Method and device for identifying a delivery party suitable for a mixed delivery mode

Abstract

The present application provides a method, device, computer-readable storage medium, and electronic device for identifying a delivery party suitable for a mixed delivery mode. The method includes: generating a second delivery range of the target delivery party to be identified based on the first delivery range of the target delivery party; wherein the second delivery range includes the first delivery range; determining the second delivery range characteristics based on the second delivery range, and obtaining the first delivery range characteristics of the first delivery range and the delivery party characteristics of the target delivery party; based on the second delivery range characteristics, the first delivery range characteristics, and the delivery party characteristics, predicting the change value of the business within the second delivery range after the target delivery party adopts mixed delivery; and determining that the target delivery party is suitable for the mixed delivery mode when the change value meets the preset conditions.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a method, device, computer storage medium and electronic device for identifying a distributor suitable for a mixed delivery mode. Background Art

[0002] In logistics distribution, there are usually two different delivery modes: dedicated delivery and express delivery. Among them, dedicated delivery can refer to a mode in which a full-time delivery person provided by a logistics platform performs delivery. Express delivery can refer to a mode in which social personnel perform delivery part-time in their spare time (in some embodiments, express delivery may also be referred to as crowdsourcing). Dedicated delivery has the advantage of good service experience, but it also has the disadvantages of high delivery cost and small delivery range. However, express delivery is just the opposite. It has the advantages of low delivery cost and large delivery range, but also has the disadvantages of poor service experience.

[0003] In the prior art, in order to strike a balance between service experience and delivery costs, delivery platforms will open a mixed delivery mode of dedicated and express delivery (hereinafter referred to as the mixed delivery mode) for the delivery party, that is, dedicated delivery is used within a preset smaller delivery range (to ensure service experience); and express delivery is used within a larger outer ring range (i.e. a circular delivery range outside the smaller delivery range) (to reduce delivery costs and increase the number of delivery orders).

[0004] The following is based on Figure 1 The delivery range diagram shown introduces the delivery range of the special delivery method described in this application (hereinafter referred to as the first delivery range), and the delivery range of the express delivery method outside the first delivery range (hereinafter referred to as the second delivery range).

[0005] Figure 1 In the figure, the merchant's position is P (the position of the black dot in the figure). When the merchant adopts the mixed delivery method, based on the characteristics of the mixed delivery mentioned above, it uses special delivery within a preset smaller delivery range; and uses express delivery within a larger outer ring range. Therefore, Figure 1 The first delivery range of the merchant is S1 (the range of the white circular area in the figure); and S2 (the black ring area in the figure) surrounded by the first delivery range S1 is the second delivery range described in this specification.

[0006] However, mixed delivery is not suitable for all couriers. In some cases, after the mixed delivery is enabled, the couriers may actually suffer losses within the newly added second delivery range. In the prior art, the delivery platform mainly relies on the human experience of the auditors to review whether the couriers are suitable for the mixed delivery mode, but lacks a solution to objectively evaluate whether the couriers are suitable for the mixed delivery mode.

[0007] Therefore, there is a need to provide a solution for identifying the delivery parties suitable for the mixed delivery mode. Summary of the invention

[0008] In view of this, the present application provides a method, device, computer storage medium and electronic device for identifying whether a delivery partner is suitable for a mixed delivery mode, so as to solve the above-mentioned problem of low accuracy in identifying whether a delivery partner is suitable for a mixed delivery mode.

[0009] Specifically, the present application is implemented through the following technical solutions:

[0010] A method for identifying a delivery party suitable for a mixed delivery mode, the method comprising:

[0011] Generate a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range;

[0012] Determining a second delivery range characteristic based on the second delivery range, and acquiring a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party;

[0013] Based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, predicting the change value of the business within the second delivery range after the target delivery party adopts mixed delivery;

[0014] When the change value meets the preset conditions, it is determined that the target delivery party is suitable for the mixed delivery mode.

