Delivery method, device, computer equipment and storage medium based on user portrait

Abstract

The present application relates to a delivery method, device, computer equipment and storage medium based on user portrait. The method includes: obtaining the collected waybill data; determining the user to be queried according to the recipient information in the waybill data, and determining the receiving outlet according to the receiving address information in the waybill data; obtaining the corresponding user outlet dimension portrait by querying the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet; when the corresponding user outlet dimension portrait exists in the preset user outlet dimension portrait database, pushing a first telephone contact prompt according to the user outlet dimension portrait; when the corresponding user outlet dimension portrait does not exist in the preset user outlet dimension portrait database, obtaining the user's overall dimension portrait according to the user to be queried, and pushing a second telephone contact prompt according to the user's overall dimension portrait. The use of this method can improve the delivery efficiency.

Description

Technical Field

[0001] The present application relates to the field of logistics technology, and in particular to a delivery method, apparatus, computer equipment and storage medium based on user portraits. Background Art

[0002] With the development of logistics technology, express delivery has emerged. Express delivery refers to the delivery of express parcels to customers by couriers.

[0003] In traditional technology, express delivery includes two delivery methods: direct door-to-door delivery and express locker delivery. Generally speaking, in the delivery process of these two delivery methods, the courier needs to contact the customer by phone before delivery, and then put the courier in the designated area or deliver it to the express locker.

[0004] However, the traditional method has the problem of low delivery efficiency. Summary of the invention

[0005] Based on this, it is necessary to provide a user portrait-based delivery method, device, computer equipment and storage medium that can improve delivery efficiency in response to the above technical problems.

[0006] A delivery method based on user portrait, the method comprising:

[0007] Get the collected waybill data;

[0008] Determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data;

[0009] According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database;

[0010] When a corresponding user branch dimension portrait exists in the preset user branch dimension portrait database, a first telephone contact reminder is pushed according to the user branch dimension portrait;

[0011] When there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, the user's overall dimensional portrait is obtained according to the user to be queried, and a second telephone contact prompt is pushed according to the user's overall dimensional portrait.

[0012] In one embodiment, according to the to-be-queried user and the receiving outlet, before obtaining the corresponding user outlet dimensional portrait by querying a preset user outlet dimensional portrait database, the method further includes:

[0013] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0014] Based on the historical mail delivery volume and branch behavior characteristic data, calculate the complaint behavior indicators of the users to be profiled at each branch;

[0015] Obtain the outlet index weights corresponding to the complaint behavior indicators of each outlet, and obtain the outlet dimension portraits of the users to be profiled at each outlet based on the outlet index weights and the complaint behavior indicators of each outlet;

[0016] Update the branch-dimensional portrait of the user to be profiled in each branch to the preset user branch-dimensional portrait database.

[0017] In one embodiment, the network point indicator weight corresponding to each network point complaint behavior indicator is obtained, and the network point dimension portrait of the user to be profiled at each network point is obtained according to the network point indicator weight and the complaint behavior indicator of each network point, including:

[0018] Obtaining the outlet index weights corresponding to the complaint behavior indicators of each outlet, and performing standardization processing on the complaint behavior indicators of each outlet according to a preset standardization function;

[0019] Based on the weights of branch indicators and the standardized complaint behavior indicators of each branch, the branch-dimensional portrait of the user to be profiled in each branch is obtained.

[0020] In one embodiment, the branch behavior characteristic data includes complaint behavior characteristic data and rejection behavior characteristic data, and the branch complaint behavior indicators include the branch's historical rejection rate, the branch's historical evaluation non-visit rate, the branch's historical delivery unknown rate, and the branch's historical service complaint rate.

[0021] In one embodiment, obtaining the overall dimension portrait of the user according to the user to be queried includes:

[0022] According to the user to be queried, the preset user overall dimensional portrait database is queried to obtain the user's overall dimensional portrait.

[0023] In one embodiment, according to the user to be queried, before querying the preset user overall dimensional portrait database and obtaining the user overall dimensional portrait, the method further includes:

[0024] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0025] The overall historical volume of mail delivery and receipt is obtained based on the historical volume of mail delivery and receipt, and the overall behavior characteristic data is obtained based on the behavior characteristic data of the outlets;

[0026] Calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volume and overall behavioral feature data;

[0027] Obtain the overall indicator weights corresponding to each overall complaint behavior indicator, and obtain the overall dimensional profile of the user to be profiled based on the overall indicator weights and each overall complaint behavior indicator;

[0028] Update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0029] In one embodiment, pushing the first telephone contact reminder according to the user's network dimension portrait includes:

[0030] Based on the user branch dimension portrait, obtain the user branch pre-delivery telephone contact analysis score;

[0031] Compare the user's pre-delivery telephone contact analysis score with the preset telephone contact reminder threshold, and push the first telephone contact reminder based on the comparison result.

[0032] A delivery device based on user portrait, the device comprising:

[0033] The acquisition module is used to obtain the collected waybill data;

[0034] A processing module, used to determine the user to be queried according to the recipient information in the waybill data, and to determine the receiving outlet according to the receiving address information in the waybill data;

[0035] A query module is used to obtain the corresponding user outlet dimension portrait by querying a preset user outlet dimension portrait database according to the user to be queried and the receiving outlet;

[0036] A first push module is used to push a first telephone contact reminder according to the user branch dimensional portrait when a corresponding user branch dimensional portrait exists in a preset user branch dimensional portrait database;

[0037] The second push module is used to obtain the user's overall dimensional portrait based on the user to be queried when there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, and push the second telephone contact prompt based on the user's overall dimensional portrait.

[0038] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Get the collected waybill data;

[0040] Determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data;

[0041] According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database;

[0042] When there is a user branch dimension portrait corresponding to the user to be queried and the receiving branch in the preset user branch dimension portrait database, a first telephone contact prompt is pushed according to the user branch dimension portrait;

[0043] When there is no user branch dimensional portrait corresponding to the user to be queried and the receiving branch in the preset user branch dimensional portrait database, the user's overall dimensional portrait is obtained based on the user to be queried, and a second telephone contact prompt is pushed based on the user's overall dimensional portrait.

