An information prediction and analysis system and method based on big data

Abstract

The present invention relates to the field of big data technology, and specifically to an information prediction and analysis system and method based on big data, comprising: an acquisition module, a database, a processing module, an analysis module and a display module; the acquisition module acquires equipment data, stores the equipment data in the database, the processing module acquires equipment data, processes the retrieved data, obtains a model, transmits the model to the analysis module, the analysis module acquires equipment data, calculates an investment payback period, transmits the investment payback period to the display module, the display module gives prompts based on the data, and makes decisions in line with reality and reasonable and feasible by analyzing the influence of multiple factors, selects a suitable model and establishes the model, directly substitutes the data for calculation, makes the parameters more accurate, and then selects data from different intervals to calculate the parameters, which can simplify the model, improve the model accuracy, reduce errors, and judge whether to prompt to replace the equipment based on the model prediction analysis, thereby improving production efficiency and reducing costs.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to an information prediction and analysis system and method based on big data. Background Art

[0002] At present, information prediction analysis refers to the process of predicting future events or trends by statistics, analysis and modeling of existing data. It can help people better understand the current situation and make more accurate decisions. In the manufacturing industry, factory equipment is an indispensable part of the production process. New equipment can improve production efficiency, reduce costs and improve product quality. However, factory equipment requires a lot of money and resources, and the investment cost is high. It also takes time and energy to install, debug and train the equipment. Investing a lot of money to purchase and update equipment is a complex decision-making process, and it is difficult to judge whether it is reasonable and feasible.

[0003] Therefore, people need an information prediction and analysis system and method based on big data to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an information prediction and analysis system and method based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an information prediction and analysis system based on big data, the system comprising: a collection module, a database, a processing module, an analysis module and a display module;

[0006] Acquire device data through the acquisition module and store the device data in a database;

[0007] The processing module acquires device data, processes the acquired data, obtains a model, and transmits the model to the analysis module;

[0008] Acquire equipment data through the analysis module, calculate the investment payback period, and transmit the investment payback period to the display module;

[0009] Prompts are given according to the data through the display module.

[0010] Furthermore, the acquisition module acquires equipment data and stores the equipment data in a database, wherein the equipment data includes investment cost, maintenance cost, production efficiency and payback period data. Data is acquired once every day at T time, stored, and stored. The acquisition module acquires data for storage, selects a suitable model, and establishes an accurate model to provide a data basis for prediction.

[0011] Furthermore, the processing module obtains historical investment cost, maintenance cost, production efficiency and investment recovery period data from the database, puts them into sets respectively, selects a model according to the data, substitutes the obtained data into the model to obtain an equation, and then directly calculates the parameters by grouping the equations, and then selects parameters from each calculated parameter in intervals, calculates the mean of each parameter, brings the calculated parameter mean into the model to obtain the model, and transmits the model to the analysis module; the processing module directly calculates the model parameters by obtaining historical data and bringing them into the model, and directly substituting them into the data for calculation, which will make the calculated data more accurate, and then selects parameters from different intervals to calculate the parameter mean to obtain the model. Selecting parameters calculated from different intervals can simplify the model, improve the model accuracy, reduce errors, make the model parameters more accurate, and more in line with reality, and the application of the model to actual prediction is more reasonable and feasible.

[0012] Furthermore, after receiving the model, the analysis module obtains the current investment cost, maintenance cost, and production efficiency data from the database, where the current data is the data obtained on the day, and the obtained data is brought into the model as a parameter to calculate the current investment payback period, and the current investment payback period is transmitted to the display module; the analysis module estimates the current situation based on the calculated model, and can clearly express whether it is necessary to replace equipment, improve production efficiency and reduce costs, thereby providing data basis for decision-making.

[0013] Furthermore, the display module receives the current payback period, compares the current payback period with the current payback period threshold, and if the current payback period is greater than the current payback period threshold, a prompt is given to not replace the equipment; if the current payback period is less than or equal to the current payback period threshold, a prompt is given to replace the equipment; the display module compares the received data with the threshold, and can clearly determine whether the equipment needs to be replaced. By displaying prompts, the factory can replace equipment in a timely manner, improve production efficiency and reduce costs, make better investment decisions and evaluations, and make decisions more reasonable and feasible.

