Property work planning method and device based on artificial intelligence technology

Abstract

The invention discloses a property work planning method and device based on an artificial intelligence technology. The method comprises the following steps: establishing a work planning network based on a graph neural network technology; the work planning network comprises a plurality of task nodes in a target area and task paths among the task nodes; determining a target function according to the work planning network; collecting task data in a target area, inputting the task data into the work planning network, and determining a work planning scheme according to the task node and the task path by using the target function; based on the artificial intelligence technology, the work planning scheme is formulated, dimension factors such as time consumption, constraint conditions, resource consumption and the like can be considered, and the work route is comprehensively scored, so that the overall efficiency is highest; the defects of low efficiency and insufficient intelligent degree in the traditional mode are avoided.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular, to a property work planning method and device based on artificial intelligence technology. Background Art

[0002] In daily property service work, various service personnel and various service contents are involved. Moreover, different service contents / work contents have different priority orders and time limits. In actual work, generally, corresponding work plans need to be formulated in advance for the work scope of each staff member. That is, to determine the time arrangement of the staff member within a period of time (such as within one day).

[0003] In the prior art, such work plans often rely on manual formulation. However, due to the large number of relevant personnel, work contents and various variables, and the actual situation is relatively complex, the process of completing relevant overall planning and formulating work plans is rather cumbersome, time-consuming, and requires a large amount of manpower.

[0004] In some cases, the work plan can be formulated by using an office system (Office Automation, i.e., OA system). However, an ordinary office system can only formulate work plans relying on fixed programs, the mechanism is very rigid, lacks the ability to conduct targeted analysis for specific situations, and cannot make rapid adjustments in combination with sudden special events and real-time events.

[0005] That is to say, in the prior art, there is a lack of a high-efficient, intelligent and highly adaptable work plan formulation scheme. Summary of the Invention

[0006] The present invention provides a property work planning method and device based on artificial intelligence technology, and realizes a more intelligent work plan based on artificial intelligence technology.

[0007] In a first aspect, the present invention provides a property work planning method based on artificial intelligence technology, including:

[0008] Establishing a work planning network based on graph neural network technology; in the work planning network, there are multiple task nodes within the target area and task paths between the task nodes;

[0009] Determining an objective function according to the work planning network;

[0010] Collecting task data within the target area, inputting the task data into the work planning network, and using the objective function to determine a work planning scheme according to the task nodes and the task paths.

[0011] Preferably, establishing the work planning network based on graph neural network technology includes:

[0012] Determine the task nodes within the target area and the task paths between the task nodes;

[0013] Configure a weight coefficient for the task path according to the passing efficiency of the task path;

[0014] Establish the work planning network based on the task nodes, the task paths, and the weight coefficient.

[0015] Preferably, the objective function in establishing the work planning network includes:

[0016] Establish the objective function according to the time evaluation item, the constraint violation evaluation item, and the resource consumption evaluation item.

[0017] Preferably, the target data includes:

[0018] Static basic data and dynamic real-time data.

[0019] Preferably, the step of determining the work planning scheme according to the task nodes and the task paths by using the objective function includes:

[0020] In the work planning network, determine multiple alternative schemes; each of the alternative schemes includes a task line composed of task nodes and task paths;

[0021] Determine the time evaluation score, the constraint violation evaluation score, and the resource consumption evaluation score of each task line;

[0022] Use the objective function, the time evaluation score, the constraint violation evaluation score, and the resource consumption evaluation score to determine the comprehensive score of each alternative scheme;

[0023] Determine the work planning scheme according to the comprehensive score.

[0024] Preferably, after determining the work planning scheme, it further includes:

[0025] When an emergency occurs, determine the temporary nodes and temporary paths of the emergency in the work planning network;

[0026] Determine the emergency planning scheme according to the temporary nodes, the temporary paths, and the work planning scheme.

