Medical Supplies Warehouse Management Method and System Based on Cloud Computing and Radio Frequency Identification

Abstract

The present invention relates to the technical field of warehouse management, and discloses a medical supplies warehouse management method and system based on cloud computing and radio frequency identification. The method includes: performing signal dimensionality reduction projection on a radio frequency identification signal set read from a target warehouse to obtain a signal center; separating the radio frequency identification signal set according to the signal center to obtain separated signals, and calculating medical supplies data according to the separated signals; calculating the material warehouse data and medical supplies prediction data of the target warehouse according to the medical supplies data; constructing a warehouse optimization function according to the material warehouse data and the material prediction data; and performing material area allocation by using the warehouse optimization function to obtain a warehouse management strategy for the target warehouse. The present invention can improve the efficiency and accuracy of medical supplies warehouse management.

Description

Technical Field

[0001] The present invention relates to the field of warehouse management technology, and in particular to a medical material warehouse management method and system based on cloud computing and radio frequency identification. Background Art

[0002] With the rapid development of the medical industry, the types and quantities of medical supplies are increasing. Traditional warehousing management methods can no longer meet the high requirements of modern medical institutions for material management. For example, traditional management methods often rely on manual work such as material entry and exit registration and inventory. The workload is large and the efficiency is low, which is prone to human errors and inaccurate data.

[0003] In recent years, some advanced technologies have begun to be applied to the storage management of medical supplies. Radio Frequency Identification (RFID) technology, as an automatic identification technology, uses wireless radio frequency to perform non-contact two-way data communication, which can achieve fast and accurate object identification and data collection. It has begun to be widely used in material storage. However, the large amount of data read by the RFID reader in the existing technology needs to be effectively processed and analyzed to provide decision support. However, the current RFID system has limited data processing capabilities, which leads to delayed inventory data updates and difficulty in real-time monitoring of material dynamics, resulting in inventory redundancy or shortages. Therefore, how to improve the efficiency and accuracy of medical material storage management has become an urgent problem to be solved. Summary of the invention

[0004] The present invention provides a medical supplies warehouse management method and system based on cloud computing and radio frequency identification, the main purpose of which is to solve the problem of poor efficiency and accuracy of medical supplies warehouse management.

[0005] To achieve the above objectives, the present invention provides a medical supplies storage management method based on cloud computing and radio frequency identification, comprising:

[0006] Obtaining a set of radio frequency identification signals read by a target warehouse, and performing signal dimension reduction projection on the set of radio frequency identification signals to obtain a signal center;

[0007] Performing signal separation on the radio frequency identification signal set according to the signal center to obtain separated signals, and calculating medical material data corresponding to the radio frequency identification signal set according to the separated signals;

[0008] Calculating the material storage data and medical material forecast data of the target warehouse according to the medical material data;

[0009] Constructing a storage optimization function corresponding to the target warehouse according to the material storage data and the material forecast data;

[0010] Use the warehouse optimization function to perform material area allocation on the target warehouse to obtain the warehouse management strategy of the target warehouse.

[0011] Optionally, the signal dimensionality reduction projection of the RFID signal set to obtain the signal center includes:

[0012] Demodulate each signal in the RFID signal set to obtain a demodulated signal;

[0013] Perform principal component dimensionality reduction based on the signal sampling points in the demodulated signal to obtain a signal projection direction;

[0014] Perform signal projection on the demodulated signal according to the signal projection direction to obtain a projected signal point;

[0015] Perform interval partitioning on the projected signal points, and calculate the signal center according to the result of the interval partitioning.

[0016] Optionally, the signal separation of the RFID signal set according to the signal center to obtain a separated signal includes:

[0017] Calculate the Euclidean distance from each signal point in the RFID signal corresponding to the signal center to the signal center;

[0018] Classify the signal points according to the Euclidean distance to obtain classified signal points;

[0019] Construct the separated signal corresponding to the RFID signal according to the classified signal points.

[0020] Optionally, the calculation of the medical material data corresponding to the RFID signal set according to the separated signal includes:

[0021] Decode the separated signal to obtain a decoded signal;

[0022] Perform phase jump modulation on the decoded signal to obtain a target signal;

[0023] Identify the signal identifier corresponding to the RFID signal set according to the target signal, and count the medical material data according to the signal identifier.

[0024] Optionally, the calculation of the material storage data and medical material prediction data of the target warehouse according to the medical material data includes:

[0025] Classify the medical material data to obtain category material data;

[0026] Determine the material storage data according to the category material data, and extract the corresponding historical material data from a preset database;

[0027] Construct category data features based on the historical material data and the category material data;

[0028] Calculate the predicted data of each category of material data according to the category data features, and determine the medical material prediction data according to the predicted data.

