Agricultural big data price early warning management system

Abstract

The invention relates to the technical field of agricultural information, and discloses an agricultural big data price early warning management system, which comprises an information acquisition module, a price prediction module and a price fluctuation early warning module. The information acquisition module is arranged in the large fruit and vegetable planting base and used for acquiring rainfall information, drought information and natural disaster information, the price prediction module is arranged in the large fruit and vegetable planting base and used for predicting the prices of fruits and vegetables, and the price fluctuation early warning module is arranged in the large fruit and vegetable planting base and used for warning the prices of fruits and vegetables. The method is used for evaluating the influence on fruit and vegetable prices according to natural disasters, market fluctuation and supply-demand imbalance. Meteorological and environmental data are collected through the information acquisition module, an environmental influence coefficient is calculated, and the price prediction module predicts the fruit and vegetable prices by using a specific formula in combination with the coefficient, the market transaction price, the average price and other information.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology, and in particular to an agricultural big data price early warning management system. Background Art

[0002] In the agricultural field, fruit and vegetable planting is affected by many factors, among which meteorological conditions and market factors play a crucial role in fruit and vegetable price fluctuations.

[0003] In terms of meteorology, natural disasters such as rain, drought, frost, hail, and blizzards, as well as the occurrence of pests and diseases, will directly affect the growing environment, yield, and quality of fruits and vegetables. For example, excessive rainfall may cause floods, submerge farmland, damage the roots of fruits and vegetables, and lead to reduced production; drought will cause fruits and vegetables to grow slowly or even wither due to lack of water; severe frost, hail, and blizzards may directly damage fruit and vegetable plants; the invasion of pests and diseases will also reduce the yield and quality of fruits and vegetables. However, traditional agricultural production often lacks accurate quantification and systematic analysis of these meteorological and disaster factors. It is difficult for staff to know in advance the specific impact of environmental changes on fruit and vegetable production, and it is impossible to make effective response strategies in time.

[0004] In the market, fruit and vegetable prices are affected by factors such as supply and demand, market transaction price fluctuations, etc. Due to limited information access channels, staff usually find it difficult to fully grasp market dynamics and lack accurate price trend references when making planting decisions. They are prone to blindly follow the trend or miss the best planting time, resulting in excess or insufficient fruit and vegetable production, which in turn causes large price fluctuations and affects planting income.

[0005] In addition, with the development of information technology, big data is increasingly used in various industries. However, in the agricultural field, especially in the integration of meteorological and market data for fruit and vegetable planting, price warning management, etc., there is still a lack of a complete system to comprehensively process this information to help staff make scientific decisions and reduce risks.

[0006] In order to solve the above problems, the present invention proposes an agricultural big data price early warning management system. Summary of the invention

[0007] The present invention proposes an agricultural big data price warning management system, which solves the problems that meteorological and market factors in fruit and vegetable planting affect price fluctuations but lack precise quantitative analysis, staff members have insufficient information acquisition and find it difficult to make scientific decisions, and the integration of meteorological and market data in the agricultural field and the price warning management system are imperfect.

[0008] The technical solution of the present invention is as follows:

[0009] An agricultural big data price early warning management system includes: an information collection module, a price prediction module, and a price fluctuation early warning module.

[0010] The information collection module is set in a large-scale fruit and vegetable planting base, and is used to collect waterlogging information, drought information and natural disaster information.

[0011] The price prediction module is set in a large-scale fruit and vegetable planting base, and is used to predict the prices of fruits and vegetables.

[0012] The price fluctuation warning module is set in a large-scale fruit and vegetable planting base, and is used to evaluate the impact on the prices of fruits and vegetables according to natural disasters, market fluctuations and supply-demand imbalance.

[0013] Preferably, the information collection module includes a meteorological processor and a meteorological information database.

[0014] The meteorological information database is used for uploading and storing by staff the daily rainfall, rainfall duration days, sunny days duration and the occurrence times of frost, hail, heavy snow, plant diseases and insect pests during the growth cycle of fruits and vegetables after the growth cycle of fruits and vegetables ends, and is used for storing the environmental impact coefficient after receiving the environmental impact coefficient.

