Home maintenance door-to-door service method and system

Abstract

The invention belongs to the field of Internet, and provides a home maintenance door-to-door service method and system, and the method comprises the steps: building a single-target order planning model which aims at maximizing the total weight value of order distribution, the constraint conditions at least comprise order state constraint, starting time constraint, personnel state constraint, distance constraint and arrival time constraint; obtaining basic information of all orders and technicians, circularly traversing all available technicians for each ordered order based on the basic information and a single-target order planning model, calculating weighted scores of the technicians corresponding to the orders, and allocating the technician with the highest weighted score to perform order door-to-door service. The processing is repeated until all orders are distributed, and the highest weighted score selected each time is accumulated to the total weighted value; the invention provides an efficient service scheme which enables orders to be highly matched with technicians.

Description

Technical Field

[0001] The present invention relates to the field of the Internet, and in particular to a home maintenance door-to-door service method and system. Background Art

[0002] With the improvement of living standards, people need more convenience in life. When encountering problems, they also hope to reduce their own costs. Therefore, they hope that the corresponding problem solvers can provide door-to-door services, such as large home appliance repairs, installation of air conditioners, televisions, water heaters, etc. Therefore, door-to-door repair services are gradually becoming popular.

[0003] In order to improve service quality and technicians' work efficiency, it is particularly important to allocate current orders to technicians who are closer and have better reputations. However, for a booming door-to-door service platform, there is currently a problem of order allocation: 1. Due to the high diversity and uncertainty of door-to-door service needs, the complexity of order matching increases; 2. The imbalance in the number and skill level of service personnel often leads to waste of resources or imbalance between supply and demand during the matching process; 3. Order matching has high requirements for timeliness. Traditional manual matching or short-distance allocation often cannot meet the needs of rapid response. Summary of the invention

[0004] In view of the above technical problems, the present invention provides a method and system for home maintenance door-to-door service, so as to provide an efficient service solution that highly matches orders with technicians.

[0005] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0006] According to one aspect of the present invention, a home maintenance door-to-door service method is disclosed, the method comprising: A single-objective order planning model is established, wherein the goal of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician, the start time constraint is to limit the service start time of the order to be within a preset time range and to be an integer multiple of 0.5 hours, the personnel status constraint is to limit the technician to only serve one order at the same time, the distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint, the arrival time constraint is to limit the technician's arrival time to be earlier than the order service start time, and the decision variable of the single-objective order planning model is the number of technicians; The basic information of all orders and technicians is obtained, wherein the basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time. Based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to provide door-to-door service for the order. The weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighted values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

[0007] Furthermore, the constraint condition also includes an order backlog constraint, which stipulates that if the difference between the service start time of an unassigned order and the current time is less than a threshold, the order must be assigned immediately, and if it is greater than the threshold, the order is backlogged.

[0008] Furthermore, when obtaining the basic information of the order, the obtaining method is to obtain it at a fixed time, and after a preset time, the backlog of orders is uniformly allocated based on the weighted score.

[0009] Furthermore, when the orders are accumulated, the number of the accumulated orders is limited to not exceed a preset percentage of the total number of orders.

[0010] Furthermore, when determining the preset percentage, maximizing the total weight value is taken as a goal, and traversing 1-100% is performed to obtain the optimal preset percentage.

[0011] Furthermore, the method also includes: when the total weight value is lower than a preset value, adjusting the weighted values ​​corresponding to the service score, the distance to the positioning location and the duration of the order, or increasing the number of service personnel and improving the service level of the service personnel.

[0012] Furthermore, the constraint condition also includes a moving speed constraint, and the moving speed constraint is to limit the moving speed of the service personnel to no more than 15KM / h.

[0013] Furthermore, the service rating is determined by the following method: Get the first customer ratings of technicians; Obtaining video and audio records of the technician at the scene, and obtaining a second score after analyzing the video and audio records; The first score and the second score are combined to obtain the service score.

