Intelligent supply chain optimization and management system and method based on artificial intelligence

Abstract

The invention provides a supply chain intelligent optimization and management system and method based on artificial intelligence, and the method comprises the steps: obtaining a historical storage data set of a target fresh food supply chain platform, determining a plurality of storage data nodes according to the historical storage data set, converting all storage data nodes into a storage data node sequence, and storing the storage data node sequence in a database; determining the local responsivity of each storage data node in the storage data node sequence, determining a storage confluence decision domain through all the local responsivity, and further determining a confluence characteristic value of the storage confluence decision domain; and according to the confluence characteristic value and the local responsivity of all the storage data nodes, determining an abnormal monitoring definition quantity of a target fresh food supply chain platform, so that monitoring and early warning are performed on the target fresh food supply chain platform through the abnormal monitoring definition quantity, namely, storage confluence early warning of the semi-vacant warehouse is realized.

Description

Technical Field

[0001] The present application relates to the field of big data supply chain technology, and more specifically, to an artificial intelligence-based supply chain intelligent optimization and management system and method. Background Art

[0002] Supply chain technology is a field that covers information technology and management methods, focusing on optimizing, coordinating and improving the entire process of products or services from suppliers to end customers. These technologies cover logistics, inventory management, production planning, demand forecasting, supplier relationship management and data analysis, aiming to improve efficiency, reduce costs, increase visibility, reduce risks, and adapt to rapidly changing market demands, so that enterprises can be more competitive.

[0003] The monitoring of the big data supply chain platform is based on data analysis and integration technology to fully understand, track and optimize the entire supply chain ecosystem to ensure the smooth operation of the supply chain process. However, in the existing fresh food supply chain platform, semi-empty warehouses will cause storage confluence in the fresh food supply chain. Specifically, storage confluence refers to the situation where fresh products from other warehouses in the fresh food supply chain platform are stored in the same semi-empty warehouse at the same time, which requires the semi-empty warehouse to process a large amount of fresh products in a short period of time, resulting in poor circulation of the supply chain. Therefore, how to achieve storage confluence warning for semi-empty warehouses has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an artificial intelligence-based supply chain intelligent optimization and management system and method, which can realize warehouse convergence early warning for semi-vacant warehouses.

[0005] In a first aspect, the present application provides a supply chain management method based on artificial intelligence, comprising the following steps: Obtain the historical storage data set of the target fresh food supply chain platform; Determine a plurality of storage data nodes according to the historical storage data set, and convert all the storage data nodes into a storage data node sequence; Determine the local responsiveness of each storage data node in the storage data node sequence, and determine the storage confluence decision domain through all the local responsiveness; Determine the confluence characteristic value of the warehouse confluence decision domain, and determine the abnormal monitoring limit of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all warehouse data nodes; The target fresh food supply chain platform is monitored and warned through the abnormal monitoring definition quantity.

[0006] In some embodiments, converting all storage data nodes into a storage data node sequence specifically includes: Determine the multiple time scales of each storage data node; The storage data node sequence is determined according to the multiple time scales of all the storage data nodes.

[0007] In some embodiments, determining the storage confluence decision domain through all local responsiveness specifically includes: All local responsiveness is smoothed to obtain the storage measurement smoothed sequence; The storage confluence decision domain is determined according to the storage measurement smoothing sequence.

[0008] In some embodiments, all local responsiveness are smoothed to obtain a storage measurement smoothing sequence, specifically including: Determining a scaling and smoothing eigenvalue for each local responsivity; Determine the storage measure damping sequence based on all scaled damped eigenvalues.

[0009] In some embodiments, determining the scaling and smoothing characteristic value of each local responsiveness specifically includes: Select a local responsivity; Scaling the local responsiveness to obtain a measurement scaling value of the local responsiveness; The storage distant neighbor distance of the storage data node corresponding to the local responsiveness is smoothed by using the measurement scaling value of the local responsiveness to obtain the scaled and smoothed characteristic value of the local responsiveness.

[0010] Repeat the above steps to obtain the scaling and smoothing eigenvalue of the remaining local responsiveness.

