Information scheduling system based on event response

Abstract

The invention relates to the field of information scheduling, in particular to an information scheduling system based on event response, which comprises a plurality of response modules used for collecting response time and occurrence frequency of events to be monitored, a learning module used for preprocessing the response time and the occurrence frequency, generating corresponding preprocessing data and sending the preprocessing data to a server. The system comprises a preprocessing module used for preprocessing data, selecting a plurality of index characteristics of the preprocessed data for learning and generating a corresponding event response diagram, a sequence module used for determining the priority of events to be monitored according to the event response diagram and determining the response sequence of the events to be monitored according to the priority, and an adjusting module used for sequentially responding to the events to be monitored again according to the response sequence and learning the events to be monitored. According to the method, the response efficiency of the event to be monitored can be monitored in real time, the priority is allocated according to a machine learning result, the processing efficiency of a system is improved, and timely transmission of event information and reasonable allocation of resources are ensured.

Description

Technical Field

[0001] The present invention relates to the field of information scheduling, and particularly to an information scheduling system based on event response. Background Art

[0002] With the continuous development of artificial intelligence technology, the system becomes more intelligent. Among them, the information scheduling system based on event response is an efficient information management system, which can perform scheduling processing according to the occurrence of specific events to ensure the timely transmission of information and the reasonable allocation of resources.

[0003] Chinese Patent Grant Publication No.: CN102136190B discloses an emergency response scheduling management system and method for urban bus passenger transport, which comprehensively uses the method of combining measured data, event prediction models and algorithms, and event real-time scheduling models and algorithms, scientifically integrates geographic information technology, positioning technology and modern communication technology, and uses the bus emergency scheduling technology for the intelligent development of the bus network and the multi-mode coordinated scheduling technology of the urban public passenger transport system. With the networked public passenger vehicle scheduling and operation scheduling management as the core, based on the key theories and methods of intelligent coordination scheduling among multiple modes and multiple lines of the urban public passenger transport system, an emergency coordination scheduling model and method for urban public passenger transport system events are established, providing good theoretical, method and technical support for the real-time scheduling of urban bus events, effectively reducing the event recognition time, generating fast real-time scheduling strategies, efficiently eliminating the impact of events, and restoring the driving plan, effectively improving the operation efficiency and safety of buses.

[0004] Chinese Patent Grant Publication No.: CN107239865B discloses a scheduling method for Internet information resources, so that when an event of overdue repayment of borrowed resources occurs, the resource lender can regain the right to use the lent resources. The method includes: when it is monitored that an event of overdue repayment of borrowed resources occurs, sending a resource scheduling request to a risk service platform, so that the risk service platform executes: in response to the resource scheduling request, scheduling the first quantity of Internet information resources from the compensation resource pool to a specified resource pool; scheduling the second quantity of Internet information resources in the specified resource pool to the resource lender of the overdue Internet information resources. This application also discloses a scheduling device and system for Internet information resources, a fund scheduling method, device and system.

[0005] However, the above methods have the following problems: they cannot intelligently monitor and control the events to be monitored in real time and have low operation efficiency. Summary of the Invention

[0006] To this end, the present invention provides an information scheduling system based on event response to overcome the problems in the prior art that it is impossible to intelligently monitor and control the events to be monitored in real time and the operation efficiency is low.

[0007] To achieve the above object, the present invention provides an information scheduling system based on event response, including:

[0008] A number of response modules for collecting the response time and occurrence frequency of the events to be monitored;

[0009] A learning module connected to the number of response modules for preprocessing the response time and the occurrence frequency, generating corresponding preprocessed data, selecting a number of index features of the preprocessed data for learning, and generating a corresponding event response graph;

[0010] An order module connected to the learning module for determining the priority of the events to be monitored according to the event response graph and determining the response order of the events to be monitored according to the priority;

[0011] An adjustment module connected to the response module and the order module respectively for re-responding and learning the events to be monitored in sequence according to the response order and adjusting the priority according to the obtained secondary response graph;

[0012] Wherein, the preprocessed data includes time data and frequency data;

[0013] An event response learning model is provided in the learning module for generating a corresponding event response graph according to the corresponding index features.