[0015] Optionally, the generating the second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified includes:

[0016] The boundary of the first delivery range is extended outward by a preset distance, and the extended area is determined as the second delivery range.

[0017] Optionally, the step of extending the boundary of the first delivery range outward by a preset distance and determining the extended area as the second delivery range includes:

[0018] Taking the boundary coordinate points of the first delivery range as reference points, the preset distances are respectively extended outwards to serve as boundary coordinate points of the second delivery range;

[0019] The boundary of the second delivery range is determined according to the navigation path between adjacent boundary coordinate points among the boundary coordinate points of the second delivery range; wherein the area between the boundary of the second delivery range and the boundary of the first delivery range is the second delivery range.

[0020] Optionally, the predicting, based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, of a change value of the business within the second delivery range after the target delivery party adopts mixed delivery, includes:

[0021] Inputting the second delivery range feature, the first delivery range feature and the delivery party feature into a preset machine learning model;

[0022] Obtain the change value of the target delivery party adopting the mixed delivery business output after calculation by the machine learning model.

[0023] Optionally, the method further includes training the preset machine learning model in the following manner:

[0024] Obtain the second delivery range characteristics, first delivery range characteristics, and delivery party characteristics generated by the delivery party adopting mixed delivery history, as well as the change value of the business within the second delivery range;

[0025] Input the second delivery range feature, the first delivery range feature, the delivery party feature and the change value as training samples to the machine learning algorithm training; wherein the second delivery range feature, the first delivery range feature and the delivery party feature are used as sample inputs, and the change value is used as sample output;

[0026] Get the final trained machine learning model.

[0027] Optionally, the machine learning algorithm includes a random forest algorithm.

[0028] Optionally, when the change value meets a preset condition, determining that the target delivery party is suitable for a mixed delivery mode includes:

[0029] When the change value reaches a threshold value, it is determined that the target delivery party is suitable for the mixed delivery mode.

[0030] Optionally, the first delivery range feature includes: at least one of the distribution of historical orders of the delivery party within the first delivery range and the revenue of historical orders;

[0031] The second delivery range characteristics include:

[0032] At least one of user preference and user consumption amount within the second delivery range;

[0033] The delivery party characteristics include:

[0034] Basic information of the delivery party and at least one of the transportation capabilities surrounding the delivery party.

[0035] A device for identifying a delivery party suitable for a mixed delivery mode, the device comprising:

[0036] A generating unit, which generates a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range;

[0037] A construction unit, which determines a second delivery range characteristic based on the second delivery range, and obtains a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party;

[0038] A prediction unit, based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, predicts a change value of the business within the second delivery range after the target delivery party adopts mixed delivery;

[0039] The identification unit determines that the target delivery party is suitable for the mixed delivery mode when the change value meets the preset conditions.

[0040] A computer-readable storage medium stores a computer program, wherein the computer program is used to execute any of the above methods for identifying a delivery party suitable for a mixed delivery mode.

[0041] An electronic device, comprising:

[0042] processor;

[0043] a memory for storing processor-executable instructions;

[0044] The processor is configured to implement any of the above-mentioned methods for identifying a delivery party suitable for a mixed delivery mode.

[0045] An embodiment of the present application provides a scheme for identifying a delivery party suitable for a mixed delivery mode, wherein a second delivery range of the target delivery party to be identified is generated according to the first delivery range of the target delivery party; the second delivery range characteristics are determined according to the second delivery range, and the first delivery range characteristics of the first delivery range and the delivery party characteristics of the target delivery party are obtained; based on the first delivery range characteristics, the second delivery range characteristics and the delivery party characteristics, the change value of the business within the second delivery range after the target delivery party adopts mixed delivery is predicted; when the change value meets the preset conditions, it is determined that the target delivery party is suitable for the mixed delivery mode. In this way, by predicting the change in the business within the second delivery range of the delivery party after the mixed delivery is adopted, it is determined whether the delivery party is suitable for mixed delivery, so that only those delivery parties suitable for mixed delivery can be opened. Since the prediction result is based on the objectively existing first delivery range characteristics, second delivery range characteristics and delivery personnel characteristics, the prediction result is also objective and conforms to the laws of nature. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic diagram of a first delivery range and a second delivery range shown in an exemplary embodiment of the present application;

