Traffic behavior prediction method based on user personal preference

Abstract

The invention relates to the technical field of prediction methods, and provides a user personal preference-based traffic behavior prediction method, which has the advantages that the coverage range of basic data is wide, the matched basic data is fused into a time axis, the diversity and comprehensiveness of the basic data are enriched, and the user experience is improved. The method improves rationality and reliability of traffic travel behavior prediction based on user personal preference, enables a result of traffic travel behavior prediction based on user personal preference to better fit the user personal preference, and further improves prediction reliability and personalized matching performance, and comprises the following steps: data collection and preprocessing; the method comprises the following steps: establishing an adaptation algorithm according to a data collection condition, generating transportation recommendation, generating transportation behavior prediction, generating comprehensive transportation behavior prediction, after a transportation behavior prediction scheme is generated, collecting personal actual transportation behaviors, and comparing the personal actual transportation behaviors with the comprehensive transportation behavior prediction scheme. And optimizing the fitting degree of the traffic behavior prediction based on the personal preference of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of prediction methods, and in particular to a method for predicting traffic travel behavior based on user personal preferences. Background Art

[0002] As we all know, traffic travel behavior prediction is a technical field that aims to understand and predict people's travel patterns in different situations. In order to facilitate users' personal traffic travel, pay attention to individual differences, consider each user's unique preferences and behavior patterns, and improve users' personal traffic travel experience, we propose a traffic travel behavior prediction method based on user personal preferences.

[0003] After searching, the invention patent with Chinese patent publication number CN105809962A discloses a method for dividing transportation modes based on mobile phone data. The method is roughly described as follows: when in use, the residential area and work area of ​​the mobile phone user are predicted based on the mobile phone communication data according to the mobile phone user's behavioral characteristics, and the communication records generated by the mobile phone user in the residential area and the work area on weekdays are used to construct the commuting OD matrix of the mobile phone user between the residential area and the work area. The time information and location information contained in the mobile phone data are used to calculate the commuting travel time, travel distance and travel speed. The speed and distance grade algorithm is established through the travel characteristics of different travel modes, and the urban transportation network information data is introduced and a Logit model based on travel time is constructed to realize large-scale urban transportation travel mode division.

[0004] Although the above-mentioned existing technical solutions provide users with predictions and recommendations on transportation modes based on their personal information, the customer information they are based on is the behavioral characteristics of mobile phone users' communication records. The data base is relatively narrow, and the reference data for transportation behavior prediction is relatively weak. The reliability of the prediction and the personalized matching need to be further improved. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a method for predicting traffic travel behavior based on user personal preferences. The basic data covers a wide range, and the supporting basic data is integrated into the time axis, enriching the diversity and comprehensiveness of the basic data, improving the rationality and reliability of the traffic travel behavior prediction based on user personal preferences, making the results of the traffic travel behavior prediction based on user personal preferences more in line with the user's personal preferences, and the reliability of the prediction and the personalized matching are further improved.

[0006] To achieve the above object, the present invention provides the following technical solution: a method for predicting traffic travel behavior based on user personal preferences, comprising the following steps:

[0007] S1. Acquisition of basic data, data collection and preprocessing;

[0008] S2. Algorithm selection: Establish an adaptation algorithm based on the data collected in the previous step to generate transportation recommendations;

[0009] S3. Generate a traffic travel behavior forecast. For simple travel needs, a single mode of traffic travel behavior forecast is used. For complex travel needs, a comprehensive traffic travel behavior forecast is generated.

[0010] S4. Continuous optimization and feedback. After the predicted travel behavior plan is generated, the actual travel behavior of the individual is collected, the two are compared, and the comparison information is stored to optimize the fit of the travel behavior prediction based on the user's personal preferences.

[0011] Based on the above solution, step S1 includes:

[0012] S11 Data collection: Data acquisition includes static information acquisition and dynamic information acquisition, both of which are integrated into the time dimension;

[0013] S12 Data processing: Remove outliers and erroneous data, and encode categorical variables, such as transportation methods can be encoded as numbers.