[0044] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the following steps:

[0045] Get the collected waybill data;

[0046] Determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data;

[0047] According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database;

[0048] When there is a user branch dimension portrait corresponding to the user to be queried and the receiving branch in the preset user branch dimension portrait database, a first telephone contact prompt is pushed according to the user branch dimension portrait;

[0049] When there is no user branch dimensional portrait corresponding to the user to be queried and the receiving branch in the preset user branch dimensional portrait database, the user's overall dimensional portrait is obtained based on the user to be queried, and a second telephone contact prompt is pushed based on the user's overall dimensional portrait.

[0050] The above-mentioned delivery method, device, computer equipment and storage medium based on user portrait, when delivering, determine the user to be queried and the receiving outlet according to the collected waybill data, query the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet, when the user outlet dimension portrait is queried, push the first telephone contact prompt according to the user outlet dimension portrait, when the user outlet dimension portrait is not queried, obtain the user's overall dimension portrait, and push the second telephone contact prompt according to the user's overall dimension portrait. During the whole process, it is possible to determine whether the user needs to be contacted by phone before delivery according to the user outlet dimension portrait and the user's overall dimension portrait, so that different delivery methods can be adopted in a targeted manner to improve delivery efficiency. At the same time, it is also possible to provide customers with better services, improve customer experience, and reduce customer complaints. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1This is an application environment diagram of a delivery method based on user portrait in one embodiment;

[0052] Figure 2 It is a flowchart of a delivery method based on user portrait in one embodiment;

[0053] Figure 3 This is an application scenario diagram of a delivery method based on user portrait in one embodiment;

[0054] Figure 4 is a structural block diagram of a delivery device based on user portrait in one embodiment;

[0055] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] The user portrait-based delivery method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The server 104 obtains the collected waybill data, determines the user to be queried according to the recipient information in the waybill data, and determines the receiving outlet according to the receiving address information in the waybill data. According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database. When the corresponding user outlet dimension portrait exists in the preset user outlet dimension portrait database, the first telephone contact prompt is pushed to the terminal 102 according to the user outlet dimension portrait. When the corresponding user outlet dimension portrait does not exist in the preset user outlet dimension portrait database, the user overall dimension portrait is obtained according to the user to be queried, and the second telephone contact prompt is pushed to the terminal 102 according to the user overall dimension portrait. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0058] In one embodiment, Figure 2 As shown in FIG. 1 , a delivery method based on user portrait is provided, and the method is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0059] Step 202, obtaining the collected waybill data.

[0060] Among them, the collected waybill data refers to the data of the waybill that has been collected by the courier and is waiting to be delivered.

[0061] Specifically, when the courier confirms the collection of the waybill through his own terminal, the server will obtain the collected waybill data, and the collected waybill data corresponds to the courier.

[0062] Step 204, determine the user to be queried according to the recipient information in the waybill data, and determine the receiving outlet according to the receiving address information in the waybill data.

[0063] The user to be queried refers to the recipient of the waybill. The receiving point refers to the destination point to be delivered.

[0064] Specifically, the server will identify the recipient ID from the recipient information in the waybill data, determine the user to be queried based on the recipient ID, and query the preset address-outlet correspondence information based on the recipient address information in the waybill data to determine the recipient outlet. Among them, the recipient ID can specifically be the recipient's name, recipient's phone number, etc. The user to be queried can be uniquely determined by the identified recipient's name and recipient's phone number. The preset address-outlet correspondence information refers to the correspondence between the address and the outlet, that is, which outlet each address belongs to.

[0065] Step 206, according to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database.

[0066] Among them, the preset user outlet dimension portrait database refers to a database that stores the user outlet dimension portraits of users at various outlets. Furthermore, the user outlet dimension portrait will only exist in the user outlet dimension portrait database when the user meets the preset conditions of the outlet dimension portrait. The preset conditions of the outlet dimension portrait can specifically be that the user has made complaints in two or more outlets. The user outlet dimension portrait refers to the portrait of the user at the destination outlet, which is used to indicate whether the user needs to make a telephone contact before delivery. For example, the user outlet dimension portrait can specifically refer to the user's pre-delivery telephone contact score at the outlet.

[0067] Specifically, the server will first obtain all user branch dimension portraits corresponding to the receiving branch from the preset user branch dimension portrait database according to the receiving branch, and then query all user branch dimension portraits according to the user to be queried to find out whether there is a user branch dimension portrait corresponding to the user to be queried and the receiving branch.

[0068] Step 208: When there is a user branch dimensional portrait corresponding to the user to be queried and the receiving branch in the preset user branch dimensional portrait database, a first telephone contact prompt is pushed according to the user branch dimensional portrait.

[0069] The first telephone contact prompt refers to a prompt to the courier whether to make a telephone contact before delivery. For example, the first telephone contact prompt may specifically be that a telephone contact is required. For another example, the first telephone contact prompt may specifically be that a telephone contact is not required.

[0070] Specifically, when there is a corresponding user outlet dimension portrait in the preset user outlet dimension portrait database, the server will obtain the user outlet pre-delivery telephone contact analysis score based on the user outlet dimension portrait, obtain the first telephone contact prompt based on the user outlet pre-delivery telephone contact analysis score, and push the first telephone contact prompt to the courier's terminal to let the courier know whether it is necessary to contact the user by phone before delivery.

[0071] Step 210, when there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, the user overall dimensional portrait is obtained according to the user to be queried, and a second telephone contact prompt is pushed according to the user overall dimensional portrait.

[0072] Among them, the overall dimension portrait of the user is used to characterize the user's portrait in each outlet as a whole. When the user does not have a user outlet dimension portrait corresponding to the receiving outlet, the overall dimension portrait of the user can be used to determine whether the user needs to make a phone call before delivery. For example, the overall dimension portrait of the user may specifically refer to the user's pre-delivery phone contact score, which is independent of the outlet and can be applied to each outlet. The second phone contact prompt refers to a prompt to the courier whether to make a phone call before delivery. For example, the second phone contact prompt may specifically be that a phone call is required. For another example, the second phone contact prompt may specifically be that a phone call is not required.