[0047] Figure 2is a flow chart of a method for identifying a delivery party suitable for a mixed delivery mode, shown in an exemplary embodiment of the present application;

[0048] Figure 3 It is a hardware structure diagram of a device for identifying a delivery party suitable for a mixed delivery mode, shown in an exemplary embodiment of the present application;

[0049] Figure 4 It is a module diagram of a device for identifying a delivery party suitable for a mixed delivery mode, shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0050] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0051] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be understood that although the terms first, second, third, etc. may be used in the present application to describe various information, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0053] As mentioned above, mixed delivery is not suitable for all couriers. In some cases, activating mixed delivery may cause the couriers to lose money.

[0054] To this end, this application provides a solution for identifying a delivery party that is suitable for the mixed delivery mode. By predicting the changes in the delivery party's business within the second delivery range after the mixed delivery is adopted, it is determined whether the delivery party is suitable for mixed delivery, so that only those delivery parties suitable for mixed delivery can be opened. Since the prediction result is based on the objectively existing first delivery range characteristics, second delivery range characteristics and delivery personnel characteristics, the prediction result is also objective and in line with natural laws.

[0055] The following takes the instant delivery scenario as an example to introduce the delivery party and other related business parties described in this application. The instant delivery scenario may include but is not limited to offline door-to-door services such as takeout, express delivery, and errands. In the instant delivery scenario, merchants and customers can reach a logistics order through the instant delivery APP. The customer can be the logistics recipient, the instant delivery APP can be the server, and the merchant can be the delivery party. Customers can browse different merchants and a variety of goods provided by merchants through the instant delivery APP. When the customer determines the goods and the merchant where they are located, they can place an order; generally, during the ordering process, the customer is required to provide logistics information such as the receiving address, contact information, etc.; after the customer places an order, the server can push the order information to the corresponding merchant, and the merchant needs to confirm whether to accept the order. If the order is confirmed, the server can match the delivery person for delivery based on the merchant's delivery method. If the merchant adopts mixed delivery, when the customer's receiving address is located in the first delivery range corresponding to the merchant's special delivery method, the server can match the best special delivery courier for delivery; when the customer's receiving address is located in the second delivery range corresponding to the merchant's express delivery method, the server can match the best express delivery courier for delivery; when the customer's receiving address is located in both the first delivery range and the second delivery range of the merchant, based on the cost-first strategy (the delivery fee charged by the express delivery courier is lower than that of the special delivery courier), the server can match the best express delivery courier for delivery.

[0056] The following combination Figure 2 An exemplary embodiment of the present application shows a flow chart of a method for identifying a delivery party suitable for a mixed delivery mode. The method can be applied in a server. The method can specifically include the following steps:

[0057] Step 110: Generate a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range.

[0058] In an embodiment of the present application, the server may receive an identification request for a target delivery party, and the identification request carries the first delivery range data of the target delivery party. Generally, both the first delivery range and the second delivery range may refer to coordinate data represented by a number of position coordinates (e.g., longitude and latitude coordinates). Usually, the boundaries of the original delivery range may be planned based on the position coordinates (e.g., the convex hull algorithm may be used to draw the maximum range of the area contained by these position coordinates on a map).

[0059] Since the current target delivery party has not yet opened mixed delivery, the target delivery party only has the first delivery range but not the second delivery range. Therefore, the server needs to generate a second delivery range based on the first delivery range for the target delivery party.

[0060] The server may use a preset second delivery range generation algorithm to generate a second delivery range outside the first delivery range and surrounding the first delivery range.

[0061] In one embodiment, the server may expand the boundary of the first delivery range outward by a preset distance and determine the expanded area as the second delivery range.

