Fresh food freshness monitoring method, system and equipment and storage medium

Abstract

The invention provides a fresh food freshness monitoring method, system and device and a storage medium, and relates to the technical field of fresh food monitoring, and the method comprises the steps: obtaining a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference value between the current weight and the initial weight of the target fresh food; determining a first freshness score of the target fresh food according to a first environment feature of the current environment and the surface image; determining a second freshness score of the target fresh food according to the weight difference value and a second environment feature of the current environment; determining an initial fresh degree grade of the target fresh food in combination with the first fresh degree score and the second fresh degree score; and obtaining a target gas concentration of the target fresh food in a preset range, adjusting the initial fresh degree grade according to the target gas concentration, and generating a target fresh degree grade of the target fresh food. The method has the technical effect that the accuracy of fresh freshness evaluation is improved.

Description

Technical Field

[0001] The present application relates to the technical field of fresh produce freshness monitoring, and in particular to a fresh produce freshness monitoring method, system, device and storage medium. Background Art

[0002] Fresh products are prone to quality deterioration during circulation and storage, leading to economic losses, so the freshness of fresh products needs to be monitored and evaluated in real time.

[0003] Currently, the commonly used monitoring methods usually evaluate the freshness of fresh produce from a single dimension. For example, some rely only on image recognition technology to analyze the surface characteristics of fresh produce, while others only use weighing to determine the degree of water loss. This single-dimensional evaluation method ignores the complex changes in the characteristics of fresh produce during storage, resulting in inaccurate evaluation results. Summary of the invention

[0004] The present application provides a method for monitoring the freshness of fresh produce, which is used to improve the accuracy of freshness assessment of fresh produce.

[0005] In a first aspect, the present application provides a method for monitoring the freshness of fresh food, the method comprising: obtaining a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference between a current weight of the target fresh food and an initial weight of the target fresh food; determining a first freshness score of the target fresh food based on a first environmental feature of the current environment and the surface image; determining a second freshness score of the target fresh food based on the weight difference and a second environmental feature of the current environment, the current environment including the first environmental feature and the second environmental feature; determining an initial freshness level of the target fresh food in combination with the first freshness score and the second freshness score; obtaining a target gas concentration within a preset range of the target fresh food, adjusting the initial freshness level based on the target gas concentration, and generating a target freshness level of the target fresh food.

[0006] By adopting the above technical solution, the surface image and weight difference of the target fresh food are collected as basic data, and these data are analyzed and processed in combination with the current environmental characteristics, so as to obtain the first freshness score and the second freshness score reflecting the appearance and water loss of the fresh food. This scoring method takes into account the impact of environmental factors on the quality change of fresh food, making the evaluation results more objective. By combining the two scores to determine the initial freshness level, and then introducing the target gas concentration as an important indicator for level adjustment, a comprehensive evaluation of the freshness of fresh food from three dimensions: appearance, weight and gas is achieved. This multi-dimensional evaluation method overcomes the limitations of single indicator evaluation and improves the accuracy of freshness evaluation.

[0007] Optionally, determining the first freshness score of the target fresh produce based on the first environmental feature of the current environment and the surface image includes: determining an environmental error coefficient of the current environment relative to the standard environment based on the first environmental feature; correcting the surface image based on the environmental error coefficient to obtain a target surface image, wherein the environmental error coefficient is used as a coefficient for correcting color parameters and brightness parameters of the surface image; matching the target surface image with a standard surface image in a pre-stored standard image library, and determining the first freshness score of the target fresh produce based on the matching result, wherein the standard image library includes standard surface images corresponding to the target fresh produce at different freshness scores.

[0008] By adopting the above technical solution, the technical solution of correcting the surface image by the environmental error coefficient solves the problem that there may be color and brightness differences in fresh images taken under different environmental conditions. Specifically, the environmental error coefficient is obtained by comparing the current environment with the standard environment, and the color parameters and brightness parameters of the surface image are corrected with the coefficient to obtain the target surface image. This corrected image can eliminate the interference of factors such as ambient lighting, making it closer to the imaging effect under the standard environment. When the corrected target surface image is matched with the standard surface image in the standard image library, a more accurate matching result can be obtained, thereby improving the accuracy of the first freshness score. This image evaluation method based on environmental correction makes the evaluation results of freshness under different environmental conditions more comparable and reliable.

[0009] Optionally, determining a second freshness score for the target fresh produce based on the weight difference and a second environmental characteristic of the current environment includes: determining a weight error coefficient of the current environment relative to the standard environment based on the second environmental characteristic; correcting the weight difference based on the weight error coefficient to obtain a target weight difference, wherein the weight error coefficient is a coefficient for correcting a deviation of the weight difference due to environmental influences; matching the target weight difference with a standard weight difference in a pre-stored standard weight library, and determining a second freshness score for the target fresh produce based on the matching result, wherein the standard weight library includes standard weight differences corresponding to the target fresh produce at different freshness scores.

[0010] By adopting the above technical solution, the weight error coefficient is obtained by comparing the current environment with the standard environment, and the weight difference is corrected with the coefficient to obtain the target weight difference. This corrected weight difference can eliminate the influence of factors such as ambient temperature and humidity on the water loss rate of fresh food, making it closer to the weight change under the standard environment. When the corrected target weight difference is matched with the standard weight difference in the standard weight library, a more accurate matching result can be obtained, thereby improving the accuracy of the second freshness score. This weight assessment method based on environmental correction makes the assessment results of freshness under different environmental conditions more comparable and reliable.