[0027] Preferably, the step of determining the emergency planning scheme according to the temporary nodes, the temporary paths, and the work planning scheme includes:

[0028] Determine the remaining nodes in the work planning scheme and the task paths corresponding to the remaining nodes;

[0029] Determine the emergency planning plan according to the temporary nodes, the temporary paths, the remaining nodes, and the task paths corresponding to the remaining nodes.

[0030] In a second aspect, the present invention provides a property work planning device based on artificial intelligence technology, which is characterized by including:

[0031] A network establishment module, configured to establish a work planning network based on graph neural network technology; in the work planning network, a plurality of task nodes within the target area and task paths between the task nodes are included;

[0032] An objective function module, configured to determine an objective function according to the work planning network;

[0033] A plan formulation module, configured to collect task data within the target area, input the task data into the work planning network, and use the objective function to determine a work planning plan according to the task nodes and the task paths.

[0034] In a third aspect, the present invention provides a readable medium, including execution instructions. When a processor of an electronic device executes the execution instructions, the electronic device executes the method described in any one of the first aspects.

[0035] In a fourth aspect, the present invention provides an electronic device, including a processor and a memory storing execution instructions. When the processor executes the execution instructions stored in the memory, the processor executes the method described in any one of the first aspects.

[0036] The present invention provides a property work planning method and device based on artificial intelligence technology. Based on artificial intelligence technology, the formulation of a work planning plan is realized, and factors such as time consumption, constraint conditions, and resource consumption can be considered, and a comprehensive score is given to the work route, so as to achieve the highest overall efficiency; the defects of low efficiency and insufficient intelligence in the traditional method are avoided.

[0037] The further effects of the above non-conventional preferred methods will be described in combination with specific embodiments below. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the existing technical solutions, the following will briefly introduce the drawings required for use in the description of the embodiments or the existing technical solutions. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1A flowchart of a property work planning method based on artificial intelligence technology provided by an embodiment of the present invention;

[0040] Figure 2 A flowchart of another property work planning method based on artificial intelligence technology provided by an embodiment of the present invention;

[0041] Figure 3 A structural diagram of a property work planning device based on artificial intelligence technology provided by an embodiment of the present invention;

[0042] Figure 4 A structural diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0043] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] In daily property service work, various service personnel and various service contents are involved. Moreover, different service contents / work contents have different priority orders and time limits. In actual work, generally, a corresponding work plan needs to be formulated in advance for the work scope of each staff member. That is, to determine the time arrangement of the staff member within a period of time (such as within one day).

[0045] In other words, according to the work plan of the day, a "work route", or called an "inspection route", can be further formulated for the staff member. The inspection route covers multiple work tasks of the staff member, multiple work locations, and the execution order of each work task. Usually, if the staff member executes according to this, the highest efficiency can be guaranteed, and at the same time, each task can be completed within the specified time limit.

[0046] In the prior art, such work plans often rely on manual formulation. However, due to the large number of relevant personnel, work contents and various variables, the actual situation is relatively complex. Different work contents have different constraint conditions. Therefore, the process of completing relevant overall planning and formulating work plans is rather cumbersome, time-consuming, and requires a large amount of manpower.

[0047] In some cases, the work plan can be formulated by using an office automation system (OA system). However, an ordinary office automation system can only formulate a work plan relying on fixed procedures, with a very rigid mechanism, lacking the ability to conduct targeted analysis for specific situations, and unable to make rapid adjustments in combination with sudden special events and real-time events.

[0048] That is to say, in the prior art, there is a lack of a solution for formulating an efficient, intelligent, and highly adaptable work plan.

[0049] In view of this, the present invention provides a property work plan method based on artificial intelligence technology. See Figure 1 As shown, it is a specific embodiment of the property work plan method based on artificial intelligence technology provided by the present invention. In this embodiment, the method includes:

[0050] Step 101: Establish a work plan network based on graph neural network technology.

[0051] In the present invention, a model will be established based on the graph neural network (Graph Neural Network, abbreviated as GNN) in the field of artificial intelligence technology, that is, a work plan network will be established and targeted data training will be carried out on it. By using this work plan network, a work plan solution in property work can be determined more intelligently.

