Travel discount customer group identification method and system, and computer program product

Abstract

The invention provides a travel discount customer group identification method and system and a computer program product, and the method comprises the steps: for at least one given historical period, obtaining historical travel data of a passenger traveling through a ground code in the at least one historical period in a rolling manner, and discount issuing data, therefore, according to the historical travel data of the passengers and the discount issuing data, historical travel behaviors related to the issued discounts are counted, the travel characteristics of the passengers are obtained, travel discount target passengers can be obtained through travel characteristic recognition, the travel discount target passengers obtained through recognition form a discount target passenger group, and the discount target passenger group is obtained. And according to the identified preferential target customer group, preferential issuing of travel code travel is controlled and implemented, so that travel preferential issuing can be dynamically and accurately realized in the process that the passengers use the travel codes to travel by accurately identifying and positioning the target customer group, and the benefit of promoting the passengers to travel by preferential issuing is improved.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and specifically to a method and system for identifying travel preferential customer groups, and a computer program product. Background Art

[0002] The use of travel codes covers a variety of transportation modes such as buses and subways. In public transportation such as buses and subways, the use of travel codes generates travel data for each passenger, and implements the identity authentication and payment processes involved in the travel, so as to provide ticketing services for passengers.

[0003] However, the application of travel codes is limited to a single payment and identity authentication function. The travel discounts implemented for passengers rely on the subjective judgment and manual issuance of travel service operators. How to dynamically and accurately realize the issuance of travel discounts when passengers use travel codes to travel has become a technical problem that urgently needs to be solved. Summary of the invention

[0004] One purpose of this application is to dynamically and accurately distribute travel discounts to passengers when they use travel codes.

[0005] According to one aspect of an embodiment of the present application, a method for identifying a travel discount customer group is disclosed, the method comprising:

[0006] Rollingly obtain historical travel data of passengers using travel codes in at least one historical period, as well as discount issuance data;

[0007] According to the historical travel data of the passenger and the discount issuance data, historical travel behaviors related to the issued discounts are counted to obtain the travel characteristics of the passenger;

[0008] Obtaining target passengers with travel discounts through the travel characteristics, and identifying the target passengers with travel discounts to form a target customer group with discounts;

[0009] The preferential distribution of the travel code travel is controlled and implemented according to the identified preferential target customer group.

[0010] According to one aspect of an embodiment of the present application, the passenger initiates travel behavior by requesting a travel code through the MaaS travel code platform, and the rolling acquisition of historical travel data of the passenger's travel code in at least one historical period, as well as preferential issuance data, includes:

[0011] The MaaS travel code platform is used to obtain, on a rolling basis, historical travel data of all passengers who have used travel codes to travel in at least one historical period, and discount issuance data corresponding to discounts issued by the MaaS travel code platform to the passengers.

[0012] According to one aspect of an embodiment of the present application, the process of obtaining the travel characteristics of the passenger by counting historical travel behaviors related to the issued discounts based on the historical travel data and discount issuance data of the passenger includes:

[0013] Combining the passenger's historical travel data and discount issuance data to determine historical travel behavior related to the discount issued;

[0014] Statistics are collected on historical travel behaviors of passengers receiving preferential incentives during their travels to obtain travel characteristics of the passengers.

[0015] According to one aspect of an embodiment of the present application, the statistical analysis of historical travel behaviors of passengers issued with preferential incentives during their travel behaviors to obtain passenger travel characteristics includes:

[0016] For the historical travel behaviors of passengers issued preferential incentives during their travels, statistics are collected on the historical travel behaviors of passengers and the issuance and response of preferential incentives during the historical period, and the total number of trips of the passengers, the total number of trips triggered by preferential incentives, the number of preferential issuances, the mean preferential response time, and the variance of the preferential response time are obtained;

[0017] The passenger travel characteristics are generated according to the total number of trips, the total number of trips triggered by discounts, the number of discount issuances, the mean discount response time, and the discount response time variance obtained by statistics.

[0018] According to one aspect of an embodiment of the present application, obtaining a target passenger with travel discount through the travel characteristics, and identifying the target passenger with travel discount to form a target customer group with travel discount, includes:

[0019] Performing clustering operations among passengers based on the travel characteristics to determine a number of similar passengers;

[0020] A target customer group for discounts is formed by taking several similar passengers who have few trips and are sensitive to discounts as the target passengers for travel discounts.

[0021] According to one aspect of an embodiment of the present application, controlling and implementing the preferential issuance of the travel code travel according to the identified preferential target customer group includes:

[0022] Travel discounts are issued to the identified target customer groups through the MaaS travel code platform at a set frequency, and the issuance time and validity period of the issued travel discounts are configured.

[0023] According to one aspect of an embodiment of the present application, after the step of obtaining a target passenger with travel discount through the travel characteristics identification and identifying the obtained target passenger with travel discount to form a target customer group with discount, the method further includes:

[0024] For non-target customer groups different from the target customer groups for preferential treatment, preferential treatment is randomly distributed among the non-target customer groups by randomly selecting passengers.

[0025] According to one aspect of the embodiment of the present application, the method further includes:

[0026] For passengers who are not randomly selected to receive discounts, the full discount will be distributed according to the set full discount distribution period.

[0027] According to one aspect of an embodiment of the present application, the present application discloses a travel preferential customer group identification system, the system comprising a memory, a processor and a computer program stored in the memory, the processor executes the computer program to implement the steps of the method described above.

