Traffic big data prediction system based on artificial intelligence

Through the traffic big data prediction system based on artificial intelligence, the BP neural network is used to predict the number of passengers in railway transportation, solving the problem of improper configuration of carriages in railway transportation, achieving sufficient capacity and resource conservation.

CN118333233BActive Publication Date: 2024-12-03BEIJING ZHONGKE JIANYOU TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410589910.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-13
Publication Date
2024-12-03
Estimated Expiration
2044-05-13

AI Technical Summary

Technical Problem

It is difficult to accurately predict the number of passengers departing from the starting station during railway transportation, resulting in insufficient or excessive number of cars, resulting in waste of capacity and insufficient resources.

Method used

Using a traffic big data prediction system based on artificial intelligence, the historical data is learned multiple times through the BP neural network, combining the number of one-way mileage, number of parking stations and passenger information, intelligently predict the number of passengers at the starting station on the day, thereby dynamically adjusting the carriage configuration. .

Benefits of technology

Accurate passenger number prediction for railway transportation is achieved, carriage configuration is optimized, sufficient capacity is ensured and resource waste is reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118333233B_ABST
    Figure CN118333233B_ABST
Patent Text Reader

Abstract

The present invention relates to a traffic big data prediction system based on artificial intelligence, comprising: a prediction execution device, which is used to intelligently predict the predicted value of the number of passengers at the departure station of the set railway train on the day based on the intelligent prediction body using various travel data of the set railway train and various ride information corresponding to the set number of days before the day of the set railway train; a dynamic control device, which is used to determine the number of carriages required to be configured for the set railway train based on the predicted value of the intelligent prediction. The traffic big data prediction based on artificial intelligence of the present invention is intelligently designed and easy to operate. Since it is possible to accurately predict the number of departure passengers at the departure station every day for the set railway train using the artificial intelligence mode, and then dynamically determine the corresponding number of departure station carriage allocations, it effectively adjusts the contradiction between the limited number of departure station carriages and the random dynamic changes in the number of passengers departing from the departure station, and takes into account both sufficient transportation capacity and resource conservation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of big data, and in particular to a traffic big data prediction system based on artificial intelligence. Background Art

[0002] Railway transportation is one of the important branches in the field of transportation. Railway transportation is a mode of transportation that uses railway trains to transport passengers and goods. It plays an important role in the social material production process. Its characteristics are large transportation volume, high speed, low cost, and generally not restricted by climatic conditions. It is suitable for long-distance transportation of bulky and heavy goods.

[0003] However, in the actual management of railway transportation, there is a contradiction between limited transportation resources and the randomly changing transportation quantity. For example, there is a contradiction between the limited number of carriages at the departure station and the randomly changing number of passengers departing from the departure station. The main reason why this contradiction is difficult to adjust is that it is difficult to accurately predict the number of passengers departing from the departure station, resulting in the number of carriages at the departure station controlled by the transportation management department every day being too much or too little relative to the number of passengers departing from the departure station, resulting in a waste of limited computing resources or a dilemma of insufficient transportation capacity. Summary of the invention

[0004] In order to solve the technical problems in the prior art, the present invention provides a traffic big data prediction system based on artificial intelligence, which can accurately predict the number of passengers departing from the departure station every day for a set railway train using an artificial intelligence model, and then dynamically determine the corresponding number of carriages allocated at the departure station, thereby effectively adjusting the contradiction between the limited number of carriages at the departure station and the random dynamic changes in the number of passengers departing from the departure station, and taking into account sufficient capacity and resource conservation.