[0014] Based on the above scheme, the acquisition of static information in step S11 includes personal static information of age, gender and occupation as well as departure and destination, and the acquisition of dynamic information includes personal static information of travel time, journey time and cost as well as weather conditions and traffic congestion.

[0015] Based on the above scheme, the data acquisition in step S11 includes questionnaire survey, historical behavior data analysis and social network information extraction.

[0016] Based on the above-mentioned plan, the questionnaire survey includes travel purpose (such as work, leisure travel, visiting relatives and friends, etc.), travel frequency (how many times a week, how many times a month, etc.), sensitivity to time (whether in a hurry), cost budget, comfort level requirements, past experience evaluation of different modes of transportation, etc.

[0017] Based on the above-mentioned scheme, the historical behavior data analysis is to analyze the user's historical travel orders, including the selected mode of transportation, departure and destination, travel time, etc., monitor the user's search history and route planning behavior on map software and travel apps, and understand the user's frequented places and travel habits.

[0018] Based on the above scheme, the social network information extraction includes obtaining travel-related information from personal social network accounts, analyzing traffic bloggers and related topics that users follow, and analyzing potential points of interest of users.

[0019] On the basis of the above scheme, after the user's personal transportation travel behavior in step S4 is actually completed, the user is invited to evaluate and give feedback. The user can evaluate the accuracy, practicality and satisfaction of the scheme, collect user feedback, understand the user's specific expectations and dissatisfaction with the recommendation results, and continuously optimize the user preference model and recommendation algorithm based on user feedback and new user data.

[0020] On the basis of the above scheme, the static information updates data periodically, the dynamic information updates data in real time, and the behavior data analysis and social network information extraction both have time span.

[0021] Compared with the prior art, the present invention provides a method for predicting traffic travel behavior based on user personal preferences, which has the following beneficial effects:

[0022] In the present invention, the basic data covers a wide range, and the supporting basic data is integrated into the time axis, enriching the diversity and comprehensiveness of the basic data, improving the rationality and reliability of the traffic travel behavior prediction based on the user's personal preferences, making the results of the traffic travel behavior prediction based on the user's personal preferences more in line with the user's personal preferences, and the reliability of the prediction and the personalized matching are further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall process of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Example

[0026] See also Figure 1, a method for predicting traffic travel behavior based on user personal preferences, including the following steps: acquisition of basic data, data collection and preprocessing, data collection: data acquisition includes acquisition of static information and acquisition of dynamic information, both of which are integrated into the time dimension, that is, by statistically analyzing data within a certain period of time, the acquisition of static information includes personal static information of age, gender and occupation, as well as departure and destination, and the acquisition of dynamic information includes personal static information of travel time, travel time and cost, as well as weather conditions and traffic congestion. The forms of data acquisition include questionnaire survey, historical behavior data analysis and social network information extraction. The questionnaire survey includes travel purpose (such as work, leisure travel, visiting relatives and friends, etc.), travel frequency (how many times a week, how many times a month, etc.), and time. Sensitivity (whether in a hurry), cost budget, comfort level requirements, past experience evaluation of different modes of transportation, etc. Historical behavior data analysis is to analyze the user's historical travel orders, including the selected mode of transportation, departure and destination, travel time, etc., monitor the user's search history and route planning behavior on map software and travel apps, and understand the places and travel habits frequently visited by users. Social network information extraction includes obtaining travel-related information from personal social network accounts, analyzing the traffic bloggers and related topics that users follow, in order to analyze the user's potential personal interests. Data processing: remove outliers and erroneous data, encode categorical variables, such as transportation methods can be encoded as numbers, algorithm selection, establish an adaptation algorithm based on the data collection in the previous step, and generate transportation recommendations.