[0014] Further, the response module includes:

[0015] A response platform for responding to the events to be monitored;

[0016] A time monitor connected to the response platform for monitoring the response time corresponding to the completion of the response of the events to be monitored;

[0017] A frequency monitor connected to the response platform for counting the number of occurrences of the same events to be monitored within a fixed time and calculating the corresponding occurrence frequency,

[0018] Wherein, the occurrence frequency is the quotient of the fixed time and the number of occurrences.

[0019] Further, the learning module includes:

[0020] A fitter for fitting the response time and the occurrence frequency to generate corresponding time fitting data and frequency fitting data;

[0021] A preprocessor, which is connected to the fitter, is used to preprocess the time fitting data and the frequency fitting data, and generate corresponding preprocessed data;

[0022] A learner, which is connected to the preprocessor, is used to select several index features and learn the preprocessed data.

[0023] Further, the sequence module includes:

[0024] An analyzer, which is used to analyze the event response graph according to the index features and obtain a priority result;

[0025] A scheduler, which is connected to the analyzer, is used to classify the events to be monitored according to the priority result;

[0026] A sequencer, which is connected to the analyzer, is used to determine the response order of the events to be monitored according to the priority result,

[0027] Wherein, a response threshold is set in the analyzer.

[0028] Further, when the event to be monitored enters the response platform, the time monitor starts timing, and when the event to be monitored completes the response, the time monitor stops timing and saves the response time;

[0029] The frequency monitor marks the event to be monitored. When the same event to be monitored enters the response platform again, the frequency monitor starts counting. When the fixed time ends, the frequency monitor counts the occurrence frequency of the event to be monitored,

[0030] Wherein, a calculation device is provided in the frequency monitor to calculate the occurrence frequency.

[0031] Further, the learning module fits the response time and the occurrence frequency, and generates several preprocessed data with a sampling rate of the standard sampling rate according to the index features. The preprocessed data enters the event response learning model for learning and generates a corresponding event response graph,

[0032] Wherein, the standard sampling rate is the sampling rate that the event response learning model can recognize;

[0033] The index features are the length of the response time, the magnitude of the standard sampling rate, and / or the level of the occurrence frequency.

[0034] Further, the sequence module receives the event response graph and compares the event response graph with the response threshold;

[0035] The scheduler marks the events to be monitored below the response threshold as variable-priority events and the events to be monitored above the response threshold as high-priority events.

[0036] Among them, in the sequencer, the high-priority events are preferentially responded to.

[0037] Further, the adjustment module sends a re-learning instruction to the several response modules, and the response modules re-respond to the events to be monitored according to the priority and perform secondary learning to generate the secondary response graph.

[0038] Further, the secondary response graph is compared with the response threshold. When the secondary response graph is less than the response threshold, the priority is not adjusted. When the secondary response graph is greater than the response threshold, some variable-priority events are re-marked as high-priority events.

[0039] Further, an exit mechanism is provided in the sequencing module. If no high-priority event is monitored within the fixed time, the high-priority event is automatically re-marked as a variable-priority event.

[0040] Compared with the prior art, the present invention uses several response modules for collecting the response time and occurrence frequency of the events to be monitored, a learning module for preprocessing the response time and occurrence frequency to generate corresponding preprocessed data, selecting several index features of the preprocessed data for learning, and generating a corresponding event response graph, a sequencing module for determining the priority of the events to be monitored according to the event response graph and determining the response order of the events to be monitored according to the priority, and an adjustment module for re-responding to and learning the events to be monitored in sequence according to the response order and adjusting the priority according to the obtained secondary response graph. The present invention can monitor the response efficiency of the events to be monitored in real time, allocate priorities according to the results of machine learning, improve the processing efficiency of the system, and ensure the timely transmission of event information and the reasonable allocation of resources.

[0041] Further, by setting a time monitor and a frequency monitor in the response module, the response efficiency of the events to be monitored can be monitored in real time, and the accuracy of the machine learning results is improved.

[0042] Further, by fitting and preprocessing the response time and occurrence frequency in the learning module to obtain preprocessed data, the error in the learning results caused by incorrect processing of the preprocessed data in machine learning is eliminated, and the learning results are made more accurate.

[0043] Further, by setting a scheduler and a sequencer in the sequencing module, the priority of the events to be monitored can be quickly determined, and a response can be made preferentially to urgent events, improving the processing efficiency of the system and ensuring the timely transmission and processing of event information.