[0029] Optionally, the constructing category data features according to the historical material data and the category material data includes:

[0030] Construct a periodic data sequence with a preset time span based on the historical material data and the category material data;

[0031] Calculate the periodic data vector sequence of the periodic data sequence, and perform vector splicing on the periodic data vector sequence to obtain a fusion feature vector;

[0032] Respectively obtain the data influencing factors corresponding to the periodic data sequence, and construct the influence feature vector of the data influencing factors;

[0033] Perform normalization processing and linear transformation on the influence feature vector to obtain the standard vector of the influence feature vector, and perform vector splicing according to the standard vector to obtain an influence fusion vector;

[0034] Perform feature fusion on the fusion feature vector and the influence fusion vector to obtain category data features;

[0035] Use the following formula to calculate the feature fusion of the fusion feature vector and the influence fusion vector:

[0036] Among them, represents the category data features, represents the activation function tanh, represents the fusion feature vector, represents the influence fusion vector, represents the sigmoid activation function, represents the symbol of element-wise multiplication.

[0037] Optionally, the constructing the warehousing optimization function corresponding to the target warehouse according to the material warehousing data and the material prediction data includes:

[0038] Obtain the material basic information of each category of material data in the material warehousing data;

[0039] Construct a material outbound time function and a warehousing stability function according to the material basic information;

[0040] Construct the warehousing optimization function corresponding to the target warehouse according to the material outbound time function and the warehousing stability function.

[0041] Optionally, constructing the material outbound time function and the warehousing stability function according to the basic information of the materials includes:

[0042] Construct the material outbound time function and the warehousing stability function using the following formula:

[0043] Where, represents the material outbound time function, represents the th column in the target warehouse, represents the total number of columns of the shelves in the target warehouse, represents the th row, represents the total number of rows of the shelves in the target warehouse, represents the th type of medical supplies, represents the total number of types of medical supplies, represents the time of outbound from the th column and the th row, represents a decision variable, which is 1 when the th type of medical supplies is stored in the th column and the th row, and 0 otherwise, represents the th type of medical supplies' usage frequency;

[0044] Where, represents the warehousing stability function, represents the th column in the target warehouse, represents the total number of columns of the shelves in the target warehouse, represents the th row, represents the total number of rows of the shelves in the target warehouse, represents the th type of medical supplies, represents the total number of types of medical supplies, The th type of medical supplies' weight, represents a decision variable, which is 1 when the th type of medical supplies is stored in the th column and the th row, and 0 otherwise.

[0045] Optionally, the material area allocation for the target warehouse using the warehousing optimization function includes:

[0046] Initialize the initial particle population, and use the warehousing optimization function as the objective function to calculate the objective function value of each particle in the initial particle population;

[0047] Update the velocity of the particles according to the objective function value to obtain particle velocities;

[0048] Update the velocity of the particles using the following formula:

[0049] where represents the particle velocity of the th particle at the th update iteration, represents the corresponding preset weight value of the th particle at the th time, , are the preset first influence factor and second influence factor respectively, , represent random numbers in the interval (0, 1), represents the individual historical best particle position of the th particle, represents the particle position of the th particle at the current moment, represents the global best position of the particle;

[0050] Update and iterate the particle population according to the particle velocity to obtain the target particle population;

[0051] Calculate the objective function value corresponding to each target particle in the target particle population, and determine the warehousing location according to the objective function value corresponding to the target particle;

[0052] Perform material area allocation according to the warehousing location to obtain the warehousing management strategy of the target warehouse.

[0053] To solve the above problems, the present invention also provides a medical material warehousing management system based on cloud computing and radio frequency identification. The system includes:

[0054] A signal center calculation module, configured to obtain a radio frequency identification signal set read by the target warehouse, and perform signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center;

[0055] A medical supplies data calculation module, configured to separate signals from the radio frequency identification signal set according to the signal center to obtain separated signals, and calculate medical supplies data corresponding to the radio frequency identification signal set according to the separated signals;

[0056] A target warehouse data calculation module, configured to calculate material storage data and medical supplies prediction data of the target warehouse according to the medical supplies data;

[0057] A storage optimization function construction module, configured to construct a storage optimization function corresponding to the target warehouse according to the material storage data and the material prediction data;

[0058] A storage management strategy generation module, configured to use the storage optimization function to perform material area allocation on the target warehouse to obtain a storage management strategy for the target warehouse.