[0028] According to one aspect of an embodiment of the present application, a computer program product is disclosed, including a computer program, wherein when the computer program is executed by a processor, the steps of the method described above are implemented.

[0029] In an embodiment of the present application, for at least one given historical period, the historical travel data of passengers using location codes for travel in the at least one historical period and the discount issuance data are obtained on a rolling basis, so as to obtain the passenger's travel characteristics by counting the historical travel behavior related to the issued discounts based on the passenger's historical travel data and the discount issuance data. At this point, the target passengers for travel discounts can be identified through travel characteristics, and the identified target passengers for travel discounts can be formed into a target customer group for discounts. The issuance of discounts for travel with travel codes can be controlled based on the identified target customer group for discounts. Therefore, the issuance of travel discounts can be dynamically and accurately realized in the process of passengers using travel codes for travel by accurately identifying and positioning the target customer group, thereby improving the efficiency of driving passenger travel by issuing discounts.

[0030] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0031] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and other objects, features and advantages of the present application will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings.

[0033] Figure 1 A flow chart of a method for identifying a travel preferential customer group according to an embodiment of the present application is shown.

[0034] Figure 2 is based on Figure 1A flowchart of a method for obtaining the travel characteristics of passengers according to the passengers' historical travel data and discount issuance data, and statistics on historical travel behaviors related to the issued discounts, as shown in the corresponding embodiment.

[0035] Figure 3 is based on Figure 2 A method flow chart describing the steps of obtaining passenger travel characteristics by counting historical travel behaviors of passengers for which preferential incentives are issued, as shown in the corresponding embodiment.

[0036] Figure 4 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of obtaining target passengers for travel discounts through travel characteristics identification, and identifying the obtained target passengers for travel discounts to form a target customer group for discounts.

[0037] Figure 5 It is a schematic diagram of the implementation logic of the travel preferential customer group identification according to one embodiment.

[0038] Figure 6 A schematic diagram showing a comprehensive startup strategy and a random startup strategy cooperating to issue discounts in an embodiment.

[0039] Figure 7 A system architecture diagram of an exemplary embodiment is shown. DETAILED DESCRIPTION

[0040] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present application will be more comprehensive and complete and the concepts of the example embodiments will be fully conveyed to those skilled in the art. The accompanying drawings are only schematic illustrations of the present application and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0041] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present application. However, those skilled in the art will appreciate that the technical solution of the present application may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring the present application and making the various aspects of the present application obscure.

[0042] Some of the blocks shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0043] See also Figure 1 , Figure 1 A flow chart of a method for identifying a preferential travel customer group according to an embodiment of the present application is shown. The present application embodiment provides a method for identifying a preferential travel customer group, the method comprising:

[0044] Step S110, rolling acquisition of historical travel data of passengers using travel codes in at least one historical period, and discount issuance data;

[0045] Step S120, based on the historical travel data of the passenger and the discount issuance data, statistics are collected on the historical travel behaviors related to the issued discounts to obtain the travel characteristics of the passenger;

[0046] Step S130, obtaining travel discount target passengers through travel feature identification, and identifying the obtained travel discount target passengers to form a discount target customer group;

[0047] Step S140, controlling and implementing the issuance of travel code travel discounts based on the identified target customer group.

[0048] These steps are described in detail below.

[0049] First of all, it should be explained that with the participation of travel applications running on user terminals, passengers can request the travel code from the MaaS travel code platform through the travel application to realize identity authentication and payment in bus and subway travel to complete their travel behavior.

[0050] For example, when traveling on the subway, you use the travel code you carry to initiate identity authentication and obtain authorization to enter the station, and use the travel code you carry to initiate payment to exit the station, thereby completing your travel on the subway.

[0051] As travel behaviors are initiated, corresponding travel data will be continuously generated and accumulated. For example, each travel data describes the corresponding travel behavior.

[0052] In order to encourage travel by public transportation such as buses and subways, travel service operators will issue discounts when using travel codes to stimulate passengers to travel. However, it is understandable that for the issuance of discounts, if the passenger himself travels a lot, the discounts issued will mostly have no effect on the passenger's travel, and the benefits that can be obtained by issuing discounts to such passengers are relatively poor; while for passengers who travel less frequently but are sensitive to discounts, their travel will mostly be stimulated by the discounts and take the bus. Therefore, based on the execution of the embodiment of this application, passengers who travel less frequently and are sensitive to discounts will be identified, and then these passengers will be used as target passengers for the issuance of discounts.

[0053] Based on this, in step S110, for the continuously accumulated travel data, that is, the historical travel data, and the discount data describing the discounts issued, the time range for data acquisition will be defined with at least one historical period, so as to carry out rolling acquisition of data according to the defined time range. The rolling acquisition of data ensures the dynamic update of the data used to identify the target passengers for travel discounts, so that the target passengers for travel discounts can be continuously identified over time, the newly emerging target passengers for travel discounts can be identified, and unsuitable passengers can be removed.

[0054] Each piece of historical travel data and discount issuance data corresponds to a passenger. That is to say, as a passenger uses the travel code to travel, his travel behavior will be recorded, and then historical travel data describing his travel behavior will be generated; if a discount is issued to the passenger, the time, amount and validity period related to the issuance of the discount will also be recorded for each passenger involved. Exemplarily, a passenger's discount issuance data includes passenger identification (issuing passenger ID), discount issuance date, discount issuance time, actual discount issuance amount, discount validity period, and whether the discount has been used.