[0044] Furthermore, by setting a response threshold and comparing the event response graph and the secondary response graph with the response threshold, the screening of the priorities of the events to be monitored is realized, which facilitates the real-time adjustment of the events to be monitored according to the priorities and ensures the reasonable allocation of resources.

[0045] Furthermore, by setting an exit mechanism, the conversion of high-priority events and variable-priority events is ensured, and the unreasonable allocation of resources is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic structural diagram of the information scheduling system based on event response of the present invention;

[0047] Figure 2 It is a schematic structural diagram of the response module of the present invention;

[0048] Figure 3 It is a schematic structural diagram of the learning module of the present invention;

[0049] Figure 4 It is a schematic structural diagram of the sequence module of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0052] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention.

[0053] In addition, it should be noted that in the description of the present invention, unless otherwise clearly defined and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0054] Please refer to Figure 1 as shown in the figure, which is a schematic structural diagram of the information scheduling system based on event response of the present invention, including:

[0055] A number of response modules, which are used to collect the response time and occurrence frequency of the events to be monitored;

[0056] A learning module, which is connected to a number of response modules, used to preprocess the response time and occurrence frequency, generate corresponding preprocessed data, select several index features of the preprocessed data for learning, and generate corresponding event response diagrams;

[0057] A sequence module, which is connected to the learning module, used to determine the priority of the events to be monitored according to the event response diagram, and determine the response sequence of the events to be monitored according to the priority;

[0058] An adjustment module, which is respectively connected to the response module and the sequence module, used to respond to and learn the events to be monitored again in sequence according to the response sequence, and adjust the priority according to the obtained secondary response diagram;

[0059] Among them, the preprocessed data includes time data and frequency data;

[0060] An event response learning model is provided in the learning module, used to generate corresponding event response diagrams according to the corresponding index features.

[0061] By setting a number of response modules, which are used to collect the response time and occurrence frequency of the events to be monitored, a learning module, used to preprocess the response time and occurrence frequency, generate corresponding preprocessed data, select several index features of the preprocessed data for learning, and generate corresponding event response diagrams, a sequence module, used to determine the priority of the events to be monitored according to the event response diagram, and determine the response sequence of the events to be monitored according to the priority, and an adjustment module, used to respond to and learn the events to be monitored again in sequence according to the response sequence, and adjust the priority according to the obtained secondary response diagram, the present invention can monitor the response efficiency of the events to be monitored in real time, allocate priorities according to the results of machine learning, improve the processing efficiency of the system, and ensure the timely transmission of event information and the reasonable allocation of resources.

[0062] Please refer to Figure 2 as shown in the figure, which is a schematic structural diagram of the response module of the present invention, including:

[0063] A response platform, which is used to respond to the events to be monitored;

[0064] A time monitor, which is connected to the response platform, used to monitor the response time corresponding to the completion of the response of the events to be monitored;

[0065] A frequency monitor, which is connected to a response platform, is used to count the number of occurrences of the same event to be monitored within a fixed time and calculate the corresponding occurrence frequency.

[0066] Among them, the occurrence frequency is the quotient of the fixed time and the number of occurrences.

[0067] By setting a time monitor and a frequency monitor in the response module, the response efficiency of the event to be monitored can be monitored in real time, and the accuracy of the machine learning results is improved.

[0068] Please refer to Figure 3 As shown in the figure, it is a schematic structural diagram of the learning module of the present invention, including:

[0069] A fitter, which is used to fit the response time and the occurrence frequency to generate corresponding time fitting data and frequency fitting data;

[0070] A preprocessor, which is connected to the fitter, is used to preprocess the time fitting data and the frequency fitting data and generate corresponding preprocessed data;

[0071] A learner, which is connected to the preprocessor, is used to select several index features and learn the preprocessed data.

[0072] By fitting and preprocessing the response time and the occurrence frequency in the learning module, preprocessed data is obtained, eliminating the error in the learning results in machine learning caused by incorrect processing of the preprocessed data, and making the learning results more accurate.

[0073] Please refer to Figure 4 As shown in the figure, it is a schematic structural diagram of the sequential module of the present invention, including:

[0074] An analyzer, which is used to analyze the event response graph according to the index features and obtain a priority result;

[0075] A scheduler, which is connected to the analyzer, is used to classify the events to be monitored according to the priority result;

[0076] A sequencer, which is connected to the analyzer, is used to determine the response order of the events to be monitored according to the priority result.

