Intelligent warehouse-oriented goods warehouse-in and warehouse-out data real-time updating method
By analyzing the data propagation vector and anomaly perception factors in cold chain warehouses, and dynamically adjusting the data collection frequency and outbound strategies, the problem of inaccurate assessment of goods freshness in cold chain warehousing systems is solved, enabling real-time, refined monitoring of goods freshness and ensuring outbound delivery.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GUANGDONG VOCATIONAL COLLEGE OF SCI & TRADE
- Filing Date
- 2026-06-04
- Publication Date
- 2026-07-31
AI Technical Summary
Existing cold chain warehousing systems struggle to monitor the freshness of goods in real time and accurately assess it, resulting in a failure to promptly identify and address factors affecting the freshness of goods in cold chain warehouses.
By acquiring data from each sampling point at various collection times in the cold chain warehouse, analyzing propagation vectors and anomaly perception factors, and combining the value and shelf life of the goods, the data collection frequency and outbound strategy are dynamically adjusted to assess the freshness of the goods and formulate an outbound plan.
It enables real-time and refined monitoring of the freshness of goods in cold chain warehouses, improves the ability to detect events that affect the freshness of goods, ensures that goods are released from the warehouse in a suitable condition, and safeguards the freshness of goods in cold chain warehouses.
Smart Images
Figure CN122492098A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of warehouse management technology, and more specifically to a method for real-time updating of goods entry and exit data for intelligent warehousing. Background Technology
[0002] Cold chain warehousing typically involves deploying various sensor nodes within the warehouse to continuously collect environmental data. This ensures that goods remain within a suitable temperature range throughout their lifecycle, maintaining their freshness. Furthermore, because goods stored in cold chain warehouses (such as food and fresh agricultural products) are sensitive to environmental parameters like temperature and humidity, their freshness is directly affected by fluctuations in the storage environment. Therefore, it is necessary to continuously collect and analyze multi-dimensional environmental data (such as temperature, humidity, and airflow) from various locations within the warehouse. This allows for real-time monitoring of the warehouse's microenvironment, timely detection of local anomalies, and early warning of potential risks of goods deterioration.
[0003] Existing cold chain monitoring systems generally adopt a segmented data collection strategy with a fixed sampling frequency or triggered by a preset threshold. This means that data is collected at the same cycle whether the storage environment is stable or abnormal. This does not take into account the important impact of business attributes such as the freshness, near-expiration status, and value grade of goods on the collection frequency. It is difficult to capture factors that affect the freshness of goods in cold chain warehouses, such as abnormal temperature accumulation and insufficient local cooling capacity, in a timely manner. This makes it difficult to support real-time and refined monitoring, and thus cannot accurately assess the freshness of goods. Summary of the Invention
[0004] This invention provides a method for real-time updating of goods entry and exit data for smart warehousing, in order to solve the existing problem: traditional data updating methods are difficult to support real-time and refined monitoring, and therefore cannot accurately assess the freshness of goods.
[0005] The real-time update method for goods inbound and outbound data for intelligent warehousing of the present invention adopts the following technical solution: Includes the following steps: Acquire data from each sampling point at each time point in the cold chain warehouse, and obtain the value and shelf life of each item in the cold chain warehouse. Based on the amplitude of each dimension at different sampling points at each acquisition time and the spatial position between different sampling points, the propagation vector of each dimension at each sampling point at each acquisition time is obtained; based on the propagation vector of different dimensions at the same sampling point at the same acquisition time, the anomaly perception factor of each sampling point at each acquisition time is obtained; based on the anomaly perception factor of each sampling point at each acquisition time, the anomaly perception degree of each sampling point at each acquisition time is obtained; combined with the spatial distance between different sampling points, the anomaly coefficient at each acquisition time is obtained. Based on the anomaly coefficient at each collection time, combined with the value and shelf life of the goods, the collection interval correction weight at each collection time is obtained, and the subsequent collection time for each collection time is obtained; based on the spatial position of each sampling point and each goods at each collection time and the temperature value of each sampling point, the capture coefficient of each sampling point for each goods at each collection time is obtained, and combined with the distance between the sampling point and the goods, the temperature value of each goods at each collection time is obtained. The freshness of each item at each collection point is assessed based on its temperature value at each collection point, in order to formulate a goods release strategy.
[0006] Preferably, the specific method for obtaining the propagation vector of each dimension at each sampling point at each sampling time based on the amplitude of each dimension at different sampling points at each acquisition time and the spatial position between different sampling points includes: For the The dimension in the first At the data collection time, the first... From the sampling point to the... The sampling point will be the first sampling point. The sampling point points to the first The direction of the sampling point is used as the direction of the sampling point. The dimension in the first At the data collection time, the first... From the sampling point to the... The direction of the change vector of the nth sampling point; will the nth The dimension in the first At the data collection time, the first... The amplitude of the sampling point minus the first sampling point The difference between the amplitudes of the sampling points is compared to the previous sampling point. The sampling point and the first The ratio obtained from the spatial distance between the sampling points is used as the ratio of the sampling points. The dimension in the first At the data collection time, the first... From the sampling point to the... The magnitude of the change vector at the nth sampling point is obtained. The dimension in the first At the data collection time, the first... From the sampling point to the... The change vector of each sampling point; The first The dimension in the first At the data collection time, the first... The sum of the change vectors from the nth sampling point to all sampling points is used as the vector of the nth sampling point. The dimension in the first At the data collection time, the first... The propagation vector of each sampling point.