[0062] Specifically, the boundary coordinate points of the first delivery range are used as reference points, and the preset distances are respectively extended outward to serve as boundary coordinate points of the second delivery range;

[0063] The boundary of the second delivery range is determined according to the navigation path between adjacent boundary coordinate points among the plurality of boundary coordinate points of the second delivery range; wherein the area between the boundary of the second delivery range and the boundary of the first delivery range is the second delivery range.

[0064] In a specific implementation, the boundary of the second delivery range can be determined by using a convex hull algorithm to connect the boundary coordinate points of the multiple second delivery ranges into a closed curve of a convex hull, and the range within the closed curve of the convex hull and outside the first delivery range is the second delivery range.

[0065] In one embodiment, the preset distance may be a preset empirical value. The preset distance may be fixed or dynamically variable, for example, it may be flexibly adjusted according to the specific area where the merchant is located.

[0066] For example, the preset distance can be adjusted according to the current time period of the merchant's area. Generally, the delivery demand is different in different time periods. In time periods with strong delivery demand, such as lunch and dinner, the preset distance can be shortened accordingly to prevent the merchant from overloading; conversely, in time periods with low delivery demand, such as early morning, the preset distance can be lengthened accordingly.

[0067] For another example, the preset distance can be adjusted according to the current transportation capacity of the merchant's area. Generally, when the transportation capacity is tight, the preset distance can be shortened to avoid a burst of orders; conversely, when the transportation capacity is sufficient, the preset distance can be lengthened.

[0068] In one embodiment, the server may determine an area within a preset distance outside the first delivery range as the second delivery range according to preset parameters.

[0069] For example, if the first delivery range is expanded by 1 times, then this expanded range will become the second delivery range.

[0070] For another example, if the first delivery range is expanded by 3 kilometers, the expanded range will become the second delivery range.

[0071] Compared with the previous embodiment, this embodiment does not require complicated calculations and can generate the second delivery range simply and quickly.

[0072] The first delivery range described in the present application can be a circle, a polygon or any other shape. The second delivery range after expansion can also be any shape. Figure 1 The second delivery range is a circular delivery range.

[0073] It is worth mentioning that since the target delivery party has not yet opened mixed delivery, the second delivery range currently generated is actually a virtual second delivery range, which is not actually applicable to the target delivery party. In other words, although the server generates the second delivery range of the target delivery party, the second delivery range is invisible and imperceptible to the target delivery party or any other user, and does not participate in or affect the current actual business of the target delivery party.

[0074] Step 120: Determine a second delivery range characteristic based on the second delivery range, and obtain a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party.

[0075] After generating the second delivery range of the target delivery party, the server may determine the second delivery range characteristics of the target delivery party based on the second delivery range.

[0076] The first delivery range feature may specifically include one or more of the following features: historical order distribution of the delivery party within the first delivery range, historical delivery experience and other features, historical order revenue, and features related to profit and loss within the first delivery range;

[0077] The second delivery range characteristics may specifically include one or more of the following characteristics: demand characteristics of users within the second delivery range, including characteristics of user preferences, user consumption amounts, and characteristics related to profit and loss within the second delivery range;

[0078] The delivery party characteristics may specifically include one or more of the following characteristics: basic information of the delivery party, transportation capacity of the delivery party's surrounding areas, characteristics of the delivery party in comparison with surrounding delivery parties, and characteristics of the delivery party in comparison with the first delivery range and the second delivery range.

[0079] Step 130: Based on the characteristics of the second delivery range, the characteristics of the first delivery range and the characteristics of the delivery party, predict the change value of the business within the second delivery range after the target delivery party adopts mixed delivery.

[0080] After determining the second delivery range characteristics of the target delivery party and obtaining the first delivery range characteristics of the first delivery range and the delivery party characteristics of the target delivery party, the server can predict the change value of the business within the second delivery range after the target delivery party adopts mixed delivery.

[0081] In one embodiment, the server may pre-train a machine learning model for predicting the business change value within the second delivery range of the target delivery party based on machine learning technology.