[0055] A discount refers to a travel code payment discount issued to passengers who use travel codes to travel in order to encourage them to use travel codes for travel; the discount issued numerically indicates the amount of discount that the passenger can obtain by using the travel code to pay.

[0056] In an exemplary embodiment, the travel code used by the passenger is obtained by requesting the code from the MaaS travel code platform through the travel application of the user terminal. Based on this, the preferential distribution will also be implemented by the MaaS travel code platform. Correspondingly, with the initiation of travel behavior, the issuance and use of preferential treatment, corresponding historical travel data and preferential distribution data will be generated for the passenger, and deposited on the MaaS travel code platform.

[0057] Therefore, corresponding to the passenger initiating a travel behavior by requesting a travel code through the MaaS travel code platform, the execution process of step S110 includes:

[0058] The MaaS travel code platform is used to obtain historical travel data of all passengers who have used the travel code for travel in at least one historical period, as well as discount distribution data corresponding to discounts issued by the MaaS travel code platform to passengers.

[0059] Based on the MaaS travel code platform, the corresponding historical travel data and discount issuance data of passengers' travel behavior are accumulated to indicate whether there are any discounts issued before the passenger's current travel behavior is triggered, and the passenger's response to the discounts issued if there are any.

[0060] In the identification of travel discount customer groups conducted in this application, the MaaS travel code platform will roll out historical travel data and discount issuance data using travel codes according to at least one historical period, so as to periodically identify target passengers for travel discounts, so that the objects of discount issuance, that is, the target customer groups for discounts, can be dynamically updated adaptively.

[0061] It should be understood that for a travel behavior initiated by a passenger, corresponding historical travel data will be generated as the travel code is used, and the corresponding discount issuance data will be updated based on the travel behavior. For example, the record of whether the discount in the discount issuance data has been used will be updated based on the travel behavior.

[0062] Therefore, for a passenger, the travel behavior initiated by the passenger using the travel code corresponds to a set of data, namely, a combination of historical travel data and discount issuance data, which is used to characterize the travel behavior and the correlation between the travel behavior and the discount issued.

[0063] As the historical travel data and the preferential distribution data are obtained in a rolling manner, the data within the limited historical period will be processed in step S120 to extract the travel characteristics of the passengers.

[0064] In step S120, for each travel behavior initiated by a passenger, the correlation between the travel behavior and the issued discount is identified based on the historical travel data and discount issuance data corresponding to the travel behavior, and the historical travel behavior related to the issued discount is counted.

[0065] Specifically, for each travel behavior initiated by a passenger, historical travel data and discount issuance data are combined to obtain the correlation between the travel behavior and the issued discount, that is, the relationship between passenger travel and discount.

[0066] In this way, the historical travel behavior related to the issued discount can be determined, and then the historical travel behavior related to the issued discount can be counted for passengers to obtain the travel characteristics of the passengers.

[0067] It should be noted that the historical travel behavior related to the issued discount refers to the travel behavior triggered by the issued discount incentive. For a passenger, the passenger who is motivated to travel because of the issued discount is a passenger who is sensitive to the discount and is also a potential target for the issuance of discounts. Therefore, it is necessary to use this as a basis to identify travel characteristics that can serve as the basis for the issuance of discounts, to ensure the accuracy of the subsequent identification of target passengers for travel discounts and the accuracy of the issuance of discounts.

[0068] Exemplarily, based on the discount issuance data corresponding to the travel behavior, it can be determined that a discount was issued before the travel behavior was triggered, and the issued discount was not used, and the discount was within the validity period, then the travel behavior is deemed to be triggered by the discount incentive, and based on this, the travel behavior is included in the statistics to ultimately obtain the passenger travel characteristics.

[0069] See also Figure 2 , Figure 2 is based on Figure 1 A flowchart of a method for obtaining the travel characteristics of passengers according to the passengers' historical travel data and discount issuance data, and statistics on historical travel behaviors related to the issued discounts, as shown in the corresponding embodiment.

[0070] The step S120 of obtaining the passenger's travel characteristics by counting historical travel behaviors related to the issued discounts based on the passenger's historical travel data and discount issuance data provided in the present application includes:

[0071] Step S121, combining the historical travel data of the passenger and the discount issuance data to determine the historical travel behavior related to the issued discount;

[0072] Step S122, counting the historical travel behaviors of passengers during their travels with preferential incentives, and obtaining the travel characteristics of passengers.

[0073] These two steps are described in detail below.

[0074] In step S121, the historical travel data and discount issuance data obtained by scrolling in step S110 are combined for each passenger to determine each passenger's historical travel behavior related to the issued discount.

[0075] As mentioned above, a passenger's trip will correspond to a set of data, namely, a historical travel data and a discount distribution data. Therefore, the merger performed will be a data merger performed on the passenger's trip, so as to accurately count the passenger's historical travel behavior related to the discount.

[0076] Each piece of historical travel data of a passenger records at least the passenger identification, travel identification (travel ID), travel date, travel start station, travel end station, travel start time, travel end time and travel fare.

[0077] Among them, the passenger identification is the passenger ID, which uniquely corresponds to a passenger; the historical travel data is a travel record, and the travel identification is the number of the travel record, which will uniquely identify the travel record.