[0073] Specifically, when there is no corresponding user outlet dimension portrait in the preset user outlet dimension portrait database, the server will query the preset user overall dimension portrait database according to the user to be queried, obtain the user's overall dimension portrait, obtain the user's overall pre-delivery phone contact analysis score according to the user's overall dimension portrait, compare the user's overall pre-delivery phone contact analysis score with the preset phone contact prompt threshold, obtain the second phone contact prompt according to the comparison result, and push the second phone contact prompt to the courier's terminal to let the courier know whether it is necessary to contact the user by phone before delivery. Furthermore, when the user's overall pre-delivery phone contact analysis score is greater than or equal to the preset phone contact prompt threshold, the second phone contact prompt can be obtained as requiring phone contact. When the user's overall pre-delivery phone contact analysis score is less than the preset phone contact prompt threshold, the second phone contact prompt can be obtained as not requiring phone contact.

[0074] The above-mentioned delivery method based on user portrait, when delivering, determines the user to be queried and the receiving outlet according to the collected waybill data, queries the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet, and when the user outlet dimension portrait is queried, pushes the first telephone contact prompt according to the user outlet dimension portrait, when the user outlet dimension portrait is not queried, obtains the user's overall dimension portrait, and pushes the second telephone contact prompt according to the user's overall dimension portrait. During the whole process, it is possible to determine whether the user needs to be contacted by phone before delivery according to the user outlet dimension portrait and the user's overall dimension portrait, so that different delivery methods can be adopted in a targeted manner to improve delivery efficiency. At the same time, it can also provide customers with better services, improve customer experience, and reduce customer complaints.

[0075] In one embodiment, according to the to-be-queried user and the receiving outlet, before obtaining the corresponding user outlet dimensional portrait by querying a preset user outlet dimensional portrait database, the method further includes:

[0076] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0077] Based on the historical mail delivery volume and branch behavior characteristic data, calculate the complaint behavior indicators of the users to be profiled at each branch;

[0078] Obtain the outlet index weights corresponding to the complaint behavior indicators of each outlet, and obtain the outlet dimension portraits of the users to be profiled at each outlet based on the outlet index weights and the complaint behavior indicators of each outlet;

[0079] Update the branch-dimensional portrait of the user to be profiled in each branch to the preset user branch-dimensional portrait database.

[0080] Among them, the user to be profiled refers to the user who needs to be profiled. For example, the user to be profiled can specifically refer to all recipients who need to be profiled. The outlet behavior characteristic data is used to represent the behavioral characteristics of the recipient at the outlet. For example, the outlet behavior characteristic data can specifically refer to the complaint behavior characteristic data. For another example, the outlet behavior characteristic data can specifically refer to the rejection behavior characteristic data. The outlet complaint behavior index is used to represent the user's complaint situation at the outlet. For example, the outlet complaint behavior index can specifically be the outlet's historical rejection rate. For another example, the outlet complaint behavior index can specifically be the outlet's historical evaluation of the unattended rate. For another example, the outlet complaint behavior index can specifically be the outlet's historical delivery unknown rate. For another example, the outlet complaint behavior index can specifically be the outlet's historical service complaint rate. For another example, the outlet complaint behavior index can specifically be any combination of the outlet's historical rejection rate, the outlet's historical evaluation of the unattended rate, the outlet's historical delivery unknown rate, and the outlet's historical service complaint rate. The outlet index weight is used to represent the importance of each outlet complaint behavior index. For example, the outlet index weight may specifically be a percentage used to characterize the complaint behavior index of each outlet.

[0081] Specifically, the server will first obtain the historical mailing and receiving volumes and outlet behavior characteristic data of the user to be profiled at each outlet, and then calculate the complaint behavior indicators of the user to be profiled at each outlet based on the historical mailing and receiving volumes and outlet behavior characteristic data, and then obtain the outlet indicator weights corresponding to the complaint behavior indicators of each outlet, and calculate the outlet dimension portrait of the user to be profiled at each outlet based on the outlet indicator weights and the complaint behavior indicators of each outlet, and finally update the outlet dimension portrait of the user to be profiled at each outlet to the preset user outlet dimension portrait database.

[0082] In this embodiment, the complaint behavior index of the user to be profiled at each outlet is calculated based on the historical mailing and receiving volume and the outlet behavior characteristic data, and the outlet indicator weights corresponding to the complaint behavior index of each outlet are obtained. Based on the outlet indicator weights and the complaint behavior index of each outlet, the outlet-dimensional portrait of the user to be profiled at each outlet is obtained, thereby realizing the acquisition of the outlet-dimensional portrait of the user to be profiled at each outlet.

[0083] In one embodiment, the network point indicator weight corresponding to each network point complaint behavior indicator is obtained, and the network point dimension portrait of the user to be profiled at each network point is obtained according to the network point indicator weight and the complaint behavior indicator of each network point, including:

[0084] Obtaining the outlet index weights corresponding to the complaint behavior indicators of each outlet, and performing standardization processing on the complaint behavior indicators of each outlet according to a preset standardization function;

[0085] Based on the weights of branch indicators and the standardized complaint behavior indicators of each branch, the branch-dimensional portrait of the user to be profiled in each branch is obtained.

[0086] Among them, since the data distribution of the complaint behavior indicators of each outlet is quite different and cannot be directly compared, the complaint behavior indicators of each outlet must be standardized. Through standardization, the complaint behavior indicators of each outlet can be mapped to the same data distribution level.

[0087] Specifically, the server will obtain the outlet index weights corresponding to the complaint behavior indicators of each outlet, and standardize the complaint behavior indicators of each outlet according to the preset standardization function, and calculate the outlet dimension portrait of the user to be profiled at each outlet according to the outlet index weights and the standardized complaint behavior indicators of each outlet. Among them, the preset standardization function can be set as needed.

[0088] For example, the preset normalization function may be a modified Sigmoid normalization function, and the formula is: Among them, median is the median function, x i represents the complaint behavior index of user i, x [xi>0] It represents the complaint behavior index of all users who have made complaints in the network, that is, x [xi>0] =[x 1 ,...,x i ,...x n ], where x i >0, 10 means standardizing the scores to the range of 0-10. The RSigmoid normalization function obtains the relative position of the data in the entire data distribution by using the median of the data, and performs Sigmoid normalization mapping to 0-1 based on the relative position, with 50% of the data less than or equal to 0.5, and 50% of the data greater than 0.5. This can eliminate the displacement deviation between different data distributions, so that different distributions of complaint behavior indicators of outlets are mapped to the same level and can be directly compared. Multiplying by 10 here is to map the scores of the corresponding indicators to 0-10, and to amplify the differences between the data, thereby better differentiating the data. Furthermore, the standardized mapping multiple (i.e. 10 in this solution) can also be adjusted accordingly according to actual business needs, and can be any value set on demand.

