CN116819655B - Data management method and system based on natural language processing technology - Google Patents
Data management method and system based on natural language processing technology Download PDFInfo
- Publication number
- CN116819655B CN116819655B CN202311095467.4A CN202311095467A CN116819655B CN 116819655 B CN116819655 B CN 116819655B CN 202311095467 A CN202311095467 A CN 202311095467A CN 116819655 B CN116819655 B CN 116819655B
- Authority
- CN
- China
- Prior art keywords
- data
- observation
- preset
- required position
- less
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003058 natural language processing Methods 0.000 title claims abstract description 24
- 238000013523 data management Methods 0.000 title claims abstract description 22
- 238000005516 engineering process Methods 0.000 title claims abstract description 19
- 238000001556 precipitation Methods 0.000 claims description 91
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 description 28
- 230000008569 process Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010921 in-depth analysis Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002620 method output Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
Landscapes
- Engineering & Computer Science (AREA)
- Environmental & Geological Engineering (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Environmental Sciences (AREA)
- Ecology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Atmospheric Sciences (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the technical field of data management, and discloses a data management method and system based on a natural language processing technology, wherein the method comprises the following steps: acquiring meteorological data and a user's required position, acquiring observation site information of the required position, and judging whether the observation data of the required position is accurate or not according to the observation site information; when the observation data of the demand position is accurate, outputting real-time weather information of the demand position and carrying out weather prediction; when the observation data of the required position is inaccurate, acquiring first preset observation site data, and judging whether the observation site data of the required position is stable or not according to the first preset observation site data; when the data of the observation site in the demand position is unstable, the information of the observation site is adjusted, and the real-time weather information of the demand position is output and the weather is predicted after the adjustment. The application improves the quality of meteorological data and provides more accurate weather prediction for users.
Description
Technical Field
The application relates to the technical field of data management, in particular to a data management method and system based on a natural language processing technology.
Background
Natural language processing techniques are natural language techniques that enable a computer to understand and process humans. In the data management method, the natural language processing technology is used for extracting the client demand information from the natural language input of the user, so that man-machine interaction is realized, and the production and the life of people are facilitated.
The application of natural language processing technology in weather data management is currently realized, and the weather conditions, including real-time weather and weather prediction and the like, are provided for users. However, existing weather data management methods based on natural language processing techniques have focused mainly on directly acquiring data from the internet and communicating the information to the user through the language processing techniques. This approach lacks judgment and assessment of the accuracy of the data provided. While existing approaches have advanced in terms of convenience and user experience, they have limitations that rely solely on internet data sources, ignoring the reliability issues of the data. This may result in inaccurate or erratic weather information being received by the user, misleading the user's decisions and plans.
Therefore, there is a need to design a data management method and system based on natural language processing technology to solve the current problems.
Disclosure of Invention
In view of this, the application provides a data management method and system based on natural language processing technology, which aims to solve the problem that the current natural language technology lacks data judgment in meteorological data application, which is easy to cause low data accuracy and influence user experience.
In one aspect, the present application provides a data management method based on a natural language processing technology, including:
acquiring meteorological data and a user's required position, acquiring observation site information of the required position, and judging whether the observation data of the required position is accurate or not according to the observation site information;
the accuracy of the observed data is calculated by the following formula:
P=α*N+β*P-γ*Y；
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0; p is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0; y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0; and α+β+γ=1;
outputting real-time weather information of the demand position and carrying out weather prediction when the observation data of the demand position is accurate;
when the observation data of the required position is inaccurate, acquiring first preset observation site data, and judging whether the observation site data of the required position is stable or not according to the first preset observation site data;
when the observation site data in the required position is unstable, adjusting the observation site information, and outputting the real-time weather information of the required position and carrying out weather prediction after adjustment.
Further, the collecting the meteorological data and the required position of the user, obtaining the observation site information of the required position, and judging whether the observation data of the required position is accurate according to the observation site information, including:
the observation site information comprises the number N of observation sites, the observation frequency P and the abnormal times N;
presetting an accuracy threshold value P0, and judging whether the observed data in the required position is accurate or not according to the magnitude relation between the accuracy P of the observed data and the accuracy threshold value P0;
when P is more than or equal to PO, judging that the observation data of the required position is accurate, outputting real-time weather information of the required position and carrying out weather prediction;
and when P is less than PO, judging that the observed data of the required position is inaccurate, and further judging whether the observed data of the required position is stable or not.
Further, when it is determined that the observed data of the demand position is accurate, outputting real-time weather information of the demand position and performing weather prediction, including:
collecting real-time precipitation S0, and presetting a first preset precipitation S1, a second preset precipitation S2 and a third preset precipitation S3, wherein S1 is more than S2 and less than S3; presetting a first preset precipitation level D1, a second preset precipitation level D2 and a third preset precipitation level D3, wherein D1 is more than D2 and less than D3;
determining a real-time precipitation level according to the magnitude relation between the real-time precipitation S0 and each preset precipitation;
when S1 is less than or equal to S0 and less than S2, determining the real-time precipitation level as D1;
when S2 is less than or equal to S0 and less than S3, determining the real-time precipitation level as D2;
and when S3 is less than or equal to S0, determining that the real-time precipitation level is D3.