[0005] According to the present invention, a traffic big data prediction system based on artificial intelligence is provided, the system comprising:

[0006] The first parsing unit is used to obtain various travel data of a set railway train, wherein the various travel data of the set railway train include the one-way mileage, the number of stop stations and the average stop time of the set railway train;

[0007] The second parsing mechanism is used to obtain the individual pieces of riding information corresponding to the set number of days before the current day of the set railway train, and the single piece of riding information corresponding to each day of the set railway train is the number of passengers at the departure station of the set railway train on that day;

[0008] A multi-layer reconstruction mechanism, used for performing multiple learning on the BP neural network to obtain an intelligent prediction body, wherein the number of learning performed by the BP neural network is proportional to the one-way mileage of the set railway train number;

[0009] A prediction execution device, connected to the first analysis mechanism, the second analysis mechanism and the multi-layer reconstruction mechanism, respectively, for intelligently predicting the predicted value of the number of passengers at the departure station of the set railway train on the day by using various itinerary data of the set railway train and various pieces of riding information corresponding to a set number of days before the day based on the intelligent prediction body;

[0010] A dynamic control device, connected to the prediction execution device, is used to determine the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day predicted by intelligent prediction;

[0011] Wherein, determining the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction includes: the smaller the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction is, the smaller the number of carriages required to be configured for the determined set railway train is;

[0012] Among them, the BP neural network is subjected to multiple learning to obtain an intelligent prediction body, and the number of learnings performed by the BP neural network is proportional to the one-way mileage of the set railway train, including: taking the known number of passengers at the departure station of the set railway train on a certain day in the past as the output content of the BP neural network, taking various travel data of the set railway train and various pieces of riding information corresponding to each set number of days before the certain day in the past as various input contents of the BP neural network, to complete a single learning operation of the BP neural network.

[0013] It can be seen that the present invention has at least the following three significant substantive features:

[0014] Substantive feature 1: A customized intelligent prediction body is designed for intelligent prediction of the number of passengers at the departure station of a set railway train on the day. The intelligent prediction body is a BP neural network that has performed multiple learnings and the number of learnings performed by the BP neural network is proportional to the one-way mileage of the set railway train, thereby ensuring the effectiveness and stability of the intelligent prediction results;

[0015] Substantive feature 2: Targeted screening of various basic information for intelligent prediction, including various travel data of a set railway train and various travel information corresponding to a set number of days before the current day, and various travel data of the set railway train including the one-way mileage, number of stop stations and average stop time of the set railway train;

[0016] Substantive feature three: The number of carriages required for the set railway train is determined based on the predicted value of the number of passengers at the departure station of the day based on intelligent prediction. The smaller the predicted value of the number of passengers at the departure station of the day based on intelligent prediction, the smaller the number of carriages required for the set railway train is, thereby minimizing the waste of railway transportation resources while ensuring the effective transportation of passengers.

[0017] The traffic big data prediction based on artificial intelligence of the present invention is intelligently designed and easy to operate. Since it can accurately predict the number of passengers departing from the departure station every day by using artificial intelligence mode for the set railway train number, and then dynamically determine the corresponding number of carriages allocated at the departure station, it effectively adjusts the contradiction between the limited number of carriages at the departure station and the random dynamic changes in the number of passengers departing from the departure station, and takes into account sufficient transportation capacity and resource conservation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0019] Figure 1 It is an internal structure diagram of the traffic big data prediction system based on artificial intelligence according to the first embodiment of the present invention.

[0020] Figure 2 It is an internal structure diagram of a traffic big data prediction system based on artificial intelligence according to the second embodiment of the present invention.

[0021] Figure 3 It is an internal structure diagram of a traffic big data prediction system based on artificial intelligence according to the third embodiment of the present invention. DETAILED DESCRIPTION

[0022] The implementation scheme of the traffic big data prediction system based on artificial intelligence of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Figure 1 The internal structure diagram of the traffic big data prediction system based on artificial intelligence according to the first embodiment of the present invention is shown, and the system includes:

[0024] The first parsing unit is used to obtain various travel data of a set railway train, wherein the various travel data of the set railway train include the one-way mileage, the number of stop stations and the average stop time of the set railway train;

[0025] The second parsing mechanism is used to obtain the individual pieces of riding information corresponding to the set number of days before the current day of the set railway train, and the single piece of riding information corresponding to each day of the set railway train is the number of passengers at the departure station of the set railway train on that day;

[0026] Specifically, the first analysis mechanism and the second analysis mechanism may be implemented by using a first CPLD chip and a second CPLD chip respectively;

