Information determination method, device, equipment and medium

Abstract

The present disclosure relates to the field of data processing technology and provides an information determination method, apparatus, device, and medium, including: determining the core goal of the inventory cold start phase through first principles; breaking down the core goal into multiple quantifiable sub-goals; analyzing the impact factors associated with each sub-goal and using the impact factors as topological nodes; constructing a topological network based on nodes and directed edges; obtaining a first optimal path from a first starting node to a target node with minimum cost as a constraint; obtaining a second optimal path from a second starting node to a target node with minimum time as a constraint; obtaining a target optimal path based on the first optimal path and the second optimal path, and determining inventory information during the cold start phase based on the nodes on the target optimal path. By adopting the above scheme, inventory information can be scientifically and rationally predicted during the cold start phase.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to an information determination method, apparatus, device, and medium. Background Art

[0002] In the steel industry, fuel inventory management is a critical aspect of production operations, especially during the initial cold start phase. This phase refers to the initial planning and management of fuel inventory when a steel mill starts a new production line. Fuel inventory management during this phase is crucial to ensuring smooth production and minimizing costs.

[0003] During the cold start phase, traditional fuel inventory forecasting methods often struggle to accurately predict market and production needs due to a lack of historical data and stable production patterns. This makes it difficult to determine fuel inventory levels, making it easy to overstock or run out of stock.

[0004] Therefore, how to solve the reasonable inventory prediction in the cold start phase has become a technical problem that needs to be broken through urgently. Summary of the Invention

[0005] The present disclosure provides an information determination method, apparatus, device, and medium for scientifically and rationally predicting inventory information during a cold start phase.

[0006] In a first aspect, the present disclosure provides an information determination method, comprising:

[0007] Determine the core objectives of the inventory cold start phase through first principles;

[0008] Decompose the core goal into multiple quantifiable sub-goals; for each sub-goal, analyze the impact factors associated with each sub-goal, and use the impact factors as topological nodes; determine the causal relationships and dependencies between the nodes, and represent them as directed edges; and construct a topological network that affects the core goal based on the nodes and directed edges;

[0009] Obtaining the directed edge with the shortest side length from the directed edges of the topological network, selecting two nodes on both sides of the directed edge with the shortest side length as a first starting node and a second starting node respectively; selecting the node with the largest out-degree from the topological network as a target node; obtaining a first optimal path from the first starting node to the target node with the lowest cost as a constraint; obtaining a second optimal path from the second starting node to the target node with the shortest time as a constraint;

[0010] A target optimal path is acquired based on the first optimal path and the second optimal path, and inventory information in a cold start phase is determined based on nodes on the target optimal path.

[0011] Based on the information provided in this disclosure, the core objectives of the method include:

[0012] The core objectives are dynamically adjusted based on the weight coefficients of the four dimensions of low inventory cost, short turnover time, high supply chain stability, and small inventory forecast error.

[0013] According to the information determination method provided by the present disclosure, directed edges include:

[0014] If the change of one node affects another node, the directed edge points from one node to another, thus setting the direction of the directed edge;

[0015] Assign a weight to each directed edge, where the weight represents the strength of the causal relationship or dependency relationship between the two nodes of the directed edge;

[0016] The length of the directed edge is set according to the weight, and the weight is inversely proportional to the edge length.

[0017] According to the information determination method provided in this disclosure, the nodes with the largest out-degree include:

[0018] The out-degree refers to the number of directed edges starting from the node;

[0019] Traverse all nodes in the topological network and calculate the out-degree of each node;

[0020] Select the node with the largest out-degree from all nodes as the target node.

[0021] According to the information determination method provided by the present disclosure, obtaining the first optimal path from the first starting node to the target node includes the following traversal steps:

[0022] Taking the first starting node as the starting node for path search, traverse all directed edges extending outward from the node;

[0023] Calculate the directed edges extending outward and select the directed edges with the smallest weight;

[0024] Determine the node pointed to by the directed edge with the smallest weight as a new starting node, and use the new starting node as the starting node of a new path search;

[0025] Repeat the above traversal steps until the target node is reached, stop the traversal and obtain a first optimal path from the first starting node to the target node.

