Moving order matching method and device and electronic equipment
By building user and service portraits, using multi-dimensional matching algorithms and graph neural networks, the problem of traditional moving order matching relies on manual review is solved, and the precise matching of moving orders and moving staff is achieved, and operational efficiency and user satisfaction are improved.
Patent Information
- Application Number
- CN202411013143.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-26
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional moving order matching relies on manual review, is inefficient and susceptible to human factors, resulting in the inaccurate matching results, unable to fully understand user needs, and unable to assign the most suitable moving staff.
By building user portraits and service portraits, including moving time, starting point, end point, item type and user needs, as well as service time, service area, service type and order evaluation, multi-dimensional matching algorithm and graph neural network are used for automated matching to reduce labor Intervention to improve matching accuracy.
It achieves accurate matching between moving orders and moving staff, improves operational efficiency and service quality, saves user time, enhances user trust and loyalty, optimizes resource allocation, and reduces resource waste and idleness.
Smart Images

Figure CN119005579A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of data processing, and in particular to a moving order matching method, device and electronic equipment. Background Art
[0002] With the acceleration of urbanization and the improvement of residents' living standards, the demand for moving services has shown a continuous growth trend. Whether it is family moving, corporate relocation or warehousing logistics, professional moving services are needed to ensure the safe and efficient transportation of items.
[0003] Traditional moving order matching mostly relies on manual review and allocation, which is not only inefficient but also easily affected by human factors, resulting in inaccurate matching results. For example, manual review may not be able to fully understand the user's moving needs, such as the need to move personalized items, and thus cannot allocate the most suitable moving staff to the user, resulting in low matching accuracy of moving orders.
[0004] Therefore, there is an urgent need for a moving order matching method, device and electronic equipment. Summary of the invention
[0005] The present application provides a moving order matching method, device and electronic equipment, which are convenient for improving the matching accuracy of moving orders.
[0006] In a first aspect of the present application, a moving order matching method is provided, the method comprising: receiving a moving order sent by a user device; generating a user portrait of a user corresponding to the user device according to the moving order, the user portrait comprising a moving time, a moving starting point, a moving end point, an item type, and a user demand; obtaining service information of a moving staff member; generating a service portrait of the moving staff member according to the service information, the service portrait comprising a service time, a service area, a service type, and an order evaluation; matching the service portrait with the user portrait to obtain a matching result, the matching result comprising a target moving staff member; sending the moving order to the target moving staff member, and sending the matching result to the user.
[0007] By adopting the above technical solution, the process can ensure a more accurate match between moving orders and moving staff by constructing user portraits and service portraits in detail. The user portrait contains key information such as moving time, starting point, end point, item type and user needs, while the service portrait covers key indicators such as service time, service area, service type and order evaluation. This meticulous portrait construction enables the system to comprehensively consider multiple factors to find the most suitable moving staff for users. The automated matching process reduces manual intervention, making the allocation of moving orders more efficient and reasonable. The system can quickly match the user portrait and service portrait and assign the order to the most suitable moving staff, thereby avoiding waste and idleness of resources. This way of optimizing resource allocation helps to improve overall operational efficiency and service quality. Users only need to submit a moving order, and the system can automatically complete the matching and send the matching results to the user. This convenient operation method greatly saves users' time and energy and improves user experience. At the same time, due to the high accuracy of the matching results, users are more likely to get satisfactory services, which further enhances users' trust and loyalty to the platform. The order evaluation information in the service portrait provides an objective evaluation standard for the service quality of the moving staff. Therefore, it is convenient to assign the most suitable moving staff to the user, thereby improving the matching accuracy of the moving order.
[0008] Optionally, obtaining the service information of the moving staff specifically includes: receiving entry information input by the moving staff; obtaining first service information based on the entry information; obtaining historical moving orders of the moving staff; obtaining second service information based on the historical moving orders; performing data processing on the first service information and the second service information to obtain the service information, wherein the data processing includes denoising, filtering, feature extraction and normalization.
[0009] By adopting the above technical solution, the system can collect rich and comprehensive service information by receiving the entry information input by the moving staff and obtaining their historical moving orders. This information not only includes the basic information of the staff, but also covers their past service performance. This comprehensive information collection provides a solid foundation for the subsequent portrait construction. After obtaining the original data, the system can remove noise and interference in the data through data processing methods such as denoising and filtering to ensure the accuracy and reliability of the data. This helps to reduce matching errors caused by data errors and improve the accuracy of matching. Feature extraction and normalization processing are key steps in the data processing process. Feature extraction can identify the most critical information points in the data for the matching process, such as service time, service area, service type, etc. Normalization processing can convert data of different dimensions into the same scale, so that different features can be effectively compared and calculated. This helps to improve the efficiency and accuracy of the matching algorithm. Based on the service information after data processing, the system can generate a more detailed service portrait. This portrait not only contains the basic information and service capability description of the staff, but also reflects their performance characteristics and advantages in past services. This allows the system to more comprehensively consider the actual situation of the staff and user needs when matching, thereby obtaining more accurate matching results. Since the system can continuously obtain the new historical orders and real-time feedback information of the moving staff, the service profile can be continuously updated and optimized with the accumulation of time and service experience. This dynamic update mechanism helps to maintain the timeliness and accuracy of the profile, ensuring that the matching results always meet the actual situation.
[0010] Optionally, matching the service portrait with the user portrait to obtain a matching result specifically includes: determining time similarity based on the service time and the moving time; determining location similarity based on the service area and the moving starting point and the moving end point; determining type similarity based on the service type and the item type; determining evaluation similarity based on the order evaluation and the user demand; and calculating the matching degree based on the time similarity, the location similarity, the type similarity and the evaluation similarity.