[0011] In some embodiments, determining the confluence characteristic value of the storage confluence decision domain specifically includes: Determining a confluence coefficient of the storage confluence decision domain; Get all local responsivities; Get all multiple time scales; The confluence characteristic value of the storage confluence decision domain is determined according to all local responsiveness, all multiple time scales and the confluence coefficient.

[0012] In some embodiments, the historical warehouse data set includes the location of each semi-vacant warehouse, the remaining inventory capacity of each semi-vacant warehouse, and the timestamp of each semi-vacant warehouse storing various fresh products.

[0013] In a second aspect, the present application provides a supply chain management system based on artificial intelligence, comprising: The acquisition module is used to obtain the historical storage data set of the target fresh food supply chain platform; A processing module, used to determine a plurality of storage data nodes according to the historical storage data set, and convert all the storage data nodes into a storage data node sequence; The processing module is further used to determine the local responsiveness of each storage data node in the storage data node sequence; The processing module is further used to determine the storage confluence decision domain through all local responsiveness, and then determine the confluence characteristic value of the storage confluence decision domain; The processing module is further used to determine the abnormal monitoring limit value of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all storage data nodes; The execution module is used to monitor and warn the target fresh food supply chain platform through the abnormal monitoring definition quantity.

[0014] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned artificial intelligence-based supply chain management method.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned artificial intelligence-based supply chain management method.

[0016] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: In the artificial intelligence-based supply chain management method and system provided by the present application, first, a warehouse data node sequence for measuring the busyness of a semi-vacant warehouse is determined based on the historical warehouse data set, and the warehouse data node sequence can perform feature calibration on a semi-vacant warehouse where a warehouse convergence occurs. Secondly, the local responsiveness of each warehouse data node in the warehouse data node sequence is determined. The local responsiveness reflects the response speed of the semi-vacant warehouse corresponding to different warehouse data nodes to the possible occurrence of a warehouse convergence. The local responsiveness can be used to preliminarily judge the abnormal situation of the semi-vacant warehouse. Then, all the local responses are used to The storage convergence decision domain that limits the range of abnormal semi-vacant warehouses is determined, which can improve the monitoring efficiency of abnormal semi-vacant warehouses, and then the convergence characteristic value of the storage convergence decision domain is further determined. The convergence characteristic value can be used to measure the degree to which abnormal semi-vacant warehouses in the storage convergence decision domain can interact with each other to enhance the storage convergence. Finally, the abnormal monitoring limit of the target fresh food supply chain platform is determined according to the convergence characteristic value and the local responsiveness of all storage data nodes, so that the target fresh food supply chain platform is monitored and warned through the abnormal monitoring limit, that is, the storage convergence warning of the semi-vacant warehouses is realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is an exemplary flow chart of a supply chain management method based on artificial intelligence according to some embodiments of the present application; Figure 2 is a schematic diagram of a process for determining the local responsiveness of each storage data node in the storage data node sequence in some embodiments of the present application; Figure 3 is a schematic diagram of a flow chart of determining the confluence characteristic value of the storage confluence decision domain in some embodiments of the present application; Figure 4 is a structural block diagram of a supply chain management system based on artificial intelligence in some embodiments of the present application; Figure 5 It is a structural diagram of a computer device for implementing an artificial intelligence-based supply chain management method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] The core of this application is to obtain a historical warehouse data set of the target fresh food supply chain platform, and then determine multiple warehouse data nodes based on the historical warehouse data set, convert all the warehouse data nodes into a warehouse data node sequence, so as to determine the local responsiveness of each warehouse data node in the warehouse data node sequence, determine the warehouse convergence decision domain through all the local responsiveness, further determine the convergence characteristic value of the warehouse convergence decision domain, and then determine the abnormal monitoring limit of the target fresh food supply chain platform according to the convergence characteristic value and the local responsiveness of all warehouse data nodes, so as to monitor and warn the target fresh food supply chain platform through the abnormal monitoring limit, that is, to realize the warehouse convergence warning for semi-vacant warehouses.