[0011] Optionally, combining the first freshness score and the second freshness score to determine the initial freshness level of the target freshness includes: obtaining a first weight coefficient corresponding to the first freshness score and a second weight coefficient corresponding to the second freshness score; arithmetically multiplying the first freshness score by the first weight coefficient to obtain a first weighted score, and arithmetically multiplying the second freshness score by the second weight coefficient to obtain a second weighted score; arithmetically adding the first weighted score and the second weighted score to obtain a target score value; and determining the initial freshness level of the target freshness according to the target score value.

[0012] By adopting the above technical solution, the weighted score is obtained by multiplying the two scores with their corresponding weight coefficients, and then the weighted scores are added to obtain the target score value, thereby realizing the reasonable weighting of different scoring indicators. This weighted calculation method allows the evaluation of fresh appearance characteristics and weight changes to be differentiated according to their importance, avoiding the evaluation bias that may be caused by simple averaging, so that the final initial freshness level is more in line with the actual situation, and improves the scientificity and accuracy of freshness evaluation.

[0013] Optionally, adjusting the initial freshness level according to the target gas concentration to generate the target freshness level of the target freshness includes: determining a preset gas concentration threshold according to the type of the target freshness, wherein the preset gas concentration threshold includes multiple concentration intervals, each concentration interval corresponds to a standard gas concentration of the target freshness at different freshness levels; determining a first freshness level of the target freshness according to the target gas concentration on the basis of the preset gas concentration threshold; and adjusting the initial freshness level according to the first freshness level to generate the target freshness level of the target freshness.

[0014] By adopting the above technical solution, the problem that changes in the fresh food may be ignored when relying solely on appearance and weight evaluation is solved by comparing the target gas concentration with the preset gas concentration threshold. By setting preset gas concentration thresholds containing multiple concentration intervals for different types of target fresh food, and matching the measured target gas concentration with these intervals, a first freshness level reflecting changes in the fresh food is obtained, and the initial freshness level is adjusted with this level to finally generate a target freshness level. This gas concentration-based level adjustment method can promptly detect possible quality changes inside the fresh food, making up for the shortcomings of relying solely on appearance and weight evaluation, and making the freshness evaluation results of the fresh food more comprehensive and accurate.

[0015] Optionally, the adjusting the initial freshness level according to the first freshness level to generate the target freshness level of the target freshness level includes: calculating the level difference between the initial freshness level and the first freshness level; judging whether the level difference exceeds a level difference threshold; if the level difference does not exceed the level difference threshold, determining the initial freshness level as the target freshness level of the target freshness level; if the level difference exceeds the level difference threshold, adjusting the initial freshness level according to the first freshness level to obtain the target freshness level of the target freshness level, wherein when the first freshness level is higher than the initial freshness level, the initial freshness level is increased; when the first freshness level is lower than the initial freshness level, the initial freshness level is decreased.

[0016] By adopting the above technical solution, the solution of setting a level difference threshold to determine whether the initial freshness level needs to be adjusted solves the problem of how to make reasonable adjustments when there are differences in the levels obtained from different evaluation dimensions. When the difference between the initial freshness level and the first freshness level obtained based on gas concentration is within the threshold range, the initial evaluation result is kept unchanged to avoid unnecessary level adjustments; when the difference exceeds the threshold, the initial freshness level is adjusted accordingly according to the level of the first freshness level. This threshold-based dynamic adjustment mechanism not only ensures the stability of the evaluation results, but also can promptly discover and correct major evaluation deviations, thereby making the final target freshness level more accurate and reliable.

[0017] Optionally, after generating the target freshness level of the target freshness level of the target freshness level within a first preset time period, it also includes: obtaining a change trend of the target freshness level of the target freshness level within a first preset time period; based on the change trend, predicting a predicted freshness level of the target freshness level after a second preset time period; when the predicted freshness level is lower than a preset level threshold, generating warning information, wherein the warning information includes the current target freshness level of the target freshness level, the predicted freshness level and a recommended processing method.

[0018] By adopting the above technical solution, by analyzing the changing trend of the target freshness level within the first preset time period and predicting the predicted freshness level after the second preset time period, the problem of the difficulty in predicting the deterioration of fresh quality is solved. When the predicted freshness level is lower than the preset level threshold, the system will generate early warning information including the current target freshness level, the predicted freshness level and the recommended treatment method. This prediction and early warning mechanism based on historical data can detect the significant deterioration of fresh quality in advance, so that management personnel can take corresponding treatment measures in time, thereby effectively preventing the deterioration of fresh food and reducing economic losses.

[0019] In a second aspect, the present application provides a freshness monitoring system for fresh food, the system comprising: an acquisition module, a first determination module, a second determination module, a combination module and an adjustment module; wherein the acquisition module is used to acquire a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference between a current weight of the target fresh food and an initial weight of the target fresh food; the first determination module is used to determine a first freshness score of the target fresh food according to a first environmental feature of the current environment and the surface image; the second determination module is used to determine a second freshness score of the target fresh food according to the weight difference and a second environmental feature of the current environment, the current environment including the first environmental feature and the second environmental feature; the combination module is used to determine an initial freshness level of the target fresh food by combining the first freshness score and the second freshness score; the adjustment module is used to acquire a target gas concentration within a preset range of the target fresh food, adjust the initial freshness level according to the target gas concentration, and generate a target freshness level of the target fresh food.

