Dynamic scheduling management methods, systems, equipment and media

Abstract

This invention discloses a dynamic scheduling management method, system, device, and medium. The dynamic scheduling management method includes: using a pre-trained neural network analysis model based on a task scheduling instruction, performing logical reasoning analysis based on historical information of historical task scenarios similar to the task in the task scheduling instruction to obtain the task scheduling information of the current task scheduling instruction; wherein, the task scheduling information includes the scheduling content and the scheduling location; searching for corresponding terminals based on the scheduling content and the scheduling location, and scheduling the terminals. This invention can obtain historical task scenarios similar to the current task state based on the current task scheduling instruction using a neural network analysis model with logical reasoning capabilities, quickly locate the terminal to be scheduled through logical reasoning analysis, dynamically schedule various terminals, timely schedule various terminal resources, promptly observe security risks, improve scheduling efficiency and flexibility, and enable rapid linkage and communication.

Description

Technical Field

[0001] This invention relates to the field of Internet of Things (IoT) technology, and more specifically to a dynamic scheduling and management method, system, device, and medium. Background Technology

[0002] Currently, converged communication systems can leverage IP network technology to integrate traditionally independent and heterogeneous communication methods and applications (such as voice, video, data, and messaging) onto a unified platform, achieving comprehensive communication based on a unified interface, unified management, and unified scheduling. When applying converged communication systems, it is typically necessary to schedule various voice and video resources to promptly observe critical security risks (such as traffic accidents, severe weather, and equipment failures). These scheduled resources change with time and scenarios, and the amount of data increases significantly. Traditional voice scheduling struggles to quickly allocate relevant resources from large amounts of data and changing scenarios, resulting in problems such as untimely communication and low scheduling efficiency. Summary of the Invention

[0003] This invention provides a dynamic scheduling management method, system, device, and medium to solve the technical problems of untimely communication and low scheduling efficiency in traditional voice scheduling.

[0004] Firstly, a dynamic scheduling management method is provided, including:

[0005] Based on the task scheduling instruction, a pre-trained neural network analysis model is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the task in the task scheduling instruction to obtain the task scheduling information of the current task scheduling instruction; wherein, the task scheduling information includes the content to be scheduled and the location to be scheduled.

[0006] Search for the corresponding terminal based on the content and location to be scheduled, and then schedule the terminal.

[0007] Secondly, a dynamic scheduling management system is provided, including a unit for executing the above-described dynamic scheduling management method.

[0008] This invention also provides a dynamic scheduling and management system, including a server and multiple terminals. The server is configured with a call intelligence model, which includes multiple neural network analysis models for task scheduling and management.

[0009] The server is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the tasks in the task scheduling instructions, using a pre-trained neural network analysis model, to obtain the task scheduling information of the current task scheduling instruction; wherein, the task scheduling information includes the scheduling content and the scheduling location; and searches for corresponding terminals based on the scheduling content and the scheduling location to schedule the terminals; or

[0010] The server is used to perform logical reasoning analysis based on the call information using a pre-trained neural network analysis model to obtain call number identification results and communication link identification results. If the call number identification result is an alarm or emergency call, the server obtains task scheduling information containing the content to be scheduled and the location to be scheduled based on the call number identification result and the communication link identification result. The server searches for the corresponding terminal based on the content to be scheduled and the location to be scheduled, schedules the terminal, generates a SIP instruction, and transmits the SIP instruction to the receiving object associated with the call number.

[0011] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described dynamic scheduling management method.

[0012] Fourthly, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described dynamic scheduling management method.

[0013] Compared with existing technologies, this invention utilizes a pre-trained neural network analysis model based on task scheduling instructions. It performs logical reasoning analysis based on historical information from historical task scenarios similar to those in the task scheduling instructions to obtain the task scheduling information for the current task. Then, it searches for corresponding terminals based on the scheduling content and location in the scheduling information and schedules the terminals to access various resource data. This invention, using a neural network analysis model with logical reasoning capabilities, can quickly locate the terminal to be scheduled based on the current task scheduling instructions, dynamically schedule various terminals, and promptly schedule various terminal resources. It also allows for timely observation of security risks, greatly improving scheduling efficiency and flexibility, enabling rapid communication and enhanced decision-making efficiency. Attached Figure Description

[0014] Figure 1 A flowchart illustrating the dynamic scheduling management method provided in the first embodiment of the present invention;

