A multifunctional integrated data control method and system for intelligent storage cabinet

Abstract

The embodiment of the present invention provides a multifunctional integrated data control method and system for a smart storage cabinet, which obtains a user image by taking a photo outside the smart storage cabinet; performs user behavior analysis based on the user image, inputs the user behavior and fuzzy category sample data of stored items into a factor decomposition machine model, and obtains a trained factor decomposition machine model; converts a new user image into a user behavior feature, and inputs the user behavior feature into the trained factor decomposition machine model to obtain output second predicted usage data; combines the first predicted usage data and the second predicted usage data to obtain scheduling usage data of the smart storage cabinet box; is able to effectively predict the allocation and usage of the storage cabinet, and can also be applied in complex industrial and commercial application scenarios, and predicts the allocation of different cabinet boxes according to the usage, thereby improving management efficiency and safety performance; and also has a multifunctional integrated management function, realizing the multi-scenario application function of the smart storage cabinet.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a multifunctional integrated data control method of an intelligent storage cabinet, a multifunctional integrated data control system of an intelligent storage cabinet, a computer device and a storage medium. Background Art

[0002] With the development of Internet of Things technology and intelligent control technology, storage cabinet cluster management systems have gradually been widely used in various application scenarios, such as logistics distribution, smart express cabinets, smart storage cabinets, industrial storage cabinets, etc. However, the existing storage cabinet cluster management system has shortcomings such as low storage cabinet utilization in actual applications. The existing storage cabinet cluster management system can evaluate the operation status and use effect of the storage cabinet based on the storage cabinet status information, including the cabinet opening response time, the cabinet opening success rate and the allocation utilization rate, combined with the characteristic data of the actual stored items. However, this method can only simply evaluate the use status of the storage cabinet, and the function is too simple, which is not suitable for application scenarios with a wide variety of stored items. Summary of the invention

[0003] In view of the above problems, embodiments of the present invention are proposed to provide a multifunctional integrated data control method of an intelligent storage cabinet, a multifunctional integrated data control system of an intelligent storage cabinet, a computer device and a storage medium that overcome the above problems or at least partially solve the above problems.

[0004] In order to solve the above problems, the embodiment of the present invention discloses a multifunctional integrated data control method of an intelligent storage cabinet, which is applied to a multifunctional integrated data control system, wherein the multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, and a single intelligent storage cabinet comprises a plurality of cabinet boxes arranged horizontally and vertically, wherein a plurality of sensors are arranged inside the cabinet boxes, and the sensors include a temperature sensor and a humidity sensor; including:

[0005] Acquire the combined temperature data and combined humidity data inside multiple adjacent cabinets;

[0006] The temperature difference and the humidity difference are calculated based on the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within the preset range of the intelligent storage cabinet;

[0007] Obtain the historical usage data of cabinet types within a preset time period;

[0008] A cluster scheduling Q function model is constructed based on the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data;

[0009] Obtaining user images taken outside the smart storage cabinet;

[0010] Performing user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0011] Inputting the user behavior and the fuzzy category sample data of stored items into the factorization machine model to obtain a trained factorization machine model;

[0012] Converting a new user image into a user behavior feature, and inputting the user behavior feature into a trained factorization machine model to obtain output second predicted usage data;

[0013] The first predicted usage data and the second predicted usage data are combined to obtain scheduling usage data of the smart storage cabinet.

[0014] Preferably, the obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes:

[0015] Obtain temperature and humidity data for each cabinet;

[0016] Calculate the temperature average of the temperature data of all selected cabinets, and determine the temperature average as the combined temperature data of the central cabinet;

[0017] The humidity mean value of the humidity data of all selected cabinets is calculated, and the humidity mean value is determined as the combined humidity data of the central cabinet.

[0018] Preferably, the cabinet historical usage data includes used cabinet information and remaining cabinet information; the cluster scheduling Q function model is constructed according to the cabinet historical usage data, temperature difference, humidity difference, cabinet position and quantity to obtain the first predicted usage data, including:

[0019] Determine the used cabinet information and the remaining cabinet information as the status information;

[0020] Determine temperature difference, humidity difference, cabinet location and quantity as behavioral information;

[0021] Constructing a cluster scheduling Q function model according to the state information, the behavior information and the discount factor, obtaining a first approximate eigenvalue and a second approximate eigenvalue of the cluster scheduling Q function model, and constructing a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue;

[0022] Iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model;

[0023] The new temperature difference, humidity difference, cabinet position and quantity are input into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0024] Preferably, the performing of user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data includes:

[0025] Arrange user images in time series to obtain an image sequence;

[0026] Classifying the image sequence to obtain an action image sequence and a micro-expression image sequence;

[0027] Calculating the emotion values ​​of the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences;

[0028] A variety of user behaviors and corresponding fuzzy category sample data of stored items are obtained for the image sequence according to the emotion value.

[0029] Preferably, the step of inputting the user behavior and the fuzzy category sample data of stored items into a factor decomposition machine model to obtain a trained factor decomposition machine model comprises:

[0030] Converting the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature;

[0031] Calculating the correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screening out specific user behavior features whose correlation coefficient is lower than a preset threshold;

[0032] Converting the specific user behavior feature into a user behavior vector;

[0033] The user behavior vector and the sample data of the fuzzy categories of stored items are input into the factor decomposition machine model, and the model parameters of the factor decomposition machine model are adjusted to obtain a trained factor decomposition machine model.