[0052] Specifically, the task nodes in the target area and the task paths between the task nodes can be determined. According to the passing efficiency of the task paths, weight coefficients are configured for the task paths. The work plan network is established according to the task nodes, the task paths, and the weight coefficients.

[0053] The target area refers to the physical area covered by property service work, such as the scope of a park. Within the target area, there are multiple task nodes in the target area and the task paths between the task nodes. Specifically, a work task (and its corresponding task location) can be abstracted as a task node in the GNN network. Each task node (that is, each work task) has corresponding features, which specifically include priority, time consumption, resource consumption, and various constraint conditions.

[0054] The paths between task nodes are abstracted as "edges" in the GNN network, which are also referred to as task paths in this embodiment. And physically speaking, each task path has different passing efficiencies. For example, the length of the actual distance, road conditions, and limiting factors (such as access control) will all affect the passing efficiency. According to the level of passing efficiency, weight coefficients can be configured for task paths. It can be understood that to ensure the overall efficiency, in the planning, task paths with higher passing efficiency are often given priority, and configuring weight coefficients is also to reflect this tendency.

[0055] The work planning network can be represented as G=(V, E). Where G represents the work planning network, V represents task nodes, and E represents task paths.

[0056] After establishing the work planning network, it is necessary to perform data training on it. Specifically, it can be combined with reinforcement learning algorithms or ant colony algorithms, and training can be carried out for specific goals such as "the shortest total inspection duration", "prioritized coverage of high-priority tasks", and "the lowest resource consumption".

[0057] Step 102: Determine the objective function according to the work planning network.

[0058] In the trained work planning network, a specific objective function can be obtained. Through the operation of the objective function, the work plan (specific route) can be formulated and screened.

[0059] In this embodiment, the objective function can be established according to the time evaluation item, constraint violation evaluation item, and resource consumption evaluation item.

[0060] Specifically, F = αT + βC + γR. Where F represents the objective function. T represents the time evaluation item, that is, the total time consumption of a specific plan. C represents the constraint violation evaluation item, that is, the number of times the constraint conditions of each task node are violated in a specific plan. R represents the resource consumption evaluation item, that is, the total amount of resources consumed under a specific plan. The so-called consumed resources can include energy consumption, consumable consumption, and other various related consumptions. α, β, and γ are hyperparameters obtained after data training.

[0061] Combined with the above objective function, it can be understood that the result F of the objective function is a "comprehensive score" for a specific plan, which reflects the comprehensive efficiency of a plan to a certain extent, referring to the time consumption, resource consumption, and the number of times of violating constraint conditions. Ideally, a route with the shortest time consumption, no violation of constraint conditions, and the least resource consumption should be found as the specific work plan. However, in some more complex situations, or in most actual situations, there is no absolutely ideal route. Therefore, it is often necessary to conduct comprehensive evaluation and consideration to find an optimal solution to maximize the overall efficiency.

[0062] In the prior art, the work plan is often determined manually or by a fixed process, and usually the optimal solution cannot be found. In this embodiment, a graph neural network and an objective function are used to implement this process.

[0063] Step 103: Collect task data in the target area, input the task data into the work plan network, and use the objective function to determine a work plan according to the task nodes and the task paths.

[0064] In specific practice, after establishing the work plan network and the objective function, the actual data in the target area can be substituted into them for calculation, so as to obtain a work plan. Therefore, the task data in the target area should be collected first. The target data includes static basic data and dynamic real-time data.

[0065] The static basic data includes an electronic map of the target area, which accurately marks the building layout and the position coordinates of various devices; the detailed attributes of the task nodes, including the device type, the specified inspection cycle, and the safety level classification; and also includes the relevant constraints when the steward performs tasks, such as the daily working hours limit, the weight and volume limits of the devices that can be carried, etc.

[0066] The dynamic real-time data includes the device operation status data and environmental parameter data, such as temperature, humidity, air quality, etc. fed back by real-time sensors; the past historical inspection records, which detail the time consumed for each inspection and the problem feedback found; the emergency event information, such as the temporary equipment failure repair request, the severe weather anomaly warning, etc.; and also the urgent inspection requirement for a specific area temporarily proposed by the owner.

