Method, device and storage medium for determining a drop-off area

Abstract

The application discloses a delivery area determination method and device and a storage medium. The method comprises the following steps: determining a payment association feature and a traffic flow trend sequence feature of a candidate area; determining a first mutual information between a delivery index of a target object and the payment association feature and a second mutual information between the delivery index and the traffic flow trend sequence feature; constructing a comprehensive mutual information function; adjusting a value corresponding to the delivery index based on the comprehensive mutual information function, calculating a comprehensive mutual information value; when the comprehensive mutual information value is a preset threshold value, determining a value corresponding to the preset threshold value as a predicted delivery index value of the candidate area; determining a delivery category prediction result of the candidate area based on the predicted delivery index value; when the prediction result is that the candidate area is a to-be-delivered area, regarding the candidate area as a delivery area of the target object; the delivery index value of the target object delivery area is improved, and the delivery area of the target object is accurately recommended to a user.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus and storage medium for determining a deployment area. Background Technology

[0002] Merchant site selection, vending machine site selection, and offline advertising are very common in the business sector. For merchants, choosing the right investment area can provide ideal customer acquisition channels and target audiences, thereby directly stimulating and driving revenue growth for products and businesses.

[0003] In existing technologies, regression model-based site selection methods obtain target values ​​by fitting and predicting the characteristics of already deployed areas. However, for cross-regional areas, the differences between regions are ignored, making it difficult for the model to learn the regional differences between areas, i.e., the relationships between regions. Therefore, it is difficult to generalize. As a result, the deployment index values ​​of the determined target areas are low, which cannot well meet user needs.

[0004] Therefore, it is necessary to provide a method, apparatus, and storage medium for determining the delivery area to improve the accuracy of determining the delivery category of the candidate area, thereby improving the delivery index value of the target object delivery area. Summary of the Invention

[0005] This application provides a method, apparatus, and storage medium for determining a delivery area, which can improve the accuracy of determining the delivery category of a candidate area, thereby improving the delivery index value of the delivery area for the target object.

[0006] On the one hand, this application provides a method for determining a deployment area, the method comprising:

[0007] Determine the payment association characteristics and traffic flow trend sequence characteristics of the candidate regions;

[0008] Determine the first mutual information between the target object's delivery indicators and the payment association features, and the second mutual information between the delivery indicators and the traffic flow trend sequence features;

[0009] Based on the first mutual information and the second mutual information, a comprehensive mutual information function is constructed;

[0010] Based on the comprehensive mutual information function, adjust the values ​​corresponding to the delivery indicators and calculate the comprehensive mutual information value;

[0011] When the comprehensive mutual information value is a preset threshold, the value corresponding to the preset threshold is determined as the predicted delivery index value of the candidate region.

[0012] Based on the predicted delivery index values, the delivery category prediction results for the candidate areas are determined;

[0013] When the prediction result indicates that the candidate region is a region to be deployed, the candidate region is used as the deployment region for the target object.

[0014] On the other hand, a device for determining a delivery area is provided, the device comprising:

[0015] The feature determination module is used to determine the payment association features and traffic flow trend sequence features of the candidate region;

[0016] The mutual information determination module is used to determine the first mutual information between the target object's delivery indicator and the payment association feature, and the second mutual information between the delivery indicator and the traffic flow trend sequence feature.

[0017] The function construction module is used to construct a comprehensive mutual information function based on the first mutual information and the second mutual information;

[0018] The comprehensive mutual information value calculation module is used to adjust the value corresponding to the delivery indicator based on the comprehensive mutual information function and calculate the comprehensive mutual information value.

[0019] The prediction delivery indicator value determination module is used to determine the value corresponding to the preset threshold as the prediction delivery indicator value of the candidate area when the comprehensive mutual information value is a preset threshold.

[0020] The delivery category prediction module is used to determine the delivery category prediction result for the candidate area based on the predicted delivery index value.

[0021] The delivery area determination module is used to determine the delivery area of ​​the target object when the prediction result indicates that the candidate area is a delivery area to be delivered.

[0022] On the other hand, a device for determining a delivery area is provided, the device comprising:

[0023] On the other hand, a computer storage medium is provided that stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the deployment area determination method as described above.

[0024] On the other hand, a computer program product or computer program is provided, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the deployment area determination method as described above.

[0025] The method, apparatus, and storage medium for determining the delivery area provided in this application have the following technical advantages:

[0026] This application, after determining the payment association characteristics and traffic flow trend sequence characteristics of candidate areas, determines the first mutual information between the target object's delivery index and the payment association characteristics, and the second mutual information between the delivery index and the traffic flow trend sequence characteristics. By integrating the mutual information function, it determines the predicted delivery index value for the candidate area, and based on this value, determines the predicted delivery category, thereby deciding whether to identify the candidate area as the delivery area for the target object. This scheme combines two independent features—payment association characteristics and traffic flow trend sequence characteristics—to improve the accuracy of determining the delivery category for candidate areas. By accurately obtaining the predicted delivery index value based on the first mutual information between the delivery index and the payment association characteristics, and the second mutual information between the delivery index and the traffic flow trend sequence characteristics, it further improves the accuracy of determining the delivery category for candidate areas, thereby increasing the delivery index value for the target object's delivery area. Attached Figure Description

[0027] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of a delivery area determination system provided in an embodiment of this application;

[0029] Figure 2 This is a flowchart illustrating a method for determining a delivery area provided in an embodiment of this application;

[0030] Figure 3 This is a flowchart illustrating a method for determining payment association characteristics and traffic flow trend sequence characteristics of candidate regions, as provided in an embodiment of this application.

[0031] Figure 4 This is a flowchart illustrating a method for determining traffic flow trend sequence characteristics based on the aforementioned traffic flow time series characteristics, provided in an embodiment of this application.

[0032] Figure 5 This is a flowchart illustrating the method for determining the first mutual information between the target object's delivery indicators and the aforementioned payment-related characteristics, and the second mutual information between the delivery indicators and the aforementioned traffic flow trend sequence characteristics, provided in this application embodiment.