[0014] According to another aspect of the present invention, a home maintenance door-to-door service system is disclosed, the system comprising: A model generation module is used to establish a single-objective order planning model, wherein the objective of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician, the start time constraint is to limit the service start time of the order to be within a preset time range and to be an integer multiple of 0.5 hours, the personnel status constraint is to limit the technician to only serve one order at the same time, the distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint, the arrival time constraint is to limit the technician's arrival time to be earlier than the order's service start time, and the decision variable of the single-objective order planning model is the number of technicians; The personnel matching module is used to obtain the basic information of all orders and technicians. The basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time. Based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to provide door-to-door service for the order. The weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighted values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

[0015] The technical solution disclosed in this disclosure has the following beneficial effects: Based on the established single-objective order planning model, efficient and rapid allocation of orders is achieved, and better technicians are assigned to corresponding orders as much as possible. The higher the total weight value calculated by the objective function, the higher the overall service quality for customers, thereby ensuring the service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of a home maintenance door-to-door service method in an embodiment of this specification; Figure 2 is a structural block diagram of a recording system in an embodiment of this specification; Figure 3 This is a structural block diagram of a home maintenance door-to-door service system in an embodiment of this specification. DETAILED DESCRIPTION

[0017] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as being limited to the examples set forth herein; on the contrary, these embodiments are provided so that the present disclosure will be more comprehensive and complete, and the concepts of the example embodiments are fully conveyed to those skilled in the art. The described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known technical solutions are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0018] In addition, the accompanying drawings are only schematic illustrations of the present disclosure. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities, which do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0019] In one embodiment, if Figure 1 As shown, this specification provides a home maintenance door-to-door service method, and the execution subject of the method can be a computer, a server, etc. The method can specifically include the following steps S101~S102: In step S101, a single-objective order planning model is established. The goal of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician. The start time constraint is to limit the service start time of the order to be within a preset time range and to be an integer multiple of 0.5 hours. The personnel status constraint is to limit the technician to only serve one order at the same time. The distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint. The arrival time constraint is to limit the technician's arrival time to be earlier than the order service start time. The decision variable of the single-objective order planning model is the number of technicians.

[0020] Among them, in the single-objective order planning model, the objective function can be expressed as , sum is the total weight value, N is the number of orders, For the technicians are assigned to The weighted score of the order.

[0021] The order status constraint can be expressed as: ; For the The status of an order, O means the order has been matched, 1 means the order is waiting to be matched.

[0022] The start time constraint is expressed as: ; For the The start time of the order, is the earliest start time and is the latest start time , which means that the order must be between the earliest start time and the latest start time, and must be an integer multiple of half an hour.

[0023] The personnel status constraint is expressed as: ; The technician's status, 0 means idle, 1 means processing an order.

[0024] The distance constraint is expressed as: ; d is the Euclidean distance, are the coordinates of the technician, are the coordinates of the th order.

[0025] The arrival time constraint is expressed as: ; Beijing time, is the moving speed of the technician, which is generally set to 15 km / h. That is, the constraint condition also includes a moving speed constraint, which limits the moving speed of the service personnel to no more than 15 km / h. The arrival time of the technician Must be before the order start time.

[0026] In step S102, basic information of all orders and technicians is obtained, wherein the basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time, and based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to provide door-to-door service for the order, wherein the weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighting values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

[0027] After the single-objective order planning model is established, the service orders can be allocated. Specifically, all order data are first arranged in chronological order, and then orders are selected according to the arranged order. The technician with the highest weighted score is searched through a loop, and the technician's location information and service time are stored. The weighted score is added to the Sum until all orders are found. Finally, the Sum value is output and the order is processed. Here, , For the Service scores of technicians, The distance between the order and the technician is calculated by Euclidean distance, that is, the distance from the technician to the location of the order. For the The time interval between orders, i.e. the duration of an order, is determined by the order type. , , is the corresponding weighted value. Different orders have different weighted values. For example, for orders that require timeliness, such as water pipe leakage, circuit failure, gas leakage, emergency door lock failure, etc., the weighted value of distance is For larger orders that require experienced repairmen, such as home appliance repairs, the service rating should be Too big.