[0027] It should be further explained that when generating travel behavior predictions, for simple travel needs, a single mode of travel behavior prediction is used, and for complex travel needs, a comprehensive travel behavior prediction is generated, and continuous optimization and feedback are provided. After the predicted travel behavior plan is generated, the actual personal travel behavior is collected, the two are compared, and the comparison information is stored. The travel behavior prediction is optimized based on the degree of fit with the user's personal preferences. After the individual's travel behavior is actually completed, the user is invited to evaluate and give feedback. The user can evaluate the accuracy, practicality and satisfaction of the plan, collect user feedback, understand the user's specific expectations and dissatisfaction with the recommendation results, and continuously optimize the user preference model and recommendation algorithm based on user feedback and new user data. Static information is updated regularly, and dynamic information is updated in real time. Both behavioral data analysis and social network information extraction have time spans.

[0028] Historical behavior data analysis and social network information extraction should be matched with the current time period. For example, if the current time period is rainy days, evenings and weekdays, the historical behavior data analysis and social network information extraction should extract the analysis and extraction of relevant information under the same rainy days, evenings and weekdays in a certain time dimension in the past. In the actual traffic travel behavior prediction process, the obtained basic data will be combined to form the corresponding generation of traffic travel behavior prediction, and the generated traffic travel behaviors are of multiple types, which are sorted and pushed according to the level of fit with the user's personal preferences.

[0029] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

[0030] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for predicting traffic travel behavior based on user personal preferences, characterized in that: The steps include: S1. Acquisition of basic data, data collection and preprocessing; S2. Algorithm selection: Establish an adaptation algorithm based on the data collected in the previous step to generate transportation recommendations; S3. Generate a traffic travel behavior forecast. For simple travel needs, a single mode of traffic travel behavior forecast is used. For complex travel needs, a comprehensive traffic travel behavior forecast is generated. S4. Continuous optimization and feedback. After the predicted travel behavior plan is generated, the actual travel behavior of the individual is collected, the two are compared, and the comparison information is stored to optimize the fit of the travel behavior prediction based on the user's personal preferences.

2. The method for predicting traffic travel behavior based on user personal preference according to claim 1, characterized in that: The step S1 comprises: S11 Data collection: Data acquisition includes static information acquisition and dynamic information acquisition, both of which are integrated into the time dimension; S12 Data processing: Remove outliers and erroneous data and encode categorical variables.

3. The method for predicting traffic travel behavior based on user personal preference according to claim 2, characterized in that: The acquisition of static information in step S11 includes personal static information of age, gender and occupation as well as departure and destination, and the acquisition of dynamic information includes personal static information of travel time, journey time and cost as well as weather conditions and traffic congestion.

4. The method for predicting traffic travel behavior based on user personal preference according to claim 3, characterized in that: The data acquisition in step S11 includes questionnaire survey, historical behavior data analysis and social network information extraction.

5. The method for predicting traffic travel behavior based on user personal preference according to claim 4, characterized in that: The questionnaire survey includes travel purpose, travel frequency, sensitivity to time, cost budget, comfort level requirements, and past experience evaluation of different modes of transportation.

6. A method for predicting traffic travel behavior based on user personal preferences according to claim 5, characterized in that: The historical behavior data analysis is to analyze the user's historical travel orders, including the selected mode of transportation, departure and destination, travel time, monitor the user's search history and route planning behavior on map software and travel apps, and understand the user's frequented places and travel habits.

7. A method for predicting traffic travel behavior based on user personal preferences according to claim 6, characterized in that: The social network information extraction includes obtaining travel-related information from personal social network accounts, analyzing traffic bloggers and related topics that users follow, and analyzing potential points of interest of users.

8. The method for predicting traffic travel behavior based on user personal preference according to claim 7, characterized in that: After the user's personal transportation travel behavior is actually completed in step S4, the user is invited to evaluate and give feedback. The user can evaluate the accuracy, practicality and satisfaction of the plan, collect user feedback, understand the user's specific expectations and dissatisfaction with the recommendation results, and continuously optimize the user preference model and recommendation algorithm based on user feedback and new user data.

9. The method for predicting traffic travel behavior based on user personal preference according to claim 8, characterized in that: The static information updates data periodically, the dynamic information updates data in real time, and the behavior data analysis and social network information extraction both have a time span.

Images