[0034] The embodiment of the present invention discloses a multifunctional integrated data control system of an intelligent storage cabinet, wherein the multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, wherein a single intelligent storage cabinet comprises a plurality of cabinet boxes arranged horizontally and vertically, wherein a plurality of sensors are arranged inside the cabinet boxes, wherein the sensors comprise a temperature sensor and a humidity sensor; and

[0035] A first acquisition module is used to acquire combined temperature data and combined humidity data inside a plurality of adjacent cabinets;

[0036] A temperature difference and humidity difference module, used to calculate the temperature difference and humidity difference according to the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within a preset range of the intelligent storage cabinet;

[0037] The second acquisition module is used to acquire the historical usage data of cabinet types within a preset time period;

[0038] The first predicted usage data module is used to construct a cluster scheduling Q function model according to the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data;

[0039] A user image module is used to obtain a user image taken outside the smart storage cabinet;

[0040] A behavior analysis module, used to perform user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0041] A training module, used for inputting the user behavior and the fuzzy category sample data of the stored items into the factor decomposition machine model to obtain a trained factor decomposition machine model;

[0042] A second predicted usage data module is used to convert a new user image into a user behavior feature, and input the user behavior feature into a trained factor decomposition machine model to obtain output second predicted usage data;

[0043] The scheduling and use module is used to combine the first predicted use data and the second predicted use data to obtain the scheduling and use data of the smart storage cabinet.

[0044] Preferably, the obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes:

[0045] The first acquisition submodule is used to acquire the temperature data and humidity data of each cabinet;

[0046] A first calculation submodule, used for calculating a temperature mean of the temperature data of all selected cabinets, and determining the temperature mean as the combined temperature data of the central cabinet;

[0047] The second calculation submodule is used to calculate the humidity mean value of the humidity data of all selected cabinets, and determine the humidity mean value as the combined humidity data of the central cabinet.

[0048] Preferably, the cabinet historical usage data includes used cabinet information and remaining cabinet information; the first predicted usage data module includes:

[0049] A status information submodule, used to determine the used cabinet information and the remaining cabinet information as status information;

[0050] A behavior information submodule, for determining temperature difference, humidity difference, cabinet position and quantity as behavior information;

[0051] A construction submodule is used to construct a cluster scheduling Q function model according to the state information, behavior information and discount factor, obtain the first approximate eigenvalue and the second approximate eigenvalue of the cluster scheduling Q function model, and construct a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue;

[0052] A training submodule, used for iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model;

[0053] The first predicted usage data submodule is used to input the new temperature difference, humidity difference, cabinet position and quantity into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0054] The embodiment of the present invention further discloses a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of multifunctional integrated data control of the above-mentioned intelligent storage cabinet when executing the computer program.

[0055] The embodiment of the present invention further discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of multifunctional integrated data control of the above-mentioned intelligent storage cabinet are implemented.

[0056] The embodiments of the present invention include the following advantages:

[0057] In an embodiment of the present invention, the multifunctional integrated data control method of the intelligent storage cabinet may include:

[0058] The combined temperature data and combined humidity data inside multiple adjacent cabinets are obtained; the temperature difference and humidity difference are calculated based on the combined temperature data and combined humidity data and the ambient temperature data and ambient humidity data within the preset range of the intelligent storage cabinet; the historical type usage data of the cabinets within the preset time period are obtained; the cluster scheduling Q function model is constructed based on the historical type usage data of the cabinets, the temperature difference and humidity difference, and the position and number of the cabinets to obtain the first predicted usage data; the user image is obtained by shooting outside the intelligent storage cabinet; the user behavior is analyzed based on the user image to obtain the user behavior and the fuzzy type sample data of the stored items; the user behavior and the fuzzy type sample data of the stored items are input into the factor analysis The trained factor decomposition machine model is obtained by decomposing the new user image into the user behavior feature, and the user behavior feature is input into the trained factor decomposition machine model to obtain the second predicted usage data as output; the first predicted usage data and the second predicted usage data are combined to obtain the scheduling usage data of the smart storage cabinet; the smart storage cabinet can effectively predict the allocation and usage of the storage cabinet, and can also be applied in complex industrial and commercial application scenarios, and different cabinets can be allocated and predicted according to the usage, so as to improve the management efficiency and safety performance; the smart storage cabinet can also be applied in complex industrial and commercial application scenarios, and can realize the multi-scenario application function of the smart storage cabinet by multi-functional integrated management functions, such as temperature monitoring function, humidity monitoring function and user abnormal behavior analysis and prediction function. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 It is a flowchart of the steps of an embodiment of a multifunctional integrated data control method of an intelligent storage cabinet according to an embodiment of the present invention;

[0061] Figure 2 is a schematic diagram of cabinet boxes arranged horizontally and vertically in an intelligent storage cabinet according to an embodiment of the present invention;

[0062] Figure 3 It is a structural block diagram of an embodiment of a multifunctional integrated data control system of an intelligent storage cabinet according to an embodiment of the present invention;

[0063] Figure 4 The diagram is a diagram of the internal structure of a computer device according to an embodiment. DETAILED DESCRIPTION

[0064] In order to make the technical problems, technical solutions and beneficial effects solved by the embodiments of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0065] In the embodiments of the present invention, in the application scenarios of smart storage cabinets with strong industrial and commercial fixity and relatively fixed application frequency, firstly, the predicted usage data is obtained based on the historical usage data and physical characteristic data of the storage cabinets in combination with the cluster scheduling Q function model. In addition, the approximate types of stored items that the user may use can be predicted based on the user behavior of the storage cabinets and the inferred fuzzy types of items. The above-mentioned usage data is superimposed on the approximate types of stored items that may be used to obtain prediction results for multiple scenarios, which can effectively predict the allocation and usage of storage cabinets. It can also be applied in complex industrial and commercial application scenarios, and different cabinets are allocated and predicted according to usage, thereby improving management efficiency and safety performance. It also has multi-functional integrated management functions, such as temperature monitoring function, humidity monitoring function, and user abnormal behavior analysis and prediction function, realizing the multi-scenario application function of smart storage cabinets.