[0011] By adopting the above technical solution, the matching process can more comprehensively evaluate the matching degree between movers and users by considering multiple dimensions such as time, location, type and evaluation. This multi-dimensional matching method is more accurate and reliable than single-dimensional matching because it can capture more key factors that affect the matching results. Each similarity indicator targets key elements in the moving service, such as time, location, service type and customer needs. By calculating these similarities separately and combining them to calculate the matching degree, the system can more accurately find the movers who best match the user's needs. This precise matching helps to improve user satisfaction and trust. The matching process can be flexibly adjusted according to actual needs. For example, if a dimension becomes less important in a specific situation, the system can reduce the weight of the dimension to reflect this change. In addition, as technology advances and new needs emerge, the system can easily add new similarity indicators to adapt to more complex matching scenarios. By providing movers who are highly matched with user needs, the system can bring users a better service experience. Users no longer need to worry about the various uncertainties and potential problems in the moving process because they know that the system has found the most suitable solution for them.
[0012] Optionally, the calculating the matching degree based on the time similarity, the location similarity, the type similarity and the evaluation similarity specifically includes: obtaining weight parameters corresponding to the time similarity, the location similarity, the type similarity and the evaluation similarity; calculating the matching degree according to the weight parameters; if it is determined that the matching degree is greater than a preset threshold, determining that the moving staff corresponding to the matching degree is the target moving staff.
[0013] By adopting the above technical solution, by setting corresponding weight parameters for each similarity, the system can flexibly adjust the importance of different factors in the matching process according to actual needs. This flexibility enables the system to cope with various complex matching scenarios and ensure that the matching results are more in line with the actual situation. The introduction of weight parameters enables the system to comprehensively consider multiple similarity factors and perform weighted calculations based on their relative importance. This weighted calculation method can more accurately reflect the degree of match between the movers and users, thereby improving the accuracy and reliability of matching. By setting a preset threshold to determine whether the match is high enough, it is determined whether a mover is considered as the target mover. This clear decision-making standard helps to reduce human intervention and subjective judgment, making the matching process more objective, fair and transparent. Because the matching process is more accurate and reliable, the system can recommend movers that better meet the needs of users. This will greatly improve user satisfaction and trust and optimize the overall user experience. By quickly and accurately matching the target movers, the system can reduce the time and energy consumed by users in the process of finding suitable moving services. At the same time, this also helps the moving service platform improve service efficiency and reduce operating costs.
[0014] Optionally, the method also includes: determining the user, the moving staff and the moving order as nodes; determining the relationship between the user, the moving staff and the moving order as edges; constructing a graph model based on the nodes and the edges; and using a graph neural network to perform feature learning and matching on the graph model to determine the target moving staff.
[0015] By adopting the above technical solution, by taking users, movers and moving orders as nodes and the relationships between them as edges to construct a graph model, this method can capture and represent the complex interactions and dependencies between these entities. This complex relationship modeling capability is difficult to match with traditional matching methods because it can take into account more dimensions of information and context. Graph neural networks can use the connection relationship between nodes to learn deep feature representations of nodes and edges through information transmission and aggregation mechanisms. This deep feature learning helps to more accurately understand the intrinsic connection between users, movers and moving orders, thereby improving the accuracy of matching. This method directly learns and matches features of the graph model through graph neural networks, realizing an end-to-end matching process. This means that the system can directly output matching results from the original data (i.e., nodes and edges) without multi-step intermediate processing or manual intervention. This end-to-end matching process not only simplifies the matching process, but also improves the efficiency and reliability of matching. Since graph neural networks can process changes in graph data in real time, this method supports real-time matching and dynamic updates. When new users, movers, or moving orders appear, the system can immediately add them to the graph model and re-learn and match features through the graph neural network to ensure the timeliness and accuracy of the matching results.
[0016] Optionally, the method also includes: analyzing the moving order to determine a priority corresponding to the moving order, the priority being determined based on a timing relationship, and the priority being used to represent a dispatch response speed of the moving order; obtaining a browsing and ordering time for the moving order; if it is determined that the browsing and ordering time is less than a preset time, determining that the priority is a first priority; if it is determined that the browsing and ordering time is greater than or equal to a preset time, determining that the priority is a second priority, and the dispatch response speed corresponding to the first priority is faster than the dispatch response speed corresponding to the second priority.
[0017] By adopting the above technical solution, by determining the priority of orders according to the browsing and ordering time, the system can respond faster to users who show higher urgency or demand. When users browse and place orders quickly in a short period of time, it is likely that they are in urgent need of moving services, so setting these orders to a higher priority can arrange moving workers for them faster, thereby improving user satisfaction and experience. On the moving service platform, resources (i.e. moving workers) are limited. By giving priority to those more urgent or urgent orders, the system can use these limited resources more effectively and ensure that they are allocated to users who need them most. This way of optimizing resource allocation helps to improve overall service efficiency and service quality. This mechanism allows the system to dynamically adjust order priorities based on user behavior (browsing and ordering time). This flexibility enables the system to better adapt to changes in different scenarios and needs, thereby providing more personalized and accurate services. For those orders set as the first priority, the system will assign moving workers to them more quickly, thereby reducing the waiting time for users. This fast response speed helps to improve users' trust and loyalty to the platform.
[0018] Optionally, the method further includes: receiving a modification request sent by the user device; modifying the moving order according to the modification request to obtain a modified order; and dispatching orders to a plurality of moving workers according to the modified order.
[0019] By adopting the above technical solution, allowing users to modify orders is an important part of improving user experience. In real life, users may need to modify submitted orders for various reasons (such as time changes, additions and reductions of items, address changes, etc.). By receiving and processing users' modification requests, the system can respond to users' needs quickly, avoid users' dissatisfaction or cancellation of orders due to the inability to modify orders, and thus improve user satisfaction and loyalty. The existence of the order modification function makes the order processing process more flexible. The system is no longer limited to the order information submitted by the user for the first time, but can be dynamically adjusted according to the actual needs of the user. This flexibility helps to better meet the personalized needs of users, and also reduces service errors and disputes caused by incorrect or changed order information. Re-dispatching orders after modifying orders helps to optimize resource allocation. An order that may have been assigned to a moving worker may no longer be applicable due to user modifications. At this time, the system can re-evaluate all available moving workers and select the most suitable person to execute the modified order. This way of reallocating resources helps to ensure that resources are maximized, and also improves the efficiency and quality of services. By modifying orders in a timely manner and re-dispatching orders, the system can reduce service errors and disputes caused by incorrect or inconsistent order information. For example, if the user changes the moving time or address, but the system still dispatches the order according to the original order information, it may cause the moving staff to arrive at the wrong place or time, causing unnecessary trouble and disputes. This situation can be avoided by processing the user's modification request in a timely manner. This process also reflects the system's ability to respond to user requests in a timely manner. When users submit modification requests, the system can quickly receive and process these requests, and then dispatch the order according to the modified order information. This fast response speed helps to improve users' trust and satisfaction with the system, and also enhances the system's competitiveness and market position.