[0019] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an artificial intelligence-based supply chain management method according to some embodiments of the present application. The artificial intelligence-based supply chain management method 100 mainly includes the following steps: In step 101, a historical storage data set of a target fresh food supply chain platform is obtained.

[0020] In the specific implementation, a historical warehouse data set is obtained from the database of the target fresh food supply chain platform. The historical warehouse data set specifically includes the location of each semi-vacant warehouse, the remaining inventory capacity of each semi-vacant warehouse, and the timestamp of various fresh products stored in each semi-vacant warehouse. It should be noted that the remaining inventory capacity described in this application represents the remaining available capacity of the semi-vacant warehouse.

[0021] In step 102, a plurality of storage data nodes are determined according to the historical storage data set, and all the storage data nodes are converted into a storage data node sequence.

[0022] In specific implementation, multiple storage data nodes are determined based on the historical storage data set, that is, multiple storage data nodes are created, and the location of each semi-vacant warehouse in the historical storage data, the remaining inventory capacity of each semi-vacant warehouse, and the timestamp information of various fresh products stored in each semi-vacant warehouse are stored in the corresponding storage data nodes, thereby obtaining multiple different storage data nodes. It should be noted that the storage data node described in this application represents a memory block used to store historical storage data.

[0023] In some embodiments, converting all storage data nodes into a storage data node sequence may be implemented by the following steps: Determine the multiple time scales of each storage data node; The storage data node sequence is determined according to the multiple time scales of all the storage data nodes.

[0024] In some embodiments, the multiple time scales of each storage data node may be determined using the following formula: in, Indicates Multiple time scales of warehouse data nodes, Indicates The types of fresh products stored in the semi-vacant warehouses corresponding to the storage data nodes, Indicates storage Timestamp of fresh products, Indicates storage Timestamp of fresh products, Represents the base of natural logarithms.

[0025] It should be noted that the multi-time scale described in the present application represents a parameter for measuring the busyness of a semi-vacant warehouse corresponding to a storage data node. The larger the multi-time scale, the busier the semi-vacant warehouse corresponding to the storage data node. In addition, the storage data node sequence can be used to measure the busyness of different semi-vacant warehouses in the fresh food supply chain platform. The storage data node sequence can perform feature calibration on semi-vacant warehouses where storage convergence occurs.

[0026] In the specific implementation, the storage data node sequence is determined according to the multi-time scales of all the storage data nodes, that is: all the storage data nodes are sorted in descending order according to the multi-time scales of the storage data nodes, and the sequence obtained by the descending sorting is used as the transitional storage data node sequence; the transitional storage data node sequence is sorted in ascending order according to the remaining inventory capacity of the storage data nodes, and the sequence obtained after the ascending sorting is used as the storage data node sequence.

[0027] In step 103, the local responsiveness of each storage data node in the storage data node sequence is determined.

[0028] In some embodiments, reference Figure 2 As shown, this figure is a schematic diagram of a process for determining the local responsiveness of each storage data node in the storage data node sequence in some embodiments of the present application. In this embodiment, the local responsiveness of each storage data node in the storage data node sequence can be determined by the following steps: First, in step 1031, a storage distant neighbor distance set is determined according to the storage data node sequence; Secondly, in step 1032, the distant neighbor balance coefficient of the storage distant neighbor distance set is determined; Finally, in step 1033, the local responsiveness of each storage data node in the storage data node sequence is determined based on the storage distant neighbor distance set and the distant neighbor balancing coefficient.

[0029] In a specific implementation, the storage distant neighbor distance set is determined according to the storage data node sequence, that is: the first storage data node in the storage data node sequence is selected, and the distance between the semi-vacant warehouse corresponding to the first storage data node and the semi-vacant warehouse corresponding to the adjacent storage data node is calculated, and the obtained value is used as the adjacent factor of the first storage data node. If the adjacent factors are all greater than the distance between the semi-vacant warehouse corresponding to the first storage data node and the semi-vacant warehouse corresponding to the remaining storage data nodes, then the adjacent factors are used as the storage distant neighbor of the first storage data node. Distance, if the adjacent factor is less than or equal to the distance between the semi-vacant state warehouse corresponding to the first storage data node and the semi-vacant state warehouse corresponding to any remaining storage data nodes, then the largest distance between the semi-vacant state warehouse corresponding to the first storage data node and the semi-vacant state warehouses corresponding to the remaining storage data nodes is taken as the storage distant neighbor distance of the first storage data node, and the above steps are repeated to determine the storage distant neighbor distances of the remaining storage data nodes in the storage data node sequence in turn, and the set of storage distant neighbor distances of all storage data nodes is taken as the storage distant neighbor distance set.