Further, after determining that the real-time precipitation level is Di, i=1, 2,3, outputting real-time weather information of the required position and performing weather prediction, and further including:
acquiring a humidity change rate DeltaQ, and presetting a first preset humidity change rate DeltaQ 1, a second preset humidity change rate DeltaQ 2, a third preset humidity change rate DeltaQ 3 and a fourth preset humidity change rate DeltaQ 4, wherein DeltaQ 1 is less than DeltaQ 2 and DeltaQ 3 is less than DeltaQ 4;
according to the magnitude relation between the humidity change rate delta Q and each preset humidity change rate, the real-time precipitation level is adjusted, and the adjusted precipitation level is used as the precipitation level after a time interval T;
when DeltaQ 1 is less than or equal to DeltaQ < DeltaQ2, the real-time precipitation grade Di is lowered by two stages;
when delta Q2 is less than or equal to delta Q < 0, the real-time precipitation grade Di is lowered by one stage;
when delta Q is less than or equal to 0 and less than delta Q3, the real-time precipitation grade Di is increased by one stage;
when DeltaQ 3 is less than or equal to DeltaQ < DeltaQ4, the real-time precipitation grade Di is regulated to be higher by two stages.
Further, adjust the real-time precipitation level, after taking the precipitation level after the adjustment as the precipitation level after the time interval T, output the real-time weather information of demand position and carry out weather forecast, still include:
acquiring real-time wind power data F0, and presetting a first preset wind power F1, a second preset wind power F2 and a third preset wind power F3, wherein F1 is smaller than F2 and smaller than F3; presetting a first preset adjustment coefficient A1, a second preset adjustment coefficient A2 and a third preset adjustment coefficient A3, wherein A1 is more than A2 and less than A3;
selecting an adjustment coefficient according to the relation between the real-time wind power data F0 and the magnitude of each preset wind power to adjust the time interval T, and obtaining an adjusted time interval;
when F1 is less than or equal to F0 and less than F2, selecting the third preset adjustment coefficient A3 to adjust the time interval T, and obtaining the adjusted time interval as T.A3;
when F2 is less than or equal to F0 and less than F3, selecting the second preset adjustment coefficient A2 to adjust the time interval T, and obtaining the adjusted time interval as T.A2;
when F3 is less than or equal to F0, the first preset adjustment coefficient A1 is selected to adjust the time interval T, and the adjusted time interval is obtained to be T.A1.
Further, when it is determined that the observed data of the required position is inaccurate, further determining whether the observed data of the required position is stable includes:
acquiring a first fluctuation range W0 of first preset observation site data, wherein the fluctuation range W1 of the observation data of the required position is used for judging whether the observation site data of the required position is stable or not according to the magnitude relation between the first fluctuation range W0 and the fluctuation range W1 of the observation data of the required position;
when W1 is less than or equal to W0, judging that the observation data of the required position is stable;
when W1 is larger than W0, the observation data of the required position is judged to be unstable.
Further, when the observed data of the required position is unstable, acquiring altitude information H1 of a first preset observed site, acquiring average altitude H0 of the observed site of the required position, and judging whether the first preset observed site data can be integrated into the observed data of the required position according to the relation between the altitude information H1 and the average altitude H0;
when 0.9H0 is less than or equal to H1 is less than or equal to 1.1H0, judging that the first preset observation site data can be integrated into the observation data of the required position;
when H1 is less than 0.9H0 or H1 is more than 1.1H0, judging that the first preset observation site data cannot be integrated into the observation data of the required position, adjusting the observation site information, and outputting real-time weather information of the required position and carrying out weather prediction after adjustment.
Further, when it is determined that the first preset observation site data cannot be incorporated into the observation data of the required position, acquiring an average observation frequency P0 of the observation site in the required position, acquiring a fluctuation difference Δw=w1-Wmax between a fluctuation range W1 of the observation data in the required position and a preset fluctuation threshold Wmax, and presetting a first preset difference Δw1, a second preset difference Δw2 and a third preset difference Δw3, wherein Δw1 < Δw2 < Δw3;
and adjusting the average observation frequency P0 according to the magnitude relation between the fluctuation difference value DeltaW and each preset difference value, and obtaining the adjusted observation frequency.
Further, according to the magnitude relation between the fluctuation difference Δw and each preset difference, the average observation frequency P0 is adjusted, and the adjusted observation frequency is obtained, including:
presetting a first preset frequency adjustment coefficient B1, a second preset frequency adjustment coefficient B2 and a third preset frequency adjustment coefficient B3, wherein B1 is more than B2 and less than B3;
when DeltaW 1 is less than or equal to DeltaW < DeltaW2, selecting the first preset frequency adjustment coefficient B1 to adjust the average observation frequency P0, and obtaining an adjusted observation frequency P0 x B1;
when DeltaW 2 is less than or equal to DeltaW < DeltaW3, selecting the second preset frequency adjustment coefficient B2 to adjust the average observation frequency P0, and obtaining an adjusted observation frequency P0 x B2;
when Δw3 is less than or equal to Δw, selecting the third preset frequency adjustment coefficient B3 to adjust the average observed frequency P0, and obtaining an adjusted observed frequency P0×b3.