[0066] Reference Figure 1 , shows a flowchart of a multifunctional integrated data control method of an intelligent storage cabinet according to an embodiment of the present invention, which is applied to a multifunctional integrated data control system, wherein the multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, wherein a single intelligent storage cabinet comprises a plurality of cabinets arranged horizontally and vertically, wherein a plurality of sensors are arranged inside the cabinets, wherein the sensors comprise a temperature sensor and a humidity sensor; specifically, the following steps may be included:

[0067] Step 101, obtaining combined temperature data and combined humidity data inside a plurality of adjacent cabinets;

[0068] In an embodiment of the present invention, the intelligent storage cabinet may be connected to a server, and the server may be provided with a multifunctional integrated data control system, which may have multiple functions such as temperature monitoring function, humidity monitoring function, cabinet allocation prediction and use function, user abnormal behavior analysis and prediction function, etc. The embodiment of the present invention does not impose too many restrictions on the types of functions;

[0069] The multifunctional integrated data control system is connected to a plurality of smart storage cabinets. A single smart storage cabinet includes a plurality of cabinet boxes arranged horizontally and vertically. A plurality of sensors are arranged inside the cabinet boxes, including temperature sensors and humidity sensors. An image acquisition device and a plurality of environmental sensors may also be arranged outside the smart storage cabinet. The image acquisition device is used to acquire user images. The environmental sensors may acquire environmental temperature sensors and environmental humidity sensors. The embodiments of the present invention do not impose excessive restrictions on this.

[0070] Specifically applied to the embodiment of the present invention, the acquisition of combined temperature data and combined humidity data inside a plurality of adjacent cabinets includes:

[0071] Obtain temperature and humidity data for each cabinet;

[0072] Calculate the temperature average of the temperature data of all selected cabinets, and determine the temperature average as the combined temperature data of the central cabinet;

[0073] The humidity mean value of the humidity data of all selected cabinets is calculated, and the humidity mean value is determined as the combined humidity data of the central cabinet.

[0074] like Figure 2 As shown, a temperature sensor and a humidity sensor can be provided inside each cabinet box in the horizontally and vertically arranged cabinet boxes, and the temperature sensor and the humidity sensor are used to measure the temperature data and the humidity data inside each cabinet box. In the embodiment of the present invention, in order to avoid the superposition of measurement errors of adjacent cabinet boxes and affect the measurement results, the average temperature and humidity data measured by adjacent cabinet boxes are processed to obtain more accurate temperature and humidity average data processing results, thereby improving the accuracy of the data measurement results.

[0075] Specifically, firstly, a central cabinet and adjacent cabinets adjacent to the central cabinet can be determined, and the central cabinet and the adjacent cabinets constitute a selected cabinet, that is, the average temperature and average humidity of multiple selected cabinets in the area are calculated as the combined humidity data and combined temperature data of the central cabinet; in the embodiment of the present invention, the central cabinet refers to the cabinet in the surrounded position among all the selected cabinets in a certain area of ​​the smart storage cabinet. In one embodiment, Figure 2 The two situations are shown in .

[0076] In an embodiment of the present invention, the smart storage cabinet may be provided with a terminal and a camera; the terminal may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The embodiment of the present invention does not limit the specific type of the terminal, and the operating system of the terminal may include Android, Harmony OS, IOS, Windows Phone, Windows, etc., and the present invention does not impose excessive restrictions on this.

[0077] In a preferred embodiment, the multifunctional integrated data control method of the intelligent storage cabinet provided in the embodiment of the present invention can be applied to an application environment including a terminal and a server. The terminal communicates with the server through a network. The terminal can be, but is not limited to, various personal computers, laptops, and tablet computers, and the server can be implemented as an independent server or a server cluster composed of multiple servers.

[0078] It should be noted that the smart storage cabinet may refer to an industrial circulation cabinet or a storage cabinet, etc., and the embodiments of the present invention do not impose too many restrictions on this. In addition, with regard to the structure of the smart storage cabinet, the structure of the main cabinet may include side panels, top panels, bottom panels, back panels, supporting feet, bases, adjustable casters, etc.; the internal structure may include adjustable shelves or fixed shelves, vertical or horizontal partition dividers, sliding drawers, classification grids, pull-out metal mesh baskets, hinged doors or sliding doors and corresponding mechanical locks, etc. The embodiments of the present invention do not impose too many restrictions on the structure and function of the smart storage cabinet.

[0079] Step 102, calculating the temperature difference and the humidity difference according to the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within a preset range of the intelligent storage cabinet;

[0080] Further applied to the embodiment of the present invention, after obtaining the combined temperature data and the combined humidity data, a difference operation is performed between the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data of the intelligent storage cabinet to obtain a temperature difference and a humidity difference;

[0081] For example, the combined temperature data of a central cabinet is a1, and the combined humidity data is b1; and the ambient temperature data within the preset range of the smart storage cabinet is a2, and the ambient humidity data is b2; then the temperature difference of the central cabinet is a1-a2, and the humidity difference is b1-b2. It should be noted that the preset range may refer to a range within 1 meter of the perimeter of the smart storage cabinet body. The range may be any range measured by the environmental sensor, and the embodiments of the present invention do not impose excessive restrictions on this.