[0020] In a third aspect, the present application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface, and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned freshness monitoring methods.

[0021] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and execute any of the above-mentioned freshness monitoring methods.

[0022] In summary, the present application includes at least one of the following beneficial technical effects: 1. By collecting the surface image and weight difference of the target fresh produce as basic data, and analyzing and processing these data in combination with the current environmental characteristics, the first freshness score and the second freshness score reflecting the appearance and water loss of the fresh produce are obtained. This scoring method takes into account the impact of environmental factors on the quality changes of fresh produce, making the evaluation results more objective; 2. By combining the two scores to determine the initial freshness level, and then introducing the target gas concentration as an important indicator to adjust the level, a comprehensive evaluation of the freshness of fresh food from three dimensions: appearance, weight, and gas is achieved. This multi-dimensional evaluation method overcomes the limitations of single indicator evaluation and improves the accuracy of freshness evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of a method for monitoring the freshness of fresh produce provided in an embodiment of the present application; Figure 2 It is a structural schematic diagram of a fresh produce freshness monitoring system provided in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0024] Description of reference numerals: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of the present application, words such as "illustrative", "for example" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "illustrative", "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "illustrative", "for example" or "for example" is intended to present related concepts in a concrete way.

[0027] Figure 1 FIG. 1 is a flow chart of a method for monitoring the freshness of fresh produce provided in an embodiment of the present application. Figure 1 As shown, the method includes S101-S105: S101, obtaining a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference between a current weight of the target fresh food and an initial weight of the target fresh food.

[0028] Since the freshness of fresh produce during storage and sales is directly related to food safety, an accurate freshness monitoring method needs to be established. During storage, fresh produce may experience surface color changes, water loss, and other phenomena, which are important indicators for judging freshness. This embodiment achieves accurate freshness monitoring by acquiring two key indicators, the surface image and weight difference of the target fresh produce.

[0029] Specifically, an image acquisition device and a weight sensor are set in the storage environment of the target fresh food, wherein the image acquisition device can be a CCD camera or a CMOS camera, which is used to acquire the surface image of the target fresh food in real time; the weight sensor can be a high-precision electronic weighing device, which is used to measure the real-time weight of the target fresh food. When the target fresh food is put into storage, the weight in the initial state is first acquired and recorded as the initial weight, and then during the monitoring process, the current weight is acquired in real time by the weight sensor, and the difference between the current weight and the initial weight is used as the weight difference. The data acquired by the image acquisition device and the weight sensor are transmitted to the data processing unit through a wireless communication module or a wired connection. Among them, the image acquisition device acquires the surface image of the target fresh food every preset time period (for example, 30 minutes), and the weight sensor continuously acquires weight data. This method can not only obtain the information on the change of the appearance of the fresh food, but also monitor the degree of water loss, thereby providing comprehensive data support for the subsequent freshness evaluation. Through the implementation of this step, the real-time and accurate monitoring of the state of the target fresh food can be realized, providing a reliable data basis for the subsequent freshness scoring. At the same time, due to the use of an automated monitoring method, the subjectivity and discontinuity of manual detection are avoided, and the monitoring efficiency and accuracy are improved.

[0030] S102: Determine a first freshness score of a target fresh product according to a first environmental feature and a surface image of a current environment.

[0031] Specifically, since the surface image of the target fresh food will be affected by factors such as ambient light, temperature, and humidity, direct freshness assessment based on the surface image may result in large errors. Therefore, it is necessary to correct the image based on environmental characteristics before scoring.

[0032] In this embodiment, the first environmental feature includes parameters such as ambient light intensity, color temperature, and ambient temperature and humidity. First, environmental monitoring equipment such as light sensors and temperature and humidity sensors are set in the storage environment of the target fresh food to collect environmental parameters in real time. The currently collected environmental parameters are compared with the parameters under the standard environment to calculate the environmental error coefficient. Among them, the standard environment refers to an ideal storage environment with a light intensity of 500lux, a color temperature of 5000K, a temperature of 4°C, and a relative humidity of 85%. The calculation of the environmental error coefficient takes into account the weight of each environmental parameter. For example, the deviation of light intensity can be assigned a weight of 0.4, the color temperature deviation can be assigned a weight of 0.3, the temperature deviation can be assigned a weight of 0.2, and the humidity deviation can be assigned a weight of 0.1. The comprehensive environmental error coefficient is obtained by weighted calculation. After obtaining the environmental error coefficient, the surface image of the target fresh food is corrected, mainly including the correction of color parameters and brightness parameters.

[0033] Specifically, the image processing algorithm is used to adjust the image parameters such as RGB value, brightness value, and contrast to restore the image features under the standard environment. The corrected target surface image is matched with a pre-established standard image library, which stores standard surface images corresponding to the target fresh food under different freshness scores. These standard images are all collected under a standard environment. The image feature matching algorithm is used to calculate the similarity between the target surface image and each standard surface image in the standard image library, and the freshness score corresponding to the standard surface image with the highest similarity is selected as the first freshness score.

[0034] Based on the above embodiment, as an optional implementation, in S102, determining the first freshness score of the target fresh food according to the first environmental feature and the surface image of the current environment specifically includes S201-S203: S201, determining an environmental error coefficient of a current environment relative to a standard environment according to a first environmental feature.

[0035] S202, correcting the surface image according to the environmental error coefficient to obtain a target surface image, wherein the environmental error coefficient is used as a coefficient for correcting color parameters and brightness parameters of the surface image.