Compared with the prior art, the application has the beneficial effects that: by collecting meteorological data and user demand positions and combining observation site information, the system evaluates and judges the provided observation data through a data accuracy calculation model. The weight distribution of the number of the observation sites, the observation frequency and the abnormal times is fully considered, so that the credibility of the data is comprehensively measured. When the system determines that the observed data for the desired location is accurate, the user will benefit from obtaining accurate real-time weather information and reliable weather predictions, supporting the user to make decisions and plans. In the case of inaccurate data, the multi-level response mechanism of the system provides higher-level response for the user: judging the stability of the data by acquiring first preset observation site data; secondly, for unstable situations, the system will improve the reliability of the data by adjusting the observation site information. This process will allow the user to obtain more reliable real-time weather information and more accurate weather predictions, thereby effectively reducing misdirection and decision bias due to inaccurate data.
On the other hand, the application also provides a data management system based on natural language processing technology, which comprises:
the acquisition unit acquires meteorological data and a user's required position, acquires observation site information of the required position, and judges whether the observation data of the required position is accurate or not according to the observation site information;
the accuracy of the observed data is calculated by the following formula:
P=α*N+β*P-γ*Y；
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0; p is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0; y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0; and α+β+γ=1;
the prediction unit is configured to output real-time weather information of the demand position and conduct weather prediction when the observed data of the demand position are accurate;
the judging unit is configured to acquire first preset observation site data when the observation data in the required position is inaccurate, and judge whether the observation site data of the required position is stable or not according to the first preset observation site data;
and the adjusting unit is configured to adjust the observation site information when the observation site data in the required position is unstable, and output the real-time weather information of the required position and conduct weather prediction after adjustment.
It can be appreciated that the data management method and system based on the natural language processing technology have the same beneficial effects, and are not described herein.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a flow chart of a data management method based on natural language processing technology according to an embodiment of the present application;
fig. 2 is a block diagram of a data management system based on a natural language processing technology according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
Natural language processing (Natural Language Processing, NLP) is a interdisciplinary field involving computer science, artificial intelligence, and linguistics, intended to enable computers to understand, process, and generate human natural language. It covers a series of techniques and methods that enable computers to communicate and interact with humans in natural language, thereby enabling in-depth analysis, understanding, and application of text and speech data.
Referring to fig. 1, in some embodiments of the present application, a data management method based on a natural language processing technique includes:
step S100: and acquiring meteorological data and the required position of the user, acquiring observation site information of the required position, and judging whether the observation data of the required position is accurate or not according to the observation site information.
Wherein the accuracy of the observed data is calculated by the following formula:
P=α*N+β*P-γ*Y。
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0.P is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0.Y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0. And α+β+γ=1.
Step S200: when the observation data of the demand position is accurate, outputting real-time weather information of the demand position and carrying out weather prediction. When the observation data of the required position is inaccurate, acquiring first preset observation site data, and judging whether the observation site data of the required position is stable or not according to the first preset observation site data.
Step S300: when the data of the observation site in the demand position is unstable, the information of the observation site is adjusted, and the real-time weather information of the demand position is output and the weather is predicted after the adjustment.
Specifically, the system first collects the user's demand location and weather data, and the demand location is the destination in the user's problem, such as asking for the weather condition of J, when the demand location is J. And then obtaining the information of the observation site in the required position. By calculating the formula p=αn+βp- γ, the system comprehensively considers the number of observation sites, the observation frequency, and the weight distribution of the number of abnormalities, thereby evaluating the accuracy of the observation data of the required position. Where α, β and γ are weight parameters, the sum of which is 1, for adjusting the influence of the accuracy of each factor. When the calculation is performed again, the data can be standardized before the calculation in order to eliminate the variability of the data. Wherein,,
normalized value= (original value-minimum)/(maximum-minimum).
It will be appreciated that by normalizing the observed data, the variability of the observed data can be eliminated, allowing it to be calculated in a unified calculation formula. The standardized accuracy value reflects the influence of each index under comprehensive balance, and the accuracy of the observed data is more accurately evaluated.
It will be appreciated that when the data is determined to be accurate, the system will output real-time weather information for the desired location and make weather predictions. This means that users will get trusted weather conditions to support their decision making and planning. If the data is determined to be inaccurate, the system takes further action. And acquiring data of a first preset observation site, and judging whether the data of the observation site at the required position is stable or not according to the data. The first preset observation site is the observation site of the rest of the areas closest to the demand position. When the accuracy of the data of the observation site at the required position is low, stability analysis is carried out on the data by using sites which are in other areas and are close to the required position, so that the reliability of the data is improved. If the data is unstable, the system adjusts the information of the observation station point in the required position so as to improve the reliability of the data. After adjustment, the system outputs corrected real-time weather information and performs weather prediction. This process will help the user obtain more reliable weather information, reducing mislead and decision bias due to inaccurate data.
In some embodiments of the present application, the step S100 of collecting weather data and a user' S required position, obtaining observation site information of the required position, and determining whether the observation data of the required position is accurate according to the observation site information includes: the observation site information includes the number N of observation sites, the observation frequency P, and the number N of anomalies. An accuracy threshold value P0 is preset, and whether the observed data in the required position is accurate or not is judged according to the size relation between the accuracy P of the observed data and the accuracy threshold value P0. When P is more than or equal to PO, accurate observation data of the required position is judged, real-time weather information of the required position is output, and weather prediction is carried out. When P is less than PO, the observation data of the required position is judged to be inaccurate, and whether the observation data of the required position is stable or not is further judged.
