Space-time crowdsourcing service planning method and platform based on capability constraint, and electronic equipment

Abstract

The invention relates to the field of spatio-temporal data processing, in particular to a spatio-temporal crowdsourcing service planning method and platform based on capability constraint and electronic equipment, and the method can fully excavate and utilize cooperation potential of workers, realize accurate matching of task requirements and skills of the workers, optimize task completion paths of the workers, and improve working efficiency of the workers. The task completion rate of the platform, the participation degree of workers and the satisfaction degree of the users are remarkably improved, and meanwhile higher commercial value is created for the platform and the workers; the method has a wide application prospect, can be applied to various types of space-time crowdsourcing service platforms such as take-out, express delivery, housekeeping, maintenance and the like, and is expected to become one of key enabling technologies of smart cities and digital economy times.

Description

Technical Field

[0001] The present invention relates to the technical field of spatio-temporal data processing, and particularly to a spatio-temporal crowdsourcing service planning method, platform and electronic device based on ability constraints. Background Art

[0002] With the rapid development of the sharing economy and mobile Internet, spatio-temporal crowdsourcing service platforms have been widely used. The platform realizes the real-time allocation and efficient completion of tasks by allocating service requests (i.e., tasks) to service providers (i.e., workers); however, how to efficiently and accurately allocate tasks to workers under time and space constraints to maximize the benefits is one of the core challenges faced by the task allocation problem.

[0003] Currently, existing research mainly focuses on the following aspects:

[0004] 1) Task spatio-temporal attributes: Most research has considered spatio-temporal attributes such as the geographical location, start time, and end time of tasks, and explored how to allocate tasks to workers available in space and time. For example, existing matching algorithms based on task and worker locations improve task completion efficiency by minimizing the moving distance of workers to the task location.

[0005] 2) Worker spatio-temporal availability: The research has considered the geographical location and available working time periods of workers, and explored how to allocate tasks to them when they are available in space and time. For example, existing real-time task allocation algorithms based on the current location and moving speed of workers select appropriate workers by predicting the arrival time of workers.

[0006] However, existing spatio-temporal crowdsourcing task allocation methods still have the following limitations:

[0007] Firstly, most research assumes that a task can only be independently completed by one worker, ignoring the situation where a task can be completed by multiple workers collaborating; in practical applications, complex tasks often require multiple workers to collaborate to complete, and a single worker may not be competent. Therefore, considering the allocation mechanism for workers to collaborate to complete tasks is more in line with actual needs. Secondly, although some research has considered skill constraints, it has not considered the overall path planning of workers when completing a series of tasks; in actual operation, workers often need to complete multiple tasks in a certain order and route, rather than frequently shuttling between the platform and a single task location. The lack of optimization of the worker task chain path leads to waste of workers' time and energy, reducing task completion efficiency and workers' income. Summary of the Invention

[0008] In view of the above problems, embodiments of the present invention provide a spatio-temporal crowdsourcing service planning method, platform and electronic device based on ability constraints.

[0009] On the one hand, an implementation of the present invention provides a spatio-temporal crowdsourcing service planning method based on capacity constraints, which is applied to a spatio-temporal crowdsourcing service platform. The spatio-temporal crowdsourcing service platform includes two roles: tasks and workers. The method includes:

[0010] Determine the worker attributes of each worker, and establish a tuple w = <id w , time w , loc w , v w ,, ψ w > to represent the attributes of each worker, where id w represents the unique identifier of worker w, used to distinguish different workers; time w represents the available working time period of worker w, and the start time and departure time are represented by [start_time, end_time]; loc w represents the real-time geographical location of worker w, represented by a <longitude, latitude> tuple; v w is the moving speed of worker w; ψ w represents the set of skills mastered by worker w, Ψ represents the set of skill capabilities;

[0011] Determine the task attributes of each task, and establish a tuple t = <id t , type, loc t , time t , ψ t , r t > to represent the attributes of each task, where id t represents the unique identifier of task t, used to distinguish different tasks; type represents the type of task t, loc t represents the geographical location of task t, represented by a <longitude, latitude> tuple; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the set of skills required to complete task t, r t represents the reward that can be obtained for completing task t;

[0012] Establish boundary conditions during the process of workers serving tasks. For each task t, generate a set of service workers by matching the availability of the working time period and geographical location of each worker w, as well as the skill matching degree, and aiming to maximize the revenue of the crowdsourcing service platform;

[0013] Add the geographical location loc t of task t to the working path of the workers in the set of service workers in sequence to complete the service planning. The working path includes the geographical location order of the workers serving the tasks.