[0082] That is, the step 130 includes:

[0083] Inputting the second delivery range feature, the first delivery range feature and the delivery party feature into a preset machine learning model;

[0084] Obtain the change value of the target delivery party adopting the mixed delivery business output after calculation by the machine learning model.

[0085] With the development of machine learning technology, the pre-trained machine learning model is used to predict the change value of the hybrid delivery service adopted by the standard delivery party, with high calculation efficiency and accuracy.

[0086] The following describes the training process of the preset machine learning model:

[0087] Obtain the second delivery range characteristics, first delivery range characteristics, and delivery party characteristics generated by the delivery party adopting mixed delivery history, as well as the change value of the business within the second delivery range;

[0088] Input the second delivery range feature, the first delivery range feature, the delivery party feature and the change value as training samples to the machine learning algorithm training; wherein the second delivery range feature, the first delivery range feature and the delivery party feature are used as sample inputs, and the change value is used as sample output;

[0089] Get the final trained machine learning model.

[0090] Specifically, the server can pre-collect a large number of second delivery range characteristics, first delivery range characteristics and delivery party characteristics generated by the history of delivery parties that have activated mixed delivery, as well as the change value of each delivery party's business within the second delivery range.

[0091] Then, the second delivery range feature, first delivery range feature, delivery party feature and change value (paired data) of each delivery party are used as training sample sets (generally, the feature can be used as input value and the change value can be used as output value), and the machine learning model is trained based on the machine learning algorithm. The machine learning model can be continuously improved through continuous learning. When the machine learning model meets the exit condition (for example, the accuracy of the predicted change value and the actual change value predicted for all delivery parties meets the business requirements), the machine learning model can be put online and used.

[0092] When predicting the change value of the target delivery party's business, after the target delivery party's second delivery range characteristics, first delivery range characteristics and delivery party characteristics are input into the machine learning model as input data, the machine learning model can calculate and output a change value based on the trained algorithm.

[0093] The machine learning model may adopt, for example, logistic regression (LR), GBDT (gradient boosted decision tree), random forest algorithm, etc.

[0094] Taking the random forest algorithm as an example, the algorithm of the machine learning model can be:

[0095] For example, A = f(B,C,D)

[0096] Among them, A represents the change value, B represents the first delivery range characteristics, C represents the second delivery range characteristics, and D represents the delivery party characteristics.

[0097] The random forest algorithm is used as the machine learning model, which has the advantages of good model generalization performance and fast model training convergence.

[0098] Step 140: When the change value meets the preset conditions, determine that the target delivery party is suitable for the mixed delivery mode.

[0099] The preset condition can be flexibly set in advance according to business needs.

[0100] For example, the preset conditions may also be set by the target delivery party. In this way, different target delivery parties may have different preset conditions to meet the personalized needs of different delivery parties and achieve a personalized effect.

[0101] In one embodiment, the change value may include a profit value of the target delivery party in the second delivery area. In this case, the preset condition may be related to the profit value.

[0102] For example, when the change value, i.e., the profit value, reaches (is equal to or greater than) a threshold, it is determined that the target delivery party is suitable for the mixed delivery mode. The threshold can also be preset by the target delivery person.

[0103] Taking merchants as an example, in order to ensure profitability, merchants can set the threshold to a positive value; in this way, merchants are allowed to enable mixed delivery only when the business within the second delivery range is profitable.

[0104] In some cases, in order to increase visibility or traffic, merchants can also set the threshold to a negative value, that is, after activating mixed delivery, merchants allow the business within the second delivery range to be loss-making; as long as the loss amount does not exceed the threshold, mixed delivery can be activated.

[0105] Of course, the above are just examples. In actual applications, the target delivery person can be flexibly set based on business needs.

[0106] In one embodiment, the change value may include the time taken by the deliveryman to pick up the goods, and the preset condition may be less than the preset time; that is, when the time taken by the deliveryman to pick up the goods is less than the preset time, it is determined that the target delivery party is suitable for the mixed delivery mode. This ensures that the deliveryman does not take too long to pick up the goods, thus avoiding delivery timeout.