[0026] According to the information determination method provided by this disclosure, obtaining the optimal path to the target includes:

[0027] For the first optimal path, extract the total cost C of the first optimal path minand key cost node sequences;

[0028] For the second optimal path, extract the total duration T of the second optimal path min and key duration node sequences;

[0029] Remove duplicate nodes from the key cost node sequence and the key duration node sequence, and compare the cost of each node in the key cost node sequence with the total cost C min The ratio of is set as the weight of the node, and the duration of each node in the key duration node sequence is compared with the total duration T min The ratio of is set as the weight of the node; the weights are sorted, and the optimal path to the target is obtained according to the sorted nodes.

[0030] According to the information determination method provided by the present disclosure, determining the inventory information in the cold start phase includes:

[0031] Influence factors represented by nodes on the target optimal path are determined, and initial inventory information in a cold start phase is determined based on the influence factors.

[0032] In a second aspect, the present disclosure further provides an information determination device, comprising:

[0033] The target module determines the core goals of the inventory cold start phase through first principles;

[0034] A topology module breaks down the core goal into multiple quantifiable sub-goals; for each sub-goal, analyzes the impact factors associated with each sub-goal and uses the impact factors as topological nodes; determines the causal and dependency relationships between the nodes, representing them as directed edges; and constructs a topological network that affects the core goal based on the nodes and directed edges.

[0035] A path module is configured to obtain the directed edge with the shortest side length from the directed edges of the topological network, select two nodes on both sides of the directed edge with the shortest side length as a first starting node and a second starting node, respectively; select the node with the largest out-degree from the topological network as a target node; obtain a first optimal path from the first starting node to the target node with the lowest cost as a constraint; and obtain a second optimal path from the second starting node to the target node with the shortest time as a constraint;

[0036] A determination module is configured to obtain a target optimal path based on the first optimal path and the second optimal path, and to determine inventory information in a cold start phase based on nodes on the target optimal path.

[0037] Compared with the prior art, the present disclosure relates to an information determination method, which includes: determining the core goal of the inventory cold start phase through first principles; breaking down the core goal into multiple quantifiable sub-goals; analyzing the influencing factors associated with each sub-goal, and using the influencing factors as topological nodes; constructing a topological network based on nodes and directed edges; obtaining a first optimal path from the first starting node to the target node with the lowest cost as a constraint; obtaining a second optimal path from the second starting node to the target node with the shortest time as a constraint; obtaining a target optimal path based on the first optimal path and the second optimal path, and determining the inventory information of the cold start phase based on the nodes on the target optimal path. By adopting the above scheme, the problem of missing reference data in the cold start phase can be effectively solved, thereby scientifically and rationally predicting inventory information and significantly improving the efficiency and accuracy of information management. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the present disclosure, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0039] Figure 1 A flowchart of an information determination method provided by the present disclosure;

[0040] Figure 2 A schematic diagram of an information determination device provided by the present disclosure;

[0041] Figure 3 A schematic diagram of the electronic device provided in the present disclosure. DETAILED DESCRIPTION

[0042] To make the objectives, technical solutions, and advantages of this disclosure more clear, the technical solutions of this disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of this disclosure, not all of them. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of this disclosure without creative effort shall fall within the scope of protection of this disclosure.

[0043] In modern steel production, fuel inventory management plays a crucial role during the cold start phase. Its rationality is directly related to the smooth start-up of production and subsequent stable operation. During this cold start phase, steel mills face numerous challenges, such as commissioning new production lines, re-commissioning equipment, and readjusting the production rhythm. During this phase, fuel, as a key driver of production, ensures timely and adequate supply.