[0014] Optionally, the boundary conditions include:

[0015] Service time condition: The available working period of worker w needs to cover the working period of task t, that is, the worker should appear on the platform before the task starts and leave the platform after the task is completed, expressed as

[0016] Service space condition: Worker w arrives at loc before task t t , considering the movement cost of the worker, it is necessary to satisfy dis(loc w , loc t ) ≤ v w ×Δt, where Δt is the time difference between two tasks;

[0017] Exclusive condition: For the same worker w, if the working periods of two tasks t 1 and t 2 overlap, then worker w can only choose one of the tasks;

[0018] Capability condition: The set of skills of all workers W′ serving task t should include the skills required by the task, that is

[0019] Optionally, the process of generating the set of service workers includes:

[0020] S1. Preparation stage

[0021] S1-1. Sort all tasks t ∈ T in descending order according to the return r t ;

[0022] S1-2. Initialize the working path S of all workers w ∈ W w = {loc w};

[0023] S2. Calculation stage

[0024] S2-1. Enumerate all tasks t according to the sorted T;

[0025] S2-2. For each task t, generate the candidate set of workers W c according to the availability in space and time;

[0026] S2-3. For each task t, generate the set of service workers W′ in the candidate set of workers W c according to the skill matching degree.

[0027] Optionally, the process of generating the candidate set of workers W c in S2-2 includes:

[0028] S2-2-1. Initialize Wc = φ;

[0029] S2-2-2. Traverse all workers w ∈ W. If a worker meets the following two conditions, retain the worker w;

[0030] Condition 1: There is an intersection between the skills of the worker and the skills required for the task, i.e., ψ w ∩ ψ t ≠ φ;

[0031] Condition 2: The worker can arrive at the task location on time, i.e., after appending or inserting the task geographical location into S w the entire work path still meets the service time condition, service space condition, and exclusive condition;

[0032] S2-2-3. Add the worker w to W c , and sort them in ascending order according to the movement time of the workers. Among them, workers with the same time are sorted in descending order according to |ψ w ∩ ψ t .

[0033] Optionally, the process of generating the service worker set W' in S2-3 includes:

[0034] S2-3-1. Initialize W' = φ;

[0035] S2-3-2. Traverse all workers w ∈ W c ;

[0036] S2-3-3. If after adding w to W', the intersection between the workers in W' and ψ t increases, then retain w;

[0037] S2-3-4. If meets then remove w' from W'.

[0038] Another aspect of the implementation of the present invention also provides a spatio-temporal crowdsourcing service planning platform based on capacity constraints, including:

[0039] Worker attribute determination module, used to determine the worker attributes of each worker and establish a multi-tuple w = <id w , time w , loc w , v W ,, ψ w > to represent the attributes of each worker, where id w represents the unique identifier of the worker w, used to distinguish different workers; time w represents the workable time period of the worker w, and the start time and departure time are represented by [start_time, end_time]; loc wRepresents the real-time geographical location of worker w, represented by a <longitude, latitude> pair; v w Is the moving speed of worker w; ψ w Represents the set of skills mastered by worker w, Ψ represents the set of skill capabilities;

[0040] Task attribute determination module, used to determine the task attributes of each task and establish a multi-tuple t = <id t , type, loc t , time t , ψ t , r t > to represent each task attribute, where id t Represents the unique identifier of task t, used to distinguish different tasks; type represents the type of task t, and loc t Represents the geographical location of task t, represented by a <longitude, latitude> pair; time t Represents the working time period of task t, represented by [start_time, end_time]; ψ t Represents the set of skills required to complete task t, r t Represents the reward that can be obtained for completing task t;

[0041] Service worker determination module, used to establish boundary conditions during the process of workers serving tasks. For each task t, generate a set of service workers by matching the availability of the working time period and geographical location of each worker w, as well as the skill matching degree, with the goal of maximizing the revenue of the crowdsourcing service platform;

[0042] Working path planning module, used to add the geographical location loc of task t t to the working paths of the workers in the set of service workers in sequence to complete the service planning. The working path includes the geographical location order of the workers serving tasks.