[0007] Preferably, the method for obtaining the anomaly perception factor of each sampling point at each acquisition time based on the propagation vectors of the same sampling point at the same acquisition time with different dimensions includes: In the formula, Indicates the first At the data collection time, the first... Anomaly sensing factor at each sampling point; Indicates the number of dimensions; Indicates the first The dimension in the first At the data collection time, the first... The propagation vector of each sampling point; Indicates the first The dimension in the first At the data collection time, the first... The propagation vector of each sampling point; This represents the cosine function; Represents the modulo function; This represents the function that takes the absolute value.
[0008] Preferably, the specific method for obtaining the degree of anomaly perception at each sampling point at each sampling time based on the anomaly perception factor at each sampling point at each continuous sampling time is as follows: For the At the data collection time, the first... The sampling point will be the first sampling point. At the data collection time, the first... The anomaly perception factor of the sampling point minus the first sampling point At the data collection time, the first... The difference obtained from the anomaly perception factor at the sampling point is compared with the previous point. The data collection time and the first The ratio obtained from the temporal distance between the acquisition times is used as the first... At the data collection time, the first... The rate of change of the abnormal sensing factors at each sampling point; Preset a local time range , will the Before the data collection time The data collection time, as the first... The local acquisition time of the acquisition moment, according to the first acquisition moment At each local acquisition time of the acquisition time, the first... The rate of change of the abnormal sensing factor at the sampling point, combined with the first sampling point At the data collection time, the first... The anomaly sensing factor of the sampling point, the first The temporal distance between the first acquisition time and its local acquisition time, and the first acquisition time The temporal distance between local acquisition times at the i-th acquisition time is used to obtain the i-th acquisition time. At the data collection time, the first... The degree of anomaly perception at each sampling point.
[0009] Preferably, the acquisition of the first At the data collection time, the first... The anomaly detection level for each sampling point includes the following specific methods: In the formula, Indicates the first At the data collection time, the first... The degree of anomaly detection at each sampling point; Indicates the first The number of local acquisition moments per acquisition moment; Indicates the first At the data collection time, the first... Anomaly sensing factor at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time Each local acquisition moment; Indicates the first The first data collection time Each local acquisition moment; Indicates the first Each data collection moment.
[0010] Preferably, the specific method for obtaining the anomaly coefficient at each acquisition time is as follows: For the The data collection time, according to the first collection time... The degree of anomaly perception at all sampling points at the sampling time, for the first... Sort all sampling points at the i-th acquisition time in descending order to obtain the i-th... The sampling point sequence at the acquisition time, based on the The spatial distance between sampling points in the sampling point sequence at the acquisition time, combined with the The anomaly perception level of each sampling point at the i-th acquisition time is obtained. The anomaly coefficient at each acquisition time is calculated using the following formula: In the formula, Indicates the first Anomaly coefficient at each acquisition time; Indicates the first The mean of the degree of abnormality perception at each sampling point at each collection time; Indicates the first The number of sampling points in the sampling point sequence at each acquisition time; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the sign-return function; This represents the normalization function.
[0011] Preferably, the specific method for obtaining the collection interval correction weight for each collection time based on the anomaly coefficient at each collection time, combined with the value and shelf life of the goods, and obtaining the subsequent collection times for each collection time is as follows: For the The first collection time will be the first... The cold chain warehouse with the shortest remaining shelf life at the time of data collection. The goods are designated as the target goods. For the preset quantity of goods to be inspected, the first... The average value of all goods at the first collection time and the value at the second collection time. The ratio of the average remaining shelf life of all target goods at the first collection time to the first multiplier of the second collection time. The product of the anomaly coefficients at the acquisition time is used as the . The acquisition interval correction coefficient for the acquisition time; for the acquisition time of the... The acquisition interval correction coefficient at the acquisition time is negatively correlated and normalized. The result of the negative correlation normalization is used as the first... Weighting adjustment for the acquisition interval at each acquisition time; Preset an initial data collection time interval For the first The data collection time, the first... The acquisition interval correction weight at each acquisition time and The product of , as the first The time interval between the first acquisition time and its next acquisition time is obtained. Each data collection moment.
[0012] Preferably, the method for obtaining the capture coefficient of each sampling point for each cargo at each sampling time based on the spatial location of each sampling point and each cargo at each sampling time, as well as the temperature value of each sampling point, includes the following specific methods: For the At the data collection time, the first... The sampling point and any goods will be the first sampling point. At the data collection time, the first... The vector pointing from the sampling point to the location of the goods is used as the first sampling point. At the data collection time, the first... The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo spatial vector .... At the data collection time, the first... The spatial distance between the sampling point and the cargo is recorded as the baseline distance, and the first sampling point is recorded as the baseline distance. The sampling point whose spatial distance from the cargo is less than the reference distance at the sampling time is denoted as the i-th sampling point. At the data collection time, the first... Reference sampling points for each sampling point; For the At the data collection time, the first... The sampling point and its i.e. The nth reference sampling point, the nth At the data collection time, the first... The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo At the data collection time, the first... The sampling point of the first sampling point The cosine similarity between the spatial vectors of the reference sampling points and the cargo is used as the first... At the data collection time, the first... The sampling point and its i.e. The collinearity of the reference sampling points with respect to the goods will be... At the data collection time, the first... The sampling point and its i.e. The collinearity of the reference sampling points for the goods is greater than that of the previous one. At the data collection time, the first... The sampling point and its i.e. The ratio of the absolute values of the temperature differences at each of the nth reference sampling points is used as the... At the data collection time, the first... The sampling point for its first sampling point Radiation levels at each reference sampling point; For the At the data collection time, the first... The sum of the radiance levels of each sampling point and all its reference sampling points is negatively correlated and normalized. The result of the negative correlation normalization is taken as the first... At the data collection time, the first... The capture coefficient of the cargo at each sampling point.
