Traffic information identification management system and method based on data processing

Abstract

The invention discloses a traffic information identification management system and method based on data processing, and relates to the technical field of data analysis, and the method comprises the steps: collecting signaling data, identifying a destination and a terminal point, building a travel identification system, and summarizing historical identification records of personnel numbers; calculating an average stay duration and a threshold value, and determining a feature record set of the feature number; collecting occupational information of the feature numbers, obtaining departure time points of occupations, and determining occupational feature time periods; setting a training period, calculating an identification success rate of a characteristic time period, determining a monitoring period, and calculating a risk value; the real-time identification success rate of the characteristic time period is monitored, grid division is reminded if the real-time identification success rate is lower than a threshold value, and the monitoring period is adjusted if the real-time identification success rate is higher than the threshold value

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a traffic information identification management system and method based on data processing. Background Art

[0002] With the development of intelligent transportation systems, accurate identification and management of traffic travel information has become a key issue in improving traffic efficiency, optimizing urban planning and improving travel services. Traditional traffic travel data mainly relies on traffic monitoring equipment or manual surveys. In recent years, with the development of communication technology, especially the widespread application of signaling data, signaling data has become an important data source for analyzing urban travel characteristics, making the collection of traffic travel data more efficient and real-time, which has greatly promoted the in-depth development of traffic data analysis;

[0003] As time goes by, the accuracy of traffic travel information recognition technology based on signaling data will fluctuate, so the original grid records of signaling data need to be regularly re-divided in a more detailed manner. However, the premise of grid division is to evaluate the accuracy of recognition. When to evaluate the accuracy of recognition is of paramount importance. If the evaluation frequency is too frequent, it may lead to the consumption of a large amount of resources. If the evaluation frequency is too sparse, it may lead to a decrease in recognition accuracy. Therefore, it is necessary to find a suitable time for evaluation to refine the original grid, which can improve the accuracy of recognition and effectively improve resource utilization. Summary of the invention

[0004] The purpose of the present invention is to provide a traffic information identification management system and method based on data processing to solve the problems raised in the prior art.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for identifying and managing traffic information based on data processing, the method comprising:

[0006] Step S100: by collecting signaling data, identifying the destination of the person, establishing a travel identification system, collecting the person number in the historical identification record, and summarizing the historical identification record set of a certain person number;

[0007] Step S200: in a historical identification record set of a certain personnel number, calculating the average daily stay time of the personnel number, calculating the average stay time threshold, and determining a feature identification record set of the feature number;

[0008] Step S300: collecting occupations corresponding to feature numbers, obtaining a feature identification record set of a certain occupation, collecting the departure time point of the feature identification record, determining the time period corresponding to the feature identification record, and determining the feature time period of a certain occupation;

[0009] Step S400: setting a training cycle, calculating the recognition success rate of a characteristic time period, determining a monitoring cycle of the characteristic time period, and calculating a risk value of the recognition success rate;

[0010] Step S500: Calculate the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, remind the staff to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, calculate the dynamically adjusted monitoring period.

[0011] Furthermore, step S100 includes:

[0012] Step S101: Divide the urban area into several grids, arrange base stations of communication equipment in the grids, collect signaling data of any person within a certain grid range, number the collected persons, input the signaling data into the travel identification model, identify the destination of the person, and form a travel identification system;

[0013] Step S102: In the historical identification record set, collect the personnel number in a certain historical identification record, aggregate the historical identification records with the same personnel number, and obtain a historical identification record set for a certain personnel number;

[0014] The signaling data includes the specific timestamp of the collected signaling data, the time spent at each location, the destination end point, the actual end point, etc.;

[0015] The specific working process of the travel identification model is to obtain the location information of personnel through communication equipment such as base stations, Wi-Fi access points, etc., clean, denoise and structure the collected raw data, extract the trajectory data of personnel, and establish model recognition rules based on historical trajectories and travel characteristics, such as common routes, destination classification, etc., and use machine learning or deep learning algorithms such as neural networks and spatiotemporal analysis models to identify the destination of personnel under current conditions.

[0016] Further, step S200 includes:

[0017] Step S201: In a historical identification record set of a certain personnel number, obtain the system collection date and personnel stay duration in a certain historical identification record, summarize the historical identification records of the same month, and calculate the average daily stay duration of the personnel according to the following formula:

[0018] ;

[0019] Where T represents the average daily stay time of personnel, t a It is represented by the length of stay of the personnel on day a, and b is represented by the total number of days;

[0020] Step S202: Summarize the average daily stay time of all personnel with personnel numbers, and calculate the average stay time threshold of personnel according to the following formula:

[0021] ;

[0022] Among them, T' represents the threshold of the average stay time of personnel, T c represents the average daily stay time of the person with the cth person number, and d represents the total number of person numbers;

[0023] Step S203: comparing the average daily stay time of a person with a certain person number with a person average stay time threshold, if the average daily stay time of the person exceeds the person average stay time threshold, marking the person number as a feature number, and setting the historical identification record set of the feature number as a feature identification record set;

[0024] By analyzing the collection date and length of stay of historical identification records, aggregating the data and calculating the average daily stay time, we can more accurately reflect the behavioral characteristics of each person. By comparing the average daily stay time of a person with the average stay time threshold of all people, we can effectively screen out people who live or work in the grid for a long time.

[0025] Furthermore, step S300 includes:

[0026] Step S301: collecting occupations corresponding to a certain feature number, summarizing the feature numbers of the same occupation to obtain a feature number set of a certain occupation, and summarizing the feature identification record sets of all feature numbers in the feature number set to obtain a feature identification record set of a certain occupation;

[0027] Step S302: Divide a day into several time periods, obtain the time range corresponding to any time period, collect the departure time point in a feature recognition record in a certain occupational feature recognition record set, obtain the time period corresponding to the feature recognition record, summarize the time periods corresponding to all feature recognition records, collect the number of feature recognition records in a certain time period, and calculate the frequency of occurrence of feature recognition records in the time period according to the following formula:

[0028] ;

[0029] Among them, A represents the frequency of feature recognition records in the time period, B represents the number of feature recognition records in the time period, and C represents the total number of feature recognition records;

[0030] Step S303: setting a frequency threshold, setting the time period in which the frequency of feature recognition records exceeds the frequency threshold as a feature time period, and summarizing them to obtain a feature time period set for a certain occupation;

[0031] By summarizing and analyzing the characteristic numbers and characteristic identification records of the same occupation, it is possible to effectively identify and classify occupation-specific behavior patterns. The behavioral characteristics of people in different occupations will vary;

[0032] Dividing a day into multiple time periods and calculating the frequency of occurrence of feature recognition records in different time periods allows for a more refined analysis of people's behavioral characteristics. For example, the frequency of activities of a certain occupation in a specific time period may be regular. Identifying these "high-frequency" time periods helps to understand people's work patterns, behavioral concentration periods, etc.

[0033] Furthermore, step S400 includes:

[0034] Step S401: Select several consecutive days as a training cycle, obtain a set of recognition records in a certain characteristic time period of a certain day in a characteristic time period set of a certain occupation, collect the inferred destination end point and the actual destination end point of a certain recognition record, if the inferred destination end point is consistent with the actual destination end point, then the recognition record result is successful, if the inferred destination end point is inconsistent with the actual destination end point, then the recognition record result is failed;

[0035] Step S402: Collect the number of successful and failed recognition records in a certain characteristic time period of a certain day, and calculate the recognition success rate in a certain characteristic time period of a certain day according to the following formula:

[0036] ;

[0037] Where X represents the recognition success rate in a certain characteristic time period of a certain day, Y represents the number of successful records in a certain characteristic time period of a certain day, and Z represents the number of failed records in a certain characteristic time period of a certain day;

[0038] Step S403: Summarize the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draw a recognition success rate curve graph of a certain characteristic time period with date as the X-axis and recognition success rate as the Y-axis;

[0039] Step S404: setting a recognition success rate threshold, marking the recognition success rate threshold on the recognition success rate curve graph of the characteristic time period, setting an abnormal days threshold, collecting the number of days that are continuously lower than the recognition success rate threshold, and if the number of days reaches the abnormal days threshold, collecting the date of the last day of the number of days and setting it as the monitoring period of the characteristic time period;

[0040] Step S405: collect dates that are lower than the recognition success rate threshold within the monitoring period and set them as abnormal dates, obtain the recognition success rate of the abnormal dates and set them as abnormal recognition success rate, summarize the abnormal dates, calculate the interval between each abnormal date, and calculate the risk value of the recognition success rate according to the following formula:

[0041] ;

[0042] Among them, H represents the risk value of the recognition success rate, N represents the number of days below the recognition success rate threshold, and E e is the interval duration of the eth segment, f is the total number of interval durations, V is the recognition success rate threshold, S k It is represented as the success rate of the kth anomaly recognition, h is represented as the total number of anomaly recognition success rates, and U is represented as the weight of the risk value;

[0043] By setting the recognition success rate threshold and abnormal days threshold, the system automatically identifies abnormal situations that are continuously below the success rate standard and determines the monitoring cycle. This function provides an early warning for long-term performance degradation and provides a basis for timely adjustment of strategies, thereby improving system stability.

[0044] By analyzing the monitoring cycle and risk value, we can accurately locate the problem time period and its risk level, which helps to reasonably allocate resources, optimize scheduling plans, and improve management efficiency.

[0045] Furthermore, step S500 includes:

[0046] Step S501: In a characteristic time period of a certain occupation, the number of successes and failures of the real-time results of the recognition record is collected respectively, and the real-time recognition success rate of the characteristic time period is calculated within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, step S502 is executed;

[0047] Step S502: If the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased by one, and the dynamically adjusted monitoring period is calculated according to the following formula:

[0048] ;

[0049] Wherein, Q' represents the monitoring period after dynamic adjustment, Q represents the monitoring period of the characteristic time period, W represents the number of risks, j represents the real-time recognition success rate of the characteristic time period, and the recognition success rate of the characteristic time period is calculated according to the monitoring period after dynamic adjustment;

[0050] By combining the number of risk events and the real-time success rate, the monitoring cycle is redefined through a dynamic adjustment formula, so that the system can adapt to the fluctuation of success rate and the change of risk. This dynamic adjustment mechanism avoids the waste of resources or unnecessary delays that may be caused by a fixed monitoring cycle, and improves the accuracy and flexibility of monitoring.

[0051] By dynamically adjusting the monitoring cycle, the system can automatically allocate resources according to the risk level, avoiding excessive monitoring during low-risk time periods, thereby making more efficient use of human and equipment resources.

[0052] In order to better implement the above method, a traffic information identification and management system based on data processing is also proposed, which includes a travel identification system module, a feature number module, a feature time period module, a training module and a dynamic adjustment module;

[0053] Travel identification system module: by collecting signaling data, identifying the destination of the person, establishing a travel identification system, collecting the person number in the historical identification record, and summarizing the historical identification record set of a certain person number;

[0054] Feature number module: in a historical identification record set of a certain personnel number, calculate the average daily stay time of the personnel number, calculate the average stay time threshold, and determine the feature identification record set of the feature number;

[0055] Feature time period module: collects the occupation corresponding to the feature number, obtains a feature identification record set of a certain occupation, collects the starting time point of the feature identification record, determines the time period corresponding to the feature identification record, and determines the feature time period of a certain occupation;

[0056] Training module: set the training cycle, calculate the recognition success rate of the characteristic time period, determine the monitoring cycle of the characteristic time period, and calculate the risk value of the recognition success rate;

[0057] Dynamic adjustment module: calculate the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, the dynamically adjusted monitoring period is calculated.

[0058] Furthermore, the feature number module includes a threshold unit for calculating the average stay time of personnel and a unit for determining feature numbers:

[0059] Unit for calculating the threshold value of the average length of stay of personnel: in the historical identification record set of a certain personnel number, obtain the system collection date and the length of stay of the personnel in a certain historical identification record, summarize the historical identification records of the same month, calculate the average length of stay of the personnel per day, summarize the average length of stay of the personnel of all personnel numbers per day, and calculate the threshold value of the average length of stay of the personnel;

[0060] Determine a characteristic number unit: compare the average daily stay time of a person with a certain personnel number with the average personnel stay time threshold; if the average daily stay time of the person exceeds the average personnel stay time threshold, mark the person number as a characteristic number.

[0061] Furthermore, the training module includes a monitoring cycle calculation unit and an identification success rate risk value calculation unit:

[0062] Calculate the monitoring cycle unit: select several consecutive days as the training cycle, obtain the set of recognition records in a certain characteristic time period of a certain day in the characteristic time period set of a certain occupation, collect the inferred destination end point and the actual destination end point of a certain recognition record, collect the number of success and failure results of the recognition record in a certain characteristic time period of a certain day, calculate the recognition success rate in a certain characteristic time period of a certain day, summarize the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draw a recognition success rate curve of a certain characteristic time period with the date as the X-axis and the recognition success rate as the Y-axis; set the recognition success rate threshold, and mark the recognition success rate threshold on the recognition success rate curve of the certain characteristic time period, set the abnormal day threshold, collect the number of days that are continuously lower than the recognition success rate threshold, if the number of days reaches the abnormal day threshold, collect the date of the last day of the number of days, and set it as the monitoring cycle of a certain characteristic time period;

[0063] The unit for calculating the risk value of the recognition success rate is as follows: the dates that are lower than the recognition success rate threshold during the monitoring period are collected and set as abnormal dates, the recognition success rate of the abnormal dates is obtained and set as the abnormal recognition success rate, the abnormal dates are summarized, the interval between each abnormal date is calculated, and the risk value of the recognition success rate is calculated.

[0064] Furthermore, the dynamic adjustment module includes a real-time evaluation unit and a monitoring period unit after calculating the dynamic adjustment:

[0065] Real-time evaluation unit: in a characteristic time period of a certain occupation, the number of successes and failures of the real-time results of the recognition record is collected respectively, and the real-time recognition success rate of the characteristic time period is calculated within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid;

[0066] Calculate the dynamically adjusted monitoring period unit: If the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased once, and the dynamically adjusted monitoring period is calculated. According to the dynamically adjusted monitoring period, the recognition success rate of the characteristic time period is calculated.

[0067] Compared with the prior art, the present invention has the following beneficial effects:

[0068] 1. By setting the real-time recognition success rate threshold and risk value, combined with the mechanism of dynamically adjusting the monitoring cycle, it can remind and adjust the grid division when abnormal travel behavior occurs;

[0069] 2. By calculating the residence time threshold and real-time recognition success rate, this method can accurately identify characteristic grids and high-frequency behavior time periods, optimize resource allocation, avoid excessive monitoring of low-demand areas or time periods, and improve system resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 A flow chart of a method for identifying and managing traffic information based on data processing according to the present invention;

[0071] Figure 2 The present invention is a schematic structural diagram of a traffic information identification and management system based on data processing. DETAILED DESCRIPTION

[0072] 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.

[0073] See also Figure 1 and Figure 2 The present invention provides a technical solution: a method for identifying and managing traffic information based on data processing, the method comprising:

[0074] Step S100: by collecting signaling data, identifying the destination of the person, establishing a travel identification system, collecting the person number in the historical identification record, and summarizing the historical identification record set of a certain person number;

[0075] Wherein, step S100 includes:

[0076] Step S101: Divide the urban area into several grids, arrange base stations of communication equipment in the grids, collect signaling data of any person within a certain grid range, number the collected persons, input the signaling data into the travel identification model, identify the destination of the person, and form a travel identification system;

[0077] Step S102: In the historical identification record set, collect the personnel number in a certain historical identification record, aggregate the historical identification records with the same personnel number, and obtain a historical identification record set for a certain personnel number.

[0078] Step S200: in a historical identification record set of a certain personnel number, calculating the average daily stay time of the personnel number, calculating the average stay time threshold, and determining a feature identification record set of the feature number;

[0079] Wherein, step S200 includes:

[0080] Step S201: In a historical identification record set of a certain personnel number, obtain the system collection date and personnel stay duration in a certain historical identification record, summarize the historical identification records of the same month, and calculate the average daily stay duration of the personnel according to the following formula:

[0081] ;

[0082] Where T represents the average daily stay time of personnel, t a It is represented by the length of stay of the personnel on day a, and b is represented by the total number of days;

[0083] Step S202: Summarize the average daily stay time of all personnel with personnel numbers, and calculate the average stay time threshold of personnel according to the following formula:

[0084] ;

[0085] Among them, T' represents the threshold of the average stay time of personnel, T c represents the average daily stay time of the person with the cth person number, and d represents the total number of person numbers;

[0086] Step S203: Compare the average daily stay time of a person with a certain personnel number with the personnel average stay time threshold. If the average daily stay time of the person exceeds the personnel average stay time threshold, mark the person number as a feature number, and set the historical identification record set of the feature number as the feature identification record set.

[0087] Step S300: collecting occupations corresponding to feature numbers, obtaining a feature identification record set of a certain occupation, collecting the departure time point of the feature identification record, determining the time period corresponding to the feature identification record, and determining the feature time period of a certain occupation;

[0088] Wherein, step S300 includes:

[0089] Step S301: collecting occupations corresponding to a certain feature number, summarizing the feature numbers of the same occupation to obtain a feature number set of a certain occupation, and summarizing the feature identification record sets of all feature numbers in the feature number set to obtain a feature identification record set of a certain occupation;

[0090] Step S302: Divide a day into several time periods, obtain the time range corresponding to any time period, collect the departure time point in a feature recognition record in a certain occupational feature recognition record set, obtain the time period corresponding to the feature recognition record, summarize the time periods corresponding to all feature recognition records, collect the number of feature recognition records in a certain time period, and calculate the frequency of occurrence of feature recognition records in the time period according to the following formula:

[0091] ;

[0092] Among them, A represents the frequency of feature recognition records in the time period, B represents the number of feature recognition records in the time period, and C represents the total number of feature recognition records;

[0093] Step S303: setting a frequency threshold, setting the time period in which the frequency of feature recognition records exceeds the frequency threshold as a feature time period, and summarizing them to obtain a feature time period set for a certain occupation;

[0094] For example, there are 5 feature recognition records in the first occupation, the departure time of the first feature recognition record is 7:45, the departure time of the second feature recognition record is 7:35, the departure time of the third feature recognition record is 12:15, the departure time of the fourth feature recognition record is 8:00, and the departure time of the fifth feature recognition record is 11:00. A day is divided into the following 4 time periods: the morning time period is 06:00-10:00, the noon time period is 10:00-14:00, the afternoon time period is 14:00-18:00, and the evening time period is 18:00-22:00;

[0095] The calculated frequency in the morning is 0.6, the frequency at noon is 0.4, and the frequency threshold is set to 0.5. Therefore, the characteristic time period of the first occupation is morning.

[0096] Step S400: setting a training cycle, calculating the recognition success rate of a characteristic time period, determining a monitoring cycle of the characteristic time period, and calculating a risk value of the recognition success rate;

[0097] Wherein, step S400 includes:

[0098] Step S401: Select several consecutive days as a training cycle, obtain a set of recognition records in a certain characteristic time period of a certain day in a characteristic time period set of a certain occupation, collect the inferred destination end point and the actual destination end point of a certain recognition record, if the inferred destination end point is consistent with the actual destination end point, then the recognition record result is successful, if the inferred destination end point is inconsistent with the actual destination end point, then the recognition record result is failed;

[0099] Step S402: Collect the number of successful and failed recognition records in a certain characteristic time period of a certain day, and calculate the recognition success rate in a certain characteristic time period of a certain day according to the following formula:

[0100] ;

[0101] Where X represents the recognition success rate in a certain characteristic time period of a certain day, Y represents the number of successful records in a certain characteristic time period of a certain day, and Z represents the number of failed records in a certain characteristic time period of a certain day;

[0102] Step S403: Summarize the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draw a recognition success rate curve graph of a certain characteristic time period with date as the X-axis and recognition success rate as the Y-axis;

[0103] Step S404: setting a recognition success rate threshold, marking the recognition success rate threshold on the recognition success rate curve graph of the characteristic time period, setting an abnormal days threshold, collecting the number of days that are continuously lower than the recognition success rate threshold, and if the number of days reaches the abnormal days threshold, collecting the date of the last day of the number of days and setting it as the monitoring period of the characteristic time period;

[0104] Step S405: collect dates that are lower than the recognition success rate threshold within the monitoring period and set them as abnormal dates, obtain the recognition success rate of the abnormal dates and set them as abnormal recognition success rate, summarize the abnormal dates, calculate the interval between each abnormal date, and calculate the risk value of the recognition success rate according to the following formula:

[0105] ;

[0106] Among them, H represents the risk value of the recognition success rate, N represents the number of days below the recognition success rate threshold, and E eis the interval duration of the eth segment, f is the total number of interval durations, V is the recognition success rate threshold, S k It is represented as the success rate of the kth anomaly recognition, h is represented as the total number of anomaly recognition success rates, and U is represented as the weight of the risk value;

[0107] For example, set the recognition success rate threshold V to 0.6, the abnormal day threshold to 2 days, the success rate of 2024-11-01 is 0.50, the success rate of 2024-11-02 is 0.67, the success rate of 2024-11-03 is 0.55, the success rate of 2024-11-04 is 0.45, 2024-11-01 and 2024-11-03 are abnormal dates, and the interval from 2024-11-01 to 2024-11-03 is 2 days. The calculated risk value is 0.3.

[0108] Step S500: Calculate the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, remind the staff to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, calculate the dynamically adjusted monitoring period.

[0109] Wherein, step S500 includes:

[0110] Step S501: In a characteristic time period of a certain occupation, the number of successes and failures of the real-time results of the recognition record is collected respectively, and the real-time recognition success rate of the characteristic time period is calculated within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, step S502 is executed;

[0111] Step S502: If the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased by one, and the dynamically adjusted monitoring period is calculated according to the following formula:

[0112] ;

[0113] Wherein, Q' represents the monitoring period after dynamic adjustment, Q represents the monitoring period of the characteristic time period, W represents the number of risks, j represents the real-time recognition success rate of the characteristic time period, and the recognition success rate of the characteristic time period is calculated according to the monitoring period after dynamic adjustment.

[0114] In order to better implement the above method, a traffic information identification and management system based on data processing is also proposed, the system includes a travel identification system module, a feature number module, a feature time period module, a training module and a dynamic adjustment module;

[0115] Travel identification system module: by collecting signaling data, identifying the destination of the person, establishing a travel identification system, collecting the person number in the historical identification record, and summarizing the historical identification record set of a certain person number;

[0116] Feature number module: in a historical identification record set of a certain personnel number, calculate the average daily stay time of the personnel number, calculate the average stay time threshold, and determine the feature identification record set of the feature number;

[0117] Among them, the feature number module includes a unit for calculating the average stay time threshold of personnel and a unit for determining the feature number:

[0118] Unit for calculating the threshold value of the average length of stay of personnel: in the historical identification record set of a certain personnel number, obtain the system collection date and the length of stay of the personnel in a certain historical identification record, summarize the historical identification records of the same month, calculate the average length of stay of the personnel per day, summarize the average length of stay of the personnel of all personnel numbers per day, and calculate the threshold value of the average length of stay of the personnel;

[0119] Determine a characteristic number unit: compare the average daily stay time of a person with a certain personnel number with the average personnel stay time threshold; if the average daily stay time of the person exceeds the average personnel stay time threshold, mark the person number as a characteristic number.

[0120] Feature time period module: collects the occupation corresponding to the feature number, obtains a feature identification record set of a certain occupation, collects the starting time point of the feature identification record, determines the time period corresponding to the feature identification record, and determines the feature time period of a certain occupation;

[0121] Training module: set the training cycle, calculate the recognition success rate of the characteristic time period, determine the monitoring cycle of the characteristic time period, and calculate the risk value of the recognition success rate;

[0122] The training module includes a monitoring cycle calculation unit and an identification success rate risk value calculation unit:

[0123] Calculate the monitoring cycle unit: select several consecutive days as the training cycle, obtain the set of recognition records in a certain characteristic time period of a certain day in the characteristic time period set of a certain occupation, collect the inferred destination end point and the actual destination end point of a certain recognition record, collect the number of success and failure results of the recognition record in a certain characteristic time period of a certain day, calculate the recognition success rate in a certain characteristic time period of a certain day, summarize the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draw a recognition success rate curve of a certain characteristic time period with the date as the X-axis and the recognition success rate as the Y-axis; set the recognition success rate threshold, and mark the recognition success rate threshold on the recognition success rate curve of the certain characteristic time period, set the abnormal day threshold, collect the number of days that are continuously lower than the recognition success rate threshold, if the number of days reaches the abnormal day threshold, collect the date of the last day of the number of days, and set it as the monitoring cycle of a certain characteristic time period;

[0124] The unit for calculating the risk value of the recognition success rate is as follows: the dates that are lower than the recognition success rate threshold during the monitoring period are collected and set as abnormal dates, the recognition success rate of the abnormal dates is obtained and set as the abnormal recognition success rate, the abnormal dates are summarized, the interval between each abnormal date is calculated, and the risk value of the recognition success rate is calculated.

[0125] Dynamic adjustment module: calculate the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, the dynamically adjusted monitoring period is calculated.

[0126] The dynamic adjustment module includes a real-time evaluation unit and a monitoring cycle unit after calculating the dynamic adjustment:

[0127] Real-time evaluation unit: in a characteristic time period of a certain occupation, the number of successes and failures of the real-time results of the recognition record is collected respectively, and the real-time recognition success rate of the characteristic time period is calculated within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid;

[0128] Calculate the dynamically adjusted monitoring period unit: If the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased once, and the dynamically adjusted monitoring period is calculated. According to the dynamically adjusted monitoring period, the recognition success rate of the characteristic time period is calculated.

[0129] 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.

Claims

1. A method for identifying and managing traffic information based on data processing, characterized in that: Methods include: Step S100: by collecting signaling data, identifying the destination of the person, establishing a travel identification system, collecting the person number in the historical identification record, and summarizing the historical identification record set of a certain person number; Step S200: in a historical identification record set of a certain personnel number, calculating the average daily stay time of the personnel number, calculating the average stay time threshold, and determining a feature identification record set of the feature number; Step S300: collecting occupations corresponding to feature numbers, obtaining a feature identification record set of a certain occupation, collecting the departure time point of the feature identification record, determining the time period corresponding to the feature identification record, and determining the feature time period of a certain occupation; Step S400: setting a training cycle, calculating the recognition success rate of a characteristic time period, determining a monitoring cycle of the characteristic time period, and calculating a risk value of the recognition success rate; Step S500: Calculate the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, remind the staff to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, calculate the dynamically adjusted monitoring period.

2. A method for identifying and managing traffic information based on data processing according to claim 1, characterized in that: The step S100 includes the following steps: Step S101: Divide the urban area into several grids, arrange base stations of communication equipment in the grids, collect signaling data of any person within a certain grid range, number the collected persons, input the signaling data into the travel identification model, identify the destination of the person, and form a travel identification system; Step S102: In the historical identification record set, collect the personnel number in a certain historical identification record, aggregate the historical identification records with the same personnel number, and obtain a historical identification record set for a certain personnel number.

3. The method for identifying and managing traffic information based on data processing according to claim 2, characterized in that: The step S200 includes the following steps: Step S201: In a historical identification record set of a certain personnel number, obtain the system collection date and personnel stay duration in a certain historical identification record, summarize the historical identification records of the same month, and calculate the average daily stay duration of the personnel according to the following formula: ； Where T represents the average daily stay time of personnel, t a It is represented by the length of stay of the personnel on day a, and b is represented by the total number of days; Step S202: Summarize the average daily stay time of all personnel with personnel numbers, and calculate the average stay time threshold of personnel according to the following formula: ； Among them, T' represents the threshold of the average length of stay of personnel, T c represents the average daily stay time of the person with the cth person number, and d represents the total number of person numbers; Step S203: Compare the average daily stay time of a person with a certain personnel number with the personnel average stay time threshold. If the average daily stay time of the person exceeds the personnel average stay time threshold, mark the person number as a feature number, and set the historical identification record set of the feature number as the feature identification record set.

4. The method for identifying and managing traffic information based on data processing according to claim 3 is characterized in that: The step S300 includes the following steps: Step S301: collecting occupations corresponding to a certain feature number, summarizing the feature numbers of the same occupation to obtain a feature number set of a certain occupation, and summarizing the feature identification record sets of all feature numbers in the feature number set to obtain a feature identification record set of a certain occupation; Step S302: Divide a day into several time periods, obtain the time range corresponding to any time period, collect the departure time point in a feature recognition record in a certain occupational feature recognition record set, obtain the time period corresponding to the feature recognition record, summarize the time periods corresponding to all feature recognition records, collect the number of feature recognition records in a certain time period, and calculate the frequency of occurrence of feature recognition records in the time period according to the following formula: ； Among them, A represents the frequency of feature recognition records in the time period, B represents the number of feature recognition records in the time period, and C represents the total number of feature recognition records; Step S303: setting a frequency threshold, setting the time period in which the frequency of feature recognition records exceeds the frequency threshold as a feature time period, and summarizing them to obtain a feature time period set for a certain occupation.

5. The method for identifying and managing traffic information based on data processing according to claim 4 is characterized in that: The step S400 includes the following steps: Step S401: Select several consecutive days as a training cycle, obtain a set of recognition records in a certain characteristic time period of a certain day in a characteristic time period set of a certain occupation, collect the inferred destination end point and the actual destination end point of a certain recognition record, if the inferred destination end point is consistent with the actual destination end point, then the recognition record result is successful, if the inferred destination end point is inconsistent with the actual destination end point, then the recognition record result is failed; Step S402: Collect the number of successful and failed recognition records in a certain characteristic time period of a certain day, and calculate the recognition success rate in a certain characteristic time period of a certain day according to the following formula: ； Where X represents the recognition success rate in a certain characteristic time period of a certain day, Y represents the number of successful records in a certain characteristic time period of a certain day, and Z represents the number of failed records in a certain characteristic time period of a certain day; Step S403: Summarize the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draw a recognition success rate curve graph of a certain characteristic time period with date as the X-axis and recognition success rate as the Y-axis; Step S404: setting a recognition success rate threshold, marking the recognition success rate threshold on the recognition success rate curve graph of the characteristic time period, setting an abnormal days threshold, collecting the number of days that are continuously lower than the recognition success rate threshold, and if the number of days reaches the abnormal days threshold, collecting the date of the last day of the number of days and setting it as the monitoring period of the characteristic time period; Step S405: collect dates that are lower than the recognition success rate threshold within the monitoring period and set them as abnormal dates, obtain the recognition success rate of the abnormal dates and set them as abnormal recognition success rate, summarize the abnormal dates, calculate the interval between each abnormal date, and calculate the risk value of the recognition success rate according to the following formula: ； Among them, H represents the risk value of the recognition success rate, N represents the number of days below the recognition success rate threshold, and E e is the interval duration of the eth segment, f is the total number of interval durations, V is the recognition success rate threshold, S k It is represented as the kth anomaly recognition success rate, h is represented as the total number of anomaly recognition success rates, and U is represented as the weight of the risk value.

6. The method for identifying and managing traffic information based on data processing according to claim 5, characterized in that: The step S500 includes the following steps: Step S501: In a characteristic time period of a certain occupation, the number of successes and failures of the real-time results of the recognition record is collected respectively, and the real-time recognition success rate of the characteristic time period is calculated within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, step S502 is executed; Step S502: If the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased by one, and the dynamically adjusted monitoring period is calculated according to the following formula: ； Wherein, Q' represents the monitoring period after dynamic adjustment, Q represents the monitoring period of the characteristic time period, W represents the number of risks, j represents the real-time recognition success rate of the characteristic time period, and the recognition success rate of the characteristic time period is calculated according to the monitoring period after dynamic adjustment.

7. A traffic information identification and management system based on data processing, used to implement a traffic information identification and management method based on data processing as claimed in any one of claims 1 to 6, characterized in that: The system includes a travel identification system module, a feature numbering module, a feature time period module, a training module and a dynamic adjustment module; The travel identification system module: collects signaling data, identifies the destination of the person, establishes a travel identification system, collects the person number in the historical identification record, and summarizes the historical identification record set of a certain person number; The feature number module: in a historical identification record set of a certain personnel number, calculates the average daily stay time of the personnel number, calculates the average stay time threshold, and determines the feature identification record set of the feature number; The characteristic time period module: collects the occupation corresponding to the characteristic number, obtains a characteristic identification record set of a certain occupation, collects the starting time point of the characteristic identification record, determines the time period corresponding to the characteristic identification record, and determines the characteristic time period of a certain occupation; The training module: sets a training cycle, calculates the recognition success rate of a characteristic time period, determines a monitoring cycle of the characteristic time period, and calculates a risk value of the recognition success rate; The dynamic adjustment module calculates the real-time recognition success rate of the characteristic time period within the monitoring period of the characteristic time period. If the real-time recognition success rate is lower than the recognition success rate threshold, the staff is reminded to re-divide the grid. If the real-time recognition success rate is higher than the recognition success rate threshold, the dynamically adjusted monitoring period is calculated.

8. The traffic information identification and management system based on data processing according to claim 7 is characterized in that: The feature number module includes a unit for calculating the average stay time threshold of personnel and a unit for determining feature numbers: The personnel average stay time threshold calculating unit: in a historical identification record set of a certain personnel number, obtain the system collection date and personnel stay time in a certain historical identification record, summarize the historical identification records of the same month, calculate the personnel average daily stay time, summarize the personnel average daily stay time of all personnel numbers, and calculate the personnel average stay time threshold; The characteristic number determination unit compares the average daily stay time of a person with a certain personnel number with the average personnel stay time threshold, and if the average daily stay time of the person exceeds the average personnel stay time threshold, marks the person number as a characteristic number.

9. The traffic information identification and management system based on data processing according to claim 7 is characterized in that: The training module includes a monitoring cycle calculation unit and an identification success rate risk value calculation unit: The calculation monitoring cycle unit: selects several consecutive days as a training cycle, obtains a set of recognition records in a certain characteristic time period of a certain day in a characteristic time period set of a certain occupation, collects the inferred destination end point and the actual destination end point of a certain recognition record, and respectively collects the number of success and failure results of the recognition record in a certain characteristic time period of a certain day, calculates the recognition success rate in a certain characteristic time period of a certain day, summarizes the recognition success rate of a certain characteristic time period in the training cycle in chronological order, and draws a recognition success rate curve chart of a certain characteristic time period with date as the X-axis and recognition success rate as the Y-axis; sets a recognition success rate threshold, and marks the recognition success rate threshold on the recognition success rate curve chart of the certain characteristic time period, sets an abnormal day threshold, collects the number of days that are continuously lower than the recognition success rate threshold, and if the number of days reaches the abnormal day threshold, collects the date of the last day of the number of days and sets it as the monitoring cycle of a certain characteristic time period; The unit for calculating the risk value of the recognition success rate: collects dates that are lower than the recognition success rate threshold during the monitoring period and sets them as abnormal dates, obtains the recognition success rate of the abnormal dates and sets them as abnormal recognition success rate, summarizes the abnormal dates, calculates the interval time between each abnormal date, and calculates the risk value of the recognition success rate.

10. The traffic information identification and management system based on data processing according to claim 7, characterized in that: The dynamic adjustment module includes a real-time evaluation unit and a monitoring period unit after calculating the dynamic adjustment: The real-time evaluation unit: collects the number of successes and failures of the real-time results of the recognition record in a characteristic time period of a certain occupation, calculates the real-time recognition success rate of the characteristic time period in the monitoring period of the characteristic time period, and reminds the staff to re-divide the grid if the real-time recognition success rate is lower than the recognition success rate threshold; The unit for calculating the dynamically adjusted monitoring period: if the real-time recognition success rate is lower than the risk value of the recognition success rate, the risk times are increased once, the dynamically adjusted monitoring period is calculated, and the recognition success rate of the characteristic time period is calculated according to the dynamically adjusted monitoring period.

Images