[0078] The trip start and end stations are the stations where passengers enter and exit the subway, or the bus stations where passengers get on and get off the bus.

[0079] The discount issuance data corresponding to the historical travel data describes whether the passenger has received any discount before the current corresponding trip, and if so, whether the passenger's current trip is within the validity period of the discount.

[0080] It should be understood that for the current trip, if the current trip is within the validity period of the issued discount, then it can be determined that the trip is related to the issued discount. Therefore, in terms of data, based on the historical travel data and discount issuance data corresponding to the trip, it is possible to confirm whether the historical travel behavior of the trip occurred within the validity period of the issued discount, and then determine that the historical travel behavior of the trip is a trip triggered by the discount, that is, determine the travel behavior related to the issued discount.

[0081] After determining whether the historical travel behavior of a passenger's trip is related to the issued discount through the execution of step S121, the historical travel behavior of the passenger during the trip and the passenger's travel characteristics can be counted through the execution of step S122.

[0082] In step S121, the historical travel behaviors of the passengers that are motivated by the preferential treatment are determined for all their trips. That is, for each passenger, the historical travel behaviors motivated by the preferential treatment are counted, and the travel characteristics corresponding to the passenger are obtained by taking all the historical travel behaviors motivated by the preferential treatment as the statistical objects.

[0083] Among them, for the historical travel behavior generated by preferential incentives during passenger travel, statistics of the historical travel behavior itself in the historical period, statistics of the preferential treatment that occurred, statistics of travel in response to the preferential treatment, etc. are carried out to obtain the passenger travel characteristics.

[0084] Correspondingly, the obtained passenger travel characteristics are obtained by calculating the total number of passengers' trips, the total number of trips triggered by discounts, the number of discount issuances, the mean discount response time and the variance of the discount response time, which can be the daily number of trips, the discount response rate, the mean discount response time and the variance of the discount response time, which are not listed one by one here.

[0085] See also Figure 3 , Figure 3 is based on Figure 2 A method flow chart describing the steps of obtaining passenger travel characteristics by counting historical travel behaviors of passengers for which preferential incentives are issued, as shown in the corresponding embodiment.

[0086] The step S122 of obtaining passenger travel characteristics by counting historical travel behaviors of preferential incentives issued during passenger travel behaviors provided in the embodiment of the present application includes:

[0087] Step S1221, for the historical travel behaviors of passengers for which preferential incentives were issued, statistics are collected on the historical travel behaviors of passengers in the historical period, as well as the issuance and response of preferential incentives, to obtain the total number of passengers' trips, the total number of trips triggered by preferential incentives, the number of preferential issuances, the mean preferential response time, and the variance of the preferential response time;

[0088] Step S1222, generating passenger travel characteristics based on the total number of trips, the total number of trips triggered by discounts, the number of discount issuances, the mean discount response time, and the discount response time variance.

[0089] The following describes these two steps in detail.

[0090] In step S1221, by combining the historical travel data of the passenger corresponding to each historical travel behavior and the discount issuance data, it is determined whether the historical travel behavior is related to the issued discount, that is, whether the historical travel behavior is triggered by the issued discount incentive.

[0091] Similarly, all historical travel behaviors of each passenger triggered by the preferential incentives, the historical travel behaviors of the passenger, and the preferential issuance and response statistics will be collected. The statistics of the historical travel behaviors of the passenger at least include the total number of passenger trips, the total number of trips triggered by the preferential incentives, etc.

[0092] The statistics of the preferential issuance shall at least include the statistics of the number of times the preferential issuance is carried out; the statistics of the travel in response to the preferential issuance shall at least include the statistics of the mean preferential response time and the statistics of the variance of the preferential response time.

[0093] Exemplarily, adapted to at least one historical period of the rolling acquired historical travel data and discount issuance data, the total number of trips m1, the total number of trips triggered by discounts m2, the number of discount issuances m3, the mean value of discount response time E(ty), and the variance of discount response time D(ty) of each passenger are calculated for this historical period, such as within a month;

[0094] Among them, the mean value of preferential response time E(ty) and the variance of preferential response time D(ty) can be calculated by the following formula, namely:

[0095]

[0096]

[0097] ty is the discount response time, discount response time ty = travel start time - discount issuance time.

[0098] After obtaining the total number of passenger trips, the total number of trips triggered by discounts, the number of discount issuances, the mean discount response time and the discount response time variance through statistics of the passengers in step S1221, the passenger travel characteristics are generated through step S1222.

[0099] In step S1222, for each passenger, the total number of trips, the total number of trips triggered by discounts, the number of discounts issued, the mean value of discount response time, and the variance of discount response time are used to generate corresponding passenger travel characteristics. For example, based on the total number of trips m1, the total number of trips triggered by discounts m2, and the number of discounts issued m3, the average daily number of trips and the discount response rate of the passenger are calculated, respectively, where the average daily number of trips is m1 / T, T is the number of days involved, for example, T=30 days; the discount response rate is m2 / m3.

[0100] For each passenger's travel characteristics, whether the passenger is a target passenger for travel discounts is identified based on the travel characteristics during the execution of step S130, so that target passengers for travel discounts are identified from all passengers based on their travel characteristics, and the identified target passengers for travel discounts form a target customer group for discounts.