[0089] In this embodiment, by obtaining the outlet indicator weights corresponding to the complaint behavior indicators of each outlet, and standardizing the complaint behavior indicators of each outlet according to a preset standardization function, the outlet dimension portraits of the users to be profiled at each outlet are obtained according to the outlet indicator weights and the standardized complaint behavior indicators of each outlet, thereby achieving the acquisition of the outlet dimension portraits of the users to be profiled at each outlet.

[0090] In one embodiment, the branch behavior characteristic data includes complaint behavior characteristic data and rejection behavior characteristic data, and the branch complaint behavior indicators include the branch's historical rejection rate, the branch's historical evaluation non-visit rate, the branch's historical delivery unknown rate, and the branch's historical service complaint rate.

[0091] Among them, the complaint behavior characteristic data includes the historical unknown delivery volume, the historical service complaint volume, the historical CX evaluation of no door-to-door volume, etc. The historical service complaint categories specifically include: physical conflicts, inappropriate language, poor quality image, no door-to-door, no collection, unreasonable demands, falsified records and other complaints. The historical unknown delivery volume and the historical service complaint volume can be obtained directly from the customer service end. When a user has a complaint behavior, the customer service end will record and process it. The customer service end can specifically refer to the terminal used by the customer service staff. The historical CX evaluation of no door-to-door volume comes from the CX end. The rejection behavior characteristic data can specifically refer to the historical rejection volume. Furthermore, the complaint behavior characteristic data and the rejection behavior characteristic data can both refer to the data within the preset historical dimension, that is, in this embodiment, the historical data within a certain period of time can be analyzed through the preset historical dimension. For example, the preset historical dimension can be specifically six months, that is, the historical data within six months is analyzed.

[0092] Among them, the historical rejection rate of the outlet refers to the ratio of the number of historical rejections of users at the outlet to the historical number of received parcels. The historical evaluation non-visit rate of the outlet refers to the ratio of the number of historical CX evaluation non-visit of users at the outlet to the historical number of sent and received parcels. The historical delivery unknown meeting rate of the outlet refers to the ratio of the number of historical delivery unknown meetings of users at the outlet to the historical number of sent and received parcels. The historical service complaint rate of the outlet refers to the ratio of the number of historical service complaint types of users at the outlet to the historical number of sent and received parcels.

[0093] In one embodiment, obtaining the overall dimension portrait of the user according to the user to be queried includes:

[0094] According to the user to be queried, the preset user overall dimensional portrait database is queried to obtain the user's overall dimensional portrait.

[0095] Specifically, the preset user overall dimensional portrait database refers to a database storing user overall dimensional portraits. The server queries the preset user overall dimensional portrait database according to the user to be queried, and can obtain the user overall dimensional portrait. Among them, different from the preset user outlet dimensional portrait database, each user has a corresponding user overall dimensional portrait in the preset user overall dimensional portrait database.

[0096] In this embodiment, the overall dimensional portrait of the user is obtained by querying a preset overall dimensional portrait database according to the user to be queried, thereby obtaining the overall dimensional portrait of the user.

[0097] In one embodiment, according to the user to be queried, before querying the preset user overall dimensional portrait database and obtaining the user overall dimensional portrait, the method further includes:

[0098] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0099] The overall historical volume of mail delivery and receipt is obtained based on the historical volume of mail delivery and receipt, and the overall behavior characteristic data is obtained based on the behavior characteristic data of the outlets;

[0100] Calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volume and overall behavioral feature data;

[0101] Obtain the overall indicator weights corresponding to each overall complaint behavior indicator, and obtain the overall dimensional profile of the user to be profiled based on the overall indicator weights and each overall complaint behavior indicator;

[0102] Update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0103] Among them, the overall historical mailing and receiving volume is the statistical value of the historical mailing and receiving volume, which can be obtained by counting the historical mailing and receiving volume. The overall behavior characteristic data refers to the statistical value of the outlet behavior characteristic data, which is used to express the overall behavioral characteristics of the recipient in receiving mail, and can be obtained by counting the same type of outlet behavior characteristic data separately. For example, the overall behavior characteristic data can specifically include the overall complaint behavior characteristic data and the overall rejection behavior characteristic data, and the overall complaint behavior characteristic data includes the overall historical delivery unknown volume, the overall historical service complaint type volume, the overall historical CX evaluation non-visit volume, etc. The overall rejection behavior characteristic data can specifically refer to the overall historical rejection volume. The overall complaint behavior index is used to characterize the overall user's complaints in the process of receiving mail. For example, the overall complaint behavior index can specifically be the outlet historical rejection rate. For another example, the overall complaint behavior index can specifically be the outlet historical evaluation non-visit rate. For another example, the overall complaint behavior index can specifically be the outlet historical delivery unknown rate. For another example, the overall complaint behavior index can specifically be the outlet historical service complaint type rate. For another example, the overall complaint behavior indicator can be any combination of the overall historical rejection rate, the overall historical evaluation failure rate, the overall historical delivery unknown rate, and the overall historical service complaint rate. The overall indicator weight is used to represent the importance of each overall complaint behavior indicator. For example, the overall indicator weight can be a percentage used to represent each overall complaint behavior indicator.