[0020] In a second aspect of the present application, a moving order matching device is provided, the moving order matching device comprising an acquisition module and a processing module, wherein the acquisition module is used to receive a moving order sent by a user device; the processing module is used to generate a user portrait of the user corresponding to the user device according to the moving order, the user portrait including moving time, moving starting point, moving end point, item type and user needs; the acquisition module is also used to acquire service information of the moving staff; the processing module is also used to generate a service portrait of the moving staff according to the service information, the service portrait including service time, service area, service type and order evaluation; the processing module is also used to match the service portrait with the user portrait to obtain a matching result, the matching result including a target moving staff; the processing module is also used to send the moving order to the target moving staff, and send the matching result to the user.
[0021] In the third aspect of the present application, an electronic device is provided, which includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs the method described above.
[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, the method described above is executed.
[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By building user and service portraits in detail, the process can ensure a more accurate match between moving orders and moving workers. User portraits include key information such as moving time, starting point, destination, item type and user needs, while service portraits cover key indicators such as service time, service area, service type and order evaluation. This detailed portrait construction enables the system to comprehensively consider multiple factors to find the most suitable moving workers for users. The automated matching process reduces manual intervention, making the allocation of moving orders more efficient and reasonable. The system can quickly match orders based on user portraits and service portraits, and allocate orders to the most suitable moving workers, thereby avoiding waste and idleness of resources. This way of optimizing resource allocation helps to improve overall operational efficiency and service quality. Users only need to submit moving orders, and the system can automatically complete the matching and send the matching results to users. This convenient operation method greatly saves users' time and energy and improves user experience. At the same time, due to the high accuracy of the matching results, users are more likely to get satisfactory services, which further enhances users' trust and loyalty to the platform. The order evaluation information in the service portrait provides an objective evaluation standard for the service quality of moving workers. Therefore, it is convenient to assign the most suitable moving staff to the user, thereby improving the matching accuracy of the moving order. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] Figure 1 A flowchart of a moving order matching method provided in an embodiment of the present application.
[0025] Figure 2 Another flowchart of a moving order matching method provided in an embodiment of the present application.
[0026] Figure 3 A module diagram of a moving order matching device provided in an embodiment of the present application.
[0027] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.
[0028] Explanation of the reference numerals: 31, acquisition module; 32, processing module; 41, processor; 42, communication bus; 43, user interface; 44, network interface; 45, memory. DETAILED DESCRIPTION
[0029] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.
[0030] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.
[0031] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.
[0032] With the rapid advancement of urbanization and the significant improvement in the quality of life of residents, the demand for moving services is growing at an unprecedented rate, covering many fields such as family relocation, corporate relocation and even warehousing and transportation. This trend highlights the urgent need for professional and efficient moving services to ensure the safety and rapid circulation of items during the relocation process.
[0033] However, the traditional moving order matching mechanism often relies on cumbersome manual review and manual allocation processes. This model not only significantly restricts processing efficiency, but also inevitably introduces the subjectivity and limitations of human judgment. Specifically, manual review may be difficult to accurately capture and fully understand the unique moving needs of each customer, such as the requirements for the transportation of special items or personalized service expectations, and thus it is difficult to accurately match the most suitable moving team or staff to execute the order.
[0034] In order to solve the above technical problems, this application provides a moving order matching method, referring to Figure 1 , Figure 1 A flow chart of a moving order matching method provided in an embodiment of the present application. The moving order matching method is applied to a server and includes steps S110 to S160, which are as follows: S110: Receive a moving order sent by a user device.
[0035] Specifically, in a computer network, a server is a special computer that provides services. It has powerful processing power, storage space, and network bandwidth, and is used to receive requests from clients (such as user devices), process these requests, and return the processing results to the client. In an embodiment of the present application, the server is responsible for storing order information, managing user data, coordinating resources such as moving staff, and providing a user interface for users to interact with the platform. A user device is an electronic device that users use to access online services or applications. It can be a smartphone, tablet computer, laptop, or desktop computer, etc. Users connect to the Internet through these devices and use a browser or application to communicate with the server. In the scenario of moving services, user devices are used to create, submit, and modify moving orders, as well as interact with other functions on the platform. A moving order is a request submitted by a user to a moving service platform to request the platform to provide moving services. The order usually contains detailed information such as the user's personal information (such as name, contact information), moving time, moving address, list of items, service requirements, etc. This information is crucial for the platform because it determines how to arrange moving staff, prepare necessary tools and vehicles, and ensure that services can be completed on time, in quality, and in quantity.
[0036] For example, suppose Xiao Ming is preparing to move. He uses his smartphone to open an application for a moving service platform. In the application, he finds a moving service option that suits his needs and clicks to enter the order filling page. On the page, he fills in his name, contact number, moving date, original address and new address, and describes in detail the items he needs to move and special service requirements (such as the need to disassemble and assemble furniture, provide packaging materials, etc.). After filling in the form, he clicks the "Submit Order" button. At this time, Xiao Ming's smartphone sends the moving order to the server of the moving service platform via the Internet. After receiving the order, the server will perform a series of processing and verification work to ensure the accuracy and completeness of the order information. Once the order is successfully received and processed, the server will send a confirmation message to Xiao Ming, informing him that the order has been successfully submitted and waiting for the platform to arrange for the moving staff to contact him to confirm the specific moving matters.
[0037] S120. Generate a user profile of the user corresponding to the user device according to the moving order. The user profile includes moving time, moving starting point, moving destination, item type, and user needs.