[0014] An information prediction and analysis method based on big data comprises the following steps:

[0015] S1. Obtain device data and store device data;

[0016] S2, obtain historical equipment data, calculate model parameters, and obtain the model;

[0017] S3, obtain current equipment data and calculate the current investment payback period;

[0018] S4. Prompt based on the calculated data.

[0019] Furthermore, in step S1, equipment data is acquired and stored, wherein the equipment data includes investment cost, maintenance cost, production efficiency and payback period data, and the data is acquired and stored once every day at time T; by acquiring data for storage, selecting a suitable model and establishing an accurate model, a data basis is provided for prediction.

[0020] Furthermore, in step S2, historical investment cost, maintenance cost, production efficiency and investment payback period data are obtained, and the obtained investment cost data are put into a set A = {A1, A2, ..., A n}, put the acquired maintenance cost data into set B = {B1, B2, ..., B n}, put the obtained production efficiency data into the set C = {C1, C2, ..., C n}, put the acquired payback period data into the set D = {D1, D2, ..., D n}, the number of data in sets A, B, C, and D is n and equal. Select the model based on the data and calculate the model parameters: a is the constant term, b, c, and d are all independent variable coefficients, where b represents the coefficient of investment cost, c represents the coefficient of maintenance cost, d represents the coefficient of production efficiency, and e represents the error term. The model is obtained based on the parameters:

[0021] q=a+bx1+cx2+dx3+e

[0022] According to the above model, q represents the payback period, x1 represents the investment cost, x2 represents the maintenance cost, and x3 represents the production efficiency. Substitute the i-th data in set A, the i-th data in set B, the i-th data in set C, and the i-th data in set D into the model to obtain an equation, where initially i=1, then substitute the i+1th data in sets A, B, C, and D, set g to 1 initially, record the number of equations, and the g to g+4 equations are a group of data. If g is g+4, then g is set to 1. According to each Set data, perform calculations, and obtain parameters a, b, c, d, and e. Put the parameters into sets F, G, H, I, and J respectively. Get the zth data from each parameter set, and then get the z+wth data. Put the obtained data into sets F1, G1, H1, I1, and J1. The number of data in sets F1, G1, H1, I1, and J1 is h and equal. Calculate the parameters: mt represents the tth data in sets F1, G1, H1, I1, and J1, and h represents the number of data:

[0023]

[0024] According to the above calculation method, s represents a parameter. If the data in the sets F1, G1, H1, I1 and J1 are respectively used for the calculation, the calculated results are the values ​​of parameters a, b, c, d and e, respectively, and the model is obtained; the above method of directly calculating the model parameters by obtaining historical data and substituting it into the model for data calculation will make the calculated data more accurate, and then selecting parameters in different intervals to calculate the parameter mean to obtain the model. Selecting parameters calculated in different intervals can simplify the model, improve the model accuracy, reduce errors, make the model parameters more accurate, and more in line with reality, and the application of the model to actual prediction is more reasonable and feasible.

[0025] Furthermore, in step S3, the current investment cost, maintenance cost, and production efficiency data are obtained, wherein the current data is the data obtained on the current day, and the obtained data is brought into the model as a parameter to calculate the q value, i.e., the current investment payback period; the future situation is predicted based on the calculated model, which can clearly express whether it is necessary to replace equipment, improve production efficiency and reduce costs, and provide data basis for decision-making.

[0026] Furthermore, in step S4, if the current payback period is greater than the current payback period threshold, a prompt is given not to replace the equipment; if the current payback period is less than or equal to the current payback period threshold, a prompt is given to replace the equipment; by comparing the received data with the threshold, it is possible to clearly determine whether the equipment needs to be replaced, and by displaying prompts, the factory can replace equipment in a timely manner, improve production efficiency and reduce costs, make better investment decisions and evaluations, and make decisions more reasonable and feasible.

[0027] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention solves the problem of being unable to judge whether a decision is reasonable under the influence of multiple factors by analyzing the influence of multiple factors, so that the decision is in line with reality and is reasonable and feasible; by selecting a suitable model and establishing a model, directly substituting the data into calculation to make the parameters more accurate, and then selecting different interval data to calculate the parameters to obtain the model, the model can be simplified, the model accuracy can be improved, the error can be reduced, and accurate predictions can be made; according to the model prediction analysis, it is judged whether to prompt the replacement of equipment, which solves the problem of being unable to judge whether the decision is reasonable and feasible, improves production efficiency and reduces costs, and makes better investment decisions and evaluations. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0029] Figure 1 This is a structural block diagram of an information prediction and analysis system based on big data in the present invention;

[0030] Figure 2 This is a workflow diagram of an information prediction and analysis method based on big data of the present invention. DETAILED DESCRIPTION

[0031] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0032] Combine the following Figure 1-Figure 2 The present invention is further described with reference to the accompanying drawings and specific embodiments.