[0013] Preferably, the specific method for obtaining the temperature values of each item at each sampling time is as follows: For the At the data collection time, the first... The sampling point and any goods, for the first sampling point and any goods, At the data collection time, the first... The capture coefficient of the cargo at the sampling point is higher than that of the previous sampling point. At the data collection time, the first... The ratio of the spatial distance between each sampling point and the cargo is weighted and normalized, and the normalized result is used as the weighted ratio of the sampling points. At the data collection time, the first... Each sampling point has a capture weight for the cargo; According to the The capture weight of each sampling point for the cargo at the i-th collection time, for the i-th collection time. The temperature values of all sampling points at each sampling time are weighted and summed, and the result of the weighted sum is used as the first... The temperature value of the goods at each sampling time.
[0014] Preferably, the method for assessing the freshness of each item at each collection time based on its temperature value at each collection time to formulate an outbound strategy includes: For the For any item at the current collection time, according to the... The temperature of the goods at the first sampling time and at all previous sampling times was calculated using the temperature cumulative effect method. The freshness of the goods at each collection point; The system obtains the freshness of all goods in the cold chain warehouse at each data collection time, and prioritizes the goods with lower freshness when they are taken out of the warehouse.
[0015] The beneficial effects of the technical solution of the present invention are as follows: This application analyzes the data of each sampling point at each collection time in the cold chain warehouse in various dimensions to assess the possibility of events affecting the freshness of goods occurring in the cold chain warehouse. This is to capture the characteristics of changes in the local environment of the cold chain warehouse when events affecting the freshness of goods occur, which in turn show consistent changes in the data of each dimension at multiple sampling points. Furthermore, by analyzing the impact of events affecting the freshness of goods on the entire cold chain warehouse space over a continuous period of time, the anomaly coefficient at each collection time is obtained to assess the possibility of events affecting the freshness of goods occurring in the cold chain warehouse at each collection time.
[0016] The next sampling time is determined by combining the anomaly coefficient at each sampling moment with the value and shelf life of the goods. When the goods in the cold chain warehouse are valuable and have a short remaining shelf life, the storage risk in the cold chain warehouse is greater. In this case, the data update frequency in the cold chain warehouse should be increased, and the next sampling time should be determined by further combining the anomaly coefficient at each sampling moment. Since the data at different locations in the cold chain warehouse may vary, to accurately assess the freshness of each good in the cold chain warehouse, it is also necessary to obtain the temperature of each good at each sampling moment based on the spatial location of the goods in the cold chain warehouse and the spatial location of each sampling point. This will help assess the freshness of the goods. When goods are removed from the warehouse, those with lower freshness should be removed first to ensure the freshness of the goods in the cold chain warehouse. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the steps of the real-time update method for goods inbound and outbound data in intelligent warehousing according to the present invention. Detailed Implementation
[0019] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the real-time updating method for goods entering and leaving warehouses for intelligent warehousing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.
[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0021] The following description, in conjunction with the accompanying drawings, details the specific scheme of the real-time updating method for goods entering and leaving warehouses for intelligent warehousing provided by this invention.
[0022] Please see Figure 1 The diagram illustrates a flowchart of a method for real-time updating of goods inbound and outbound data for smart warehousing, according to an embodiment of the present invention. The method includes the following steps: Step S001: Obtain data for each dimension at each sampling point in the cold chain warehouse at each collection time, and obtain the value and shelf life of each item in the cold chain warehouse.
[0023] It should be noted that traditional cold chain warehouses often use a fixed frequency of data collection and update, which makes it difficult to provide sufficiently detailed monitoring data when the freshness of goods deteriorates rapidly. At the same time, it generates a large amount of redundant data when the condition of goods in the cold chain warehouse is stable. As a result, the data collection and update frequency of traditional cold chain warehouses is difficult to accurately assess the true freshness of goods, which is not conducive to ensuring the freshness of goods in cold chain warehouses. Therefore, this embodiment is a real-time data update method for goods entering and leaving the warehouse for intelligent warehousing. Specifically, it analyzes the data collected in the cold chain warehouse to assess the probability of events affecting the freshness of goods in the cold chain warehouse. Based on this, it adaptively generates the optimal data collection and update frequency for the cold chain warehouse, thereby accurately assessing the freshness of goods in the cold chain warehouse. When goods need to be released, goods with lower freshness are released first, thereby ensuring the freshness of goods in the cold chain warehouse.
[0024] Specifically, a preset initial data collection time interval is used. Starting time range and the number of sampling points The , as well as The specific value can be set according to the actual situation. This embodiment does not make a hard requirement. In this embodiment, it is used as... , , Taking cold chain storage warehouses as an example, the layout of the warehouses will be described. There are 10 sampling points, and several types of sensors are installed at each sampling point to collect data in various dimensions of each sampling point. The types of sensors include temperature sensors, humidity sensors, airflow sensors, etc. Make all sensors in each cold chain warehouse initially Every hour interval Data is collected every minute to obtain data of each dimension at each sampling point in the cold chain warehouse at several collection times within the initial collection time range.