[0030] It should be noted that in the present application, for the first storage data node and the last storage data node in the storage data node sequence, their adjacent storage data nodes are the second storage data node and the second to last storage data node respectively. In addition, for the storage data nodes other than the first storage data node and the last storage data node, their adjacent storage data nodes are the two storage data nodes at the left and right ends that are adjacent in the storage data node sequence.

[0031] Among them, in the specific implementation, the distant neighbor balance coefficient of the storage distant neighbor distance set is determined, that is: the storage distant neighbor distances of all storage data nodes in the storage distant neighbor distance set are averaged, and the obtained value is used as the distant neighbor balance coefficient of the storage distant neighbor distance set. It should be noted that the distant neighbor balance coefficient described in the present application represents a parameter for measuring the tendency of the storage distant neighbor distances of the storage data nodes in the storage distant neighbor distance set to be concentrated in a high numerical range. The larger the distant neighbor balance coefficient, the higher the tendency of the storage distant neighbor distances of the storage data nodes in the storage distant neighbor distance set to be concentrated in a high numerical range.

[0032] Among them, in some embodiments, determining the local responsiveness of each storage data node in the storage data node sequence according to the storage distant neighbor distance set and the distant neighbor balancing coefficient can be implemented by the following steps: Get the first The semi-empty warehouse corresponding to the storage data node and the The distance between the semi-vacant warehouses corresponding to the storage data nodes ; Get the distant neighbor balance coefficient of the distant neighbor distance set of the storage ; Get the first The storage distance of the storage data node ; Get the first The adjacent factor of the storage data node ; According to the storage data node sequence The semi-empty warehouse corresponding to the storage data node and the The distance between the semi-vacant warehouses corresponding to the storage data nodes , the distant neighbor balance coefficient of the storage distant neighbor distance set , the storage distant neighbor distance concentration The storage distance of the storage data node And the storage distant neighbor distance concentration The adjacent factor of the storage data node Determine the local responsiveness of each storage data node in the storage data node sequence, wherein the first The local responsiveness of a storage data node can be determined using the following formula:

[0033] in, Indicates the first The local responsiveness of each storage data node, Indicates the total number of storage data nodes in the storage distant neighbor distance concentration. Indicates the total number of storage data nodes in the storage data node sequence.

[0034] It should be noted that the local responsiveness described in the present application reflects the response speed of the semi-vacant warehouse corresponding to the storage data node to the possible occurrence of storage convergence. The greater the local responsiveness, the faster the response speed of the semi-vacant warehouse corresponding to the storage data node to the possible occurrence of storage convergence. The local responsiveness can be used to preliminarily judge the abnormal situation of the semi-vacant warehouse.

[0035] In step 104, the storage confluence decision domain is determined through all local responsiveness, and then the confluence characteristic value of the storage confluence decision domain is determined.

[0036] In some embodiments, determining the storage confluence decision domain through all local responsiveness can be implemented by the following steps: All local responsiveness is smoothed to obtain the storage measurement smoothed sequence; The storage confluence decision domain is determined according to the storage measurement smoothing sequence.

[0037] In some embodiments, all local responsiveness is smoothed to obtain a storage measurement smoothing sequence, which can be implemented by the following steps: Determining a scaling and smoothing eigenvalue for each local responsivity; Determine the storage measure damping sequence based on all scaled damped eigenvalues.

[0038] In the specific implementation, the storage measure smoothing sequence is determined according to all the scaled and smoothed eigenvalues, that is, all the scaled and smoothed eigenvalues ​​are sorted in descending order, and the sequence obtained after descending order is used as the storage measure smoothing sequence.