[0028] After obtaining the total weight value, the total weight value can be used to measure the quality of the order allocation. The higher the total weight value, the higher the corresponding service quality, service timeliness, etc. If the total weight value is low, such as when the total weight value is lower than the preset value, the order type can be optimized, and the service score, the distance to the location and the weighted value corresponding to the duration of the order can be adjusted, or the number of service personnel can be increased and the service level of the service personnel can be improved.

[0029] In another embodiment, another home maintenance door-to-door service method is provided. In the previous embodiment, the order allocation is a one-time allocation, and the allocation of the orders generated after the order collection is not considered. Therefore, this embodiment provides an order door-to-door method that can be allocated online. Different from the previous embodiment, an order backlog constraint is additionally added to the constraint condition. The order backlog constraint is to limit the unallocated order to be allocated immediately if the difference between the service start time and the current time is less than a threshold, and the order is backlogged if it is greater than the threshold. It is expressed as follows: ; The formula uses 2 hours as the threshold.

[0030] In addition, in the online distribution order delivery method, when the orders are backlogged, the number of backlogged orders is limited to not more than a preset percentage of the total number of orders. When determining the preset percentage, the goal is to maximize the total weight value, and traverse 1-100% to obtain the optimal preset percentage. The percentage is calculated as follows: ; in, The percentage calculated for the traversal.

[0031] In addition, when obtaining the basic information of the order, the acquisition method is to obtain it at a fixed time, and after the preset time, the backlog of orders is uniformly allocated based on the weighted score. That is, in the online allocation method, the orders are first sorted by time, and then a batch of orders are collected at a fixed time, and the newly generated online orders are summarized and processed to accumulate sufficient order information so that technicians with higher service quality can be more effectively selected during allocation. In order to control the number of backlog orders, a preset percentage is set above to limit the number of backlog orders to no more than a certain percentage of the total number of orders. Therefore, orders will only be allocated in the following cases: When the backlog reaches a preset percentage; or when certain orders must be assigned immediately due to urgent need for service.

[0032] Therefore, after collecting the data of an order at a regular interval, the information of the technician for each current order is checked, and the technician with the highest weighted score is selected to take the order to ensure that the customer can receive appropriate service. After the technician takes the order, the technician's location information and service time are updated for future order allocation, and the order is deleted from the list to be allocated. As new orders continue to arrive, the online allocation model will continue to perform the previous collection and backlog steps, and allocate work when conditions are met. The whole process continues until all orders are properly processed.

[0033] In one embodiment, the method further includes: when the total weight value is lower than a preset value, adjusting the weighted values ​​corresponding to the service score, the distance to the location and the duration of the order, or increasing the number of service personnel and improving the service level of the service personnel.

[0034] Specifically, when the total weight value calculated by the model is lower than a preset target value, the service allocation can be optimized by adjusting the weight coefficients and. For example, if it is found that the service score does not contribute enough to the total weight, the weight value can be increased to increase the importance of the service score in the total weight. Adjust service score, distance, and duration: In addition to adjusting the weight coefficient, you can also directly adjust the calculation method or parameters of the service score, distance, and order duration to better reflect the actual situation, making order allocation more reasonable and providing a better customer experience.

[0035] In one embodiment, the service score is determined by the following method: obtaining a first score of the technician from the customer; obtaining a video record and an audio record of the technician on site, and obtaining a second score after analyzing the video record and the audio record; and combining the first score and the second score to obtain the service score.

[0036] The first rating can be a rating provided by customers who have been served by technicians on the APP or website, which is a subjective rating by customers, while the second rating is an objective frequency rating after analyzing video and audio records. Different ratings have different weights. A reasonable service rating can be obtained by combining the two ratings.

[0037] The second score is obtained through a recording system, such as Figure 2As shown, the system includes: a camera module 101, a microphone module 102, a control module 103, a positioning module 104, a wireless module 105, a storage module 107, an edge video recognition module 108 and a voice recognition module 109, wherein the positioning module 104 is used to obtain the current positioning, the wireless module 105 is used to connect to an external server, the control module 103 is used to obtain the video stream from the camera module 101 and the user's audio stream from the microphone module 102, and is used to pre-process the video stream and the audio stream and send them to the edge video recognition module 108 and the voice recognition module 109 respectively, and the storage module 107 is used to locally store the video stream and the audio stream.

