A method, device, equipment and medium for identifying supply and demand states of online car hailing

Abstract

This invention provides a method and apparatus for identifying the supply and demand status of ride-hailing services. The method includes: acquiring historical order data for ride-hailing services; identifying peak time periods for ride-hailing services based on the historical order data; determining a supply and demand status identification threshold based on the peak time periods and historical order data; the supply and demand status identification threshold includes an order acceptance rate threshold and / or an average order acceptance time threshold; and identifying the supply and demand status based on the supply and demand status identification threshold and current order data. In this invention, the order acceptance rate threshold is not subjectively set by the administrator based on historical experience, but is determined jointly based on the peak time periods for ride-hailing services as a typical scenario of supply and demand tension, using both the peak time periods and historical order data. This avoids interference from the administrator's historical experience, improves the accuracy of the order acceptance rate threshold, and thus identifies an objective supply and demand status.

Description

Technical Field

[0001] This invention relates to the field of Internet technology, and in particular to a method, apparatus, electronic device, and computer-readable storage medium for identifying the supply and demand status of ride-hailing services. Background Technology

[0002] There are two types of supply and demand relationships between ride-hailing platforms: a state of supply shortage (including supply exceeding demand and supply falling short of demand) and a state of supply-demand equilibrium. When the supply and demand situation is in different states, the actions taken and optimization goals of ride-hailing platforms will differ.

[0003] Accurately identifying supply and demand is crucial for ride-hailing platforms' dispatching and precise order management. However, passengers and drivers are scarce resources on ride-hailing platforms, making a strict balance between supply and demand impossible. Even in relatively balanced situations, supply is still less than demand. Therefore, identifying the supply and demand situation in ride-hailing requires determining the extent to which the gap between supply and demand indicates a supply shortage.

[0004] Current solutions typically rely on the historical experience of ride-hailing platform administrators to determine supply and demand status. For example, for a specific city, historical experience might indicate a supply-demand imbalance when the order acceptance rate is below 75%. However, this judgment is individualized and dependent on the specific administrator. For the same city, a different administrator might interpret the situation differently, estimating a supply-demand imbalance below 70%. Therefore, using administrators' historical experience as the basis for supply and demand status assessment is a subjective, human-based method lacking scientific objectivity and interpretability. This leads to significant biases in supply and demand status identification, resulting in low accuracy. Summary of the Invention

[0005] In view of the above problems, embodiments of the present invention are proposed to provide a method, apparatus, electronic device, and computer-readable storage medium for identifying the supply and demand status of ride-hailing services in order to overcome or at least partially solve the above problems.

[0006] To address the aforementioned problems, according to a first aspect of the present invention, a method for identifying the supply and demand status of ride-hailing services is disclosed, comprising: acquiring historical order data of ride-hailing services; identifying peak time periods for ride-hailing services based on the historical order data; determining a supply and demand status identification threshold based on the peak time periods and the historical order data; the supply and demand status identification threshold comprising: an order acceptance rate threshold and / or an average order acceptance duration threshold; and identifying the supply and demand status based on the supply and demand status identification threshold and current order data of ride-hailing services.

[0007] Optionally, identifying peak time periods for ride-hailing services based on the historical ride-hailing order data includes: filtering multiple peak points based on a distribution map of ride-hailing order data in the historical order data; the distribution map of ride-hailing order data includes order data points corresponding to each time period, the peak points belong to the order data points, and the order data corresponding to each peak point is greater than the order data corresponding to the two order data points adjacent to the peak point on the left and right; calculating the convexity of each peak point; the convexity is the difference between the order data of the corresponding peak point and the smallest order data point on the left. The difference between individual data points is the minimum value between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point on the right. The minimum bill of lading data point on the left is the bill of lading data point whose data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the left. The minimum bill of lading data point on the right is the bill of lading data point whose data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the right. The peak period time for ride-hailing is determined based on the convexity of each peak point and the peak period width threshold.

[0008] Optionally, determining the peak period time for ride-hailing services based on the protrusion degree of each peak point and the peak period width threshold includes: sorting the peak points in descending order based on their protrusion degree; using the waves containing the top-ranked peak points as a candidate set of peak periods; using the waves in the candidate set whose width is greater than the peak period width threshold as peak periods for ride-hailing services; and using the time period corresponding to the time window of the peak points within the peak period in the ride-hailing order data distribution map as the peak period time for ride-hailing services.