[0043] Optionally, the boundary conditions include:

[0044] Service time condition: The available working time period of worker w needs to cover the working time period of task t, that is, the worker needs to appear on the platform before the task starts and leave the platform after the task is completed, expressed as

[0045] Service space condition: Worker w arrives at loc before task t starts t , considering the moving cost of the worker, it needs to satisfy dis(loc w , loc t ) ≤ v w ×Δt, where Δt is the time difference between two tasks;

[0046] Exclusive condition: For the same worker w, if the working time periods of two tasks t 1 and t 2 overlap, then the worker w can only choose one of the tasks;

[0047] Capability condition: The set of skills of all workers W′ for a service task t should include the skills required by the task, that is

[0048] Optionally, a service worker determination module, specifically used for

[0049] S1. Preparation stage

[0050] S1-1. Sort all tasks t∈T in descending order according to the reward r t ;

[0051] S1-2. Initialize the working path S of all workers w∈W w ={loc w};

[0052] S2. Calculation stage

[0053] S2-1. Enumerate all tasks t according to the sorted T;

[0054] S2-2. For each task t, generate a candidate set of workers W c ;

[0055] S2-2-1. Initialize W c =φ;

[0056] S2-2-2. Traverse all workers w∈W. If the worker meets the following two conditions, retain the worker w;

[0057] Condition 1: There is an intersection between the skills of the worker and the skills required by the task, that is ψ w ∩ψ t ≠φ;

[0058] Condition 2: The worker can arrive at the task location on time, that is, after appending or inserting the task geographical location into S w , the entire working path still meets the service time condition, service space condition, and exclusive condition;

[0059] S2-2-3. Add the worker w to W c , and sort them in ascending order according to the movement time of the worker. Among the workers with the same time, sort them in descending order according to |ψ w ∩ψ t |;

[0060] S2-3. For each task t, in the candidate set of workers W cGenerate a set of service workers \(W'\) according to the skill matching degree;

[0061] S2-3-1. Initialize \(W'=\varnothing\);

[0062] S2-3-2. Traverse all workers \(w\in W\) c ;

[0063] S2-3-3. If after adding \(w\) to \(W'\), the intersection of the workers in \(W'\) and \(\psi\) t increases, then retain \(w\);

[0064] S2-3-4. If satisfies then remove \(w'\) from \(W'\).

[0065] In another aspect of the implementation of the present invention, an electronic device is further provided, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus;

[0066] The memory is used to store executable instructions of the processor;

[0067] The processor, when executing the instructions stored on the memory, implements the above-mentioned spatio-temporal crowdsourcing service planning method based on ability constraints.

[0068] Compared with the prior art, the beneficial effects of the present invention are as follows: 1) Multi-worker collaboration: fully considers the situation of multiple workers collaborating to complete tasks. Different from existing research, the present invention is no longer limited to assigning tasks to a single worker, but by evaluating the spatio-temporal availability and skill matching degree of worker combinations, more tasks can be completed in a timely manner and with high quality;

[0069] 2) Skill constraint and matching: The present invention comprehensively considers the skill requirements of tasks and the skill matching degree of workers (combinations) during task assignment, and realizes the accurate matching of task requirements and worker skills.

[0070] 3) Optimization of the worker task chain path: The present invention breaks through the limitation of single task assignment and considers the task completion path of workers from the perspective of overall optimization. Specifically, a series of tasks completed by a worker within a period of time are regarded as a task chain, and a work path optimization algorithm is designed to optimize the order and route of the worker to complete the task chain on the premise of meeting the spatio-temporal constraints and skill requirements of each task, so as to maximize the total income of the worker.