[0015] The meteorological processor is communicatively connected to the meteorological information database, and is used for calling the daily rainfall and rainfall duration days information, classifying rainfall into light rain, moderate rain and heavy rain according to the rainfall information, recording the moderate rain duration days when the moderate rain duration days are greater than the set threshold, recording the heavy rain duration days when the heavy rain duration days are greater than the set threshold, calculating the waterlogging frequency according to the recorded moderate rain and heavy rain duration days, used for calling the sunny days, calculating the drought frequency according to the sunny days during the growth cycle of fruits and vegetables, used for calling the occurrence times information of frost, hail, heavy snow, plant diseases and insect pests, then calculating the natural disaster degree according to the occurrence times information of frost, hail, heavy snow, plant diseases and insect pests, then calculating the environmental impact coefficient according to the waterlogging frequency, drought frequency and natural disaster degree, and then sending the environmental impact coefficient to the meteorological information database.

[0016] Preferably, the waterlogging frequency calculation formula is:

[0017]

[0018] Where: Y i is the waterlogging frequency, D m is the moderate rain duration days, unit: days, D h is the heavy rain duration days, unit: days.

[0019] The drought frequency calculation formula is:

[0020]

[0021] Where: G x is the drought frequency, D c is the sunny days duration, unit: days.

[0022] Preferably, the natural disaster degree calculation formula is:

[0023] Z c = a 1 × ln(Z 1 2 + Z 2 2 ) + a 2 × Z 3 .

[0024] Where: Z c is the natural disaster degree, Z 1 is the number of frost occurrences, Z 2 is the number of hail occurrences, Z 3 is the number of heavy snow occurrences, a 1 , a 2 are respectively the preset proportionality coefficients of ln(Z 1 2 + Z 2 2 ), Z 3 .

[0025] Preferably, the environmental impact coefficient calculation formula is:

[0026]

[0027] Where: H is the environmental impact coefficient, b 1 , b 2 , b 3 are respectively the preset proportionality coefficients of the rainwaterlogging frequency Y i , the drought frequency G x , and the natural disaster degree Z c , and b 1 , b 2 , b 3 are all greater than 0.

[0028] Preferably, the price prediction module includes a price prediction processor and a fruit and vegetable information database.

[0029] The fruit and vegetable information database is communicatively connected to the network information collection device, and is used for staff to upload various fruit and vegetable market transaction prices, average prices, trading volumes, and inventory information, and then store various fruit and vegetable predicted price information, and is used to store various fruit and vegetable predicted price information after receiving various fruit and vegetable predicted price information.

[0030] The price prediction processor is communicatively connected to the meteorological information database and the fruit and vegetable information database, and is used to call the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, calculate the predicted prices of various fruits and vegetables according to the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, and then send the predicted price information of various fruits and vegetables to the fruit and vegetable information database.

[0031] Preferably, the predicted price formula for the i-th type of fruit and vegetable is:

[0032]

[0033] Where: F i is the predicted price of the i-th type of fruit and vegetable, unit: yuan, i is the fruit and vegetable category number, i = 1, 2, 3,..., S, S is the total number of fruit and vegetable categories, unit: species, J ai is the market transaction price of the i-th type of fruit and vegetable, unit: yuan, J bi is the market transaction average price of the i-th type of fruit and vegetable, unit: yuan, x 1 and x 2 are respectively the weight ratios of the market price and the market transaction average price to the price of the fruit and vegetable.

[0034] Preferably, the price fluctuation warning module is communicatively connected to the fruit and vegetable information database and the staff mobile terminal, and is used to call the market transaction price information of various fruits and vegetables, calculate the short-term price fluctuation range according to the market transaction prices of various fruits and vegetables within the set time, generate a warning message when the short-term price fluctuation range exceeds the set threshold, and then send the warning message to the staff mobile terminal.

[0035] Preferably, the formula for calculating the price fluctuation range of the i-th type of fruit and vegetable crop at time t is:

[0036]

[0037] Where: P Ai is the price fluctuation range of the i-th type of fruit and vegetable crop at time t, P t,i is the market transaction price of the i-th type of fruit and vegetable crop at time t, unit: yuan, P t-1,i is the market transaction price of the i-th type of fruit and vegetable crop at time t-1, unit: yuan.