[0015] Figure 2 for Figure 1A schematic diagram of a specific implementation of step S120;

[0016] Figure 3 for Figure 2 A flowchart illustrating a specific implementation of step S123;

[0017] Figure 4 A flowchart illustrating the dynamic scheduling management method provided in the second embodiment of the present invention;

[0018] Figure 5 This is a schematic diagram of the structure of the dynamic scheduling management system provided in the first embodiment of the present invention;

[0019] Figure 6 This is a schematic diagram of the structure of the dynamic scheduling management system provided in the second embodiment of the present invention;

[0020] Figure 7 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0023] It should also be understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0024] Please see Figure 1 , Figure 1 This is a schematic flowchart illustrating the dynamic scheduling management method provided in the first embodiment of the present invention. In the embodiment shown in the figures, the dynamic scheduling management method includes the following steps S110-130:

[0025] S110. Obtain information from each terminal and generate terminal feature data that associates the features of each terminal.

[0026] In this invention, the terminal can be a variety of different types of terminals, such as IP / video phones, surveillance cameras, drones, law enforcement recorders, and positioning devices.

[0027] In this step, the information of the accessing terminals is obtained. Various terminals can access the network (such as Wi-Fi, cellular network, etc.). Each accessing terminal has a unique identifier. Terminal feature data is generated based on the terminal characteristics to further identify the terminal, so as to quickly search for the terminal to be scheduled in subsequent tasks. Among them, the terminal features include the terminal location and the target features of the generated content. For example, when the terminal is a surveillance ball, the terminal features of the surveillance ball can include the location of the surveillance ball and the target features targeted by the surveillance ball when shooting. The target features can include the target category (such as a car, a person, or certain specific objects, etc.). For example, the terminal feature data of surveillance ball 1 can include the target features (cars and license plates of passing vehicles) and location. The terminal feature data of surveillance ball 2 can include the target features (faces of people who do not comply with traffic rules / appear in dangerous areas) and location. The terminal feature data of drone 1 can include the target features (environmental landmarks) and location.

[0028] S120. Based on the task scheduling instruction, a pre-trained neural network analysis model is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the tasks in the task scheduling instruction, to obtain the task scheduling information of the current task scheduling instruction.

[0029] In this invention, the neural network analysis model can be pre-trained based on the scheduling datasets of different types of tasks that have occurred, enabling it to have logical reasoning capabilities. The neural network analysis model can call historical information of historical task scenarios similar to the current task scheduling instruction to perform logical reasoning analysis, thereby obtaining the task scheduling information of the current task scheduling instruction, so as to dynamically call resource data of different terminals.

[0030] In this embodiment, the task scheduling information includes the content to be scheduled and the location to be scheduled, and the task scheduling instruction can be a voice scheduling instruction generated by the user according to the task progress.

[0031] like Figure 2 As shown, step S120 may specifically include steps S121-S123:

[0032] S121. Analyze the input task scheduling instructions using a pre-trained neural network analysis model to obtain the current task.

[0033] In this step, the current task can be a resource allocation instruction or a monitoring instruction for an emergency (such as a traffic accident, severe weather, equipment failure, or hazardous material leakage).

[0034] S122. Obtain historical information of historical task scenarios similar to the current task in real time, and infer and configure instruction variables related to the current task based on prompt words.

[0035] In this step, historical information of historical task scenarios similar to the current task is acquired in real time to synchronize the data required by the current task (such as multimodal data such as audio, video, text, and location) in real time; wherein, the historical information may include historical variable data and historical scheduling information.

[0036] In this invention, machine learning methods are used to infer and configure instruction variables based on prompt words. The prompt words are associated with the task scenario. This step can call pre-stored prompt words associated with each task scenario, or retrieve prompt words selected / input by the user. The instruction variables are also task-related factors that can describe the characteristics of the task. For example, when the task scheduling instruction is "water pipe freezing situation," and the user inputs prompt words representing the location and past freezing data, the neural network analysis model can infer and configure instruction variables (such as water pipe material, weather temperature, construction years, location, etc.) related to the current task based on the prompt words, the characteristics of the target object, the task purpose, and / or the task environment. In some task scenarios, instruction variables can also include prompt words. When the task scheduling instruction is "traffic accident handling," the prompt word is location, and the configured instruction variables can be road conditions, pedestrian traffic, whether it is at an intersection / critical driving road, etc.