[0033] Figure 6This is a flowchart illustrating the method for determining the delivery area of ​​the target object based on the predicted delivery index value corresponding to each candidate area, as provided in this application embodiment.

[0034] Figure 7 This is a flowchart illustrating the method for determining the delivery area of ​​a target object according to an embodiment of this application;

[0035] Figure 8 This is a schematic diagram of the structure of a blockchain system provided in an embodiment of this application;

[0036] Figure 9 This is a schematic diagram of the block structure provided in an embodiment of this application;

[0037] Figure 10 This is a schematic diagram of the structure of a deployment area determination device provided in an embodiment of this application;

[0038] Figure 11 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0041] Please see Figure 1 , Figure 1 This is a schematic diagram of a deployment area determination system provided in an embodiment of this application, such as... Figure 1 As shown, the deployment area determination system may include at least server 01 and client 02.

[0042] Specifically, in the embodiments of this specification, server 01 may include a standalone server, a distributed server, or a server cluster composed of multiple servers. It may also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Server 01 may include a network communication unit, a processor, and a memory, etc. Specifically, server 01 can be used to determine the prediction result of the delivery category of the candidate area based on the payment association characteristics and traffic flow trend sequence characteristics of the candidate area; and when the prediction result indicates that the candidate area is a delivery area to be delivered, the candidate area is used as the delivery area for the target object.

[0043] Specifically, in this embodiment of the specification, the client 02 may include physical devices such as smartphones, desktop computers, tablets, laptops, digital assistants, smart wearable devices, smart speakers, in-vehicle terminals, and smart TVs. It may also include software running on the physical device, such as web pages provided to users by service providers, or applications provided to users by such service providers. Specifically, the client 02 can be used to query the prediction results of the delivery category for candidate areas online.

[0044] The following describes a method for determining the deployment area according to this application. Figure 2 This is a flowchart illustrating a method for determining a deployment area according to an embodiment of this application. This specification provides the operational steps of the method described in the embodiments or flowchart, but based on conventional or non-inventive methods, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only possible execution order. In actual system or server product execution, the method can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment) as shown in the embodiments or accompanying drawings. Specifically, as... Figure 2 As shown, the above method may include:

[0045] S201: Determine the payment association characteristics and traffic flow trend sequence characteristics of the candidate region.

[0046] In cloud technology, big data refers to data sets that cannot be captured, managed, and processed within a certain timeframe using conventional software tools. It represents massive, rapidly growing, and diverse information assets that require new processing models to achieve stronger decision-making, insight discovery, and process optimization capabilities. With the advent of the cloud era, big data has attracted increasing attention. Big data requires specialized technologies to effectively process large amounts of data within a tolerable timeframe. Technologies suitable for big data include massively parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the Internet, and scalable storage systems. This application aims to determine payment association characteristics and traffic flow trend sequence characteristics of candidate regions using big data.

[0047] In the embodiments described in this specification, such as Figure 3 As shown, the payment association characteristics and traffic flow trend sequence characteristics for determining candidate regions include:

[0048] S20101: Obtain the payment characteristics, payment user attribute characteristics, and traffic flow time series characteristics of the above candidate areas;

[0049] S20103: Based on the above payment characteristics and the above payment user attribute characteristics, determine the above payment association characteristics.

[0050] In the embodiments of this specification, in the application scenario of merchant site selection, the payment-related characteristics of the candidate area include, but are not limited to, overall regional characteristics such as the number of regional merchants, the number of regional users, the total regional payment amount, the total number of regional payments, the average order value of the region, the regional payment time distribution (such as the number of users and the number of payments during different payment times), the regional payment transaction distribution; as well as the distribution of user attribute characteristics (such as by age, gender, education, etc.), and the distribution of target industries that compete with the selected merchants, the distribution of the number of users with product preferences, etc.

[0051] Specifically, in the embodiments of this specification, before determining the payment association characteristics based on the payment characteristics and the attribute characteristics of the payment user, the method further includes:

[0052] Obtain the target industry distribution characteristics and the distribution characteristics of the number of preferred users in the above candidate regions.

[0053] In the embodiments of this specification, the target industry distribution feature is the industry distribution feature that competes with the candidate region. This feature can be the geographical location feature of the target industry; for example, in a merchant site selection application scenario, the target industry distribution feature can be the industry distribution feature that competes with the selected merchants. The preferred user number distribution feature can be the preferred user number distribution feature of the product corresponding to the candidate region.

[0054] Accordingly, based on the aforementioned payment characteristics and the attribute characteristics of the aforementioned payment users, the aforementioned payment association characteristics are determined, including:

[0055] By combining the above payment characteristics and the attribute characteristics of the above payment users, derived characteristics are obtained;

[0056] The aforementioned payment characteristics, the aforementioned payment user attribute characteristics, the aforementioned derived characteristics, the aforementioned target industry distribution characteristics, and the aforementioned preference user number distribution characteristics are identified as the aforementioned payment-related characteristics.

[0057] In the embodiments of this specification, payment features, payment user attribute features, derived features, target industry distribution features, and preferred user number distribution features can be combined to obtain payment association features, which further enriches the payment association features; thereby improving the accuracy of the prediction results of the delivery category in the candidate area.

[0058] Specifically, in the embodiments of this specification, feature engineering can be constructed to process the payment association features of candidate regions, specifically including:

[0059] 1. Discard features with too many missing values; set the feature missing value threshold as follows: missing value filtering threshold = sample data size * X, X∈(0,1); for example, set X to 0.4, if the number of missing data for a certain feature exceeds this threshold, then delete the feature;

[0060] 2. Delete single-value features, handle outliers for features, and filter out useless features and interference information; discard the top m values ​​of the feature header based on the feature distribution, where m is set to 1 / 10000 for example; a single-value feature refers to a feature whose feature values ​​are all the same, for example, if all gender features are female, then the gender feature is a single-value feature and needs to be deleted; the top m values ​​of the feature header are outliers with particularly large values ​​and need to be deleted.

[0061] 3. Missing value handling: For continuous features, missing values ​​are filled using the mean; for discrete features, missing values ​​are filled using a constant.