[0039] In some embodiments, determining the scaling and smoothing characteristic value of each local responsiveness may be implemented by the following steps: Select a local responsivity; Scaling the local responsiveness to obtain a measurement scaling value of the local responsiveness; The storage distant neighbor distance of the storage data node corresponding to the local responsiveness is smoothed by using the measurement scaling value of the local responsiveness to obtain the scaled and smoothed characteristic value of the local responsiveness.

[0040] Repeat the above steps to obtain the scaling and smoothing eigenvalue of the remaining local responsiveness.

[0041] In a specific implementation, the logarithm with a constant e as the base is calculated for the largest local responsiveness among all local responsivenesses, and the obtained value is used as the maximum logarithmic response measure; the logarithm with a constant e as the base is calculated for the smallest local responsiveness among all local responsivenesses, and the obtained value is used as the minimum logarithmic response measure; the logarithm with a constant e as the base is calculated for the local responsiveness, and the obtained value is used as the logarithmic response measure of the local responsiveness; the logarithmic response measure is divided by the difference between the maximum logarithmic response measure and the minimum logarithmic response measure, and the value obtained by the division is used as the measure scaling value of the local responsiveness, for example: the measure scaling value of the local responsiveness ,in represents the local responsiveness, represents the maximum logarithmic response measure, Represents the minimum logarithmic response measure; the storage distant neighbor distance of the storage data node corresponding to the local responsiveness is normalized, and the normalized value is multiplied by the measure scaling value of the local responsiveness, and the multiplied value is used as the scaling and smoothing characteristic value of the local responsiveness, for example: the scaling and smoothing characteristic value of the local responsiveness ,in, represents the measurement scaling value of the local responsiveness, Indicates the storage distant neighbor distance of the storage data node corresponding to the local responsiveness, Indicates the maximum storage neighbor distance of the storage data node in the storage distant neighbor distance concentration. It represents the minimum storage distant neighbor distance of the storage data node in the storage distant neighbor distance set. It should be noted that in the present application, a scaling and smoothing characteristic value corresponds to a semi-vacant warehouse, that is, a scaling and smoothing characteristic value corresponds to a local responsiveness, a local responsiveness corresponds to a storage data node, and a storage data node corresponds to a semi-vacant warehouse.

[0042] It should be noted that the smoothing in the present application can avoid the situation where the storage measurement smoothing sequence is only affected by the storage distant neighbor distance or local responsiveness due to the uneven distribution of the storage distant neighbor distance and the local responsiveness.

[0043] In some embodiments, determining the storage confluence decision domain according to the storage measurement smoothing sequence can be implemented by the following steps: Determining a smoothing characteristic confluence curve according to the storage measurement smoothing sequence; The storage confluence decision domain is determined by the flattening characteristic confluence curve.

[0044] In a specific implementation, a flattening characteristic confluence curve is determined according to the storage measurement flattening sequence, that is, according to the order of the storage measurement flattening sequence, a first scaling flattening characteristic value is selected, the scaling flattening characteristic value is used as the first ordinate value, the number of types of fresh products in the semi-vacant warehouse corresponding to the scaling flattening characteristic value is used as the first abscissa value, the coordinate composed of the first ordinate value and the first abscissa value is used as the feature point of the first scaling flattening characteristic value, a second scaling flattening characteristic value is selected, a second ordinate value and a second abscissa value corresponding to the second scaling flattening characteristic value are determined, the coordinate composed of the second ordinate value and the second abscissa value is used as the feature point of the second scaling flattening characteristic value, the above steps are repeated, the feature points of the remaining scaling flattening characteristic values ​​are determined in turn, all the feature points of the scaling flattening characteristic values ​​are mapped to a two-dimensional plane, the feature point of the first scaling flattening characteristic value is used as the starting point, the feature point of the last scaling flattening characteristic value is used as the end point, the end point and the starting point are connected to form a flattening characteristic confluence curve, and the expression of the flattening characteristic confluence curve is obtained by the ordinate values ​​and abscissa values ​​of the starting point and the end point.