[0033] Embodiment 1:

[0034] like Figure 1 As shown, this embodiment provides an information prediction and analysis system based on big data, the system includes: a collection module, a database, a processing module, an analysis module and a display module;

[0035] Acquire equipment data through the acquisition module and store the equipment data in the database;

[0036] The acquisition module acquires equipment data and stores the equipment data in the database, where the equipment data includes investment cost, maintenance cost, production efficiency and investment payback period data. The data is acquired and stored once every day at T time.

[0037] The processing module obtains the device data, processes the retrieved data, obtains the model, and transmits the model to the analysis module;

[0038] The processing module obtains historical investment cost, maintenance cost, production efficiency and investment payback period data from the database, puts them into sets respectively, selects a model according to the data, substitutes the obtained data into the model to obtain the equation, then directly calculates the parameters by grouping the equation, and then selects parameters from each calculated parameter in intervals, calculates the mean of each parameter, brings the calculated parameter mean into the model, obtains the model, and transmits the model to the analysis module.

[0039] Obtain equipment data through the analysis module, calculate the investment payback period, and transmit the investment payback period to the display module;

[0040] After receiving the model, the analysis module obtains the current investment cost, maintenance cost, and production efficiency data from the database, where the current data is the data obtained on the day. The obtained data is brought into the model as a parameter, the current investment payback period is calculated, and the current investment payback period is transmitted to the display module.

[0041] Prompt based on data through display module;

[0042] The display module receives the current investment payback period, compares the current investment payback period with the current investment payback period threshold, and prompts to replace the equipment if the current investment payback period is greater than or equal to the current investment payback period threshold; if the current investment payback period is less than the current investment payback period threshold, prompts not to replace the equipment.

[0043] For example:

[0044] The acquisition module obtains the investment cost, maintenance cost, production efficiency and investment payback period data at T time every day, and stores the investment cost, maintenance cost, production efficiency and investment payback period data in the database. The processing module obtains the historical investment cost, maintenance cost, production efficiency and investment payback period data from the database, and puts them into the collection respectively. The model is selected according to the data, and the equation is obtained by substituting the obtained data into the model. Then, the parameters are directly calculated by grouping the equation. Then, from each calculated parameter, the parameters are selected in intervals, and the mean of each parameter is calculated. The calculated parameter mean is brought into the model to obtain the model, and the model is transmitted to the analysis module. After receiving the model, the analysis module obtains the investment cost, maintenance cost and production efficiency data of the day from the database, brings the obtained data into the model as parameters, calculates the current investment payback period, and transmits the current investment payback period to the display module. The display module receives the current investment payback period and compares the current investment payback period with the current investment payback period threshold. If the current investment payback period is greater than the current investment payback period threshold, it is prompted not to replace the equipment. If the current investment payback period is less than or equal to the current investment payback period threshold, it is prompted to replace the equipment.

[0045] Embodiment 2:

[0046] like Figure 2 As shown, this embodiment provides an information prediction and analysis method based on big data, which is implemented based on the information prediction and analysis system in the embodiment, and specifically includes the following steps:

[0047] S1. Obtain device data and store device data;

[0048] In step S1, equipment data is acquired and stored, wherein the equipment data includes investment cost, maintenance cost, production efficiency and investment payback period data. The data is acquired and stored once every day at T hours.