[0062] 4. Feature Derivation: More relevant features can be derived through linear combination. Original features can be combined, such as by performing addition, subtraction, multiplication, division, or concatenation, to obtain derived features, thereby further enriching the payment-related features and improving the prediction accuracy of the delivery category prediction model.

[0063] 5. Feature processing; Normalize the features. Specifically, bin discretize continuous features to classify them, for example, group the age range of 10-20 years old into one category; perform one-hot encoding on discrete features. One-hot encoding is the process of converting categorical variables into a form that is easy for machine learning algorithms to use.

[0064] In the embodiments described in this specification, there are no abnormal features in the processed payment association features, thereby improving the prediction accuracy of the delivery category prediction model.

[0065] S20105: Based on the above traffic flow time series characteristics, determine the above traffic flow trend series characteristics.

[0066] Specifically, in the embodiments of this specification, such as Figure 4 As shown, the above method also includes:

[0067] S201001: Obtain the traffic flow of each road segment in the above candidate areas;

[0068] S201003: Based on the traffic flow of each road segment, determine the traffic flow change value of each road segment in each time period to obtain the traffic flow time series characteristics.

[0069] Accordingly, based on the aforementioned traffic flow time series characteristics, the aforementioned traffic flow trend series characteristics are determined, including:

[0070] S201051: Based on the above traffic flow time series characteristics, determine the traffic flow increase / decrease trend indicators for each of the above road segments in each time period;

[0071] S201053: Based on the traffic flow increase / decrease trend indicators of each road segment in each time period, determine the traffic flow change trend of each road segment in each time period.

[0072] S201055: Based on the traffic flow change trends of each road segment in different time periods, determine the traffic flow trend sequence characteristics.

[0073] Specifically, in the embodiments of this specification, the method for determining the traffic flow trend sequence characteristics of the candidate area is as follows:

[0074] First, a mapping relationship between time series and traffic flow series is established. Traffic flow data for each road segment in the city is acquired using technologies such as traffic camera recognition. Then, a mapping relationship between each traffic route is constructed based on the 24-hour time series and the traffic flow series for each road segment. Assuming the 24-hour traffic flow data for a certain route and segment is collected, as shown in Table 1 below:

[0075] Table 1: 24-hour traffic flow of a certain section of a certain route

[0076]

[0077]

[0078] The relationship between routes and road segments in Table 1 is shown in Table 2 below, and the 24-hour route and traffic flow mapping relationship for each road segment is shown in Table 3 below.

[0079] Table 2: Relationship between routes and road segments

[0080]

[0081]

[0082] Table 3: 24-hour route and traffic flow mapping relationship for each road segment

[0083]

[0084]

[0085] In the embodiments of this specification, after constructing the traffic flow relationships for each route, the next step is to set time intervals and analyze the changing trends of each road segment within the time intervals, thereby constructing a change sequence for each route over a 24-hour period. The specific operation steps are as follows:

[0086] (1) Set a time interval, such as one hour, and calculate the difference between the traffic flow in the next hour and the traffic flow in the previous hour to obtain the change value of the road segment in different time periods. For example, based on the 24-hour route and traffic flow mapping table of step 1, the traffic flow changes of each road segment in different time periods are obtained, as shown in Table 4 below.

[0087] Table 4: Traffic flow trends of various road sections at different time periods

[0088]

[0089]

[0090] In the embodiments of this specification, the increase or decrease trend (i.e., the positive or negative difference in traffic flow within each time period) is identified by symbols: increase (positive difference) is identified as 1, decrease (negative difference) is identified as -1, and no change (0 difference) is identified as 0. The increase or decrease in traffic flow for each road segment within each time interval after processing is shown in Table 5 below; the changes in traffic flow increase or decrease trend for each road segment of the route divided by time period are shown in Table 6 below.

[0091] Table 5: Traffic flow trends for each road segment during different time intervals

[0092]

[0093] Table 6: Traffic Flow Trends of Various Road Sections at Different Time Periods

[0094]

[0095]

[0096] In the embodiments of this specification, based on the changing trends of each road segment within a time interval, a traffic flow change sequence for each route is constructed. For example, for each road segment of route 1, the traffic flow trend sequence characteristics (route flow increase / decrease sequence) are constructed as shown in Table 7 below.

[0097] Table 7: Daily Route Traffic Increase / Decrease Sequences for Different Time Periods

[0098]

[0099]

[0100] In the embodiments of this specification, the above steps construct traffic flow trend sequence features for candidate areas. For different candidate areas, the traffic flow trend sequence features describe the traffic flow change trend of the candidate area over time. Candidate areas with similar traffic flow changes have many similarities in terms of site selection reference. Therefore, based on this feature, the accuracy of the prediction results of the placement category for candidate areas can be further improved.

[0101] S203: Determine the first mutual information between the target object's delivery indicators and the aforementioned payment-related characteristics, and the second mutual information between the aforementioned delivery indicators and the aforementioned traffic flow trend sequence characteristics.

[0102] In the embodiments of this specification, the target objects are vending machines, merchants, offline advertisements, etc.; mutual information is a useful information metric in information theory. It can be seen as the amount of information about another random variable contained in a random variable, or the uncertainty of a random variable is reduced due to the knowledge of another random variable.

[0103] In the embodiments described in this specification, such as Figure 5 As shown, the first mutual information between the above-mentioned target-oriented delivery indicators and the above-mentioned payment-related characteristics, and the second mutual information between the above-mentioned delivery indicators and the above-mentioned traffic flow trend sequence characteristics, include:

[0104] S2031: Input the above-mentioned payment association features and traffic flow trend sequence features into the delivery category prediction model; the above-mentioned delivery category prediction model is trained based on the sample payment association features and sample traffic flow trend sequence features of the sample delivery area, and the above-mentioned sample payment association features and sample traffic flow trend sequence features are all labeled with sample delivery category tags; the above-mentioned sample delivery category is determined based on the sample delivery index values ​​of the sample object.

[0105] S2033: Based on the above-mentioned delivery category prediction model, determine the first mutual information between the delivery indicators of the above-mentioned target objects and the payment association characteristics, and the second mutual information between the delivery indicators and the traffic flow trend sequence characteristics.