[0045] Among them, the warehouse convergence decision domain is determined according to the flattening characteristic convergence curve, that is: the distance from the feature points of all scaling and flattening eigenvalues ​​to the flattening characteristic convergence curve is calculated, the scaling and flattening eigenvalue corresponding to the feature point with the largest distance is selected, and the position of the semi-vacant warehouse corresponding to the scaling and flattening eigenvalue, the position of the semi-vacant warehouse corresponding to the first scaling and flattening eigenvalue and the position of the semi-vacant warehouse corresponding to the last scaling and flattening eigenvalue are connected in pairs to form a triangular area, and the triangular area is used as the warehouse convergence decision domain.

[0046] It should be noted that the warehouse convergence decision domain in the present application represents an area consisting of semi-vacant warehouses with a higher probability of abnormality. The warehouse convergence decision domain can be used to define the scope of abnormal semi-vacant warehouses, thereby improving the efficiency of monitoring abnormal semi-vacant warehouses.

[0047] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of the process of determining the confluence characteristic value of the warehouse confluence decision domain in some embodiments of the present application. In this embodiment, determining the confluence characteristic value of the warehouse confluence decision domain can be achieved by using the following steps: In step 1041, the confluence coefficient of the storage confluence decision domain is determined; Next, in step 1042, all local responsivities are obtained; Then, in step 1043, all multiple time scales are obtained; Finally, in step 1044, the confluence characteristic value of the storage confluence decision domain is determined through all local responsiveness, all multiple time scales and the confluence coefficient.

[0048] In specific implementation, the confluence coefficient of the storage confluence decision domain is determined, that is, the remaining inventory capacity of all semi-vacant warehouses in the storage confluence decision domain is averaged to obtain the average value. The obtained mean value is converted by a negative power function with an exponential as the base, and the converted value is used as the confluence coefficient of the storage confluence decision domain. For example, the confluence coefficient of the storage confluence decision domain is , represents the mean value of the remaining inventory capacity of all semi-empty warehouses in the warehouse confluence decision domain, represents the base of natural logarithms, It should be noted that the confluence coefficient represents a parameter for measuring the abnormality of all semi-vacant warehouses in the storage confluence decision domain. The smaller the confluence coefficient, the higher the abnormality of all semi-vacant warehouses in the storage confluence decision domain.

[0049] In some embodiments, determining the confluence characteristic value of the storage confluence decision domain through all local responsiveness, all multiple time scales and the confluence coefficient can be achieved by the following steps: Get the confluence coefficient of the storage confluence decision domain ; Get the first The local responsiveness of a semi-vacant warehouse ; Get the first Multiple time scales corresponding to a semi-vacant warehouse ; According to the confluence coefficient of the storage confluence decision domain , the first The local responsiveness of a semi-vacant warehouse And the storage confluence decision domain Multiple time scales corresponding to a semi-vacant warehouse Determine the confluence characteristic value of the storage confluence decision domain, wherein the confluence characteristic value can be determined using the following formula: in, represents the confluence characteristic value of the storage confluence decision domain, represents the maximum local responsiveness corresponding to the semi-vacant warehouse in the warehouse confluence decision domain, represents the minimum local responsiveness corresponding to the semi-vacant warehouse in the warehouse confluence decision domain, represents the maximum multi-time scale of the storage data node corresponding to the semi-vacant warehouse in the storage confluence decision domain, The minimum multi-time scale of the storage data node corresponding to the semi-vacant warehouse in the storage confluence decision domain, represents the base of natural logarithms, Represents the total number of semi-vacant warehouses in the warehouse confluence decision domain.

[0050] It should be noted that the confluence characteristic value described in the present application is determined based on local responsiveness and multiple time scales. The confluence characteristic value can be used to determine the extent to which the abnormal semi-vacant warehouses in the warehouse confluence decision domain can interact with each other to enhance the warehouse confluence. The larger the confluence characteristic value, the greater the extent to which the abnormal semi-vacant warehouses in the warehouse confluence decision domain can interact with each other to enhance the warehouse confluence.