[0038] Specifically, user portraits are virtual representations built based on user data, which are used to describe user characteristics, preferences, and needs. In the scenario of a moving service platform, user portraits may include information such as the user's moving habits (such as moving frequency, moving time preferences), item type preferences (such as whether large furniture is often moved), and special service needs (such as whether disassembly and assembly services, packaging services, etc.) This information helps the platform better understand users and provide more intimate and personalized services. After the server receives the moving order submitted by the user, it will extract key information from the order (such as moving time, location, item type, etc.), and combine the user's previous behavior data (such as historical order records, browsing records, etc.) to generate the corresponding user portrait through data analysis, mining and other technical means. This process may involve multiple steps such as data cleaning, conversion, aggregation, and classification, as well as the application of machine learning, data mining and other algorithms to discover users' potential needs and preferences.
[0039] For example, suppose Ms. Li is a frequent customer of the moving service platform. She often needs to move, and the types of items she moves each time are quite special, including some large artworks and fragile items. Recently, she submitted a moving order again, which clearly stated the moving time, starting point, and end point, and specifically noted that she needed disassembly and assembly services and professional packaging materials to protect her artworks. After receiving Ms. Li's order, the server will first extract key information from the order, such as the moving time, location, item type (including artworks and fragile items), and special needs (disassembly and assembly services and packaging materials). Then, the server will combine Ms. Li's previous historical order records, browsing records and other data on the platform to conduct an in-depth analysis of her moving habits, item type preferences, and special service needs. Through analysis, the server found that Ms. Li is a user with high requirements for moving services. She often needs to move some special items and has high requirements for service quality and details. Therefore, the server generates a detailed user profile for Ms. Li, which not only contains her basic information (such as name, contact information, etc.), but also highlights her moving habits, item type preferences, and special service needs. With this user portrait, the platform can more accurately recommend suitable moving service solutions to Ms. Li, such as arranging experienced moving staff, providing professional disassembly and packing services, and providing her with personalized service suggestions, etc. This will not only improve Ms. Li's moving experience, but also enhance her trust and loyalty to the platform.
[0040] S130: Obtain service information of the moving staff.
[0041] Specifically, the service information of the moving staff includes but is not limited to the moving staff's personal information (such as name, contact information, certificate information, etc.), service skills (such as whether they can carry large items, whether they are good at disassembling and assembling furniture, etc.), work experience (such as the number of years they have been engaged in moving work, the number of orders completed, etc.), current status (such as whether they are online, whether they have been assigned tasks, etc.), location information (such as current location or serviceable area), etc. This information is crucial for the server because it determines how the server matches the most suitable moving staff for users. The server can obtain the service information of the moving staff in many ways. One way is that the moving staff actively submits their service information to the server, including personal information, skill certificates, work experience, etc. The server will review and verify this information to ensure its authenticity and accuracy. Another way is that the server obtains the location information and status information of the moving staff in real time through technical means (such as GPS positioning, online status detection, etc.). This information helps the server to understand the availability and service capabilities of each moving staff more accurately.
[0042] In a possible implementation, obtaining service information of moving staff specifically includes: receiving employment information input by the moving staff; obtaining first service information based on the employment information; obtaining historical moving orders of the moving staff; obtaining second service information based on the historical moving orders; performing data processing on the first service information and the second service information to obtain service information, wherein the data processing includes denoising, filtering, feature extraction, and normalization.
[0043] Specifically, the entry information is the basic information submitted by the moving staff when joining the platform, including but not limited to name, age, gender, contact information, work experience, skill certificates, etc. This information provides the platform with a preliminary understanding of the basic situation and ability level of the moving staff. The first service information is the service information directly extracted or derived from the entry information. For example, the number of years of work of the moving staff in the moving industry can be inferred from the work experience, and whether they have specific skills (such as disassembling and assembling furniture, driving a specific type of vehicle, etc.) can be confirmed from the skill certificate. The historical moving order records the moving tasks completed by the moving staff in the past, including the time, location, item type, user evaluation, etc. of the order. This information is crucial for evaluating the actual work performance and service quality of the moving staff. The second service information is obtained by analyzing the historical moving orders. The platform can calculate indicators such as the order completion rate, user satisfaction score, and average service time of the moving staff to evaluate their work efficiency, service attitude, and service quality. Data processing is a key step in integrating the first service information and the second service information. It may include techniques such as denoising (removing erroneous or invalid data), filtering (smoothing data to reduce noise), feature extraction (extracting key information or patterns from data), and normalization (converting data to the same scale for comparison or analysis). Through these processing steps, the platform can more accurately evaluate the comprehensive service capabilities of moving workers and provide users with more accurate service recommendations.
[0044] For example, suppose there is a platform called "Smart Moving" that wants to build comprehensive service information for each moving worker through the server. The following is a specific example of this process: When Master Zhang joined the "Smart Moving" platform, he submitted his entry information, including 5 years of moving work experience, driver's license and furniture disassembly and assembly skills. Based on Master Zhang's entry information, the platform extracted his first service information such as his years of work experience (5 years) and skills (driver's license, furniture disassembly and assembly). The platform retrieved Master Zhang's historical moving orders in the past year and found that he had completed a total of 100 orders, with a user satisfaction score of 4.8 / 5 (out of 5 points) and an average service time of 3 hours / order. Based on the historical order data, the platform calculated Master Zhang's second service information such as order completion rate (100%), user satisfaction score (4.8 / 5) and average service time (3 hours / order). The platform performed data processing steps such as denoising, filtering, feature extraction and normalization on the first service information and the second service information. After processing, the platform obtains comprehensive service information of Mr. Zhang, including his rich work experience, superb skill level, high user satisfaction score and high work efficiency. This information will be used to recommend suitable moving workers to users, ensuring that users can obtain high-quality and efficient moving services.
[0045] S140. Generate a service profile of the moving staff based on the service information. The service profile includes service time, service area, service type and order evaluation.