[0038] Preferably, the price fluctuation warning module is a server.

[0039] The beneficial effects of the present invention are:

[0040] 1. The information collection module collects meteorological and environmental data, calculates the environmental impact coefficient, and the price prediction module combines this coefficient with market transaction prices, average prices and other information, and uses a specific formula to predict the prices of fruits and vegetables.

[0041] 2. Monitor the trading prices of fruits and vegetables in real time and calculate the short-term price fluctuation range. Once the fluctuation range exceeds the set threshold, an early warning message will be immediately sent to the mobile terminals of the staff. With the long-term accumulated meteorological data, price forecasts, and fluctuation early warning information, the staff can better plan the types and scales of fruit and vegetable planting.

[0042] 3. Through the application of the price fluctuation early warning module, the real-time monitoring and early warning of the prices in the fruits and vegetables market are realized. This module can accurately call the predicted price information and market trading price information of various fruits and vegetables. Through scientific calculation and analysis, it can keenly capture the short-term price fluctuations. Once the price fluctuation exceeds the set threshold, the module will automatically generate an early warning message and immediately send it to the mobile terminals of the staff. This early warning mechanism not only improves the response speed of the staff to market dynamics but also provides them with scientific decision-making support. Brief Description of the Drawings

[0043] The present invention will be further described in detail below in conjunction with the drawings and specific embodiments.

[0044] Figure 1 It is a schematic block diagram of an agricultural big data price early warning management system of the present invention; Specific Embodiments

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of the present invention.

[0046] Please refer to Figure 1 , the present invention provides an agricultural big data price early warning management system, including: an information collection module, a price prediction module, and a price fluctuation early warning module.

[0047] The information collection module is set in large-scale fruit and vegetable planting bases and is used to collect waterlogging information, drought information, and natural disaster information.

[0048] The price prediction module is set in large-scale fruit and vegetable planting bases and is used to predict the prices of fruits and vegetables.

[0049] The price fluctuation early warning module is set in large-scale fruit and vegetable planting bases and is used to evaluate the impact on fruit and vegetable prices based on natural disasters, market fluctuations, and supply-demand imbalances.

[0050] In this embodiment, the information collection module includes a meteorological information collection station, a meteorological processor, and a meteorological information database.

[0051] The meteorological information database is used for uploading and storing the daily rainfall, rainfall duration days, sunny days, and the occurrence times of frost, hail, heavy snow, and pests and diseases during the growth cycle of fruits and vegetables by staff after the growth cycle of fruits and vegetables ends, and for storing the environmental impact coefficient after receiving the environmental impact coefficient. The meteorological information database can adopt a cloud server.

[0052] The meteorological processor is communicatively connected to the meteorological information database, and is used for calling the daily rainfall and rainfall duration days information. According to the rainfall information, it is divided into light rain, moderate rain, and heavy rain. When the duration days of moderate rain are greater than the set threshold, the duration days of moderate rain are recorded. When the duration days of heavy rain are greater than the set threshold, the duration days of heavy rain are recorded. The waterlogging frequency is calculated according to the recorded duration days of moderate rain and heavy rain. It is used for calling the number of sunny days and calculating the drought frequency according to the number of sunny days during the growth cycle of fruits and vegetables. It is used for calling the occurrence times information of frost, hail, heavy snow, and pests and diseases, and then calculating the natural disaster degree according to the occurrence times information of frost, hail, heavy snow, and pests and diseases. Then, the environmental impact coefficient is calculated according to the waterlogging frequency, drought frequency, and natural disaster degree, and then the environmental impact coefficient is sent to the meteorological information database.

[0053] Light rain: within 24 hours, the rainfall is below 10 mm, the clothes can be wetted, there is a small amount of water accumulation on the road, and the muddy ground is completely wet but there is no water accumulation phenomenon.

[0054] Moderate rain: within 24 hours, the rainfall is between 10 and 25 mm, the sound of rain can be heard, and there is a small amount of water accumulation in the depressions.