[0051] In step 105, the abnormal monitoring limit of the target fresh food supply chain platform is determined according to the confluence characteristic value and the local responsiveness of all storage data nodes.

[0052] In some embodiments, determining the abnormal monitoring limit of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all storage data nodes can be achieved by the following steps: Get the first Local responsiveness of storage data nodes ; Obtain the confluence characteristic value of the storage confluence decision domain ; According to the storage data node sequence Local responsiveness of storage data nodes And the confluence characteristic value of the storage confluence decision domain Determine the abnormal monitoring limit of the target fresh food supply chain platform, wherein the abnormal monitoring limit can be determined using the following formula: in, represents the abnormal monitoring limit of the target fresh food supply chain platform, Indicates the total number of storage data nodes in the storage data node sequence.

[0053] It should be noted that the abnormal monitoring limit value described in the present application can be used to determine the degree of influence of the storage convergence generated by semi-vacant warehouses in the storage convergence decision domain on the entire fresh food supply chain platform. The larger the abnormal monitoring limit value, the greater the influence of the storage convergence generated by semi-vacant warehouses in the storage convergence decision domain on the entire fresh food supply chain platform.

[0054] In step 106, the target fresh food supply chain platform is monitored and warned by using the abnormal monitoring definition quantity.

[0055] In specific implementation, when the abnormal monitoring boundary value is less than or equal to the preset monitoring boundary threshold value, all semi-vacant warehouses in the warehouse convergence decision domain are judged as not having warehouse convergence; when the abnormal monitoring boundary value is greater than the preset monitoring boundary threshold value, all semi-vacant warehouses in the warehouse convergence decision domain are judged as having had warehouse convergence, and an early warning is issued to the target fresh food supply chain platform.

[0056] It should be noted that in the present application, the monitoring threshold value can be set accordingly according to the specific needs of the target fresh food supply chain platform. For example, if the target fresh food supply chain platform is required to maintain a high sensitivity to storage confluence occurring in semi-vacant warehouses, the monitoring threshold value can be set within a lower abnormal monitoring threshold value range.

[0057] In addition, in another aspect of the present application, in some embodiments, the present application provides a supply chain management system based on artificial intelligence, referring to Figure 4 , which is a schematic diagram of exemplary hardware and / or software of an artificial intelligence-based supply chain management system according to some embodiments of the present application. The artificial intelligence-based supply chain management system 400 includes: an acquisition module 401, a processing module 402 and an execution module 403, which are described as follows: Acquisition module 401, in this application, acquisition module 401 is mainly used to acquire the historical storage data set of the target fresh food supply chain platform; Processing module 402, in the present application, the processing module 402 is used to determine a plurality of storage data nodes according to the historical storage data set, and convert all storage data nodes into a storage data node sequence; In a specific implementation, the processing module 402 in the present application is also used to determine the local responsiveness of each storage data node in the storage data node sequence; In addition, the processing module 402 in the present application is also used to determine the storage confluence decision domain through all local responsiveness, and then determine the confluence characteristic value of the storage confluence decision domain; In addition, the processing module 402 is further used to determine the abnormal monitoring limit value of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all storage data nodes; Execution module 403, in this application, execution module 403 is mainly used to monitor and warn the target fresh food supply chain platform through the abnormal monitoring definition quantity.

[0058] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned artificial intelligence-based supply chain management method.

[0059] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device using an artificial intelligence-based supply chain management method according to some embodiments of the present application. The artificial intelligence-based supply chain management method in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0060] Processor 501 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the artificial intelligence-based supply chain management method in the present application.

[0061] Communication bus 502 may include a pathway for transmitting information between the above-mentioned components.

[0062] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0063] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The determination of the supply chain aggregation area in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0064] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0065] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0066] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0067] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the above-mentioned artificial intelligence-based supply chain management method.