[0106] S205: Construct a comprehensive mutual information function based on the first mutual information and the second mutual information mentioned above.

[0107] In the embodiments of this specification, the sum of the first mutual information and the second mutual information can be used as the comprehensive mutual information function.

[0108] S207: Based on the above comprehensive mutual information function, adjust the values ​​corresponding to the above delivery indicators and calculate the comprehensive mutual information value.

[0109] In the embodiments described in this specification, the comprehensive mutual information value can be calculated by adjusting the values ​​corresponding to the delivery indicators.

[0110] S209: When the above comprehensive mutual information value is a preset threshold, the value corresponding to the preset threshold is determined as the predicted delivery index value of the above candidate area.

[0111] In the embodiments of this specification, a preset threshold corresponding to the comprehensive mutual information can be set according to user needs. When the comprehensive mutual information reaches the preset threshold, the predicted delivery indicator value can be determined.

[0112] S2011: Based on the above predicted distribution index values, determine the predicted distribution category results for the above candidate areas.

[0113] In the embodiments of this specification, the prediction results of the delivery category may include two (delivery area and non-delivery area) or more (multiple delivery categories divided according to the delivery index value, used to determine the delivery priority).

[0114] Specifically, in the embodiments of this specification, for a given input feature Q (payment association feature and traffic flow trend sequence feature), P(Q) is the probability of the input feature Q, that is, the probability of the occurrence of the payment association feature and the traffic flow trend sequence feature. The probability that the candidate region features contain feature set Q is specifically, in this invention, the probability that the candidate region contains the feature set of payment association feature q1 and traffic flow trend sequence feature q2.

[0115] For predicting the target A, construct P(A|Q) to maximize the conditional probability, using Bayes' theorem. For a given candidate region, the probability of the delivery category is returned as the output, i.e., P(A) = P(a), where a is the output delivery target; based on the constructed input features, the probability is: therefore,

[0116] therefore, The final model result is: This involves calculating the mutual information between the delivery target and the payment association features, and the mutual information between the delivery target and the traffic flow trend sequence features. These two parts of mutual information are then aggregated, and a mutual information filtering threshold is set to transform P(A|Q) into mutual information. Candidate areas where P(A|Q) meets the threshold requirements are then identified as the delivery areas for the target objects.

[0117] In the embodiments described in this specification, the above method further includes:

[0118] Determine whether the predicted target values ​​are greater than the preset target thresholds.

[0119] When the predicted delivery indicator value is greater than the preset indicator threshold, the candidate area is determined as a non-delivery area, and the delivery category prediction result of the candidate area being a non-delivery area is obtained.

[0120] S2013: When the above prediction result indicates that the above candidate area is the area to be deployed, the above candidate area shall be used as the deployment area for the above target object.

[0121] In the embodiments described in this specification, there are multiple candidate regions, and the method further includes:

[0122] S20131: Based on the predicted delivery index value corresponding to each candidate region, determine the delivery area for the above target objects.

[0123] Specifically, in the embodiments of this specification, determining the delivery area of ​​the target object based on the predicted delivery index value corresponding to each candidate area includes:

[0124] Among the multiple candidate regions, the candidate region whose predicted delivery index value is greater than the preset delivery threshold is determined as the delivery region for the aforementioned target object.

[0125] In the embodiments of this specification, when there are multiple candidate areas, the target area is determined based on the predicted delivery index value of each candidate area, thereby selecting the optimal delivery area to achieve the optimal delivery index value.

[0126] Specifically, in the embodiments of this specification, such as Figure 6 As shown, the above determination of the target area for the above-mentioned objects based on the predicted delivery index value corresponding to each candidate area includes:

[0127] S201311: Based on the predicted delivery index values ​​corresponding to each of the above candidate regions, sort the above candidate regions.

[0128] Specifically, in the embodiments of this specification, the sorting of the multiple candidate regions based on the predicted delivery index value corresponding to each candidate region includes:

[0129] Multiple candidate regions are sorted from largest to smallest according to the predicted deployment index values.

[0130] S201313: Based on the sorting results, determine the delivery area for the above target objects.

[0131] Specifically, in the embodiments of this specification, determining the delivery area of ​​the target object based on the sorting results includes:

[0132] The top-ranked, predetermined number of candidate regions will be selected as the target regions for the aforementioned objects.

[0133] In the embodiments of this specification, one or more candidate regions with larger delivery index values ​​can be selected as the delivery regions for the target objects based on the sorting results; thereby, the delivery regions for the number of users required can be obtained.

[0134] Specifically, in the embodiments of this specification, after determining multiple delivery areas, the delivery priority of each delivery area can be determined according to the sorting results; according to the predicted delivery index values ​​from largest to smallest, the delivery areas ranked earlier have higher priority than the delivery areas ranked later.

[0135] Specifically, in the embodiments of this specification, such as Figure 7 As shown, there are multiple target areas. After determining the target areas based on the sorting results, the method further includes:

[0136] S201315: Obtain the location information for each delivery area;

[0137] S201317: Based on the location information of each of the above-mentioned delivery areas, determine the target delivery area set; any target delivery area in the target delivery area set is adjacent to at least one other target delivery area; the other target delivery areas are areas in the target delivery area set other than any of the above-mentioned target delivery areas.

[0138] S201319: When the number of target delivery areas in the above-mentioned target delivery areas exceeds the preset number threshold, the target delivery areas in the above-mentioned target delivery areas are sorted from largest to smallest according to the predicted delivery index value.

[0139] S2013111: The top-ranked target delivery areas (those with a preset quantity threshold) are determined as the delivery areas for the target objects.

[0140] In the embodiments of this specification, if the number of adjacent regions exceeds the set maximum number of adjacent regions threshold N (which can be set to 5 according to the actual situation), these adjacent regions are selected as candidate regions of the predicted delivery index value TOPN as delivery regions; this can avoid the excessive concentration of delivery regions and thus improve the revenue of delivery regions.

[0141] In the embodiments described in this specification, the above method further includes:

[0142] The numerical prediction model for the delivery index was trained using the following method:

[0143] The sample payment correlation characteristics and sample traffic flow trend sequence characteristics are obtained from the sample delivery area labeled with the sample delivery category; the sample delivery category is determined based on the sample delivery index value of the sample object.