Specifically, the number N of observation sites is the sum of the number of observation sites for observation of meteorological data in the demand location. The observation frequency is the frequency at which the observation site observes the meteorological data. The abnormal number is the number of obvious data errors recorded in the observation site data. The accuracy threshold is a predetermined value that defines the level of accuracy of the observed data. Which is set according to the importance of the data, the acceptable error range of the application, and the user's desired factors. In a data management method based on natural language processing technology, an accuracy threshold is used to determine whether observed data is sufficiently accurate to determine whether the data is reliable.
Specifically, when the accuracy of the calculated observed data is greater than or equal to the accuracy threshold, the system can identify that the observed data is accurate and can directly output weather information and predict. When the accuracy of the observed data obtained by calculation is smaller than the accuracy threshold, the system considers that the accuracy of the observed data is insufficient, and a certain error or instability can exist. At this time, more analysis of the data is required to ensure reliability.
It will be appreciated that by comprehensively considering a number of factors of the observed data, including quantity, frequency and anomalies, the system is able to accurately evaluate the confidence level of the observed data. The preset accuracy threshold allows the system to further judge when the accuracy of the data is lower than a certain standard, so that the information obtained by the user is ensured to have high reliability. This will help the user make more informed decisions, plan activities, and improve production and life efficiency.
In some embodiments of the present application, in step S200, when it is determined that the observed data of the demand location is accurate, outputting real-time weather information of the demand location and performing weather prediction includes: the real-time precipitation S0 is collected, a first preset precipitation S1, a second preset precipitation S2 and a third preset precipitation S3 are preset, and S1 is more than S2 and less than S3. The method comprises the steps of presetting a first preset precipitation level D1, a second preset precipitation level D2 and a third preset precipitation level D3, wherein D1 is more than D2 and less than D3, and determining the real-time precipitation level according to the magnitude relation between the real-time precipitation amount S0 and each preset precipitation amount. When S1 is less than or equal to S0 and less than S2, determining the real-time precipitation grade as D1. When S2 is less than or equal to S0 and less than S3, determining the real-time precipitation grade as D2. And when S3 is less than or equal to S0, determining that the real-time precipitation level is D3.
Specifically, the system will collect real-time precipitation, i.e. precipitation in the current time. In order to better judge the degree of precipitation, the system presets a series of precipitation thresholds, namely a first preset precipitation, a second preset precipitation and a third preset precipitation, wherein S1 is smaller than S2 and S2 is smaller than S3. These thresholds represent a division of different precipitation levels. These grades are used to describe the intensity of precipitation, such as light, medium and heavy rain grades. According to the magnitude relation between the real-time precipitation amount and the preset precipitation amount, the system can determine the current real-time precipitation level.
It can be appreciated that by presetting different precipitation thresholds and precipitation levels, the system can provide more refined weather prediction for the user according to different precipitation conditions, and the practicability and user experience of the information are further improved.
In some embodiments of the present application, after determining that the real-time precipitation level is Di in step S200, i=1, 2,3, the method outputs real-time weather information of the required location and performs weather prediction, and further includes: obtaining a humidity change rate DeltaQ, presetting a first preset humidity change rate DeltaQ 1, a second preset humidity change rate DeltaQ 2, a third preset humidity change rate DeltaQ 3 and a fourth preset humidity change rate DeltaQ 4, wherein DeltaQ 1 is less than DeltaQ 2 and DeltaQ 3 is less than DeltaQ 4. According to the relation between the humidity change rate delta Q and each preset humidity change rate, the real-time precipitation level is adjusted, and the adjusted precipitation level is taken as the precipitation level after the time interval T. When DeltaQ 1 is less than or equal to DeltaQ < DeltaQ2, the real-time precipitation level Di is reduced by two stages. When DeltaQ 2 is less than or equal to DeltaQ less than 0, the real-time precipitation grade Di is lowered by one stage. When delta Q is less than or equal to 0 and less than delta Q3, the real-time precipitation grade Di is increased by one stage. When DeltaQ 3 is less than or equal to DeltaQ < DeltaQ4, the real-time precipitation grade Di is regulated to be higher by two stages.
Specifically, the system first obtains a real-time humidity change rate Δq reflecting the trend of humidity change in the current weather environment. I.e. the rate of change of the current humidity compared to the humidity over a period of time. The preset humidity change rate represents the degree and trend of the humidity change.
It will be appreciated that when the rate of change of humidity is small or negative, this means that the level of water vapour in the air is reduced and the humidity is reduced. In this case, as the supply of water vapour in the air is reduced, the likelihood of precipitation is correspondingly reduced, and a lighter precipitation, or even no precipitation, may occur. The rate of change of humidity may be an important indicator of future precipitation conditions. In weather prediction, the predicted precipitation level can be adjusted according to the humidity change rate so as to more accurately reflect the possible precipitation condition. For example, a large positive rate of change of humidity may result in a strong precipitation, while a negative or small rate of change of humidity may result in a slight or no precipitation. By combining the relationship between the humidity change rate and the precipitation level, the weather prediction system can more comprehensively consider the influence of humidity on precipitation, provide more accurate precipitation prediction information, help users better understand future weather conditions and make more intelligent decisions and arrangements.