[0055] Heavy rain: within 24 hours, the rainfall is above 25 mm, the sound of rain is intense, and the water in the drainage ditch flows very fast.

[0056] Key data including daily rainfall, rainfall duration days, number of sunny days, and the occurrence times of special meteorological events such as frost, hail, heavy snow, and pests and diseases are regularly collected by staff. These data are then sent to the meteorological information database for storage, ensuring the centralized management and long-term preservation of information. The meteorological processor further uses these data for analysis and processing, calculates the waterlogging frequency through the duration days of moderate rain and heavy rain, screens and calculates the number of sunny days during the growth cycle of fruits and vegetables to obtain the drought frequency, and evaluates the natural disaster degree according to the special meteorological events and pest and disease information. Finally, the meteorological processor comprehensively calculates the environmental impact coefficient, which reflects the degree of influence of a specific area by meteorological conditions and natural disasters, and is sent to the meteorological information database for storage again.

[0057] In this embodiment, the formula for calculating the waterlogging frequency is:

[0058]

[0059] Where: Yi is the rainstorm frequency, D m is the number of moderate rain days, unit: day, D h is the number of heavy rain days, unit: day, D b is a growth period, unit: day.

[0060] For example: within a 100-day growth period, the number of consecutive moderate rain days is 8 days, and the number of consecutive heavy rain days is 5 days. The calculated rainstorm frequency is 0.13.

[0061] In this embodiment, the drought frequency calculation formula is:

[0062]

[0063] where: G x is the drought frequency, D c is the number of sunny days, unit: day.

[0064] For example: within a 100-day growth period, the number of sunny days is 7 days. The calculated drought frequency is 0.07.

[0065] The natural disaster degree calculation formula is:

[0066] Z c = a 1 ×ln(Z 1 2 + Z 2 2 ) + a 2 ×Z 3 .

[0067] where: Z c is the natural disaster degree, Z 1 is the number of frost occurrences, Z 2 is the number of hail occurrences, Z 3 is the number of heavy snow occurrences, a 1 、a 2 are the preset proportionality coefficients of ln(Z 1 2 + Z 2 2 )、Z 3 respectively.

[0068] For example: within a growth period, the number of frost occurrences is 2 times, the number of hail occurrences is 1 time, and the number of heavy snow occurrences is 0 time. And the preset proportionality coefficients, a 1 = 0.3、a 2 = 0.2. The calculated natural disaster degree is 0.48.

[0069] In this embodiment, the environmental impact coefficient calculation formula is:

[0070]

[0071] Where: H is the environmental impact coefficient, b 1 、b 2 、b 3 are respectively the preset proportionality coefficients of the waterlogging frequency Y i 、the drought frequency G x 、and the degree of natural disasters Z c and b 1 、b 2 、b 3 are all greater than 0.

[0072] For example: the waterlogging frequency is 0.13, the drought frequency is 0.07, and the degree of natural disasters is 0.48. The preset proportionality coefficients b i 、b x 、b c of the waterlogging frequency Y 1 、the drought frequency G 2 、and the degree of natural disasters Z 3 are 0.3, 0.4, and 0.3 respectively, and the calculated environmental impact coefficient is 0.21.

[0073] In this embodiment, the price prediction module includes a price prediction processor and a fruit and vegetable information database.

[0074] The fruit and vegetable information database is communicatively connected to the network information collection device and is used for staff to upload various fruit and vegetable market transaction prices, average prices, trading volumes, and inventory information, and then store various fruit and vegetable predicted price information. After receiving various fruit and vegetable predicted price information, it stores various fruit and vegetable predicted price information. The fruit and vegetable information database can adopt a cloud server.

[0075] The price prediction processor is communicatively connected to the meteorological information database and the fruit and vegetable information database, and is used to call the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, calculate various fruit and vegetable predicted prices according to the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, and then send various fruit and vegetable predicted price information to the fruit and vegetable information database.

[0076] Through the network information collection device, the module can capture the transaction prices, average prices, trading volumes, and inventory information of various fruits and vegetables in the market in real time, and summarize this information to the fruit and vegetable information database. The price prediction processor then uses this data, combined with the environmental impact coefficient obtained from the meteorological information database, to calculate the predicted prices of various fruits and vegetables over a period of time through a complex algorithm model. Finally, this predicted price information is also stored back in the fruit and vegetable information database for staff reference.