[0059] In an embodiment of the present invention, by calculating the signal center of the radio frequency identification signal set, signal separation can be performed on the conflicting signals in the radio frequency identification signal set, improving the accuracy of subsequent signal tag calculations; calculating medical supplies data according to the separated signals can improve the accuracy of medical supplies data calculations; calculating the material storage data and medical supplies prediction data of the target warehouse according to the medical supplies data can comprehensively perform data prediction in combination with historical data and influencing factors; then calculating the storage optimization function and performing material area allocation according to the storage optimization function to obtain a storage management strategy for the target warehouse can minimize the outbound time of medical supplies and ensure the safety of medical supplies storage, effectively improving the efficiency and accuracy of medical supplies storage management. Therefore, the medical supplies storage management method and system based on cloud computing and radio frequency identification proposed by the present invention can solve the problem of poor efficiency and accuracy of medical supplies storage management. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flowchart of a medical supplies storage management method based on cloud computing and radio frequency identification provided by an embodiment of the present invention;

[0061] Figure 2 It is a flowchart of signal separation of a radio frequency identification signal set provided by an embodiment of the present invention;

[0062] Figure 3 It is a flowchart of calculating the material storage data and medical supplies prediction data of a target warehouse provided by an embodiment of the present invention;

[0063] Figure 4 It is a functional module diagram of a medical supplies storage management system based on cloud computing and radio frequency identification provided by an embodiment of the present invention.

[0064] The implementation, functional features and advantages of the present invention will be further described in conjunction with embodiments with reference to the accompanying drawings. Specific embodiments

[0065] 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.

[0066] The embodiments of the present application provide a medical supplies warehouse management method based on cloud computing and radio frequency identification. The execution subject of the medical supplies warehouse management method based on cloud computing and radio frequency identification includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiments of the present application. In other words, the medical supplies warehouse management method based on cloud computing and radio frequency identification can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms.

[0067] Refer to Figure 1 As shown, it is a flowchart of a medical supplies warehouse management method based on cloud computing and radio frequency identification provided by an embodiment of the present invention. In this embodiment, the medical supplies warehouse management method based on cloud computing and radio frequency identification includes:

[0068] S1. Obtain the radio frequency identification signal set read by the target warehouse, and perform signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center.

[0069] In the embodiment of the present invention, the radio frequency identification signal set is a signal set collected by signal tags on medical supplies read by a reader. However, there may be a problem that a reader reads signals on multiple tags at the same time, which is likely to cause information aliasing to form conflict signals. Therefore, it is necessary to calculate the signal center to perform signal separation by clustering the radio frequency identification signal set and identify the information corresponding to each signal in the radio frequency identification signal set.

[0070] In the embodiment of the present invention, the performing signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center includes:

[0071] Demodulate each signal in the radio frequency identification signal set to obtain a demodulated signal;

[0072] Perform principal component dimensionality reduction according to the signal sampling points in the demodulated signal to obtain a signal projection direction;

[0073] Perform signal projection on the demodulated signal according to the signal projection direction to obtain projection signal points;

[0074] Perform interval division on the projection signal points, and calculate the signal center according to the result of the interval division.

[0075] In the embodiment of the present invention, signal demodulation is to perform IQ modulation on the radio frequency identification signal set. During the IQ modulation process, the radio frequency identification signal set is divided into two paths of signals, which are respectively called the in-phase component (I) and the quadrature component (Q). These two paths of signals are multiplied by two orthogonal carriers (usually cosine and sine waves) and then added together to obtain the demodulated signal.

[0076] Further, the signal points after demodulation are composed of the I component and the Q component. Then, the I component and the Q component of the signal points are used as data points to construct a data matrix. Furthermore, principal component dimensionality reduction is performed on the signal sampling points in the demodulated signal to obtain eigenvalues. The eigenvector corresponding to the largest eigenvalue is used as the new signal projection direction. Then, the dot product operation is performed between each sampling point and the signal projection direction to obtain the projection signal points after dimensionality reduction, which can reduce the dimensionality of the data while retaining the main features of the data.

[0077] Specifically, the projection signal points are divided into several finite equally spaced intervals. Then, the projection signal points in each interval are statistically analyzed to draw a cluster diagram. The local peaks of each cluster are the signal centers of each cluster. Thus, the signal centers can be used to separate the conflicting signals in the radio frequency identification signal set, improving the accuracy of subsequent signal label calculation.

[0078] S2. Perform signal separation on the radio frequency identification signal set according to the signal center to obtain separated signals, and calculate the medical supplies data corresponding to the radio frequency identification signal set according to the separated signals.

[0079] In the embodiment of the present invention, signal separation is to separate the signal points in the conflicting signals in the radio frequency identification signal set. It is necessary for each cluster center to correspond to each signal label state one by one to complete the signal separation.

