Automatic qualitative attribution method for running water fluctuation

Abstract

The invention discloses an automatic qualitative attribution method for running water fluctuation, which comprises the following steps: S1, calculating a running water related index, a previous week synchronization index and a previous week synchronization index in the current period, the index needing to be calculated being an index after the running water is disassembled; s2, if running water is increased by gt compared with the last week; the increase is gt on year-on-year basis; 5%, determining the rising; the running water is decreased by gt compared with the last week; the amplitude gt is decreased from the year-on-year to the year-on-year; 5%, which is determined to be decline; other conditions are determined as fluctuations and are not attributed to the fluctuations; s3, if the qualitative result is rising; the two year-on-year increase ranges are gt; the subdivision is qualitative as greatly rising; the year-on-year increase is gt; if the upper and upper weeks increase on the year-on-year basis, continuous rising is indicated, and the subdivision is qualitative as continuous rising; other subdivisions are determined as common rising; according to the invention, qualitative flowing water changes of different cities are automatically given, rising, falling or natural fluctuation is visually displayed, and reasons are given; a detailed cause and a main channel causing flowing water fluctuation can be seen by clicking a specific date.

Description

Technical Field

[0001] The present invention belongs to the technical field of online car-hailing, and specifically relates to an automatic qualitative attribution method for flow fluctuations. Background Art

[0002] In the daily business operation process, cash flow is an important operating indicator, which is affected by many process indicators. When cash flow fluctuates abnormally, it is generally calculated through indicator statistics, monitoring and analyzing the trend, increase / decrease of related indicators, and making historical comparisons. This method is not intuitive, has low analysis efficiency, and high repetitive work. In addition, different people have different analysis standards, and the definition and splitting methods of related indicators are not unified, which easily leads to conflicting conclusions, and subsequent optimization measures cannot form a synergy.

[0003] To this end, the present invention designs an automatic qualitative attribution method for water flow fluctuations. Summary of the invention

[0004] The purpose of the present invention is to provide a method for automatic qualitative attribution of water flow fluctuations to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: a method for automatic qualitative attribution of turnover fluctuations, S1: calculating the turnover-related indicators of the current period, the indicators of the same period last week, and the indicators of the same period the week before last, where the indicators to be calculated are indicators after the turnover is disassembled;

[0006] S2: If the turnover increases by more than 5% compared with the previous week, or the previous week, it is qualitatively an increase; if the turnover decreases by more than 5% compared with the previous week, or the previous week, it is qualitatively a decrease; other situations are qualitatively fluctuations, and no further attribution is made;

[0007] S3: If it is characterized as an increase; if both year-on-year increases are greater than 10%, the sub-qualification is a substantial increase; if the year-on-year increase last week is greater than the year-on-year increase the week before last, it means that it is continuing to rise, and the sub-qualification is a continuous increase; other sub-qualifications are ordinary increases;

[0008] S4: If it is characterized as an increase; attribute the reasons for the increase: the number of orders increased, but the response rate decreased, indicating that the increase was driven by an increase in demand, and it is attributed to the increase in demand; the number of orders did not increase, but the number of responses increased, and the increase in turnover was mainly driven by more responses, and it is attributed to the increase in responses; for the online car-hailing business in the aggregation model, after the response, there is a PK between multiple transport capacities. If the number of responses did not increase, the number of orders notified to drivers increased, that is, the number of orders successfully PKed increased, and it is attributed to the increase in competitiveness; after being notified of an order, the driver may not necessarily complete the order because the driver postponed the order or the passenger's itinerary changed. The number of orders notified to the driver did not increase. When the number of completed orders increased, it was attributed to the increase in fulfillment; when the number of completed orders did not increase, but the turnover increased, it was mainly the increase in the average price of each order that increased the turnover, indicating that the order structure has changed, and it is attributed to the increase in the average price of each order;

[0009] S5: If it is determined to be an increase and initially attributed to an increase in demand, further attribute the source and reason of the increase; calculate the top 5 channels with increased flow by source, and the order volume by time period; by source and time period, if the increase in a certain period is >100%, it is attributed to a local surge; if it is an increase in all periods, it is attributed to a general increase; if there is no local surge, nor an increase in all periods, there are increases and decreases, it is attributed to small fluctuations;

[0010] S6: If it is characterized as a decline; if both year-on-year declines are greater than 10%, the sub-qualification is a sharp decline; if the year-on-year decline last week is less than the year-on-year decline the week before last, it means that it is continuing to decline, and the sub-qualification is a continuous decline; other sub-qualifications are ordinary declines;

[0011] S7: If it is characterized as a decrease; generally, when demand decreases, if the transportation capacity remains unchanged, the response rate will increase. When the number of orders decreases and the response rate decreases, it means that both supply and demand are decreasing, which can be attributed to the decrease in both supply and demand. When the number of orders decreases and the response rate increases, it is uncertain whether the transportation capacity has decreased, which can be attributed to the decrease in demand. The number of orders has not decreased, but the number of responses has decreased, which can be attributed to the decrease in responses, that is, the transportation capacity has decreased. The number of responses has not decreased, but the number of orders notified to drivers has decreased, which can be attributed to the decrease in competitiveness. The number of orders notified to drivers has not decreased, but the number of completed orders has decreased, which can be attributed to the decrease in performance. The number of completed orders has not decreased, but the turnover has decreased. At this time, the order structure has changed, which can be attributed to the decrease in average orders.