[0036] S203, matching the target surface image with a standard surface image in a pre-stored standard image library, and determining a first freshness score of the target fresh food according to the matching result, wherein the standard image library includes standard surface images corresponding to the target fresh food at different freshness scores.

[0037] The essence of the environmental error coefficient is to measure the degree of influence of the current environmental conditions on image acquisition. It is a normalized coefficient obtained by weighted combination of multiple environmental parameters. Taking the standard environment (light intensity 500lux, color temperature 5000K, temperature 4℃, relative humidity 85%) as the benchmark, calculate the deviation between the current environmental parameters and the standard values. The specific calculation process is as follows: Light intensity deviation coefficient: Assuming the current light intensity is 600 lux, the deviation is: |(600-500)| / 500=0.2, the weight is 0.4, then the weighted value is: 0.2×0.4=0.08.

[0038] Color temperature deviation coefficient: Assuming the current color temperature is 5500K, the deviation is: |(5500-5000)| / 5000=0.1, the weight is 0.3, and the weighted value is: 0.1×0.3=0.03.

[0039] Temperature deviation coefficient: Assuming the current temperature is 6°C, the deviation is: |(6-4)| / 4 = 0.5, the weight is 0.2, and the weighted value is: 0.5×0.2=0.1.

[0040] Humidity deviation coefficient: Assuming the current humidity is 80%, the deviation is: |(80-85)| / 85=0.059, the weight is 0.1, and the weighted value is: 0.059×0.1=0.0059.

[0041] The final environmental error coefficient is the sum of all weighted values: 0.08+0.03+0.1+0.0059=0.2159.

[0042] Specifically, when evaluating the freshness of food, image features are an important basis for judgment, but environmental factors can have a significant impact on image acquisition, so a series of processing steps are required to ensure the accuracy of the evaluation.

[0043] First, the first environmental feature mainly includes parameters such as ambient light intensity, color temperature, and temperature and humidity, which are different from the standard environment. The standard environment in this embodiment refers to an ideal storage environment with a light intensity of 500lux, a color temperature of 5000K, a temperature of 4°C, and a relative humidity of 85%. The current environmental parameters are collected in real time by the environmental sensor, and compared with the standard environmental parameters to obtain the deviation values ​​of each parameter. When calculating the environmental error coefficient, taking into account the different degrees of influence of different environmental parameters on image quality, a weighted calculation method is adopted, and the weight of the light intensity deviation is set to 0.4, the weight of the color temperature deviation is set to 0.3, the weight of the temperature deviation is set to 0.2, and the weight of the humidity deviation is set to 0.1. The comprehensive environmental error coefficient is obtained by weighted summation.

[0044] After obtaining the environmental error coefficient, the collected surface image needs to be corrected. Specifically, the RGB value of the image is corrected through the image processing algorithm, and the environmental error coefficient is used as the correction factor to adjust the pixel values ​​of the red, green and blue channels respectively; at the same time, the brightness value and contrast of the image are corrected accordingly according to the environmental error coefficient to eliminate the influence of ambient light on the visual effect of the image. The target surface image obtained after correction is closer to the real image characteristics under the standard environment.

[0045] Next, the corrected target surface image is matched with the pre-established standard image library. The standard image library stores standard surface images of the target fresh produce at different freshness scoring stages, and these standard images are collected under standard environments. The matching process uses an image feature matching algorithm, including multiple dimensions such as color feature matching, texture feature matching, and shape feature matching. By calculating the similarity between the target surface image and each standard surface image in the standard image library, the freshness score corresponding to the standard surface image with the highest similarity is selected as the first freshness score.

[0046] S103, determining a second freshness score of the target fresh food according to the weight difference and a second environmental characteristic of the current environment, where the current environment includes the first environmental characteristic and the second environmental characteristic.

[0047] Since the weight change of the target fresh food is affected not only by its own water loss, but also by factors such as ambient temperature and humidity, directly using weight difference to evaluate freshness may lead to inaccurate evaluation results.

[0048] In this embodiment, the second environmental characteristics mainly include parameters such as ambient temperature, relative humidity and air pressure. These parameters will affect the evaporation rate of fresh water, and thus affect the accuracy of the weight difference. In order to eliminate the influence of environmental factors, it is first necessary to calculate the weight error coefficient based on the second environmental characteristics.

[0049] Specifically, the environmental parameters are collected in real time through the temperature and humidity sensor and the air pressure sensor, and these parameters are compared with the parameters under the standard environment. Among them, in addition to maintaining the temperature at 4°C and the relative humidity at 85%, the standard environment also needs to maintain the standard atmospheric pressure (i.e., 101.325 kPa). The calculation of the weight error coefficient takes into account the influence of each environmental parameter on water loss. For example, the temperature deviation can be given a weight of 0.5 (because temperature has the greatest influence on water evaporation), the humidity deviation can be given a weight of 0.3, and the air pressure deviation can be given a weight of 0.2. The comprehensive weight error coefficient is obtained by weighted calculation. After obtaining the weight error coefficient, it is corrected and calculated with the measured weight difference to obtain the target weight difference under the standard environment. The corrected target weight difference is matched with the pre-established standard weight library, which stores the standard weight differences corresponding to the target freshness scores under different freshness scores. These standard data are all measured under the standard environment. Through the numerical matching algorithm, the standard weight difference closest to the target weight difference is found, and the corresponding freshness score is used as the second freshness score.