[0071] In summary, the present invention can fully exploit and utilize the collaborative potential of workers, achieve an accurate match between task requirements and worker skills, and optimize the task completion path of workers. While significantly improving the task completion rate, worker participation, and user satisfaction of the platform, it also creates greater commercial value for the platform and workers; it has broad application prospects and can be applied to various types of spatio-temporal crowdsourcing service platforms such as food delivery, express delivery, housekeeping, and maintenance, and is expected to become one of the key enabling technologies in the era of smart cities and the digital economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, and do not limit the present invention. In the drawings:

[0073] Figure 1 is a schematic flow chart of a spatio-temporal crowdsourcing service planning method based on ability constraints provided by an embodiment of the present invention;

[0074] Figure 2 is a block diagram of the implementation of a spatio-temporal crowdsourcing service planning platform based on ability constraints provided by an embodiment of the present invention;

[0075] Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0076] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with the embodiments and the drawings. Herein, the illustrative embodiments and descriptions thereof of the present invention are used to explain the present invention, but do not limit the present invention.

[0077] See Figure 1 , a spatio-temporal crowdsourcing service planning method based on ability constraints provided by an embodiment of the present invention is applied to a spatio-temporal crowdsourcing service platform. The spatio-temporal crowdsourcing service platform includes two roles: tasks and workers. The method includes:

[0078] Step 1: Determine the worker attributes of each worker and establish a multi-tuple w = <id w , time w , loc w , v W ,, ψ w > to represent the attributes of each worker, where id w represents the unique identifier of worker w, used to distinguish different workers; time w represents the available working time period of worker w, and the start time and departure time are represented by [start_time, end_time]; loc w represents the real-time geographical location of worker w, represented by a <longitude, latitude> binary tuple; vw is the moving speed of worker w; ψ w represents the set of skills mastered by worker w, Ψ represents the set of skill capabilities;

[0079] Step 2: Determine the task attributes of each task and establish a tuple t = <id t , type, loc t , time t , ψ t , r t > to represent each task attribute, where id t represents the unique identifier of task t, used to distinguish different tasks; type represents the type of task t, and loc t represents the geographical location of task t, represented by a <longitude, latitude> tuple; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the set of skills required to complete task t, r t represents the reward that can be obtained for completing task t;

[0080] Step 3: Establish the boundary conditions during the process of workers serving tasks. For each task t, generate a set of service workers by matching the availability of the working time period and geographical location of each worker w, as well as the skill matching degree, with the goal of maximizing the revenue of the crowdsourcing service platform;

[0081] Step 4: Add the geographical location loc of task t t to the working path of the workers in the set of service workers in sequence to complete the service planning. The working path includes the order of the geographical locations of the workers' service tasks.

[0082] During implementation, the boundary conditions include:

[0083] Service time condition: The available working time period of worker w needs to cover the working time period of task t, that is, the worker needs to appear on the platform before the task starts and leave the platform after the task is completed, expressed as

[0084] Service space condition: Worker w arrives at loc before task t starts t , considering the moving cost of the worker, it needs to satisfy dis(loc w , loc t ) ≤ v w ×Δt, where Δt is the time difference between two tasks;

[0085] Exclusive condition: For the same worker w, if two tasks t 1 and t2 If the working time periods overlap, worker w can only choose one of the tasks;

[0086] Capability condition: The set of skills of all workers W' for service task t should include the skills required by the task, that is,

[0087] In implementation, the process of generating the set of service workers includes:

[0088] S1. Preparation stage

[0089] S1-1. Sort all tasks t ∈ T in descending order according to the reward r t ; That is, prioritize tasks with high rewards to ensure maximum daily income;

[0090] S1-2. Initialize the working path S of all workers w ∈ W w = {loc w}; That is, use the initial positions of the workers for initialization;

[0091] S2. Calculation stage

[0092] S2-1. Enumerate all tasks t according to the sorted T;

[0093] S2-2. For each task t, generate the candidate set of workers W according to the availability in space and time c ;

[0094] S2-3. For each task t, generate the set of service workers W' in the candidate set of workers W c according to the skill matching degree.