[0025] Step S002: Based on the amplitude of each dimension at different sampling points at each acquisition time and the spatial position between different sampling points, obtain the propagation vector of each dimension at each sampling point at each acquisition time; based on the propagation vector of different dimensions at the same sampling point at the same acquisition time, obtain the anomaly perception factor of each sampling point at each acquisition time; based on the anomaly perception factor of each sampling point at each acquisition time, obtain the anomaly perception degree of each sampling point at each acquisition time; and based on the spatial distance between different sampling points, obtain the anomaly coefficient at each acquisition time.
[0026] It should be noted that this embodiment, as a real-time data update method for goods entering and leaving the warehouse for intelligent warehousing, specifically analyzes the data already collected in the cold chain warehouse to assess the probability of events affecting the freshness of goods occurring in the cold chain warehouse, thus adaptively generating the optimal data collection and update frequency for the cold chain warehouse. When an event affecting the freshness of goods occurs in the cold chain warehouse, the local environment of the cold chain warehouse changes, resulting in consistent changes in the data of multiple sampling points across various dimensions. Therefore, based on this, the anomaly perception factor of each sampling point at each collection time is obtained, and further combined with its temporal changes, the anomaly perception degree of each sampling point at each collection time is obtained. Furthermore, since the impact of events affecting the freshness of goods in the cold chain warehouse on the environment of the cold chain warehouse is not an instantaneous impact of a single sampling point at a single moment, but rather an impact on the entire cold chain warehouse space over a period of time, the anomaly coefficient of each collection time is obtained by analyzing the anomaly perception degree of all sampling points in the cold chain warehouse space over the complete time period. This coefficient is used to quantify the probability of events affecting the freshness of goods occurring in the cold chain warehouse at each collection time.
[0027] Preferably, in a specific embodiment of the present invention, for the first The dimension in the first At the data collection time, the first... From the sampling point to the... The sampling point will be the first sampling point. The sampling point points to the first The direction of the sampling point is used as the direction of the sampling point. The dimension in the first At the data collection time, the first... From the sampling point to the... The direction of the change vector of the nth sampling point; will the nth The dimension in the first At the data collection time, the first... The amplitude of the sampling point minus the first sampling point The difference between the amplitudes of the sampling points is compared to the previous sampling point. The sampling point and the first The ratio obtained from the spatial distance between the sampling points is used as the ratio of the sampling points. The dimension in the first At the data collection time, the first... From the sampling point to the... The magnitude of the change vector at the nth sampling point is obtained. The dimension in the first At the data collection time, the first... From the sampling point to the... The change vector of each sampling point; Furthermore, the first The dimension in the first At the data collection time, the first... The sum of the change vectors from the nth sampling point to all sampling points is used as the vector of the nth sampling point. The dimension in the first At the data collection time, the first... The propagation vector of each sampling point.
[0028] It should be noted that when events that may affect the freshness of goods occur in a cold chain warehouse (such as reduced refrigeration capacity, heat input, humidity accumulation, gas diffusion, etc.), the environmental state is not only manifested at a single point, but diffuses in space through heat conduction, convection, and water vapor mass transfer, causing the change directions of adjacent sampling points to tend to be consistent in multiple dimensions. Therefore, this embodiment constructs a propagation vector by the amplitude difference between sampling points in each dimension to represent the spatial gradient of environmental disturbance. When the local environment of the cold chain warehouse changes, the propagation vector will produce significant directionality and an increasing trend, which is used to subsequently assess the possibility of events affecting the freshness of goods occurring in the cold chain warehouse.
[0029] Preferably, in a specific embodiment of the present invention, for the first At the data collection time, the first... The sampling point, based on all dimensions at the nth sampling point. At the data collection time, the first... The propagation vector of the nth sampling point is obtained. At the data collection time, the first... The specific formula for calculating the anomaly perception factor of each sampling point is as follows: In the formula, Indicates the first At the data collection time, the first... Anomaly sensing factor at each sampling point; Indicates the number of dimensions; Indicates the first The dimension in the first At the data collection time, the first... The propagation vector of each sampling point; Indicates the first The dimension in the first At the data collection time, the first... The propagation vector of each sampling point; This represents the cosine function; Represents the modulo function; This represents the function that takes the absolute value.
[0030] It should be noted that when events affecting the freshness of goods occur in cold chain warehouses, the temperature, humidity, airflow, or gas indicators within the warehouse exhibit trend disturbances. The directions of change across multiple dimensions become synchronized, and the differences between propagation vectors increase. Therefore... The larger the value, the The smaller the value, the more likely an event affecting the freshness of goods is to occur in the cold chain warehouse.