[0037] S123. Based on the instruction variable, call the corresponding historical information for matching analysis to obtain the task scheduling information of the current task scheduling instruction.

[0038] In this step, the instruction variables are matched and analyzed with the corresponding historical information. The task scheduling information may include the content to be scheduled and the location to be scheduled.

[0039] Specifically, such as Figure 3 As shown, step S123 may include steps S1231-S1233:

[0040] S1231. Call the historical variable data corresponding to the instruction variable in the historical task scenario;

[0041] S1232. Using a weighted linear algorithm, calculate the matching value between the historical task scenario and the current task based on the historical variable data corresponding to the instruction variable in the historical task scenario.

[0042] In this step, the matching value is calculated using the formula y=b+a1*x1+a2*x2+a3*x3+……+an*xn based on the historical variable data and the instruction variable data of the current task. Here, y represents the matching value between the historical task scenario and the current task, a represents the weight, x represents the deviation between the historical variable data corresponding to the instruction variable and the instruction variable data in the current task, which can be set manually or obtained by training based on the training set and validation set. For example, when the historical temperature is 1 degree lower than the temperature in the current task, x can be set to 1. The larger the deviation, the smaller x is. b represents the deviation constant.

[0043] S1233. If the matching value is greater than a preset threshold, the task scheduling information of the current task scheduling instruction is inferred based on the historical scheduling information of the historical task scenario.

[0044] In this embodiment, the scheduling location and scheduling content are selected based on the similarity with the previously occurred task scenario. When the matching value calculated by the model is greater than a preset threshold, it indicates that the historical task scenario and the current task have a high degree of similarity. Based on the historical scheduling information of the historical task scenario, which includes the scheduling location and scheduling content, the task scheduling information of the current task scheduling instruction is inferred.

[0045] S130. Search for the corresponding terminal based on the content to be scheduled and the location to be scheduled, and schedule the terminal.

[0046] In this step, based on the target features in the content to be scheduled and the desired location, the terminal feature data of each terminal is searched and compared to find the corresponding terminal, and the data resources acquired by the terminal are scheduled. The data resources may include video, audio, and / or text data. That is, based on the target features in the content to be scheduled and the desired location, the terminal to be scheduled is determined in reverse, and control commands are sent to the determined terminal to retrieve its resource data, such as captured videos and recorded audio, to achieve the uploading of audio, video, and location information, facilitating timely observation of security risks.

[0047] In this invention, the specific scheduling operation process of the current task can refer to the historical scheduling information of historical task scenarios (such as some emergency management accidents). Alternatively, in some specific object monitoring tasks, the historical scheduling information of nearly identical historical task scenarios can be used as the task-desired scheduling information of the current task scheduling instruction. For example, in the aforementioned "water pipe freezing and bursting" task scheduling instruction, when the matching value obtained by weighting the instruction variable data of a water pipe at a certain location through a weighted linear algorithm formula is greater than a preset threshold, the model infers that the water pipe at that location is the water pipe currently being monitored for freezing and bursting, and schedules the resource data of monitoring equipment such as the surveillance camera used to photograph and observe the water pipe at that location. When the task scheduling instruction is a task scheduling instruction related to an emergency management accident, that is, when the current task type is an emergency management accident, it usually involves multiple dimensions of demand scheduling such as on-site perception, personnel safety, and / or vehicle tracking. In this case, the task-desired scheduling information of the current task scheduling instruction is obtained by referring to the historical scheduling information of historical task scenarios with high similarity obtained from the above steps. It is usually task-desired scheduling information that includes multiple dimensions of demand, such as... In a joint emergency rescue mission involving a chemical plant leak and explosion, the most similar historical mission scenario is obtained based on a neural network analysis model. The historical scheduling information of this historical mission scenario may include three dimensions of the content and location to be scheduled: rapid detection and location of the accident to achieve on-site perception; querying whether personnel were in the most dangerous position (leak source) at the time of the explosion; and whether personnel have been safely evacuated to achieve personnel safety information and tracking and investigating hazardous chemical delivery vehicles during a specific period to quickly locate the suspected vehicle that caused the leak. For example, if the location of the on-site perception is the leak location, and the content to be scheduled includes environmental markers at the leak location, then based on the target characteristics and location of the content to be scheduled, it is known that the on-site perception of the current mission also needs to obtain the markers at the leak location. The terminal set up at the leak location in the current mission scenario is searched and compared. The target characteristics of the terminal feature data and the target characteristics of the content to be scheduled are queried and compared to obtain the terminal to be scheduled (i.e., the terminal that takes pictures of the markers at the current leak location, such as the drone 1 that takes pictures of the markers at this location). The data taken by the terminal is obtained to quickly detect and locate the accident.