In some embodiments of the present application, in step S200, the real-time precipitation level is adjusted, and after the adjusted precipitation level is taken as the precipitation level after the time interval T, the real-time weather information of the required position is output and weather prediction is performed, and further including: real-time wind power data F0 are acquired, a first preset wind power F1, a second preset wind power F2 and a third preset wind power F3 are preset, and F1 is smaller than F2 and smaller than F3. The method comprises the steps of presetting a first preset adjustment coefficient A1, a second preset adjustment coefficient A2 and a third preset adjustment coefficient A3, wherein A1 is more than A2 and less than A3. And selecting an adjustment coefficient according to the relation between the real-time wind power data F0 and the magnitude of each preset wind power to adjust the time interval T, and obtaining the adjusted time interval. When F1 is less than or equal to F0 and less than F2, a third preset adjustment coefficient A3 is selected to adjust the time interval T, and the adjusted time interval T is obtained. When F2 is less than or equal to F0 and less than F3, a second preset adjustment coefficient A2 is selected to adjust the time interval T, and the adjusted time interval T is obtained. When F3 is less than or equal to F0, a first preset adjustment coefficient A1 is selected to adjust the time interval T, and the adjusted time interval is obtained to be T.A1.
Specifically, considering the influence of wind power on weather, according to the comparison of the real-time wind power data and the preset wind power, a corresponding adjustment coefficient is selected to adjust the time interval T. When the wind power is strong, the water vapor gathering rate is accelerated, and rainfall is caused in a shorter time. Therefore, after the humidity change is obtained, the time interval T is adjusted according to wind power, and the prediction accuracy is improved.
It will be appreciated that by incorporating wind factors into the time interval adjustment process, the system may more finely predict precipitation conditions under different wind conditions, thereby providing more accurate weather information to the user. The method for comprehensively considering the factors is beneficial to comprehensively considering the influence of various meteorological variables in weather prediction, improves the accuracy and practicality of prediction, and provides more valuable information for users.
In some embodiments of the present application, when it is determined that the observed data of the required position is inaccurate in step S200, further determining whether the observed data of the required position is stable includes: acquiring a first fluctuation range W0 of first preset observation site data, a fluctuation range W1 of observation data of a required position, and judging whether the observation site data of the required position is stable or not according to the magnitude relation between the first fluctuation range W0 and the fluctuation range W1 of the observation data of the required position. When W1 is less than or equal to W0, judging that the observation data of the required position is stable. When W1 > W0, the observation data of the required position is judged to be unstable.
Specifically, in order to determine the stability of the observed data of the demand location, the system first acquires a first fluctuation range of the first preset observation site data and a fluctuation range of the observed data of the demand location. The fluctuation range refers to the change range of the observed data in a certain time, and can reflect the stability and fluctuation degree of the data. Next, the system compares the magnitude relation of the first fluctuation range with the fluctuation range of the observation data of the demand position. If the fluctuation range of the observed data of the demand position is smaller than or equal to the first fluctuation range of the first preset observation site data, it is determined that the observed data of the demand position is stable. This means that the observed data has relatively small fluctuation in a certain period of time and high stability, and can be relied on to a certain extent to make weather predictions. Conversely, if the fluctuation range of the observed data of the demand position is greater than the first fluctuation range of the first preset observation site data, it is determined that the observed data of the demand position is unstable. This may indicate that the observed data has a large fluctuation in a short time.
It will be appreciated that by such a determination process, the system can more finely evaluate the stability of the observed data at the desired location, thereby more accurately determining whether data adjustments are needed or weather predictions are made using other reliable data sources.
In some embodiments of the present application, when the observed data of the required position is determined to be unstable in step S300, altitude information H1 of the first preset observation site is obtained, an average altitude H0 of the observation site of the required position is obtained, and whether the first preset observation site data can be incorporated into the observed data of the required position is determined according to the magnitude relation between the altitude information H1 and the average altitude H0. When 0.9H0 is less than or equal to H1 is less than or equal to 1.1H0, it is determined that the first preset observation site data can be incorporated into the observation data of the demand location. When H1 is less than 0.9H0 or H1 is more than 1.1H0, judging that the first preset observation site data cannot be integrated into the observation data of the required position, adjusting the observation site information, and outputting real-time weather information of the required position and carrying out weather prediction after adjustment.
Specifically, the system obtains altitude information of a first preset observation site and an average altitude of the observation site at the required location. The altitude information refers to the altitude of the place where the observation site is located, and the average altitude is the average value of the altitudes of all observation sites in the required position. Next, the system compares the altitude information to the magnitude of the average altitude (H0). When the altitude information is between 0.9 times the average altitude and 1.1 times the average altitude, the system determines to incorporate the data of the first preset observation site into the observation data of the demand location. This is because in the case where the altitudes are relatively uniform, the difference between the data is small, and thus the data can be merged to increase the reliability of the data. However, when the altitude information is less than 0.9 times the average altitude or greater than 1.1 times the average altitude, the system determines that it is not appropriate to incorporate the data of the first preset observation site into the observation data of the demand position. This is because the altitude difference is large, which results in a large influence between data, and thus adjustment of the observation site information is required.
It can be understood that by comprehensively considering the altitude difference, whether the data of different observation sites are suitable to be combined is judged, so that the accuracy and the stability of the data are improved.