[0144] The above-mentioned sample payment correlation features and sample traffic flow trend sequence features are input into a preset machine learning model to perform prediction training for sample delivery categories;

[0145] During training, the parameters of the above-mentioned preset machine learning model are adjusted until the sample distribution category output by the above-mentioned preset machine learning model matches the input sample distribution area.

[0146] The machine learning model corresponding to the current model parameters is used as the numerical prediction model for the delivery index; where the current model parameters are the model parameters when the output sample delivery category matches the input sample delivery area.

[0147] In the embodiments of this specification, the preset machine learning model can be a Bayesian model, which satisfies the independence assumption, the input features are independent of each other, the model has high computational efficiency and strong interpretability.

[0148] In the embodiments described in this specification, the above method may include:

[0149] Obtain the sample distribution index value corresponding to each sample distribution area.

[0150] The sample distribution areas mentioned above are classified according to the sample distribution index values.

[0151] Specifically, in the embodiments of this specification, the sample placement indicators are different in different application scenarios; the sample placement indicator can be one indicator or multiple indicators. For example, in the offline advertising placement site selection scenario, the sample placement indicator is the advertising conversion rate; its corresponding value is the conversion rate value; in the merchant site selection scenario, the sample placement indicator can be product sales revenue or store transaction volume.

[0152] In the embodiments of this specification, the sample objects mentioned above include multiple sample deployment indicators, and the method mentioned above further includes:

[0153] Obtain the sample values ​​for each sample's delivery metrics;

[0154] Determine the weight information of each of the above sample delivery indicators;

[0155] Based on the sample values ​​and corresponding weight information of each sample delivery indicator, the sample delivery indicator values ​​are determined.

[0156] Specifically, in the embodiments of this specification, after obtaining the sample value of each sample deployment indicator, the above method further includes:

[0157] Filter out empty and abnormal sample values ​​from the sample values ​​to obtain filtered sample values;

[0158] Unit standardization is performed on the filtered sample values.

[0159] Specifically, in the embodiments of this specification, empty sample values ​​can be data that cannot be collected due to equipment (e.g., vending machine) malfunction; abnormal sample values ​​are values ​​that are significantly higher than theoretical values. For example, if the population of a region is 2 million and the collected data is 20 million, then this feature value is an abnormal sample value; unit unification processing of filtered sample values ​​refers to unifying the units of sample values ​​corresponding to the same feature, such as unifying the time unit to hours.

[0160] Specifically, in the embodiments of this specification, when the sample deployment index includes a first sample index, a second sample index, and a third sample index, the corresponding first weight information, second weight information, and third weight information are obtained respectively; the first product of the first sample index and the first weight information, the second product of the second sample index and the second weight information, and the third product of the third sample index and the third weight information are calculated; and the sum of the first product, the second product, and the third product is calculated to obtain the sample deployment index value.

[0161] In the embodiments of this specification, the above-mentioned multiple sample placement areas are classified according to the sample placement index values, including:

[0162] Obtain the indicator values ​​for the first sample and the indicator values ​​for the second sample;

[0163] Based on the values ​​of the first and second sample indicators, the multiple sample distribution areas are divided into N equal intervals.

[0164] Samples from the same interval are treated as one category.

[0165] Specifically, in the embodiments of this specification, the first sample indicator value is the largest sample deployment indicator value, and the second sample indicator value is the smallest sample deployment indicator value. Based on the first sample indicator value S... max Second sample index value S min The values ​​of multiple sample indicators are divided into N equal intervals, with intervals of 1 / 2. The intervals are: [S min S min +F],[S min +F,S min +2F],[S min +2F, S min +3F],……,[S min +(N-1)F,S max The same range of distribution areas is treated as one category. That is, multiple sample distribution areas are divided into N category labels according to the sample distribution index values. The specific N value is selected according to the actual needs of the scoring categories and ranges, ensuring that each range is distributed. Finally, the <sample distribution area, sample distribution index value> scoring library is constructed as shown in Table 8 below.

[0166] Table 8: Rating Library

[0167]

[0168]

[0169] Among them, sample distribution areas 1-4 belong to one category, sample distribution areas 5-7 belong to another category, and the higher the sample distribution index value, the greater the distribution value of the distribution area.

[0170] The method in this embodiment can be applied to scenarios such as merchant site selection, vending machine site selection, and offline advertising.

[0171] In the embodiments described in this specification, the above method further includes:

[0172] Based on the payment association characteristics and traffic flow trend sequence characteristics of candidate areas stored in the blockchain system, the blockchain system includes multiple nodes, and the multiple nodes form a peer-to-peer network.

[0173] In some embodiments, the blockchain system can be Figure 8The structure shown depicts a peer-to-peer (P2P) network formed by multiple nodes. The P2P protocol is an application layer protocol that runs on top of the Transmission Control Protocol (TCP). In a blockchain system, any machine, such as a server or terminal, can join and become a node. A node comprises a hardware layer, a middleware layer, an operating system layer, and an application layer.

[0174] Figure 8 The functions of each node in the blockchain system shown include:

[0175] 1) Routing: A basic function of nodes used to support communication between nodes.

[0176] In addition to routing capabilities, nodes can also have the following functions:

[0177] 2) Applications are deployed in the blockchain to implement specific business needs. They record data related to the implementation of functions to form record data, carry digital signatures in the record data to indicate the source of the task data, and send the record data to other nodes in the blockchain system. When other nodes successfully verify the source and integrity of the record data, they add the record data to a temporary block.

[0178] 3) A blockchain consists of a series of blocks that are sequentially generated. Once a new block is added to the blockchain, it will not be removed. The blocks contain the data submitted by the nodes in the blockchain system.

[0179] In some embodiments, the block structure can be Figure 9 The structure shown includes a block structure where each block contains the hash value of the transactions stored in that block (the hash value of this block) and the hash value of the previous block. These blocks are linked together to form the blockchain. Additionally, blocks may include information such as a timestamp when they were generated. Essentially, a blockchain is a decentralized database, a chain of data blocks linked together using cryptographic methods. Each data block contains relevant information used to verify the validity of the information (anti-counterfeiting) and to generate the next block.