[0048] As can be seen, in the above scheme, the dynamic scheduling management method of the present invention uses a pre-trained neural network analysis model to perform historical task scenario reasoning and matching based on the task scheduling instruction, obtains historical task scenarios with similarity exceeding a preset threshold, performs logical reasoning based on the historical scheduling information of the historical task scenario, obtains the task scheduling information of the current task scheduling instruction, and then searches for the corresponding terminal based on the scheduling content and location in the scheduling information, and schedules the terminal. It can be seen that the present invention can obtain historical task scenarios with high similarity to the current task state based on the current task scheduling instruction according to the current task scheduling instruction using a neural network analysis model with logical reasoning ability, quickly locate the terminal to be scheduled through logical reasoning analysis, dynamically schedule various terminals, and timely schedule various terminal resources, promptly observe safety hazards, greatly improve the efficiency and flexibility of scheduling, enable rapid linkage and communication, and be applicable to various scheduling scenarios (such as public transportation management, intelligent management, emergency management, etc. in various scenarios such as scenic spots, factories, commercial areas, stadiums, etc.). Dynamically scheduling various terminal resources can break down communication barriers in various scheduling scenarios, and the scheduled resource data can be transmitted back in real time, which facilitates the timely issuance of instructions as needed, helps the command center to make rapid decisions, and effectively reduces risk losses.

[0049] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0050] Reference Figure 4 , Figure 4 This is a flowchart illustrating the dynamic scheduling management method provided in the second embodiment of the present invention. As shown in the figure, the method includes the following steps S210-S280:

[0051] S210. Obtain information from each terminal and generate terminal feature data that associates the features of each terminal.

[0052] Initially, information from each terminal is acquired. When there is a scheduling requirement, steps S220 and S230 can be executed according to the input task scheduling instructions or call information. Since step S210 is the same as or similar to step S110, it will not be described again here.

[0053] S220. Based on the task scheduling instruction, a pre-trained neural network analysis model is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the tasks in the task scheduling instruction, to obtain the task scheduling information of the current task scheduling instruction.

[0054] This step is the same as or similar to step S120, and will not be described again here.

[0055] S230. Receive call information, and perform logical reasoning analysis using a pre-trained neural network analysis model based on the call information to obtain call number identification results and communication link identification results.

[0056] In this step, the call information includes the mobile terminal number that dialed the number, the call number, and the communication link. A pre-trained neural network analysis model is used to perform logical reasoning analysis based on the call number and the communication link to obtain the call number identification result and the communication link identification result. The call number identification result indicates the type of the call number, such as whether the call is for emergency or police calls. If the call number is 110, it is inferred to be a police call; if the call number is 120 or 119, it is inferred to be an emergency call.

[0057] S240. If the call number identification result is an alarm or emergency call, the task scheduling information containing the content to be scheduled and the location to be scheduled is obtained based on the call number identification result and the communication link identification result.

[0058] In this step, if the call number identification result is an alarm or emergency call, the desired location can be obtained based on the communication link identification result, and the desired dispatch content can be obtained based on the call number identification result. If it is an alarm or emergency call, the desired dispatch content is the current status of the owner of the mobile terminal that dialed the number, which can be obtained by capturing images from terminals such as surveillance cameras or drones.

[0059] S250. Search for the corresponding terminal based on the content and location to be scheduled, and schedule the terminal.

[0060] In this step, when the input is call information, the system searches for a terminal at the desired location to capture or generate content targeting the desired content, based on the desired dispatch content and desired dispatch location. Since the specific implementation of this step is the same as or similar to step S130, it will not be described again here.

[0061] S260. Obtain the receiving object associated with the task scheduling instruction / call number.

[0062] In this step, when the input is a call message, the receiving object associated with the call number (such as the police, hospital, etc.) is obtained. If the input is a task scheduling instruction, and the completion of the current task corresponding to the task scheduling instruction requires the cooperation of other departments, the receiving object associated with the cooperation of the current task can be obtained, which facilitates real-time communication and cooperation.

[0063] In this embodiment, after obtaining the associated receiving object, step S270 or step S280 can be executed.

[0064] S270. Generate a SIP instruction based on the location, and schedule a communication link to transmit the SIP instruction to the receiving object.