[0044] However, during cold start scenarios, the lack of effective historical data support leads to a significant disconnect between inventory planning and actual demand. Therefore, reasonable forecasting can effectively balance fuel supply and production demand, ensuring the stability and economy of fuel supply during the cold start phase. This lays a solid foundation for efficient production at steel mills, ensuring the continuity and stability of production activities, and has a profound impact on the economic benefits and market competitiveness of steel mills.

[0045] Figure 1 This is a flow chart of an information determination method provided by the present disclosure, such as Figure 1 As shown, the method includes:

[0046] Step 1: Determine the core objectives of the inventory cold start phase through first principles;

[0047] Furthermore, first principles refers to a methodology that starts from the most fundamental elements and logic of inventory management, without relying on historical data or empirical assumptions. It deconstructs the essence of the problem and analyzes cause-and-effect relationships to derive the core objectives. For example, in the steel plant fuel inventory scenario, first principles can be manifested as building an underlying logical model for inventory management based on fundamental elements such as steel production processes, energy consumption patterns, and market supply and demand.

[0048] The cold start phase refers to the initial planning and management of inventory at the start-up of a new production line. Inventory management during this phase is crucial to ensure smooth production, reduce costs, and improve customer satisfaction.

[0049] The core objective refers to the most fundamental and critical goal that a company must achieve through inventory management during the cold start phase. It is typically expressed as multiple quantifiable sub-objectives. For example, in steel mill fuel inventory management, the core objective can be broken down into sub-objectives such as minimizing inventory costs, minimizing turnover time, minimizing supply disruption risk, and minimizing inventory forecast errors.

[0050] Therefore, determining the core objectives of the inventory cold start phase through first principles is the basis of the entire inventory management strategy.

[0051] Step 2: Decompose the core goal into multiple quantifiable sub-goals; for each sub-goal, analyze the impact factors associated with each sub-goal, and use the impact factors as topological nodes; determine the causal and dependency relationships between the nodes, representing them as directed edges; and construct a topological network that affects the core goal based on the nodes and directed edges;

[0052] Furthermore, the process of breaking down the core goal into multiple quantifiable sub-goals refers to breaking down the complex core goal into multiple specific and actionable sub-goals to facilitate subsequent analysis and optimization. For example, in steel plant fuel inventory management, the core goal can be broken down into the following sub-goals:

[0053] (1) Minimizing inventory costs: ensuring that the total cost of fuel inventory, including holding costs, procurement costs, and transportation costs, is minimized while meeting production needs.

[0054] (2) Minimize turnover time: Optimize the inventory turnover rate of fuel, reduce the time fuel stays in inventory, and ensure the rapid flow of fuel.

[0055] (3) Minimizing supply disruption risks: By optimizing supply chain management, the risk of fuel supply disruption caused by supplier delivery delays or transportation problems can be reduced.

[0056] (4) Minimizing inventory forecast errors: By optimizing the forecast model, the accuracy of fuel demand forecasts can be improved, and inventory backlogs or stockouts caused by inaccurate forecasts can be reduced.

[0057] For each sub-goal, analyze the impact factors associated with each sub-goal and use the impact factors as topological nodes. For example:

[0058] 1) Minimize inventory costs: Influencing factors include fuel purchase price, inventory holding costs, transportation costs, etc.

[0059] 2) Minimize turnaround time: Influencing factors include fuel procurement cycle, transportation time, flexibility of production plan, etc.

[0060] 3) Minimizing the risk of supply disruption: Influencing factors include supplier reliability, stability of transportation methods, inventory safety level, etc.

[0061] 4) Minimizing inventory forecast errors: Influencing factors include the volatility of market demand, the frequency of production plan adjustments, etc.

[0062] Furthermore, the causal relationship and dependency relationship between the nodes are determined and represented by directed edges:

[0063] A causal relationship means that a change in one node directly causes a change in another node; for example, the purchase price of fuel (node ​​A) directly affects the inventory holding cost (node ​​B), so a directed edge points from node A to node B.

