An intelligent control system for digital processing of archives

Abstract

The present invention relates to the field of digital information control technology, and in particular to an intelligent control system for digital processing of archives, comprising analyzing initial identification information during archive processing, determining feature labels and archive feature values ​​under different identification scenarios, determining a reference device according to a standard processing speed of a processing equipment group, and then acquiring historical operation data of the reference device for analysis, determining the influence of the amount of processed data and the amount of unprocessed data in the reference device on the processing speed of the reference device, and generating an influencing parameter model, and then collecting real-time processing information of the reference device, and determining a front-end transmission amount based on the amount of processed data in the real-time processing information, and then comparing the front-end transmission amount with the amount of data to be processed, and controlling the front-end device according to the comparison result, thereby realizing refined control of the equipment operation process and avoiding equipment operation abnormality caused by data backlog in equipment with slow processing.

Description

Technical Field

[0001] The invention relates to the technical field of digital information control, and in particular to an intelligent control system for digital processing of archives. Background Art

[0002] Archive digitization is the process of converting traditional paper archives, audio-visual archives, etc. into digital form through a series of technical means for the convenience of storage, management, retrieval and utilization.

[0003] Prior art CN116401432A discloses a digital archive processing management system and method, including an information collection terminal, an information service terminal and an information access terminal; the information collection terminal is used to collect archive data information, including image information and file information; the information service terminal is used to provide archive data service support and archive data management according to the collected archive data information; the information access terminal is used to provide users with a port for querying and managing archive data, including a data visualization component and an information query component.

[0004] However, when digital processing of archives is carried out, a series of data processing equipment needs to be combined to complete the processing flow of digital processing of archives. However, when multiple data processing equipment are combined for processing, different equipment has different data processing speeds. When the task volume of digital processing of archives increases, if there is a processing device that is continuously overloaded, it is easy to cause the overloaded equipment to run jams, further reducing the efficiency of digital processing of archives. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the background technology and to propose an intelligent control system for digital processing of archives.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An intelligent control system for digital processing of archives, comprising:

[0008] An information collection module is used to collect archive processing information and transmit it to the archive identification module and the equipment analysis module respectively, wherein the archive processing information includes digital processing information and equipment information;

[0009] The archive recognition module is used to extract the initial recognition information from the historical recognition data, and divide the initial recognition information according to the data similarity value to determine the archive data group, and then extract the feature value of the initial recognition information in the archive data group to obtain the feature label, and at the same time determine the archive feature value according to the archive processing volume in the archive data group, and then obtain the real-time information, calculate the similarity value between the real-time information and the feature label of the archive data group, and at the same time determine the task budget of this archive processing based on the archive feature value of the archive data group, and then the archive recognition module transmits the task budget to the equipment analysis module;

[0010] The equipment analysis module is used to obtain the equipment information of the processing equipment group, and determine the benchmark equipment according to the standard processing speed in the equipment information, and then obtain the historical operation data of the benchmark equipment, first determine the processing speed curve and curve function expression of the benchmark equipment in different processing processes based on the continuous processing time and data processing speed in the historical operation data, and determine the slope change function according to the curve function expression, and then select the slope value in the slope change function, and combine it with the processed data volume and unprocessed data volume in the historical operation data into an array, integrate the corresponding arrays in all processing speed curves to obtain a data set, and use the data set as an experimental group for simulation calculation to obtain an influencing parameter model, and then determine the applicable interval in the influencing parameter model according to the task budget, and identify and mark the positive area in the applicable interval, and then the equipment analysis module transmits the influencing parameter model in the applicable interval to the data monitoring module;

[0011] A data monitoring module is used to obtain real-time processing information of the reference device, and determine a minimum slope value in the influencing parameter model based on the amount of processed data in the real-time processing information, and then determine a pre-transmission amount based on the minimum slope value, and transmit the pre-transmission amount to the device control module;

[0012] The device control module is used to compare the amount of data to be processed in the real-time processing information with the amount of front-end transmission, and control the data transmission of the front-end device according to the comparison result.