[0104] Specifically, the server will first obtain the historical mailing and receiving volumes and the outlet behavior characteristic data of the user to be profiled at each outlet, obtain the overall historical mailing and receiving volumes by counting the historical mailing and receiving volumes, and obtain the overall behavior characteristic data by counting the outlet behavior characteristic data, and then calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volumes and the overall behavior characteristic data, obtain the overall index weights corresponding to each overall complaint behavior index, and finally calculate the overall dimensional portrait of the user to be profiled based on the overall index weights and each overall complaint behavior index, and update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0105] Specifically, when calculating the overall complaint behavior index of the user to be profiled based on the overall historical volume of mail sent and received and the overall behavioral characteristic data, the overall historical rejection rate can be obtained by calculating the ratio of the overall historical volume of rejected mails to the overall historical volume of mail received. The overall historical evaluation failure to meet rate can be obtained by calculating the ratio of the overall historical CX evaluation failure to meet rate to the overall historical volume of mail sent and received. The overall historical delivery unknown rate can be obtained by calculating the ratio of the overall historical delivery unknown rate to the overall historical volume of mail sent and received. The overall historical service complaint rate can be obtained by calculating the ratio of the overall historical service complaint rate to the historical volume of mail sent and received.

[0106] Specifically, according to the overall indicator weight and each overall complaint behavior indicator, the overall dimension portrait of the user to be profiled is calculated, including: standardizing each overall complaint behavior indicator, and calculating the overall dimension portrait of the user to be profiled according to each overall complaint behavior indicator and the overall indicator weight after standardization. Among them, the method of standardizing each overall complaint behavior indicator can be the same as the method of standardizing each outlet complaint behavior indicator, and both are standardized by using the Sigmoid standardization function. For example, the standardized overall complaint behavior indicators can be represented by rejection score, CX evaluation door-to-door score, delivery unknown score, and service complaint score, respectively, where the rejection score is the standardized value of the overall historical rejection rate, the CX evaluation door-to-door score is the standardized value of the overall historical evaluation door-to-door rate, the delivery unknown score is the standardized value of the overall historical delivery unknown rate, and the service complaint score is the standardized value of the overall historical service complaint rate. The overall dimension portrait can be specifically, overall dimension portrait = A*rejection score + B*CX evaluation door-to-door score + C*delivery unknown score + D*service complaint score. A, B, C, and D are the overall indicator weights, which can be adjusted according to actual business needs. For example, since there are more rejected customers and fewer customers with other complaints, and the probability of rejection is greater than the probability of other complaints, in order to weigh different complaint behavior indicators and amplify the impact of other complaints, we set a lower weight for the rejection score. The calculation method of the branch dimension portrait is the same as the overall dimension portrait.

[0107] In this embodiment, the overall historical mailing and receiving volumes are obtained based on the historical mailing and receiving volumes, and the overall behavior characteristic data are obtained based on the branch behavior characteristic data. The overall complaint behavior index of the user to be profiled is calculated based on the overall historical mailing and receiving volumes and the overall behavior characteristic data, and the overall index weights corresponding to each overall complaint behavior index are obtained. Based on the overall index weights and each overall complaint behavior index, the overall dimensional portrait of the user to be profiled is obtained, thereby realizing the acquisition of the overall dimensional portrait.

[0108] In one embodiment, pushing the first telephone contact reminder according to the user's network dimension portrait includes:

[0109] Based on the user branch dimension portrait, obtain the user branch pre-delivery telephone contact analysis score;

[0110] Compare the user's pre-delivery telephone contact analysis score with the preset telephone contact reminder threshold, and push the first telephone contact reminder based on the comparison result.

[0111] The pre-delivery telephone contact analysis score of the user outlet is used to characterize the degree to which the user needs telephone contact. The preset telephone contact reminder threshold can be set as needed.

[0112] Specifically, the server will obtain the user outlet pre-delivery telephone contact analysis score based on the user outlet dimension portrait, which includes user information and the user outlet pre-delivery telephone contact analysis score. By comparing the user outlet pre-delivery telephone contact analysis score and the preset telephone contact prompt threshold, the server can obtain the first telephone contact prompt based on the comparison result. After obtaining the first telephone contact prompt, the server will push the first telephone contact prompt to the courier's terminal to let the courier know whether it is necessary to contact the user by phone before delivery. Further, when the user outlet pre-delivery telephone contact analysis score is greater than or equal to the preset telephone contact prompt threshold, the first telephone contact prompt can be obtained as telephone contact is required. When the user outlet pre-delivery telephone contact analysis score is less than the preset telephone contact prompt threshold, the first telephone contact prompt can be obtained as no telephone contact is required.

[0113] In this embodiment, by obtaining the user branch pre-delivery telephone contact analysis score based on the user branch dimensional portrait, comparing the user branch pre-delivery telephone contact analysis score with the preset telephone contact prompt threshold, and pushing the first telephone contact prompt based on the comparison result, the push of the first telephone contact prompt can be realized.

[0114] like Figure 3 As shown, the present application also provides an application scenario, and the application scenario applies the above-mentioned user portrait-based delivery method. Specifically, the application of the user portrait-based delivery method in the application scenario is as follows:

[0115] Before real-time calculation, the service will use feature selection to build customer portraits, obtain the historical mailing and receiving volumes and outlet behavior characteristic data of the user to be profiled at each outlet, calculate the complaint behavior indicators of the user to be profiled at each outlet based on the historical mailing and receiving volumes and outlet behavior characteristic data, obtain the outlet indicator weights corresponding to the complaint behavior indicators of each outlet, and standardize the complaint behavior indicators of each outlet according to the preset standardization function, obtain the outlet dimension portraits of the user to be profiled at each outlet based on the outlet indicator weights and the standardized complaint behavior indicators of each outlet, update the outlet dimension portraits of the user to be profiled at each outlet to the preset user outlet dimension portrait database, and obtain the overall historical mailing and receiving volumes based on the historical mailing and receiving volumes, obtain the overall behavior characteristic data based on the outlet behavior characteristic data, calculate the overall complaint behavior indicators of the user to be profiled based on the overall historical mailing and receiving volumes and the overall behavior characteristic data, obtain the overall indicator weights corresponding to each overall complaint behavior indicator, obtain the overall dimension portrait of the user to be profiled based on the overall indicator weights and each overall complaint behavior indicator, and update the overall dimension portrait to the preset user overall dimension portrait database. Among them, the branch behavior characteristic data include complaint behavior characteristic data and rejection behavior characteristic data. The complaint behavior characteristic data include the number of unknown deliveries, the number of service complaints and the number of CX evaluation home visits. The rejection behavior characteristic data include the historical number of rejections. The branch complaint behavior indicators include the branch’s historical rejection rate, the branch’s historical evaluation home visit rate, the branch’s historical unknown delivery rate and the branch’s historical service complaint rate.