[0064] A dependency relationship means that the state or change of one node depends on another node. For example, the inventory level of fuel (node ​​C) depends on the procurement cycle (node ​​D) and transportation time (node ​​E), so there is a directed edge from node D and node E to node C.

[0065] All topological nodes and directed edges are integrated to form a complete topological network. This network intuitively displays the impact paths of various influencing factors on core objectives, as well as the interactions between these factors. For example, the "fuel purchase price" node not only directly affects "inventory holding costs" but also indirectly affects "procurement cycle." These relationships are clearly reflected in the topological network.

[0066] Through the above steps, the core goal is broken down into multiple quantifiable sub-goals. The influencing factors associated with each sub-goal are analyzed, and a topological network that influences the core goal is constructed. This method can scientifically optimize inventory management strategies and improve the efficiency and effectiveness of inventory management during the cold start phase.

[0067] Step 3: Obtain the directed edge with the shortest length from the directed edges of the topological network, select two nodes on both sides of the directed edge with the shortest length as the first starting node and the second starting node respectively; select the node with the largest out-degree from the topological network as the target node; obtain a first optimal path from the first starting node to the target node with the lowest cost as the constraint condition; obtain a second optimal path from the second starting node to the target node with the shortest time as the constraint condition;

[0068] Furthermore, the length of a directed edge refers to the weight of each directed edge in a topological network, representing the strength of the causal and / or dependency relationship between nodes. The weight is inversely proportional to the edge length, that is, the greater the weight, the shorter the edge length, indicating a closer relationship between the two nodes.

[0069] The target node refers to the node with the largest out-degree in the topological network, that is, the node has the largest number of directed edges starting from it, representing the key influencing factor with the widest impact on the core target and the most associated nodes.

[0070] The optimal path is the path with the best comprehensive evaluation indicators among all feasible paths from the starting node to the target node under specific constraints. The first optimal path is optimized for the lowest cost, and the second optimal path is optimized for the shortest time.

[0071] First, we traverse all directed edges in the topological network and read the weight of each edge. According to the rule that weight is inversely proportional to edge length, we convert the weight value into edge length.

[0072] The directed edge with the shortest length is selected, and the nodes at both ends of the directed edge are marked as the first starting node and the second starting node respectively, so as to ensure that the selected starting node is in the most closely associated influence factor connection.

[0073] Specifically, the out-degree of each node in the topological network (i.e., the number of directed edges starting from the node) is counted in turn.

[0074] Sort the out-degree of all nodes and select the node with the largest out-degree value as the target node. This node is usually at a hub position in the entire inventory influencing factor network and plays a key role in achieving the core goal.

[0075] Then, the first starting node is used as the search starting point and a path search algorithm is used to traverse the topological network.

[0076] During the search, the lowest cost constraint is used to calculate the comprehensive cost for each path, including the cost of each node and the cost coefficient for the weight conversion of directed edges. Branch paths with lower costs are preferentially selected for exploration until the target node is reached.

[0077] The path with the lowest cost during the search process is recorded and determined as the first optimal path from the first starting node to the target node.

[0078] Next, using the second starting node as the search starting point, the topological network is traversed using the same path search algorithm. This time, with the shortest possible time constraint, the total duration of each path is calculated, using the time coefficients for each node's processing time and the weight conversion of directed edges. Branch paths with shorter durations are preferentially selected for exploration until the target node is reached. The path with the shortest total duration is recorded and determined as the second-best path from the second starting node to the target node.

[0079] Through the above steps, the directed edge with the shortest side length is obtained from the topological network, the first starting node and the second starting node are determined, the node with the largest out-degree is selected as the target node, and the optimal path from the first starting node and the second starting node to the target node is obtained respectively. This can scientifically optimize the path selection and ensure that the optimization goal of inventory management is achieved during the cold start phase.