[0107] In one embodiment, the change value may include the receiving time of the logistics recipient, and the preset condition may be less than the preset time; that is, when the receiving time of the logistics recipient is less than the preset time, it is determined that the target delivery party is suitable for the mixed delivery mode. This ensures that the receiving time of the logistics recipient is not too long, thus avoiding delivery timeout.

[0108] The above-mentioned change values ​​can be used in combination to more accurately identify whether the target delivery party is suitable for opening a mixed delivery mode.

[0109] After determining that the target delivery party is suitable for the mixed delivery mode, the server may enable mixed delivery for the target delivery party.

[0110] Specifically, when the change value meets the preset conditions, the server can enable mixed delivery for the target delivery party, and make the second delivery range of the target delivery party generated above effective, so that the actual business of the target delivery party can adopt the second delivery range. For example, the target delivery party is pushed to users within the second delivery range, so that users within the second delivery range can see the services provided by the target delivery party.

[0111] In summary, the present application provides a solution for identifying the delivery party that is suitable for the mixed delivery mode, determining the second delivery range characteristics according to the second delivery range, and obtaining the first delivery range characteristics of the first delivery range and the delivery party characteristics of the target delivery party; predicting the change value of the business within the second delivery range after the target delivery party adopts mixed delivery according to the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics; determining that the target delivery party is suitable for the mixed delivery mode when the change value meets the preset conditions. In this way, by predicting the change of the delivery party's business within the second delivery range after the mixed delivery is adopted, it is determined whether the delivery party is suitable for mixed delivery, so that only those delivery parties that are suitable for mixed delivery can be opened. Since the prediction result is based on the objectively existing first delivery range characteristics, second delivery range characteristics and delivery personnel characteristics, the prediction result is also objective and in line with the laws of nature.

[0112] Corresponding to the aforementioned embodiment of the method for identifying whether a delivery partner is suitable for a mixed delivery mode, the present application also provides an embodiment of a device for identifying whether a delivery partner is suitable for a mixed delivery mode.

[0113] The embodiment of the device for identifying the delivery party suitable for the mixed delivery mode in this application can be applied on the server. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor in which it is located reading the corresponding computer program instructions in the non-volatile memory into the memory and running them. From the hardware level, if Figure 3 As shown, it is a hardware structure diagram of the device for identifying the delivery party suitable for the mixed delivery mode in this application, except Figure 3 In addition to the processor, memory, network interface, and non-volatile memory shown, the embodiments may also include other hardware based on the actual function of identifying the delivery party suitable for the mixed delivery mode, which will not be described in detail.

[0114] Please refer to Figure 4 In a software implementation, the device for identifying that the delivery party is suitable for the mixed delivery mode may include:

[0115] A generating unit 310 generates a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range;

[0116] A construction unit 320 determines a second delivery range characteristic based on the second delivery range, and obtains a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party;

[0117] The prediction unit 330 predicts the change value of the business within the second delivery range after the target delivery party adopts mixed delivery based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics;

[0118] The identification unit 340 determines that the target delivery party is suitable for the mixed delivery mode when the change value meets the preset conditions.

[0119] Optionally, the generating unit 310 includes:

[0120] The boundary of the first delivery range is extended outward by a preset distance, and the extended area is determined as the second delivery range.

[0121] Optionally, the generating unit 310 includes:

[0122] The expansion subunit uses the boundary coordinate point of the first delivery range as a reference point and expands outward by a preset distance to serve as the boundary coordinate point of the second delivery range;

[0123] The generation subunit determines the boundary of the second delivery range according to the navigation path between adjacent boundary coordinate points among the boundary coordinate points of the second delivery range; wherein the area between the boundary of the second delivery range and the boundary of the first delivery range is the second delivery range.