[0067] For the collected task data, certain preprocessing can be performed, including using the spatial vector encoding technology to cleverly transform the geographical coordinates and device attributes into numerical features convenient for computer processing, laying a foundation for subsequent data analysis. By means of time series analysis, the rules in the historical inspection time-consuming data are mined, and accordingly a "prediction model for inspection point time consumption" is constructed to estimate the time required for future inspections. For the dynamic data, the real-time feature fusion technology is adopted to integrate different sources and different types of dynamic information to generate a dynamic constraint vector containing both time and space information, enabling the system to comprehensively and accurately grasp the real-time situation.

[0068] After determining the task data, multiple alternative solutions can be determined in the work planning network; each of the alternative solutions includes a task line composed of task nodes and task paths. Determine the time evaluation score, constraint violation evaluation score, and resource consumption evaluation score of each of the task lines; use the objective function, the time evaluation score, the constraint violation evaluation score, and the resource consumption evaluation score to determine the comprehensive score of each of the alternative solutions; determine the work planning solution according to the comprehensive score.

[0069] It should also be noted that in this embodiment, the work planning network can have the ability to model multiple constraint conditions through targeted data training. It can fully consider complex actual business constraints such as the physical strength limit of staff (stipulating that the continuous working hours shall not exceed 4 hours), equipment dependency relationships (certain inspection points that require specific tool detection must be continuously visited), time window limitations (for example, elevator machine room inspections need to avoid peak usage periods), etc., greatly improving the practicality and operability of the plan. It also has the ability of self-learning. By continuously collecting historical inspection data and feedback information during the actual execution process, such as the specific reasons for route delays, response records after the insertion of sudden tasks, etc., the internal parameters of the model are continuously optimized, and then the accuracy and reliability of the route planning are gradually improved. During the task assignment process, based on the skill tags possessed by each staff member, such as strong and weak electricity maintenance skills, greening maintenance skills, etc., the system automatically and reasonably assigns inspection tasks to ensure that each task can be matched with the most suitable staff member, achieving the best match of "person-task". It can effectively support multi-steward collaborative planning operations, especially suitable for large property areas, such as comprehensive parks, commercial complexes, etc., to solve the complex requirements of distributed inspections and improve the overall inspection efficiency.

[0070] The work plan established through the above method can be comprehensively evaluated. The operation effect of the system can be quantitatively evaluated from multiple dimensions such as inspection coverage rate, task completion on-time rate, and sudden task response speed. The model is continuously optimized through the method of comparative learning. Deviation data between the actual execution route and the planned route, such as a certain section of the path being temporarily detoured due to a construction site, etc., is fed back and input into the AI large model to continuously update the environmental constraint knowledge base of the system, enabling the model to better adapt to complex and changeable actual scenarios.

[0071] This method can achieve multi-dimensional constraint fusion, breaking the limitation of traditional path planning that only focuses on distance. For the first time, it successfully transforms complex business rules such as device priority, strict time window constraints, and differences in staff skills into quantifiable and computable mathematical constraint conditions, significantly enhancing the practicality and effectiveness of route planning in actual applications. It also realizes self-evolution. By continuously collecting and analyzing historical execution data and continuously optimizing model parameters, a virtuous closed-loop of "planning - execution - feedback - iteration" is formed. After long-term use, it can improve the property inspection efficiency by 30% - 50%, bringing significant efficiency improvement and cost savings to property management.

[0072] From the above technical solutions, it can be seen that the beneficial effects of this embodiment at least include: formulating a work planning scheme based on artificial intelligence technology, which can consider factors in dimensions such as time consumption, constraint conditions, and resource consumption, comprehensively score the work route, and thus achieve the highest overall efficiency; avoiding the defects of low efficiency and insufficient intelligence in the traditional method.

[0073] Figure 1 The shown is only the basic embodiment of the method of the present invention. Based on it, with certain optimization and expansion, other preferred embodiments of the method can also be obtained.