[0046] Specifically, the generation of service portraits is based on the service information of moving staff. This information includes but is not limited to service time (such as the time period in which they can work), service area (such as the service locations that can be covered), service type (such as whether they can move large items, whether they provide disassembly and assembly services, etc.) and order evaluation (such as user evaluation and feedback on their services). The platform will use data analysis and mining technology to extract key features from service information and build a service portrait for each moving staff. Service time refers to the time period in which moving staff can provide services, such as 8 am to 6 pm, or all day on weekends. This helps the platform match suitable moving staff according to the specific needs of users (such as moving time) when users place orders. Service area refers to the range of service locations that moving staff can cover, such as a specific area in a city or the entire city. This helps the platform consider the location of moving staff and the user's moving location when assigning tasks, thereby improving service efficiency and user satisfaction. Service type refers to the specific service content that moving staff can provide, such as moving large items, disassembling and assembling furniture, packing and sorting, etc. This helps the platform recommend moving staff with corresponding skills to users after understanding their needs. Order evaluation refers to the user's evaluation and feedback on the service quality of the moving staff, usually in the form of ratings, comments, etc. This helps the platform evaluate the service performance of the moving staff and provide improvement suggestions for their future services.
[0047] S150: Match the service portrait with the user portrait to obtain a matching result, where the matching result includes the target moving staff.
[0048] Specifically, the matching process is to compare and analyze the key information in the two portraits to find the moving staff that best meets the user's needs. The matching result refers to the target moving staff screened out through the matching process. These staff members are highly matched with the user's needs in terms of service time, service area, service type, etc., and usually have high user satisfaction and evaluation. In actual applications, the server may use a variety of algorithms and technologies to achieve the matching of service portraits and user portraits. These algorithms may include rule-based matching, similarity-based matching, machine learning algorithms, etc. For example, the server can set a series of rules, such as giving priority to moving staff whose service area is consistent with the user's moving location, or selecting staff with high user evaluation. At the same time, the server can also use machine learning algorithms to continuously optimize the matching model by learning historical order data to improve the accuracy and efficiency of matching.
[0049] In a possible implementation, the service profile is matched with the user profile to obtain a matching result, which specifically includes: determining time similarity based on service time and moving time; determining location similarity based on service area and moving starting point and moving end point; determining type similarity based on service type and item type; determining evaluation similarity based on order evaluation and user needs; and calculating the matching degree based on time similarity, location similarity, type similarity and evaluation similarity.
[0050] Specifically, it is determined based on the service time in the service portrait and the moving time in the user portrait. If the working time of the moving staff can cover the moving time of the user, then the time similarity is high. For example, if the working time of the moving staff is from 9 am to 6 pm every day, and the moving time of the user is from 2 pm to 5 pm, then the time similarity is 100%, because the moving time is completely within the service time. It is determined based on the service area in the service portrait and the moving starting point and moving end point in the user portrait. If the service area of the moving staff can cover the moving starting point and end point of the user, then the location similarity is high. For example, if the service area of the moving staff is the entire city A, and the user's moving starting point is the east district of city A and the end point is the west district, then the location similarity is also 100%, because the service area completely covers the moving path. It is determined based on the service type in the service portrait and the item type in the user portrait. If the service type provided by the moving staff can meet the user's needs for moving specific items, then the type similarity is high. For example, if the user's item types include large furniture and fragile items, and the movers are good at moving large items and provide professional packaging services to prevent fragile items from being damaged, then the type similarity will be high. Determined based on the order evaluation in the service profile and the user's needs in the user profile (which may include expectations for service quality). Although the user's direct needs may not directly involve evaluations, the platform can assume that the user is more inclined to choose movers with high evaluations and good service quality. For example, if the user evaluations of movers are generally high and the user expects high-quality service, then the evaluation similarity will be high. Based on the above four similarities (time, location, type, evaluation), the platform will use certain algorithms (such as weighted sum, machine learning model, etc.) to calculate the final match. Each similarity may be assigned a different weight to reflect its importance to the user. For example, if the user attaches great importance to time and service quality, the weights of time similarity and evaluation similarity may be relatively high.
[0051] For example, suppose that the "Shunxin Moving" platform is looking for a suitable moving worker for Mr. Zhang. Mr. Zhang's moving requirements are as follows: Moving time: next Wednesday from 2 to 5 p.m.; Moving starting point: the southern district of city B; Moving destination: the northern district of city B; Item types: including a large bed, a set of sofas and some fragile items; User needs: I hope that the moving workers can arrive on time, have a good service attitude, and are good at moving large items and packing fragile items. At the same time, the "Shunxin Moving" platform has two service portraits of moving workers: Master Li: The service time is from 9 a.m. to 7 p.m. every day, and the service area covers the north and south districts of city B. He is good at moving large items and provides professional packaging services. User evaluation is generally high. Master Wang: The service time is from 1 p.m. to 8 p.m. every day, and the service area also covers the north and south districts of city B, but he is mainly good at moving small items, and the user evaluation is medium. Based on the above information, the "Shunxin Moving" platform can make the following matches: Master Li and Master Wang can both meet Mr. Zhang's moving time requirements, so the time similarity is 100%. The service areas of both masters cover Mr. Zhang's moving route, so the location similarity is also 100%. Master Li is good at moving large items and providing packaging services, which is more in line with Mr. Zhang's needs, so Master Li's type similarity is higher than Master Wang's. Master Li's user rating is higher than Master Wang's, so the rating similarity is also higher. In the end, based on these four similarities and the possible weights that can be set, the "Shunxin Moving" platform will calculate that Master Li's match is higher than Master Wang's, so Master Li will be recommended to Mr. Zhang as the target moving worker.
[0052] In a possible implementation, the matching degree is calculated based on time similarity, location similarity, type similarity and evaluation similarity, specifically including: obtaining weight parameters corresponding to time similarity, location similarity, type similarity and evaluation similarity; calculating the matching degree according to the weight parameters; if it is determined that the matching degree is greater than a preset threshold, determining the moving staff corresponding to the matching degree as the target moving staff.