[0031] Preferably, in a specific embodiment of the present invention, for the first At the data collection time, the first... The sampling point will be the first sampling point. At the data collection time, the first... The anomaly perception factor of the sampling point minus the first sampling point At the data collection time, the first... The difference obtained from the anomaly perception factor at the sampling point is compared with the previous point. The data collection time and the first The ratio obtained from the temporal distance between the acquisition times is used as the first... At the data collection time, the first... The rate of change of the abnormal sensing factors at each sampling point; Furthermore, a local time range is preset. The The specific value can be set according to the actual situation. This embodiment does not make a hard requirement. In this embodiment, it is used as... Taking the example of the first... Before the data collection time The data collection time, as the first... The local acquisition time of the acquisition moment (if the first acquisition moment) The number of collection times before the current collection time is less than [number] times. The first one, then the second one All acquisition times prior to the first acquisition time are considered as the first acquisition time. (Local acquisition time of the acquisition moment), according to the first acquisition moment At each local acquisition time of the acquisition time, the first... The rate of change of the abnormal sensing factor at the sampling point, combined with the first sampling point At the data collection time, the first... The anomaly sensing factor of the sampling point, the first The temporal distance between the first acquisition time and its local acquisition time, and the first acquisition time The temporal distance between local acquisition times at the i-th acquisition time is used to obtain the i-th acquisition time. At the data collection time, the first... The specific formula for calculating the anomaly perception level of each sampling point is as follows: In the formula, Indicates the first At the data collection time, the first... The degree of anomaly detection at each sampling point; Indicates the first The number of local acquisition moments per acquisition moment; Indicates the first At the data collection time, the first... Anomaly sensing factor at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time Each local acquisition moment; Indicates the first The first data collection time Each local acquisition moment; Indicates the first Each data collection moment.
[0032] It should be noted that the impact of events affecting the freshness of goods in cold chain warehouses on the environment is not an instantaneous effect at a single moment, but a continuous effect over a period of time. Therefore, to accurately perceive the persistence of environmental changes in cold chain warehouses, further analysis of the rate and trend of change of abnormal perception factors over this period is necessary. The higher the value, the more likely an event affecting the freshness of goods will occur in the cold chain warehouse. Further, combined with the... At the data collection time, the first... Anomaly perception factors for each sampling point are assigned a negative correlation weight based on temporal distance, which is used to accurately assess the likelihood of events affecting the freshness of goods occurring in cold chain warehouses at each sampling time.
[0033] Preferably, in a specific embodiment of the present invention, for the first The data collection time, according to the first collection time... The degree of anomaly perception at all sampling points at the sampling time, for the first... Sort all sampling points at the i-th acquisition time in descending order to obtain the i-th... The sampling point sequence at the acquisition time, based on the The spatial distance between sampling points in the sampling point sequence at the acquisition time, combined with the The anomaly perception level of each sampling point at the i-th acquisition time is obtained. The anomaly coefficient at each acquisition time is calculated using the following formula: In the formula, Indicates the first Anomaly coefficient at each acquisition time; Indicates the first The mean of the degree of abnormality perception at each sampling point at each collection time; Indicates the first The number of sampling points in the sampling point sequence at each acquisition time; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the sign-return function; This represents the normalization function, which is used for normalization processing in this embodiment.
[0034] It should be noted that when the perceived anomalies at different sampling points at the same collection time exhibit a spatially clustered distribution, it indicates the presence of risks such as hot spots, damp spots, or localized insufficient cooling in the cold chain warehouse. The impact of these risks can spread and amplify spatially. Therefore, this embodiment uses anomaly coefficients constructed by sorting the sampling points according to their anomaly severity and combining this with their spatial distance relationships to quantify whether the perceived anomalies at each sampling point at the same collection time exhibit regional concentration and expansion trends. The larger the value, the more concentrated and expanding the perceived abnormality of each sampling point is at that time. By further combining the abnormality perception level of each sampling point at that time, we can accurately quantify whether an event affecting the freshness of goods has occurred in the cold chain warehouse at that time.
[0035] Thus, the anomaly coefficient for each acquisition moment is obtained.
[0036] Step S003: Based on the anomaly coefficient at each collection time, combined with the value and shelf life of the goods, obtain the collection interval correction weight at each collection time, and obtain the subsequent collection time for each collection time; based on the spatial position of each sampling point and each goods at each collection time and the temperature value of each sampling point, obtain the capture coefficient of each sampling point for each goods at each collection time, and combined with the distance between the sampling point and the goods, obtain the temperature value of each goods at each collection time.
[0037] It should be noted that this embodiment, as a real-time data update method for goods entering and leaving the warehouse for intelligent warehousing, aims to accurately assess the freshness of goods in cold chain warehouses, thereby formulating outbound strategies to ensure the freshness of goods in cold chain warehouses. Therefore, when the goods in cold chain warehouses are valuable and have a short remaining shelf life, the data update frequency in cold chain warehouses should be increased. Furthermore, by combining the anomaly coefficient of the collection time obtained in step S002, a collection interval correction weight is formulated for each collection time, which is used to obtain the next collection time for each collection time. By using the temperature data at each collection time, the freshness of goods in cold chain warehouses can be accurately assessed, thereby formulating the optimal outbound strategy for cold chain warehouses to ensure the freshness of goods in cold chain warehouses.
[0038] Preferably, in a specific embodiment of the present invention, for the first The first collection time will be the first... The cold chain warehouse with the shortest remaining shelf life at the time of data collection. The goods are designated as the target goods. This is the preset quantity of goods to be inspected for quality assurance. The specific value can be set according to the actual situation. This embodiment does not make a hard requirement. In this embodiment, it is used as... Taking the example of the first... The average value of all goods at the first collection time and the value at the second collection time. The ratio of the average remaining shelf life of all target goods at the first collection time to the first multiplier of the second collection time. The product of the anomaly coefficients at the acquisition time is used as the . The acquisition interval correction coefficient for the acquisition time; for the acquisition time of the... The acquisition interval correction coefficient at each acquisition time is negatively correlated and normalized (using...). The function is normalized for negative correlation, where It is an exponential function with the natural constant as its base. As input to the model, the implementer can set a negative correlation normalization function according to the actual situation, and use the result of the negative correlation normalization as the first... The weighting of the acquisition interval at each acquisition time.