[0074] As Figure 2 shown, it is another specific embodiment of the property work planning method based on artificial intelligence technology of the present invention. This embodiment is further described on the basis of the foregoing embodiment. In this embodiment, the method includes the following steps:

[0075] Step 201: Establish a work planning network based on graph neural network technology.

[0076] In the present invention, a model will be established based on the graph neural network (Graph Neural Network, abbreviated as GNN) in the field of artificial intelligence technology, that is, a work planning network will be established and targeted data training will be carried out on it. Using this work planning network, it is possible to more intelligently determine the work planning scheme in property work.

[0077] Specifically, the task nodes in the target area can be determined, and the task paths between the task nodes can be determined. According to the passing efficiency of the task paths, weight coefficients are configured for the task paths. The work planning network is established according to the task nodes, the task paths, and the weight coefficients.

[0078] The target area refers to the physical area covered by property service work, such as the scope of a park. Within the target area, there are multiple task nodes and task paths between each of the task nodes. Specifically, a work task (and its corresponding task location) can be abstracted as a task node in the GNN network. Each task node (i.e., each work task) has corresponding features, which specifically include priority, time consumption, resource consumption, and various constraint conditions.

[0079] The paths between task nodes are abstracted as "edges" in the GNN network, which are also referred to as task paths in this embodiment. And physically speaking, each task path has different passing efficiencies. For example, the length of the actual distance, road conditions, and limiting factors (such as access control) will all affect the passing efficiency. According to the level of passing efficiency, weight coefficients can be configured for the task paths. It can be understood that to ensure the overall efficiency, in the planning, task paths with higher passing efficiencies are often given priority, and the configuration of weight coefficients is also to reflect this tendency.

[0080] The work planning network can be represented as G=(V, E). Where G represents the work planning network, V represents task nodes, and E represents task paths.

[0081] After establishing the work planning network, it is necessary to perform data training on it. Specifically, in combination with reinforcement learning algorithms or ant colony algorithms, training can be carried out for specific goals such as "the shortest total inspection duration", "prioritized coverage of high-priority tasks", and "the lowest resource consumption".

[0082] Step 202: Determine the objective function according to the work planning network.

[0083] In the trained work planning network, a specific objective function can be obtained. Through the operation of the objective function, the work plan (specific route) can be formulated and screened.

[0084] In this embodiment, the objective function can be established according to the time evaluation item, constraint violation evaluation item, and resource consumption evaluation item.

[0085] Specifically, F = αT + βC + γR. Where F represents the objective function. T represents the time evaluation item, that is, the total time consumption of a specific plan. C represents the constraint violation evaluation item, that is, the number of times the constraint conditions of each task node are violated in a specific plan. R represents the resource consumption evaluation item, that is, the total amount of resources consumed under a specific plan. The so-called resource consumption can include energy consumption, consumable consumption, and other various related consumptions. α, β, and γ are hyperparameters obtained after data training.

[0086] As can be understood in combination with the above objective function, the result F of the objective function is a "comprehensive score" for a specific plan, which to a certain extent reflects the comprehensive efficiency of a plan, and takes into account the time consumption, resource consumption, and the number of violations of constraints. Ideally, a route with the shortest time consumption, no violation of constraints, and the least resource consumption should be found as the specific work plan. However, in some more complex situations, or rather, in most actual situations, there is no absolutely ideal route. Therefore, it is often necessary to conduct comprehensive evaluation and consideration to find an optimal solution to maximize the overall efficiency.

[0087] In the prior art, the work plan is often determined manually or by a fixed process, and usually, the optimal solution cannot be found. In this embodiment, a graph neural network and an objective function are used to implement this process.

[0088] Step 203: Collect task data in the target area, input the task data into the work plan network, and use the objective function to determine a work plan according to the task nodes and the task path.

[0089] In specific practice, once the work plan network and the objective function are established, the actual data in the target area can be substituted into them for calculation to obtain a work plan. Therefore, the task data in the target area should be collected first. The target data includes static basic data and dynamic real-time data.