[0050] Based on the above embodiment, as an optional implementation, in S103, determining the second freshness score of the target fresh food according to the weight difference and the second environmental feature of the current environment specifically includes S301-S303: S301, determining a weight error coefficient of a current environment relative to a standard environment according to a second environment characteristic.

[0051] S302, correcting the weight difference according to the weight error coefficient to obtain a target weight difference, wherein the weight error coefficient is a coefficient for correcting the deviation of the weight difference due to environmental influences.

[0052] S303, matching the target weight difference with the standard weight difference in a pre-stored standard weight library, and determining a second freshness score of the target fresh produce according to the matching result, wherein the standard weight library includes standard weight differences corresponding to the target fresh produce at different freshness scores.

[0053] Specifically, the weight change of fresh food during storage is significantly affected by environmental factors. In order to accurately assess the degree of water loss of fresh food, it is necessary to eliminate the impact of environmental factors on weight measurement.

[0054] First, the second environmental characteristics mainly include parameters such as ambient temperature, relative humidity and air pressure, which directly affect the evaporation rate of fresh water. The standard environment in this embodiment refers to an ideal storage environment with a temperature of 4°C, a relative humidity of 85% and an air pressure of 101.325 kPa. The current environmental parameters are collected in real time by environmental sensors and compared with the standard environmental parameters. When calculating the weight error coefficient, a weighted calculation method is adopted to take into account the different degrees of influence of different environmental parameters on water evaporation.

[0055] For example, when the current ambient temperature is 6°C, the temperature deviation is |(6-4)| / 4=0.5, and the weight is 0.5; when the current relative humidity is 80%, the humidity deviation is |(80-85)| / 85=0.059, and the weight is 0.3; when the current air pressure is 100kPa, the air pressure deviation is |(100-101.325)| / 101.325=0.013, and the weight is 0.2. Multiply each deviation by the corresponding weight and sum them to get the comprehensive weight error coefficient.

[0056] After obtaining the weight error coefficient, the measured weight difference needs to be corrected. For example, if the measured weight difference of a fresh product is 50g and the weight error coefficient is 0.25, the formula can be used to correct it: target weight difference = measured weight difference × (1 ± weight error coefficient). Whether to increase or decrease depends on the deviation direction of the current environmental parameters relative to the standard environment.

[0057] If the temperature of the current environment is higher than the standard environment and the humidity is lower than the standard environment, it means that the environment will accelerate the evaporation of water. At this time, the measured weight difference should be reduced, that is, the target weight difference = 50×(1-0.25) = 37.5g. The corrected target weight difference is closer to the actual water loss under the standard environment. Next, the corrected target weight difference is matched with the pre-established standard weight library, which stores the standard weight differences of the target fresh food at different freshness scoring stages. These standard data are measured under a standard environment. Through the numerical matching algorithm, find the standard weight difference closest to the target weight difference, and use its corresponding freshness score as the second freshness score. If the target weight difference falls exactly between the two standard values, the corresponding score can be calculated by linear interpolation.

[0058] S104: Determine an initial freshness level of the target fresh food by combining the first freshness score and the second freshness score.

[0059] In this embodiment, it is first necessary to determine the weight coefficients of the two scoring indicators. Different types of fresh produce may show different characteristic change rules during storage. For example, for leafy fresh produce, the surface morphology changes more obviously, while the water loss is relatively slow, so the first weight coefficient can be set to 0.7 and the second weight coefficient can be set to 0.3; for fruit fresh produce, the water loss and surface change are both more significant, so the first weight coefficient and the second weight coefficient can be set to 0.5.

[0060] After determining the weight coefficient, multiply the first freshness score by the first weight coefficient to obtain the first weighted score, and multiply the second freshness score by the second weight coefficient to obtain the second weighted score. Perform arithmetic addition on the two weighted scores to obtain the target score value. For example, when the first freshness score is 85 points and the second freshness score is 80 points, and the corresponding weight coefficients are 0.6 and 0.4 respectively, the final target score value is 85×0.6+80×0.4=83 points. According to the pre-set score range, the target score value is converted into the initial freshness grade. Specifically, 90 points and above can be divided into Grade A (very fresh), 80-90 points can be divided into Grade B (fresh), 70-80 points can be divided into Grade C (relatively fresh), 60-70 points can be divided into Grade D (slightly worse), and below 60 points can be divided into Grade E (poor).

[0061] Based on the above embodiment, as an optional implementation, in S104, combining the first freshness score and the second freshness score to determine the initial freshness level of the target fresh food specifically includes S401-S404: S401, obtaining a first weight coefficient corresponding to a first freshness score and a second weight coefficient corresponding to a second freshness score.

[0062] S402 arithmetically multiplies the first freshness score by the first weight coefficient to obtain a first weighted score, and arithmetically multiplies the second freshness score by the second weight coefficient to obtain a second weighted score.

[0063] S403: arithmetically add the first weighted score and the second weighted score to obtain a target score value.

[0064] S404: Determine the initial freshness level of the target fresh produce according to the target score value.

[0065] In one example, because the impact of surface characteristics and water loss characteristics of fresh produce on its freshness changes dynamically with changes in storage environment and time, a dynamic weighting system is required to comprehensively evaluate the freshness level of the fresh produce.