[0124] Optionally, the prediction unit 330 includes:

[0125] An input subunit, inputting the second delivery range feature, the first delivery range feature and the delivery party feature into a preset machine learning model;

[0126] The output subunit obtains the change value of the target delivery party adopting the mixed delivery service output after calculation by the machine learning model.

[0127] Optionally, the device further comprises: training the preset machine learning model using the following subunits:

[0128] Obtaining subunits, obtaining the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics generated by the delivery party adopting mixed delivery history, and the change value of the business within the second delivery range;

[0129] A training subunit, inputting the second delivery range feature, the first delivery range feature, the delivery party feature and the change value as training samples into a machine learning algorithm training; wherein the second delivery range feature, the first delivery range feature and the delivery party feature are used as sample inputs, and the change value is used as sample output;

[0130] Determine the subunits and obtain the final trained machine learning model.

[0131] Optionally, the machine learning algorithm includes a random forest algorithm.

[0132] Optionally, the identification unit 340 includes:

[0133] When the change value reaches a threshold value, it is determined that the target delivery party is suitable for the mixed delivery mode.

[0134] Optionally, the first delivery range characteristics include:

[0135] At least one of the distribution of historical orders and revenue of historical orders of the delivery party within the first delivery range;

[0136] The second delivery range characteristics include:

[0137] At least one of user preference and user consumption amount within the second delivery range;

[0138] The delivery party characteristics include:

[0139] Basic information of the delivery party and at least one of the transportation capabilities surrounding the delivery party.

[0140] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.

[0141] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present application scheme. A person of ordinary skill in the art can understand and implement it without paying any creative work.

[0142] above Figure 4 The internal functional modules and structural schematic diagram of the device for identifying the delivery party suitable for the mixed delivery mode are described. The substantial execution subject thereof can be an electronic device, including:

[0143] processor;

[0144] a memory for storing processor-executable instructions;

[0145] Wherein, the processor is configured to:

[0146] Generate a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range;

[0147] Determining a second delivery range characteristic based on the second delivery range, and acquiring a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party;

[0148] Based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, predicting the change value of the business within the second delivery range after the target delivery party adopts mixed delivery;

[0149] When the change value meets the preset conditions, it is determined that the target delivery party is suitable for the mixed delivery mode.

[0150] Optionally, the generating the second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified includes:

[0151] The boundary of the first delivery range is extended outward by a preset distance, and the extended area is determined as the second delivery range.

[0152] Optionally, the step of extending the boundary of the first delivery range outward by a preset distance and determining the extended area as the second delivery range includes:

[0153] Taking the boundary coordinate points of the first delivery range as reference points, the preset distances are respectively extended outwards to serve as boundary coordinate points of the second delivery range;

[0154] The boundary of the second delivery range is determined according to the navigation path between adjacent boundary coordinate points among the boundary coordinate points of the second delivery range; wherein the area between the boundary of the second delivery range and the boundary of the first delivery range is the second delivery range.

[0155] Optionally, the predicting, based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, of a change value of the business within the second delivery range after the target delivery party adopts mixed delivery, includes:

[0156] Inputting the second delivery range feature, the first delivery range feature and the delivery party feature into a preset machine learning model;

[0157] Obtain the change value of the target delivery party adopting the mixed delivery business output after calculation by the machine learning model.

[0158] Optionally, the method further includes training the preset machine learning model in the following manner:

[0159] Obtain the second delivery range characteristics, first delivery range characteristics, and delivery party characteristics generated by the delivery party adopting mixed delivery history, as well as the change value of the business within the second delivery range;

[0160] Input the second delivery range feature, the first delivery range feature, the delivery party feature and the change value as training samples to the machine learning algorithm training; wherein the second delivery range feature, the first delivery range feature and the delivery party feature are used as sample inputs, and the change value is used as sample output;

[0161] Get the final trained machine learning model.

[0162] Optionally, the machine learning algorithm includes a random forest algorithm.

[0163] Optionally, when the change value meets a preset condition, determining that the target delivery party is suitable for a mixed delivery mode includes:

[0164] When the change value reaches a threshold value, it is determined that the target delivery party is suitable for the mixed delivery mode.