[0095] Specifically, the process of generating the candidate set of workers W in S2-2 c includes:

[0096] S2-2-1. Initialize W c = φ;

[0097] S2-2-2. Traverse all workers w ∈ W. If the worker meets the following two conditions, retain worker w;

[0098] Condition 1: There is an intersection between the skills of the worker and the skills required by the task, that is, ψ w ∩ψ t ≠ φ;

[0099] Condition 2: The worker can arrive at the task point on time, that is, after appending or inserting the geographical location of the task into S w the entire working path still meets the service time condition, service space condition, and exclusive condition;

[0100] S2-2-3. Add worker w to Wc and sort them in ascending order according to the moving time of the workers. Among them, for workers with the same time, they are sorted in descending order according to |ψ w ∩ψ t |.

[0101] Specifically, the process of generating the set of service workers W' in S2-3 includes:

[0102] S2-3-1. Initialize W' = φ;

[0103] S2-3-2. Traverse all workers w ∈ W c ;

[0104] S2-3-3. If after adding w to W', the intersection of the workers in W' and ψ t increases, then retain w;

[0105] S2-3-4. If satisfies then remove w' from W'; that is, the skills of the newly added worker can cover the skills of the existing workers. In fact, the skills of the existing worker are no longer useful, and it doesn't matter whether he is there or not. So the existing worker can be excluded.

[0106] See Figure 2 , this embodiment of the present invention also provides a spatio-temporal crowdsourcing service planning platform based on ability constraints, including:

[0107] Worker attribute determination module, used to determine the worker attributes of each worker, and establish a multi-tuple w = <id w , time w , loc w , v W ,, ψ w > to represent the attributes of each worker, where id w represents the unique identifier of worker w, used to distinguish different workers; time w represents the workable time period of worker w, and the start time and departure time are represented by [start_time, end_time]; loc w represents the real-time geographical location of worker w, represented by a <longitude, latitude> binary tuple; v w is the moving speed of worker w; ψ w represents the set of skills mastered by worker w, Ψ represents the set of skill capabilities;

[0108] Task attribute determination module, used to determine the task attributes of each task, and establish a multi-tuple t = <id t , type, loc t , timet , ψ t , r t >, where id t represents the unique identifier of task t, used to distinguish different tasks; type represents the type of task t, and loc t represents the geographical location of task t, represented by a <longitude, latitude> tuple; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the set of skills required to complete task t, r t represents the reward that can be obtained for completing task t;

[0109] The service worker determination module is used to establish the boundary conditions during the process of workers serving tasks. For each task t, by matching the availability of the working time period and geographical location of each worker w, as well as the skill matching degree, and aiming at maximizing the revenue of the crowdsourcing service platform, a set of service workers is generated;

[0110] The working path planning module is used to add the geographical location loc of task t t to the working path of the workers in the set of service workers in sequence to complete the service planning. The working path includes the geographical location order of the workers' service tasks.

[0111] During implementation, the boundary conditions include:

[0112] Service time condition: The available working time period of worker w needs to cover the working time period of task t, that is, the worker should appear on the platform before the task starts and leave the platform after the task is completed, expressed as

[0113] Service space condition: Worker w arrives at loc before task t starts t , considering the movement cost of the worker, it is necessary to satisfy dis(loc w , loc t ) ≤ v w ×Δt, where Δt is the time difference between two tasks;

[0114] Exclusive condition: For the same worker w, if the working time periods of two tasks t 1 and t 2 overlap, then worker w can only choose one of the tasks;

[0115] Capability condition: The set of skills of all workers W′ for service task t should include the skills required by the task, that is

[0116] During implementation, the service worker determination module is specifically used for

[0117] S1. Preparation stage

[0118] S1-1. Sort all tasks \(t\in T\) in descending order according to the reward \(r\). t Descending order;

[0119] S1-2. Initialize the working path \(S\) of all workers \(w\in W\) as \(\{loc\}\). w =\(\{loc\}\); w \(\}\);

[0120] S2. Calculation stage

[0121] S2-1. Enumerate all tasks \(t\) according to the sorted \(T\).