[0039] Furthermore, regarding the first The data collection time, the first... The acquisition interval correction weight at each acquisition time and The product (the product of the ... (The preset initial acquisition time interval) is used as the first... The time interval between the first acquisition time and its next acquisition time is obtained. Each data collection moment; By doing so, the subsequent acquisition times for each acquisition time can be obtained.
[0040] It should be noted that the storage risk is higher when goods in cold chain warehouses are valuable and have short remaining shelf lives. In such cases, the data update frequency should be increased to accurately assess the freshness of the goods. Furthermore, by combining the anomaly coefficients at each sampling time, a sampling interval correction weight can be obtained for each sampling time, thus determining the next sampling time for each sampling time. Also, since data from different locations within the cold chain warehouse may vary, to accurately assess the freshness of each item, it is necessary to further obtain the temperature of each item at each sampling time based on the spatial location of the goods and the spatial location of each sampling point, which is then used to evaluate the freshness of the goods.
[0041] Preferably, in a specific embodiment of the present invention, for the first At the data collection time, the first... The sampling point and any goods will be the first sampling point. At the data collection time, the first... The vector pointing from the sampling point to the location of the goods is used as the first sampling point. At the data collection time, the first... The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo spatial vector .... At the data collection time, the first... The spatial distance between the sampling point and the cargo is recorded as the baseline distance, and the first sampling point is recorded as the baseline distance. The sampling point whose spatial distance from the cargo is less than the reference distance at the sampling time is denoted as the i-th sampling point. At the data collection time, the first... Reference sampling points for each sampling point; Furthermore, regarding the first At the data collection time, the first... The sampling point and its i.e. The nth reference sampling point, the nth At the data collection time, the first... The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo At the data collection time, the first... The sampling point of the first sampling point The cosine similarity between the spatial vectors of the reference sampling points and the cargo is used as the first... At the data collection time, the first... The sampling point and its i.e. The collinearity of the reference sampling points with respect to the goods will be... At the data collection time, the first... The sampling point and its i.e. The collinearity of the reference sampling points for the goods is greater than that of the previous one. At the data collection time, the first... The sampling point and its i.e. The ratio of the absolute values of the temperature differences at each of the nth reference sampling points is used as the... At the data collection time, the first... The sampling point for its first sampling point Radiation levels at each reference sampling point; For the At the data collection time, the first... The sum of the radiance levels of each sampling point with respect to all its reference sampling points is negatively correlated and normalized (using...). The function is normalized for negative correlation, where It is an exponential function with the natural constant as its base. As input to the model, the implementer can set a negative correlation normalization function according to the actual situation, and use the result of the negative correlation normalization as the first... At the data collection time, the first... The capture coefficient of the cargo at each sampling point.
[0042] It should be noted that the greater the cosine similarity between the spatial vectors from the sampling point and its reference sampling point to the cargo at the same collection time, the closer the cargo position and the structure between the sampling point and its reference sampling point are to a collinear structure. In this case, the sampling point and its reference sampling point share a more consistent heat transfer direction and environmental influence path. If the temperature difference between the sampling point and its reference sampling point is smaller at this time, it indicates uneven heat diffusion or the existence of local disturbances. The ability of the sampling point to represent the cargo temperature is reduced, that is, the temperature of the sampling point is less representative of the true temperature of the cargo. Furthermore, by combining the distance between the sampling point and the cargo, the capture weight of the sampling point on the cargo is obtained, which is used to evaluate the temperature value of the cargo, thereby assessing the freshness of the cargo in the subsequent process and formulating a cargo release strategy.
[0043] Preferably, in a specific embodiment of the present invention, for the first At the data collection time, the first... The sampling point and any goods, for the first sampling point and any goods, At the data collection time, the first... The capture coefficient of the cargo at the sampling point is higher than that of the previous sampling point. At the data collection time, the first... The ratio of the spatial distance between each sampling point and the cargo is weighted and normalized (the specific normalization range is the first sampling point). The capture coefficients of all sampling points for the cargo at the first sampling time and the first sampling time are related to the capture coefficients of all sampling points for the cargo at the second sampling time. The spatial distance between all sampling points and the cargo at the current sampling time (the spatial distance between all sampling points and the cargo at the current sampling time) is used as the normalized result as the first... At the data collection time, the first... Each sampling point has a capture weight for the cargo; Furthermore, according to Article The capture weight of each sampling point for the cargo at the i-th collection time, for the i-th collection time. The temperature values of all sampling points at each sampling time are weighted and summed, and the result of the weighted sum is used as the first... The temperature value of the goods at each sampling time.
[0044] It should be noted that the smaller the capture coefficient of the sampling point for the goods, the less the temperature of the sampling point can represent the true temperature of the goods. Since the heat propagation decreases with distance, the capture weight of the sampling point for the goods is obtained by further combining the distance between the goods and the sampling point, so as to accurately evaluate the temperature value of the sampling point and thus evaluate the freshness of the goods in the subsequent assessment.
[0045] At this point, the temperature value of each item at each sampling time is obtained.
[0046] Step S004: Evaluate the freshness of each item at each collection time based on the temperature value of each item at each collection time, in order to formulate an outbound strategy for the goods.