[0082] Step 103, obtaining the historical usage data of the cabinet types within a preset time period;

[0083] In an embodiment of the present invention, historical cabinet type usage data of the smart storage cabinet can also be obtained. The historical cabinet type usage data can refer to the type of stored items, cabinet number, etc., or other types of usage data. The embodiment of the present invention does not impose too many restrictions on this.

[0084] Step 104, constructing a cluster scheduling Q function model according to the historical usage data of cabinet types, temperature difference, humidity difference, cabinet locations and quantities, and obtaining first predicted usage data;

[0085] In industrial application scenarios, the items stored in cabinets have periodicity and relatively fixed types of items. The historical usage data of the cabinet types and the temperature difference, humidity difference, cabinet location and quantity of each cabinet are clustered and scheduled into a Q function model to obtain the first predicted usage data.

[0086] It should be noted that the cabinet position refers to the vertical and horizontal coordinate positions represented in the plane coordinates of the front of the smart storage cabinet. Furthermore, the cluster scheduling Q function model is an improved Markov decision process model in the embodiment of the present invention, which improves the accuracy of prediction, improves resource utilization, and realizes the improvement of resource utilization of smart storage boxes; specifically applied to the embodiment of the present invention, the cabinet historical type usage data includes the used cabinet information and the remaining cabinet information; the cluster scheduling Q function model is constructed according to the cabinet historical type usage data, temperature difference, humidity difference and cabinet position and quantity, and the first predicted usage data is obtained, including:

[0087] Determine the used cabinet information and the remaining cabinet information as the status information;

[0088] In the embodiment of the present invention, the used cabinet information and the remaining cabinet information in the cabinet history usage data can be determined as the status information, that is, the status information ;

[0089] in, represents the state information at time t, Indicates the used cabinet information, i=1,2,3······d, d is a positive integer, represents the remaining cabinet information, j=1,2,3······d, d is a positive integer;

[0090] Determine temperature difference, humidity difference, cabinet location and quantity as behavioral information;

[0091] Furthermore, the behavior information may include:

[0092] ;

[0093] in, represents the behavior information at time t, Indicates the storage coordinate position of the cabinet, q=1,2,3······d, d is a positive integer, Represents the temperature difference of the cabinet stored in the coordinate position, q=1,2,3······d, d is a positive integer, Indicates the humidity difference of the cabinets at the storage location, q=1,2,3······d, d is a positive integer; the temperature difference and humidity difference can represent slight differences between the types of stored items.

[0094] A cluster scheduling Q function model is constructed according to the state information, the behavior information and the discount factor, and a characteristic loss function is constructed according to the first approximate eigenvalue and the second approximate eigenvalue of the cluster scheduling Q function model;

[0095] In addition, the instant reward of the cluster scheduling Q function model It can be expressed as:

[0096] ;

[0097] in, represents the immediate reward at time t, Indicates the coordinate position of the current cabinet. Indicates the deposit time, i=1,2,3······d, d is a positive integer, Represents the storage time of item, i=1,2,3······d, where d is a positive integer.

[0098] In the embodiment of the present invention, the first approximate eigenvalue refers to the Q value corresponding to the state transition probability in a certain state; and the second approximate eigenvalue refers to the Q value corresponding to each behavior in the current state;

[0099] Then the cluster scheduling Q function model is:

[0100] ;

[0101] Among them, the represents the discount factor, Express expectations, represents the cluster scheduling Q function model;

[0102] The feature loss function It can be expressed as

[0103] ;

[0104] in, Indicates the Q value corresponding to the state transition probability under a certain state; Indicates the Q value corresponding to each behavior in the current state;

[0105] Iterate the feature loss function until the cluster scheduling Q function model function converges to obtain the trained cluster scheduling Q function model, that is, complete the training process of the sample data;

[0106] The new temperature difference, humidity difference, cabinet position and quantity are input into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0107] The first predicted usage data refers to predicted usage data, such as the predicted number and location of cabinet usage within a certain period of time in the future; it provides a reference for inventory management and production management.

[0108] Step 105, obtaining a user image taken outside the smart storage cabinet;

[0109] Furthermore, in the embodiment of the present invention, the user image can also be obtained by shooting through a camera arranged outside the smart storage cabinet; in order to realize the diversity of algorithm functions, the following steps are mainly applied to commercial smart storage cabinets.

[0110] Step 106, performing user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0111] First, the fuzzy categories of stored items can be obtained according to user behavior, and multiple fuzzy categories of stored items can be combined into sample data.

[0112] The fuzzy category of the stored items refers to the fuzzy field of the category of the stored items and the corresponding storage location of the items. For example, the fuzzy field of the category can be "light", "heavy", "fragile", "hard", "soft", "difficult to hold", etc. The embodiment of the present invention does not impose too many restrictions on this. Specifically applied to the embodiment of the present invention, the user behavior analysis is performed based on the user image to obtain the user behavior and the fuzzy category sample data of the stored items, including:

[0113] Arrange user images in time series to obtain an image sequence;

[0114] Classifying the image sequence to obtain an action image sequence and a micro-expression image sequence;

[0115] Calculating the emotion values ​​of the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences;

[0116] The image sequence is reclassified according to the emotion value to obtain various user behaviors and corresponding fuzzy category sample data of stored items.