[0080] Specifically, referring to Figure 2 As shown, the performing signal separation on the radio frequency identification signal set according to the signal center to obtain separated signals includes:

[0081] S21. Calculate the Euclidean distance from each signal point in the radio frequency identification signal corresponding to the signal center to the signal center;

[0082] S22. Classify the signal points according to the Euclidean distance to obtain classified signal points;

[0083] S23. Construct the separated signal corresponding to the radio frequency identification signal according to the classified signal points.

[0084] Specifically, after signal demodulation, there are signal centers corresponding to the collision signal, where is the number of signals included in the collision signal. For example, the collision signal generated by two tag signals has four signal centers. Then, each signal point is assigned to the corresponding clustering center according to the distance, and then corresponding classification is performed using a preset signal attenuation complex coefficient to obtain classified signal points, and further a separated signal is constructed.

[0085] Specifically, each signal tag has a corresponding attenuation complex coefficient, and at the same time, each signal tag contains a same known signal for identification, so that the signal points corresponding to different signal centers can be corresponded to obtain classified signal points corresponding to different tag signals.

[0086] In an embodiment of the present invention, the calculating the medical supplies data corresponding to the radio frequency identification signal set according to the separated signal includes:

[0087] Performing signal decoding on the separated signal to obtain a decoded signal;

[0088] Performing phase jump modulation on the decoded signal to obtain a target signal;

[0089] Identifying the signal identifier corresponding to the radio frequency identification signal set according to the target signal, and counting the medical supplies data according to the signal identifier.

[0090] In an embodiment of the present invention, signal decoding is to decode the separated signal using a matched filter. When the signal is transmitted through a channel and may be interfered by noise, the matched filter can help extract the information of the original signal from the noise, thereby improving the signal-to-noise ratio of the separated signal.

[0091] Specifically, the matched filter uses the conjugate mirror image of the separated signal as the impulse response, and performs a convolution operation on the impulse response and the separated signal to obtain a decoded signal.

[0092] Specifically, the signal identifier is the detailed information of the material, including the name, specification, etc., so that medical supplies such as syringes, infusion sets, dressings, or other tissue articles and medical devices can be identified, the medical supplies corresponding to each signal are obtained, and the quantity of the same category of materials is counted to obtain the medical supplies data.

[0093] Furthermore, phase jump modulation transmits information by changing the phase of a signal according to the phase jump principle. The original information needs to be restored according to the phase jump pattern. For example, in a radio frequency signal coding scheme, a specific phase jump pattern corresponds to a specific bit sequence. When decoding, the transmitted signal is determined by detecting these phase jump patterns. Therefore, the signal identifier corresponding to the target signal can be identified, and the medical supply data of different categories can be counted through the signal identifier to obtain the medical supply data.

[0094] In the embodiments of the present invention, by separating signals to calculate the medical supply data corresponding to the radio frequency identification signal set, the identification error caused by conflicting signals can be avoided, thereby effectively improving the accuracy of calculating the medical supply data.

[0095] S3. Calculate the material storage data and medical supply prediction data of the target warehouse according to the medical supply data.

[0096] In the embodiments of the present invention, the material storage data is the data of different categories of materials that have been warehoused in the target warehouse, including the materials to be warehoused in the medical supply data and the material data already stored in the target warehouse, etc., including the quantity and the storage area in the target warehouse, etc. The medical supply prediction data is the data that the medical supplies may be warehoused in the future for a period of time.

[0097] In the embodiments of the present invention, refer to Figure 3 As shown, calculating the material storage data and medical supply prediction data of the target warehouse according to the medical supply data includes:

[0098] S31. Classify the medical supply data to obtain category material data;

[0099] S32. Determine the material storage data according to the category material data, and extract the corresponding historical material data from a preset database;

[0100] S33. Construct category data features according to the historical material data and the category material data;

[0101] S34. Calculate the prediction data of each category material data according to the category data features, and determine the medical supply prediction data according to the prediction data.

[0102] In the embodiments of the present invention, classify according to the categories of medical supplies, and extract the material storage data of each category of medical supplies in the target warehouse by using a preset database. The database is a data storage medium for recording the medical supply data in the target warehouse. Through the database, the storage data of each medical supply in the target warehouse can be obtained, including the data stored in different time periods.

[0103] Specifically, constructing the category data features based on the historical material data and the category material data includes:

[0104] Constructing a periodic data sequence according to the historical material data and the category material data by using a preset time span;

[0105] Calculating a periodic data vector sequence of the periodic data sequence, and performing vector splicing on the periodic data vector sequence to obtain a fusion feature vector;

[0106] Respectively obtaining data influencing factors corresponding to the periodic data sequence, and constructing an influence feature vector of the data influencing factors;

[0107] Performing normalization processing and linear transformation on the influence feature vector to obtain a standard vector of the influence feature vector, and performing vector splicing according to the standard vector to obtain an influence fusion vector;

[0108] Performing feature fusion on the fusion feature vector and the influence fusion vector to obtain category data features.