[0047] It should be noted that after obtaining the temperature value of each item at each sampling time through step S003, the freshness of each item at each sampling time can be evaluated based on the temperature value of each item at each sampling time. When the goods need to be shipped out, the goods with lower freshness are shipped out first to ensure the freshness of the goods in the cold chain warehouse.
[0048] Specifically, for the first For any item at the current collection time, according to the... The temperature of the goods at the first sampling time and at all previous sampling times was calculated using the temperature cumulative effect method. The freshness of the goods at each collection time point will not be described in detail in this embodiment, as the temperature cumulative effect method is a well-known prior art. Furthermore, the freshness of all goods in the cold chain warehouse is obtained at each collection time. When goods are shipped out, the goods with lower freshness are shipped out first to ensure the freshness of goods in the cold chain warehouse.
[0049] It should be noted that, in order to avoid the denominator being 0 during the fraction operation process in this embodiment, 0.01 is added to the denominator during the fraction operation process in this example.
[0050] This concludes the embodiment.
[0051] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A method for real-time updating of goods warehouse-in and warehouse-out data for intelligent warehousing, characterized in that, The method includes the following steps: Acquire data from each sampling point at each time point in the cold chain warehouse, and obtain the value and shelf life of each item in the cold chain warehouse. Based on the amplitude of each dimension at different sampling points at each acquisition time and the spatial position between different sampling points, the propagation vector of each dimension at each sampling point at each acquisition time is obtained; based on the propagation vector of different dimensions at the same sampling point at the same acquisition time, the anomaly perception factor of each sampling point at each acquisition time is obtained; based on the anomaly perception factor of each sampling point at each acquisition time, the anomaly perception degree of each sampling point at each acquisition time is obtained; combined with the spatial distance between different sampling points, the anomaly coefficient at each acquisition time is obtained. Based on the anomaly coefficient at each collection time, combined with the value and shelf life of the goods, the collection interval correction weight at each collection time is obtained, and the subsequent collection time for each collection time is obtained; based on the spatial position of each sampling point and each goods at each collection time and the temperature value of each sampling point, the capture coefficient of each sampling point for each goods at each collection time is obtained, and combined with the distance between the sampling point and the goods, the temperature value of each goods at each collection time is obtained. The freshness of each item at each collection point is assessed based on its temperature value at each collection point, in order to formulate a goods release strategy. 2.The method of claim 1, wherein, The method for obtaining the propagation vector of each dimension at each sampling point at each acquisition time by combining the amplitude of each dimension at different sampling points at each acquisition time with the spatial position between different sampling points includes the following specific methods: For the The dimension in the first At the first collection time, the first From the sampling point to the... The sampling point will be the first sampling point. The sampling point points to the first The direction of the sampling point is used as the first... The dimension in the first At the first collection time, the first From the sampling point to the... The direction of the change vector of the nth sampling point; will the nth The dimension in the first At the first collection time, the first The amplitude of the sampling point minus the first sampling point The difference between the amplitudes of the sampling points is compared to the previous sampling point. The sampling point and the first The ratio obtained from the spatial distance between the sampling points is used as the ratio of the sampling points. The dimension in the first At the first collection time, the first From the sampling point to the... The magnitude of the change vector at the nth sampling point is obtained. The dimension in the first At the first collection time, the first From the sampling point to the... The change vector of each sampling point; The first The dimension in the first At the first collection time, the first The sum of the change vectors from the nth sampling point to all sampling points is used as the vector of the nth sampling point. The dimension in the first At the first collection time, the first The propagation vector of each sampling point.
3. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The specific method for obtaining the anomaly perception factor of each sampling point at each acquisition time based on the propagation vector of the same sampling point at the same acquisition time with different dimensions includes: In the formula, Indicates the first At the first collection time, the first Anomaly sensing factor at each sampling point; Indicates the number of dimensions; Indicates the first The dimension in the first At the first collection time, the first The propagation vector of each sampling point; Indicates the first The dimension in the first At the first collection time, the first The propagation vector of each sampling point; This represents the cosine function; Represents the modulo function; This represents the function that takes the absolute value.
4. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The specific method for obtaining the degree of anomaly perception at each sampling point at each sampling time based on the anomaly perception factor at each sampling point during continuous acquisition includes: For the At the first collection time, the first The sampling point will be the first sampling point. At the first collection time, the first The anomaly perception factor of the sampling point minus the first sampling point At the first collection time, the first The difference obtained from the anomaly perception factor at the sampling point is compared with the previous point. The data collection time and the first The ratio obtained from the temporal distance between the acquisition times is used as the first... At the first collection time, the first The rate of change of the abnormal sensing factors at each sampling point; Preset a local time range , will the Before the data collection time The data collection time, as the first... The local acquisition time of the acquisition moment, according to the first acquisition moment At each local acquisition time of the acquisition time, the first... The rate of change of the abnormal sensing factor at the sampling point, combined with the first sampling point At the first collection time, the first The anomaly sensing factor of the sampling point, the first The temporal distance between the first acquisition time and its local acquisition time, and the first acquisition time The temporal distance between local acquisition times at the i-th acquisition time is used to obtain the i-th acquisition time. At the first collection time, the first The degree of anomaly perception at each sampling point.
5. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 4, characterized in that, The acquisition of the first At the first collection time, the first The degree of anomaly detection for each sampling point includes the following specific methods: In the formula, Indicates the first At the first collection time, the first The degree of anomaly detection at each sampling point; Indicates the first The number of local acquisition moments per acquisition moment; Indicates the first At the first collection time, the first Anomaly sensing factor at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time At the local acquisition time, the first The rate of change of the abnormal sensing factors at each sampling point; Indicates the first The first data collection time Each local acquisition moment; Indicates the first The first data collection time Each local acquisition moment; Indicates the first Each data collection moment.
6. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The specific method for obtaining the anomaly coefficient at each acquisition time is as follows: For the The data collection time, according to the first collection time. The degree of anomaly perception at all sampling points at the sampling time, for the first... Sort all sampling points at the i-th acquisition time in descending order to obtain the i-th... The sampling point sequence at the i-th acquisition time, based on the i-th acquisition time... The spatial distance between sampling points in the sampling point sequence at the acquisition time, combined with the The anomaly perception level of each sampling point at the i-th acquisition time is obtained. The anomaly coefficient at each acquisition time is calculated using the following formula: In the formula, Indicates the first Anomaly coefficient at each acquisition time; Indicates the first The mean of the degree of abnormality perception at each sampling point at each collection time; Indicates the first The number of sampling points in the sampling point sequence at each acquisition time; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the first The first sampling point in the sampling point sequence at the sampling time of the sampling moment is related to the first sampling point. Spatial distance between sampling points; Indicates the sign-return function; This represents the normalization function.
7. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The specific method for obtaining the collection interval correction weight for each collection time based on the anomaly coefficient at each collection time, combined with the value and shelf life of the goods, and obtaining the subsequent collection times for each collection time includes: For the The first collection time will be the first... The cold chain warehouse with the shortest remaining shelf life at the time of data collection. The goods are designated as the target goods. For the preset quantity of goods to be inspected, the first... The average value of all goods at the first collection time and the value at the second collection time. The ratio of the average remaining shelf life of all target goods at the first collection time to the first multiplier of the second collection time. The product of the anomaly coefficients at the acquisition time is used as the . The acquisition interval correction coefficient for the acquisition time; for the acquisition time of the... The acquisition interval correction coefficient at the acquisition time is negatively correlated and normalized. The result of the negative correlation normalization is used as the first... Weighting of the acquisition interval at each acquisition moment; Preset an initial data collection time interval For the first The data collection time, the first... The acquisition interval correction weight at each acquisition time and The product of , as the first The time interval between the first acquisition time and its next acquisition time is obtained. Each data collection moment.
8. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The method for obtaining the capture coefficient of each sampling point for each cargo at each sampling time based on the spatial location of each sampling point and each cargo at each sampling time, as well as the temperature value of each sampling point, includes the following specific methods: For the At the first collection time, the first The sampling point and any goods will be the first sampling point. At the first collection time, the first The vector pointing from the sampling point to the location of the goods is used as the first sampling point. At the first collection time, the first The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo spatial vector .... At the first collection time, the first The spatial distance between the sampling point and the cargo is recorded as the baseline distance, and the first sampling point is recorded as the baseline distance. The sampling point whose spatial distance from the cargo is less than the reference distance at the sampling time is denoted as the i-th sampling point. At the first collection time, the first Reference sampling points for each sampling point; For the At the first collection time, the first The sampling point and its i.e. The nth reference sampling point, the nth At the first collection time, the first The spatial vector from the sampling point to the cargo, and the first sampling point to the cargo At the first collection time, the first The sampling point of the first sampling point The cosine similarity between the spatial vectors of the reference sampling points and the cargo is used as the first... At the first collection time, the first The sampling point and its i.e. The collinearity of the reference sampling points with respect to the goods will be... At the first collection time, the first The sampling point and its i.e. The collinearity of the reference sampling points for the goods is greater than that of the previous one. At the first collection time, the first The sampling point and its i.e. The ratio of the absolute values of the temperature differences at each of the nth reference sampling points is used as the... At the first collection time, the first The sampling point for its first sampling point Radiation levels at each reference sampling point; For the At the first collection time, the first The sum of the radiance levels of each sampling point and all its reference sampling points is negatively correlated and normalized. The result of the negative correlation normalization is taken as the first... At the first collection time, the first The capture coefficient of the cargo at each sampling point.
9. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The specific method for obtaining the temperature values of each item at each collection time is as follows: For the At the first collection time, the first The sampling point and any goods, for the first sampling point and any goods, At the first collection time, the first The capture coefficient of the cargo at the sampling point is higher than that of the previous sampling point. At the first collection time, the first The ratio of the spatial distance between each sampling point and the cargo is weighted and normalized, and the normalized result is used as the weighted ratio of the sampling points. At the first collection time, the first Each sampling point has a capture weight for the cargo; According to the The capture weight of each sampling point for the cargo at the i-th collection time, for the i-th collection time. The temperature values of all sampling points at each sampling time are weighted and summed, and the result of the weighted sum is used as the first... The temperature value of the goods at each sampling time.
10. The method for real-time updating of goods inbound and outbound data for intelligent warehousing according to claim 1, characterized in that, The method for assessing the freshness of each item at each collection time based on its temperature value at each collection time, in order to formulate an outbound strategy, includes the following specific methods: For the For any item at the current collection time, according to the... The temperature of the goods at the first sampling time and at all previous sampling times was calculated using the temperature cumulative effect method. The freshness of the goods at each collection point; The system obtains the freshness of all goods in the cold chain warehouse at each data collection time, and prioritizes the goods with lower freshness when they are taken out of the warehouse.