[0009] Optionally, determining the supply and demand status identification threshold based on the peak time period of ride-hailing and the historical order data of ride-hailing includes: determining alternative combinations of the supply and demand status identification threshold based on the peak time period of ride-hailing and the historical order data of ride-hailing; and selecting the supply and demand status identification threshold from the alternative combinations.

[0010] Optionally, determining the alternative combination of the supply and demand status identification threshold based on the peak period of ride-hailing and the historical order data of ride-hailing includes: taking the order acceptance rate and / or average order acceptance time corresponding to each order data point within the wave where each peak point is located as the alternative combination.

[0011] Optionally, the step of selecting the supply and demand status identification threshold from the candidate combinations includes: within a preset spatiotemporal block range, selecting the supply and demand status identification threshold from the candidate combinations based on the bubble count in the ride-hailing historical order data; the bubble count is the number of times each ride-hailing user inputs the starting point and destination.

[0012] Optionally, the step of selecting the supply and demand status identification threshold from the candidate combinations based on the bubble count in the historical ride-hailing order data within a preset spatiotemporal block includes: calculating the accuracy and recall rate representing a tight supply and demand state in each time period based on the bubble count in each time period within the spatiotemporal block and the candidate combinations; calculating the weighted harmonic mean of the accuracy and the recall rate; and using the candidate combination corresponding to the largest weighted harmonic mean as the supply and demand status identification threshold; wherein the accuracy rate is the ratio of the number of bubbles representing a tight supply and demand state within the peak ride-hailing period to the number of bubbles representing a tight supply and demand state; and the recall rate is the ratio of the number of bubbles representing a tight supply and demand state within the peak ride-hailing period to the number of bubbles within the peak ride-hailing period.

[0013] Optionally, identifying the supply and demand status based on the supply and demand status identification threshold and the current ride-hailing order data includes: identifying the supply and demand status as a tight supply and demand state when the order acceptance rate in the current ride-hailing order data is less than the order acceptance rate threshold; or, identifying the supply and demand status as a tight supply and demand state when the average order acceptance time in the current ride-hailing order data is less than the average order acceptance time threshold; or, identifying the supply and demand status as a tight supply and demand state when both the order acceptance rate in the current ride-hailing order data and the average order acceptance time in the current ride-hailing order data are less than the average order acceptance time threshold.

[0014] According to a second aspect of the present invention, a ride-hailing supply and demand status identification device is also disclosed, comprising: an acquisition module for acquiring historical ride-hailing order data; a filtering module for identifying peak time periods for ride-hailing based on the historical order data; a determination module for determining a supply and demand status identification threshold based on the peak time periods and the historical order data; the supply and demand status identification threshold includes: an order acceptance rate threshold and / or an average order acceptance duration threshold; and an identification module for identifying the supply and demand status based on the supply and demand status identification threshold and current ride-hailing order data.

[0015] Optionally, the filtering module includes: a peak point filtering module, used to filter out multiple peak points based on the ride-hailing order data distribution map in the ride-hailing historical order data; the ride-hailing order data distribution map contains order data points corresponding to each time period, the peak points belong to the order data points, and the order data corresponding to the peak point is greater than the order data corresponding to the two order data points adjacent to the peak point on the left and right; and a convexity calculation module, used to calculate the convexity of each peak point; the convexity is the difference between the order data of the corresponding peak point and the order data of the smallest order data point on the left. The minimum difference between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point on the right; the minimum bill of lading data point on the left is the bill of lading data point whose data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the left; the minimum bill of lading data point on the right is the bill of lading data point whose data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the right; the time period determination module is used to determine the peak period time period for ride-hailing based on the protrusion degree of each peak point and the peak period width threshold.

[0016] Optionally, the time period determination module includes: a convexity sorting module, used to sort the peak points in descending order according to their convexity; a candidate set determination module, used to select the waves containing the top-ranked peak points as a peak period candidate set; a peak period determination module, used to select the waves in the peak period candidate set whose width is greater than the peak period width threshold as the ride-hailing peak period; and a peak period time period determination module, used to select the time period corresponding to the peak points in the ride-hailing peak period in the time window of the ride-hailing order data distribution map as the ride-hailing peak period time period.