[0053] Specifically, the weight parameters are set in advance to reflect the importance of different similarities in the matching process. For example, if the platform believes that time similarity is very important to users, then the weight parameter corresponding to time similarity will be set higher. The setting of weight parameters can be determined based on various factors such as the platform's historical data, user feedback, market research, etc., or it can be automatically optimized through machine learning models. After obtaining each similarity and its corresponding weight parameter, the platform will use a certain algorithm (such as weighted summation) to calculate the matching degree. Specifically, each similarity value is multiplied by its corresponding weight parameter, and then all the results are added together to obtain the matching degree.
[0054] The calculation formula for the matching degree can be expressed as: matching degree = (time similarity * time weight) + (location similarity * location weight) + (type similarity * type weight) + (evaluation similarity * evaluation weight). After calculating the matching degree, the platform will compare it with the preset threshold. If the matching degree is greater than the threshold, it means that the moving worker has a high degree of matching with the user's needs and can be identified as the target moving worker. The setting of the preset threshold is also based on platform strategy and user needs. If the platform wants to recommend more accurate services to users, the threshold may be set higher; if the platform wants to improve the availability of services, the threshold may be set lower.
[0055] For example, suppose that the "Yida Moving" platform is looking for a suitable moving worker for Ms. Zhao. Ms. Zhao's moving needs and weight parameters are set as follows: Moving time: next Friday from 10 am to 2 pm. Moving starting point: the central area of City C; Moving destination: the suburbs of City C; Item type: including some furniture and electrical appliances; Weight parameter settings: Time similarity weight 0.4, location similarity weight 0.3, type similarity weight 0.2, evaluation similarity weight 0.1. At the same time, the "Yida Moving" platform has two moving workers' service portraits and their similarity calculation results: Master Li: Time similarity 90% (service time covers the demand time), location similarity 100% (service area covers the moving path), type similarity 80% (good at moving furniture and electrical appliances), evaluation similarity 95% (high user evaluation). Master Wang: Time similarity 100% (service time completely covers the demand time), location similarity 80% (service area partially covers the moving path), type similarity 70% (average handling ability), evaluation similarity 80% (medium user evaluation).
[0056] Among them, according to the weight parameters and similarity calculation results, the platform can calculate the matching degree of the two masters: Master Li's matching degree = (90%*0.4) + (100%*0.3) + (80%*0.2) + (95%*0.1) = 0.915. Master Wang's matching degree = (100%*0.4) + (80%*0.3) + (70%*0.2) + (80%*0.1) = 0.86. Assuming that the preset threshold is 0.9, only Master Li's matching degree is greater than the threshold, so the "Yida Moving" platform will identify Master Li as the target moving staff and recommend him to Ms. Zhao.
[0057] S160: Sending a moving order to a target moving worker, and sending a matching result to a user.
[0058] Specifically, this step is to notify the target movers that they have been selected as the service provider for a specific moving task. The moving order contains detailed information such as the user's basic information (such as name, contact information), moving time, moving starting and ending points, a list of items to be moved, special needs (such as furniture disassembly and assembly, packaging services, etc.), and service fees. By sending the moving order, the platform ensures that the movers can understand the specific requirements of the task in advance and make corresponding preparations. And it is to confirm to the user that the platform has found the right movers for them. The matching results usually include the basic information of the target movers (such as name, contact information, service evaluation, etc.), estimated arrival time, an overview of the service costs, and other matters that the user may need to know. By sending the matching results, the platform enhances the user's sense of trust and provides users with the opportunity to communicate directly with the service provider (if necessary).
[0059] Therefore, by constructing user portraits and service portraits in detail, the process can ensure a more accurate match between moving orders and moving staff. User portraits include key information such as moving time, starting point, end point, item type and user needs, while service portraits cover key indicators such as service time, service area, service type and order evaluation. This detailed portrait construction enables the server to comprehensively consider multiple factors to find the most suitable moving staff for users. The automated matching process reduces manual intervention, making the allocation of moving orders more efficient and reasonable. The server can quickly match the user portrait and service portrait and allocate the order to the most suitable moving staff, thus avoiding waste and idleness of resources. This way of optimizing resource allocation helps to improve overall operational efficiency and service quality. Users only need to submit a moving order, and the server can automatically complete the matching and send the matching results to the user. This convenient operation method greatly saves users' time and energy and improves user experience. At the same time, due to the high accuracy of the matching results, users are more likely to get satisfactory services, which further enhances users' trust and loyalty to the platform. The order evaluation information in the service portrait provides an objective evaluation standard for the service quality of the moving staff. Therefore, it is convenient to assign the most suitable moving staff to the user, thereby improving the matching accuracy of the moving order.
[0060] In one possible implementation, users, moving staff, and moving orders are determined as nodes; the relationship between users, moving staff, and moving orders is determined as edges; a graph model is constructed based on the nodes and edges; a graph neural network is used to perform feature learning and matching on the graph model to determine the target moving staff.
[0061] Specifically, in the graph model, each entity (such as user, mover, moving order) is regarded as a node. These nodes contain their own attribute information, such as the user's geographic location, historical order records, the service scope and evaluation level of the mover, and the detailed information of the moving order (such as time, location, item type, etc.). Edges are used to represent the relationship between nodes. In the context of the moving service platform, edges may represent the "initiate" relationship between the user and the moving order, the "accept" or "reject" relationship between the mover and the moving order, and the "historical cooperation" relationship that may exist between the user and the mover. Among them, the graph neural network is a neural network specially designed to process graph structured data. It can capture the complex relationship between nodes and update the representation of nodes by propagating information in the graph. In the scenario of the moving service platform, GNN can learn the potential connections between users, movers, and moving orders, so as to more accurately predict which movers are most suitable for which orders. By training the graph model with the graph neural network, the platform can learn the feature representation of each node. These feature representations not only contain the attribute information of the node itself, but also incorporate the information of the nodes connected to it. During the matching process, the platform can use the learned feature representation to calculate the matching degree between the user and the mover. This usually involves calculating the distance or similarity between the two in the feature space and recommending the most suitable mover based on these calculation results.