[0027] For example, the first CPLD chip is used to obtain various travel data of a set railway train, wherein the various travel data of the set railway train include the one-way mileage, the number of stop stations and the average stop time of the set railway train;

[0028] And, the second CPLD chip is used to obtain the respective pieces of riding information corresponding to the set number of days before the current day of the set railway train, and the single piece of riding information corresponding to each day of the set railway train is the number of passengers at the departure station of the set railway train on that day;

[0029] A multi-layer reconstruction mechanism, used for performing multiple learning on the BP neural network to obtain an intelligent prediction body, wherein the number of learning performed by the BP neural network is proportional to the one-way mileage of the set railway train number;

[0030] A prediction execution device, connected to the first analysis mechanism, the second analysis mechanism and the multi-layer reconstruction mechanism, respectively, for intelligently predicting the predicted value of the number of passengers at the departure station of the set railway train on the day by using various itinerary data of the set railway train and various pieces of riding information corresponding to a set number of days before the day based on the intelligent prediction body;

[0031] A dynamic control device, connected to the prediction execution device, is used to determine the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day predicted by intelligent prediction;

[0032] Wherein, determining the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction includes: the smaller the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction is, the smaller the number of carriages required to be configured for the determined set railway train is;

[0033] The BP neural network is subjected to multiple learning to obtain an intelligent prediction body, and the number of learnings performed by the BP neural network is proportional to the one-way mileage of the set railway train number, including: taking the known number of passengers at the departure station of the set railway train number on a certain day in the past as the output content of the BP neural network, taking various itinerary data of the set railway train number and various pieces of riding information corresponding to each set number of days before the certain day in the past as various input contents of the BP neural network, and completing a single learning operation of the BP neural network;

[0034] The step of obtaining various travel data of a set railway train, wherein the various travel data of the set railway train include the one-way mileage, the number of stop stations and the average stop time of the set railway train, comprises: obtaining the stop times corresponding to the set railway train at each stop station, calculating the arithmetic mean of the stop times to obtain the average stop time of the set railway train;

[0035] Among them, based on the intelligent prediction body, the travel data of the set railway train and the riding information corresponding to the set number of days before the set railway train are used to intelligently predict the predicted value of the number of passengers at the departure station of the set railway train on the day, including: synchronously inputting the travel data of the set railway train and the riding information corresponding to the set number of days before the set railway train into the intelligent prediction body, and running the intelligent prediction body to obtain the predicted value of the number of passengers at the departure station of the set railway train on the day output by the intelligent prediction body.

[0036] Figure 2 It is an internal structure diagram of a traffic big data prediction system based on artificial intelligence according to the second embodiment of the present invention.

[0037] exist Figure 2 In, with Figure 1 Differently, the traffic big data prediction system based on artificial intelligence shown in the second embodiment of the present invention may also include:

[0038] a volume detection component, connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, respectively, for measuring the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively;

[0039] The volume detection component is connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively, and is used to measure the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively. The volume detection component includes a plurality of volume measurement units, which are used to be connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively, so as to complete the measurement of the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively;

[0040] The volume detection component includes a plurality of volume measurement units, which are respectively connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device to respectively measure the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: the plurality of volume measurement units are a plurality of visual detectors, which are respectively connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device to respectively measure the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device;

[0041] Wherein, the plurality of volume measurement units are a plurality of visual detectors, which are used to be connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively, so as to complete the respective measurement of the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively, including: the structures of the plurality of visual detectors are the same;

[0042] And wherein the multiple volume measurement units are multiple visual detectors, which are used to connect to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively to complete the respective measurements of the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device, and also include: each of the multiple visual detectors includes a stereo camera.

[0043] Figure 3 It is an internal structure diagram of a traffic big data prediction system based on artificial intelligence according to the third embodiment of the present invention.

[0044] exist Figure 3 In, with Figure 1 Differently, the traffic big data prediction system based on artificial intelligence shown in the third embodiment of the present invention may also include:

[0045] a synchronous operation mechanism, connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the plurality of volume measurement units of the prediction execution device, respectively, for performing a synchronous operation between the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device;

[0046] The synchronous operation mechanism is respectively connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the plurality of volume measurement units of the prediction execution device, and is used to perform the synchronous operation between the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: the synchronous operation mechanism performs the synchronous operation between the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device based on a square wave waveform;

[0047] And wherein, the synchronous operation mechanism is respectively connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and multiple volume measurement units of the prediction execution device, and is used to perform synchronous operations between the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: using an ASIC chip to implement the synchronous operation mechanism.

[0048] In addition, in the traffic big data prediction system based on artificial intelligence, the number of passengers at the departure station of a set railway train number on a certain day in the past is used as the output content of the BP neural network, and the various travel data of the set railway train number and the various ride information corresponding to the set number of days before the set railway train number are used as the various input contents of the BP neural network. The single learning operation of the BP neural network is completed, including: using a numerical simulation mode to realize the use of the known number of passengers at the departure station of a set railway train number on a certain day in the past as the output content of the BP neural network, and the various travel data of the set railway train number and the various ride information corresponding to the set number of days before the set railway train number are used as the various input contents of the BP neural network to complete the simulation and test of the single learning operation of the BP neural network;

[0049] The number of passengers of the departure station of a set railway train number on a certain day in the past is used as the output content of the BP neural network, and the various travel data of the set railway train number and the various travel information corresponding to the set number of days before the certain day in the past are used as the various input contents of the BP neural network. The single learning operation of the BP neural network also includes: each learning operation of the BP neural network corresponds to each piece of associated data corresponding to the set railway train number on each day in the past;

[0050] Among them, each learning operation of the BP neural network corresponds to each piece of associated data corresponding to the set railway train number on each past day, including: the associated data corresponding to the set railway train number on a certain day in the past is each piece of travel information corresponding to a set number of days before the certain day in the past.

[0051] It will be appreciated by those skilled in the art that various modifications and changes may be made without departing from the scope and spirit of the present invention. It should therefore be understood that the above embodiments are for illustration only and are not intended to be limiting. Because the scope of the present invention is defined by the claims rather than the foregoing description, any changes and modifications that fall within the scope and boundaries of the claims or the equivalents of these scopes and boundaries are subject to the claims.

Claims

1. A traffic big data prediction system based on artificial intelligence, characterized in that: The system comprises: The first parsing unit is used to obtain various travel data of a set railway train, wherein the various travel data of the set railway train include the one-way mileage, the number of stop stations and the average stop time of the set railway train; The second parsing mechanism is used to obtain the individual pieces of riding information corresponding to the set number of days before the current day of the set railway train, and the single piece of riding information corresponding to each day of the set railway train is the number of passengers at the departure station of the set railway train on that day; A multi-layer reconstruction mechanism, used for performing multiple learning on the BP neural network to obtain an intelligent prediction body, wherein the number of learning performed by the BP neural network is proportional to the one-way mileage of the set railway train number; A prediction execution device, connected to the first analysis mechanism, the second analysis mechanism and the multi-layer reconstruction mechanism, respectively, for intelligently predicting the predicted value of the number of passengers at the departure station of the set railway train on the day by using various itinerary data of the set railway train and various pieces of riding information corresponding to a set number of days before the day based on the intelligent prediction body; A dynamic control device, connected to the prediction execution device, is used to determine the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day predicted by intelligent prediction; Wherein, determining the number of carriages required to be configured for the set railway train based on the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction includes: the smaller the predicted value of the number of passengers of the set railway train at the departure station of the day according to the intelligent prediction is, the smaller the number of carriages required to be configured for the determined set railway train is; The BP neural network is subjected to multiple learning to obtain an intelligent prediction body, and the number of learnings performed by the BP neural network is proportional to the one-way mileage of the set railway train number, including: taking the known number of passengers at the departure station of the set railway train number on a certain day in the past as the output content of the BP neural network, taking various itinerary data of the set railway train number and various pieces of riding information corresponding to each set number of days before the certain day in the past as various input contents of the BP neural network, and completing a single learning operation of the BP neural network; The numerical simulation mode is adopted to realize that the number of passengers of the departure station of the set railway train number at a certain day in the past is used as the output content of the BP neural network, and the various travel data of the set railway train number and the various pieces of riding information corresponding to the set number of days before the certain day in the past are used as the various input contents of the BP neural network to complete the simulation and test of the single learning operation of the BP neural network; Wherein, each learning operation of the BP neural network corresponds to each piece of associated data corresponding to the set railway train number on each past day; wherein each learning operation of the BP neural network corresponds to each piece of associated data corresponding to the set railway train number on each past day, including: the associated data corresponding to the set railway train number on a certain past day is each piece of riding information corresponding to each set number of days before the certain past day; obtaining each piece of travel data of the set railway train number, the each piece of travel data of the set railway train number includes the one-way mileage, the number of stop stations and the average stop time of the set railway train number, including: obtaining each piece of stop time corresponding to the set railway train number at each stop station, and calculating the arithmetic mean of each piece of stop time to obtain the average stop time of the set railway train number; Among them, based on the intelligent prediction body, the travel data of the set railway train and the riding information corresponding to the set number of days before the set railway train are used to intelligently predict the predicted value of the number of passengers at the departure station of the set railway train on the day, including: synchronously inputting the travel data of the set railway train and the riding information corresponding to the set number of days before the set railway train into the intelligent prediction body, and running the intelligent prediction body to obtain the predicted value of the number of passengers at the departure station of the set railway train on the day output by the intelligent prediction body.

2. The traffic big data prediction system based on artificial intelligence as claimed in claim 1, characterized in that: The system further comprises: a volume detection component, connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, respectively, for measuring the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively; Among them, the volume detection component is respectively connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, and is used to respectively measure the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device. The volume detection component includes a plurality of volume measurement units, which are respectively connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device to complete the respective measurements of the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device.

3. The traffic big data prediction system based on artificial intelligence as claimed in claim 2, characterized in that: The volume detection component includes a plurality of volume measurement units, which are used to respectively connect with the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device to complete the respective measurement of the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: the plurality of volume measurement units are a plurality of visual detectors, which are used to respectively connect with the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device to complete the respective measurement of the current real-time volume values ​​of the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device.

4. The traffic big data prediction system based on artificial intelligence as claimed in claim 3, characterized in that: The multiple volume measurement units are multiple visual detectors, which are used to connect to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively to complete the respective measurements of the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: the structures of the multiple visual detectors are the same.

5. The traffic big data prediction system based on artificial intelligence as claimed in claim 4, characterized in that: The multiple volume measurement units are multiple visual detectors, which are used to connect to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device respectively to complete the respective measurements of the current real-time volume values ​​of the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device. It also includes: each of the multiple visual detectors includes a stereo camera.

6. The traffic big data prediction system based on artificial intelligence according to any one of claims 1 to 5, characterized in that: The system further comprises: The synchronous operation mechanism is respectively connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the multiple volume measurement units of the prediction execution device, and is used to perform synchronous operations between the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device.

7. The traffic big data prediction system based on artificial intelligence as claimed in claim 6, characterized in that: A synchronous operation mechanism is respectively connected to the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and multiple volume measurement units of the prediction execution device, and is used to perform synchronous operations between the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: the synchronous operation mechanism performs synchronous operations between the first analysis mechanism, the second analysis mechanism, the multi-layer reconstruction mechanism and the prediction execution device based on a square wave waveform.

8. The traffic big data prediction system based on artificial intelligence as claimed in claim 6, characterized in that: A synchronous operation mechanism is respectively connected to the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and multiple volume measurement units of the prediction execution device, and is used to perform synchronous operations between the first parsing mechanism, the second parsing mechanism, the multi-layer reconstruction mechanism and the prediction execution device, including: using an ASIC chip to implement the synchronous operation mechanism.