[0080] Step 4: Obtain a target optimal path based on the first optimal path and the second optimal path, and determine inventory information in the cold start phase based on nodes on the target optimal path.

[0081] Furthermore, based on the comprehensive evaluation of the first optimal path and the second optimal path, the target optimal path is determined, and based on the node information on the path, the inventory information of the cold start phase is determined, so that the inventory management strategy can be scientifically optimized and the inventory management efficiency and effectiveness of the cold start phase can be improved.

[0082] Compared with the existing technology, the information determination method disclosed in the present invention determines the core goal of the inventory cold start phase through first principles; breaks down the core goal into multiple quantifiable sub-goals; analyzes the influencing factors associated with each sub-goal, and uses the influencing factors as topological nodes; constructs a topological network based on nodes and directed edges; obtains the first optimal path from the first starting node to the target node with the lowest cost as the constraint; obtains the second optimal path from the second starting node to the target node with the shortest time as the constraint; obtains the target optimal path based on the first optimal path and the second optimal path, and determines the inventory information of the cold start phase based on the nodes on the target optimal path. By adopting the above solution, the problem of missing reference data in the cold start phase can be effectively solved, thereby scientifically and rationally predicting inventory information and significantly improving the efficiency and accuracy of information management.

[0083] In one embodiment, the core objectives in step 1 include:

[0084] The core objectives are dynamically adjusted based on the weight coefficients of the four dimensions of low inventory cost, short turnover time, high supply chain stability, and small inventory forecast error.

[0085] Specifically, the weighting of each dimension may vary depending on the production stage, market conditions, or corporate strategy. Therefore, by dynamically adjusting the weighting coefficients, companies can flexibly prioritize certain objectives while taking others into account based on actual circumstances. For example, when funds are tight, the weighting of minimizing inventory costs can be increased; when facing supply instability, the weighting of supply chain stability can be increased. This dynamic adjustment mechanism makes inventory management strategies more flexible and adaptable, better able to cope with the complexities of the cold start phase, ensuring efficient inventory management from the beginning of production and laying a solid foundation for subsequent stable production.

[0086] In one embodiment, directed edges not only represent connections between nodes, but also quantify the strength and direction of these connections. The directed edges in step 2 include:

[0087] If the change of one node affects another node, the directed edge points from one node to another, thus setting the direction of the directed edge;

[0088] Assign a weight to each directed edge, where the weight represents the strength of the causal relationship and / or the strength of the dependency relationship between the two nodes of the directed edge;

[0089] The length of the directed edge is set based on the weight, with the weight being inversely proportional to the edge length. That is, the greater the weight, the shorter the edge length, and the weight reflects the closeness of the relationship between nodes. Paths with shorter edge lengths typically indicate stronger causal or dependency relationships between nodes, and these paths are more likely to be selected during path optimization. For example, if the weight between nodes A and B is high, indicating a close relationship between them, the path from node A to node B will be prioritized during path planning because its shorter edge length represents a stronger causal and / or dependency relationship.

[0090] Through the above steps, setting the direction, weight, and length of directed edges not only clearly expresses the causal and dependency relationships between nodes, but also provides a quantitative basis for subsequent path planning and network analysis. This approach enables the topological network to more accurately reflect the actual inventory management situation and provides a foundation for inventory optimization during the cold start phase.

[0091] In one embodiment, the node with the largest out-degree in step 3 includes:

[0092] The out-degree refers to the number of directed edges that originate from the node. Specifically, in a topological network, each node can be connected to other nodes through directed edges. The out-degree refers to the number of directed edges that extend outward from a node. The out-degree reflects the influence of the node in the network. The larger the out-degree, the wider the direct influence of the node on other nodes.