[0065] In this step, SIP instructions can be generated based on the desired scheduling location and transmitted to the receiving object via the IMS communication link.

[0066] S280. Generate SIP instructions based on the location, schedule the communication link to transmit the SIP instructions to the receiving object, and push the scheduled data resources to the receiving object.

[0067] In this step, SIP instructions can be generated based on the location and transmitted to the receiving object through the IMS communication link. Data resources of the dispatched terminal can also be pushed to the receiving object, making it easier for the receiving object to understand the situation in a timely manner. This enables more efficient linkage with external units such as public security, fire protection, and medical care, achieving real-time information sharing, more efficient cross-departmental collaboration, significantly improving dispatch management efficiency, and providing strong functional expansion and remote management capabilities.

[0068] As can be seen, in the above scheme, the present invention can obtain historical task scenarios with high similarity to the current task state based on the current task scheduling instructions using a neural network analysis model with logical reasoning capabilities. Through logical reasoning analysis, it can quickly locate the terminal to be scheduled and dynamically schedule various types of terminals. Alternatively, it can analyze call information based on a neural network analysis model to obtain call number identification results and communication link identification results. When the call number identification result is an alarm or emergency call, it can obtain task scheduling information containing the content and location to be scheduled based on the call number identification result and communication link identification result. This allows it to search for the terminal to be scheduled, schedule the resource data of the corresponding terminal, and, based on... The location generates a SIP command, which is transmitted to the receiving object associated with the current task scheduling command / call number via the IMS communication link. Furthermore, the scheduled data resources can be pushed to the receiving object. It can be seen that the dynamic scheduling management method in this embodiment can timely schedule various terminal resources, promptly observe security risks, and realize real-time information sharing. It can more efficiently realize cross-departmental collaboration, effectively link external units such as public security, fire protection, and medical care, and achieve real-time information sharing. Cross-departmental collaboration is more efficient, significantly improving scheduling management efficiency. In emergencies, it can realize high-definition video transmission and real-time voice communication, helping the command center to make rapid decisions and allocate resources, effectively reducing risk losses and enhancing emergency response capabilities.

[0069] Reference Figure 5 , Figure 5 This is a schematic diagram of the structure of the dynamic scheduling management system provided in the first embodiment of the present invention. In the embodiment shown in the figure, the dynamic scheduling management system includes a terminal feature collection unit 101, a model inference unit 102, and a scheduling unit 103. The detailed descriptions of each functional unit are as follows:

[0070] The terminal feature collection unit 101 is used to acquire information about each terminal and generate terminal feature data associated with the features of each terminal; wherein, the terminal features include the terminal location and the target features of the generated content.

[0071] The model reasoning unit 102 is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the task in the task scheduling instruction, using a pre-trained neural network analysis model to obtain the task scheduling information of the current task scheduling instruction; wherein, the task scheduling information includes the content to be scheduled and the location to be scheduled.

[0072] The scheduling unit 103 is used to search for the corresponding terminal based on the content to be scheduled and the location to be scheduled, and to schedule the terminal.

[0073] In some embodiments, the model inference unit 102 is specifically used for:

[0074] The input task scheduling instructions are analyzed using a pre-trained neural network analysis model to determine the current task;

[0075] Real-time acquisition of historical information of historical task scenarios similar to the current task, and inference configuration of instruction variables related to the current task based on prompt words;

[0076] Based on the instruction variable, the corresponding historical information is called for matching analysis to obtain the task scheduling information of the current task scheduling instruction.

[0077] In some embodiments, the model inference unit 102 is further specifically used for:

[0078] Retrieve the historical variable data corresponding to the instruction variable in the historical task scenario;

[0079] The matching value between the historical task scenario and the current task is calculated using a weighted linear algorithm based on the historical variable data corresponding to the instruction variable in the historical task scenario.

[0080] If the matching value is greater than a preset threshold, the task scheduling information of the current task scheduling instruction is inferred based on the historical scheduling information of the historical task scenario; wherein, the historical information includes historical variable data and historical scheduling information.

[0081] In some embodiments, the model inference unit 102 is specifically used for:

[0082] Based on the historical variable data corresponding to the instruction variable in the historical task scenario and the instruction variable data of the current task, the matching value between the historical task scenario and the current task is calculated using the formula y=b+a1*x1+a2*x2+a3*x3+……+an*xn; where a represents the weight, x represents the deviation between the historical variable data corresponding to the instruction variable and the instruction variable data in the current task, and b represents the deviation constant.