[0038] The edge video recognition module 108 is used to: recognize faces in the preprocessed video stream in real time based on a locally built-in pre-trained custom MobileNet network, wherein the custom MobileNet network includes a hybrid deep convolution unit, a full convolution layer, a global average pooling layer, a fully connected layer, and a classification layer composed of an activation function, wherein the hybrid deep convolution unit is composed of two point-by-point convolutions and one deep convolution, and the activation functions of the classification layer include Mish, TanhExp, and ReLU.

[0039] The application scenario of the edge video recognition module 108 is generally for the technician to arrive at the customer's designated work area, the order takes effect, and the technician communicates with the customer face to face. The camera module 101 records the video stream including the customer's face. The edge video recognition module 108 recognizes the face in the video stream and then feeds it back to the control module 103. The control module 103 allows the order to take effect and starts recording the reference data for the second score. The reference data can be the audio or video described below. In addition, the edge video recognition module 108 can also be used to recognize the technician's face, and only after the recognition is passed can the clock in be allowed.

[0040] The speech recognition module 109 is used to: perform speech recognition and emotion classification on mixed audio features in real time based on a pre-trained classification model, and obtain the speech content and emotion record of the audio, wherein the mixed audio features are fused by the extracted MFCC features and the corresponding time domain features in the pre-processed audio, and the MFCC features are obtained by performing frame segmentation, Hamming window processing, discrete Fourier transform, obtaining Mel spectrum and applying discrete cosine transform on the pre-processed audio, and the time domain features are multiple types of the maximum value, minimum value, mean value, median, mode, standard deviation, variance, covariance, root mean square and percentile of a partial area of ​​the matrix composed of the MFCC features.

[0041] Through the above-mentioned recording system, starting from voice recognition, it is possible to monitor whether the user is operating according to standard procedures, such as monitoring whether the user's opening and closing remarks during the service process are read according to the speech template, whether uncivilized language is used, whether the conversation with the employer contains negative emotions, etc. Therefore, a second score can be evaluated.

[0042] The speech recognition module 109 can be run on the mobile device body to perform speech recognition locally, or it can be run in an external server. Since the volume of the audio stream is very small relative to the video stream, the time delay in remote data transmission and analysis is very small, and real-time performance can be achieved. The classification model contained in the speech recognition module 109 needs to be pre-trained, and the classification model can be a type of CNN. When training the classification model, a data set representing different speech templates, a data set representing different emotions, and a data set representing uncivilized language are used. The speech template can be "hello, goodbye, thank you, etc.", and the emotion can be anger, boredom, disgust, fear, happiness, neutrality, and sadness, etc., and then the data set is pre-processed to extract MFCC features and time domain features. After the MFCC features and time domain features are fused, they are trained with the labels of each data set to obtain a classification model. When the classification model performs speech recognition, the MFCC features and time domain features in the pre-processed audio are first extracted, and then the mixed audio features that fuse the MFCC features and time domain features are recognized, and the labels corresponding to the audio are output. These labels exist at the same time, such as speech template 1, happy.

[0043] Through the above-mentioned recording system, after comprehensive audio analysis, a second score is obtained, and then, after assigning different weights to the first score and the second score, the service score can be calculated.

[0044] Based on the same idea, Figure 3 As shown, an exemplary embodiment of the present disclosure also provides a home maintenance door-to-door service system, the system comprising: Model generation module 301, used to establish a single-objective order planning model, the goal of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician, the start time constraint is to limit the service start time of the order to be within a preset time range and an integer multiple of 0.5 hours, the personnel status constraint is to limit the technician to only serve one order at the same time, the distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint, the arrival time constraint is to limit the technician's arrival time to be earlier than the order's service start time, and the decision variable of the single-objective order planning model is the number of technicians; The personnel matching module 302 is used to obtain the basic information of all orders and technicians. The basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time. Based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to perform door-to-door service for the order. The weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighted values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

[0045] In the above-mentioned embodiment, based on the established single-objective order planning model, efficient and fast allocation of orders is achieved, and better technicians are allocated to corresponding orders as much as possible. The higher the total weight value calculated by the objective function, the higher the overall service quality for customers, thereby ensuring the service quality.