[0101] In step S130, based on the travel characteristics, aggregation operations are performed between passengers to determine several similar passengers among all passengers. Then, according to the average daily number of trips, discount response rate, discount response time mean and discount response time variance corresponding to each passenger, several passengers with few trips and sensitive to discounts are determined to form the target customer group for discounts.

[0102] The similar passengers referred to herein refer to two or more passengers having similarities in terms of travel characteristics, which are obtained through the aggregation operation of travel characteristics during the execution of step S130.

[0103] After obtaining several similar passengers, the passengers with few trips and who are sensitive to discounts can be determined as target passengers for travel discounts based on the average daily number of trips, discount response rate, discount response time mean and discount response time variance of each passenger.

[0104] It should be understood that passengers can be divided into: passengers who travel frequently and have good preferential effects, passengers who travel frequently but have poor preferential effects, passengers who travel less frequently but have good preferential effects, passengers who travel less frequently and have poor preferential effects, etc. The preferential effects referred to are reflected in the sensitivity of passengers to preferential effects. Specifically, good preferential effects refer to passengers' sensitivity to preferential effects.

[0105] See also Figure 4 , Figure 4 is based on Figure 1 The corresponding embodiment shows a method flow chart describing the steps of obtaining target passengers for travel discounts through travel characteristics identification, and identifying the obtained target passengers for travel discounts to form a target customer group for discounts.

[0106] The step S130 of obtaining target passengers with travel discounts by identifying travel characteristics and identifying the obtained target passengers with travel discounts to form a target customer group with discounts provided in the embodiment of the present application includes:

[0107] Step S131, performing clustering operation among passengers based on travel characteristics to determine a number of similar passengers;

[0108] Step S132, forming a preferential target customer group with a number of similar passengers who have a small number of trips and are sensitive to preferential treatment as the travel preferential target passengers.

[0109] These two steps are described in detail below.

[0110] In step S131, the passenger travel information statistics corresponding to the travel characteristics obtained by the above statistics are aggregated, and the passenger clustering result is obtained by the implemented similar customer group clustering algorithm, and the customer group for issuing travel discounts, that is, the target customer group for discounts, is determined by the passenger clustering result.

[0111] The passenger aggregation result indicates at least one group of similar passengers. Therefore, based on this, through the execution of step S132, for each group of similar passengers, passengers with few trips and sensitive to discounts are identified as target passengers for travel discounts.

[0112] The similar customer group clustering algorithm implemented is to cluster the data based on travel characteristics in an attempt to find the partition that minimizes the square error function value, so as to repeatedly recursively calculate the center of each cluster, and then assign passengers to different clusters. In other words, the set of n passengers who are motivated by preferential treatment is divided into k clusters, and the similarity within the cluster is high, while the similarity between clusters is low.

[0113] Specifically, the execution process of the similar customer group clustering algorithm includes: first, randomly selecting a number of data points as initial clustering centers to complete the clustering initialization process. For example, the number of selected data points can be 10, that is, k=10, thereby obtaining the initial clustering center c 1 , c 2 , c 3 , ..., c 10 .

[0114] Then, for each passenger, based on its travel characteristics, it is assigned to the nearest cluster. i , calculate its relationship with each cluster center c k The distance dis(c k , c k ), in order to assign the passenger to the cluster with the closest distance.

[0115] For example, with each cluster center c k The distance can be calculated by Euclidean distance, that is:

[0116]

[0117] Among them, x ij represents the value of the i-th passenger on the j-th travel feature, c kj It represents the value of the k-th cluster center on the j-th travel feature, and d represents the dimension of the travel feature.

[0118] After assigning each passenger to the nearest cluster, the cluster center update step is performed. Specifically, for each cluster c k , recalculate its center. For example, take all samples in the cluster, that is, the average value of all passengers assigned to the cluster as the new center, that is:

[0119]

[0120] Among them, |S k | represents the number of passengers in the kth cluster, S k represents all passengers in the kth cluster, x i represents the passengers in the collection;

[0121] The assignment of passengers to the nearest cluster and the updating of cluster centers are repeated until the cluster centers no longer change or the maximum number of iterations is reached.

[0122] At this point, k clusters can be finally obtained, each cluster contains a group of passengers and the corresponding cluster center.

[0123] After performing clustering operations among passengers based on travel characteristics, several clusters can be determined, and the group of passengers contained in each cluster is a group of similar passengers.

[0124] Since the target passengers for travel discounts should have the characteristics of few daily trips and being easily attracted by travel discounts, for the clustering operation, the travel characteristics of each passenger in dimensions such as average daily trips, discount response rate, mean discount response time and discount response time variance are selected to perform clustering operations among passengers in order to obtain several groups of passengers who are similar to each other.

[0125] Each group of passengers, i.e. each cluster, is adapted to the selected travel characteristics and has corresponding characteristics in terms of the number of trips and the preferential effect. In other words, the population corresponding to each group of passengers has the characteristics of the number of trips and the preferential effect.

[0126] Specifically, as mentioned above, the people clustered according to travel characteristics in dimensions such as average daily trips, discount response rate, mean discount response time, and discount response time variance can be divided into the following types, namely: those with more trips and good discount effects, those with more trips and poor discount effects, those with fewer trips but good discount effects, and those with fewer trips and discounts.

