get-off probability in the ride record to be supplemented can be improved, thereby improving the screening accuracy of the site with the maximum get-off probability, which is beneficial to improving the accuracy of determining the travel chain supplement information, and thereby improving the supplement flexibility and accuracy of the travel chain.

[0265] Example 4

[0266] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of another travel chain supplement device based on user travel data disclosed in an embodiment of the present invention. Figure 6 As shown, the travel chain supplement device based on user riding data may include:

[0267] A memory 401 storing executable program code;

[0268] a processor 402 coupled to the memory 401;

[0269] The processor 402 calls the executable program code stored in the memory 401 to execute part or all of the steps of the travel chain supplement method based on user travel data described in the first embodiment of the present invention or the second embodiment of the present invention.

[0270] Example 5

[0271] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the travel chain supplement method based on user ride data described in Example 1 or Example 2 of the present invention.

[0272] Example 6

[0273] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute some or all of the steps in the travel chain supplement method based on user ride data described in Example 1 or Example 2.

[0274] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0275] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0276] Finally, it should be noted that the travel chain supplement method and device based on user riding data disclosed in the embodiment of the present invention is only a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A travel chain supplement method based on user travel data, characterized in that: The method comprises: Obtaining ride data corresponding to the user; the ride data includes at least one single-day ride data, and each single-day ride data includes at least one ride record; each ride record is a bus ride record or a subway ride record; Determining whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition; When it is determined that the ride record to be supplemented meets the combined travel mode condition, determining a target combined travel mode that matches the ride record to be supplemented based on a pre-set mode classification condition; analyzing the ride data based on a travel chain supplement formula corresponding to the target combined travel mode to obtain first supplementary information for the ride record to be supplemented; When it is determined that the ride record to be supplemented does not satisfy the combined travel mode condition or the first supplementary information indicates that the trip chain supplementation formula has no solution, analyzing the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented; The travel chain corresponding to the riding data is supplemented according to the determined travel chain supplementary information; the travel chain supplementary information is the first supplementary information or the second supplementary information.

2. The method for supplementing a travel chain based on user travel data according to claim 1, characterized in that: The determining whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition includes: Determining the single-day travel data containing the travel record to be supplemented in the travel data as the target single-day travel data; Determining whether the target single-day ride data belongs to preset single-day ride data; wherein the preset single-day ride data only includes one ride record and no new single-day ride data exists within a preset number of days after the ride record; When it is determined that the target single-day ride data belongs to the preset single-day ride data, determining that the ride record to be supplemented does not meet the preset combined travel mode condition; When it is determined that the target single-day ride data does not belong to the preset single-day ride data, it is determined that the ride record to be supplemented meets a preset combined travel mode condition.

3. The method for supplementing a travel chain based on user travel data according to claim 2, characterized in that: The step of determining a target combined travel mode that matches the ride record to be supplemented based on a preset mode classification condition includes: When the target single-day ride data includes multiple ride records and the multiple ride records are of the same type, determining the target combined travel mode that matches the ride record to be supplemented as the first combined travel mode; When the target single-day ride data includes multiple ride records and the first ride record in the target single-day ride data is the bus ride record and the second ride record is the subway ride record, determining that the target combined travel mode that matches the ride record to be supplemented is the second combined travel mode; wherein the first ride record and the second ride record are two adjacent ride records in the target single-day ride data; When the target single-day ride data includes at least one ride record and there is newly added single-day ride data within the preset number of days after the target single-day ride data, if the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data do not belong to the same type of ride record, then determining that the target combined travel mode that matches the ride record to be supplemented is the third combined travel mode; If the last ride record included in the target single-day ride data and the first ride record included in the newly added single-day ride data belong to the same type of ride record, then the target combined travel mode that matches the ride record to be supplemented is determined to be the fourth combined travel mode.

4. The method for supplementing a travel chain based on user travel data according to claim 3, characterized in that: The travel chain supplementary formula corresponding to the target combined travel mode is provided with the maximum transfer distance that the user can bear; The method of analyzing the ride data based on the travel chain supplement formula corresponding to the target combined travel mode to obtain the first supplementary information for the ride record to be supplemented includes: When the target combined travel mode is the first combined travel mode, analyzing the target single-day travel data based on the first supplementary formula to obtain a first calculation result corresponding to the first supplementary formula; When the target combined travel mode is the second combined travel mode, analyzing the target single-day travel data based on the second supplementary formula to obtain a second calculation result corresponding to the second supplementary formula; When the target combined travel mode is the third combined travel mode or the fourth combined travel mode, determining a target supplementary formula corresponding to the target combined travel mode from the first supplementary formula and the second supplementary formula based on a preset formula selection condition, and analyzing the target single-day ride data and the newly added single-day ride data based on the target supplementary formula to obtain a third calculation result corresponding to the target supplementary formula; The first supplementary information for the ride record to be supplemented is one of the first calculation result, the second calculation result and the third calculation result.