[0090] The static basic data includes the electronic map in the target area, which accurately marks the building layout and the position coordinates of various devices; the detailed attributes of the task nodes, including the device type, the specified inspection cycle, and the safety level classification; and at the same time, it includes the relevant constraints when the steward executes the task, such as the daily working hours limit, the weight and volume limits of the devices that can be carried, etc.

[0091] The dynamic real-time data includes the device operation status data and environmental parameter data, such as temperature, humidity, air quality, etc., fed back by real-time sensors; the past historical inspection records, which detail the time consumed for each inspection and the problem feedback found; the emergency event information, such as temporary equipment failure repair requests, severe weather anomaly warnings, etc.; and the urgent inspection requirements for specific areas temporarily proposed by the owners.

[0092] For the collected task data, certain preprocessing can be performed, including the use of spatial vector coding technology to cleverly transform geographic coordinates and equipment attributes into numerical features that are easy for computer processing, laying the foundation for subsequent data analysis. Through time series analysis, the rules in historical inspection time data are mined, and a "inspection point time prediction model" is constructed based on this to estimate the time required for future inspections. For dynamic data, real-time feature fusion technology is used to integrate dynamic information from different sources and types to generate dynamic constraint vectors that contain both time and space information, so that the system can grasp the real-time situation more comprehensively and accurately.

[0093] After determining the task data, multiple alternatives can be determined in the work planning network; each of the alternatives includes a task line consisting of a task node and a task path. Determine the time evaluation score, constraint violation evaluation score and resource consumption evaluation score of each task line; use the objective function, the time evaluation score, the constraint violation evaluation score and the resource consumption evaluation score to determine the comprehensive score of each alternative; determine the work planning scheme based on the comprehensive score.

[0094] Step 204: When an emergency occurs, determine a temporary node and a temporary path of the emergency in the working plan network.

[0095] Step 205: Determine an emergency plan according to the temporary node, the temporary path and the work plan.

[0096] In this embodiment, the specific method of the method in this embodiment to deal with emergencies will also be specifically described. When the work plan has been determined and has been executed or is halfway through, you may still face emergencies, that is, emergencies. For example, consumption events, sudden failures, etc. The priority of such events is very high and usually needs to be handled as soon as possible, which means that the original work plan will inevitably be disrupted. In this case, the method in this embodiment can also form a new work plan for this purpose.

[0097] Specifically, when an emergency occurs, the temporary node and temporary path of the emergency in the work planning network can be determined. In other words, the emergency can be regarded as a same "task node" in the GNN network, or as a newly added node, and there are also newly added "edges", that is, temporary paths. Then the temporary nodes and temporary paths can be substituted into the network for a new round of operations.

[0098] Specifically, the remaining nodes in the work planning scheme and the task paths corresponding to the remaining nodes can be determined; based on the temporary nodes, the temporary paths, the remaining nodes, and the task paths corresponding to the remaining nodes, the emergency planning scheme can be determined.

[0099] Generally, when an emergency occurs, the original work plan may be in the middle of execution. That is to say, some of the work tasks have been completed, and some have not. In this case, first determine the remaining nodes (i.e., the unfinished part of the tasks) and the task paths corresponding to the remaining nodes. Then merge them with the temporary nodes and temporary paths and perform calculations together. Usually, in this case, the temporary nodes have the highest priority. Its operation principle is the same as that of the foregoing embodiments. On such a premise, a new work plan, that is, an emergency planning scheme, can be calculated.

[0100] In this embodiment, the dynamic replanning algorithm will be immediately triggered in case of an emergency. This algorithm can intelligently retain the records of the completed inspection points, reorder the remaining unfinished tasks, and give priority to inserting the urgent tasks into the planned route to ensure that emergencies are handled in a timely manner. Combining with the traffic data obtained in real time, such as the situation where the floor passage is blocked due to an elevator failure, etc., with the powerful computing power of the AI large model, quickly calculate the optimal solution for the local path, effectively avoiding the time loss caused by re-performing the global planning and greatly improving the response speed.