In some embodiments of the present application, when it is determined in step S300 that the first preset observation site data cannot be incorporated into the observation data of the demand location, the average observation frequency P0 of the observation sites in the demand location is obtained, the fluctuation difference Δw=w1-Wmax between the fluctuation range W1 of the observation data in the demand location and the preset fluctuation threshold Wmax is obtained, the first preset difference Δw1, the second preset difference Δw2, and the third preset difference Δw3 are preset, and Δw1 < Δw2 < Δw3. And adjusting the average observation frequency P0 according to the magnitude relation between the fluctuation difference value DeltaW and each preset difference value, and obtaining the adjusted observation frequency.
Specifically, a first preset frequency adjustment coefficient B1, a second preset frequency adjustment coefficient B2, and a third preset frequency adjustment coefficient B3 are preset, and B1 < B2 < B3. When DeltaW 1 is less than or equal to DeltaW < DeltaW2, selecting a first preset frequency adjustment coefficient B1 to adjust the average observation frequency P0, and obtaining an adjusted observation frequency P0 x B1. When DeltaW 2 is less than or equal to DeltaW < DeltaW3, selecting a second preset frequency adjustment coefficient B2 to adjust the average observation frequency P0, and obtaining the adjusted observation frequency P0. When DeltaW 3 is less than or equal to DeltaW, a third preset frequency adjustment coefficient B3 is selected to adjust the average observation frequency P0, and the adjusted observation frequency P0 x B3 is obtained.
Specifically, the system obtains an average observation frequency for the observation sites within the demand location. The observation frequency refers to the number of times of observing data in a certain time, and is used for representing the acquisition density of the data. Then, the system acquires a fluctuation range of the observed data in the demand position and a preset fluctuation threshold. The fluctuation range represents the fluctuation range of the data, and the fluctuation threshold is a preset acceptable maximum fluctuation range. Then, the system calculates a fluctuation difference, i.e., a difference between a fluctuation range of the observed data and a preset fluctuation threshold. And according to the relation between the delta W and the preset difference value, the system adjusts the average observation frequency to acquire the adjusted observation frequency.
It can be understood that the observation frequency is dynamically adjusted according to the fluctuation condition of the observation data, and more data in unit time is used as a reference after the observation frequency is improved, so that the change of the data is adapted, and the stability and the accuracy of the data are improved. The weather prediction method is beneficial to more accurately performing weather prediction and providing more reliable weather information for users.
In the above embodiment, by collecting meteorological data and a user demand position and combining with observation site information, the system evaluates and determines the provided observation data through a data accuracy calculation model. The weight distribution of the number of the observation sites, the observation frequency and the abnormal times is fully considered, so that the credibility of the data is comprehensively measured. When the system determines that the observed data for the desired location is accurate, the user will benefit from obtaining accurate real-time weather information and reliable weather predictions, supporting the user to make decisions and plans. In the case of inaccurate data, the multi-level response mechanism of the system provides higher-level response for the user: and judging the stability of the data by acquiring the first preset observation site data. Secondly, for unstable situations, the system will improve the reliability of the data by adjusting the observation site information. This process will allow the user to obtain more reliable real-time weather information and more accurate weather predictions, thereby effectively reducing misdirection and decision bias due to inaccurate data.
In another preferred manner based on the foregoing embodiment, referring to fig. 2, the present embodiment provides a data management system based on a natural language processing technology, including:
the acquisition unit acquires meteorological data and a user's required position, acquires observation site information of the required position, and judges whether the observation data of the required position is accurate or not according to the observation site information;
the accuracy of the observed data is calculated by the following formula:
P=α*N+β*P-γ*Y；
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0; p is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0; y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0; and α+β+γ=1;
the prediction unit is configured to output real-time weather information of the demand position and predict weather when the observed data of the demand position is accurate;
the judging unit is configured to acquire first preset observation site data when the observation data in the required position is inaccurate, and judge whether the observation site data in the required position is stable or not according to the first preset observation site data;
and the adjusting unit is configured to adjust the observation site information when the observation site data in the demand position is unstable, and output the real-time weather information of the demand position and conduct weather prediction after adjustment.
It can be appreciated that the data management method and system based on the natural language processing technology have the same beneficial effects, and are not described herein.
It will be appreciated by those skilled in the art that embodiments of the application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present application and not for limiting the same, and although the present application has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the application without departing from the spirit and scope of the application, which is intended to be covered by the claims.