[0013] As a further solution of the present invention, a method for determining a task budget includes:

[0014] S1: Obtaining historical recognition data in the file recognition module, the historical recognition data includes initial recognition information and file processing volume, the initial recognition information includes file recognition time, file type, handwriting clarity and text density;

[0015] S2: Marking a file recognition process as a single processing process, and obtaining the file processing volume in each single processing process;

[0016] Obtaining initial identification information, and dividing a single processing process according to the initial identification information to obtain a number of file processing groups;

[0017] Among them, in one file processing group, the data similarity value between the initial identification information corresponding to any two single processing processes is greater than or equal to the similarity threshold A1;

[0018] After the file processing group is set, the initial identification information in the file processing group is obtained, and the feature value of the initial identification information is extracted, and the feature value is used as the feature label of this file processing group;

[0019] S3: In an archive processing group, obtain the archive processing volume corresponding to a single processing process, calculate the mean of the archive processing volume, and then mark the mean calculation result as the archive characteristic value;

[0020] S4: When the archive recognition module detects the recognition task, it obtains the real-time initial recognition information and marks it as real-time information. It then calculates the similarity between the real-time information and the feature labels of each archive processing group, identifies the maximum value in the similarity calculation results, and uses the archive feature value of the archive processing group corresponding to the maximum value as the task budget for this archive processing.

[0021] As a further solution of the present invention, a method for determining a reference device includes:

[0022] Obtain equipment information in the processing equipment group. The processing equipment group refers to the processing equipment related to the digital processing of archives. The equipment information includes the standard processing speed of the equipment.

[0023] The standard processing speed of each device in the processing equipment group is obtained, the minimum value of the standard processing speed is identified, and the processing equipment corresponding to the minimum value is obtained and marked as the reference equipment.

[0024] As a further solution of the present invention, a method for determining a processing speed curve and a curve function expression includes:

[0025] Acquire historical operation data of the benchmark device, wherein the historical operation data includes continuous processing time, data processing speed, amount of data to be processed, and amount of data processed of the benchmark device;

[0026] Set the continuous processing time as the horizontal axis and the data processing speed as the vertical axis, set the plane coordinate system, then obtain n processing processes, and draw the curve of the change of data processing speed with the continuous processing time in each processing process in the plane coordinate system to obtain n processing speed curves;

[0027] Mathematical tools are used to perform polynomial fitting on each processing speed curve to obtain the curve function expression Fi, where i represents different processing speed curves and i∈[1,n].

[0028] As a further solution of the present invention, a method for determining a data set includes:

[0029] Select any processing speed curve and mark it as the target curve, obtain the curve function expression Fr of the target curve, perform the first-order derivative operation on the curve function expression Fr, and obtain the slope change function ,in is the first-order derivative of the curve function expression Fr;

[0030] Then, the amount of data to be processed and the amount of data that have been processed of the target curve are obtained. Based on the time length of the target curve, the amount of experimental data d is selected according to the time length. The amount of experimental data d = time length × unit data amount. The unit data amount refers to the minimum number of data points selected in a unit time.

[0031] Then, according to the amount of experimental data, a data point is randomly selected in the target curve, the time value of the data point is obtained, and the time value is input into the slope change function Kr to obtain the slope value. At the same time, the amount of data to be processed and the amount of processed data corresponding to each data point are obtained. The slope value, the amount of data to be processed and the amount of processed data of a data point are taken as an array, and then d arrays are obtained in the target curve, where d represents the amount of experimental data in the target curve;

[0032] All processing speed curves are taken as target curves in turn, and arrays of each processing speed curve are obtained respectively. The arrays of all processing speed curves are integrated to obtain a data set.