[0017] Optionally, the determining module includes: a candidate combination determining module, used to determine a candidate combination of the supply and demand status identification threshold based on the peak time period of the ride-hailing service and the historical order data of the ride-hailing service; and a threshold filtering module, used to filter out the supply and demand status identification threshold from the candidate combinations.

[0018] Optionally, the alternative combination determination module is used to take the bill of lading acceptance rate and / or average acceptance time corresponding to each bill of lading data point within the wave where each peak point is located as the alternative combination.

[0019] Optionally, the threshold filtering module is used to filter the supply and demand status identification threshold from the candidate combinations within a preset spatiotemporal block range based on the bubble count in the ride-hailing historical order data; the bubble count is the number of times each ride-hailing user inputs the starting point and destination.

[0020] Optionally, the threshold filtering module includes: a rate calculation module, used to calculate the precision and recall rate representing a supply-demand imbalance in each time period based on the number of bubbles in each time period within the spatiotemporal block and the candidate combinations; an average calculation module, used to calculate the weighted harmonic mean of the precision and the recall rate; and a threshold determination module, used to take the candidate combination corresponding to the largest weighted harmonic mean as the supply-demand state identification threshold; wherein, the precision rate is the ratio of the number of bubbles representing a supply-demand imbalance within the peak ride-hailing period to the total number of bubbles representing a supply-demand imbalance; and the recall rate is the ratio of the number of bubbles representing a supply-demand imbalance within the peak ride-hailing period to the total number of bubbles within the peak ride-hailing period.

[0021] Optionally, the identification module is configured to identify the supply and demand status as a tight supply and demand state when the order acceptance rate in the current order data of the ride-hailing vehicle is less than the order acceptance rate threshold; or, when the average order acceptance time in the current order data of the ride-hailing vehicle is less than the average order acceptance time threshold; or, when both the order acceptance rate in the current order data of the ride-hailing vehicle and the average order acceptance time in the current order data of the ride-hailing vehicle are less than the order acceptance rate threshold, the supply and demand status is identified as a tight supply and demand state.

[0022] According to a third aspect of the present invention, an electronic device is also disclosed, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the ride-hailing vehicle supply and demand status identification method described in the first aspect.

[0023] According to a fourth aspect of the present invention, a computer-readable storage medium is also disclosed, on which a computer program is stored, which, when executed by a processor, implements the ride-hailing supply and demand status identification method described in the first aspect.

[0024] Compared with the prior art, the technical solution provided by the embodiments of the present invention has the following advantages:

[0025] This invention provides a supply and demand status identification scheme for ride-hailing services. It acquires historical order data for ride-hailing services and identifies peak time periods based on this data. This invention considers peak time periods as typical scenarios of supply and demand imbalance; therefore, peak time periods are defined as periods of supply and demand imbalance. Then, a supply and demand status identification threshold is determined based on the peak time periods and historical order data. This threshold includes an order acceptance rate threshold and / or an average order acceptance time threshold. The supply and demand status is then identified based on the supply and demand status identification threshold and current order data. This invention uses the order acceptance rate threshold as one of the supply and demand status identification thresholds. However, this threshold is not subjectively set by administrators based on historical experience. Instead, it is determined jointly based on the peak time periods as typical scenarios of supply and demand imbalance, using both the peak time periods and historical order data. This avoids interference from the historical experience of administrators, improves the accuracy of the order acceptance rate threshold, and thus identifies an objective supply and demand status. In this embodiment of the invention, the average order acceptance time threshold is also used as one of the supply and demand status identification thresholds. When the order acceptance rate threshold fluctuates greatly due to the small number of orders, the average order acceptance time threshold is used to identify the supply and demand status, which further enriches the supply and demand status identification scenario for ride-hailing services. Attached Figure Description

[0026] Figure 1 This is a flowchart illustrating the steps of a method for identifying the supply and demand status of ride-hailing services according to an embodiment of the present invention.

[0027] Figure 2 This is a bill of lading quantity distribution diagram according to an embodiment of the present invention;

[0028] Figure 3 This is a flowchart illustrating the steps for identifying peak time periods for ride-hailing services according to an embodiment of the present invention.