[0117] Specifically applied to the embodiments of the present invention, the correspondence between the emotion value and the fuzzy category of the stored items is established. For example, a certain emotion value range (k1-k2) corresponds to the fuzzy category of the stored items: "heavy", and a certain emotion value range (k2-k3) corresponds to the fuzzy category of the stored items: "fragile". The corresponding fuzzy category of the stored items can be inferred based on the emotion values ​​such as the actions and micro-expression images in the user image.

[0118] In the embodiment of the present invention, the calculation expression of the sentiment value is as follows:

[0119] ;

[0120] in, Represents the sentiment value, A sequence value representing a specific action in an action image sequence, represents the sequence value of micro-expressions in the micro-expression image sequence, and k represents the corresponding number of category fuzzy fields;

[0121] Step 107, inputting the user behavior and the fuzzy category sample data of the stored items into the factor decomposition machine model to obtain a trained factor decomposition machine model;

[0122] In the embodiment of the present invention, the step of inputting the user behavior and the fuzzy category sample data of stored items into a factor decomposition machine model to obtain a trained factor decomposition machine model includes:

[0123] Converting the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature;

[0124] Calculating the correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screening out specific user behavior features whose correlation coefficient is lower than a preset threshold;

[0125] Convert specific user behavior features into user behavior vectors;

[0126] The user behavior vector and the sample data of the fuzzy categories of stored items are input into the factor decomposition machine model, and the model parameters of the factor decomposition machine model are adjusted to obtain a trained factor decomposition machine model.

[0127] In the embodiment of the present invention, the first distinguishing behavior feature may refer to a corresponding action feature in an action image sequence, and the second distinguishing behavior feature may refer to a corresponding micro-expression feature in a micro-expression image sequence.

[0128] The correlation coefficient may refer to the Pearson correlation coefficient between the corresponding action features in the action image sequence and the corresponding micro-expression features in the micro-expression image sequence.

[0129] Step 108, converting the new user image into user behavior features, and inputting the user behavior features into the trained factorization machine model to obtain output second predicted usage data;

[0130] The second predicted usage data may refer to the approximate types of stored items inferred based on user behavior, providing reference information for the scheduling of smart storage cabinets and improving the efficiency of cabinet scheduling and usage.

[0131] Step 109: Combine the first predicted usage data and the second predicted usage data to obtain scheduling usage data of the smart storage cabinet.

[0132] Further applied to the embodiments of the present invention, different scenarios can be identified first, such as industrial application scenarios or commercial application scenarios, and different prediction functions can be called according to different application scenarios.

[0133] The algorithm of the present invention can be applied to fixed storage items (such as industrial product application scenarios) and personal storage items (commercial application scenarios), improving the algorithm's multi-scenario applicability.

[0134] In an embodiment of the present invention, the multifunctional integrated data control method of the intelligent storage cabinet may include:

[0135] The combined temperature data and combined humidity data inside multiple adjacent cabinets are obtained; the temperature difference and humidity difference are calculated based on the combined temperature data and combined humidity data and the ambient temperature data and ambient humidity data within the preset range of the intelligent storage cabinet; the historical type usage data of the cabinets within the preset time period are obtained; the cluster scheduling Q function model is constructed based on the historical type usage data of the cabinets, the temperature difference and humidity difference, and the position and number of the cabinets to obtain the first predicted usage data; the user image is obtained by shooting outside the intelligent storage cabinet; the user behavior is analyzed based on the user image to obtain the user behavior and the fuzzy type sample data of the stored items; the user behavior and the fuzzy type sample data of the stored items are input into the factor analysis The trained factor decomposition machine model is obtained by decomposing the new user image into the user behavior feature, and the user behavior feature is input into the trained factor decomposition machine model to obtain the second predicted usage data as output; the first predicted usage data and the second predicted usage data are combined to obtain the scheduling usage data of the smart storage cabinet; the smart storage cabinet can effectively predict the allocation and usage of the storage cabinet, and can also be applied in complex industrial and commercial application scenarios, and different cabinets can be allocated and predicted according to the usage, so as to improve the management efficiency and safety performance; the smart storage cabinet can also be applied in complex industrial and commercial application scenarios, and can realize the multi-scenario application function of the smart storage cabinet by multi-functional integrated management functions, such as temperature monitoring function, humidity monitoring function and user abnormal behavior analysis and prediction function.

[0136] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0137] Reference Figure 3 , shows a structural block diagram of an embodiment of a multifunctional integrated data control system of an intelligent storage cabinet according to an embodiment of the present invention, wherein the multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, wherein a single intelligent storage cabinet comprises a plurality of cabinet boxes arranged horizontally and vertically, wherein a plurality of sensors are arranged inside the cabinet boxes, wherein the sensors comprise a temperature sensor and a humidity sensor; and specifically, the following modules may be included:

[0138] The first acquisition module 301 is used to acquire the combined temperature data and the combined humidity data inside a plurality of adjacent cabinets;

[0139] The temperature difference and humidity difference module 302 is used to calculate the temperature difference and humidity difference according to the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within the preset range of the intelligent storage cabinet;

[0140] The second acquisition module 303 is used to acquire the historical usage data of the cabinet type within a preset time period;

[0141] The first predicted usage data module 304 is used to construct a cluster scheduling Q function model according to the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data;

[0142] The user image module 305 is used to obtain the user image taken outside the smart storage cabinet;

[0143] Behavior analysis module 306, used to perform user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0144] A training module 307, for inputting the user behavior and the fuzzy category sample data of stored items into the factor decomposition machine model to obtain a trained factor decomposition machine model;

[0145] The second predicted usage data module 308 is used to convert the new user image into user behavior features, and input the user behavior features into the trained factor decomposition machine model to obtain output second predicted usage data;

[0146] The scheduling and use module 309 is used to combine the first predicted use data and the second predicted use data to obtain the scheduling and use data of the smart storage cabinet.