5. The method for supplementing a travel chain based on user travel data according to any one of claims 1 to 4, characterized in that: The step of analyzing the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented includes: Based on the improved DBSCAN algorithm, a clustering operation is performed on the ride data to obtain a travel clustering result; wherein the ride data used for performing the clustering operation includes outlier data and / or noise data; the travel clustering result includes at least one cluster, each of the clusters includes a plurality of sample points, and each of the sample points is one of the boarding / alighting stations or one of the entry / exit stations included in the ride data; Calculating the weighted geometric center corresponding to each of the clusters based on the determined weighted geometric center calculation formula; wherein the weighted geometric center calculation formula is provided with a weight factor based on the number of rides; Substituting the weighted geometric center corresponding to each cluster into a preset optimization problem to obtain a calculation result corresponding to the optimization problem; When the calculation result indicates that the optimization problem has a solution, the weighted geometric center corresponding to the best cluster of the optimization problem is determined as the second supplementary information for the ride record to be supplemented.

6. The method for supplementing a travel chain based on user travel data according to claim 5, characterized in that: The weighted geometric center calculation formula is also provided with a center point calculation coefficient; The step of calculating the weighted geometric center corresponding to each cluster based on the determined weighted geometric center calculation formula includes: For each of the clusters, calculating the ratio of the weight factor corresponding to each of the sample points in the cluster to the total number of rides corresponding to the cluster, as the ratio of the number of rides corresponding to the sample point; When the proportion of the number of rides corresponding to any of the sample points is less than or equal to the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the first value; When the proportion of the number of rides corresponding to any of the sample points is greater than the preset proportion, the value of the center point calculation coefficient corresponding to the sample point is determined as the second value; Based on the center point calculation coefficient corresponding to each of the sample points and the determined weighted geometric center calculation formula, the weighted geometric center corresponding to the cluster is calculated.

7. The method for supplementing a travel chain based on user travel data according to claim 5, characterized in that: The step of analyzing the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented further includes: When the calculation result indicates that the optimization problem has no solution, determining whether there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented; When it is determined that there is matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, calculating a first maximum alighting probability site corresponding to the ride record to be supplemented based on a first site prediction formula and the matching ride data; When it is determined that there is no matching ride data in the ride data that matches the ride schedule of the ride record to be supplemented, obtaining passenger flow data corresponding to the ride schedule of the ride record to be supplemented, and calculating the second maximum alighting probability station corresponding to the ride record to be supplemented based on a second station prediction formula and the passenger flow data; The first maximum alighting probability site or the second maximum alighting probability site is determined as the second supplementary information for the ride record to be supplemented.

8. A travel chain supplement device based on user travel data, characterized in that: The device comprises: An acquisition module is used to acquire the user's corresponding travel data; the travel data includes at least one single-day travel data, and each single-day travel data includes at least one travel record; each travel record is a bus travel record or a subway travel record; A judgment module, configured to judge whether the to-be-supplemented ride record in the ride data satisfies a preset combined travel mode condition; a determination module configured to determine, when the determination module determines that the ride record to be supplemented meets the combined travel mode condition, a target combined travel mode that matches the ride record to be supplemented according to a preset mode classification condition; an analysis module, configured to analyze the ride data based on a travel chain supplementation formula corresponding to the target combined travel mode, and obtain first supplementary information for the ride record to be supplemented; The analysis module is further configured to, when the judgment module determines that the ride record to be supplemented does not meet the combined travel mode condition or the first supplementary information indicates that the trip chain supplementation formula has no solution, analyze the ride data based on the determined trip chain prediction algorithm to obtain second supplementary information for the ride record to be supplemented; The supplementing module is used to supplement the travel chain corresponding to the riding data according to the determined travel chain supplementing information; the travel chain supplementing information is the first supplementing information or the second supplementing information.

9. A travel chain supplement device based on user travel data, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the travel chain supplement method based on user riding data as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer instructions, which, when called, are used to execute the travel chain supplement method based on user riding data as described in any one of claims 1 to 7.

Images