[0093] Traverse all nodes in the topological network and calculate the out-degree of each node. For example, the "Fuel Market Price Fluctuation" node in the topological network has directed edges pointing to "Purchasing Cost", "Purchasing Decision", and "Inventory Strategy Adjustment", and the out-degree of this node is 3. However, the "Transportation Route Selection" node has directed edges pointing only to "Transportation Cost" and "Transportation Time", and the out-degree is 2.

[0094] The target node is selected from all nodes with the highest out-degree. Specifically, the node with the highest out-degree, selected from all nodes in the topological network, is chosen as the target node. The target node is a key hub in the entire network structure, having a significant impact on the achievement of core goals and serving as the core reference point for subsequent path search and decision analysis.

[0095] In one embodiment, obtaining the first optimal path from the first starting node to the target node in step 3 includes the following traversal steps:

[0096] Taking the first starting node as the starting node for path search, traverse all directed edges extending outward from the node;

[0097] Calculate the directed edges extending outward and select the directed edges with the smallest weight;

[0098] The node pointed to by the directed edge with the smallest weight is determined as the new starting node, and the new starting node is used as the starting node for a new path search; for example, after reaching the "Transportation Cost" node from the "Supplier Geographic Location" node via the directed edge with the smallest weight, the "Transportation Cost" node becomes the new starting node, and the subsequent path is continued to be explored;

[0099] Repeat the above traversal steps to traverse all directed edges extending outward from the starting node of the new path search, calculate the edge weights, select the directed edge with the smallest weight, and determine the node pointed to by this edge as the new starting node. When the traversal reaches the target node, the traversal stops and the first optimal path from the first starting node to the target node is obtained.

[0100] For example, starting from the "Quality Supplier Selection" node, the directed edges extending outward point to the "Purchase Unit Price", "Delivery Cycle", and "Transportation Distance" nodes respectively. After calculating the weights of each edge, the weight of the directed edge pointing to the "Purchase Unit Price" node is the smallest, and the "Purchase Unit Price" node is set as the new starting node.

[0101] Continue searching with the "Purchase Unit Price" node, whose directed edges point to nodes such as "Contract Terms" and "Market Price Fluctuations". Filter out the directed edge with the smallest weight again, determine the next new starting node, and repeat this process.

[0102] When the target node of "total fuel inventory cost control" is finally searched, the path formed by the nodes and directed edges passed through is the first optimal path under the constraint of minimum cost. This path effectively reduces the fuel inventory cost by reasonably selecting suppliers, controlling the purchase unit price and other links.

[0103] In this embodiment, by minimizing the weight of the screening path, ensuring that each step is selected in the direction of cost reduction, the optimal cost path is systematically searched in the topological network, providing a scientific and efficient decision-making basis for cost control in the cold start phase of the steel plant's fuel inventory, avoiding the cost waste caused by the lack of systematicness of traditional methods, and improving the accuracy and effectiveness of inventory management.

[0104] In one embodiment, obtaining the target optimal path in step 4 includes:

[0105] For the first optimal path, extract the total cost C of the first optimal path min And the key cost node sequence, the key cost node sequence refers to the set of nodes on the path that have a greater impact on costs; for example, in the steel plant fuel inventory scenario, nodes such as "supplier selection", "purchase batch", and "transportation method" may constitute the key cost node sequence.

[0106] For the second optimal path, extract the total duration T of the second optimal path minAnd the critical time node sequence, the critical time node sequence refers to the set of nodes on the path that have a greater impact on time; such as "supplier response speed", "transportation route selection", "inventory allocation efficiency" and other nodes.

[0107] Remove duplicate nodes from the key cost node sequence and the key duration node sequence, and compare the cost of each node in the key cost node sequence with the total cost C min The ratio of is set as the weight of the node, which reflects the contribution of the node to the overall cost; the duration of each node in the key duration node sequence is compared with the total duration T min The ratio of is set as the weight of the node; the weights are sorted, and the optimal path to the target is obtained according to the sorted nodes.