[0165] Optionally, the first delivery range characteristics include:

[0166] At least one of the distribution of historical orders and revenue of historical orders of the delivery party within the first delivery range;

[0167] The second delivery range characteristics include:

[0168] At least one of user preference and user consumption amount within the second delivery range;

[0169] The delivery party characteristics include:

[0170] Basic information of the delivery party and at least one of the transportation capabilities surrounding the delivery party.

[0171] In the above-mentioned embodiment of the electronic device, it should be understood that the processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can be any conventional processor, etc., and the aforementioned memory can be a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk, or a solid-state drive. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0172] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the electronic device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0173] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for identifying a delivery party suitable for a mixed delivery mode, characterized in that: The method comprises: Generate a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified; wherein the second delivery range surrounds the first delivery range; Determining a second delivery range characteristic based on the second delivery range, and acquiring a first delivery range characteristic of the first delivery range and a delivery party characteristic of the target delivery party; Based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics, predicting the change value of the business within the second delivery range after the target delivery party adopts mixed delivery; When the change value meets the preset condition, determining that the target delivery party is suitable for the mixed delivery mode; If it is determined that the target delivery party is suitable for the mixed delivery mode, opening the mixed delivery mode for the target delivery party; Pushing the target delivery party to users within the second delivery range, so that users within the second delivery range can see the services provided by the target delivery party at any time; The mixed delivery mode includes using special delivery or express delivery within the first delivery range; using express delivery between the first delivery range and the second delivery range; The predicting of the change value of the business within the second delivery range after the target delivery party adopts mixed delivery based on the second delivery range characteristics, the first delivery range characteristics and the delivery party characteristics includes: Inputting the second delivery range feature, the first delivery range feature and the delivery party feature into a preset machine learning model; Obtaining a change value of the target delivery party adopting a hybrid delivery service output after calculation by the machine learning model; The method further includes training the preset machine learning model in the following manner: Obtain the second delivery range characteristics, first delivery range characteristics, and delivery party characteristics generated by the delivery party adopting mixed delivery history, as well as the change value of the business within the second delivery range; Input the second delivery range feature, the first delivery range feature, the delivery party feature and the change value as training samples to the machine learning algorithm training; wherein the second delivery range feature, the first delivery range feature and the delivery party feature are used as sample inputs, and the change value is used as sample output; Get the final trained machine learning model; The first delivery range characteristics include: At least one of the distribution of historical orders and revenue of historical orders of the delivery party within the first delivery range; The second delivery range characteristics include: At least one of user preference and user consumption amount within the second delivery range; The delivery party characteristics include: Basic information of the delivery party and at least one of the transportation capabilities surrounding the delivery party.

2. The method according to claim 1, characterized in that The step of generating a second delivery range of the target delivery party based on the first delivery range of the target delivery party to be identified includes: The boundary of the first delivery range is extended outward by a preset distance, and the extended area is determined as the second delivery range.

3. The method according to claim 2, characterized in that The step of extending the boundary of the first delivery range outward by a preset distance and determining the extended area as the second delivery range includes: Taking the boundary coordinate points of the first delivery range as reference points, the preset distances are respectively extended outwards to serve as boundary coordinate points of the second delivery range; The boundary of the second delivery range is determined according to the navigation path between adjacent boundary coordinate points among the boundary coordinate points of the second delivery range; wherein the area between the boundary of the second delivery range and the boundary of the first delivery range is the second delivery range.

4. The method according to claim 1, characterized in that: The machine learning algorithm includes a random forest algorithm.

5. The method according to any one of claims 1 to 4, characterized in that When the change value meets the preset condition, determining that the target delivery party is suitable for the mixed delivery mode includes: When the change value reaches a threshold value, it is determined that the target delivery party is suitable for the mixed delivery mode.

6. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 5.

7. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to perform the method according to any one of claims 1 to 5.

Images