[0033] As a further solution of the present invention, a method for determining the influencing parameter model includes:

[0034] The amount of data to be processed and the amount of processed data are used as independent variable factors, the slope value is used as the dependent variable factor, and the array in the data set is used as the experimental group. The experimental group is used as the input value and input into the simulation model for simulation operation, and the simulation operation result is marked as the influencing parameter model;

[0035] Obtain the influencing parameter model and the task budget, and first determine the applicable range of the influencing parameter model based on the task budget. The applicable range refers to the independent variable range limited by the task budget of this archive processing;

[0036] Among them, in the independent variable interval, the sum of the amount of data to be processed and the amount of data processed is less than or equal to the task budget;

[0037] In the applicable interval, a positive area is selected and marked in the applicable interval, wherein the positive area is an area where the slope value is greater than or equal to 0, and then the equipment analysis module transmits the influencing parameter model in the applicable interval to the data monitoring module.

[0038] As a further solution of the present invention, a method for determining the pre-transmission amount includes:

[0039] Monitor the real-time processing information of the benchmark equipment, the real-time processing information including the amount of data to be processed and the amount of data processed;

[0040] The amount of processed data in the real-time processing information is obtained, and within the applicable interval of the influencing parameter model, the minimum value of the slope value is identified and marked as a processing vertex value, wherein the processing vertex value belongs to the positive region;

[0041] The amount of data to be processed corresponding to the processing vertex value is obtained, and the amount of data to be processed is marked as the pre-transmission amount.

[0042] As a further solution of the present invention, a method for the device control module to control data transmission of the front-end device includes:

[0043] Extract the pre-transmission amount, and at the same time obtain the amount of data to be processed in the real-time processing information, compare the pre-transmission amount with the amount of data to be processed, if the amount of data to be processed is less than the pre-transmission amount, generate a transmission signal for the front-end device, and control the front-end device to transmit data to the reference device, conversely, if the amount of data to be processed is greater than or equal to the pre-transmission amount, generate a stop signal for the front-end device, and control the front-end device to stop transmitting data to the reference device.

[0044] As a further solution of the present invention, it also includes a terminal display module, which is used to display the real-time processing information on the terminal display device, so that the staff can understand the real-time progress of the digital processing of the archives.

[0045] Compared with the prior art, the advantages of the present invention are:

[0046] The present invention analyzes the initial recognition information during the archive processing, determines the feature labels and archive feature values ​​under different recognition scenarios, and then estimates the task volume of this processing when the archive is digitally processed, which is conducive to the reasonable arrangement of equipment resources and the optimization of equipment operation plan;

[0047] The present invention determines a benchmark device according to a standard processing speed of a processing equipment group, then obtains historical operating data of the benchmark device for analysis, determines the influence of the amount of processed data and the amount of unprocessed data in the benchmark device on the processing speed of the benchmark device, generates an influencing parameter model, and then collects real-time processing information of the benchmark device, and determines the front-end transmission amount based on the amount of processed data in the real-time processing information, and then compares the front-end transmission amount with the amount of data to be processed, and controls the front-end device according to the comparison result, thereby realizing refined control of the equipment operation process, dynamically adjusting data input according to the actual processing capacity of the equipment, avoiding equipment operation abnormalities caused by data backlog in equipment with slow processing equipment, and further improving the operation efficiency and reliability of the entire system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0050] Reference Figure 1 , an intelligent control system for digital processing of archives, including an information collection module, an archive identification module, an equipment analysis module, a data monitoring module, an equipment control module and a terminal display module;

[0051] The information collection module is used to collect archive processing information, wherein the archive processing information includes digital processing information and equipment information;

[0052] Digital processing information refers to information related to the digital processing of archives, including the amount of archive data; equipment information refers to the processing equipment required for digital processing of archives, including scanners, photographic equipment, storage equipment, and transmission equipment;

[0053] Afterwards, the information collection module transmits the archive processing information to the archive identification module and the equipment analysis module respectively;