[0066] In this embodiment, the corresponding weight coefficient is first determined according to the fresh type and storage stage. For example, for leafy vegetables in the early stage of storage (0-24 hours), the change of surface characteristics is more significant, while the water loss is relatively small. At this time, the first weight coefficient (corresponding to the surface characteristic score) can be set to 0.7, and the second weight coefficient (corresponding to the weight characteristic score) can be set to 0.3; in the middle stage of storage (24-48 hours), the importance of the two characteristics is equal, and both weight coefficients can be set to 0.5; in the late stage of storage (more than 48 hours), water loss becomes the main influencing factor. At this time, the first weight coefficient can be set to 0.3 and the second weight coefficient can be set to 0.7. After obtaining the weight coefficient, the first freshness score is multiplied by the corresponding first weight coefficient to obtain the first weighted score.

[0067] For example, when the first freshness score is 85 points and the first weight coefficient is 0.7, the first weighted score is 85×0.7=59.5 points. Similarly, when the second freshness score is 80 points and the second weight coefficient is 0.3, the second weighted score is 80×0.3=24 points. Adding the two weighted scores, the final target score is 59.5+24=83.5 points. This weighted calculation method can dynamically adjust the contribution ratio of different features to the final score according to the importance of different features at different stages.

[0068] According to the calculated target score value, the initial freshness level of the target fresh food is determined by comparing it with the preset score range standard. Specifically, scores above 90 can be classified as A (excellent), 80-90 points as B (good), 70-80 points as C (average), 60-70 points as D (poor), and below 60 points as E (poor). In this example, the target score value is 83.5 points, and the corresponding initial freshness level is B. This dynamic weighted scoring method can more accurately reflect the actual quality status of fresh food at different storage stages, avoiding the one-sidedness that may be caused by a single scoring indicator.

[0069] S105, obtaining a target gas concentration within a preset range of the target freshness, adjusting the initial freshness level according to the target gas concentration, and generating a target freshness level of the target freshness.

[0070] Specifically, various volatile gases will be produced during the storage process of fresh produce. The changes in the concentration of these gases can directly reflect the degree of corruption and freshness of the fresh produce. Therefore, it is necessary to make further grade adjustments based on the initial freshness grade combined with the gas concentration data.

[0071] In this embodiment, a gas concentration sensor array is set within a preset range of the target fresh food (for example, within 10 cm from the surface of the fresh food) to detect the concentration of multiple target gases. The target gases include, but are not limited to, typical corruption-marking gases such as acetaldehyde, ethanol, and ammonia, and the concentrations of these gases show a significant correlation with the degree of corruption of the fresh food. The gas concentration sensor obtains real-time concentration data of various target gases by timed sampling (for example, sampling once every 5 minutes). The collected target gas concentration is compared with a pre-established gas concentration standard database, which stores the standard concentration ranges of various target gases at different freshness levels.

[0072] For example, for fresh leafy vegetables, when the detected ammonia concentration exceeds 5ppm and the ethanol concentration exceeds 10ppm, it indicates that the fresh produce has shown obvious signs of corruption. According to the exceeding of the target gas concentration, the grade adjustment rules are set: if the detected concentration of any target gas exceeds the upper limit of the standard range of the corresponding grade, the initial freshness grade will be lowered by one level; if the concentration of two or more gases is detected to be excessive, it will be lowered by two levels; if all gas concentrations are within the standard range, the initial grade will remain unchanged. At the same time, considering the different degrees of influence of different gases on the quality of fresh produce, the weighting coefficient of the gas concentration can be set, for example, the weighting coefficient of ammonia is 0.4, ethanol is 0.3, and acetaldehyde is 0.3. The comprehensive gas concentration evaluation index is obtained by weighted calculation, and the grade adjustment is triggered when the index exceeds the preset threshold. The final target freshness grade is a more accurate evaluation result after gas concentration correction.

[0073] Based on the above embodiment, as an optional implementation, in S105, adjusting the initial freshness level according to the target gas concentration to generate the target freshness level of the target freshness specifically includes S501-S503: S501, determining a preset gas concentration threshold according to the type of target fresh food, wherein the preset gas concentration threshold includes a plurality of concentration intervals, each concentration interval corresponding to a standard gas concentration of the target fresh food at a different freshness level.

[0074] S502: Determine a first freshness level of target fresh produce based on a preset gas concentration threshold and a target gas concentration.

[0075] S503: The initial freshness level is adjusted according to the first freshness level to generate a target freshness level of the target fresh food.

[0076] Specifically, fresh produce releases specific gases during storage, and changes in the concentration of these gases are closely related to the freshness of the produce. Therefore, using gas concentration as an adjustment factor can further improve the accuracy of freshness ratings.

[0077] Taking fresh fruits as an example, ethylene gas will be released during storage, and the change in its concentration can reflect the maturity and freshness of the fruit. In this embodiment, the corresponding preset gas concentration threshold is first determined according to the specific type of the target fresh fruit. For example, for apple fruits, the ethylene gas concentration can be divided into the following intervals: 0-0.5ppm corresponds to grade A (excellent), 0.5-1.0ppm corresponds to grade B (good), 1.0-1.5ppm corresponds to grade C (general), 1.5-2.0ppm corresponds to grade D (poor), and 2.0ppm and above corresponds to grade E (poor). When the target gas concentration is detected to be 0.8ppm, the first freshness level can be determined to be grade B by comparing with the preset gas concentration threshold. Next, the first freshness level obtained based on the gas concentration needs to be combined with the initial freshness level obtained based on the surface characteristics and weight characteristics to generate the final target freshness level.