[0029] Figure 4 This is a structural block diagram of a ride-hailing vehicle supply and demand status identification device according to an embodiment of the present invention;

[0030] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0031] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] Reference Figure 1 This document illustrates a flowchart of a method for identifying the supply and demand status of ride-hailing services according to an embodiment of the present invention. Specifically, this method may include the following steps:

[0033] Step 101: Obtain historical ride-hailing order data.

[0034] In embodiments of the present invention, ride-hailing historical order data may include order data and order acceptance data. Order data includes, but is not limited to, the number of orders, order time, order user, and order location. Order acceptance data includes, but is not limited to, the number of orders accepted, order time, order user, and order location. In addition, ride-hailing historical order data may also include order acceptance rate and average order duration generated based on the order data and order acceptance data.

[0035] In practical applications, historical ride-hailing order data for each day of the past week can be obtained. Each hour is divided into four time windows of 15 minutes each: [0-15], [15-30], [30-45], and [45-60]. The number of orders submitted, accepted, the order acceptance rate, and the average order duration are then statistically analyzed within each time window. Therefore, within the 96 time windows of a day, the following data can be obtained: Figure 2 The chart showing the distribution of bills of lading quantities is shown. Figure 2 In the diagram, the bill of lading quantity distribution curve is formed by connecting the bill of lading data points corresponding to each time window, and the value of each bill of lading data point represents the number of bills of lading.

[0036] Step 102: Identify the peak time period for ride-hailing services based on historical ride-hailing order data.

[0037] In the embodiments of the present invention, it should be noted that peak hours for ride-hailing services can be considered a typical scenario of supply and demand tension. In practical applications, a bill of lading quantity distribution curve can be generated based on historical ride-hailing order data. Then, the peak time period for ride-hailing services can be identified based on each bill of lading data point in the bill of lading data distribution curve. The embodiments of the present invention will further describe in detail how to identify the peak time period for ride-hailing services in subsequent embodiments.

[0038] Step 103: Determine the supply and demand status identification threshold based on peak hours for ride-hailing services and historical order data.

[0039] In embodiments of the present invention, the supply and demand status identification threshold includes: an order acceptance rate threshold and / or an average order acceptance time threshold. The order acceptance rate threshold directly measures the relationship between ride-hailing supply and demand. As a rate-based indicator, the order acceptance rate threshold fluctuates significantly when the number of orders is small, making it unstable. Therefore, when the number of orders is low, the average order acceptance time threshold can also be used as one of the supply and demand status identification thresholds.

[0040] Step 104: Identify the supply and demand status based on the supply and demand status identification threshold and the current order data of ride-hailing services.

[0041] In an embodiment of the present invention, the current order data of ride-hailing services can be compared with the supply and demand status identification threshold. If the current order data of ride-hailing services is less than the supply and demand status identification threshold, the supply and demand status is considered to be a state of supply and demand tension. If the current order data of ride-hailing services is greater than or equal to the supply and demand status identification threshold, the supply and demand status is considered to be a state of supply and demand balance.

[0042] This invention provides a supply and demand status identification scheme for ride-hailing services. It acquires historical ride-hailing order data and identifies peak-hour periods based on this data. This invention considers peak-hour periods as typical scenarios of supply and demand imbalance; therefore, peak-hour periods are defined as periods of supply and demand imbalance. Then, a supply and demand status identification threshold is determined based on the peak-hour periods and historical order data. This threshold includes an order acceptance rate threshold and / or an average order acceptance time threshold. The supply and demand status is then identified based on the supply and demand status identification threshold and current ride-hailing order data. This invention uses the order acceptance rate threshold as one of the supply and demand status identification thresholds. However, this threshold is not subjectively set by order personnel based on their experience. Instead, it is determined jointly based on the peak-hour periods as typical scenarios of supply and demand imbalance, using both the peak-hour periods and historical order data. This avoids interference from individual order personnel and improves the accuracy of the order acceptance rate threshold. In this embodiment of the invention, the average order acceptance time threshold is also used as one of the supply and demand status identification thresholds. When the order acceptance rate threshold fluctuates greatly due to the small number of orders, the average order acceptance time threshold is used to identify the supply and demand status, which further enriches the supply and demand status identification scenario for ride-hailing services.

[0043] In a preferred embodiment of the present invention, one method for identifying peak time periods for ride-hailing services based on historical ride-hailing order data may include the following steps.

[0044] Reference Figure 3 The diagram illustrates a flowchart of the steps for identifying peak time periods for ride-hailing services according to an embodiment of the present invention.