[0049] S2, obtain historical equipment data, calculate model parameters, and obtain the model;

[0050] In step S2, historical investment cost, maintenance cost, production efficiency and investment payback period data are obtained, and the obtained investment cost data are put into a set A = {A1, A2, ..., A n}, put the acquired maintenance cost data into set B = {B1, B2,…, B n}, put the obtained production efficiency data into the set C = {C1, C2, ..., C n}, put the acquired payback period data into the set D = {D1, D2, ..., D n}, the number of data in sets A, B, C, and D is n and equal. Select the model based on the data and calculate the model parameters: a is the constant term, b, c, and d are all independent variable coefficients, where b represents the coefficient of investment cost, c represents the coefficient of maintenance cost, d represents the coefficient of production efficiency, and e represents the error term. The model is obtained based on the parameters:

[0051] q=a+bx1+cx2+dx3+e

[0052] According to the above model, q represents the payback period, x1 represents the investment cost, x2 represents the maintenance cost, and x3 represents the production efficiency. The i-th data in set A, the i-th data in set B, the i-th data in set C, and the i-th data in set D are substituted into the model to obtain the equation, where initially i=1, and then the i+1-th data in sets A, B, C, and D are substituted, g is initially set to 1, and the number of equations is recorded. The g-th to g+4-th equations are a group of data. If g is g+4, g is set to 1. According to each group of data, calculations are performed to obtain parameters a, b, c, d, and e. The parameters are placed in sets F, G, H, I, and J respectively. The z-th data is obtained from each parameter set, and then the z+w-th data is obtained. The obtained data is placed in sets F1, G1, H1, I1, and J1. The number of data in sets F1, G1, H1, I1, and J1 is h and equal. Calculate the parameter: m t represents the tth data in the F1, G1, H1, I1 and J1 sets, and h represents the number of data:

[0053]

[0054] According to the above calculation method, s represents the parameter. If the data in the sets F1, G1, H1, I1 and J1 are used for calculation, the calculated results are the values ​​of parameters a, b, c, d and e, and the model is obtained.

[0055] S3, obtain current equipment data and calculate the current investment payback period;

[0056] In step S3, the current investment cost, maintenance cost and production efficiency data are obtained, where the current data is the data obtained on the day. The obtained data is brought into the model as a parameter to calculate the q value, that is, the current investment payback period.

[0057] S4, providing prompts based on the calculated data;

[0058] In step S4, if the current investment payback period is greater than the current investment payback period threshold, a prompt is given not to replace the equipment; if the current investment payback period is less than or equal to the current investment payback period threshold, a prompt is given to replace the equipment.

[0059] For example:

[0060] In step S1, the investment cost is 1 million yuan, the maintenance cost is 10,000 yuan, the production efficiency is 8,000 per day and the investment payback period is 15 years, and the investment cost, maintenance cost, production efficiency and investment payback period data are stored.

[0061] In step S2, historical investment cost, maintenance cost, production efficiency and investment payback period data are obtained. If there are 100 data for each, then n is 100. The obtained investment cost data are put into a set A = {A1, A2, ..., A 100}, put the acquired maintenance cost data into set B = {B1, B2, ..., B 100}, put the obtained production efficiency data into the set C = {C1, C2, ..., C 100}, put the acquired payback period data into the set D = {D1, D2, ..., D 100}, select the model according to the data, calculate the model parameters, substitute the i-th data in set A, the i-th data in set B, the i-th data in set C and the i-th data in set D into the model, and get the equation D1=a+bA1+cB1+dC1+e, where i=1 initially, then substitute the i+1th data in sets A, B, C and D, g is initially 1, the equations from g to g+4 are a group of data, that is, every 5 equations are a group of data, and calculate one data for each of the parameters a, b, c, d and e, If g is g+4, set g to 1, and put all the calculated parameters a, b, c, d and e into sets F, G, H, I and J respectively. If z is 1 and w is 1, take every other data and put it into sets F1, G1, H1, I1 and J1. The number of data in sets F1, G1, H1, I1 and J1 is h=10 respectively. Substitute the data in sets F1, G1, H1, I1 and J1 to calculate s respectively. The calculated values ​​are a, b, c, d and e respectively, and the model is obtained.

[0062] In step S3, if the model is q=0.4+0.1x1-0.1x2-0.2x3+0.6, the investment cost for the day is 100, the maintenance cost is 3, and the production efficiency is 1. The obtained data is substituted into the model as parameters, and the q value is calculated to be 10.5, which is the investment payback period for the day.

[0063] In step S4, if the current day's payback period threshold is 5, and the current day's payback period is greater than the current day's payback period threshold, a prompt is given to not replace the equipment.