[0109] Further, the following formula is used to calculate the feature fusion of the fusion feature vector and the influence fusion vector:

[0110] Wherein, represents the category data features, represents the activation function tanh, represents the fusion feature vector, represents the influence fusion vector, represents the sigmoid activation function, represents the symbol of element-wise multiplication.

[0111] In the embodiment of the present invention, the historical material data and the category material data are sorted according to the generation time and then a periodic data sequence is constructed by using a preset time span, and each periodic data in the periodic data sequence is converted into a data vector to obtain a periodic data vector sequence. For example, a periodic data sequence is constructed according to a weekly time span, a monthly periodic data sequence or a quarterly periodic data sequence, etc., and the demand for analogous material data in different span periods is reflected through the periodic data sequence to more finely predict the material demand.

[0112] In the embodiment of the present invention, the data influencing factors are factors that affect the demand for medical supplies at different times. For example, holidays, flu seasons, sudden medical rescues, etc. Under different data influencing factors, the demand for different medical supplies is different, and the category material data is also different. Therefore, by fusing the data influencing factors to construct the category data features of different medical supplies, the calculation data of medical supplies can be calculated more accurately.

[0113] Specifically, a pre-constructed fully connected layer can be used to perform activation operations on the category data features, map the category data features to the corresponding predicted demand vector space, obtain the probabilities corresponding to each predicted demand, select the maximum probability as the predicted data corresponding to each category of material data, and collect the predicted data corresponding to each category of material data to obtain the medical material prediction data.

[0114] In the embodiment of the present invention, by comprehensively calculating the predicted data based on the data influencing factors and different categories of material data, it is possible to comprehensively perform data prediction in combination with historical data and influencing factors, improving the calculation accuracy of the medical material prediction data.

[0115] S4. Construct a storage optimization function corresponding to the target warehouse according to the material storage data and the material prediction data.

[0116] In the embodiment of the present invention, since the usage requirements and material specifications of different medical materials are different, it is necessary to scientifically store medical materials and reasonably utilize the storage space of the target warehouse. For example, medical materials with high usage frequency are placed near the exit, and those with low usage frequency are placed far from the exit; materials with large mass are placed on the lower layer, and those with small mass are placed on the upper layer; large medical materials are placed on the lower layer, and small medical materials are placed on the upper layer; medical materials with high correlation should be stored as close as possible to adjacent positions, etc., to improve the efficiency of medical material storage.

[0117] In the embodiment of the present invention, the constructing the storage optimization function corresponding to the target warehouse according to the material storage data and the material prediction data includes:

[0118] Obtain the material basic information of each category of material data in the material storage data;

[0119] Construct a material outbound time function and a storage stability function according to the material basic information;

[0120] Construct the storage optimization function corresponding to the target warehouse according to the material outbound time function and the storage stability function.

[0121] In the embodiment of the present invention, the material basic information is the medical material parameter information corresponding to different categories of material data, including weight, the size of the material specifications, and the usage frequency of medical materials, etc.

[0122] Specifically, the target warehouse may include multi-layer and multi-column shelves. Assuming that the ground layer is the first layer and the column closest to the exit is the first column, according to the principle of outbound from the nearest location and accelerating turnover, construct a material outbound time function for the handling time of medical materials in each area of the target warehouse.

[0123] Specifically, the material outbound time function is expressed as:

[0124] Among them, represents the function of the material outbound time, represents the th column, represents the total number of columns of the shelves in the target warehouse, represents the th row, represents the total number of rows of the shelves in the target warehouse, represents the th type of medical supplies, represents the total number of categories of medical supplies, represents the outbound time starting from the th column and the th row, represents the decision variable, which is 1 when the th type of medical supplies is stored in the th column and the th row, and 0 otherwise, represents the th type of medical supplies' usage frequency.

[0125] Furthermore, according to the principle of lighter on top and heavier on the bottom, the warehousing stability function is expressed as the sum of the product of the mass of the medical supplies on each shelf and the layer where it is located.

[0126] Specifically, the warehousing stability function is expressed as:

[0127] Among them, represents the warehousing stability function, represents the th column in the target warehouse, represents the total number of columns of the shelves in the target warehouse, represents the th row in the target warehouse, represents the total number of rows of the shelves in the target warehouse, represents the th type of medical supplies, represents the total number of categories of medical supplies, The th type of medical supplies' weight, represents the decision variable, which is 1 when the th type of medical supplies is stored in the th column and the th row, and 0 otherwise.