[0116] During real-time calculation, the server will obtain the collected waybill data, determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data. According to the user to be queried and the receiving outlet, the server will query the preset user outlet dimension portrait database to obtain the corresponding user outlet dimension portrait. When the corresponding user outlet dimension portrait exists in the preset user outlet dimension portrait database, the server will obtain the user outlet pre-delivery telephone contact analysis score based on the user outlet dimension portrait, compare the user outlet pre-delivery telephone contact analysis score with the preset telephone contact prompt threshold, and push the first telephone contact prompt based on the comparison result. (that is, when there is a return, the waybill number, phone number and score are pushed into Kafka to the downstream app end, and the app end prompts to call the waybill before dispatching). When the corresponding user branch dimension portrait does not exist in the preset user branch dimension portrait database, the preset user overall dimension portrait database is queried according to the user to be queried, and the user's overall dimension portrait is obtained. The second telephone contact prompt is pushed according to the user's overall dimension portrait (that is, when there is no return, the object's overall pre-dispatch telephone connection score interface is retrieved according to the phone. When there is a return, the waybill number, phone number and score are pushed into Kafka to the downstream app end, and the app end prompts to call the waybill before dispatching. No processing is performed when there is no return).

[0117] Furthermore, the server will also evaluate the user portrait-based delivery method of this application through the execution rate of the deliveryman dimension and the complaint rate of the customer dimension. Among them, the execution rate refers to the analysis of the deliveryman's acceptance and use of the pre-dispatch call reminder function from the deliveryman's perspective. The execution rate is the ratio of the number of waybills for which the app shows the deliveryman to execute the pre-dispatch call reminder to the number of waybills for which the app shows the pre-dispatch call reminder. The purpose of the pre-dispatch call function is to make pre-dispatch calls to customers who often complain about not visiting the customer's home, not being notified of the delivery, etc., in order to reduce the customer complaint rate. Therefore, the customer complaint rate effectively measures the overall effect of the pre-dispatch call function, and the complaint rate is the ratio of the number of complaint orders to the total number of delivery waybills. The comparison of the effect analysis before and after the implementation of the pre-dispatch call is shown in Table 1:

[0118] Table 1

[0119]

[0120] Among them, the execution rate before the pre-dispatch call function is the app-side full-network call rate (pre-dispatch call-connection transport orders / total delivery orders). From the results in Table 1, it can be seen that the pre-dispatch call function reminder can effectively improve the customer call rate, provide high-quality services to customers, and effectively reduce the complaint rate.

[0121] It should be understood that although Figure 2The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0122] In one embodiment, Figure 4 As shown, a delivery device based on user portrait is provided, including: an acquisition module 402, a processing module 404, a query module 406, a first push module 408, and a second push module 410, wherein:

[0123] The acquisition module 402 is used to acquire the collected waybill data;

[0124] Processing module 404, used to determine the user to be queried according to the recipient information in the waybill data, and determine the receiving outlet according to the receiving address information in the waybill data;

[0125] The query module 406 is used to obtain the corresponding user outlet dimension portrait by querying the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet;

[0126] The first push module 408 is used to push a first telephone contact reminder according to the user branch dimensional portrait when there is a corresponding user branch dimensional portrait in the preset user branch dimensional portrait database;

[0127] The second push module 410 is used to obtain the user's overall dimensional portrait according to the user to be queried when there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, and push the second telephone contact prompt according to the user's overall dimensional portrait.

[0128] The above-mentioned delivery device based on user portrait determines the user to be queried and the receiving outlet according to the collected waybill data when delivering, and queries the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet. When the user outlet dimension portrait is queried, the first telephone contact prompt is pushed according to the user outlet dimension portrait. When the user outlet dimension portrait is not queried, the overall dimension portrait of the user is obtained, and the second telephone contact prompt is pushed according to the overall dimension portrait of the user. During the whole process, it is possible to determine whether the user needs to be contacted by phone before delivery according to the user outlet dimension portrait and the overall dimension portrait of the user, so that different delivery methods can be adopted in a targeted manner to improve delivery efficiency. At the same time, it can also provide customers with better services, improve customer experience, and reduce customer complaints.

[0129] In one embodiment, the delivery device based on user portrait also includes an outlet dimension portrait construction module, which is used to obtain the historical mailing and receiving volume and outlet behavior characteristic data of the user to be profiled at each outlet, calculate the complaint behavior index of each outlet of the user to be profiled at each outlet based on the historical mailing and receiving volume and outlet behavior characteristic data, obtain the outlet indicator weight corresponding to the complaint behavior index of each outlet, obtain the outlet dimension portrait of the user to be profiled at each outlet based on the outlet indicator weight and the complaint behavior index of each outlet, and update the outlet dimension portrait of the user to be profiled at each outlet to the preset user outlet dimension portrait database.

[0130] In one embodiment, the branch dimension portrait construction module is also used to obtain the branch indicator weights corresponding to the complaint behavior indicators of each branch, and standardize the complaint behavior indicators of each branch according to a preset standardization function, and obtain the branch dimension portrait of the user to be profiled at each branch according to the branch indicator weights and the standardized complaint behavior indicators of each branch.

[0131] In one embodiment, the branch behavior characteristic data includes complaint behavior characteristic data and rejection behavior characteristic data, and the branch complaint behavior indicators include the branch's historical rejection rate, the branch's historical evaluation non-visit rate, the branch's historical delivery unknown rate, and the branch's historical service complaint rate.

[0132] In one embodiment, the second push module is further used to query a preset user overall dimensional portrait database according to the user to be queried, so as to obtain the user's overall dimensional portrait.