[0180] As can be seen from the technical solutions provided in the embodiments of this specification above, after determining the payment association characteristics and traffic flow trend sequence characteristics of the candidate area, the embodiments of this specification determine the first mutual information between the target object's delivery index and the payment association characteristics, and the second mutual information between the delivery index and the traffic flow trend sequence characteristics. By synthesizing the mutual information function, the predicted delivery index value of the candidate area is determined, and the delivery category prediction result is determined based on this value, thereby determining whether to identify the candidate area as the delivery area of ​​the target object. This solution combines two independent features, namely payment association characteristics and traffic flow trend sequence characteristics, which improves the accuracy of determining the delivery category of the candidate area. Based on the first mutual information between the delivery index and the aforementioned payment association characteristics, and the second mutual information between the aforementioned delivery index and the aforementioned traffic flow trend sequence characteristics, the predicted delivery index value is accurately obtained, further improving the accuracy of determining the delivery category of the candidate area, thereby increasing the delivery index value of the target object's delivery area.

[0181] This application also provides a device for determining a delivery area, such as... Figure 10 As shown, the device includes:

[0182] The feature determination module 1010 is used to determine the payment association features and traffic flow trend sequence features of the candidate region;

[0183] The mutual information determination module 1020 is used to determine the first mutual information between the target object's delivery indicators and the aforementioned payment-related features, and the second mutual information between the aforementioned delivery indicators and the aforementioned traffic flow trend sequence features.

[0184] The function construction module 1030 is used to construct a comprehensive mutual information function based on the first mutual information and the second mutual information mentioned above.

[0185] The comprehensive mutual information value calculation module 1040 is used to adjust the values ​​corresponding to the above-mentioned delivery indicators based on the comprehensive mutual information function and calculate the comprehensive mutual information value.

[0186] The prediction delivery index value determination module 1050 is used to determine the value corresponding to the preset threshold as the prediction delivery index value of the candidate area when the above comprehensive mutual information value is a preset threshold.

[0187] The delivery category prediction module 1060 is used to determine the delivery category prediction result for the above candidate areas based on the above predicted delivery index values.

[0188] The delivery area determination module 1070 is used to determine the delivery area of ​​the target object when the prediction result indicates that the candidate area is a delivery area.

[0189] In some embodiments, the mutual information determination module described above may include:

[0190] The feature input unit is used to input the aforementioned payment association features and traffic flow trend sequence features into the delivery category prediction model; the delivery category prediction model is trained based on the sample payment association features and sample traffic flow trend sequence features of the sample delivery area, and the aforementioned sample payment association features and sample traffic flow trend sequence features are all labeled with sample delivery category tags; the aforementioned sample delivery category is determined based on the sample delivery index values ​​of the sample object.

[0191] The mutual information determination unit is used to determine, based on the above-mentioned delivery category prediction model, the first mutual information between the delivery indicators of the above-mentioned target object and the payment association features, and the second mutual information between the delivery indicators and the traffic flow trend sequence features.

[0192] In some embodiments, there are multiple candidate regions, and the apparatus further includes:

[0193] The first region determination module is used to determine the delivery region of the above target objects based on the predicted delivery index value corresponding to each candidate region.

[0194] In some embodiments, the region determination module includes:

[0195] The sorting unit is used to sort the multiple candidate regions based on the predicted delivery index value corresponding to each candidate region.

[0196] The delivery area determination unit is used to determine the delivery area of ​​the above target objects based on the sorting results.

[0197] In some embodiments, the target object can be placed in multiple areas, and the apparatus further includes:

[0198] The location information acquisition module is used to acquire the location information of each deployment area;

[0199] The target delivery area set determination module is used to determine the target delivery area set based on the location information of each of the above delivery areas; any target delivery area in the target delivery area set is adjacent to at least one other target delivery area; the other target delivery areas are areas in the target delivery area set other than any of the above target delivery areas.

[0200] The target delivery area sorting module is used to sort the target delivery areas in the above target delivery area set according to the predicted delivery index value from largest to smallest when the number of target delivery areas in the above target delivery area set exceeds a preset number threshold.

[0201] The second region determination module is used to determine the top-ranked target delivery regions (preset quantity thresholds) as the delivery regions for the target objects.

[0202] In some embodiments, the feature determination module includes:

[0203] The feature acquisition unit is used to acquire the payment features, the attribute features of the payment users, and the time series features of traffic flow for the above candidate areas.

[0204] The payment association feature determination unit is used to determine the payment association features based on the payment features and the attribute features of the payment user.

[0205] The traffic flow trend sequence feature determination unit is used to determine the traffic flow trend sequence features based on the aforementioned traffic flow time series features.

[0206] In some embodiments, the above-described apparatus further includes:

[0207] The distribution feature acquisition module is used to acquire the target industry distribution features and the distribution features of the number of preferred users in the above candidate regions.

[0208] In some embodiments, the payment association feature determination unit includes:

[0209] The derived feature determination subunit is used to combine the above-mentioned payment features and the attribute features of the above-mentioned payment users to obtain derived features;

[0210] The payment association feature determination subunit is used to determine the above-mentioned payment features, the above-mentioned payment user attribute features, the above-mentioned derived features, the above-mentioned target industry distribution features, and the above-mentioned preference user number distribution features as the above-mentioned payment association features.

[0211] In some embodiments, the above-described apparatus further includes:

[0212] The traffic flow acquisition module is used to acquire the traffic flow of each road segment in the above candidate areas;

[0213] The traffic flow change value determination module is used to determine the traffic flow change value of each road segment in each time period based on the traffic flow of each road segment mentioned above, and obtain the traffic flow time series characteristics mentioned above.

[0214] In some embodiments, the traffic flow trend sequence feature determination unit includes:

[0215] The traffic flow increase / decrease trend indicator determination sub-unit is used to determine the traffic flow increase / decrease trend indicator of each road segment in each time period based on the above traffic flow time series characteristics.