[0077] Among them, a response threshold is set in the analyzer.

[0078] By setting a scheduler and a sequencer in the sequential module, the priority of the events to be monitored can be quickly determined, and a response can be made to urgent events first, improving the processing efficiency of the system and ensuring the timely transmission and processing of event information.

[0079] Specifically, when the event to be monitored enters the response platform, the time monitor starts timing. When the event to be monitored completes the response, the time monitor stops timing and saves the response time.

[0080] The frequency monitor marks the events to be monitored. When the same event to be monitored enters the response platform again, the frequency monitor starts counting. At the end of a fixed time, the frequency monitor counts the occurrence frequency of the event to be monitored.

[0081] Among them, a computing device is provided in the frequency monitor to calculate the occurrence frequency.

[0082] Embodiment 1:

[0083] Suppose event A to be monitored enters the response platform at 0:00, and the response platform responds to it. The time monitor starts timing. Event A to be monitored completes the response at 0:11, and the time monitor stops timing. Then the response time of event A to be monitored is 11 minutes.

[0084] Embodiment 2:

[0085] Suppose the fixed time is 20 minutes. When event B to be monitored enters the response platform for the first time within the fixed time, the response platform marks it. If the response platform identifies that the marked event B to be monitored enters the response platform 4 times, at the end of a fixed time, the computing device calculates the occurrence frequency of event B to be monitored as 5 minutes / time.

[0086] Specifically, the learning module fits the response time and the occurrence frequency, and generates a number of preprocessing data with a sampling rate of the standard sampling rate according to the index characteristics. The preprocessing data enters the event response learning model for learning and generates a corresponding event response diagram.

[0087] Among them, the standard sampling rate is the sampling rate that the event response learning model can identify;

[0088] The index characteristics are the length of the response time, the size of the standard sampling rate, and / or the level of the occurrence frequency.

[0089] In a specific implementation, when the preferred standard sampling rate is 160 per second, the learning effect of the event response model on the preprocessing data is the best and the result is the most accurate.

[0090] Specifically, the sequence module receives the event response diagram and compares the event response diagram with the response threshold;

[0091] The scheduler marks the events to be monitored with a response threshold lower than the response threshold as variable priority events, and marks the events to be monitored with a response threshold higher than the response threshold as high-priority events.

[0092] Among them, in the sequencer, high-priority events are preferentially responded to.

[0093] Embodiment 3:

[0094] Set the response threshold to 80. If the value on the event response graph corresponding to the event A to be monitored is 75, which is lower than the response threshold, then mark the event A to be monitored as a variable-priority event.

[0095] If the value on the event response graph corresponding to the event B to be monitored is 85, which is higher than the response threshold, then mark the event B to be monitored as a high-priority event.

[0096] In a specific implementation, if the priority of the event B to be monitored is higher than that of the event A to be monitored, then the response order is: the event B to be monitored > the event A to be monitored.

[0097] Specifically, the adjustment module sends a re-learning instruction to several response modules. The response modules re-respond to the events to be monitored according to the priority and perform secondary learning to generate a secondary response graph.

[0098] Specifically, compare the secondary response graph with the response threshold. When the secondary response graph is less than the response threshold, do not adjust the priority. When the secondary response graph is greater than the response threshold, re-mark some variable-priority events as high-priority events.

[0099] Example 4:

[0100] Set the response threshold to 80. If the value on the secondary response graph corresponding to the high-priority event A is 89, the value on the secondary response graph corresponding to the variable-priority event B is 75, and the value on the secondary response graph corresponding to the variable-priority event C is 79, then re-mark the variable-priority event C as a high-priority event.

[0101] By setting the response threshold and comparing the event response graph and the secondary response graph with the response threshold, the screening of the priorities of the events to be monitored is realized, which facilitates the real-time adjustment of the events to be monitored according to the priorities and ensures the reasonable allocation of resources.

[0102] Specifically, there is an exit mechanism in the sequence module. If no high-priority event is detected within a fixed time, the high-priority event is automatically re-marked as a variable-priority event.

[0103] Example 5:

[0104] Set the fixed time to 20 minutes. Mark the event A to be monitored as a high-priority event within the first round of fixed time. If the event A to be monitored is not detected within the second round of fixed time, then at the end of the second round of fixed time, automatically re-mark the event A to be monitored as a variable-priority event.