[0083] In some embodiments, the model inference unit 102 is further configured to:

[0084] Receive call information, and perform logical reasoning analysis based on the call information using a pre-trained neural network analysis model to obtain call number identification results and communication link identification results;

[0085] If the call number identification result is an alarm or emergency call, task scheduling information containing the content to be scheduled and the location to be scheduled is obtained based on the call number identification result and the communication link identification result.

[0086] Search for the corresponding terminal based on the desired scheduling content and location, schedule the terminal, generate a SIP instruction, and transmit the SIP instruction to the receiving object associated with the call number.

[0087] In some embodiments, the scheduling unit 103 is specifically used for:

[0088] Based on the target features and desired location in the content to be scheduled, the terminal feature data of each terminal is searched and compared to find the corresponding terminal and schedule the data resources acquired by the terminal; wherein, the data resources include video, audio and / or text data.

[0089] In some embodiments, the scheduling unit 103 is further configured to:

[0090] Obtain the receiving object associated with the task scheduling instruction according to the task scheduling instruction;

[0091] Based on the location, a SIP command is generated, and a communication link is scheduled to transmit the SIP command to the receiving object; or

[0092] Based on the location, a SIP instruction is generated, the communication link is scheduled to transmit the SIP instruction to the receiving object, and the scheduled data resources are pushed to the receiving object.

[0093] As can be seen, this invention provides a dynamic scheduling and management system that can perform similar task operations based on a neural network analysis model with logical reasoning capabilities. It can dynamically allocate and adjust resources according to the needs input into the system (task scheduling instructions or call information), promptly observe safety hazards, and achieve real-time information sharing. This enables more efficient cross-departmental collaboration and efficient linkage with external units such as public security, fire departments, and medical services, significantly improving scheduling and management efficiency. In emergencies, it can achieve high-definition video transmission and instant voice communication, assisting the command center in making rapid decisions and allocating resources, effectively reducing risk losses, and enhancing emergency response capabilities.

[0094] Reference Figure 6 , Figure 6 This is a schematic block diagram of a dynamic scheduling management system provided in the second embodiment of the present invention. Figure 6 As shown, the dynamic scheduling management system of this embodiment includes a server 301 and multiple terminals 302. The server 301 is configured with a call intelligence model 3011, which includes multiple neural network analysis models for task scheduling management to schedule multiple task requirements.

[0095] In this embodiment, the server 301 is used to perform logical reasoning analysis based on historical information of historical task scenarios similar to the task in the task scheduling instruction, using a pre-trained neural network analysis model, to obtain the task scheduling information of the current task scheduling instruction; wherein, the task scheduling information includes the scheduling content and the scheduling location, preferably, the task scheduling information can also be output to the user device screen for display; and search for the corresponding terminal 302 according to the scheduling content and the scheduling location, so as to schedule the terminal 302;

[0096] Alternatively, the server 301 is used to perform logical reasoning analysis based on the call information using a pre-trained neural network analysis model to obtain call number identification results and communication link identification results; if the call number identification result is an alarm or emergency call, the server obtains task scheduling information containing the content to be scheduled and the location to be scheduled based on the call number identification result and the communication link identification result; the server searches for the corresponding terminal 302 based on the content to be scheduled and the location to be scheduled, schedules the terminal 302, generates a SIP instruction, and transmits the SIP instruction to the receiving object associated with the call number.

[0097] In this invention, the neural network analysis model has logical reasoning capabilities, enabling it to judge and match tasks and perform similar tasks. That is, when a sudden accident occurs (traffic accident, severe weather, equipment failure), the neural network analysis model in the dynamic scheduling management system of this embodiment can obtain historical scheduling data of historical task scenarios with high similarity, and then infer the corresponding emergency plan (i.e., task scheduling information) for the current task based on the historical scheduling data. Furthermore, it can be output and displayed on the user's device, and the user can activate the emergency plan with one click, making scheduling more intelligent, efficient and flexible.

[0098] Understandably, a neural network analysis model in the call intelligence model 3011 can schedule and manage a task, or schedule and manage a dimension of the task. For example, in scenarios such as preset patrol routes and checkpoints, different neural network analysis models can be used to monitor and schedule accident monitoring at different patrol points, so as to achieve key inspections of past accident sites at the patrol points.