[0054] The file recognition module is used to obtain initial recognition information, and estimate the task volume of this file processing based on the initial recognition information to obtain the task budget volume. The specific method for determining the task budget volume includes:

[0055] S1: Obtaining historical recognition data in the file recognition module, wherein the historical recognition data includes initial recognition information and file processing volume, and the initial recognition information includes file recognition time, file type, handwriting clarity, and text density, etc.;

[0056] S2: Marking a file recognition process as a single processing process, and obtaining the file processing volume in each single processing process;

[0057] Obtaining initial identification information, dividing the single processing process according to the initial identification information to obtain a number of file processing groups, wherein in one file processing group, the data similarity value between the initial identification information corresponding to any two single processing processes is greater than or equal to the similarity threshold A1;

[0058] It should be further explained that the data similarity in this embodiment is processed using the cosine similarity algorithm. The specific processing process is prior art and will not be described in detail here. The similarity threshold is obtained by those skilled in the art after big data calculation.

[0059] When the file processing group is set, the initial identification information in the file processing group is obtained, and the feature value is extracted from the initial identification information, and the feature value is used as the feature label of this file processing group. In this embodiment, the feature value is set to the mode, that is, the mode in the initial identification information is identified, and the mode is used as the feature label of this file processing group;

[0060] S3: In an archive processing group, obtain the archive processing amount corresponding to a single processing process, calculate the mean of the archive processing amount, and then mark the mean calculation result as the archive characteristic value, wherein there is only one archive characteristic value in an archive processing group;

[0061] S4: When the file recognition module detects the recognition task, it obtains the real-time initial recognition information and marks it as real-time information. Then, it calculates the similarity between the real-time information and the feature label of each file processing group, identifies the maximum value in the similarity calculation result, and uses the file feature value of the file processing group corresponding to the maximum value as the task budget of this file processing;

[0062] The file recognition module then transmits the task budget to the equipment analysis module;

[0063] The equipment analysis module is used to analyze the processing speed of the processing equipment group based on the equipment information and task budget. The specific analysis methods include:

[0064] Obtain equipment information in the processing equipment group. The processing equipment group refers to the processing equipment related to the digital processing of archives. The equipment information includes the standard processing speed of the equipment.

[0065] Obtaining the standard processing speed of each device in the processing device group, identifying the minimum value of the standard processing speed, and obtaining the processing device corresponding to the minimum value, and marking it as the reference device;

[0066] It should be further clarified that the standard processing speed of the equipment refers to the speed at which the archive processing equipment processes the archive content in the standard environment in which the equipment operates;

[0067] Based on historical operation data, the benchmark equipment is analyzed. The specific analysis methods include:

[0068] SS1: Obtain historical operation data of the benchmark device, wherein the historical operation data includes the continuous processing time, data processing speed, amount of data to be processed, and amount of data processed of the benchmark device;

[0069] The amount of data to be processed refers to the data transmitted from the front-end device to the reference device and waiting to be processed in the reference device;

[0070] The continuous processing time is set as the horizontal axis, the data processing speed is set as the vertical axis, a plane coordinate system is set, and then n processing processes are obtained, and the change curve of the data processing speed versus the continuous processing time in each processing process is plotted in the plane coordinate system to obtain n processing speed curves, where n is a threshold value, and the specific value of n is obtained by those skilled in the art after big data calculation;

[0071] SS2: Use mathematical tools to perform polynomial fitting on each processing speed curve to obtain the curve function expression Fi, where i represents different processing speed curves and i∈[1,n];

[0072] In this embodiment, the mathematical tool uses the polyfit function tool in MATLAB to perform polynomial fitting, and the specific fitting process is a prior art, which will not be described in detail here;

[0073] It should be further explained that a processing speed curve represents the change process of data processing speed of the reference device in a continuous processing process. When the reference device restarts the processing task, a new processing speed curve will be generated at this time;