[0101] A convenient mobile visual interface is specially created for the property steward in the system. This interface intuitively presents: the real-time planned inspection route, including detailed navigation path guidance, accurately estimated time-consuming, and prominent markings of key inspection points. Provide a dynamic adjustment prompt function. For example, when the system detects that "the water pipe in Unit 3 is leaking", it will prompt on the interface in time that "an emergency inspection point has been inserted into the route, and the delay is expected to be 15 minutes", so that the steward can understand the route change situation in the first time.

[0102] Relying on the excellent real-time learning ability of the AI large model, the GNN network realizes an efficient operation mode of "instant response to emergency tasks + dynamic correction of local paths". Compared with traditional algorithms, such as Dijkstra algorithm, genetic algorithm, etc., the response efficiency is increased by more than 70% significantly, and it can better cope with the complex and changeable actual inspection scenarios.

[0103] As Figure 3 shown, it is a specific embodiment of a property work planning device based on artificial intelligence technology according to the present invention. The device in this embodiment, that is, the entity device for executing Figures 1-2 the method described above. Its technical solution is essentially the same as that of the foregoing embodiments, and the corresponding descriptions in the foregoing embodiments are equally applicable to this embodiment. The device described in this embodiment includes:

[0104] A network establishment module 301 is configured to establish a work planning network based on graph neural network technology; in the work planning network, it includes multiple task nodes within a target area and task paths between each of the task nodes.

[0105] An objective function module 302 is configured to determine an objective function according to the work planning network.

[0106] A solution formulation module 303 is configured to collect task data within the target area, input the task data into the work planning network, and use the objective function to determine a work planning solution according to the task nodes and the task paths.

[0107] In addition, based on the Figure 3 embodiment shown, preferably, it further includes:

[0108] The network establishment module 301 includes:

[0109] A node unit 311 is configured to determine each task node within the target area and the task paths between each of the task nodes;

[0110] A weight unit 312 is configured to configure a weight coefficient for the task paths according to the passing efficiency of the task paths;

[0111] A networking unit 313 is configured to establish the work planning network according to the task nodes, the task paths, and the weight coefficient.

[0112] The solution formulation module 303 includes:

[0113] An alternative solution unit 331 is configured to determine multiple alternative solutions in the work planning network; each of the alternative solutions includes a task line composed of task nodes and task paths;

[0114] A scoring unit 332 is configured to determine a time evaluation score, a constraint violation evaluation score, and a resource consumption evaluation score for each of the task lines; use the objective function, the time evaluation score, the constraint violation evaluation score, and the resource consumption evaluation score to determine a comprehensive score for each of the alternative solutions;

[0115] A solution determination unit 333 is configured to determine the work planning solution according to the comprehensive score.

[0116] It further includes:

[0117] An emergency event module 304 is configured to, when an emergency event occurs, determine temporary nodes and temporary paths of the emergency event in the work planning network; determine an emergency planning solution according to the temporary nodes, the temporary paths, and the work planning solution.

[0118] The emergency event module 304 includes:

[0119] A remaining node unit 341, configured to determine the remaining nodes in the work planning scheme and the task paths corresponding to the remaining nodes.

[0120] An emergency plan determination unit 342, configured to determine the emergency planning scheme according to the temporary nodes, the temporary paths, the remaining nodes, and the task paths corresponding to the remaining nodes.

[0121] Figure 4 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0122] The processor, network interface, and memory can be interconnected through an internal bus, and the internal bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 4 only a bidirectional arrow is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0123] The memory is used to store execution instructions. Specifically, the execution instructions are computer programs that can be executed. The memory can include a memory and a non-volatile memory, and provide the execution instructions and data to the processor.

[0124] In a possible implementation manner, the processor reads the corresponding execution instructions from the non-volatile memory into the memory and then runs, or can also obtain the corresponding execution instructions from other devices, so as to form a property work planning device based on artificial intelligence technology at the logical level. The processor executes the execution instructions stored in the memory to implement the property work planning method provided in any embodiment of the present invention through the executed execution instructions.