[0062] In one possible implementation, the moving orders are analyzed to determine the priority corresponding to the moving orders, the priority being determined based on a timing relationship, and the priority being used to represent the order response speed of the moving orders; the browsing and ordering time of the moving orders is obtained; if it is determined that the browsing and ordering time is less than a preset time, the priority is determined to be the first priority; if it is determined that the browsing and ordering time is greater than or equal to the preset time, the priority is determined to be the second priority, and the order response speed corresponding to the first priority is faster than the order response speed corresponding to the second priority.
[0063] Specifically, the server first analyzes each moving order that enters the server to determine its priority. The priority here is determined based on the timing relationship, which means that it will consider factors such as the time when the order is submitted and the service time required by the user. The priority is used to indicate the response speed of the moving order, that is, the higher the priority of the order, the faster the server should assign the appropriate moving staff to it. In the process of determining the priority, the server will also obtain the browsing order time of the moving order. This time refers to the time taken from the user starting to browse the moving service page to the final submission of the order. The browsing order time can be used as an indicator to evaluate the degree of user's immediate needs. A shorter browsing order time may mean that the user has a more urgent or urgent need. The server will then further refine the order priority based on the browsing order time. If the browsing order time is less than the preset time (this preset time is a threshold set by the server based on historical data or business rules), the server considers this to be an urgent or immediate need and determines the priority of the order to be the first priority. If the browsing order time is greater than or equal to the preset time, the server considers this need to be relatively less urgent and determines the priority of the order to be the second priority. The response speed of the dispatch corresponding to the first priority is faster than the response speed of the dispatch corresponding to the second priority. This means that the server will give priority to processing the orders of the first priority, allocating resources (such as moving workers) and arranging service time for them.
[0064] In one possible implementation, refer to Figure 2 , Figure 2 Another flow chart of a moving order matching method provided for an embodiment of the present application includes steps S210 to S230, and the above steps are as follows: S210, receiving a modification request sent by a user device; S220, modifying the moving order according to the modification request to obtain a modified order; S230, dispatching orders to multiple moving staff according to the modified order.
[0065] Specifically, after a user submits a moving order, if the order information needs to be modified for some reason (such as a change in moving time, an increase or decrease in items, a change in address, etc.), the user can send a modification request to the moving service platform through a user device (such as a mobile phone, computer, etc.). This modification request contains the order information that the user wants to modify and the specific modification content. After receiving the user's modification request, the moving service platform will parse the request and extract the order information and modification content that the user wants to modify. Then, the server will modify the original moving order accordingly based on this information and generate a new order, namely the modification order. This modification order contains all the changes that the user wants. After receiving the modification order, the server will reschedule the moving service according to the modified order information. This may include re-evaluating the urgency of the order, recalculating the number of staff required, re-planning the moving route, etc. Finally, the server will dispatch orders to multiple moving staff according to the specific requirements of the modification order to ensure that they can provide moving services according to the new order information.
[0066] This application also provides a moving order matching device, referring to Figure 3 , Figure 3 A module schematic diagram of a moving order matching device provided in an embodiment of the present application, wherein the moving order matching device is a server, and the server includes an acquisition module 31 and a processing module 32, wherein the acquisition module 31 receives a moving order sent by a user device; the processing module 32 generates a user portrait of the user corresponding to the user device according to the moving order, and the user portrait includes moving time, moving starting point, moving end point, item type and user needs; the acquisition module 31 acquires service information of the moving staff; the processing module 32 generates a service portrait of the moving staff according to the service information, and the service portrait includes service time, service area, service type and order evaluation; the processing module 32 matches the service portrait with the user portrait to obtain a matching result, and the matching result includes a target moving staff; the processing module 32 sends the moving order to the target moving staff, and sends the matching result to the user.
[0067] In a possible implementation, the acquisition module 31 acquires the service information of the moving staff, specifically including: the acquisition module 31 receives the entry information input by the moving staff; the processing module 32 obtains the first service information according to the entry information; the acquisition module 31 acquires the historical moving orders of the moving staff; the processing module 32 obtains the second service information according to the historical moving orders; the processing module 32 performs data processing on the first service information and the second service information to obtain service information, and the data processing includes denoising, filtering, feature extraction and normalization.
[0068] In a possible implementation, the processing module 32 matches the service portrait with the user portrait to obtain a matching result, which specifically includes: the processing module 32 determines the time similarity based on the service time and the moving time; the processing module 32 determines the location similarity based on the service area and the moving starting point and the moving end point; the processing module 32 determines the type similarity based on the service type and the item type; the processing module 32 determines the evaluation similarity based on the order evaluation and user needs; the processing module 32 calculates the matching degree based on the time similarity, location similarity, type similarity and evaluation similarity.
[0069] In a possible implementation, the processing module 32 calculates the matching degree based on time similarity, location similarity, type similarity and evaluation similarity, specifically including: the acquisition module 31 obtains the weight parameters corresponding to the time similarity, location similarity, type similarity and evaluation similarity; the processing module 32 calculates the matching degree according to the weight parameters; if the processing module 32 determines that the matching degree is greater than a preset threshold, it determines that the moving staff corresponding to the matching degree is the target moving staff.
[0070] In one possible implementation, the processing module 32 determines the user, the moving staff, and the moving order as nodes; the processing module 32 determines the relationship between the user, the moving staff, and the moving order as an edge; the processing module 32 constructs a graph model based on the nodes and edges; the processing module 32 uses a graph neural network to perform feature learning and matching on the graph model to determine the target moving staff.
[0071] In one possible implementation, the processing module 32 analyzes the moving order to determine the priority corresponding to the moving order, the priority is determined according to a timing relationship, and the priority is used to represent the order response speed of the moving order; the acquisition module 31 acquires the browsing and ordering time of the moving order; if the processing module 32 determines that the browsing and ordering time is less than the preset time, the priority is determined to be the first priority; if the processing module 32 determines that the browsing and ordering time is greater than or equal to the preset time, the priority is determined to be the second priority, and the order response speed corresponding to the first priority is faster than the order response speed corresponding to the second priority.
[0072] In a possible implementation, the acquisition module 31 receives a modification request sent by a user device; the processing module 32 modifies the moving order according to the modification request to obtain a modified order; and the processing module 32 dispatches orders to multiple moving workers according to the modified order.