[0064] Finally, it should be noted that the above description is only a preferred example of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, 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 prediction and analysis method based on big data, characterized by: The following steps are involved: S1. Obtain device data and store device data; S2, obtain historical equipment data, calculate model parameters, and obtain the model; S3, obtain current equipment data and calculate the current investment payback period; S4, providing prompts based on the calculated data; In step S1, equipment data is acquired and stored, wherein the equipment data includes investment cost, maintenance cost, production efficiency and investment payback period data, and the data is acquired and stored once at T time every day; In step S2, historical investment cost, maintenance cost, production efficiency and investment payback period data are obtained, and the obtained investment cost data are put into a set A = {A1, A2, ..., A n }, put the acquired maintenance cost data into set B = {B1, B2,…, B n }, put the obtained production efficiency data into the set C = {C1, C2, ..., C n }, put the acquired payback period data into the set D = {D1, D2, ..., D n }, the number of data in sets A, B, C, and D is n and equal. Select the model based on the data and calculate the model parameters: a is the constant term, b, c, and d are all independent variable coefficients, where b represents the coefficient of investment cost, c represents the coefficient of maintenance cost, d represents the coefficient of production efficiency, and e represents the error term. The model is obtained based on the parameters: q=a+bx1+cx2+dx3+e According to the above model, q represents the payback period, x1 represents the investment cost, x2 represents the maintenance cost, and x3 represents the production efficiency. The i-th data in set A, the i-th data in set B, the i-th data in set C, and the i-th data in set D are substituted into the model to obtain the equation, where initially i=1, and then the i+1-th data in sets A, B, C, and D are substituted, g is initially set to 1, and the number of equations is recorded. The g-th to g+4-th equations are a group of data. If g is g+4, g is set to 1. According to each group of data, calculations are performed to obtain parameters a, b, c, d, and e. The parameters are placed in sets F, G, H, I, and J respectively. The z-th data is obtained from each parameter set, and then the z+w-th data is obtained. The obtained data is placed in sets F1, G1, H1, I1, and J1. The number of data in sets F1, G1, H1, I1, and J1 is h and equal. Calculate the parameter: m t represents the tth data in the F1, G1, H1, I1 and J1 sets, and h represents the number of data: According to the above calculation method, s represents the parameter. If the data in the sets F1, G1, H1, I1 and J1 are used for calculation, the calculated results are the values ​​of the parameters a, b, c, d and e, and the model is obtained. In step S3, the current investment cost, maintenance cost and production efficiency data are obtained, where the current data is the data obtained on the day, and the obtained data is brought into the model as a parameter to calculate the q value, that is, the current investment payback period; In step S4, if the current investment payback period is greater than the current investment payback period threshold, a prompt is given not to replace the equipment; if the current investment payback period is less than or equal to the current investment payback period threshold, a prompt is given to replace the equipment.

2. An information prediction and analysis system based on big data, applied to the information prediction and analysis method based on big data as claimed in claim 1, characterized in that: The system includes: a collection module, a database, a processing module, an analysis module and a display module; Acquire device data through the acquisition module and store the device data in a database; The processing module acquires device data, processes the acquired data, obtains a model, and transmits the model to the analysis module; Acquire equipment data through the analysis module, calculate the investment payback period, and transmit the investment payback period to the display module; Prompts are given according to the data through the display module.

3. The information prediction and analysis system based on big data according to claim 2, characterized in that: The acquisition module acquires equipment data and stores the equipment data in a database, wherein the equipment data includes investment cost, maintenance cost, production efficiency and investment payback period data. The data is acquired and stored once at T time every day.

4. The information prediction and analysis system based on big data according to claim 2, characterized in that: The processing module obtains historical investment cost, maintenance cost, production efficiency and investment payback period data from the database, puts them into sets respectively, selects a model according to the data, substitutes the obtained data into the model to obtain an equation, then directly calculates the parameters by grouping the equations, then selects parameters from each calculated parameter in intervals, calculates the mean of each parameter, brings the calculated parameter mean into the model, obtains the model, and transmits the model to the analysis module.

5. The information prediction and analysis system based on big data according to claim 2, characterized in that: After receiving the model, the analysis module obtains the current investment cost, maintenance cost and production efficiency data from the database, where the current data is the data obtained on the day, and brings the obtained data into the model as parameters to calculate the current investment payback period, which is then transmitted to the display module.

6. The information prediction and analysis system based on big data according to claim 2, characterized in that: The display module receives the current payback period, compares the current payback period with the current payback period threshold, and prompts not to replace the equipment if the current payback period is greater than the current payback period threshold; if the current payback period is less than or equal to the current payback period threshold, prompts to replace the equipment.

Images