[0128] In the embodiment of the present invention, each material outbound time function and the warehousing stability function are weighted and summed to obtain an objective function, and an optimization function is constructed with the minimum value of the objective function as the optimization target, so as to obtain a warehousing optimization function.

[0129] In the embodiment of the present invention, by comprehensively considering the basic information of medical supplies and the warehousing of the target warehouse to construct an optimization function, the warehousing of medical supplies can be optimized on the basis of the minimum outbound time and the storage safety of materials, thereby improving the effect of medical supplies warehousing.

[0130] S5. Use the warehousing optimization function to allocate material areas in the target warehouse to obtain a warehousing management strategy for the target warehouse.

[0131] In the embodiment of the present invention, material area allocation is to calculate which area of the target warehouse each category of medical supplies should be stored in, so as to maximize the use of the warehousing conditions of the target warehouse and ensure the maximum efficiency of medical supplies during warehousing and use.

[0132] In the embodiment of the present invention, the use of the warehousing optimization function to allocate material areas in the target warehouse includes:

[0133] Initialize an initial particle population, and use the warehousing optimization function as the objective function to calculate the objective function value of each particle in the initial particle population;

[0134] Update the velocity of the particles according to the objective function value to obtain particle velocities;

[0135] Update and iterate the particle population according to the particle velocities to obtain a target particle population;

[0136] Calculate the objective function value corresponding to each target particle in the target particle population, and determine the warehousing location according to the objective function value corresponding to the target particle;

[0137] Allocate material areas according to the warehousing location to obtain a warehousing management strategy for the target warehouse.

[0138] In the embodiment of the present invention, each particle in the initial particle population represents a different scenario for storing medical supplies in the target warehouse. Furthermore, the function corresponding to the warehousing optimization function corresponding to each particle can be calculated to obtain the objective function value.

[0139] Further, the updating the velocity of the particles according to the objective function value to obtain particle velocities includes:

[0140] Update the velocity of the particles using the following formula:

[0141] Where represents the particle velocity of the -th particle at the -th update iteration. represents the preset weight value corresponding to the -th particle at the -th time. and are respectively the preset first influence factor and second influence factor. and represent random numbers in the interval (0, 1). represents the individual historical optimal particle position of the -th particle. represents the particle position of the -th particle at the current moment. represents the global optimal position of the particle.

[0142] Furthermore, the particle positions of each particle are updated according to the particle velocity to obtain an updated particle population. Until the number of update iterations is greater than the preset number threshold, a target particle population is obtained. The function values of the storage optimization function of each particle in the target particle population are calculated to obtain target function values. The storage positions of each medical supply corresponding to the particle corresponding to the minimum target function value are used as the final storage positions.

[0143] Specifically, the storage space required for each category of medical supplies is calculated according to the basic information of the medical supplies, the material storage data, and the material prediction data of each category of medical supplies. Then, the target warehouse is divided into regions according to the storage positions to obtain the material regions corresponding to each category of medical supplies, and then a storage management strategy for the target warehouse is generated.

[0144] Preferably, since the medical supplies in the material prediction data have not been warehoused and the medical supplies in the target warehouse are being used in real time, in actual applications, the storage space may not need to meet the space required by all the material storage data and material prediction data, further improving the utilization rate of the target warehouse.

[0145] In the embodiments of the present invention, by managing the medical supplies in the target warehouse through the storage management strategy, the outbound time of the medical supplies can be minimized and the safety of the storage of the medical supplies can be ensured. Therefore, the efficiency and accuracy of the storage management of medical supplies can be effectively improved.

[0146] As Figure 4 shown, it is a functional module diagram of a medical supply storage management system based on cloud computing and radio frequency identification provided by an embodiment of the present invention.

[0147] The medical supplies warehousing management system 400 based on cloud computing and radio frequency identification according to the present invention can be installed in an electronic device. According to the functions implemented, the medical supplies warehousing management system 400 based on cloud computing and radio frequency identification can include a signal center calculation module 401, a medical supplies data calculation module 402, a target warehouse data calculation module 403, a warehousing optimization function construction module 404, and a warehousing management strategy generation module 405. The modules in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, and are stored in the memory of the electronic device.