[0122] S2-2. For each task \(t\), generate a candidate set \(W\) of workers based on the availability in space and time. c ;

[0123] S2-2-1. Initialize \(W = \varnothing\). c =\(\varnothing\);

[0124] S2-2-2. Traverse all workers \(w\in W\). If the worker meets the following two conditions, retain the worker \(w\).

[0125] Condition 1: There is an intersection between the skills of the worker and the skills required for the task, i.e., \(\psi\cap\psi\neq\varnothing\). w \(\cap\psi\); t \(\neq\varnothing\);

[0126] Condition 2: The worker can arrive at the task location on time. After appending or inserting the task geographical location into \(S\), the entire working path still meets the service time condition, service space condition, and exclusive condition. w In the middle, the entire working path still meets the service time condition, service space condition, and exclusive condition;

[0127] S2-2-3. Add the worker \(w\) to \(W\), and sort them in ascending order according to the movement time of the worker. Among the workers with the same time, sort them in descending order according to \(|\psi\cap\psi|\). c , and sort them in ascending order according to the movement time of the worker. Among the workers with the same time, sort them in descending order according to \(|\psi\cap\psi|\); w \(\cap\psi\); t |\(\cap\psi\)|\(\);

[0128] S2-3. For each task \(t\), generate a set \(W'\) of service workers in the candidate set \(W\) of workers according to the skill matching degree. c In the middle, generate a set \(W'\) of service workers according to the skill matching degree;

[0129] S2-3-1. Initialize \(W'=\varnothing\).

[0130] S2-3-2. Traverse all workers \(w\in W\). c ;

[0131] S2-3-3. If the intersection of the workers in \(W'\) and \(\psi\) increases after adding \(w\) to \(W'\), then retain \(w\). t The intersection of the workers in \(W'\) and \(\psi\) increases, then retain \(w\);

[0132] S2-3-4. If is satisfied then move w′ out of W′.

[0133] Applying the solution provided by the present invention can fully explore and utilize the collaborative potential of workers, achieve an accurate match between task requirements and worker skills, and optimize the task completion path of workers. While significantly improving the task completion rate, worker participation, and user satisfaction of the platform, it also creates greater commercial value for the platform and workers; it has broad application prospects and can be applied to various types of spatio-temporal crowdsourcing service platforms such as takeout, express delivery, housekeeping, and maintenance, and is expected to become one of the key enabling technologies in the era of smart cities and the digital economy.

[0134] The embodiment of the present invention also provides an electronic device, as Figure 3 shown, including a processor 001, a communication interface 002, a memory 003, and a communication bus 004. Among them, the processor 001, the communication interface 002, and the memory 003 complete communication with each other through the communication bus 004.

[0135] The memory 003 is used to store computer programs.

[0136] When the processor 001 is used to execute the program stored on the memory 003, it implements the above spatio-temporal crowdsourcing service planning method based on capacity constraints, including:

[0137] Determine the worker attributes of each worker and establish a tuple w = <id w , time w , loc w , v W， , ψ w > to represent the attributes of each worker, where id w represents the unique identifier of worker w, used to distinguish different workers; time w represents the available working time period of worker w, and the start time and departure time are represented by [start_time, end_time]; loc w represents the real-time geographical location of worker w, represented by a <longitude, latitude> tuple; v w is the moving speed of worker w; ψ w represents the set of skills mastered by worker w, Ψ represents the set of skill capabilities;

[0138] Determine the task attributes of each task and establish a tuple t = <id t , type, loc t , time t , ψ t , r t>, where id t represents the unique identifier of task t, used to distinguish different tasks; type represents the type of task t, loc t represents the geographical location of task t, represented by a <longitude, latitude> tuple; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the set of skills required to complete task t, r t represents the reward that can be obtained for completing task t;

[0139] Establish boundary conditions in the process of workers serving tasks. For each task t, generate a set of service workers by matching the availability of the working time period and geographical location of each worker w, as well as the skill matching degree, with the goal of maximizing the revenue of the crowdsourcing service platform;

[0140] Add the geographical location loc of task t t to the working paths of the workers in the set of service workers in sequence to complete the service planning. The working path includes the geographical location order of the workers' service tasks.