[0216] The traffic flow change trend determination sub-unit is used to determine the traffic flow change trend of each road segment in each time period based on the traffic flow increase / decrease trend indicators of each road segment in each time period.

[0217] The traffic flow trend sequence feature determination sub-unit is used to determine the traffic flow trend sequence features based on the traffic flow change trends of each road segment in each time period.

[0218] The apparatus and method embodiments described herein are based on the same inventive concept.

[0219] This application provides a delivery area determination device, which includes a processor and a memory. The memory stores at least one instruction or at least one program, which is loaded and executed by the processor to implement the delivery area determination method provided in the above method embodiments.

[0220] Embodiments of this application also provide a computer storage medium, which can be disposed in a terminal to store at least one instruction or at least one program related to implementing a method for determining a delivery area in the method embodiments. The at least one instruction or at least one program is loaded and executed by the processor to implement the method for determining a delivery area provided in the above method embodiments.

[0221] Embodiments of this application also provide a computer program product or computer program that includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0222] Optionally, in the embodiments of this specification, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0223] The memory described in the embodiments of this specification can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for the functions, etc.; the data storage area may store data created according to the use of the device, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory may also include a memory controller to provide the processor with access to the memory.

[0224] The deployment area determination method provided in this application can be executed on a mobile terminal, computer terminal, server, or similar computing device. Taking running on a server as an example, Figure 11 This is a hardware structure block diagram of a server for a method of determining a delivery area provided in an embodiment of this application. For example... Figure 11 As shown, the server 1100 can vary significantly due to different configurations or performance. It may include one or more central processing units (CPUs) 1110 (CPUs 1110 may include, but are not limited to, microprocessors such as MCUs or programmable logic devices such as FPGAs), a memory 1130 for storing data, and one or more storage media 1120 (e.g., one or more mass storage devices) for storing application programs 1123 or data 1122. The memory 1130 and storage media 1120 may be temporary or persistent storage. The program stored in the storage media 1120 may include one or more modules, each module may include a series of instruction operations on the server. Furthermore, the CPU 1110 may be configured to communicate with the storage media 1120 and execute the series of instruction operations stored in the storage media 1120 on the server 1100. Server 1100 may also include one or more power supplies 1160, one or more wired or wireless network interfaces 1150, one or more input / output interfaces 1140, and / or one or more operating systems 1121, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0225] The input / output interface 1140 can be used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of server 1100. In one example, the input / output interface 1140 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the input / output interface 1140 may be a radio frequency (RF) module for wireless communication with the Internet.

[0226] Those skilled in the art will understand that Figure 11 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, server 1100 may also include... Figure 11 The more or fewer components shown, or having the same Figure 11 The different configurations shown.

[0227] As can be seen from the embodiments of the delivery area determination method, apparatus, server, or storage medium provided in this application, after determining the payment association characteristics and traffic flow trend sequence characteristics of the candidate area, this application determines the first mutual information between the delivery index and the payment association characteristics of the target object, and the second mutual information between the delivery index and the traffic flow trend sequence characteristics. By synthesizing the mutual information function, the predicted delivery index value of the candidate area is determined, and the delivery category prediction result is determined based on this value, thereby determining whether to determine the candidate area as the delivery area of ​​the target object. This solution combines two independent features, payment association characteristics and traffic flow trend sequence characteristics, which improves the accuracy of determining the delivery category of the candidate area. Based on the first mutual information between the delivery index and the aforementioned payment association characteristics, and the second mutual information between the aforementioned delivery index and the aforementioned traffic flow trend sequence characteristics, the predicted delivery index value is accurately obtained, further improving the accuracy of determining the delivery category of the candidate area, thereby increasing the delivery index value of the target object's delivery area.

[0228] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0229] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0230] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer storage medium, such as a read-only memory, a disk, or an optical disk.

[0231] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for determining a deployment area, characterized in that, The method includes: Determine the payment association characteristics and traffic flow trend sequence characteristics of the candidate regions; The payment association features and the traffic flow trend sequence features are input into the delivery category prediction model; the delivery category prediction model is trained based on the sample payment association features and sample traffic flow trend sequence features of the sample delivery area, and both the sample payment association features and sample traffic flow trend sequence features are labeled with sample delivery category tags; the sample delivery category is determined based on the sample delivery index values ​​of the sample objects. Based on the delivery category prediction model, the first mutual information between the delivery index of the target object and the payment association feature and the second mutual information between the delivery index and the traffic flow trend sequence feature are determined. Based on the first mutual information and the second mutual information, a comprehensive mutual information function is constructed; Based on the comprehensive mutual information function, adjust the values ​​corresponding to the delivery indicators and calculate the comprehensive mutual information value; When the comprehensive mutual information value is a preset threshold, the value corresponding to the preset threshold is determined as the predicted delivery index value of the candidate region. Based on the predicted delivery index values, the delivery category prediction results for the candidate areas are determined; When the prediction result indicates that the candidate region is a region to be deployed, the candidate region is used as the deployment region for the target object.

2. The method according to claim 1, characterized in that, The candidate regions are multiple, and the method further includes: The target area is determined based on the predicted delivery index value corresponding to each candidate area.

3. The method according to claim 2, characterized in that, The step of determining the delivery area of ​​the target object based on the predicted delivery index value corresponding to each candidate area includes: Based on the predicted delivery index value corresponding to each candidate region, the multiple candidate regions are sorted. Based on the sorting results, the delivery area for the target object is determined.

4. The method according to claim 3, characterized in that, The target object has multiple delivery areas. After determining the delivery area of ​​the target object based on the sorting result, the method further includes: Obtain the location information for each delivery area; Based on the location information of each delivery area, a set of target delivery areas is determined; any target delivery area in the set of target delivery areas is adjacent to at least one other target delivery area; the other target delivery areas are the areas in the set of target delivery areas other than any of the target delivery areas. When the number of target delivery areas in the target delivery area set exceeds a preset threshold, the target delivery areas in the target delivery area set are sorted from largest to smallest according to the predicted delivery index value. The top-ranked target delivery areas (those meeting the preset quantity threshold) are determined as the delivery areas for the target objects.