[0133] In one embodiment, the delivery device based on user portrait also includes an overall dimensional portrait construction module, which is used to obtain the historical mail delivery volume and outlet behavior characteristic data of the user to be profiled at each outlet, obtain the overall historical mail delivery volume based on the historical mail delivery volume, and obtain the overall behavior characteristic data based on the outlet behavior characteristic data, calculate the overall complaint behavior index of the user to be profiled based on the overall historical mail delivery volume and the overall behavior characteristic data, obtain the overall index weight corresponding to each overall complaint behavior index, obtain the overall dimensional portrait of the user to be profiled based on the overall index weight and each overall complaint behavior index, and update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0134] In one embodiment, the first push module is also used to obtain the user branch pre-delivery telephone contact analysis score based on the user branch dimensional portrait, compare the user branch pre-delivery telephone contact analysis score with the preset telephone contact prompt threshold, and push the first telephone contact prompt based on the comparison result.

[0135] For the specific definition of the user portrait-based delivery device, please refer to the definition of the user portrait-based delivery method above, which will not be repeated here. Each module in the above-mentioned user portrait-based delivery device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0136] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store historical mail volume data and network point behavior feature data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a delivery method based on user portraits is implemented.

[0137] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0138] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0139] Get the collected waybill data;

[0140] Determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data;

[0141] According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database;

[0142] When a corresponding user branch dimension portrait exists in the preset user branch dimension portrait database, a first telephone contact reminder is pushed according to the user branch dimension portrait;

[0143] When there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, the user's overall dimensional portrait is obtained according to the user to be queried, and a second telephone contact prompt is pushed according to the user's overall dimensional portrait.

[0144] The above-mentioned delivery computer equipment based on user portrait, when making delivery, determines the user to be queried and the receiving outlet according to the collected waybill data, queries the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet, and when the user outlet dimension portrait is queried, pushes the first telephone contact prompt according to the user outlet dimension portrait, when the user outlet dimension portrait is not queried, obtains the user's overall dimension portrait, and pushes the second telephone contact prompt according to the user's overall dimension portrait. During the whole process, it is possible to determine whether the user needs to be contacted by phone before delivery according to the user outlet dimension portrait and the user's overall dimension portrait, so that different delivery methods can be adopted in a targeted manner to improve delivery efficiency. At the same time, it can also provide customers with better services, improve customer experience, and reduce customer complaints.

[0145] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0146] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0147] Based on the historical mail delivery volume and branch behavior characteristic data, calculate the complaint behavior indicators of the users to be profiled at each branch;

[0148] Obtain the outlet index weights corresponding to the complaint behavior indicators of each outlet, and obtain the outlet dimension portraits of the users to be profiled at each outlet based on the outlet index weights and the complaint behavior indicators of each outlet;

[0149] Update the branch-dimensional portrait of the user to be profiled in each branch to the preset user branch-dimensional portrait database.

[0150] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0151] Obtaining the outlet index weights corresponding to the complaint behavior indicators of each outlet, and performing standardization processing on the complaint behavior indicators of each outlet according to a preset standardization function;

[0152] Based on the weights of branch indicators and the standardized complaint behavior indicators of each branch, the branch-dimensional portrait of the user to be profiled in each branch is obtained.

[0153] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0154] According to the user to be queried, the preset user overall dimensional portrait database is queried to obtain the user's overall dimensional portrait.

[0155] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0156] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0157] The overall historical volume of mail delivery and receipt is obtained based on the historical volume of mail delivery and receipt, and the overall behavior characteristic data is obtained based on the behavior characteristic data of the outlets;

[0158] Calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volume and overall behavioral feature data;

[0159] Obtain the overall indicator weights corresponding to each overall complaint behavior indicator, and obtain the overall dimensional profile of the user to be profiled based on the overall indicator weights and each overall complaint behavior indicator;

[0160] Update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0161] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0162] Based on the user branch dimension portrait, obtain the user branch pre-delivery telephone contact analysis score;

[0163] Compare the user's pre-delivery telephone contact analysis score with the preset telephone contact reminder threshold, and push the first telephone contact reminder based on the comparison result.

[0164] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0165] Get the collected waybill data;

[0166] Determine the user to be queried based on the recipient information in the waybill data, and determine the receiving outlet based on the receiving address information in the waybill data;

[0167] According to the user to be queried and the receiving outlet, the corresponding user outlet dimension portrait is obtained by querying the preset user outlet dimension portrait database;

[0168] When a corresponding user branch dimension portrait exists in the preset user branch dimension portrait database, a first telephone contact reminder is pushed according to the user branch dimension portrait;

[0169] When there is no corresponding user branch dimensional portrait in the preset user branch dimensional portrait database, the user's overall dimensional portrait is obtained according to the user to be queried, and a second telephone contact prompt is pushed according to the user's overall dimensional portrait.

[0170] The above-mentioned delivery storage medium based on user portrait determines the user to be queried and the receiving outlet according to the collected waybill data during delivery, and queries the preset user outlet dimension portrait database according to the user to be queried and the receiving outlet. When the user outlet dimension portrait is queried, a first telephone contact prompt is pushed according to the user outlet dimension portrait. When the user outlet dimension portrait is not queried, the overall dimension portrait of the user is obtained, and a second telephone contact prompt is pushed according to the overall dimension portrait of the user. During the whole process, it is possible to determine whether the user needs to be contacted by phone before delivery according to the user outlet dimension portrait and the overall dimension portrait of the user, so that different delivery methods can be adopted in a targeted manner to improve delivery efficiency. At the same time, it can also provide customers with better services, improve customer experience, and reduce customer complaints.

[0171] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0172] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0173] Based on the historical mail delivery volume and branch behavior characteristic data, calculate the complaint behavior indicators of the users to be profiled at each branch;

[0174] Obtain the outlet index weights corresponding to the complaint behavior indicators of each outlet, and obtain the outlet dimension portraits of the users to be profiled at each outlet based on the outlet index weights and the complaint behavior indicators of each outlet;

[0175] Update the branch-dimensional portrait of the user to be profiled in each branch to the preset user branch-dimensional portrait database.

[0176] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0177] Obtaining the outlet index weights corresponding to the complaint behavior indicators of each outlet, and performing standardization processing on the complaint behavior indicators of each outlet according to a preset standardization function;

[0178] Based on the weights of branch indicators and the standardized complaint behavior indicators of each branch, the branch-dimensional portrait of the user to be profiled in each branch is obtained.

[0179] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0180] According to the user to be queried, the preset user overall dimensional portrait database is queried to obtain the user's overall dimensional portrait.