[0045] Step 301: Select multiple peak points based on the distribution map of ride-hailing bill of lading data in the historical ride-hailing order data.

[0046] In embodiments of the present invention, the ride-hailing bill of lading data distribution map may include bill of lading data points corresponding to each time period. In practical applications, the ride-hailing bill of lading data distribution map may be as follows: Figure 2 The chart shows the distribution of bills of lading quantities. Peaks represent bills of lading data points, and the bills of lading data corresponding to a peak is greater than the bills of lading data corresponding to the two adjacent bills of lading data points to the left and right.

[0047] For example, given a bill of lading data point x with corresponding data value[x], the bill of lading data point x-1 to the left of x with corresponding data value[x-1], and the bill of lading data point x+1 to the right of x with corresponding data value[x+1], where value[x+1] < value[x] > value[x-1], then this bill of lading data point x is considered a peak point. All peak points can be combined to form a peak point list, alist.

[0048] Step 302: Calculate the convexity of each wave crest.

[0049] In an embodiment of the present invention, the convexity is the minimum value between the difference between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point to the left, and the difference between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point to the right. The minimum bill of lading data point to the left is the bill of lading data point corresponding to the minimum value where the bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the left. The minimum bill of lading data point to the right is the bill of lading data point corresponding to the minimum value where the bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversed from the corresponding peak point to the right.

[0050] For example, traversing from the peak point x to the left, among all bill of lading data points with a value[x] less than the peak point x, find the bill of lading data point left_base with the smallest value. This left_base is the smallest bill of lading data point on the left, and its bill of lading data is value[left_base]. Traversing from the peak point x to the right, among all bill of lading data points with a value[x] less than the peak point x, find the bill of lading data point right_base with the smallest value. This right_base is the smallest bill of lading data point on the right, and its bill of lading data is value[right_base]. Calculate value[x] - value[left_base] and value[x] - value[right_base] respectively, and use the minimum of value[x] - value[left_base] and value[x] - value[right_base] as the convexity of the peak point x.

[0051] Step 303: Determine the peak period time for ride-hailing based on the convexity of each peak point and the peak period width threshold.

[0052] In an embodiment of the present invention, the peak points can be sorted in descending order according to their convexity. The waves containing the top-ranked peak points are taken as a candidate set of peak periods. Waves in the candidate set of peak periods whose width is greater than the peak period width threshold are taken as ride-hailing peak periods. The time period corresponding to the time window of the peak points in the ride-hailing order data distribution map is taken as the ride-hailing peak period time period.

[0053] For example, the waves containing the top n peaks in the peak elevation ranking are selected as the candidate set for peak periods. Waves in the candidate set whose width is greater than the peak period width threshold w are considered as peak periods for ride-hailing services. If the wave containing peak point x is a peak period, then the peak period time period containing peak point x is the time period [x_left, x_right] corresponding to the time window of peak point x in the ride-hailing order data distribution map. Here, x_left represents the minimum value of the time period corresponding to the time window, and x_right represents the maximum value of the time period corresponding to the time window.

[0054] In a preferred embodiment of the present invention, one way to determine the supply and demand status identification threshold based on peak ride-hailing time periods and historical ride-hailing order data is to determine alternative combinations of supply and demand status identification thresholds based on peak ride-hailing time periods and historical ride-hailing order data; and then select the supply and demand status identification threshold from the alternative combinations.

[0055] In practical applications, the order acceptance rate and / or average order acceptance time corresponding to each order data point within the wave containing each peak can be used as alternative combinations. Furthermore, since supply and demand status identification is performed at the spatiotemporal block level (a range of a city or region defined by time and space dimensions, such as dividing a city into multiple spatiotemporal blocks using a hexagon with a radius of 5 kilometers and 30 minutes), alternative combinations are applied to each spatiotemporal block to calculate the difference between business indicators identified as indicating a supply-demand imbalance using the alternative combinations and business indicators corresponding to peak ride-hailing periods. Here, the business indicator is the time period where bubbling occurs, where bubbling refers to each ride-hailing user inputting their origin and destination once. When selecting the supply-demand status identification threshold from the alternative combinations, it can be determined within the spatiotemporal block based on the number of bubbles in historical ride-hailing order data. Specifically, the accuracy and recall rate representing a supply-demand imbalance within each time period can be calculated based on the number of bubbles and the alternative combinations within the spatiotemporal block. The accuracy rate is the ratio of the number of bubbles indicating a supply-demand imbalance during peak ride-hailing hours to the total number of bubbles indicating a supply-demand imbalance. The recall rate is the ratio of the number of bubbles indicating a supply-demand imbalance during peak ride-hailing hours to the total number of bubbles during peak ride-hailing hours. Then, a weighted harmonic mean F of accuracy and recall is calculated, and the candidate combination corresponding to the largest weighted harmonic mean F is used as the supply-demand state identification threshold.