[0127] Furthermore, the characteristics corresponding to each group of people are:

[0128] Category 1: more trips, better discounts, corresponding to large m1 / T, large m2 / m3, small E(ty), and small D(ty);

[0129] Category 2: Many trips, poor discount effect, corresponding to the characteristics of large m1 / T, uncertain m2 / m3, small E(ty), and large D(ty);

[0130] Category 3: Few trips, good discount effect, corresponding to small m1 / T, large m2 / m3, small E(ty), and small D(ty);

[0131] Category 4: Few trips, poor discount effect, corresponding features: small m1 / T, small m2 / m3, large E(ty), and large D(ty).

[0132] At this point, for the several categories of people obtained by clustering, that is, several groups of similar passengers, several similar passengers corresponding to fewer trips and better discount effects will be determined as travel discount target passengers through the execution of step S132, that is, the people in category 3 will be the travel discount target passengers for travel discount issuance.

[0133] It should be understood that the target passengers for travel discounts should have few daily trips and are easily attracted by travel discounts to make trips in order to increase their income. Therefore, the target customer group for the discounts will be people in Category 3.

[0134] During the execution of step S132, passengers are screened from category 3 according to the clustering result, so as to select target passengers for travel discounts from a number of similar passengers with a small number of trips and sensitivity to discounts, thereby forming a target customer group for discounts.

[0135] For example, passengers whose average daily travel times are in the bottom 10%, whose discount response rate is in the top 10%, whose mean discount response time is in the bottom 10%, and whose discount response time variance is in the bottom 10% can be screened from the clustering results as target passengers for travel discounts, so as to serve as an alternative group suitable for issuing travel discounts.

[0136] After the preferential target customer group is identified through step S130, the preferential code travel discount can be issued to the identified preferential target customer group through the execution of step S140.

[0137] Exemplarily, for passengers in the target customer group for travel discounts, the travel service operator issues travel code travel discounts at a set frequency. For example, the set frequency may be once every two days.

[0138] Exemplarily, the execution process of step S140 includes: issuing travel discounts to the identified target customer group according to a set frequency through the MaaS travel code platform, and configuring the issuance time and validity period for the issued travel discounts.

[0139] As mentioned above, the MaaS travel code platform is a system implementation on the travel service operator side, which will dynamically issue travel discounts to the identified target customer groups.

[0140] The target customer group for discounts will change dynamically with the rolling acquisition of historical travel data and discount issuance data. For example, passengers who no longer meet the requirements and are sensitive to discounts will be removed from the target customer group, thereby ensuring the accuracy of discount issuance.

[0141] The issuance time and validity period of the travel discounts are used to control the effectiveness of the discounts on the one hand, and on the other hand, they will be recorded in the discount issuance data to determine the correlation between historical travel behavior and the discounts issued. In other words, whether the discounts issued have stimulated passengers to travel.

[0142] In another exemplary embodiment, after obtaining travel discount target passengers through travel feature identification and identifying the obtained travel discount target passengers to form a discount target customer group in step S130, the travel discount customer group identification method provided by the present application further includes:

[0143] For non-target customer groups that are different from the target customer groups for discounts, discounts are randomly distributed among the non-target customer groups through random sampling of passengers.

[0144] This is the execution of the random start strategy. Passengers outside the target customer group constitute the non-target customer group. Although the passengers in the non-target customer group are not the target passengers for travel discounts, there is a possibility of changes in the number of trips and the effect of the discount due to the influence of various factors on the passengers themselves.

[0145] For example, if a passenger changes from a state with few trips and poor discount effects to a state with few trips and sensitivity to discounts, at this time, if discounts are offered to him, the corresponding historical travel data and discount issuance data will enable the passenger to be identified and dynamically moved into the target customer group for the discount.

[0146] Therefore, it is also necessary to offer discounts to non-target customer groups, so as to provide a data basis for updating the target passengers for travel discounts and ensure the dynamic update of the target customer groups for discounts.

[0147] For example, the preferential treatment for non-target customers will be provided by randomly selecting passengers. Furthermore, for passengers in the non-target customer group, a pre-set ratio is used to randomly select passengers to avoid providing preferential treatment only to the preferential target customer group. For example, 5% of the passengers in the non-target customer group can be selected, and correspondingly, preferential treatment will be provided to the selected 5% of passengers once every three days within a month.

[0148] It should be understood that after identifying the target customer group for discounts based on travel characteristics, if the discount is only offered to the target customer group, the target customer group will continue to be affected by the discount, while the non-target customer group will have nothing to do with the discount and will have no travel related to the discount. This will result in the discount being fixed to the existing target customer group, and the potential value of other passengers cannot be discovered.

[0149] Therefore, in order to adapt to changes in people's travel behavior and attitudes towards discounts, the changes in passengers will be perceived through the random distribution of discounts, and then the target customer groups for discounts will be dynamically updated with the support of corresponding behavioral data.

[0150] On this basis, the travel discount customer group identification method provided by this application also includes: for passengers who are not randomly selected to receive discounts, full discount distribution is implemented according to the set full discount distribution period.

[0151] As a result, the discounts issued will not only be biased towards the target customer group, but will also take into account other passengers besides the target customer group and the randomly selected passengers, so as to achieve the full distribution of discounts in a targeted manner.