[0077] In this embodiment, the predicted price formula for the i-th type of fruit and vegetable is:

[0078]

[0079] Where: F i is the predicted price of the i-th type of fruit and vegetable, unit: yuan, i is the fruit and vegetable category number, i = 1, 2, 3,..., S, S is the total number of fruit and vegetable categories, unit: species, J ai is the market transaction price of the i-th type of fruit and vegetable, unit: yuan, J bi is the average market transaction price of the i-th type of fruit and vegetable, unit: yuan, x 1 and x 2 are the weight ratios of the market price and the average market transaction price to the price of the fruit and vegetable respectively.

[0080] For example: For the 3rd type of fruit and vegetable, assuming S = 5, its market transaction price J ai is 4 yuan, and the average market transaction price J bi is 3.5 yuan. The weight ratios x 1 and x 2 of the market price and the average market transaction price to the price of the fruit and vegetable are 0.7 and 0.3 respectively. It can be calculated that the predicted price of the 3rd type of fruit and vegetable is 3.85 yuan.

[0081] In this embodiment, the price fluctuation warning module is communicatively connected to the fruit and vegetable information database and the staff mobile terminal, and is used to call the market transaction price information of various fruits and vegetables, calculate the short-term price fluctuation range based on the market transaction prices of various fruits and vegetables within the set time, generate a warning message when the short-term price fluctuation range exceeds the set threshold, and then send the warning message to the staff mobile terminal.

[0082] Real-time monitoring of the dynamic market price of fruits and vegetables, and timely issuing a warning of abnormal price fluctuations to protect the interests of the staff. This module establishes a communication connection with the fruit and vegetable information database and the staff mobile terminal, and can call the predicted price information and market transaction price information of various fruits and vegetables at any time.

[0083] In this embodiment, the formula for calculating the price fluctuation range of the i-th fruit and vegetable crop at time t is:

[0084]

[0085] Where: P Ai is the price fluctuation range of the i-th fruit and vegetable crop at time t, P t,i is the market transaction price of the i-th fruit and vegetable crop at time t, unit: yuan, P t-1,i is the market transaction price of the i-th fruit and vegetable crop at time t - 1, unit: yuan.

[0086] For example: Assuming the 4th fruit and vegetable crop, the market transaction price P todayt,i is 5.5 yuan, and the market transaction price P yesterday t-1,i is 5 yuan. It can be calculated that the price fluctuation range P Ai is 0.1.

[0087] In this embodiment, the price fluctuation warning module is a server.

[0088] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, 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 agricultural big data price early warning management system, characterized by: include: Information collection module, price prediction module, price fluctuation warning module; The information collection module is set in a large fruit and vegetable planting base to collect rain and waterlogging information, drought information and natural disaster information; The price prediction module is arranged in a large fruit and vegetable planting base and is used to predict the price of fruits and vegetables; The price fluctuation warning module is arranged in a large-scale fruit and vegetable planting base, and is used to evaluate the impact on fruit and vegetable prices according to natural disasters, market fluctuations and supply and demand imbalances.

2. According to claim 1, an agricultural big data price early warning management system is characterized in that: The information collection module includes a meteorological information collection station, a meteorological processor, and a meteorological information database; The meteorological information database is used for the staff to upload and store the daily rainfall, continuous days of rainfall, continuous days of sunny days, and the number of occurrences of frost, hail, blizzard, and pests and diseases during the growth cycle of fruits and vegetables after the growth cycle of fruits and vegetables ends, and is used to store the environmental impact coefficient after receiving it; The meteorological processor is communicatively connected with the meteorological information database, and is used to call the information of daily rainfall and duration of rainfall, and is divided into light rain, moderate rain and heavy rain according to the rainfall information. When the duration of moderate rain is greater than a set threshold, the duration of moderate rain is recorded, and when the duration of heavy rain is greater than a set threshold, the duration of heavy rain is recorded. The frequency of rain and waterlogging is calculated based on the recorded duration of moderate rain and heavy rain, and is used to call the number of sunny days, and calculate the frequency of drought based on the number of sunny days in the growth cycle of fruits and vegetables. It is used to call the number of occurrences of frost, hail, blizzard, and pests and diseases, and then calculate the degree of natural disasters based on the number of occurrences of frost, hail, blizzard, and pests and diseases, and then calculate the environmental impact coefficient based on the frequency of rain and waterlogging, the frequency of drought, and the degree of natural disasters, and then send the environmental impact coefficient to the meteorological information database.