[0108] In one embodiment, determining the inventory information in the cold start phase in step 4 includes:

[0109] Influence factors represented by nodes on the target optimal path are determined, and initial inventory information in a cold start phase is determined based on the influence factors.

[0110] An information determination device provided by the present disclosure is described below. The detection system described below and the detection method described above can refer to each other.

[0111] like Figure 2 As shown, an information determination device includes:

[0112] The target module determines the core goals of the inventory cold start phase through first principles;

[0113] A topology module breaks down the core goal into multiple quantifiable sub-goals; for each sub-goal, analyzes the impact factors associated with each sub-goal and uses the impact factors as topological nodes; determines the causal and dependency relationships between the nodes, representing them as directed edges; and constructs a topological network that affects the core goal based on the nodes and directed edges.

[0114] A path module is configured to obtain the directed edge with the shortest side length from the directed edges of the topological network, select two nodes on both sides of the directed edge with the shortest side length as a first starting node and a second starting node, respectively; select the node with the largest out-degree from the topological network as a target node; obtain a first optimal path from the first starting node to the target node with the lowest cost as a constraint; and obtain a second optimal path from the second starting node to the target node with the shortest time as a constraint;

[0115] A determination module is configured to obtain a target optimal path based on the first optimal path and the second optimal path, and to determine inventory information in a cold start phase based on nodes on the target optimal path.

[0116] An electronic device provided in an embodiment of the present application is Figure 3 As shown, the electronic device includes a processor 301 and a memory 303, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, the steps of the method provided in the above embodiment are implemented.

[0117] See also Figure 3 The electronic device further includes: a communication bus 304 and a communication interface 302, the processor 301, the communication interface 302 and the memory 303 are connected via the communication bus 304; the processor 301 is used to execute the executable module stored in the memory 303, such as a computer program.

[0118] Memory 303 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk drive. Communication between the system network element and at least one other network element is achieved via at least one communication interface 302 (which may be wired or wireless), and may utilize the Internet, a wide area network, a local area network, a metropolitan area network, or the like.

[0119] The communication bus 304 may be an ISA bus, a PCI bus, or an EISA bus. The bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 3 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0120] Among them, the memory 303 is used to store programs, and the processor 301 executes the program after receiving the execution instruction. The method executed by the process definition device disclosed in any embodiment of the present application can be applied to the processor 301 or implemented by the processor 301.

[0121] The processor 301 may be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by an integrated logic circuit of hardware in the processor 301 or by instructions in the form of software. The above-mentioned processor 301 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium well-known in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in memory 303, and processor 301 reads the information in memory 303 and performs the steps of the above method in conjunction with its hardware.

[0122] Corresponding to the above-mentioned information determination method, an embodiment of the present application also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer-readable storage medium stores computer-executable instructions or a computer program. When the computer-executable instructions or the computer program are called and executed by the processor, the computer-executable instructions prompt the processor to execute the steps of the above-mentioned information determination method.