[0147] Preferably, the obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes:

[0148] The first acquisition submodule is used to acquire the temperature data and humidity data of each cabinet;

[0149] A first calculation submodule, used for calculating a temperature mean of the temperature data of all selected cabinets, and determining the temperature mean as the combined temperature data of the central cabinet;

[0150] The second calculation submodule is used to calculate the humidity mean value of the humidity data of all selected cabinets, and determine the humidity mean value as the combined humidity data of the central cabinet.

[0151] Preferably, the cabinet historical usage data includes used cabinet information and remaining cabinet information; the first predicted usage data module includes:

[0152] A status information submodule, used to determine the used cabinet information and the remaining cabinet information as status information;

[0153] A behavior information submodule, for determining temperature difference, humidity difference, cabinet position and quantity as behavior information;

[0154] A construction submodule is used to construct a cluster scheduling Q function model according to the state information, behavior information and discount factor, obtain the first approximate eigenvalue and the second approximate eigenvalue of the cluster scheduling Q function model, and construct a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue;

[0155] A training submodule, used for iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model;

[0156] The first predicted usage data submodule is used to input the new temperature difference, humidity difference, cabinet position and quantity into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0157] Preferably, the behavior analysis module includes:

[0158] The arrangement submodule is used to arrange the user images in time sequence to obtain an image sequence;

[0159] A classification submodule, used for classifying the image sequence to obtain an action image sequence and a micro-expression image sequence;

[0160] A calculation submodule, used to calculate the emotion value for the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences;

[0161] The sample data submodule is used to obtain sample data of various user behaviors and corresponding fuzzy categories of stored items for the image sequence according to the emotion value.

[0162] Preferably, the training module includes:

[0163] A conversion submodule, used to convert the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature;

[0164] A calculation submodule, configured to calculate a correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screen out a specific user behavior feature whose correlation coefficient is lower than a preset threshold;

[0165] A conversion submodule, used to convert the specific user behavior feature into a user behavior vector;

[0166] The adjustment submodule is used to input the user behavior vector and the fuzzy category sample data of the stored items into the factor decomposition machine model, adjust the model parameters of the factor decomposition machine model, and obtain the trained factor decomposition machine model.

[0167] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0168] For the specific definition of the multifunctional integrated data control system of the intelligent storage cabinet, please refer to the definition of the multifunctional integrated data control method of the intelligent storage cabinet mentioned above, which will not be repeated here. Each module in the multifunctional integrated data control system of the above-mentioned intelligent storage cabinet can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0169] The multifunctional integrated data control system of the smart storage cabinet provided above can be used to execute the multifunctional integrated data control method of the smart storage cabinet provided in any of the above embodiments, and has corresponding functions and beneficial effects.

[0170] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a multifunctional integrated data control method for an intelligent storage cabinet is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0171] Those skilled in the art will understand that Figure 4The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0172] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0173] Acquire the combined temperature data and combined humidity data inside multiple adjacent cabinets;

[0174] The temperature difference and the humidity difference are calculated based on the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within the preset range of the intelligent storage cabinet;

[0175] Obtain the historical usage data of cabinet types within a preset time period;

[0176] A cluster scheduling Q function model is constructed based on the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data;

[0177] Obtaining user images taken outside the smart storage cabinet;

[0178] Performing user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0179] Inputting the user behavior and the fuzzy category sample data of stored items into the factorization machine model to obtain a trained factorization machine model;

[0180] Converting a new user image into a user behavior feature, and inputting the user behavior feature into a trained factorization machine model to obtain output second predicted usage data;

[0181] The first predicted usage data and the second predicted usage data are combined to obtain scheduling usage data of the smart storage cabinet.

[0182] Preferably, the obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes:

[0183] Obtain temperature and humidity data for each cabinet;

[0184] Calculate the temperature average of the temperature data of all selected cabinets, and determine the temperature average as the combined temperature data of the central cabinet;

[0185] The humidity mean value of the humidity data of all selected cabinets is calculated, and the humidity mean value is determined as the combined humidity data of the central cabinet.

[0186] Preferably, the cabinet historical usage data includes used cabinet information and remaining cabinet information; the cluster scheduling Q function model is constructed according to the cabinet historical usage data, temperature difference, humidity difference, cabinet position and quantity to obtain the first predicted usage data, including:

[0187] Determine the used cabinet information and the remaining cabinet information as the status information;

[0188] Determine temperature difference, humidity difference, cabinet location and quantity as behavioral information;

[0189] Constructing a cluster scheduling Q function model according to the state information, the behavior information and the discount factor, obtaining a first approximate eigenvalue and a second approximate eigenvalue of the cluster scheduling Q function model, and constructing a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue;

[0190] Iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model;

[0191] The new temperature difference, humidity difference, cabinet position and quantity are input into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0192] Preferably, the performing of user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data includes:

[0193] Arrange user images in time series to obtain an image sequence;

[0194] Classifying the image sequence to obtain an action image sequence and a micro-expression image sequence;

[0195] Calculating the emotion values ​​of the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences;

[0196] A variety of user behaviors and corresponding fuzzy category sample data of stored items are obtained for the image sequence according to the emotion value.