[0068] In summary, in the artificial intelligence-based supply chain management method and system disclosed in the embodiments of the present application, a historical warehouse data set of the target fresh food supply chain platform is obtained, and then multiple warehouse data nodes are determined based on the historical warehouse data set, and all the warehouse data nodes are converted into a warehouse data node sequence, so as to determine the local responsiveness of each warehouse data node in the warehouse data node sequence, and determine the warehouse convergence decision domain through all the local responsiveness, and further determine the convergence characteristic value of the warehouse convergence decision domain, and then determine the abnormal monitoring limit of the target fresh food supply chain platform according to the convergence characteristic value and the local responsiveness of all warehouse data nodes, so as to monitor and warn the target fresh food supply chain platform through the abnormal monitoring limit, that is, to realize the warehouse convergence warning for semi-vacant warehouses.

[0069] Although the preferred embodiments of the present application have been described, those skilled in the art may make other 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 falling within the scope of the present application.

[0070] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A supply chain management method based on artificial intelligence, characterized in that: The steps include: Obtain the historical storage data set of the target fresh food supply chain platform; Determine a plurality of storage data nodes according to the historical storage data set, and convert all the storage data nodes into a storage data node sequence; Determining the local responsiveness of each storage data node in the storage data node sequence; Determine the storage confluence decision domain through all local responsiveness, and then determine the confluence characteristic value of the storage confluence decision domain; Determine the abnormal monitoring limit of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all storage data nodes; The target fresh food supply chain platform is monitored and warned through the abnormal monitoring definition quantity.

2. The method according to claim 1, characterized in that Converting all storage data nodes into storage data node sequences specifically includes: Determine the multiple time scales of each storage data node; The storage data node sequence is determined according to the multiple time scales of all the storage data nodes.

3. The method according to claim 1, characterized in that The storage confluence decision domain determined by all local responsiveness specifically includes: All local responsiveness is smoothed to obtain the storage measurement smoothed sequence; The storage confluence decision domain is determined according to the storage measurement smoothing sequence.

4. The method according to claim 3, characterized in that All local responsiveness is smoothed, and the storage measurement smoothing sequence is obtained, which includes: Determining a scaling and smoothing eigenvalue for each local responsivity; Determine the storage measure damping sequence based on all scaled damped eigenvalues.

5. The method according to claim 4, characterized in that Determining the scaling and smoothing eigenvalues ​​of each local responsiveness specifically includes: Select a local responsivity; Scaling the local responsiveness to obtain a measurement scaling value of the local responsiveness; The storage distant neighbor distance of the storage data node corresponding to the local responsiveness is smoothed by the measurement scaling value of the local responsiveness to obtain the scaling smoothing characteristic value of the local responsiveness; Repeat the above steps to obtain the scaling and smoothing eigenvalue of the remaining local responsiveness.

6. The method according to claim 1, characterized in that Determining the confluence characteristic value of the storage confluence decision domain specifically includes: Determining a confluence coefficient of the storage confluence decision domain; Get all local responsivities; Get all multiple time scales; The confluence characteristic value of the storage confluence decision domain is determined according to all local responsiveness, all multiple time scales and the confluence coefficient.

7. The method according to claim 1, characterized in that The historical warehouse data set includes the location of each semi-vacant warehouse, the remaining inventory capacity of each semi-vacant warehouse, and the timestamp of each semi-vacant warehouse storing various fresh products.

8. A supply chain management system based on artificial intelligence, characterized in that: include: The acquisition module is used to obtain the historical storage data set of the target fresh food supply chain platform; A processing module, used to determine a plurality of storage data nodes according to the historical storage data set, and convert all the storage data nodes into a storage data node sequence; The processing module is further used to determine the local responsiveness of each storage data node in the storage data node sequence; The processing module is further used to determine the storage confluence decision domain through all local responsiveness, and then determine the confluence characteristic value of the storage confluence decision domain; The processing module is further used to determine the abnormal monitoring limit value of the target fresh food supply chain platform according to the confluence characteristic value and the local responsiveness of all storage data nodes; The execution module is used to monitor and warn the target fresh food supply chain platform through the abnormal monitoring definition quantity.

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 supply chain management method based on artificial intelligence described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the supply chain management method based on artificial intelligence as described in any one of claims 1 to 7 are implemented.

Images