[0078] The specific adjustment rules can be set as follows: when the two levels differ by one level, the lower level is taken as the final level; when the two levels differ by two levels or more, the middle level is taken as the final level. For example, if the initial freshness level is A, and the first freshness level based on gas concentration is B, the difference between the two is one level, and the final target freshness level should be adjusted to B.

[0079] This adjustment mechanism fully considers the impact of gas concentration, an important indicator, on the freshness of fresh produce. Through a comprehensive multi-dimensional evaluation, it can more accurately reflect the actual quality of fresh produce. At the same time, since changes in gas concentration often precede significant changes in surface characteristics and weight characteristics, this adjustment mechanism has a certain early warning effect and can detect the trend of declining fresh produce quality early. This gas concentration-based grade adjustment method not only improves the accuracy and reliability of freshness ratings, but also provides warehouse managers with a more comprehensive basis for quality monitoring, which helps to take corresponding storage adjustment measures in a timely manner and extend the shelf life of fresh produce.

[0080] After generating the target freshness level of the target fresh food, the method further includes: Obtain a change trend of a target freshness level of the target fresh food within a first preset time period; predict a predicted freshness level of the target fresh food after a second preset time period based on the change trend; generate warning information when the predicted freshness level is lower than a preset level threshold, wherein the warning information includes the current target freshness level of the target fresh food, the predicted freshness level and a suggested processing method.

[0081] In one example, in order to achieve forward-looking management of fresh produce quality and avoid economic losses caused by fresh produce deterioration, it is necessary to establish a fresh produce quality prediction mechanism based on historical data. In this embodiment, the system first records the target freshness level change data of the target fresh produce within a first preset time period (for example, the last 24 hours). Taking a batch of apples as an example, the system records the freshness level every 4 hours, and the following data is recorded in the last 24 hours: 0 hours (Grade A), 4 hours (Grade A), 8 hours (Grade A), 12 hours (Grade B), 16 hours (Grade B), 20 hours (Grade B), 24 hours (Grade B).

[0082] By analyzing these data points, it can be concluded that the batch of apples has experienced a downgrade from grade A to grade B in the last 24 hours, and the downgrade occurred in about 12 hours. Combined with the current storage environment data (such as the temperature is continuously at 6°C, 4°C higher than the standard storage temperature) and the characteristics of fresh produce itself, the grade change trend in the second preset time period (for example, the next 12 hours) can be predicted.

[0083] Based on a simple linear prediction method, considering the rate of change of one grade every 12 hours, it is predicted that the freshness grade of this batch of apples may drop to Grade C in the next 12 hours. Since the preset grade threshold of the system is Grade B, it is necessary to generate an early warning information. The early warning information contains three key elements: the current target freshness grade (Grade B), the predicted freshness grade (Grade C), and the recommended treatment method.

[0084] The recommended processing method is automatically generated based on pre-set processing rules. For example, for apples that are currently grade B and are predicted to drop to grade C, the system will give the following suggestions: "Current freshness level: Grade B; expected to drop to Grade C in 12 hours; it is recommended to adjust the storage temperature to 4°C and complete the sales processing within 8 hours."

[0085] The implementation of this predictive warning mechanism has significant effects: first, by regularly recording and analyzing the data on changes in freshness levels, trends in quality deterioration can be discovered in a timely manner; second, the warning information contains complete status information and specific processing suggestions, which facilitates managers to make quick decisions and actions; finally, the historical data recorded by the system can be used to optimize preset level thresholds and processing suggestions.

[0086] For example, after a fresh food supermarket adopted this system, the loss rate of fresh food was reduced from 8% to 3%, because the management staff could predict the risk of a significant decline in the quality of fresh food in advance, and thus take corresponding measures such as temperature adjustment or promotion. In addition, the prediction and early warning mechanism can also be linked with the inventory management system. When it is predicted that the quality of fresh food is about to decline, it automatically generates corresponding inventory adjustment suggestions to achieve efficient management of fresh food. This prediction and early warning method based on historical data not only improves the scientificity and foresight of fresh food management, but also significantly reduces fresh food losses and improves operating efficiency.

[0087] Based on the above method, the present application also discloses a freshness monitoring system, such as Figure 2 As shown, Figure 2 1 is a structural schematic diagram of a freshness monitoring system provided by an embodiment of the present application, and the system includes: an acquisition module, a first determination module, a second determination module, a combination module and an adjustment module; wherein the acquisition module is used to acquire a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference between a current weight of the target fresh food and an initial weight of the target fresh food; the first determination module is used to determine a first freshness score of the target fresh food according to a first environmental feature of the current environment and the surface image; the second determination module is used to determine a second freshness score of the target fresh food according to the weight difference and a second environmental feature of the current environment, wherein the current environment includes the first environmental feature and the second environmental feature; the combination module is used to determine an initial freshness level of the target fresh food by combining the first freshness score and the second freshness score; the adjustment module is used to acquire a target gas concentration within a preset range of the target fresh food, and adjust the initial freshness level according to the target gas concentration to generate a target freshness level of the target fresh food.

[0088] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0089] See also Figure 3 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0090] The communication bus 1002 is used to realize the connection and communication between these components.

[0091] The user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0092] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0093] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0094] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally also be at least one storage device located away from the aforementioned processor 1001. As Figure 3 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a method for monitoring the freshness of fresh produce.

[0095] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 1001 can be used to call an application program for a freshness monitoring method stored in the memory 1005. When executed by one or more processors, the electronic device executes one or more methods described in the above embodiments.