[0074] SS3: Then select any processing speed curve and mark it as the target curve, obtain the curve function expression Fr of the target curve, perform the first-order derivative operation on the curve function expression Fr, and obtain the slope change function ,in is the first-order derivative of the curve function expression Fr;

[0075] Then, the amount of data to be processed and the amount of data that have been processed of the target curve are obtained, and based on the time length of the target curve, the amount of experimental data d is selected according to the time length, where the amount of experimental data d = time length × unit data amount;

[0076] It should be further explained that the unit data volume refers to the minimum number of data points selected in a unit time. In this embodiment, the unit data volume is a threshold value, and the specific unit data volume is obtained by those skilled in the art after big data calculation;

[0077] Then, according to the amount of experimental data, a data point is randomly selected in the target curve, the time value of the data point is obtained, and the time value is input into the slope change function Kr to obtain the slope value. At the same time, the amount of data to be processed and the amount of processed data corresponding to each data point are obtained. The slope value, the amount of data to be processed and the amount of processed data of a data point are taken as an array, and then d arrays are obtained in the target curve, where d represents the amount of experimental data in the target curve;

[0078] SS4: taking all processing speed curves as target curves in turn, and processing them according to the method in step SS3 above, to obtain an array of each processing speed curve;

[0079] Integrate all arrays of processing speed curves to obtain a data set, where the array is the element in the data set;

[0080] The amount of data to be processed and the amount of processed data are used as independent variable factors, the slope value is used as the dependent variable factor, and the array in the data set is used as the experimental group. The experimental group is used as the input value and input into the simulation model for simulation operation, and then the simulation operation result is marked as the influencing parameter model;

[0081] Among them, the simulation model in this embodiment uses a neural network model algorithm, and the specific simulation calculation process is a prior art, which will not be described in detail here;

[0082] SS5: Obtain the influencing parameter model and the task budget. First, determine the applicable range of the influencing parameter model based on the task budget. The applicable range refers to the independent variable range limited by the task budget of this archive processing. Furthermore, in the independent variable range, the sum of the amount of data to be processed and the amount of data processed is less than or equal to the task budget.

[0083] Then, within the applicable interval, a positive region is selected and the positive region is marked within the applicable interval, and then the equipment analysis module transmits the influencing parameter model within the applicable interval to the data monitoring module, wherein the positive region is an area where the slope value is greater than or equal to 0;

[0084] The data monitoring module is used to monitor the real-time processing information of the reference device, and the real-time processing information includes the amount of data to be processed and the amount of data processed;

[0085] Then, the amount of processed data in the real-time processing information is obtained, and within the applicable interval of the influencing parameter model, the minimum value of the slope value is identified and marked as a processing vertex value, wherein the processing vertex value belongs to the positive region;

[0086] Obtain the amount of data to be processed corresponding to the processing vertex value, and mark the amount of data to be processed as the pre-transmission amount;

[0087] It should be further explained that when the slope value is positive, it indicates that the data processing speed of the reference device is in an increasing state. When the slope value gradually decreases and transitions from a positive value to 0, it indicates that the growth trend of the data processing speed is gradually slowing down. When the slope is 0, the data processing speed is at the maximum value, and the processing efficiency of the reference device is the fastest at this time.

[0088] The data monitoring module then transmits the pre-transmission volume and real-time processing information to the device control module;

[0089] The device control module is used to control the transmission speed of the front-end device of the reference device according to the front-end transmission volume and real-time processing information. The specific control method includes:

[0090] Extracting the pre-transmission amount, and obtaining the amount of data to be processed in the real-time processing information at the same time, comparing the pre-transmission amount with the amount of data to be processed, if the amount of data to be processed is less than the pre-transmission amount, generating a transmission signal for the front-end device, and controlling the front-end device to transmit data to the reference device; conversely, if the amount of data to be processed is greater than or equal to the pre-transmission amount, generating a stop signal for the front-end device, and controlling the front-end device to stop transmitting data to the reference device;

[0091] After that, there is a one-way communication connection between the device control module and the terminal display module;

[0092] The terminal display module is used to display real-time processing information on the terminal display device, so that the staff can understand the real-time progress of the digital processing of the archives.