[0056] The core meaning of the aforementioned accuracy and recall rate is that, under the premise that the peak period is a typical scenario of tight supply and demand, the supply and demand status identification threshold can identify as many tight supply and demand scenarios as possible during the peak period.

[0057] In a preferred embodiment of the present invention, one method for identifying the supply and demand status based on the supply and demand status identification threshold and the current ride-hailing order data is as follows: The current ride-hailing order data is compared with the supply and demand status identification threshold. When the order acceptance rate in the current ride-hailing order data is less than the order acceptance rate threshold, the supply and demand status is identified as a tight supply and demand situation. Alternatively, when the average order acceptance time in the current ride-hailing order data is less than the average order acceptance time threshold, the supply and demand status is identified as a tight supply and demand situation. Or, when both the order acceptance rate and the average order acceptance time in the current ride-hailing order data are less than the average order acceptance time threshold, the supply and demand status is identified as a tight supply and demand situation.

[0058] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0059] Reference Figure 4 The diagram illustrates a structural block diagram of a ride-hailing vehicle supply and demand status identification device according to an embodiment of the present invention. This ride-hailing vehicle supply and demand status identification device may specifically include the following modules:

[0060] Module 41 is used to obtain historical order data for ride-hailing services;

[0061] The filtering module 42 is used to identify peak time periods for ride-hailing services based on the historical ride-hailing order data.

[0062] The determining module 43 is used to determine the supply and demand status identification threshold based on the peak time period of the ride-hailing service and the historical order data of the ride-hailing service; the supply and demand status identification threshold includes: order acceptance rate threshold and / or average order acceptance time threshold;

[0063] The identification module 44 is used to identify the supply and demand status based on the supply and demand status identification threshold and the current order data of the ride-hailing service.

[0064] In a preferred embodiment of the present invention, the screening module 42 includes:

[0065] The peak point filtering module is used to filter out multiple peak points based on the distribution map of ride-hailing bill of lading data in the historical order data of ride-hailing vehicles; the distribution map of ride-hailing bill of lading data includes bill of lading data points corresponding to each time period, the peak point belongs to the bill of lading data points, and the bill of lading data corresponding to the peak point is greater than the bill of lading data corresponding to the two bill of lading data points adjacent to the peak point on the left and right.

[0066] The convexity calculation module is used to calculate the convexity of each of the wave crests; the convexity is the minimum value between the difference between the bill of lading data of the corresponding wave crest and the bill of lading data of the smallest bill of lading data point to the left, and the difference between the bill of lading data of the corresponding wave crest and the bill of lading data of the smallest bill of lading data point to the right; the smallest bill of lading data point to the left is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data of the corresponding wave crest; the smallest bill of lading data point to the right is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data of the corresponding wave crest.

[0067] The time period determination module is used to determine the peak period time of ride-hailing based on the protrusion degree of each peak point and the peak period width threshold.

[0068] In a preferred embodiment of the present invention, the time period determination module includes:

[0069] A protrusion sorting module is used to sort the peaks in descending order based on their protrusion.

[0070] The candidate set determination module is used to select the waves containing the top-ranked wave crests as the peak period candidate set.

[0071] The peak period determination module is used to identify peak periods in the candidate set of peak periods where the width of the wave is greater than the peak period width threshold as peak periods for ride-hailing services.

[0072] The peak period time determination module is used to determine the time period corresponding to the peak point of the ride-hailing peak period in the time window of the ride-hailing bill of lading data distribution map as the ride-hailing peak period time.

[0073] In a preferred embodiment of the present invention, the determining module 43 includes:

[0074] The alternative combination determination module is used to determine alternative combinations of the supply and demand status identification threshold based on the peak period of the ride-hailing service and the historical order data of the ride-hailing service.