[0073] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0074] The present application also provides an electronic device, referring to Figure 4 , Figure 4 The electronic device may include: at least one processor 41 , at least one network interface 44 , a user interface 43 , a memory 45 , and at least one communication bus 42 .
[0075] The communication bus 42 is used to realize the connection and communication between these components.
[0076] The user interface 43 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 43 may also include a standard wired interface and a wireless interface.
[0077] The network interface 44 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).
[0078] Among them, the processor 41 may include one or more processing cores. The processor 41 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 45, and calling data stored in the memory 45. Optionally, the processor 41 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 41 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 41, and it can be implemented separately through a chip.
[0079] Among them, the memory 45 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 45 includes a non-transitory computer-readable storage medium. The memory 45 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 45 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 45 may also be optionally at least one storage device located away from the aforementioned processor 41. As Figure 4 As shown, the memory 45 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a moving order matching method.
[0080] exist Figure 4 In the electronic device shown, the user interface 43 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 41 can be used to call an application program storing a moving order matching method in the memory 45. When executed by one or more processors, the electronic device executes one or more methods in the above-mentioned embodiments.
[0081] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.
[0082] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.
[0083] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0084] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.
[0085] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0087] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.
[0088] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, it will be easy for those skilled in the art to think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.
Claims
1. A moving order matching method, characterized in that: The method comprises: Receive moving orders sent by user devices; Generate a user profile of the user corresponding to the user device according to the moving order, the user profile including moving time, moving starting point, moving destination, item type, and user needs; Get the service information of the moving staff; Generate a service profile of the moving staff according to the service information, wherein the service profile includes service time, service area, service type and order evaluation; Matching the service profile with the user profile to obtain a matching result, wherein the matching result includes a target moving worker; The moving order is sent to the target moving worker, and the matching result is sent to the user.
2. The moving order matching method according to claim 1, characterized in that: The obtaining of the service information of the moving staff specifically includes: Receiving employment information input by the moving staff; Obtaining first service information according to the employment information; Obtain historical moving orders of the moving staff; Obtaining second service information according to the historical moving order; Data processing is performed on the first service information and the second service information to obtain the service information, wherein the data processing includes denoising, filtering, feature extraction, and normalization processing.
3. The moving order matching method according to claim 1, characterized in that: The matching of the service profile with the user profile to obtain a matching result specifically includes: Determining time similarity based on the service time and the moving time; Determining location similarity according to the service area, the moving starting point, and the moving end point; Determining type similarity according to the service type and the item type; Determining evaluation similarity according to the order evaluation and the user demand; A matching degree is calculated based on the time similarity, the location similarity, the type similarity and the evaluation similarity.
4. The moving order matching method according to claim 3, characterized in that: The calculating the matching degree based on the time similarity, the location similarity, the type similarity and the evaluation similarity specifically includes: Obtaining weight parameters corresponding to the time similarity, the location similarity, the type similarity, and the evaluation similarity; Calculating the matching degree according to the weight parameter; If it is determined that the matching degree is greater than a preset threshold, the moving worker corresponding to the matching degree is determined as the target moving worker.
5. The moving order matching method according to claim 1, characterized in that: The method further comprises: Determine the user, the moving staff, and the moving order as nodes; Determine the relationship between the user, the moving staff, and the moving order as an edge; Constructing a graph model according to the nodes and the edges; A graph neural network is used to perform feature learning and matching on the graph model to determine the target moving staff.
6. The moving order matching method according to claim 1, characterized in that: The method further comprises: Analyze the moving order to determine a priority corresponding to the moving order, wherein the priority is determined according to a time sequence relationship and is used to indicate a response speed of dispatching the moving order; Obtain the browsing and ordering time of the moving order; If it is determined that the browsing and ordering time is less than the preset time, the priority is determined to be the first priority; If it is determined that the browsing and ordering time is greater than or equal to the preset time, the priority is determined to be the second priority, and the order response speed corresponding to the first priority is faster than the order response speed corresponding to the second priority.
7. The moving order matching method according to claim 1, characterized in that: The method further comprises: receiving a modification request sent by the user equipment; Modify the moving order according to the modification request to obtain a modified order; Dispatching orders to the plurality of moving workers according to the modified order.
8. A moving order matching device, characterized in that: The moving order matching device comprises an acquisition module (31) and a processing module (32), wherein: The acquisition module (31) is used to receive a moving order sent by a user device; The processing module (32) is used to generate a user profile of the user corresponding to the user device according to the moving order, wherein the user profile includes the moving time, the moving starting point, the moving end point, the item type and the user demand; The acquisition module (31) is also used to acquire the service information of the moving staff; The processing module (32) is further used to generate a service profile of the moving staff according to the service information, wherein the service profile includes service time, service area, service type and order evaluation; The processing module (32) is further used to match the service profile with the user profile to obtain a matching result, wherein the matching result includes a target moving worker; The processing module (32) is also used to send the moving order to the target moving worker, and send the matching result to the user.
9. An electronic device, characterized in that: The electronic device comprises a processor (41), a memory (45), a user interface (43) and a network interface (44), wherein the memory (45) is used to store instructions, the user interface (43) and the network interface (44) are both used to communicate with other devices, and the processor (41) is used to execute the instructions stored in the memory (45) so that the electronic device executes the method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is performed.
Citation Information
Patent Citations
Commodity recommendation method and device based on family and community shopping big data
CN111415219A
Work order allocation method and device, equipment and storage medium
CN114943443A
Comprehensive recommendation method and device based on user portrait, equipment and storage medium
CN117009670A
Household service intelligent recommendation method
CN118193847A
Advertisement distribution system using database constructed from housing purchase information
JP2018077898A
Cited By
Data matching method and device in charging facility verification and electronic equipment
CN119961327A
Data matching method, device and electronic equipment in charging facility verification
CN119961327B
Order matching method and system based on machine learning
CN120579787A
A machine learning based order matching method and system
CN120579787B
Construction order intelligent distribution mode driven by AI bidding mechanism
CN121052616A