[0181] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0182] Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data;

[0183] The overall historical volume of mail delivery and receipt is obtained based on the historical volume of mail delivery and receipt, and the overall behavior characteristic data is obtained based on the behavior characteristic data of the outlets;

[0184] Calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volume and overall behavioral feature data;

[0185] Obtain the overall indicator weights corresponding to each overall complaint behavior indicator, and obtain the overall dimensional profile of the user to be profiled based on the overall indicator weights and each overall complaint behavior indicator;

[0186] Update the overall dimensional portrait to the preset user overall dimensional portrait database.

[0187] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0188] Based on the user branch dimension portrait, obtain the user branch pre-delivery telephone contact analysis score;

[0189] Compare the user's pre-delivery telephone contact analysis score with the preset telephone contact reminder threshold, and push the first telephone contact reminder based on the comparison result.

[0190] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0191] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0192] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A delivery method based on user portrait, characterized in that: The method comprises: Get the collected waybill data; Determine the user to be queried according to the recipient information in the waybill data, and determine the receiving outlet according to the receiving address information in the waybill data; According to the to-be-queried user and the receiving outlet, a corresponding user outlet dimension portrait is obtained by querying a preset user outlet dimension portrait database; When the corresponding user branch dimensional portrait exists in the preset user branch dimensional portrait database, a first telephone contact prompt is pushed according to the user branch dimensional portrait; When the corresponding user branch dimensional portrait does not exist in the preset user branch dimensional portrait database, obtaining a user overall dimensional portrait according to the user to be queried, and pushing a second telephone contact reminder according to the user overall dimensional portrait; Wherein, before obtaining the corresponding user outlet dimensional portrait by querying a preset user outlet dimensional portrait database according to the to-be-queried user and the receiving outlet, the method further includes: Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data; Calculate the complaint behavior index of each branch of the user to be profiled at each branch according to the historical mailing and receiving volume and the branch behavior characteristic data; Obtaining the outlet index weights corresponding to the outlet complaint behavior indicators, and obtaining the outlet dimension portraits of the users to be profiled at each outlet according to the outlet index weights and the outlet complaint behavior indicators; The branch-dimensional portrait of the user to be profiled at each branch is updated to a preset user branch-dimensional portrait database.

2. The method according to claim 1, characterized in that The acquiring of the network point indicator weights corresponding to the network point complaint behavior indicators, and obtaining the network point dimension portraits of the users to be profiled at each network point according to the network point indicator weights and the network point complaint behavior indicators, comprises: Obtaining the network point indicator weight corresponding to each of the network point complaint behavior indicators, and performing standardization processing on each of the network point complaint behavior indicators according to a preset standardization function; According to the outlet indicator weights and the standardized complaint behavior indicators of each outlet, an outlet dimension portrait of the user to be profiled in each outlet is obtained.

3. The method according to claim 1, characterized in that The branch behavior characteristic data include complaint behavior characteristic data and rejection behavior characteristic data, and the branch complaint behavior indicators include the branch's historical rejection rate, the branch's historical evaluation non-visit rate, the branch's historical delivery unknown rate, and the branch's historical service complaint rate.

4. The method according to claim 1, characterized in that The obtaining of the overall dimension portrait of the user according to the user to be queried includes: According to the user to be queried, a preset user overall dimensional portrait database is queried to obtain the user's overall dimensional portrait.

5. The method according to claim 4, characterized in that Before querying a preset user overall dimensional portrait database according to the user to be queried to obtain the user overall dimensional portrait, the method further includes: Obtain the historical volume of mail sent and received by the user to be profiled at each outlet and the outlet behavior characteristic data; Obtaining the overall historical mailing and receiving volume according to the historical mailing and receiving volume, and obtaining the overall behavior characteristic data according to the network point behavior characteristic data; Calculate the overall complaint behavior index of the user to be profiled based on the overall historical mailing and receiving volume and the overall behavior characteristic data; Obtaining the overall indicator weights corresponding to the overall complaint behavior indicators, and obtaining the overall dimensional portrait of the user to be profiled according to the overall indicator weights and the overall complaint behavior indicators; The overall dimensional portrait is updated to a preset user overall dimensional portrait database.

6. The method according to claim 1, characterized in that The pushing of the first telephone contact prompt according to the user network dimension portrait includes: According to the user outlet dimension portrait, obtain the user outlet pre-delivery telephone contact analysis score; The pre-delivery telephone contact analysis score of the user outlet is compared with a preset telephone contact reminder threshold, and a first telephone contact reminder is pushed according to the comparison result.

7. A delivery device based on user portrait, characterized in that: The device comprises: The acquisition module is used to obtain the collected waybill data; A processing module, used to determine the user to be queried according to the recipient information in the waybill data, and to determine the receiving outlet according to the receiving address information in the waybill data; A query module, configured to obtain a corresponding user outlet dimension portrait by querying a preset user outlet dimension portrait database according to the user to be queried and the receiving outlet; A first push module, configured to push a first telephone contact reminder according to the user branch dimensional portrait when the corresponding user branch dimensional portrait exists in the preset user branch dimensional portrait database; A second push module is used to obtain a user overall dimensional portrait according to the user to be queried when the corresponding user branch dimensional portrait does not exist in the preset user branch dimensional portrait database, and push a second telephone contact reminder according to the user overall dimensional portrait; The branch dimension portrait construction module is used to obtain the historical mailing and receiving volume and branch behavior characteristic data of the user to be profiled at each branch, calculate the complaint behavior index of each branch of the user to be profiled at each branch based on the historical mailing and receiving volume and the branch behavior characteristic data, obtain the branch indicator weight corresponding to each branch complaint behavior index, obtain the branch dimension portrait of the user to be profiled at each branch based on the branch indicator weight and the branch complaint behavior index, and update the branch dimension portrait of the user to be profiled at each branch to the preset user branch dimension portrait database.

8. The device according to claim 7, characterized in that The branch dimension portrait construction module is also used to obtain the branch indicator weights corresponding to the complaint behavior indicators of each branch, and standardize the complaint behavior indicators of each branch according to a preset standardization function, and obtain the branch dimension portrait of the user to be profiled at each branch according to the branch indicator weights and the standardized complaint behavior indicators of each branch.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images