[0105] By setting the exit mechanism, the conversion between high-priority events and variable-priority events is ensured, and the unreasonable allocation of resources is avoided.

[0106] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easily understood by those skilled in the art that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0107] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An information dispatching system based on event response, characterized in that: include: Several response modules, which are used to collect the response time and occurrence frequency of the events to be monitored; A learning module, which is connected to the plurality of response modules, and is used to preprocess the response time and the occurrence frequency, generate corresponding preprocessed data, select a plurality of indicator features of the preprocessed data for learning, and generate a corresponding event response graph; A sequence module, connected to the learning module, for determining the priority of the event to be monitored according to the event response graph, and determining the response sequence of the event to be monitored according to the priority; An adjustment module, which is connected to the response module and the sequence module respectively, and is used to respond to and learn the events to be monitored again in sequence according to the response sequence, and adjust the priority according to the obtained secondary response graph; Wherein, the preprocessed data includes time data and frequency data; The learning module is provided with an event response learning model for generating a corresponding event response graph according to corresponding indicator features.

2. The information dispatching system based on event response according to claim 1, characterized in that: The response module comprises: A response platform, which is used to respond to the event to be monitored; A time monitor, which is connected to the response platform and is used to monitor the response time corresponding to the completion of the response to the event to be monitored; A frequency monitor, which is connected to the response platform, is used to count the number of occurrences of the same event to be monitored within a fixed time and calculate the corresponding occurrence frequency, The occurrence frequency is the quotient of the fixed time and the number of occurrences.

3. The information dispatching system based on event response according to claim 2 is characterized in that: The learning module includes: A fitter, which is used to fit the response time and the occurrence frequency to generate corresponding time fitting data and frequency fitting data; A preprocessor, connected to the fitter, for preprocessing the time fitting data and the frequency fitting data and generating corresponding preprocessed data; A learner is connected to the preprocessor and is used to select a number of indicator features and learn the preprocessed data.

4. The information dispatching system based on event response according to claim 3 is characterized in that: The sequence module comprises: An analyzer, which is used to analyze the event response graph according to the indicator characteristics and obtain a priority result; A scheduler, connected to the analyzer, for classifying the events to be monitored according to the priority results; A sequencer, connected to the analyzer, for determining a response sequence of the events to be monitored according to the priority results, Wherein, a response threshold is provided in the analyzer.

5. The information dispatching system based on event response according to claim 4, characterized in that: When the event to be monitored enters the response platform, the time monitor starts timing, and when the event to be monitored completes the response, the time monitor stops timing and saves the response time; The frequency monitor marks the event to be monitored. When the same event to be monitored enters the response platform again, the frequency monitor starts counting. When the fixed time is over, the frequency monitor counts the occurrence frequency of the event to be monitored. Wherein, the frequency monitor is provided with a calculation device for calculating the occurrence frequency.

6. The information dispatching system based on event response according to claim 5, characterized in that: The learning module fits the response time and the occurrence frequency, and generates a number of pre-processed data with a sampling rate of a standard sampling rate according to the indicator characteristics. The pre-processed data enters the event response learning model for learning, and generates a corresponding event response graph. Wherein, the standard sampling rate is a sampling rate that can be recognized by the event response learning model; The indicator characteristics are response time, standard sampling rate and / or occurrence frequency.

7. The information dispatching system based on event response according to claim 6, characterized in that: The sequence module receives the event response graph and compares the event response graph with the response threshold; The scheduler marks the events to be monitored that are lower than the response threshold as variable priority events, and marks the events to be monitored that are higher than the response threshold as high priority events, Wherein, in the sequencer, the high priority event is responded to first.

8. The information dispatching system based on event response according to claim 7, characterized in that: The adjustment module sends a re-learning instruction to the plurality of response modules, and the response modules respond to the event to be monitored again according to the priority and perform secondary learning to generate the secondary response graph.

9. The information dispatching system based on event response according to claim 8, characterized in that: The secondary response graph is compared with the response threshold. When the secondary response graph is smaller than the response threshold, the priority is not adjusted. When the secondary response graph is larger than the response threshold, some variable priority events are re-marked as high priority events.

10. The information dispatching system based on event response according to claim 9, characterized in that: An exit mechanism is provided in the sequence module. If the high priority event is not detected within the fixed time, the high priority event is automatically re-marked as a variable priority event.

Images