[0012] S8: If it is characterized as a decline and initially attributed to a decrease in demand, further attribute the main channels and reasons for the decline; calculate the top 5 channels with increased flow by source, and the order volume by time period; from a source and time period perspective, if there is an increase in all time periods, attribute it to a general decline; if there is not a decline in all time periods, but there are increases and decreases, attribute it to small fluctuations.

[0013] Preferably, turnover = number of completed orders * average order = number of orders notified to drivers * order completion rate after notification * average order = number of responses * PK success rate * order completion rate after notification * average order = number of orders * response rate * PK success rate * order completion rate after notification * average order.

[0014] Preferably, in step S2 and step S3, the threshold of the increase and the threshold of the decrease can be set artificially according to the city.

[0015] Preferably, in step S5 and step S6, the threshold of the increase and the threshold of the decrease can be set artificially according to the city.

[0016] Compared with the prior art, the beneficial effects of the present invention are: the present invention automatically gives qualitative flow changes by city, intuitively displays whether it is rising, falling or natural fluctuations, and gives reasons; clicking on a specific date can see detailed attribution and the main channels causing flow fluctuations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0018] 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.

[0019] See also Figure 1 , the present invention provides a technical solution: a method for automatic qualitative attribution of turnover fluctuations, the specific steps include: S1: calculating the turnover and related indicators of the current period, the indicators of the same period last week, and the indicators of the same period the week before last, and the indicators to be calculated are the indicators after the turnover is disassembled;

[0020] Turnover = number of completed orders * average order = number of orders notified to drivers * order completion rate after notification * average order = number of responses * PK success rate * order completion rate after notification * average order = number of orders * response rate * PK success rate * order completion rate after notification * average order.

[0021] S2: If the turnover increases by >5% compared with last week, or the week before last, it is characterized as an increase; if the turnover decreases by >5% compared with last week, or the week before last, it is characterized as a decrease; in other cases, it is characterized as fluctuation, and no further attribution is made.

[0022] S3: If it is characterized as an increase; both year-on-year growth rates are > 10%, the sub-characterization is a sharp increase; the year-on-year increase last week is > the year-on-year increase the week before last, indicating a continuous increase, and the sub-characterization is a continuous increase; other sub-characterizations are ordinary increases.

[0023] S4: If it is characterized as an increase; attribute the reasons for the increase: the number of orders increased, but the response rate decreased, which means that the increase was driven by the increase in demand, and it is attributed to the increase in demand; the number of orders did not increase, but the number of responses increased, and the increase in turnover was mainly driven by more responses, and it is attributed to the increase in responses; for the online car-hailing business in the aggregation model, there is a PK stage among multiple transport companies after the response, if the number of responses did not increase, but the number of orders notified to drivers increased (i.e. the number of successful PK orders increased), it is attributed to the increase in competitiveness; after the driver is notified of the order, he may not complete the order because he postpones the order or the passenger's itinerary changes, so the number of orders notified to the driver did not increase, and when the number of completed orders increased, it is attributed to the increase in fulfillment; when the number of completed orders did not increase, but the turnover increased, it was mainly the increase in the average price of each order that increased the turnover, indicating that the order structure has changed, and it is attributed to the increase in the average price of each order.

[0024] S5: If it is determined to be an increase, and it is initially attributed to an increase in demand, further attribute the source and reason of the increase. Calculate the top 5 channels with increased flow by source, and the order volume by time period. According to the source and time period, if the increase in a certain period is >100%, it is attributed to a local surge; if it is an increase in all periods, it is attributed to a general increase; if there is no local surge, nor an increase in all periods, there are increases and decreases, which is attributed to small fluctuations.

[0025] S6: If it is characterized as a decline; if both year-on-year declines are >10%, the sub-categories are characterized as a sharp decline; if the year-on-year decline last week is < the year-on-year decline the week before last, it means that it is continuing to decline, and the sub-categories are characterized as a continuous decline; other sub-categories are characterized as ordinary declines.

[0026] S7: If it is characterized as a decrease; generally when demand decreases, if the capacity remains unchanged, the response rate will increase. When the number of orders decreases and the response rate decreases, it means that both supply and demand are decreasing, which can be attributed to the decrease in both supply and demand; when the number of orders decreases and the response rate increases, it is uncertain whether the capacity has decreased, which can be attributed to the decrease in demand; when the number of orders does not decrease, but the number of responses decreases, which can be attributed to the decrease in responses, that is, the capacity has decreased; when the number of responses does not decrease, the number of orders notified to drivers decreases, which can be attributed to the decrease in competitiveness; when the number of orders notified to drivers does not decrease, the number of completed orders decreases, which can be attributed to the decrease in performance; when the number of completed orders does not decrease, the turnover decreases, and the order structure changes, which can be attributed to the decrease in average orders.