[0141] Applying the solution provided by the present invention can fully exploit and utilize the collaborative potential of workers, achieve accurate matching of task requirements and workers' skills, and optimize the task completion paths of workers. While significantly improving the platform task completion rate, worker participation, and user satisfaction, it also creates greater commercial value for the platform and workers; it has broad application prospects and can be applied to various types of spatio-temporal crowdsourcing service platforms such as food delivery, express delivery, housekeeping, and maintenance, and is expected to become one of the key enabling technologies in the era of smart cities and the digital economy.

[0142] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity, only a thick line is shown in the figure, but it does not mean that there is only one bus or one type of bus.

[0143] The communication interface is used for communication between the above electronic device and other devices.

[0144] The memory may include a Random Access Memory (RAM), or may also include a Non-Volatile Memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0145] The aforementioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0146] In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present invention are generated in whole or in part. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium that the computer can access, or a data storage device such as a server or data center that includes one or more integrated available media. The available medium may be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a Solid State Disk (SSD)).

[0147] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0148] Each embodiment in this specification is described in a related manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the platform and electronic device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, reference can be made to the partial description of the method embodiments.

[0149] The above are only the preferred embodiments of the present invention and are not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are all included in the protection scope of the present invention.

Claims

1. A spatiotemporal crowdsourcing service planning method based on capability constraints, characterized in that: Applied to a spatiotemporal crowdsourcing service platform, the spatiotemporal crowdsourcing service platform includes two roles: tasks and workers. The method includes: Determine the worker attributes of each worker and create a tuple w = < id to represent each worker attribute w , time w ,loc w , v w , ψ w >, where id w Represents the unique identifier of worker w, used to distinguish different workers; time w Indicates the working time period of worker w, the start time and the leave time are represented by [start_time, end_time]; loc w represents the real-time geographic location of worker w, represented by a tuple of <longitude, latitude>; v w is the moving speed of worker w; ψ w represents the skill set mastered by worker w, Ψ represents the set of skill capabilities; Determine the task attributes of each task and create a tuple t=<id for representing each task attribute t , type, loc t , time t , ψ t , r t >, where id t It indicates the unique identifier of task t, which is used to distinguish different tasks; type indicates the type of task t, loc t Indicates the geographical location of task t, represented by a tuple of <longitude, latitude>; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the skill set required to complete task t, r t Indicates the reward that can be obtained by completing task t; Establish boundary conditions in the process of worker service tasks. For each task t, generate a set of service workers by matching the working time and geographical location of each worker w, as well as the skill matching degree, and aiming to maximize the benefits of the crowdsourcing service platform. Set the geographical location of task t to loc t The service planning is completed by sequentially adding the work paths of the workers in the service worker set, and the work paths contain the geographical location sequence of the workers' service tasks.

2. The method for planning spatiotemporal crowdsourcing services based on capability constraints according to claim 1, characterized in that: Boundary conditions include: Service time condition: The available working time of worker w needs to cover the working time of task t, that is, the worker must appear on the platform before the task starts and leave the platform after the task is completed, which is expressed as Service space condition: Worker w arrives at loc before task t starts t , considering the worker's mobility cost, it is necessary to satisfy dis(loc w ,loc t )≤v w ×Δt, where Δt is the time difference between two tasks; Exclusive condition: For the same worker w, if the working time periods of two tasks t1 and t2 overlap, the worker w can only choose one of the tasks; Capability condition: The skill set of all workers W′ serving task t should include the skills required by the task, that is, 3. The method for planning spatiotemporal crowdsourcing services based on capability constraints as claimed in claim 2, characterized in that: The process of generating a collection of service workers includes: S1. Preparation S1-1. For all tasks t∈T, the reward r t Sort in descending order; S1-2. Initialize the work path S of all workers w∈W w ={loc w }; S2. Calculation phase S2-1, enumerate all tasks t according to the sorted T; S2-2. For each task t, generate a set of worker candidates W based on the availability of time and space c ; S2-3. For each task t, in the worker candidate set W c The service worker set W′ is generated according to the skill matching degree.