[0148] In this embodiment, the functions of each module / unit are as follows:

[0149] The signal center calculation module 401 is configured to obtain a radio frequency identification signal set read by a target warehouse, perform signal dimensionality reduction projection on the radio frequency identification signal set, and obtain a signal center;

[0150] The medical supplies data calculation module 402 is configured to separate the radio frequency identification signal set according to the signal center to obtain a separated signal, and calculate medical supplies data corresponding to the radio frequency identification signal set according to the separated signal;

[0151] The target warehouse data calculation module 403 is configured to calculate the material warehousing data and medical supplies prediction data of the target warehouse according to the medical supplies data;

[0152] The warehousing optimization function construction module 404 is configured to construct a warehousing optimization function corresponding to the target warehouse according to the material warehousing data and the material prediction data;

[0153] The warehousing management strategy generation module 405 is configured to use the warehousing optimization function to perform material area allocation on the target warehouse to obtain a warehousing management strategy for the target warehouse.

[0154] Specifically, each module in the medical supplies warehousing management system 400 based on cloud computing and radio frequency identification in the embodiment of the present invention adopts the same technical means as those in the above Figures 1 to 3 and can produce the same technical effects, which will not be elaborated here.

[0155] The present invention also provides an electronic device, which may include a processor, a memory, a communication bus, and a communication interface, and may further include a computer program stored in the memory and executable on the processor, such as a medical supplies warehousing management method program based on cloud computing and radio frequency identification.

[0156] Among them, in some embodiments, the processor may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc.

[0157] The memory at least includes one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), magnetic memories, magnetic disks, optical discs, etc. In some embodiments, the memory may be an internal storage unit of the electronic device, such as the mobile hard disk of the electronic device.

[0158] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. The bus is set to realize the connection and communication between the memory and at least one processor, etc.

[0159] The communication interface is used for the communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is usually used to establish a communication connection between this electronic device and other electronic devices. The user interface may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface.

[0160] Only the electronic device with components is shown in the figure. Those skilled in the art can understand that the structure shown in the figure does not constitute a limitation on the electronic device, and it may include fewer or more components than shown in the figure, or combine some components, or have different component arrangements.

[0161] Specifically, for the specific implementation method of the above instructions by the processor, reference may be made to the description of the relevant steps in the corresponding embodiments of the attached drawings, which will not be elaborated here.

[0162] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation.

[0163] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0164] In addition, in each embodiment of the present invention, the functional modules can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a hardware plus software functional module.

[0165] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0166] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

[0167] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0168] In addition, obviously, the word "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units or systems stated in the system claims can also be implemented by one unit or system through software or hardware. Words such as first and second are used to indicate names and do not indicate any specific order.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A medical supplies warehousing management method based on cloud computing and radio frequency identification, characterized in that, The method includes: Obtaining a radio frequency identification signal set read from a target warehouse, and performing signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center; wherein, performing signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center includes: demodulating each signal in the radio frequency identification signal set to obtain a demodulated signal; performing principal component dimensionality reduction according to signal sampling points in the demodulated signal to obtain a signal projection direction; performing signal projection on the demodulated signal according to the signal projection direction to obtain a projected signal point; performing interval division on the projected signal points, and calculating the signal center according to the result of the interval division; Separating the radio frequency identification signal set according to the signal center to obtain a separated signal, and calculating medical supply data corresponding to the radio frequency identification signal set according to the separated signal; wherein, separating the radio frequency identification signal set according to the signal center to obtain a separated signal includes: calculating the Euclidean distance from each signal point in the radio frequency identification signal corresponding to the signal center to the signal center; classifying the signal points according to the Euclidean distance to obtain classified signal points; constructing a separated signal corresponding to the radio frequency identification signal according to the classified signal points; Calculating material storage data and medical supply prediction data of the target warehouse according to the medical supply data; Constructing a storage optimization function corresponding to the target warehouse according to the material storage data and the material prediction data; Using the storage optimization function to perform material area allocation on the target warehouse to obtain a storage management strategy of the target warehouse.

2. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 1, characterized in that The calculating the medical supply data corresponding to the radio frequency identification signal set according to the separated signal includes: Decoding the separated signal to obtain a decoded signal; Performing phase jump modulation on the decoded signal to obtain a target signal; Identifying a signal identifier corresponding to the radio frequency identification signal set according to the target signal, and counting the medical supply data according to the signal identifier.

3. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 1, characterized in that, The calculating the material storage data and the medical supply prediction data of the target warehouse according to the medical supply data includes: Classifying the medical supply data to obtain category material data; Determining the material storage data according to the category material data, and extracting corresponding historical material data from a preset database; Constructing category data features according to the historical material data and the category material data; Calculating prediction data of each category material data according to the category data features, and determining the medical supply prediction data according to the prediction data.

4. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 3, characterized in that, The constructing category data features according to the historical material data and the category material data includes: Constructing a periodic data sequence with a preset time span according to the historical material data and the category material data; Calculating a periodic data vector sequence of the periodic data sequence, and performing vector splicing on the periodic data vector sequence to obtain a fused feature vector; Respectively obtaining data influencing factors corresponding to the periodic data sequence, and constructing an influencing feature vector of the data influencing factors; Normalize and linearly transform the influence feature vector to obtain the standard vector of the influence feature vector, and perform vector splicing according to the standard vector to obtain the influence fusion vector; Perform feature fusion on the fusion feature vector and the influence fusion vector to obtain the category data feature; Use the following formula to calculate the feature fusion of the fusion feature vector and the influence fusion vector: Among them, represents the categorical data feature, represents the activation function tanh, represents the fused feature vector, represents the influencing fusion vector, represents the sigmoid activation function, represents the symbol for element-wise multiplication.

5. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 1, characterized in that, The construction of the warehousing optimization function corresponding to the target warehouse according to the material warehousing data and the material prediction data includes: Obtain the material basic information of each category of material data in the material warehousing data; Construct a material outbound time function and a warehousing stability function according to the material basic information; Construct the warehousing optimization function corresponding to the target warehouse according to the material outbound time function and the warehousing stability function.

6. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 5, characterized in that The construction of the material outbound time function and the warehousing stability function according to the material basic information includes: Use the following formula to construct the material outbound time function and the warehousing stability function: Among them, represents the function of the material out - warehouse time, represents the th column, represents the total number of columns of the shelves in the target warehouse, represents the th row, represents the total number of rows of the shelves in the target warehouse, represents the th type of medical supplies, represents the total number of categories of medical supplies, represents the time of out - warehouse starting from the th column and the th row, represents the decision variable, which is 1 when the th type of medical supplies is stored in the th column and the th row, and 0 otherwise, represents the th type of medical supplies' usage frequency; Among them, represents the storage stability function, represents the th column in the target warehouse, represents the total number of columns of the shelves in the target warehouse, represents the th row, represents the total number of rows of the shelves in the target warehouse, represents the th category of medical supplies, represents the total number of categories of medical supplies, The th category of medical supplies' weight, represents a decision variable, which is 1 when the th category of medical supplies is stored in the th column and the th row, and 0 otherwise.

7. The medical supplies warehousing management method based on cloud computing and radio frequency identification according to claim 1, characterized in that The use of the warehousing optimization function to perform material area allocation for the target warehouse includes: Initialize the initial particle population, and use the warehousing optimization function as the objective function to calculate the objective function value of each particle in the initial particle population; Update the velocity of the particles according to the objective function value to obtain the particle velocity; Use the following formula to update the velocity of the particles: Among them, represents the particle velocity of the -th particle at the -th update iteration. represents the -th particle's corresponding preset weight value at the -th time. and are respectively the preset first influence factor and second influence factor. and represent random numbers within the interval (0, 1). represents the individual historical best particle position of the -th particle. represents the particle position of the -th particle at the current moment. represents the global best position of the particle. Update and iterate the particle population according to the particle velocity to obtain the target particle population; Calculate the objective function value corresponding to each target particle in the target particle population, and determine the warehousing location according to the objective function value corresponding to the target particle; Perform material area allocation according to the warehousing location to obtain the warehousing management strategy of the target warehouse.

8. A medical supplies warehousing management system based on cloud computing and radio frequency identification, characterized in that, The system includes: A signal center calculation module, configured to obtain a radio frequency identification signal set read by a target warehouse, and perform signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center; wherein, the performing signal dimensionality reduction projection on the radio frequency identification signal set to obtain a signal center includes: demodulating each signal in the radio frequency identification signal set to obtain a demodulated signal; performing principal component dimensionality reduction according to the signal sampling points in the demodulated signal to obtain a signal projection direction; performing signal projection on the demodulated signal according to the signal projection direction to obtain a projection signal point; performing interval division on the projection signal point, and calculating the signal center according to the result of the interval division; A medical material data calculation module, configured to separate the radio frequency identification signal set according to the signal center to obtain a separated signal, and calculate the medical material data corresponding to the radio frequency identification signal set according to the separated signal; wherein, the separating the radio frequency identification signal set according to the signal center to obtain a separated signal includes: calculating the Euclidean distance from each signal point in the radio frequency identification signal corresponding to the signal center to the signal center; classifying the signal points according to the Euclidean distance to obtain classified signal points; constructing the separated signal corresponding to the radio frequency identification signal according to the classified signal points; The target warehouse data calculation module is used to calculate the material storage data and medical supplies prediction data of the target warehouse according to the medical supplies data; The storage optimization function construction module is used to construct the storage optimization function corresponding to the target warehouse according to the material storage data and the material prediction data; The storage management strategy generation module is used to perform material area allocation on the target warehouse by using the storage optimization function to obtain the storage management strategy of the target warehouse.

Images