[0099] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned dynamic scheduling management system and its various units or components can be referred to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity, these details will not be repeated here.

[0100] In one embodiment, a computer device is provided, the internal structure of which can be shown as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The network interface is used to communicate with external devices via a network connection. Furthermore, the computer device may also include a display screen and input devices (e.g., mouse, keyboard, etc.) for interactive purposes.

[0101] Specifically, when the processor in the computer device executes the computer program, it implements the steps of the dynamic scheduling management method provided in the first and second embodiments described above.

[0102] In one embodiment, the present invention may also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the dynamic scheduling management method provided in the first and second embodiments described above.

[0103] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0104] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0105] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A dynamic scheduling management method, characterized by, The dynamic scheduling management method comprises: Obtaining terminal information of each terminal, and generating terminal characteristic data associated with characteristics of each terminal; wherein the terminal characteristics include terminal positions and target characteristics of generated content; Using a pre-trained neural network analysis model to analyze a task scheduling instruction based on historical information of a historical task scenario similar to a task in the task scheduling instruction to obtain task scheduling information of the task scheduling instruction; wherein the task scheduling instruction is a voice scheduling instruction generated by a user according to a task process, and the task scheduling information includes scheduled content and a scheduled position; specifically comprising: Using a pre-trained neural network analysis model to analyze an input task scheduling instruction to obtain a current task; Obtaining historical information of a historical task scenario similar to the current task in real time, and configuring an instruction variable related to the current task according to a prompt word; Calling historical variable data corresponding to the instruction variable in the historical task scenario; Using a weighted linear algorithm to calculate a matching value of the historical task scenario and the current task based on the historical variable data corresponding to the instruction variable in the historical task scenario; If the matching value is greater than a preset threshold, obtaining task scheduling information of the task scheduling instruction based on historical scheduling information of the historical task scenario; wherein the historical information includes historical variable data and historical scheduling information; Searching for a corresponding terminal according to the scheduled content and the scheduled position, and scheduling the terminal.

2. The dynamic scheduling management method of claim 1, wherein, The calculation of the matching value of the historical task scenario and the current task based on the historical variable data corresponding to the instruction variable in the historical task scenario using the weighted linear algorithm specifically comprises: Using a formula y = b + a1*x1 + a2*x2 + a3*x3 + … + an*xn to calculate the matching value of the historical task scenario and the current task based on the historical variable data corresponding to the instruction variable in the historical task scenario and instruction variable data of the current task; wherein a represents a weight, x represents a deviation of the historical variable data corresponding to the instruction variable and the instruction variable data in the current task, and b represents a deviation constant.

3. The dynamic scheduling management method of claim 1, wherein, The dynamic scheduling management method further comprises: Receiving call information, and using a pre-trained neural network analysis model to analyze the call information to obtain a call number recognition result and a communication link recognition result; If the call number recognition result is an alarm or emergency telephone, obtaining task scheduling information including scheduled content and a scheduled position based on the call number recognition result and the communication link recognition result; Searching for a corresponding terminal according to the scheduled content and the scheduled position, scheduling the terminal, generating a SIP instruction, and delivering the SIP instruction to a receiving object associated with the call number.

4. The dynamic scheduling management method of claim 1, wherein, The searching for a corresponding terminal according to the scheduled content and the scheduled position, and scheduling the terminal specifically comprises: According to a target feature in the content to be scheduled and a location to be scheduled, terminal feature data of each terminal is searched and compared to find a corresponding terminal, and data resources acquired by the terminal are scheduled; wherein the data resources include video, audio and / or text data.

5. The dynamic scheduling management method of claim 4, wherein, After the searching for the corresponding terminal according to the content to be scheduled and the location to be scheduled, and the scheduling of the terminal, the method further comprises: According to the task scheduling instruction, a receiving object associated with the task scheduling instruction is acquired; According to the location, a SIP instruction is generated, a communication link is scheduled to deliver the SIP instruction to the receiving object; or According to the location, a SIP instruction is generated, a communication link is scheduled to deliver the SIP instruction to the receiving object, and a scheduled data resource is pushed to the receiving object.

6. A dynamic dispatch management system, characterized by, The computer program product comprises a computer program for performing the dynamic scheduling management method according to any one of claims 1-5.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the dynamic scheduling management method according to any one of claims 1-5.

8. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program is executed by the processor to implement the steps of the dynamic scheduling management method according to any one of claims 1-5.

Images