[0197] Preferably, the step of inputting the user behavior and the fuzzy category sample data of stored items into a factor decomposition machine model to obtain a trained factor decomposition machine model comprises:

[0198] Converting the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature;

[0199] Calculating the correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screening out specific user behavior features whose correlation coefficient is lower than a preset threshold;

[0200] Converting the specific user behavior feature into a user behavior vector;

[0201] The user behavior vector and the sample data of the fuzzy categories of stored items are input into the factor decomposition machine model, and the model parameters of the factor decomposition machine model are adjusted to obtain a trained factor decomposition machine model.

[0202] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0203] Acquire the combined temperature data and combined humidity data inside multiple adjacent cabinets;

[0204] The temperature difference and the humidity difference are calculated based on the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within the preset range of the intelligent storage cabinet;

[0205] Obtain the historical usage data of cabinet types within a preset time period;

[0206] A cluster scheduling Q function model is constructed based on the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data;

[0207] Obtaining user images taken outside the smart storage cabinet;

[0208] Performing user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data;

[0209] Inputting the user behavior and the fuzzy category sample data of stored items into the factorization machine model to obtain a trained factorization machine model;

[0210] Converting a new user image into a user behavior feature, and inputting the user behavior feature into a trained factorization machine model to obtain output second predicted usage data;

[0211] The first predicted usage data and the second predicted usage data are combined to obtain scheduling usage data of the smart storage cabinet.

[0212] Preferably, the obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes:

[0213] Obtain temperature and humidity data for each cabinet;

[0214] Calculate the temperature average of the temperature data of all selected cabinets, and determine the temperature average as the combined temperature data of the central cabinet;

[0215] The humidity mean value of the humidity data of all selected cabinets is calculated, and the humidity mean value is determined as the combined humidity data of the central cabinet.

[0216] Preferably, the cabinet historical usage data includes information about used cabinets and information about remaining cabinets; the cluster scheduling Q function model is constructed according to the cabinet historical usage data, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data, including

[0217] Determine the used cabinet information and the remaining cabinet information as the status information;

[0218] Determine temperature difference, humidity difference, cabinet location and quantity as behavioral information;

[0219] Constructing a cluster scheduling Q function model according to the state information, the behavior information and the discount factor, obtaining a first approximate eigenvalue and a second approximate eigenvalue of the cluster scheduling Q function model, and constructing a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue;

[0220] Iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model;

[0221] The new temperature difference, humidity difference, cabinet position and quantity are input into the trained cluster scheduling Q function model to obtain the first predicted usage data.

[0222] Preferably, the performing of user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data includes:

[0223] Arrange user images in time series to obtain an image sequence;

[0224] Classifying the image sequence to obtain an action image sequence and a micro-expression image sequence;

[0225] Calculating the emotion values ​​of the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences;

[0226] A variety of user behaviors and corresponding fuzzy category sample data of stored items are obtained for the image sequence according to the emotion value.

[0227] Preferably, the step of inputting the user behavior and the fuzzy category sample data of stored items into a factor decomposition machine model to obtain a trained factor decomposition machine model comprises:

[0228] Converting the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature;

[0229] Calculating the correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screening out specific user behavior features whose correlation coefficient is lower than a preset threshold;

[0230] Converting the specific user behavior feature into a user behavior vector;

[0231] The user behavior vector and the sample data of the fuzzy categories of stored items are input into the factor decomposition machine model, and the model parameters of the factor decomposition machine model are adjusted to obtain a trained factor decomposition machine model.

[0232] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0233] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0234] It will be appreciated by those skilled in the art that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0235] The embodiments of the present invention are described with reference to flowcharts and / or block diagrams of apparatuses, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0236] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction method, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0237] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0238] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0239] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, device, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the existence of other identical elements in the process, device, article or terminal device including the elements.

[0240] The multifunctional integrated data control method of a smart storage cabinet and a multifunctional integrated data control system of a smart storage cabinet, a computer device and a storage medium provided by the present invention are introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A multifunctional integrated data control method for an intelligent storage cabinet, characterized in that: Applied to a multifunctional integrated data control system, the multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, a single intelligent storage cabinet comprises a plurality of cabinet boxes arranged horizontally and vertically, a plurality of sensors are arranged inside the cabinet boxes, the sensors include temperature sensors and humidity sensors; including: Acquire the combined temperature data and combined humidity data inside multiple adjacent cabinets; The temperature difference and the humidity difference are calculated based on the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within the preset range of the intelligent storage cabinet; Obtain the historical usage data of cabinet types within a preset time period; A cluster scheduling Q function model is constructed based on the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data; Obtaining user images taken outside the smart storage cabinet; Performing user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data; Inputting the user behavior and the fuzzy category sample data of stored items into the factorization machine model to obtain a trained factorization machine model; Converting a new user image into a user behavior feature, and inputting the user behavior feature into a trained factorization machine model to obtain output second predicted usage data; The first predicted usage data and the second predicted usage data are combined to obtain scheduling usage data of the smart storage cabinet.