[0075] The threshold filtering module is used to filter out the supply and demand status identification threshold from the candidate combinations.

[0076] In a preferred embodiment of the present invention, the alternative combination determination module is used to take the bill of lading acceptance rate and / or average acceptance time corresponding to each bill of lading data point within the wave where each peak point is located as the alternative combination.

[0077] In a preferred embodiment of the present invention, the threshold filtering module is used to filter the supply and demand status identification threshold from the candidate combinations based on the bubble count in the historical order data of the ride-hailing service within a preset spatiotemporal block range; the bubble count is the number of times each ride-hailing user inputs the starting point and destination.

[0078] In a preferred embodiment of the present invention, the threshold filtering module includes:

[0079] The rate calculation module is used to calculate the accuracy and recall rate representing the supply and demand tension in each time period based on the number of bubbles in each time period within the spatiotemporal block and the alternative combinations.

[0080] The mean calculation module is used to calculate the weighted harmonic mean of the precision and the recall.

[0081] The threshold determination module is used to take the candidate combination corresponding to the largest weighted harmonic mean as the supply and demand status identification threshold;

[0082] The accuracy rate is the ratio of the number of bubbles indicating a tight supply and demand during the peak ride-hailing period to the number of bubbles indicating a tight supply and demand; the recall rate is the ratio of the number of bubbles indicating a tight supply and demand during the peak ride-hailing period to the number of bubbles within the peak ride-hailing period.

[0083] In a preferred embodiment of the present invention, the identification module 44 is configured to identify the supply and demand state as a tight supply and demand state when the order acceptance rate in the current order data of the ride-hailing vehicle is less than the order acceptance rate threshold; or, when the average order acceptance time in the current order data of the ride-hailing vehicle is less than the average order acceptance time threshold; or, when the order acceptance rate in the current order data of the ride-hailing vehicle is less than the order acceptance rate threshold and the average order acceptance time in the current order data of the ride-hailing vehicle is less than the average order acceptance time threshold, the supply and demand state is identified as a tight supply and demand state.

[0084] This invention also provides an electronic device, see [link to relevant documentation]. Figure 5 The system includes: a processor 501, a memory 502, and a computer program 5021 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the program 5021, it implements the ride-hailing supply and demand status identification method of the aforementioned embodiment.

[0085] This invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the ride-hailing supply and demand status identification method of the aforementioned embodiments.

[0086] As the device embodiment is basically similar to the method embodiment, the description is relatively simple, and relevant parts can be found in the description of the method embodiment.

[0087] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0088] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0090] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0091] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0092] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

[0093] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0094] The above provides a detailed description of the supply and demand status identification method and apparatus for ride-hailing services provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for identifying the supply and demand status of ride-hailing services, characterized in that, include: Obtain historical order data for ride-hailing services; The peak time period for ride-hailing services is identified based on the historical order data. A supply and demand status identification threshold is determined based on the peak time period and the historical order data. The supply and demand status identification threshold includes: an order acceptance rate threshold and / or an average order acceptance time threshold. The supply and demand status is identified based on the aforementioned supply and demand status identification threshold and the current order data of ride-hailing services. The step of identifying peak time periods for ride-hailing services based on historical ride-hailing order data includes: filtering multiple peak points based on a distribution map of ride-hailing order data in the historical order data; the distribution map of ride-hailing order data includes order data points corresponding to each time period, the peak points belong to the order data points, and the order data corresponding to each peak point is greater than the order data corresponding to the two order data points adjacent to the peak point on the left and right; calculating the convexity of each peak point; the convexity is the order data of the corresponding peak point and the order data of the smallest order data point to its left. The difference is the minimum value between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point on the right; the minimum bill of lading data point on the left is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversing to the left from the corresponding peak point; the minimum bill of lading data point on the right is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversing to the right from the corresponding peak point; the peak period time for ride-hailing is determined based on the convexity of each peak point and the peak period width threshold.

2. The method according to claim 1, characterized in that, The step of determining the peak period time for ride-hailing services based on the convexity of each peak point and the peak period width threshold includes: sorting the peak points in descending order based on their convexity; taking the waves containing the top-ranked peak points as a candidate set of peak periods; taking the waves in the candidate set whose width is greater than the peak period width threshold as the peak period for ride-hailing services; and taking the time period corresponding to the time window of the peak points within the peak period in the ride-hailing order data distribution map as the peak period time for ride-hailing services.