[0096] An electronic device readable storage medium stores instructions, which, when executed by one or more processors, enable the electronic device to execute one or more of the methods described in the above embodiments.

[0097] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0098] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0103] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for monitoring the freshness of fresh produce, characterized in that: The method comprises: Acquire a surface image of a target fresh food sent by a target sensor in a current environment, and a weight difference between a current weight of the target fresh food and an initial weight of the target fresh food; Determining a first freshness score of the target fresh food according to a first environmental feature of the current environment and the surface image; determining a second freshness score of the target fresh food according to the weight difference and a second environmental feature of the current environment, wherein the current environment includes the first environmental feature and the second environmental feature; Determine an initial freshness level of the target fresh food by combining the first freshness score and the second freshness score; A target gas concentration within a preset range of the target freshness is obtained, and the initial freshness level is adjusted according to the target gas concentration to generate a target freshness level of the target freshness.

2. The method for monitoring freshness of fresh produce according to claim 1, characterized in that: The determining, according to the first environmental feature of the current environment and the surface image, a first freshness score of the target fresh food includes: Determining, according to the first environmental feature, an environmental error coefficient of the current environment relative to the standard environment; Correcting the surface image according to the environmental error coefficient to obtain a target surface image, wherein the environmental error coefficient is used as a coefficient for correcting color parameters and brightness parameters of the surface image; The target surface image is matched with a standard surface image in a pre-stored standard image library, and a first freshness score of the target fresh food is determined according to the matching result, wherein the standard image library includes standard surface images corresponding to the target fresh food at different freshness scores.

3. The method for monitoring freshness of fresh produce according to claim 1, characterized in that: The determining, according to the weight difference and the second environmental characteristic of the current environment, a second freshness score of the target fresh food includes: Determining a weight error coefficient of the current environment relative to the standard environment according to the second environment characteristic; Correcting the weight difference according to the weight error coefficient to obtain a target weight difference, wherein the weight error coefficient is a coefficient for correcting a deviation of the weight difference due to environmental influences; The target weight difference is matched with the standard weight difference in a pre-stored standard weight library, and a second freshness score of the target fresh food is determined according to the matching result, wherein the standard weight library includes the standard weight difference corresponding to the target fresh food under different freshness scores.

4. The method for monitoring freshness of fresh produce according to claim 1, characterized in that: The combining the first freshness score and the second freshness score to determine the initial freshness level of the target fresh food includes: Obtaining a first weight coefficient corresponding to the first freshness score and a second weight coefficient corresponding to the second freshness score; arithmetically multiplying the first freshness score by the first weight coefficient to obtain a first weighted score, and arithmetically multiplying the second freshness score by the second weight coefficient to obtain a second weighted score; Adding the first weighted score and the second weighted score together to obtain a target score; According to the target scoring value, an initial freshness grade of the target fresh food is determined.

5. The method for monitoring freshness of fresh produce according to claim 1, characterized in that: The step of adjusting the initial freshness level according to the target gas concentration to generate the target freshness level of the target freshness includes: Determine a preset gas concentration threshold according to the type of the target fresh food, wherein the preset gas concentration threshold includes a plurality of concentration intervals, each of the concentration intervals corresponding to a standard gas concentration of the target fresh food at a different freshness level; Based on the preset gas concentration threshold, determining a first freshness level of the target fresh food according to the target gas concentration; The initial freshness level is adjusted according to the first freshness level to generate a target freshness level of the target fresh food.

6. The method for monitoring freshness of fresh produce according to claim 5, characterized in that: The step of adjusting the initial freshness level according to the first freshness level to generate the target freshness level of the target fresh food includes: Calculating a level difference between the initial freshness level and the first freshness level; Determining whether the level difference exceeds a level difference threshold; If the level difference does not exceed the level difference threshold, determining the initial freshness level as the target freshness level of the target fresh food; If the level difference exceeds the level difference threshold, the initial freshness level is adjusted according to the first freshness level to obtain the target freshness level of the target freshness, wherein when the first freshness level is higher than the initial freshness level, the initial freshness level is increased; when the first freshness level is lower than the initial freshness level, the initial freshness level is reduced.

7. The method for monitoring freshness of fresh produce according to claim 1, characterized in that: After generating the target freshness level of the target fresh food, the method further includes: Obtaining a change trend of a target freshness level of the target fresh food within a first preset time period; According to the change trend, predict the predicted freshness level of the target fresh food after a second preset time period; When the predicted freshness level is lower than a preset level threshold, a warning message is generated, wherein the warning message includes the current target freshness level of the target fresh food, the predicted freshness level, and a suggested processing method.

8. A fresh food freshness monitoring system, characterized in that: The system includes: an acquisition module, a first determination module, a second determination module, a combination module and an adjustment module; wherein, The acquisition module is used to acquire a surface image of the target fresh food sent by the target sensor in the current environment, and a weight difference between the current weight of the target fresh food and the initial weight of the target fresh food; The first determination module is used to determine a first freshness score of the target fresh food according to a first environmental feature of the current environment and the surface image; The second determination module is used to determine a second freshness score of the target fresh food according to the weight difference and a second environmental feature of the current environment, wherein the current environment includes the first environmental feature and the second environmental feature; The combining module is used to combine the first freshness score and the second freshness score to determine the initial freshness level of the target fresh food; The adjustment module is used to obtain a target gas concentration within a preset range of the target freshness, and adjust the initial freshness level according to the target gas concentration to generate a target freshness level of the target freshness.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 7.

Images