2. The method according to claim 1, characterized in that The obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes: Obtain temperature and humidity data for each cabinet; Calculate the temperature average of the temperature data of all selected cabinets, and determine the temperature average as the combined temperature data of the central cabinet; The humidity mean value of the humidity data of all selected cabinets is calculated, and the humidity mean value is determined as the combined humidity data of the central cabinet.

3. The method according to claim 1, characterized in that The cabinet historical usage data includes used cabinet information and remaining cabinet information; the cluster scheduling Q function model is constructed according to the cabinet historical usage data, temperature difference, humidity difference, cabinet position and quantity to obtain the first predicted usage data, including: Determine the used cabinet information and the remaining cabinet information as the status information; Determine temperature difference, humidity difference, cabinet location and quantity as behavioral information; Constructing a cluster scheduling Q function model according to the state information, the behavior information and the discount factor, obtaining a first approximate eigenvalue and a second approximate eigenvalue of the cluster scheduling Q function model, and constructing a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue; Iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model; The new temperature difference, humidity difference, cabinet position and quantity are input into the trained cluster scheduling Q function model to obtain the first predicted usage data.

4. The method according to claim 1, characterized in that: The user behavior analysis is performed according to the user image to obtain user behavior and stored item fuzzy category sample data, including: Arrange user images in time series to obtain an image sequence; Classifying the image sequence to obtain an action image sequence and a micro-expression image sequence; Calculating the emotion values ​​of the action image sequence and the micro-expression image sequence to obtain the emotion values ​​of different sequences; A variety of user behaviors and corresponding fuzzy category sample data of stored items are obtained for the image sequence according to the emotion value.

5. The method according to claim 1, characterized in that The step of inputting the user behavior and the fuzzy category sample data of the stored items into the factor decomposition machine model to obtain the trained factor decomposition machine model includes: Converting the user behavior into a user behavior feature, wherein the user behavior feature can be divided into a first distinguishing behavior feature and a second distinguishing behavior feature; Calculating the correlation coefficient between the first distinguishing behavior feature and the second distinguishing behavior feature, and screening out specific user behavior features whose correlation coefficient is lower than a preset threshold; Converting the specific user behavior feature into a user behavior vector; The user behavior vector and the sample data of the fuzzy categories of stored items are input into the factor decomposition machine model, and the model parameters of the factor decomposition machine model are adjusted to obtain a trained factor decomposition machine model.

6. A multifunctional integrated data control system for an intelligent storage cabinet, characterized in that: The multifunctional integrated data control system is connected to a plurality of intelligent storage cabinets, wherein a single intelligent storage cabinet comprises a plurality of cabinet boxes arranged horizontally and vertically, wherein a plurality of sensors are arranged inside the cabinet boxes, wherein the sensors include temperature sensors and humidity sensors; and A first acquisition module is used to acquire combined temperature data and combined humidity data inside a plurality of adjacent cabinets; A temperature difference and humidity difference module, used to calculate the temperature difference and humidity difference according to the combined temperature data and the combined humidity data and the ambient temperature data and the ambient humidity data within a preset range of the intelligent storage cabinet; The second acquisition module is used to acquire the historical usage data of cabinet types within a preset time period; The first predicted usage data module is used to construct a cluster scheduling Q function model according to the historical usage data of cabinet types, temperature difference, humidity difference, cabinet location and quantity to obtain the first predicted usage data; A user image module is used to obtain a user image taken outside the smart storage cabinet; A behavior analysis module, used to perform user behavior analysis based on the user image to obtain user behavior and stored item fuzzy category sample data; A training module, used for inputting the user behavior and the fuzzy category sample data of the stored items into the factor decomposition machine model to obtain a trained factor decomposition machine model; A second predicted usage data module is used to convert a new user image into a user behavior feature, and input the user behavior feature into a trained factor decomposition machine model to obtain output second predicted usage data; The scheduling and use module is used to combine the first predicted use data and the second predicted use data to obtain the scheduling and use data of the smart storage cabinet.

7. The system according to claim 6, characterized in that The obtaining of the combined temperature data and the combined humidity data inside the plurality of adjacent cabinets includes: The first acquisition submodule is used to acquire the temperature data and humidity data of each cabinet; A first calculation submodule, used for calculating a temperature mean of the temperature data of all selected cabinets, and determining the temperature mean as the combined temperature data of the central cabinet; The second calculation submodule is used to calculate the humidity mean value of the humidity data of all selected cabinets, and determine the humidity mean value as the combined humidity data of the central cabinet.

8. The system according to claim 6, characterized in that The cabinet historical usage data includes used cabinet information and remaining cabinet information; the first predicted usage data module includes: A status information submodule, used to determine the used cabinet information and the remaining cabinet information as status information; A behavior information submodule, for determining temperature difference, humidity difference, cabinet position and quantity as behavior information; A construction submodule is used to construct a cluster scheduling Q function model according to the state information, behavior information and discount factor, obtain the first approximate eigenvalue and the second approximate eigenvalue of the cluster scheduling Q function model, and construct a characteristic loss function according to the first approximate eigenvalue and the second approximate eigenvalue; A training submodule, used for iterating the feature loss function until the cluster scheduling Q function model converges to obtain a trained cluster scheduling Q function model; The first predicted usage data submodule is used to input the new temperature difference, humidity difference, cabinet position and quantity into the trained cluster scheduling Q function model to obtain the first predicted usage data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multifunctional integrated data control method of the intelligent storage cabinet described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multifunctional integrated data control method of the intelligent storage cabinet described in any one of claims 1 to 5 are implemented.

Images