[0125] The above is as in the present invention Figure 3The method executed by the property work planning device based on artificial intelligence technology provided by the illustrated embodiment can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above-mentioned 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. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0127] The embodiments of the present invention also propose a readable medium. When the execution instructions stored in the readable storage medium are executed by the processor of an electronic device, the electronic device can be enabled to execute the property work planning method based on artificial intelligence technology provided in any embodiment of the present invention, and is specifically used to execute as Figure 1 or Figure 2 the method shown.

[0128] The electronic device described in each of the foregoing embodiments may be a computer.

[0129] Those skilled in the art should understand that the embodiments of the present invention may be provided as a method or a computer program product. Therefore, the present invention may adopt a completely hardware embodiment, a completely software embodiment, or a form combining software and hardware.

[0130] Each embodiment in the present invention is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the corresponding parts in the method embodiments for relevant details.

[0131] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device including a series of elements not only includes those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the presence of another identical element in the process, method, commodity or device including the said element.

[0132] The above description is only for the embodiments of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and changes can be made to the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A property work planning method based on artificial intelligence technology, characterized in that, Including: Establish a work planning network based on graph neural network technology; In the work planning network, it includes multiple task nodes within the target area and task paths between each of the task nodes; Determine the objective function according to the work planning network; Collect task data within the target area, input the task data into the work planning network, and use the objective function to determine the work planning scheme according to the task nodes and the task paths.

2. The method according to claim 1, characterized in that, The establishing of the work planning network based on graph neural network technology includes: Determine the task nodes within the target area and the task paths between each of the task nodes; Configure weight coefficients for the task paths according to the passing efficiency of the task paths; Establish the work planning network according to the task nodes, the task paths, and the weight coefficients.

3. The method according to claim 2, wherein The establishing of the objective function in the work planning network includes: Establish the objective function according to the time evaluation item, the constraint violation evaluation item, and the resource consumption evaluation item.

4. The method according to claim 3, wherein The target data includes: Static basic data and dynamic real-time data.

5. The method according to claim 4, wherein The using of the objective function to determine the work planning scheme according to the task nodes and the task paths includes: In the work planning network, determine multiple alternative schemes; each of the alternative schemes includes task lines composed of task nodes and task paths; Determine the time evaluation scores, the constraint violation evaluation scores, and the resource consumption evaluation scores of each of the task lines; Use the objective function, the time evaluation scores, the constraint violation evaluation scores, and the resource consumption evaluation scores to determine the comprehensive scores of each of the alternative schemes; Determine the work planning scheme according to the comprehensive scores.

6. The method according to any one of claims 1 to 5, characterized in that After determining the work planning scheme, it further includes: When an emergency occurs, determine the temporary nodes and temporary paths of the emergency in the work planning network; Determine the emergency planning scheme according to the temporary nodes, the temporary paths, and the work planning scheme.

7. The method according to claim 6, characterized in that The determining of the emergency planning scheme according to the temporary nodes, the temporary paths, and the work planning scheme includes: Determine the remaining nodes in the work planning scheme and the task paths corresponding to the remaining nodes; Determine the emergency planning scheme according to the temporary nodes, the temporary paths, the remaining nodes, and the task paths corresponding to the remaining nodes.

8. A property work planning device based on artificial intelligence technology, characterized in that, Including: A network establishment module for establishing a work planning network based on graph neural network technology; In the work planning network, it includes multiple task nodes within the target area and task paths between each of the task nodes; An objective function module for determining the objective function according to the work planning network; A scheme formulation module for collecting task data within the target area, inputting the task data into the work planning network, and using the objective function to determine the work planning scheme according to the task nodes and the task paths.

9. A computer-readable storage medium storing a computer program for executing the property work planning method based on artificial intelligence technology according to any one of claims 1 - 7 above.

10. An electronic device, the electronic device includes: A processor; A memory for storing the executable instructions that can be executed by the processor; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the property work planning method based on artificial intelligence technology according to any one of claims 1-7 above.

Images