[0152] In other words, under the full implementation of the discount, the identified target passengers for travel discounts will be able to receive preferential treatment in order to increase the profits of travel operators during the discount distribution; randomly selected passengers will also receive discounts, so as to ensure that the subsequent identification of travel discount customer groups can tap into potential target passengers for travel discounts; finally, on this basis, the full discount will be implemented for the remaining passengers according to the set full discount period, so that the implemented discount can cover all passengers, and the travel discount customer group identification thus performed can also cover all passengers, and dynamically update the target customer group for discounts.

[0153] Furthermore, the full discount distribution period is a set time range, during which discounts will be distributed by executing a full discount activation strategy. The historical travel data and discount distribution data generated thereby will serve as basic data for rolling data acquisition for travel discount customer group identification.

[0154] The following is a specific example to illustrate the execution process of identifying the travel discount customer group as described above.

[0155] First of all, it should be explained that the identification of travel preferential customer groups is carried out on a rolling basis based on the generated data, so as to dynamically identify the preferential target customer groups and dynamically update the existing preferential target customer groups that have been identified.

[0156] See also Figure 5 , Figure 5 This is a logic diagram of the implementation of the travel discount customer group identification according to an embodiment. Based on the MaaS travel code platform, a travel discount customer group identification system is built. The travel discount customer group identification system built will read the data accumulated by the MaaS travel code platform, that is, the historical travel data and discount issuance data, and then use this to identify the target customer group, that is, the discount target customer group formed by the travel discount target passengers.

[0157] The MaaS travel code platform provides discounts to the target customer groups. On this basis, the MaaS travel code platform also provides discounts to other passengers through the implementation of comprehensive start-up strategies and random start-up strategies.

[0158] Specifically, in order to adapt to the identification of travel discount customer groups, the MaaS travel code platform is configured with at least a database and a discount issuance module. The database is used to store historical travel data and discount issuance data generated by passenger travel, and the discount issuance module is controlled to issue discounts to passengers.

[0159] The travel discount customer group identification system constructed includes a data processing module and a travel discount target customer group identification module. The data processing module will obtain the corresponding historical travel data and discount issuance data of the passengers from the database and process them to confirm the existing relationship between passenger travel and discounts. Based on the relationship between passenger travel and discounts, statistics are performed to obtain passenger travel information statistics, which are the travel characteristics referred to above.

[0160] The obtained travel characteristics can characterize the number of passengers' trips and the effects of discounts. Therefore, through the travel characteristics, the passenger travel discount target customer group identification module can identify several similar passengers through a clustering algorithm, and several similar passengers with few trips and good discount effects will constitute the discount target customer group.

[0161] At this point, the discount distribution module in the MaaS travel code platform will issue discounts to the identified target customer groups, and will also provide discounts to other passengers besides the target passengers under the control of the random start strategy and / or the comprehensive start strategy.

[0162] In summary, with the support of the travel discount customer identification system and the comprehensive launch strategy and random launch strategy, the MaaS travel code platform dynamically issues discounts to each passenger.

[0163] Figure 6 The schematic diagram of the comprehensive start strategy and random start strategy in one embodiment of the invention is shown. For passengers other than the target passengers for travel discounts, the comprehensive start strategy issues discounts to all passengers once every three days, and the random start strategy randomly selects 5% of the passengers to issue discounts once every three days.

[0164] In terms of time, the full-start strategy and the random-start strategy are coordinated and executed alternately, and the corresponding full-start strategy period and random-start strategy period can be seamlessly connected in time, so that other passengers besides the target passengers with travel discounts can be identified from turning into the target passengers with travel discounts.

[0165] For example, Figure 6 On the schematic axis shown, a full launch strategy period covers the first three months, followed by a random launch strategy period covering March to May, followed by another random launch strategy period covering May to July, and so on.

[0166] Therefore, the data generated during the full launch of the strategy, that is, the historical travel data and discount issuance data of passengers who are not the target customer group and are not randomly selected, will be used as basic data to identify whether the passenger has become a target passenger for travel discounts; correspondingly, the data generated during the random launch of the strategy, that is, the data generated by passengers randomly selected outside the non-target customer group will also be used as basic data to identify whether the passenger has become a target passenger for travel discounts.

[0167] For example, with the initial operation of the travel discount customer group identification system, basic data has not been generated and there is no discount target customer group. Of course, there is no random selection of passengers outside the discount target customer group. Therefore, a comprehensive startup strategy is adopted to issue discounts to all passengers on the MaaS travel code platform to obtain basic data.

[0168] For example, the time for executing the full launch strategy may be one month, and during the initial operation of the system, discounts may be issued to all passengers once every three days within one month.

[0169] With the implementation of the full launch strategy, the database of the MaaS travel code platform can accumulate historical travel data and discount issuance data. The data processing module of the travel discount customer group identification system can obtain the travel characteristics of passengers based on the historical travel data and discount issuance data within a month, and then identify the target passengers for travel discounts and obtain the target customer group for discounts.

[0170] The travel preferential customer group identification system sends the passenger information corresponding to the preferential target customer group to the MaaS travel code platform through the data interface. The MaaS travel code platform continues to issue discounts at a frequency of once every three days until the passenger is removed from the preferential target customer group.

[0171] With the issuance of discounts to the target customer groups, and the implementation of the comprehensive start-up strategy and the random start-up strategy, the travel discount customer group identification system can obtain data in a rolling manner, and through the data processing module and the travel discount target customer group identification module, it can realize the identification of the discount target customer groups in at least the most recent historical period, and then continuously update the discount target customer groups for issuing discounts.