5. The method according to any one of claims 1-4, characterized in that, The determination of the payment association characteristics and traffic flow trend sequence characteristics of the candidate region includes: Obtain the payment characteristics, payment user attribute characteristics, and traffic flow time series characteristics of the candidate region; The payment association features are determined based on the payment features and the attribute features of the payment user; Based on the time series characteristics of the traffic flow, the trend sequence characteristics of the traffic flow are determined.

6. The method according to claim 5, characterized in that, Before determining the payment association feature based on the payment feature and the attribute feature of the payment user, the method further includes: Obtain the target industry distribution characteristics and the distribution characteristics of the number of preferred users in the candidate region; Accordingly, determining the payment association features based on the payment features and the attribute features of the payment user includes: The payment features and the attribute features of the payment user are combined to obtain derived features; The payment characteristics, the attribute characteristics of the payment users, the derived characteristics, the target industry distribution characteristics, and the distribution characteristics of the number of preferred users are determined as the payment association characteristics.

7. The method according to claim 5, characterized in that, The method further includes: Obtain the traffic flow of each road segment in the candidate region; Based on the traffic flow of each road segment, the traffic flow change value of each road segment in each time period is determined, and the traffic flow time series characteristics are obtained. Accordingly, determining the traffic flow trend sequence characteristics based on the traffic flow time series characteristics includes: Based on the traffic flow time series characteristics, determine the traffic flow increase / decrease trend indicators for each road segment in each time period; Based on the traffic flow increase / decrease trend indicators of each road segment in each time period, determine the traffic flow change trend of each road segment in each time period; Based on the traffic flow change trend of each road segment in different time periods, the traffic flow trend sequence characteristics are determined.

8. A device for determining a delivery area, characterized in that, The device includes: The feature determination module is used to determine the payment association features and traffic flow trend sequence features of the candidate region; The mutual information determination module is used to input the payment association features and the traffic flow trend sequence features into the delivery category prediction model; the delivery category prediction model is trained based on the sample payment association features and sample traffic flow trend sequence features of the sample delivery area, and both the sample payment association features and the sample traffic flow trend sequence features are labeled with sample delivery category tags; the sample delivery category is determined based on the sample delivery index values ​​of the sample object; based on the delivery category prediction model, the first mutual information between the delivery index of the target object and the payment association features and the second mutual information between the delivery index and the traffic flow trend sequence features are determined; The function construction module is used to construct a comprehensive mutual information function based on the first mutual information and the second mutual information; The comprehensive mutual information value calculation module is used to adjust the value corresponding to the delivery indicator based on the comprehensive mutual information function and calculate the comprehensive mutual information value. The prediction delivery indicator value determination module is used to determine the value corresponding to the preset threshold as the prediction delivery indicator value of the candidate area when the comprehensive mutual information value is a preset threshold. The delivery category prediction module is used to determine the delivery category prediction result for the candidate area based on the predicted delivery index value. The delivery area determination module is used to determine the delivery area of ​​the target object when the prediction result indicates that the candidate area is a delivery area to be delivered.

9. The apparatus according to claim 8, characterized in that, The candidate regions are multiple, and the device further includes: The first region determination module is used to determine the delivery region of the target object based on the predicted delivery index value corresponding to each candidate region.

10. The apparatus according to claim 9, characterized in that, The region determination module includes: The sorting unit is used to sort the multiple candidate regions based on the predicted delivery index value corresponding to each candidate region. The delivery area determination unit is used to determine the delivery area of ​​the target object based on the sorting results.

11. The apparatus according to claim 10, characterized in that, The target object can be placed in multiple areas, and the device further includes: The location information acquisition module is used to acquire the location information of each deployment area; The target delivery area set determination module is used to determine a target delivery area set based on the location information of each delivery area; any target delivery area in the target delivery area set is adjacent to at least one other target delivery area; the other target delivery areas are areas in the target delivery area set other than any target delivery area. The target delivery area sorting module is used to sort the target delivery areas in the target delivery area set from largest to smallest according to the predicted delivery index value when the number of target delivery areas in the target delivery area set is greater than a preset number threshold. The second region determination module is used to determine the top-ranked preset quantity threshold target delivery regions as the delivery regions for the target object.

12. The apparatus according to any one of claims 8-11, characterized in that, The feature determination module includes: The feature acquisition unit is used to acquire the payment features of the candidate region, the attribute features of the paying users, and the time series features of traffic flow. A payment association feature determination unit is used to determine the payment association feature based on the payment feature and the attribute feature of the payment user; The traffic flow trend sequence feature determination unit is used to determine the traffic flow trend sequence features based on the traffic flow time series features.

13. The apparatus according to claim 12, characterized in that, The device further includes: The distribution feature acquisition module is used to acquire the target industry distribution features and the distribution features of the number of preferred users in the candidate region. The payment association feature determination unit includes: The derived feature determination subunit is used to combine the payment features and the attribute features of the payment user to obtain derived features; The payment association feature determination subunit is used to determine the payment feature, the attribute feature of the payment user, the derived feature, the target industry distribution feature, and the preference user number distribution feature as the payment association feature.

14. The apparatus according to claim 13, characterized in that, The device further includes: The traffic flow acquisition module is used to acquire the traffic flow of each road segment in the candidate area; The traffic flow change value determination module is used to determine the traffic flow change value of each road segment in each time period based on the traffic flow of each road segment, and obtain the traffic flow time series characteristics. The traffic flow trend sequence feature determination unit includes: The traffic flow increase / decrease trend identification subunit is used to determine the traffic flow increase / decrease trend identification of each road segment in each time period based on the traffic flow time series characteristics. The traffic flow change trend determination subunit is used to determine the traffic flow change trend of each road segment in each time period based on the traffic flow increase / decrease trend indicator of each road segment in each time period. The traffic flow trend sequence feature determination subunit is used to determine the traffic flow trend sequence features based on the traffic flow change trend of each road segment in each time period.

15. A computer storage medium, characterized in that, The computer storage medium stores at least one instruction or at least one program, which is loaded and executed by a processor to implement the deployment area determination method as described in any one of claims 1-7.

Images