4. The method for planning spatiotemporal crowdsourcing services based on capability constraints as claimed in claim 3, characterized in that: Generate the worker candidate set W in S2-2 c The process includes: S2-2-1. Initialize W c =φ; S2-2-2. Traverse all workers w∈W. If the worker meets the following two conditions, keep the worker w; Condition 1: The worker’s skills and the skills required by the task have an intersection, that is, ψ w ∩ψ t ≠φ; Condition 2: Workers can arrive at the task point on time, that is, the task location is appended or inserted into S w After the middle, the entire work path still meets the service time condition, service space condition and exclusivity condition; S2-2-3. Add worker w to W c , and sorted in ascending order according to the workers' moving time, where workers with the same time are sorted according to |ψ w ∩ψ t |Sort in descending order.

5. The method for planning spatiotemporal crowdsourcing services based on capability constraints as claimed in claim 4, characterized in that: The process of generating the service worker set W′ in S2-3 includes: S2-3-1, initialize W′=φ; S2-3-2. Traverse all workers w∈W c ; S2-3-3. If w is added to W′, the workers in W′ and ψ t The intersection of increases, so keep w; S2-3-4, if satisfy Then move w' out of W'.

6. A spatiotemporal crowdsourcing service planning platform based on capability constraints, characterized in that: include: The worker attribute determination module is used to determine the worker attributes of each worker and establish a multi-tuple w=<id for representing each worker attribute w , time w ,loc w , v w , ψ w >, where id w Represents the unique identifier of worker w, used to distinguish different workers; time w Indicates the working time period of worker w, the start time and the leave time are represented by [start_time, end_time]; loc w represents the real-time geographic location of worker w, represented by a tuple of <longitude, latitude>; v w is the moving speed of worker w; ψ w represents the skill set mastered by worker w, Ψ represents the set of skill capabilities; The task attribute determination module is used to determine the task attributes of each task and establish a multi-tuple t=<id for representing each task attribute t , type, loc t , time t , ψ t , r t >, where id t It indicates the unique identifier of task t, which is used to distinguish different tasks; type indicates the type of task t, loc t Indicates the geographical location of task t, represented by a tuple of <longitude, latitude>; time t represents the working time period of task t, represented by [start_time, end_time]; ψ t represents the skill set required to complete task t, r t Indicates the reward that can be obtained by completing task t; The service worker determination module is used to establish the boundary conditions of the workers in the process of serving tasks. For each task t, a set of service workers is generated by matching the working time period and geographical location of each worker w, as well as the skill matching degree, with the goal of maximizing the benefits of the crowdsourcing service platform. The work path planning module is used to locate the geographical location of task t t The service planning is completed by sequentially adding the work paths of the workers in the service worker set, and the work paths contain the geographical location sequence of the workers' service tasks.

7. The spatiotemporal crowdsourcing service planning platform based on capability constraints as claimed in claim 6, characterized in that: Boundary conditions include: Service time condition: The available working time of worker w needs to cover the working time of task t, that is, the worker must appear on the platform before the task starts and leave the platform after the task is completed, which is expressed as Service space condition: Worker w arrives at loc before task t starts t , considering the worker's mobility cost, it is necessary to satisfy dis(loc w ,loc t )≤v w ×Δt, where Δt is the time difference between two tasks; Exclusive condition: For the same worker w, if the working time periods of two tasks t1 and t2 overlap, the worker w can only choose one of the tasks; Capability condition: The skill set of all workers W′ serving task t should include the skills required by the task, that is, 8. The spatiotemporal crowdsourcing service planning platform based on capability constraints as claimed in claim 7, characterized in that: Service worker identification module, specifically for S1. Preparation S1-1. For all tasks t∈T, the reward r t Sort in descending order; S1-2. Initialize the work path S of all workers w∈W w ={loc w }; S2. Calculation phase S2-1, enumerate all tasks t according to the sorted T; S2-2. For each task t, generate a set of worker candidates W based on the availability of time and space c ; S2-3. For each task t, in the worker candidate set W c The service worker set W′ is generated according to the skill matching degree.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; A memory for storing processor executable instructions; A processor, for implementing the method steps described in any one of claims 1 to 5 when executing instructions stored in a memory.

Images