[0172] Figure 7 A system architecture diagram of an exemplary embodiment is shown. Figure 7 In the system architecture provided by the illustrated embodiment, each passenger uses the travel code presented by his / her own terminal device to initiate travel behavior to the gate, and if a discount is received, the discount is used to initiate payment for the ride.

[0173] At this time, through the passenger terminal device, that is, the passenger client composed of the travel application and the gate machine interacting with the MaaS travel code platform, the corresponding historical travel data and discount distribution data are stored in the database of the MaaS travel code platform.

[0174] In at least one historical period, the deployed travel discount customer group identification system has been rollingly acquiring basic data from the database, and with the cooperation of the travel discount target customer group identification module, has provided the MaaS travel code platform with the passenger information of the discount target customer group for the purpose of issuing discounts.

[0175] In other words, by identifying the target customer group for discounts, a comprehensive launch strategy or a random launch strategy, passengers can obtain the discounts issued, and then the historical travel data and discount issuance data generated by passengers with fewer trips after being motivated by discounts can identify the passengers as target passengers for travel discounts, and then update them to the target customer group for discounts, or keep them in the target customer group for discounts.

[0176] In summary, through the travel discount customer group identification provided in the embodiment of the present application, the accuracy and effectiveness of the travel code travel discount issuance can be enhanced, which will greatly improve the operating income of the MaaS travel platform.

[0177] A travel discount customer group identification system includes a memory, a processor, and a computer program stored in the memory, and the processor executes the computer program to implement the steps of the method described above.

[0178] A computer program product comprises a computer program, wherein when the computer program is executed by a processor, the steps of the method described above are implemented.

[0179] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0180] In an exemplary embodiment of the present application, a computer program medium is further provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is enabled to execute the method described in the above method embodiment.

[0181] According to one embodiment of the present application, a program product for implementing the method in the above method embodiment is also provided, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited to this. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0182] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0183] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0184] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0185] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0186] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0187] In addition, although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0188] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0189] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present application. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the appended claims.

Claims

1. A method for identifying travel discount customer groups, characterized in that: The method comprises: Rollingly obtain historical travel data of passengers using travel codes in at least one historical period, as well as discount issuance data; According to the historical travel data of the passenger and the discount issuance data, historical travel behaviors related to the issued discounts are counted to obtain the travel characteristics of the passenger; Obtaining target passengers with travel discounts through the travel characteristics, and identifying the target passengers with travel discounts to form a target customer group with discounts; The preferential distribution of the travel code travel is controlled and implemented according to the identified preferential target customer group.

2. The method according to claim 1, characterized in that The passenger initiates travel behavior by requesting a travel code through the MaaS travel code platform, and the rolling acquisition of historical travel data of the passenger using the travel code in at least one historical period, as well as preferential issuance data, includes: The MaaS travel code platform is used to obtain, on a rolling basis, historical travel data of all passengers who have used travel codes to travel in at least one historical period, and discount issuance data corresponding to discounts issued by the MaaS travel code platform to the passengers.

3. The method according to claim 1, characterized in that: The process of obtaining the travel characteristics of the passenger by counting historical travel behaviors related to the issued discounts based on the historical travel data of the passenger and the discount issuance data includes: Combining the passenger's historical travel data and discount issuance data to determine historical travel behavior related to the discount issued; Statistics are collected on historical travel behaviors of passengers receiving preferential incentives during their travels to obtain travel characteristics of the passengers.

4. The method according to claim 1, characterized in that: The statistical analysis of the historical travel behaviors of the passengers in which the preferential incentives are issued to obtain the travel characteristics of the passengers includes: For the historical travel behaviors of passengers issued preferential incentives during their travels, statistics are collected on the historical travel behaviors of passengers and the issuance and response of preferential incentives during the historical period, and the total number of trips of the passengers, the total number of trips triggered by preferential incentives, the number of preferential issuances, the mean preferential response time, and the variance of the preferential response time are obtained; The passenger travel characteristics are generated based on the total number of trips, the total number of trips triggered by discounts, the number of discount issuances, the mean discount response time, and the discount response time variance obtained by statistics.

5. The method according to claim 1, characterized in that: The step of obtaining target passengers with travel discounts through the travel characteristics and identifying the target passengers with travel discounts to form a target customer group with travel discounts includes: Performing clustering operations among passengers based on the travel characteristics to determine a number of similar passengers; A target customer group for discounts is formed by taking several similar passengers who have few trips and are sensitive to discounts as the target passengers for travel discounts.

6. The method according to claim 1, characterized in that The controlling and implementing the preferential issuance of the travel code travel discount according to the identified preferential target customer group includes: Travel discounts are issued to the identified target customer groups through the MaaS travel code platform at a set frequency, and the issuance time and validity period of the issued travel discounts are configured.

7. The method according to claim 1, characterized in that After the step of obtaining the target passengers with travel discounts through the travel characteristics identification and identifying the obtained target passengers with travel discounts to form a target customer group with discounts, the method further includes: For non-target customer groups different from the target customer groups for preferential treatment, preferential treatment is randomly distributed among the non-target customer groups by randomly selecting passengers.

8. The method according to claim 7, characterized in that The method further comprises: For passengers who are not randomly selected to receive discounts, the full discount will be distributed according to the set full discount distribution period.

9. A travel discount customer group identification system, the system comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images