[0046] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A home maintenance door-to-door service method, characterized in that: The method comprises: A single-objective order planning model is established, wherein the goal of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician, the start time constraint is to limit the service start time of the order to be within a preset time range and to be an integer multiple of 0.5 hours, the personnel status constraint is to limit the technician to only serve one order at the same time, the distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint, the arrival time constraint is to limit the technician's arrival time to be earlier than the order service start time, and the decision variable of the single-objective order planning model is the number of technicians; The basic information of all orders and technicians is obtained, wherein the basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time. Based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to provide door-to-door service for the order. The weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighted values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

2. A home maintenance door-to-door service method according to claim 1, characterized in that: The constraint conditions also include an order backlog constraint, which stipulates that if the difference between the service start time of an unassigned order and the current time is less than a threshold, the order must be assigned immediately, and if it is greater than the threshold, the order is backlogged.

3. A home maintenance door-to-door service method according to claim 2, characterized in that: When obtaining the basic information of the order, the obtaining method is to obtain it at a fixed time, and after a preset time, the backlog of orders is uniformly allocated based on the weighted score.

4. A home maintenance door-to-door service method according to claim 2, characterized in that: When backlogging orders, the number of backlogged orders is limited to no more than a preset percentage of the total number of orders.

5. A home maintenance door-to-door service method according to claim 4, characterized in that: When determining the preset percentage, the goal is to maximize the total weight value, and traverse 1-100% to obtain the optimal preset percentage.

6. A home maintenance door-to-door service method according to claim 1, characterized in that: The method also includes: when the total weight value is lower than a preset value, adjusting the weighted values ​​corresponding to the service score, the distance to the positioning location and the duration of the order, or increasing the number of service personnel and improving the service level of the service personnel.

7. A home maintenance door-to-door service method according to claim 1, characterized in that: The constraint condition also includes a moving speed constraint, and the moving speed constraint is to limit the moving speed of the service personnel to no more than 15KM / h.

8. A home maintenance door-to-door service method according to claim 1, characterized in that: The service rating is determined by the following method: Get the first customer ratings of technicians; Obtaining video and audio records of the technician at the scene, and obtaining a second score after analyzing the video and audio records; The first score and the second score are combined to obtain the service score.

9. A home maintenance door-to-door service system, characterized in that: The system comprises: A model generation module is used to establish a single-objective order planning model, wherein the objective of the single-objective order planning model is to maximize the total weight value of order allocation, and its constraints include at least order status constraint, start time constraint, personnel status constraint, distance constraint, and arrival time constraint. The order status constraint is to limit each order to be allocated and can only be allocated to one technician, the start time constraint is to limit the service start time of the order to be within a preset time range and to be an integer multiple of 0.5 hours, the personnel status constraint is to limit the technician to only serve one order at the same time, the distance constraint is to calculate the distance between the technician's location and the order location based on the Euclidean distance constraint, the arrival time constraint is to limit the technician's arrival time to be earlier than the order's service start time, and the decision variable of the single-objective order planning model is the number of technicians; The personnel matching module is used to obtain the basic information of all orders and technicians. The basic information of the orders includes the start time and location, and the basic information of the technicians includes the work status, location, and service score. All orders are sorted according to the start time. Based on the basic information and the single-objective order planning model, all available technicians are looped through for each sorted order, and the weighted scores of the technicians corresponding to the orders are calculated. The technician with the highest weighted score is assigned to provide door-to-door service for the order. The weighted score is the sum of the technician's service score, the distance to the location, and the duration of the order multiplied by different weighted values. The process is repeated until all orders are assigned, and the highest weighted score selected each time is added to the total weight value.

Images