Claims (2)
1. A data management method based on natural language processing technology, comprising:
acquiring meteorological data and a user's required position, acquiring observation site information of the required position, and judging whether the observation data of the required position is accurate or not according to the observation site information;
the accuracy P of the observed data is calculated by:
P=α×N+β×Q-γ×Y；
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0; q is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0; y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0; and α+β+γ=1;
outputting real-time weather information of the demand position and carrying out weather prediction when the observation data of the demand position is accurate;
when the observation data of the required position is inaccurate, acquiring first preset observation site data, and judging whether the observation site data of the required position is stable or not according to the first preset observation site data;
when the observation site data in the required position is unstable, adjusting the observation site information, and outputting real-time weather information of the required position and carrying out weather prediction after adjustment;
the method for acquiring the meteorological data and the required position of the user, acquiring the observation site information of the required position, judging whether the observation data of the required position is accurate according to the observation site information, and comprises the following steps:
the observation site information comprises the number N of observation sites, the observation frequency Q and the abnormal times N;
presetting an accuracy threshold value P0, and judging whether the observed data in the required position is accurate or not according to the magnitude relation between the accuracy P of the observed data and the accuracy threshold value P0;
when P is more than or equal to PO, judging that the observation data of the required position is accurate, outputting real-time weather information of the required position and carrying out weather prediction;
when P is less than PO, judging that the observed data of the required position is inaccurate, and further judging whether the observed data of the required position is stable or not;
when the observation data of the required position is accurate, outputting the real-time weather information of the required position and carrying out weather prediction, wherein the method comprises the following steps:
collecting real-time precipitation S0, and presetting a first preset precipitation S1, a second preset precipitation S2 and a third preset precipitation S3, wherein S1 is more than S2 and less than S3; presetting a first preset precipitation level D1, a second preset precipitation level D2 and a third preset precipitation level D3, wherein D1 is more than D2 and less than D3;
determining a real-time precipitation level according to the magnitude relation between the real-time precipitation S0 and each preset precipitation;
when S1 is less than or equal to S0 and less than S2, determining the real-time precipitation level as D1;
when S2 is less than or equal to S0 and less than S3, determining the real-time precipitation level as D2;
when S3 is less than or equal to S0, determining that the real-time precipitation level is D3;
adjusting the real-time precipitation level, taking the adjusted precipitation level as the precipitation level after a time interval T, outputting the real-time weather information of the required position and carrying out weather prediction, and further comprising:
acquiring real-time wind power data F0, and presetting a first preset wind power F1, a second preset wind power F2 and a third preset wind power F3, wherein F1 is smaller than F2 and smaller than F3; presetting a first preset adjustment coefficient A1, a second preset adjustment coefficient A2 and a third preset adjustment coefficient A3, wherein A1 is more than A2 and less than A3;
selecting an adjustment coefficient according to the relation between the real-time wind power data F0 and the magnitude of each preset wind power to adjust the time interval T, and obtaining an adjusted time interval;
when F1 is less than or equal to F0 and less than F2, selecting the third preset adjustment coefficient A3 to adjust the time interval T, and obtaining the adjusted time interval as T.A3;
when F2 is less than or equal to F0 and less than F3, selecting the second preset adjustment coefficient A2 to adjust the time interval T, and obtaining the adjusted time interval as T.A2;
when F3 is less than or equal to F0, selecting the first preset adjustment coefficient A1 to adjust the time interval T, and obtaining an adjusted time interval as T.A1;
when the observation data of the required position is inaccurate, further judging whether the observation data of the required position is stable or not, including:
acquiring a first fluctuation range W0 of first preset observation site data, wherein the fluctuation range W1 of the observation data of the required position is used for judging whether the observation site data of the required position is stable or not according to the magnitude relation between the first fluctuation range W0 and the fluctuation range W1 of the observation data of the required position;
when W1 is less than or equal to W0, judging that the observation data of the required position is stable;
when W1 is more than W0, judging that the observed data of the required position is unstable;
when the observation data of the required position is unstable, acquiring altitude information H1 of a first preset observation site, acquiring average altitude H0 of the observation site of the required position, and judging whether the first preset observation site data can be integrated into the observation data of the required position according to the size relation between the altitude information H1 and the average altitude H0;
when 0.9H0 is less than or equal to H1 is less than or equal to 1.1H0, judging that the first preset observation site data can be integrated into the observation data of the required position;
when H1 is less than 0.9H0 or H1 is more than 1.1H0, judging that the first preset observation site data cannot be integrated into the observation data of the required position, adjusting the observation site information, and outputting real-time weather information of the required position and carrying out weather prediction after adjustment;
when it is determined that the first preset observation site data cannot be incorporated into the observation data of the required position, acquiring an average observation frequency Q0 of the observation site in the required position, acquiring a fluctuation difference DeltaW=W1-Wmax between a fluctuation range W1 of the observation data in the required position and a preset fluctuation threshold Wmax, and presetting a first preset difference DeltaW 1, a second preset difference DeltaW 2 and a third preset difference DeltaW 3, wherein DeltaW 1 < DeltaW2 < DeltaW3;
according to the magnitude relation between the fluctuation difference DeltaW and each preset difference value, the average observation frequency Q0 is adjusted, and the adjusted observation frequency is obtained;
according to the magnitude relation between the fluctuation difference DeltaW and each preset difference value, the average observation frequency Q0 is adjusted, and the adjusted observation frequency is obtained, wherein the method comprises the following steps:
presetting a first preset frequency adjustment coefficient B1, a second preset frequency adjustment coefficient B2 and a third preset frequency adjustment coefficient B3, wherein B1 is more than B2 and less than B3;
when DeltaW 1 is less than or equal to DeltaW < DeltaW2, selecting the first preset frequency adjustment coefficient B1 to adjust the average observation frequency Q0, and obtaining an adjusted observation frequency Q0 x B1;
when DeltaW 2 is less than or equal to DeltaW < DeltaW3, selecting the second preset frequency adjustment coefficient B2 to adjust the average observation frequency Q0, and obtaining an adjusted observation frequency Q0 x B2;
when Δw3 is less than or equal to Δw, selecting the third preset frequency adjustment coefficient B3 to adjust the average observed frequency Q0, and obtaining an adjusted observed frequency Q0×b3.