3. The method according to claim 2, characterized in that, The step of determining the supply and demand status identification threshold based on the peak time period of ride-hailing and the historical order data of ride-hailing includes: determining alternative combinations of the supply and demand status identification threshold based on the peak time period of ride-hailing and the historical order data of ride-hailing; and selecting the supply and demand status identification threshold from the alternative combinations.

4. The method according to claim 3, characterized in that, The step of determining the alternative combination of the supply and demand status identification threshold based on the peak time period of ride-hailing and the historical order data of ride-hailing includes: taking the order acceptance rate and / or average order acceptance time corresponding to each order data point within the wave where each peak point is located as the alternative combination.

5. The method according to claim 3, characterized in that, The step of selecting the supply and demand status identification threshold from the candidate combinations includes: within a preset spatiotemporal block range, selecting the supply and demand status identification threshold from the candidate combinations based on the bubble count in the ride-hailing historical order data; the bubble count is the number of times each ride-hailing user inputs the starting point and destination.

6. The method according to claim 5, characterized in that, Within a preset spatiotemporal block, the step of selecting the supply and demand status identification threshold from the candidate combinations based on the bubble count in the historical ride-hailing order data includes: calculating the accuracy and recall rate representing a supply and demand imbalance in each time period based on the bubble count in each time period within the spatiotemporal block and the candidate combinations; calculating the weighted harmonic mean of the accuracy and the recall rate; and using the candidate combination corresponding to the largest weighted harmonic mean as the supply and demand status identification threshold; wherein, the accuracy rate is the ratio of the number of bubbles representing a supply and demand imbalance within the peak ride-hailing period to the total number of bubbles representing a supply and demand imbalance; and the recall rate is the ratio of the number of bubbles representing a supply and demand imbalance within the peak ride-hailing period to the total number of bubbles within the peak ride-hailing period.

7. The method according to claim 1, characterized in that, The step of identifying the supply and demand status based on the supply and demand status identification threshold and the current ride-hailing order data includes: identifying the supply and demand status as a tight supply and demand state when the order acceptance rate in the current ride-hailing order data is less than the order acceptance rate threshold; or identifying the supply and demand status as a tight supply and demand state when the average order acceptance time in the current ride-hailing order data is less than the average order acceptance time threshold; or identifying the supply and demand status as a tight supply and demand state when both the order acceptance rate in the current ride-hailing order data and the average order acceptance time in the current ride-hailing order data are less than the average order acceptance time threshold.

8. A supply and demand status identification device for ride-hailing services, characterized in that, include: The acquisition module is used to retrieve historical order data for ride-hailing services. The filtering module is used to identify peak time periods for ride-hailing services based on the historical ride-hailing order data. The determination module is used to determine a supply and demand status identification threshold based on the peak time period of the ride-hailing service and the historical order data of the ride-hailing service; the supply and demand status identification threshold includes: order acceptance rate threshold and / or average order acceptance time threshold; the identification module is used to identify the supply and demand status based on the supply and demand status identification threshold and the current order data of the ride-hailing service. The step of identifying peak time periods for ride-hailing services based on historical ride-hailing order data includes: filtering multiple peak points based on a distribution map of ride-hailing order data in the historical order data; the distribution map of ride-hailing order data includes order data points corresponding to each time period, the peak points belong to the order data points, and the order data corresponding to each peak point is greater than the order data corresponding to the two order data points adjacent to the peak point on the left and right; calculating the convexity of each peak point; the convexity is the order data of the corresponding peak point and the order data of the smallest order data point to its left. The difference is the minimum value between the bill of lading data at the corresponding peak point and the bill of lading data at the minimum bill of lading data point on the right; the minimum bill of lading data point on the left is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversing to the left from the corresponding peak point; the minimum bill of lading data point on the right is the bill of lading data point whose bill of lading data is less than the minimum value of the bill of lading data at the corresponding peak point, traversing to the right from the corresponding peak point; the peak period time for ride-hailing is determined based on the convexity of each peak point and the peak period width threshold.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the ride-hailing supply and demand status identification method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the ride-hailing supply and demand status identification method according to any one of claims 1 to 7.

Images