[0093] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent control system for digital processing of archives, characterized in that: include: An information collection module is used to collect archive processing information and transmit it to the archive identification module and the equipment analysis module respectively, wherein the archive processing information includes digital processing information and equipment information; The archive recognition module is used to extract the initial recognition information from the historical recognition data, and divide the initial recognition information according to the data similarity value to determine the archive data group, and then extract the feature value of the initial recognition information in the archive data group to obtain the feature label, and at the same time determine the archive feature value according to the archive processing volume in the archive data group, and then obtain the real-time information, calculate the similarity value between the real-time information and the feature label of the archive data group, and at the same time determine the task budget of this archive processing based on the archive feature value of the archive data group, and then the archive recognition module transmits the task budget to the equipment analysis module; The equipment analysis module is used to obtain the equipment information of the processing equipment group, and determine the benchmark equipment according to the standard processing speed in the equipment information, and then obtain the historical operation data of the benchmark equipment, first determine the processing speed curve and curve function expression of the benchmark equipment in different processing processes based on the continuous processing time and data processing speed in the historical operation data, and determine the slope change function according to the curve function expression, and then select the slope value in the slope change function, and combine it with the processed data volume and unprocessed data volume in the historical operation data into an array, integrate the corresponding arrays in all processing speed curves to obtain a data set, and use the data set as an experimental group for simulation calculation to obtain an influencing parameter model, and then determine the applicable interval in the influencing parameter model according to the task budget, and identify and mark the positive area in the applicable interval, and then the equipment analysis module transmits the influencing parameter model in the applicable interval to the data monitoring module; A data monitoring module is used to obtain real-time processing information of the reference device, and determine a minimum slope value in the influencing parameter model based on the amount of processed data in the real-time processing information, and then determine a pre-transmission amount based on the minimum slope value, and transmit the pre-transmission amount to the device control module; The device control module is used to compare the amount of data to be processed in the real-time processing information with the amount of front-end transmission, and control the data transmission of the front-end device according to the comparison result.

2. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: Methods for determining task budgets include: S1: Obtaining historical recognition data in the file recognition module, the historical recognition data includes initial recognition information and file processing volume, the initial recognition information includes file recognition time, file type, handwriting clarity and text density; S2: Marking a file recognition process as a single processing process, and obtaining the file processing volume in each single processing process; Obtaining initial identification information, and dividing a single processing process according to the initial identification information to obtain a number of file processing groups; Among them, in one file processing group, the data similarity value between the initial identification information corresponding to any two single processing processes is greater than or equal to the similarity threshold A1; After the file processing group is set, the initial identification information in the file processing group is obtained, and the feature value of the initial identification information is extracted, and the feature value is used as the feature label of the file processing group; S3: In an archive processing group, obtain the archive processing volume corresponding to a single processing process, calculate the mean of the archive processing volume, and then mark the mean calculation result as the archive characteristic value; S4: When the archive recognition module detects the recognition task, it obtains the real-time initial recognition information and marks it as real-time information. It then calculates the similarity between the real-time information and the feature labels of each archive processing group, identifies the maximum value in the similarity calculation results, and uses the archive feature value of the archive processing group corresponding to the maximum value as the task budget for this archive processing.

3. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: The methods for determining the reference equipment include: Obtain equipment information in the processing equipment group. The processing equipment group refers to the processing equipment related to the digital processing of archives. The equipment information includes the standard processing speed of the equipment. The standard processing speed of each device in the processing equipment group is obtained, the minimum value of the standard processing speed is identified, and the processing equipment corresponding to the minimum value is obtained and marked as the reference equipment.

4. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: The method for determining the processing speed curve and the curve function expression includes: Acquire historical operation data of the benchmark device, wherein the historical operation data includes continuous processing time, data processing speed, amount of data to be processed, and amount of data processed of the benchmark device; Set the continuous processing time as the horizontal axis and the data processing speed as the vertical axis, set the plane coordinate system, then obtain n processing processes, and draw the curve of the change of data processing speed with the continuous processing time in each processing process in the plane coordinate system to obtain n processing speed curves; Mathematical tools are used to perform polynomial fitting on each processing speed curve to obtain the curve function expression Fi, where i represents different processing speed curves and i∈[1,n].

5. The intelligent control system for digital processing of archives according to claim 4 is characterized in that: Methods for determining data sets include: Select any processing speed curve and mark it as the target curve, obtain the curve function expression Fr of the target curve, perform the first-order derivative operation on the curve function expression Fr, and obtain the slope change function ,in is the first-order derivative of the curve function expression Fr; Then, the amount of data to be processed and the amount of data that have been processed of the target curve are obtained. Based on the time length of the target curve, the amount of experimental data d is selected according to the time length. The amount of experimental data d = time length × unit data amount. The unit data amount refers to the minimum number of data points selected in a unit time. Then, according to the amount of experimental data, a data point is randomly selected in the target curve, the time value of the data point is obtained, and the time value is input into the slope change function Kr to obtain the slope value. At the same time, the amount of data to be processed and the amount of processed data corresponding to each data point are obtained. The slope value, the amount of data to be processed and the amount of processed data of a data point are taken as an array, and then d arrays are obtained in the target curve, where d represents the amount of experimental data in the target curve; All processing speed curves are taken as target curves in turn, and arrays of each processing speed curve are obtained respectively. The arrays of all processing speed curves are integrated to obtain a data set.

6. The intelligent control system for digital processing of archives according to claim 5 is characterized in that: Methods for determining the influencing parameter model include: The amount of data to be processed and the amount of processed data are used as independent variable factors, the slope value is used as the dependent variable factor, and the array in the data set is used as the experimental group. The experimental group is used as the input value and input into the simulation model for simulation operation, and the simulation operation result is marked as the influencing parameter model; Obtain the influencing parameter model and the task budget, and first determine the applicable range of the influencing parameter model based on the task budget. The applicable range refers to the independent variable range limited by the task budget of this archive processing; Among them, in the independent variable interval, the sum of the amount of data to be processed and the amount of data processed is less than or equal to the task budget; In the applicable interval, a positive area is selected and marked in the applicable interval, wherein the positive area is an area where the slope value is greater than or equal to 0, and then the equipment analysis module transmits the influencing parameter model in the applicable interval to the data monitoring module.

7. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: Methods for determining the amount of pre-transmission include: Monitor the real-time processing information of the benchmark equipment, the real-time processing information including the amount of data to be processed and the amount of data processed; The amount of processed data in the real-time processing information is obtained, and within the applicable interval of the influencing parameter model, the minimum value of the slope value is identified and marked as a processing vertex value, wherein the processing vertex value belongs to the positive region; The amount of data to be processed corresponding to the processing vertex value is obtained, and the amount of data to be processed is marked as the pre-transmission amount.

8. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: The method for the device control module to control the data transmission of the front-end device includes: Extract the pre-transmission amount, and at the same time obtain the amount of data to be processed in the real-time processing information, compare the pre-transmission amount with the amount of data to be processed, if the amount of data to be processed is less than the pre-transmission amount, generate a transmission signal for the front-end device, and control the front-end device to transmit data to the reference device, conversely, if the amount of data to be processed is greater than or equal to the pre-transmission amount, generate a stop signal for the front-end device, and control the front-end device to stop transmitting data to the reference device.

9. The intelligent control system for digital processing of archives according to claim 1 is characterized in that: It also includes a terminal display module, which is used to display real-time processing information on a terminal display device, so that the staff can understand the real-time progress of the digital processing of the archives.

Images