2. A system for applying the natural language processing technology based data management method of claim 1, comprising:
the acquisition unit acquires meteorological data and a user's required position, acquires observation site information of the required position, and judges whether the observation data of the required position is accurate or not according to the observation site information;
the accuracy P of the observed data is calculated by:
P=α×N+β×Q-γ×Y；
wherein N is the number of the observation sites, alpha is the weight occupied by the number of the observation sites, and alpha is more than 0; q is the observation frequency, beta is the weight occupied by the observation frequency, and beta is more than 0; y is the number of anomalies, gamma is the weight occupied by the number of anomalies, and gamma is more than 0; and α+β+γ=1;
the prediction unit is configured to output real-time weather information of the demand position and conduct weather prediction when the observed data of the demand position are accurate;
the judging unit is configured to acquire first preset observation site data when the observation data in the required position is inaccurate, and judge whether the observation site data of the required position is stable or not according to the first preset observation site data;
and the adjusting unit is configured to adjust the observation site information when the observation site data in the required position is unstable, and output the real-time weather information of the required position and conduct weather prediction after adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311095467.4A CN116819655B (en) | 2023-08-29 | 2023-08-29 | Data management method and system based on natural language processing technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311095467.4A CN116819655B (en) | 2023-08-29 | 2023-08-29 | Data management method and system based on natural language processing technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116819655A CN116819655A (en) | 2023-09-29 |
| CN116819655B true CN116819655B (en) | 2023-11-03 |
Family
ID=88124360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311095467.4A Active CN116819655B (en) | 2023-08-29 | 2023-08-29 | Data management method and system based on natural language processing technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116819655B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111831635A (en) * | 2020-07-27 | 2020-10-27 | 广西科技师范学院 | Method and device for accurately extracting meteorological data |
| CN111860970A (en) * | 2020-06-29 | 2020-10-30 | 浪潮电子信息产业股份有限公司 | River flow prediction method and device, electronic equipment and storage medium |
| CN115291774A (en) * | 2022-07-28 | 2022-11-04 | 内蒙古自治区大气探测技术保障中心 | Comprehensive meteorological observation product service system |
| CN115685385A (en) * | 2022-09-19 | 2023-02-03 | 中国气象局乌鲁木齐沙漠气象研究所 | Method and equipment for evaluating release of multi-source live data in rainfall weather |
-
2023
- 2023-08-29 CN CN202311095467.4A patent/CN116819655B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860970A (en) * | 2020-06-29 | 2020-10-30 | 浪潮电子信息产业股份有限公司 | River flow prediction method and device, electronic equipment and storage medium |
| CN111831635A (en) * | 2020-07-27 | 2020-10-27 | 广西科技师范学院 | Method and device for accurately extracting meteorological data |
| CN115291774A (en) * | 2022-07-28 | 2022-11-04 | 内蒙古自治区大气探测技术保障中心 | Comprehensive meteorological observation product service system |
| CN115685385A (en) * | 2022-09-19 | 2023-02-03 | 中国气象局乌鲁木齐沙漠气象研究所 | Method and equipment for evaluating release of multi-source live data in rainfall weather |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116819655A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116089846B (en) | New energy settlement data anomaly detection and early warning method based on data clustering | |
| CN112285807B (en) | Meteorological information prediction method and device | |
| CN110969306B (en) | Power distribution low-voltage transformer area load prediction method and device based on deep learning | |
| CN112182720B (en) | Building energy consumption model evaluation method based on building energy management application scene | |
| CN112818604A (en) | Wind turbine generator risk degree assessment method based on wind power prediction | |
| CN109995562A (en) | Network traffic prediction technique, device, equipment and medium | |
| CN117852723B (en) | Determination method of ecological dispatching scheme of large reservoir engineering | |
| CN111126699B (en) | Hydrological forecasting method and hydrological forecasting system considering rainfall level | |
| CN113988398A (en) | Wind turbine generator power prediction method and device, electronic equipment and storage medium | |
| CN118249348B (en) | Power load prediction method, device, electronic equipment and medium | |
| CN110298765A (en) | A kind of power distribution network electric power method for detecting abnormality based on objective correlative factor | |
| CN108960522A (en) | A kind of photovoltaic power generation quantity prediction analysis method | |
| CN116760017A (en) | Prediction method for photovoltaic power generation | |
| CN117408394B (en) | Carbon emission factor prediction method and device for electric power system and electronic equipment | |
| CN117318051B (en) | Intelligent energy storage management and control system and method based on Internet of things technology | |
| CN116819655B (en) | Data management method and system based on natural language processing technology | |
| CN114254833A (en) | Reservoir water level prediction and scheduling method based on multiple linear regression and meteorological data | |
| CN118011911A (en) | Self-adaptive energy consumption monitoring and adjusting system based on intelligent laboratory | |
| CN110930060B (en) | Parameter calculation-based method for evaluating AGC regulation performance of generator set | |
| CN115051384B (en) | Frequency modulation performance evaluation method, device, equipment and medium | |
| CN110751335B (en) | Regional ecological quality annual scene prediction evaluation method and device | |
| CN116777027A (en) | Load prediction method and system for abnormal days | |
| CN109617122B (en) | Method and device for predicting output of distributed power supply | |
| CN114781685A (en) | Big user power load prediction method and system based on big data mining technology | |
| CN110555543B (en) | Uncertainty analysis method and system for wind power plant prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |