A Warehouse Intelligent Application Management System Based on Blockchain Technology

Abstract

The present invention relates to the technical field of electrical digital data processing, and specifically relates to a warehousing intelligent application management system based on blockchain technology. The system includes a memory and a processor, and the processor executes a computer program stored in the memory to implement the following steps: determining a first correlation factor and a second correlation factor of the ambient temperature and the warehousing quantity in each warehousing area of the warehousing space, and further determining the degree of correlation; determining each correction coefficient according to the difference between the degree of correlation, the predicted value of the warehousing quantity and the warehousing quantity corresponding to the clustering center, using each correction coefficient to correct the initial membership degree, obtaining each preferred membership degree, and further determining the current adjusted temperature. By determining the correction coefficient to correct each initial membership degree, the clustering accuracy when clustering the monitoring data of the warehousing space is effectively improved, the effect of temperature adjustment in the warehousing space is further enhanced, and the stability of the temperature change in the warehousing space is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to a warehousing intelligent application management system based on blockchain technology. Background Art

[0002] When performing warehousing intelligent application management, in order to ensure the storage safety of items in the warehousing space, it is necessary to monitor the temperature of the warehousing space in real time. Blockchain technology ensures the security of data through encryption algorithms. Each block contains the hash value of the previous block, forming an immutable chain structure, which can effectively prevent data from being illegally modified or deleted. Using blockchain technology, the temperature data in the warehousing environment can be recorded in real time, accurately, and immutably, and then the temperature of the warehousing space can be accurately controlled. Currently, the monitored data is usually clustered, and then the temperature of the warehousing space is adjusted based on the clustering result. Among them, the clustering method can be FCM (Fuzzy C-means), and the monitored data can include the ambient temperature and the adjusted temperature.

[0003] When using FCM to cluster the monitored data, only the existing data is analyzed. Due to environmental changes, the accurate temperature change trend may not be obtained, resulting in a low accuracy of the final clustering result. The temperature adjustment based on this clustering result has a large span, resulting in unstable changes in the warehousing temperature, affecting the warehousing storage effect, and being unfavorable for warehousing intelligent application management. Summary of the Invention

[0004] In order to solve the technical problem of the low clustering accuracy of the above-mentioned existing clustering method when clustering the monitored data of the warehousing space, resulting in a poor temperature adjustment effect based on the clustering result, the purpose of the present invention is to provide a warehousing intelligent application management system based on blockchain technology, and the specific technical solution adopted is as follows:

[0005] An embodiment of the present invention provides a warehousing intelligent application management system based on blockchain technology, including a memory and a processor. The processor executes the computer program stored in the memory to implement the following steps:

[0006] Real-time obtain the monitored data sequence of each type in the warehousing space. On a three-dimensional coordinate system, cluster the data points formed by the monitored data of each type at the same acquisition moment to obtain the initial membership degree of the ambient temperature of the current warehousing space relative to each clustering cluster; the monitored data in each type of monitored data sequence is the average value of the ambient temperature in all warehousing areas, the cumulative value of the warehousing quantity, and the average value of the adjusted temperature;

[0007] For each storage area in the storage space, according to the environmental temperature sequence and storage volume sequence of the storage area, analyze the stability of the environmental temperature change of similar storage volumes in the same period and the proportional relationship between the environmental temperature and the corresponding storage volume in different periods, and determine the first correlation factor between the environmental temperature and the storage volume in the storage area;

[0008] According to the environmental temperature sequences and storage volume sequences of the storage area and its respective comparison areas, analyze the influence of the environmental temperature in all comparison areas on the environmental temperature in the storage area, and determine the second correlation factor between the environmental temperature and the storage volume in the storage area; the comparison areas are other storage areas except the current storage area itself;

[0009] Determine the correlation degree between the environmental temperature and the storage volume in each storage area according to the first correlation factor and the second correlation factor; according to the correlation degree and the difference between the predicted storage volume of each storage area and the storage volume of the storage area corresponding to the cluster center of each cluster, determine the correction coefficient of each cluster;

[0010] Use the correction coefficients of each cluster to correct the initial membership degree of the environmental temperature of the current storage space with respect to each cluster, obtain the preferred membership degree of the environmental temperature of the current storage space with respect to each cluster, and then determine the adjusted temperature of the current storage space.

[0011] Further, the step of analyzing the stability of the environmental temperature change of similar storage volumes in the same period and the proportional relationship between the environmental temperature and the corresponding storage volume in different periods according to the environmental temperature sequence and storage volume sequence of the storage area, and determining the first correlation factor between the environmental temperature and the storage volume in the storage area includes:

[0012] For the storage area, form a temperature subsequence with the environmental temperatures on the same day in the environmental temperature sequence; cluster the data points composed of the environmental temperature and the acquisition time of each temperature subsequence to obtain the clustering result corresponding to each temperature subsequence; use the time division method corresponding to the clustering result with the highest occurrence frequency to divide each temperature subsequence into time periods, and obtain each time period in each temperature subsequence;

[0013] Form a storage volume subsequence with the storage volumes on the same day in the storage volume sequence, and the storage volumes in the same storage volume subsequence are equal; cluster the data points composed of the storage volume and the acquisition time of the storage volume sequence to obtain each storage volume cluster; determine the acquisition time of each storage volume subsequence corresponding to each storage volume cluster;

[0014] According to the environmental temperatures in each time period in the temperature subsequence at the acquisition time of each storage volume subsequence corresponding to each storage volume cluster, determine the temperature change stability index corresponding to the storage area;

[0015] Determine the storage temperature - related index corresponding to the storage area according to the storage quantity in each storage quantum sequence and the average ambient temperature of each period in the temperature sub - sequence at the collection time of each storage quantum sequence.

[0016] Take the product of the temperature change stability index corresponding to the storage area and the storage temperature - related index as the first correlation factor of the ambient temperature and the storage quantity in the storage area.

[0017] Further, the method for determining the temperature change stability index corresponding to the storage area according to the ambient temperatures of each period in the temperature sub - sequences at the collection times of each storage quantum sequence corresponding to each storage quantity clustering cluster includes:

[0018] In the formula, Ces a is the temperature change stability index corresponding to the a - th storage area, D is the number of periods, d is the serial number of the period, L is the number of storage quantity clustering clusters, e is the serial number of the storage quantity clustering cluster, exp is the exponential function with the natural constant as the base, η is the number of storage quantum sequences corresponding to the storage quantity clustering cluster, δ is the serial number of the storage quantum sequence corresponding to the storage quantity clustering cluster, fcn (a,e,δ,d) is the average ambient temperature of the d - th period in the temperature sub - sequence at the collection time of the δ - th storage quantum sequence corresponding to the e - th storage quantity clustering cluster of the a - th storage area, is the average value of the average ambient temperatures of the d - th period in the temperature sub - sequences at the collection times of all storage quantum sequences corresponding to the e - th storage quantity clustering cluster of the a - th storage area, and || is the absolute - value symbol.

[0019] Further, the method for determining the storage temperature - related index corresponding to the storage area according to the storage quantity in each storage quantum sequence and the average ambient temperature of each period in the temperature sub - sequence at the collection time of each storage quantum sequence includes:

[0020] In the formula, Tes a is the storage temperature - related index corresponding to the a - th storage area, exp is the exponential function with the natural constant as the base, D is the number of periods, d is the serial number of the period, n is the serial number of the storage quantum sequence, N is the number of storage quantum sequences, Tcn (a,n,d) is the ratio of the storage quantity of the n - th storage quantum sequence of the a - th storage area to the average ambient temperature of the d - th period in the temperature sub - sequence at the collection time of the n - th storage quantum sequence, || is the absolute - value symbol.

[0021] Further, analyzing the influence of the ambient temperature in all comparison regions on the ambient temperature in the storage region according to the ambient temperature sequences and storage quantity sequences of the storage region and its respective comparison regions, and determining the second correlation factor between the ambient temperature and the storage quantity in the storage region, including:

[0022] For each comparison region, determining each ambient temperature at each time period in each temperature subsequence in the ambient temperature sequence of each comparison region, and determining the acquisition time of each storage quantity subsequence corresponding to each storage quantity clustering cluster in each comparison region and the acquisition time of each temperature subsequence.

[0023] According to each ambient temperature at each time period in each temperature subsequence at the acquisition time of each storage quantity subsequence corresponding to each storage quantity clustering cluster of the storage region and its respective comparison regions, determining the second correlation factor between the ambient temperature and the storage quantity in the storage region.

[0024] Further, the determining the second correlation factor between the ambient temperature and the storage quantity in the storage region according to each ambient temperature at each time period in each temperature subsequence at the acquisition time of each storage quantity subsequence corresponding to each storage quantity clustering cluster of the storage region and its respective comparison regions, includes:

[0025] In the formula, Hbc a is the second correlation factor between the ambient temperature and the storage quantity in the a-th storage region, exp is the exponential function with the natural constant as the base, B is the number of comparison regions, b is the serial number of the comparison region, L is the number of storage quantity clustering clusters, e is the serial number of the storage quantity clustering cluster, D is the number of time periods, d is the serial number of the time period, η represents the number of storage quantity subsequences, fcn (a,e,δ,d) is the average value of the ambient temperature at the d-th time period in the temperature subsequence at the acquisition time of the δ-th storage quantity subsequence corresponding to the e-th storage quantity clustering cluster in the a-th storage region, is the average value of the average values of the ambient temperatures at the d-th time period in the temperature subsequences at the acquisition times of all storage quantity subsequences corresponding to the e-th storage quantity clustering cluster in the a-th storage region, || is the absolute value symbol, fcn (a,b,e,δ,d) is the average value of the ambient temperature at the d-th time period in the temperature subsequence at the acquisition time of the δ-th storage quantity subsequence corresponding to the e-th storage quantity clustering cluster in the b-th comparison region of the a-th storage region.

[0026] Further, the determining the correlation degree between the ambient temperature and the storage quantity in each storage region according to the first correlation factor and the second correlation factor, includes:

[0027] For any storage area, the product of the first correlation factor and the second correlation factor of the ambient temperature and the storage volume in the storage area is used as the correlation degree between the ambient temperature and the storage volume in the storage area.

[0028] Further, determining the correction coefficient of each clustering cluster according to the difference between the correlation degree, the predicted value of the storage volume of each storage area and the storage volume of the storage area corresponding to the clustering center of each clustering cluster includes:

[0029] For each storage area in the storage space, the correlation degree between the ambient temperature and the storage volume in the storage area is used as the numerator of the ratio, the difference between the predicted value of the storage volume of the storage area and the storage volume of the storage area corresponding to the clustering center of any clustering cluster is used as the denominator of the ratio, and the cumulative value of all ratios corresponding to all storage areas is used as the correction coefficient of the clustering cluster, thereby obtaining the correction coefficients of each clustering cluster.

[0030] Further, using the correction coefficients of each clustering cluster to correct the initial membership degree of the ambient temperature of the current storage space with respect to each clustering cluster to obtain the preferred membership degree of the ambient temperature of the current storage space with respect to each clustering cluster includes:

[0031] For any clustering cluster with respect to the ambient temperature of the current storage space, calculate the product of the correction coefficient of the clustering cluster and the initial membership degree of the ambient temperature of the current storage space with respect to the clustering cluster as the corrected value of the initial membership degree of the clustering cluster, and use the value obtained by adding the corrected value of the initial membership degree of the clustering cluster to the initial membership degree as the preferred membership degree of the clustering cluster.

[0032] Further, determining the adjustment temperature of the current storage space includes:

[0033] According to the preferred membership degrees of the ambient temperature of the current storage space with respect to each clustering cluster, select the largest preferred membership degree; use the average value of each adjustment temperature within the clustering cluster corresponding to the largest preferred membership degree as the adjustment temperature of the current storage space.

[0034] The present invention has the following beneficial effects:

[0035] The present invention provides a warehousing intelligent application management system based on blockchain technology, which relates to the technology of electrical digital data processing and is mainly applied to the field of temperature regulation in warehousing space. By correcting the initial membership degree obtained by the existing clustering algorithm, the clustering accuracy of monitoring data in the warehousing space is enhanced, the adaptability of temperature regulation in the warehousing space according to the clustering result is greatly improved, the effect of temperature regulation based on the clustering result is further enhanced, and the stability of the ambient temperature change in the warehousing space is ensured. The monitoring data changes in different warehousing areas in the warehousing space are different. In order to more accurately analyze the change of the monitoring data, when determining the regulated temperature of the current warehousing space, data analysis and processing are carried out based on the ambient temperature data and the warehousing volume data of different warehousing areas; when analyzing the first correlation factor, not only the stability of the ambient temperature change of similar warehousing volumes in the same time period is analyzed, but also the proportional relationship between the ambient temperature in different time periods and the corresponding warehousing volume is analyzed. The numerical accuracy of the first correlation factor obtained from the two aspects of analysis is better, providing reliable data support for determining the degree of correlation in the follow-up; when quantifying the degree of correlation between the warehousing volume and the ambient temperature in the warehousing area, both the influence degree of the ambient temperature in the warehousing area by the warehousing volume and the influence of the ambient temperature in the comparison area on the ambient temperature change in the warehousing area are analyzed, which effectively improves the reliability of the degree of correlation participating in the subsequent membership degree correction calculation process; the correction coefficient determined by combining the degree of correlation and the predicted value of the warehousing volume in each warehousing area is beneficial to improving the accuracy of the initial membership degree correction, obtaining a more accurate preferred membership degree, and the preferred membership degree provides data support for determining the regulated temperature of the current warehousing space, making the process of warehousing temperature regulation change more stable. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0037] Figure 1 It is the execution flowchart of a warehousing intelligent application management system based on blockchain technology according to an embodiment of the present invention;

[0038] Figure 2 It is the step flowchart of determining the first correlation factor of the ambient temperature and the warehousing volume in the warehousing area according to an embodiment of the present invention. Detailed Embodiments

[0039] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes the implementation manner, structure, features and effects of the technical solution proposed according to the present invention in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0041] The application scenario targeted by the present invention is as follows:

[0042] When the existing FCM clustering algorithm performs clustering analysis, it cannot analyze in combination with future data. After the temperature is adjusted, due to environmental changes, a suitable temperature may not be obtained, resulting in too large a difference between the adjusted temperature and the current adjusted temperature during the next temperature adjustment, and the temperature change in the storage space is unstable, affecting the storage effect of the storage space. Therefore, it is necessary to correct the clustering results to a certain extent to obtain a more accurate clustering result and improve the accuracy of temperature adjustment in the storage space. To ensure the stability of the storage temperature, the prediction results cannot be directly added during the clustering process. It is necessary to correct the results of each initial clustering cluster in combination with the relationship between the environmental temperature and the storage volume in the storage space.

[0043] Reference Figure 1 , which shows the execution flowchart of a warehousing intelligent application management system of blockchain technology according to an embodiment of the present invention. Implementing the warehousing intelligent application management system includes the following steps:

[0044] S1, obtain the monitoring data sequence of each type in the storage space in real time, cluster the data points formed by the monitoring data of each type, and obtain the initial membership degree of the environmental temperature of the current storage space with respect to each clustering cluster.

[0045] The first step is to obtain the monitoring data sequence of each type in the storage space in real time.

[0046] First of all, it should be noted that the monitoring data of each type is the average value of the environmental temperature in all storage areas, the cumulative value of the storage volume, and the average value of the adjusted temperature; each storage area only stores a specific type of storage item, that is, one storage area only corresponds to one type of storage item, and the placement method of the storage items is from the inside to the outside, from the bottom to the top, and from the left to the right. That is, when the storage volume of a certain item is fixed, its placement method is uniquely determined; the monitoring data sequence contains the monitoring data of the current storage space.

[0047] In this embodiment, in order to determine the adjusted temperature of the air conditioner in the storage space within the current hour, it is necessary to collect the ambient temperature and relevant data as basic data for subsequent data clustering analysis. Specifically, the ambient temperature in each storage area is collected using temperature sensors. There are multiple temperature sensors in a single storage area, and the average temperature of the multiple temperature sensors is used as the ambient temperature of the corresponding storage area. There is only one air conditioner in the storage space, and the wind speed cannot be adjusted. The adjustable parameter for changing the ambient temperature is the adjusted temperature of the air conditioner, and the adjusted temperatures of the air conditioner are collected. The adjusted temperatures of each storage area at the same collection moment are the same. For the storage volume of each storage area, it can be collected using RFID (Radio Frequency Identification) devices. The collection duration of the ambient temperature and its relevant data can be set to 30 days, and the collection frequency can be set to once every 1 hour. The collection duration and collection frequency of the data can be set by the implementer according to the specific actual situation and are not specifically limited.

[0048] It should be noted that for the storage volume of each storage area, the collection frequency is once a day. However, for the convenience of subsequent data processing, the storage volume of each hour within a day is made consistent and is equal to the storage volume collected in the first hour of the day.

[0049] In the second step, cluster the data points formed by the monitoring data of each type to obtain the initial membership degrees of the ambient temperature of the current storage space with respect to each cluster.

[0050] In this embodiment, first, based on the monitoring data sequence of each type, let the monitoring data of each type form data points, that is, in a three-dimensional coordinate system, the monitoring data of each type at the same collection moment form data points. Secondly, use the FCM clustering algorithm to perform clustering processing on all the obtained data points to obtain each cluster. The number K of clusters can be set to 20, and the clustering distance is the Euclidean distance between the data points in the three-dimensional coordinate system. Then, in order to improve the reliability and accuracy of temperature adjustment, during the clustering process, determine the membership degrees of the ambient temperature of the current storage space with respect to each cluster as the initial membership degrees for subsequent correction processing of the initial membership degrees.

[0051] Among them, the implementation process of the FCM clustering algorithm is prior art and not within the protection scope of the present invention, so it will not be elaborated in detail here. The size of the number K of clusters can be set by the implementer according to the specific actual situation and is not specifically limited.

[0052] So far, this embodiment has obtained the monitoring data sequences of each type in each storage area and the initial membership degrees of the ambient temperature of the current storage space with respect to each cluster.

[0053] S2. According to the environmental temperature sequence and storage volume sequence of each storage area, analyze the stability of the environmental temperature change of similar storage volumes in the same period and the proportional relationship between the environmental temperature and the corresponding storage volume in different periods, and determine the first correlation factor between the environmental temperature and the storage volume in each storage area.

[0054] First of all, it should be noted that the main reason for the influence of the storage volume on the temperature of the storage space is the accumulation and distribution of heat. When the storage volume increases, the number of items therein increases, and the volume occupied by the items increases, resulting in the accumulation of heat in the storage space. The accumulated heat will affect the temperature of the storage space and make it warmer. There is a certain correlation between the environmental temperature and the storage volume. The correction coefficient determined by analyzing the correlation between the environmental temperature and the storage volume can make the subsequent corrected membership degree satisfy both the current adjusted temperature and be smooth with the future adjusted temperature. The first correlation factor is obtained by analyzing the stability of the environmental temperature change of the storage area itself and the stability of the proportional relationship between the environmental temperature and the storage volume. The first correlation factor is one of the important indicators for calculating the correlation degree between the environmental degree and the storage volume subsequently.

[0055] In this embodiment, the calculation process of the first correlation factor between the environmental temperature and the storage volume in each storage area is the same. To reduce the description, taking any one storage area as an example, the first correlation factor between the environmental temperature and the storage volume in the storage area is determined, as Figure 2 shown. The specific implementation steps may include:

[0056] The first step is to determine each period corresponding to the environmental temperature sequence.

[0057] It should be noted that the environmental temperature of the storage area may change over time. Therefore, the collection times in the environmental temperature sequence can be time-divided. Furthermore, since the storage volume is only counted once a day, the characteristics of the environmental temperature change over time can be analyzed under the condition that the storage volume remains unchanged.

[0058] Specifically, first, the ambient temperatures on the same day in the ambient temperature sequence are grouped into temperature subsequences, that is, the ambient temperatures for each hour of the day are grouped into temperature subsequences. Secondly, using the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm, the data points composed of the ambient temperatures and the acquisition times of each temperature subsequence are clustered, and the clustering results corresponding to each temperature subsequence can be obtained. The clustering results can represent the classification of the ambient temperature change over time each day. Then, using the time division method corresponding to the clustering result with the highest frequency, each temperature subsequence is divided into time periods, and each time period in each temperature subsequence is obtained. Among them, the time division method for each day in the same storage area is the same. The time division method includes the number of clusters and the acquisition times of each data point within each cluster. For example, a day is divided into three time periods, the first time period is from the 1st hour to the 6th hour, the second time period is from the 7th hour to the 12th hour, and the third time period is from the 13th hour to the 24th hour.

[0059] In the second step, determine the acquisition times of each storage quantity subsequence corresponding to each storage quantity cluster.

[0060] It should be noted that different storage quantities in the same storage area may cause changes in the ambient temperature in the same time period. In order to analyze the stability of the ambient temperature change within the same time period for similar storage quantities, similar storage quantities need to be placed in the same cluster, and the stability of the ambient temperature change is analyzed under the premise of this cluster. At this time, first determine the acquisition times of each storage quantity subsequence corresponding to each storage quantity cluster.

[0061] Specifically, first, to be consistent with the temperature subsequence, the storage quantities on the same day in the storage quantity sequence are grouped into storage quantity subsequences, and the storage quantities in the same storage quantity subsequence are equal, that is, a storage quantity subsequence corresponds to only one numerical type of storage quantity. Secondly, using the DBSCAN clustering algorithm, the data points composed of the storage quantities and the acquisition times of the storage quantity sequence are clustered to obtain each storage quantity cluster, and a single storage quantity cluster contains similar but different numerical types of storage quantities. Then, each numerical type of storage quantity has its corresponding acquisition time, and the acquisition times of each storage quantity subsequence corresponding to each storage quantity cluster can be determined.

[0062] In this embodiment, the subsequence generally refers to the various data collected throughout the day. To distinguish it from the acquisition time of a single data, it is called the acquisition time of the subsequence, and the acquisition time specifically refers to the day. For example, the acquisition time of a certain subsequence is the first day. Among them, the subsequence includes the temperature subsequence and the storage quantity subsequence.

[0063] In the third step, according to the ambient temperatures in each time period of the temperature subsequences at the collection times of the respective storage quantity sub-sequences corresponding to each storage quantity clustering cluster, determine the temperature change stability index corresponding to the storage area.

[0064] It should be noted that the temperature change stability index can characterize the stability of the ambient temperature change of similar storage quantities corresponding to the storage area in the same time period. The larger the temperature change stability index, the more stable the ambient temperature change of the a-th storage area in the same time period under the premise of similar storage quantities, and the stronger the correlation between the storage quantity and the ambient temperature.

[0065] As an example, the calculation formula for the temperature change stability index corresponding to the a-th storage area can be:

[0066] In the formula, Ces a is the temperature change stability index corresponding to the a-th storage area, D is the number of time periods, d is the serial number of the time period, L is the number of storage quantity clustering clusters, e is the serial number of the storage quantity clustering cluster, exp is the exponential function with the natural constant as the base, η is the number of storage quantity sub-sequences corresponding to the storage quantity clustering cluster, δ is the serial number of the storage quantity sub-sequence corresponding to the storage quantity clustering cluster, fcn (a,e,δ,d) is the average ambient temperature of the d-th time period in the temperature subsequence at the collection time of the δ-th storage quantity sub-sequence corresponding to the e-th storage quantity clustering cluster of the a-th storage area, is the average value of the average ambient temperatures of the d-th time period in the temperature subsequences at the collection times of all storage quantity sub-sequences corresponding to the e-th storage quantity clustering cluster of the a-th storage area, and || is the absolute value symbol.

[0067] In the calculation formula of the temperature change stability index, the larger it is, the greater the difference between the ambient temperature of the d-th time period every day and the average value of the ambient temperatures of the d-th time period of all days, and the worse the stability of the ambient temperature change. Therefore, a negative correlation process needs to be performed on the final accumulated difference result; the negative correlation relationship means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases, which can be a subtraction relationship, a division relationship, etc., and is determined by the actual application. In this embodiment, exp(-) is used to implement the negative correlation normalization process of the data.

[0068] In the fourth step, according to the storage quantity in each storage quantity sub-sequence and the average ambient temperature of each time period in the temperature subsequence at the collection time of each storage quantity sub-sequence, determine the storage temperature correlation index corresponding to the storage area.

[0069] It should be noted that by analyzing the stability of the ratio change between the storage volume and the ambient temperature in the same storage area, the correlation between the storage volume and the ambient temperature is quantified, that is, the storage temperature-related index corresponding to the storage area is determined. The larger the storage temperature-related index, the more stable the ratio change between the storage volume and the ambient temperature in the storage area, and the stronger the correlation between the storage volume and the ambient temperature.

[0070] As an example, the calculation formula for the storage temperature-related index corresponding to the a-th storage area can be:

[0071] In the formula, Tes a is the storage temperature-related index corresponding to the a-th storage area, exp is the exponential function with the natural constant as the base, D is the number of time periods, d is the serial number of the time period, n is the serial number of the storage quantity subsequence, N is the number of storage quantity subsequences, and Tcn (a,n,d) is the ratio of the storage volume of the n-th storage quantity subsequence in the a-th storage area to the average ambient temperature of the d-th time period in the temperature subsequence at the acquisition time of the n-th storage quantity subsequence. || is the absolute value symbol.

[0072] In the calculation formula of the storage temperature-related index, can represent the ratio change of the storage volume at the same acquisition time in the a-th storage area to the average ambient temperature obtained in the d-th time period. The smaller it is, the smaller the ratio change between the storage volume and the ambient temperature, and in the same time period, the stronger the correlation between the storage volume and the ambient temperature in the a-th storage area; is negatively correlated with the storage temperature-related index Tes a So negative correlation processing needs to be performed on That is, negative correlation processing is realized by using exp(-).

[0073] In the fifth step, the product of the temperature change stability index corresponding to the storage area and the storage temperature-related index is used as the first correlation factor between the ambient temperature and the storage volume in the storage area.

[0074] It should be noted that the temperature change stability index, the storage temperature-related index and the first correlation factor are positively correlated. A positive correlation means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplicative relationship, an additive relationship, the power of an exponential function, etc. Therefore, the product of the temperature change stability index corresponding to the storage area and the storage temperature-related index can be used as the first correlation factor between the ambient temperature and the storage volume in the storage area.

[0075] So far, the first correlation factor between the ambient temperature and the storage volume in each storage area has been obtained in this embodiment.

[0076] S3. According to the environmental temperature sequences and storage quantity sequences of each storage area and its respective comparison areas, analyze the influence of the environmental temperature in all comparison areas on the environmental temperature in the storage area, and determine the second correlation factor between the environmental temperature and the storage quantity in each storage area.

[0077] First of all, it should be noted that the environmental temperature diffuses from high to low. When the placement of items in another storage area affects the ventilation of the current storage area, it will thus affect the environmental temperature of the current storage area. Therefore, the environmental temperature is not only affected by the storage quantity information of the storage area to which it belongs, but may also be affected by other storage areas. By analyzing the influence of the environmental temperature in all comparison areas on the environmental temperature in the storage area, the correlation between the environmental temperature and the storage quantity in the storage area is quantified, that is, the second correlation factor between the environmental temperature and the storage quantity in the storage area is determined.

[0078] In this embodiment, the calculation processes of the second correlation factors between the environmental temperature and the storage quantity in each storage area are the same. To reduce unnecessary descriptions, take any one storage area as an example to determine the second correlation factor. The specific implementation steps may include:

[0079] The first step is to, for each comparison area, determine the environmental temperatures at each time period in each temperature subsequence in the environmental temperature sequence of each comparison area, and determine the collection times of the respective storage quantity subsequences corresponding to each storage quantity clustering cluster in each comparison area and the collection times of each temperature subsequence.

[0080] The comparison area refers to other storage areas other than the current storage area itself. To facilitate the subsequent determination of the environmental temperature difference between the current storage area and its comparison areas, it is necessary to refer to the first and second steps of step S2 to determine the collection times of each time period in each temperature subsequence in the environmental temperature sequence of each comparison area, the collection times of the respective storage quantity subsequences corresponding to each storage quantity clustering cluster, and the collection times of each temperature subsequence.

[0081] The second step is to determine the second correlation factor between the environmental temperature and the storage quantity in the storage area according to the environmental temperatures at each time period in each temperature subsequence at the collection times of the respective storage quantity subsequences corresponding to each storage quantity clustering cluster of the storage area and its respective comparison areas.

[0082] It should be noted that the second correlation factor can characterize the influence degree of the comparison area on the storage area. The smaller the influence degree of the comparison area on the storage area, the greater the influence degree of the environmental temperature in the storage area by the change of the storage quantity, that is, the greater the first correlation factor. Analyzing the correlation between the environmental temperature and the storage quantity from the perspective of the influence of the environmental temperature in the comparison area on the environmental temperature in the storage area helps to further improve the numerical accuracy of the correlation degree between the environmental temperature and the storage quantity determined subsequently.

[0083] As an example, the calculation formula for the second correlation factor of the environmental temperature and the storage quantity in the a-th storage area can be:

[0084] In the formula, Hbc a is the second correlation factor of the environmental temperature and the storage quantity in the a-th storage area, exp is the exponential function with the natural constant as the base, B is the number of comparison areas, b is the serial number of the comparison area, L is the number of storage quantity clustering clusters, e is the serial number of the storage quantity clustering cluster, D is the number of time periods, d is the serial number of the time period, η is the number of storage quantity sub-sequences, fcn (a,e,δ,d) is the average environmental temperature of the d-th time period in the temperature sub-sequence at the acquisition time of the δ-th storage quantity sub-sequence corresponding to the e-th storage quantity clustering cluster in the a-th storage area, is the average value of the average environmental temperature of the d-th time period in the temperature sub-sequences at the acquisition times of all storage quantity sub-sequences corresponding to the e-th storage quantity clustering cluster in the a-th storage area, || is the absolute value symbol, fcn (a,b,e,δ,d) is the average environmental temperature of the d-th time period in the temperature sub-sequence at the acquisition time of the δ-th storage quantity sub-sequence corresponding to the e-th storage quantity clustering cluster in the b-th comparison area of the a-th storage area.

[0085] In the calculation formula of the second correlation factor, on the premise of similar storage quantities, can characterize the difference between the environmental temperature in the a-th storage area at the d-th time period of each day and the average environmental temperature at the d-th time period of all days, and |fcn (a,e,δ,d) -fcn (a,b,e,δ,d) | can characterize the difference between the environmental temperature in the a-th storage area at the d-th time period of each day and the environmental temperature in the b-th comparison area at the d-th time period of each day; and |fcn (a,e,δ,d) -fcn (a,b,e,δ,d) | are smaller, the smaller the environmental temperature difference between the two storage areas and the more stable the change of the environmental temperature in the storage area itself, indicating that the environmental temperature in the a-th storage area is less affected by the environmental temperature in the b-th comparison area.

[0086] So far, the second correlation factor between the ambient temperature and the storage volume in each storage area has been obtained in this embodiment.

[0087] S4. Determine the correlation degree between the ambient temperature and the storage volume in each storage area according to the first correlation factor and the second correlation factor; determine the correction coefficient of each clustering cluster according to the correlation degree and the difference between the predicted storage volume of each storage area and the storage volume of the storage area corresponding to the clustering center of each clustering cluster.

[0088] It should be noted that the storage volume in the storage interval has a high correlation with both the ambient temperature and the regulated temperature. Since there is no corresponding regulated temperature in the current storage area for the time being, in order to analyze the influence of the storage volume on the regulated temperature, the correlation degree between the storage volume and the regulated temperature can be indirectly quantified according to the correlation degree between the ambient temperature and the storage volume. Determining the correction coefficient by combining the correlation degree between the storage volume and the regulated temperature and the predicted storage volume of the current storage space not only helps to improve the accuracy of temperature regulation, but also overcomes the defect that the existing clustering algorithm cannot adapt to the continuous change of the ambient temperature when clustering only based on the existing data, ensures the stability of the ambient temperature in the storage space, and thus improves the effect of intelligent application management in the storage.

[0089] The first step is to determine the correlation degree between the ambient temperature and the storage volume in each storage area according to the first correlation factor and the second correlation factor.

[0090] In this embodiment, the first correlation factor, the second correlation factor and the correlation degree between the ambient temperature and the storage volume in the storage area are in a positive correlation relationship. For any storage area, the product of the first correlation factor and the second correlation factor corresponding to the storage area can be used as the correlation degree between the ambient temperature and the storage volume in the storage area.

[0091] It should be noted that when calculating the correlation degree, the first correlation factor and the second correlation factor act as weights. When the first correlation factor is larger, the second correlation factor is smaller, indicating that the influence degree of the ambient temperature in the storage area by the ambient temperature in the comparison area is smaller, and the first correlation factor and the second correlation factor are in a negative correlation relationship.

[0092] The second step is to determine the correction coefficient of each clustering cluster according to the correlation degree and the difference between the predicted storage volume of each storage area and the storage volume of the storage area corresponding to the clustering center of each clustering cluster.

[0093] In this embodiment, each clustering cluster is the clustering cluster obtained in step S1. The clustering cluster contains data points composed of the ambient temperature, regulated temperature and storage volume of the storage space at the same time. Each clustering cluster has its corresponding correction coefficient. The specific implementation steps may include:

[0094] For each storage area, the degree of correlation between the ambient temperature and the storage volume in the storage area is used as the numerator of the ratio, the difference between the predicted storage volume of the storage area and the storage volume of the storage area corresponding to the cluster center of any cluster is used as the denominator of the ratio, and the cumulative value of all ratios is used as the correction coefficient of the cluster, so as to obtain the correction coefficients of each cluster.

[0095] As an example, the calculation formula for the correction coefficient of the k-th cluster can be:

[0096] In the formula, Hn k is the correction coefficient of the k-th cluster, a is the serial number of the storage area in the storage space, A is the number of storage areas in the storage space, Tvc a is the degree of correlation between the ambient temperature and the storage volume in the a-th storage area, ΔYcd (a,k) is the difference between the predicted storage volume of the a-th storage area and the storage volume of the a-th storage area corresponding to the cluster center of the k-th cluster.

[0097] In the calculation formula of the correction coefficient, regarding the predicted storage volume of each storage area, based on the obtained storage volume data sequence of each storage area, the predicted storage volume of each storage area can be obtained by using the existing prediction algorithm; Tvc a can represent the degree of correlation between the ambient temperature and the storage volume in the storage space, that is, the influence degree of the storage volume on the ambient temperature. The greater the influence degree, the greater the correction coefficient of the cluster; ΔYcd (a,k) can represent the possibility that the predicted storage volume belongs to the k-th cluster. The smaller the difference between the predicted storage volume and the storage volume of the cluster center of the k-th cluster, the more likely the predicted storage volume belongs to the k-th cluster, and the greater the correction coefficient.

[0098] It should be noted that under normal circumstances, there is no possibility that ΔYcd (a,k) is zero. If there is an extreme situation resulting in ΔYcd (a,k) being zero, then a hyperparameter is adaptively added to the denominator of the fraction . The hyperparameter can be set to 0.1, and the size of the hyperparameter is not specifically limited. The existing prediction algorithms include but are not limited to: exponential smoothing method, regression moving average model, and seasonal autoregressive integrated moving average model, etc. The implementation process of the existing prediction algorithms is the prior art and is not within the protection scope of the present invention, so no detailed description will be given here.

[0099] So far, this embodiment has obtained the correction coefficients of each cluster.

[0100] S5. Use the correction coefficients of each clustering cluster to correct the initial membership degrees of the environmental temperature of the current storage space with respect to each clustering cluster, obtain the preferred membership degrees of the environmental temperature of the current storage space with respect to each clustering cluster, and then determine the adjusted temperature of the current storage space.

[0101] First step, use the correction coefficients of each clustering cluster to correct the initial membership degrees of the environmental temperature of the current storage space with respect to each clustering cluster, and obtain each preferred membership degree.

[0102] Specifically, for any clustering cluster with respect to the environmental temperature of the current storage space, calculate the product of the correction coefficient of this clustering cluster and the initial membership degree of the environmental temperature of the current storage space with respect to this clustering cluster as the corrected value of the initial membership degree of this clustering cluster, and use the value obtained by adding the corrected value of the initial membership degree of this clustering cluster to the initial membership degree as the preferred membership degree of this clustering cluster.

[0103] Second step, determine the adjusted temperature of the current storage space according to each preferred membership degree.

[0104] Specifically, according to the preferred membership degrees of the environmental temperature of the current storage space with respect to each clustering cluster, select the largest preferred membership degree; use the average value of each adjusted temperature within the clustering cluster corresponding to the largest preferred membership degree as the adjusted temperature of the current storage space.

[0105] So far, this embodiment has completed the monitoring and adjustment of the environmental temperature in the storage space.

[0106] The present invention provides a storage intelligent application management system based on blockchain technology. This system quantifies the influence degree of the storage quantity on the environmental temperature, combines the future storage quantity data, corrects the initial membership degrees of the environmental temperature of the current storage space with respect to each clustering cluster, improves the accuracy of the relevant data clustering results of the storage space, further enhances the reliability of the environmental temperature adjustment in the storage space, and is conducive to ensuring the stability of the temperature change in the storage space; and every temperature change and the response of the intelligent adjustment system are recorded on the blockchain, which can effectively ensure the authenticity and integrity of the data, and any tampering behavior can be detected, facilitating the application management of storage intelligence.

[0107] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of each embodiment of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A blockchain technology-based intelligent warehouse application management system, characterized in that: The invention comprises a memory and a processor, wherein the processor executes a computer program stored in the memory to implement the following steps: Acquire each type of monitoring data sequence of the storage space in real time, cluster the data points of each type of monitoring data at the same collection time in the three-dimensional coordinate system, and obtain the initial membership of the ambient temperature of the current storage space relative to each clustering cluster; the monitoring data in each type of monitoring data sequence is the average value of the ambient temperature in all storage areas, the accumulated value of the storage volume and the average value of the adjusted temperature; For each storage area of ​​the storage space, according to the ambient temperature sequence and storage volume sequence of the storage area, the stability of the ambient temperature change of similar storage volumes in the same period and the proportional relationship between the ambient temperature and the corresponding storage volume in different periods are analyzed to determine the first correlation factor between the ambient temperature and the storage volume in the storage area; According to the ambient temperature sequence and storage quantity sequence of the storage area and its respective comparison areas, the influence of the ambient temperature in all comparison areas on the ambient temperature in the storage area is analyzed to determine the second correlation factor between the ambient temperature and the storage quantity in the storage area; The comparison area is other storage areas except the current storage area itself; Determine the correlation between the ambient temperature and the storage volume in each storage area according to the first correlation factor and the second correlation factor; Determine the correction coefficient of each cluster according to the correlation degree and the difference between the predicted storage volume of each storage area and the storage volume of the storage area corresponding to the cluster center of each cluster; The correction coefficient of each cluster is used to correct the initial membership of the ambient temperature of the current storage space relative to each cluster, and the optimal membership of the ambient temperature of the current storage space relative to each cluster is obtained, thereby determining the adjustment temperature of the current storage space.

2. According to the blockchain technology of claim 1, the intelligent storage application management system is characterized in that: The method of analyzing the stability of the ambient temperature change of similar storage quantities in the same period and the proportional relationship between the ambient temperature and the corresponding storage quantity in different periods according to the ambient temperature sequence and the storage quantity sequence of the storage area to determine the first correlation factor between the ambient temperature and the storage quantity in the storage area includes: For the storage area, the ambient temperatures of the same day in the ambient temperature sequence are grouped into temperature subsequences; the data points consisting of the ambient temperature and the acquisition time of each temperature subsequence are clustered to obtain the clustering results corresponding to each temperature subsequence; each temperature subsequence is divided into time periods using the time division method corresponding to the clustering result with the highest frequency of occurrence, to obtain each time period in each temperature subsequence; The storage quantities of the same day in the storage quantity sequence are grouped into storage quantum sequences, and the storage quantities in the same storage quantum sequence are equal; the data points consisting of the storage quantities and the collection time of the storage quantity sequence are clustered to obtain various storage quantity clustering clusters; and the collection time of each storage quantum sequence corresponding to each storage quantity clustering cluster is determined; According to the ambient temperatures in each period of the temperature subsequence at the collection time of each storage quantum sequence corresponding to each storage volume cluster, the temperature change stability index corresponding to the storage area is determined; Determine the storage temperature related indicators corresponding to the storage area according to the storage volume in each storage quantum sequence and the average value of the ambient temperature in each period of the temperature subsequence under the collection time of each storage quantum sequence; The product of the temperature change stability index corresponding to the storage area and the storage temperature related index is used as the first correlation factor between the ambient temperature and the storage volume in the storage area.

3. According to the blockchain technology of claim 2, the intelligent storage application management system is characterized in that: The method of determining the temperature change stability index corresponding to the storage area according to each ambient temperature in each time period in the temperature subsequence at the collection time of each storage quantum sequence corresponding to each storage quantity clustering cluster includes: In the formula, Ces a is the temperature change stability index corresponding to the a-th storage area, D is the number of time periods, d is the sequence number of the time period, L is the number of storage volume clusters, e is the sequence number of the storage volume cluster, exp is the exponential function with natural constant as the base, η is the number of storage quantum sequences corresponding to the storage volume cluster, δ is the sequence number of the storage quantum sequence corresponding to the storage volume cluster, fcn (a,e,δ,d) is the mean value of the ambient temperature in the dth period of the temperature subsequence at the collection time of the δth storage quantum sequence corresponding to the eth storage quantity cluster of the ath storage area, is the average value of the ambient temperature mean in the dth period of the temperature subsequence under the collection time of all storage quantum subsequences corresponding to the eth storage quantity cluster of the ath storage area, and || is the sign for finding the absolute value.

4. According to the blockchain technology of claim 2, the intelligent storage application management system is characterized in that: Determining storage temperature related indicators corresponding to the storage area according to the storage volume in each storage quantum sequence and the average value of the ambient temperature in each period in the temperature subsequence at the collection time of each storage quantum sequence includes: In the formula, Tes a is the storage temperature related index corresponding to the a-th storage area, exp is the exponential function with natural constant as the base, D is the number of time periods, d is the sequence number of the time period, n is the sequence number of the storage quantum sequence, N is the number of the storage quantum sequence, Tcn (a,n,d) is the ratio of the storage volume of the nth storage quantum sequence of the ath storage area to the average ambient temperature of the dth period in the temperature subsequence at the collection time of the nth storage quantum sequence, || is the absolute value symbol.

5. According to the blockchain technology of claim 2, the intelligent storage application management system is characterized in that: The method of analyzing the influence of the ambient temperature in all the comparison areas on the ambient temperature in the storage area according to the ambient temperature sequence and the storage quantity sequence of the storage area and its respective comparison areas, and determining the second correlation factor between the ambient temperature and the storage quantity in the storage area, comprises: For each comparison area, determine each ambient temperature of each time period in each temperature subsequence in the ambient temperature sequence of each comparison area, and determine the collection time of each storage quantity subsequence and the collection time of each temperature subsequence corresponding to each storage quantity cluster of each comparison area; According to the ambient temperatures in each time period in each temperature subsequence at the collection time of each storage subsequence corresponding to each storage quantity clustering cluster of the storage area and its respective comparison areas, a second correlation factor between the ambient temperature and the storage quantity in the storage area is determined.

6. According to the blockchain technology of claim 5, the intelligent storage application management system is characterized in that: The second correlation factor between the ambient temperature and the storage quantity in the storage area is determined according to the ambient temperatures in each time period in each temperature subsequence at the acquisition time of each storage subsequence corresponding to each storage quantity clustering cluster of the storage area and each comparison area thereof, including: In the formula, Hbc a is the second correlation factor between ambient temperature and storage volume in the ath storage area, exp is an exponential function with natural constant as the base, B is the number of comparison areas, b is the serial number of comparison areas, L is the number of storage volume clusters, e is the serial number of storage volume clusters, D is the number of time periods, d is the serial number of time periods, η represents the number of storage quantum sequences, and fcn (a,e,δ,d) is the mean value of the ambient temperature in the dth period of the temperature subsequence at the collection time of the δth storage quantum sequence corresponding to the eth storage quantity cluster of the ath storage area, is the average value of the ambient temperature in the dth period of the temperature subsequence under the acquisition time of all storage quantum subsequences corresponding to the eth storage quantity cluster of the ath storage area, || is the sign of the absolute value, and fcn (a,b,e,δ,d) It is the mean value of the ambient temperature in the dth period in the temperature subsequence at the collection time of the δth storage quantum sequence corresponding to the eth storage quantity cluster of the bth comparison area of ​​the ath storage area.

7. According to the blockchain technology of claim 1, the intelligent warehouse application management system is characterized in that: The step of determining the correlation between the ambient temperature and the storage volume in each storage area according to the first correlation factor and the second correlation factor includes: For any storage area, the product of the first correlation factor and the second correlation factor of the ambient temperature and the storage quantity in the storage area is taken as the correlation degree between the ambient temperature and the storage quantity in the storage area.

8. According to the blockchain technology of claim 1, the intelligent warehouse application management system is characterized in that: Determining the correction coefficient of each cluster according to the correlation degree, the difference between the predicted storage volume of each storage area and the storage volume of the storage area corresponding to the cluster center of each cluster, includes: For each storage area in the storage space, the correlation between the ambient temperature and the storage volume in the storage area is taken as the numerator of the ratio, and the difference between the predicted storage volume of the storage area and the storage volume of the storage area corresponding to the cluster center of any cluster is taken as the denominator of the ratio. The accumulated value of all ratios corresponding to all storage areas is taken as the correction coefficient of the cluster, so as to obtain the correction coefficient of each cluster.

9. According to claim 8, a blockchain technology based intelligent warehouse application management system is characterized in that: The method uses the correction coefficient of each cluster to correct the initial membership of the ambient temperature of the current storage space relative to each cluster to obtain the optimal membership of the ambient temperature of the current storage space relative to each cluster, including: For any cluster to which the ambient temperature of the current storage space is relative, calculate the product of the correction coefficient of the cluster and the initial membership of the ambient temperature of the current storage space relative to the cluster as the initial membership correction value of the cluster, and take the value obtained by adding the initial membership correction value of the cluster to the initial membership as the preferred membership of the cluster.

10. According to the blockchain technology of claim 1, the intelligent warehouse application management system is characterized in that: The step of determining the current adjustment temperature of the storage space includes: According to the preferred membership of the current storage space ambient temperature relative to each cluster, the largest preferred membership is selected; the average value of each adjustment temperature in the cluster corresponding to the largest preferred membership is used as the adjustment temperature of the current storage space.

Images