3. According to claim 2, an agricultural big data price early warning management system is characterized in that: The calculation formula for rainwater flooding frequency is: Where: Y i is the frequency of flooding, D m The number of moderate rainy days, unit: day, D h is the number of days with heavy rain, unit: day, D b It is a growth cycle, unit: day.

4. According to claim 3, an agricultural big data price early warning management system is characterized in that: The drought frequency calculation formula is: Where: G x is the drought frequency, D c is the number of sunny days, unit: day; The formula for calculating the degree of natural disasters is: WITH c =a1×ln(Z1 2 +Z2 2 )+a2×Z3; Where: Z c is the degree of natural disasters, Z1 is the number of frost occurrences, Z2 is the number of hail occurrences, Z3 is the number of blizzard occurrences, a1 and a2 are ln(Z1 2 +Z2 2 ), preset scale factor of Z3.

5. According to claim 4, an agricultural big data price early warning management system is characterized in that: The environmental impact coefficient calculation formula is: Among them: H is the environmental impact coefficient, b1, b2, b3 are the rain and waterlogging frequencies Y i , drought frequency G x , Natural disaster severity Z c The proportional coefficient is preset, and b1, b2, and b3 are all greater than 0.

6. According to claim 4, an agricultural big data price early warning management system is characterized in that: The price prediction module includes a price prediction processor and a fruit and vegetable information database; The fruit and vegetable information database is connected to the network information collection device for communication, and is used for the staff to upload the market transaction price and average price, transaction volume, and inventory information of various fruits and vegetables, and then store various fruit and vegetable forecast price information, and is used for storing various fruit and vegetable forecast price information after receiving various fruit and vegetable forecast price information; The price prediction processor is connected to the meteorological information database and the fruit and vegetable information database for communication, and is used to call the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, calculate various fruit and vegetable forecast prices based on the environmental impact coefficient, various fruit and vegetable market transaction prices and average price information, and then send the various fruit and vegetable forecast price information to the fruit and vegetable information database.

7. According to claim 6, an agricultural big data price early warning management system is characterized in that: The formula for predicting the price of the i-th category of fruits and vegetables is: Among them: F i is the predicted price of the i-th category of fruits and vegetables, unit: yuan, i is the fruit and vegetable category number, i=1, 2, 3, ..., S, S is the total number of fruit and vegetable categories, unit: species, J ai is the market transaction price of the i-th type of fruits and vegetables, unit: yuan, J bi is the average market transaction price of the i-th category of fruits and vegetables, unit: yuan, x1 and x2 are the weighted proportions of market price and average market transaction price to the price of fruits and vegetables respectively.

8. According to claim 6, an agricultural big data price early warning management system is characterized by: The price fluctuation warning module is communicatively connected with the fruit and vegetable information database and the staff mobile terminal, and is used to call the market transaction price information of various fruits and vegetables, calculate the short-term price fluctuation range according to the market transaction prices of various fruits and vegetables within a set time, and generate warning information when the short-term price fluctuation range exceeds a set threshold, and then send the warning information to the staff mobile terminal.

9. The agricultural big data price early warning management system according to claim 8, characterized in that: The formula for calculating the price fluctuation of the i-th fruit and vegetable crop at time t is: Where: P Ai is the price fluctuation range of the i-th fruit and vegetable crop at time t, P t,i is the market transaction price of the i-th fruit and vegetable crop at time t, unit: yuan, P t-1,i is the market transaction price of the i-th fruit and vegetable crop at time t-1, unit: yuan.

10. The agricultural big data price early warning management system according to claim 8, characterized in that: The price fluctuation early warning module is a server.

Images