[0027] S8: If it is characterized as a decline and initially attributed to a decrease in demand, further attribute the main channels and reasons for the decline; calculate the top 5 channels with increased flow by source, and the order volume by time period; from a source and time period perspective, if there is an increase in all time periods, attribute it to a general decline; if there is not a decline in all time periods, but there are increases and decreases, attribute it to small fluctuations.

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for automatic qualitative attribution of flow fluctuations, characterized by: S1: Calculate the current period's turnover-related indicators, the indicators for the same period last week, and the indicators for the same period the week before last. The indicators to be calculated are the indicators after the turnover is disassembled; S2: If the turnover increases by more than 5% compared with the previous week, or the previous week, it is qualitatively an increase; if the turnover decreases by more than 5% compared with the previous week, or the previous week, it is qualitatively a decrease; other situations are qualitatively fluctuations, and no further attribution is made; S3: If it is characterized as an increase; if both year-on-year increases are greater than 10%, the sub-qualification is a substantial increase; if the year-on-year increase last week is greater than the year-on-year increase the week before last, it means that the price is continuing to rise, and the sub-qualification is a continuous increase; other sub-qualifications are ordinary increases; S4: If it is characterized as an increase; attribute the reasons for the increase: the number of orders increased, but the response rate decreased, indicating that the increase was driven by an increase in demand, and it is attributed to the increase in demand; the number of orders did not increase, but the number of responses increased, and the increase in turnover was mainly driven by more responses, and it is attributed to the increase in responses; for the online car-hailing business in the aggregation model, after the response, there is a PK between multiple transport capacities. If the number of responses did not increase, the number of orders notified to drivers increased, that is, the number of orders successfully PKed increased, and it is attributed to the increase in competitiveness; after being notified of an order, the driver may not necessarily complete the order because the driver postponed the order or the passenger's itinerary changed. The number of orders notified to the driver did not increase. When the number of completed orders increased, it was attributed to the increase in fulfillment; when the number of completed orders did not increase, but the turnover increased, it was mainly the increase in the average price of each order that increased the turnover, indicating that the order structure has changed, and it is attributed to the increase in the average price of each order; S5: If it is determined to be an increase and initially attributed to an increase in demand, further attribute the source and reason of the increase; calculate the top 5 channels with increased flow by source, and the order volume by time period; by source and time period, if the increase in a certain period is >100%, it is attributed to a local surge; if it is an increase in all periods, it is attributed to a general increase; if there is no local surge, nor an increase in all periods, there are increases and decreases, it is attributed to small fluctuations; S6: If it is characterized as a decline; if both year-on-year declines are greater than 10%, the sub-qualification is a sharp decline; if the year-on-year decline last week is less than the year-on-year decline the week before, it means that it is continuing to decline, and the sub-qualification is a continuous decline; other sub-qualifications are ordinary declines; S7: If it is characterized as a decline; Generally, when demand decreases, if the transportation capacity remains unchanged, the response rate will increase. When the number of orders decreases and the response rate decreases, it means that both supply and demand are decreasing, which can be attributed to the decrease in both supply and demand. When the number of orders decreases and the response rate increases, it is uncertain whether the transportation capacity has decreased, which can be attributed to the decrease in demand. When the number of orders does not decrease, but the number of responses decreases, it can be attributed to the decrease in responses, that is, the transportation capacity has decreased. When the number of responses does not decrease, but the number of orders notified to drivers decreases, it can be attributed to the decrease in competitiveness. When the number of orders notified to drivers does not decrease, but the number of completed orders decreases, it can be attributed to the decrease in performance. When the number of completed orders does not decrease, but the turnover decreases, the order structure changes, which can be attributed to the decrease in average orders. S8: If it is qualitatively a decline and is initially attributed to a decline in demand, further attribute the decline to the main channels and reasons; calculate the top 5 channels with increased flow by source, and the order volume by time period; if the flow increases in all time periods, attribute it to a general decline; It did not fall throughout the entire period, there were ups and downs, which were attributed to small fluctuations.

2. The method for automatic qualitative attribution of water flow fluctuation according to claim 1, characterized in that: Turnover = number of completed orders * average order = number of orders notified to drivers * order completion rate after notification * average order = number of responses * PK success rate * order completion rate after notification * average order = number of orders * response rate * PK success rate * order completion rate after notification * average order.

3. The method for automatic qualitative attribution of water flow fluctuation according to claim 1, characterized in that: In step S2 and step S3, the threshold of the increase and the threshold of the decrease can be set manually according to the city.

4. The method for automatic qualitative attribution of water flow fluctuation according to claim 1, characterized in that: In step S5 and step S6, the threshold of the increase and the threshold of the decrease can be set manually according to the city.

Images