[0123] The information determination device provided in the embodiment of the present application can be specific hardware on the device or software or firmware installed on the device. The implementation principle and technical effects of the device provided in the embodiment of the present application are the same as those of the aforementioned method embodiment. For the sake of brief description, for any part not mentioned in the device embodiment, reference can be made to the corresponding content in the aforementioned method embodiment. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0124] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0125] For another example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0126] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0127] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the information determination method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0129] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0130] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The scope of protection of the present application is not limited thereto. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present application, or perform equivalent replacements for some of the technical features thereof. However, these modifications, changes, or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application. They should all be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining information, characterized in that: include: Determine the core objectives of the inventory cold start phase through first principles; The core goal is broken down into four sub-goals: minimizing inventory costs, minimizing turnover time, minimizing supply disruption risks, and minimizing inventory forecast errors; For each sub-goal, analyzing the impact factors associated with each sub-goal, and using the impact factors as topological nodes; Determine the causal relationships and dependency relationships between the nodes, expressed as directed edges; construct a topological network that affects the core target based on the nodes and the directed edges; Obtaining the directed edge with the shortest side length from the directed edges of the topological network, selecting two nodes on both sides of the directed edge with the shortest side length as a first starting node and a second starting node respectively; selecting the node with the largest out-degree from the topological network as a target node; obtaining a first optimal path from the first starting node to the target node with the lowest cost as a constraint; obtaining a second optimal path from the second starting node to the target node with the shortest time as a constraint; Acquire a target optimal path based on the first optimal path and the second optimal path, and determine inventory information in a cold start phase based on nodes on the target optimal path; The obtaining of the optimal target path includes: For the first optimal path, extract the total cost C of the first optimal path min and key cost node sequences; For the second optimal path, extract the total duration T of the second optimal path min and key duration node sequences; Remove duplicate nodes from the key cost node sequence and the key duration node sequence, and compare the cost of each node in the key cost node sequence with the total cost C min The ratio of is set as the weight of the node, and the duration of each node in the key duration node sequence is compared with the total duration T min The ratio of is set as the weight of the node; the weights are sorted, and the optimal path to the target is obtained according to the sorted nodes.

2. The information determination method according to claim 1, characterized in that: The core objectives include: The core objectives are dynamically adjusted based on the weight coefficients of the four dimensions of inventory cost, turnover time, supply chain stability, and inventory forecast error.

3. The information determination method according to claim 1, characterized in that: The directed edges include: If the change of one node affects another node, the directed edge points from one node to another, thus setting the direction of the directed edge; Assign a weight to each directed edge, where the weight represents the strength of the causal relationship or dependency relationship between the two nodes of the directed edge; The length of the directed edge is set according to the weight, and the weight is inversely proportional to the edge length.

4. The information determination method according to claim 1, wherein: The nodes with the largest out-degree include: The out-degree refers to the number of directed edges starting from the node; Traverse all nodes in the topological network and calculate the out-degree of each node; Select the node with the largest out-degree from all nodes as the target node.

5. The information determination method according to claim 1, wherein: The obtaining of the first optimal path from the first starting node to the target node comprises the following traversal steps: Taking the first starting node as the starting node for path search, traverse all directed edges extending outward from the node; Calculate the weights of the directed edges extending outward and select the directed edges with the smallest weights; Determine the node pointed to by the directed edge with the smallest weight as a new starting node, and use the new starting node as the starting node of a new path search; Repeat the above traversal steps until the target node is reached, stop the traversal and obtain a first optimal path from the first starting node to the target node.

6. The information determination method according to claim 1, characterized in that: Determining the inventory information in the cold start phase includes: Influence factors represented by nodes on the target optimal path are determined, and initial inventory information in a cold start phase is determined based on the influence factors.

7. An information determination device, characterized in that: include: The target module determines the core goals of the inventory cold start phase through first principles; The topology module breaks down the core goal into four sub-goals: minimizing inventory costs, minimizing turnover time, minimizing supply disruption risks, and minimizing inventory forecast errors. For each sub-goal, analyzing the impact factors associated with each sub-goal, and using the impact factors as topological nodes; Determine the causal relationships and dependency relationships between the nodes, expressed as directed edges; construct a topological network that affects the core target based on the nodes and the directed edges; A path module is configured to obtain the directed edge with the shortest side length from the directed edges of the topological network, select two nodes on both sides of the directed edge with the shortest side length as a first starting node and a second starting node, respectively; select the node with the largest out-degree from the topological network as a target node; obtain a first optimal path from the first starting node to the target node with the lowest cost as a constraint; and obtain a second optimal path from the second starting node to the target node with the shortest time as a constraint; a determination module, configured to obtain a target optimal path based on the first optimal path and the second optimal path, and determine inventory information in a cold start phase based on nodes on the target optimal path; The obtaining of the optimal target path includes: For the first optimal path, extract the total cost C of the first optimal path min and key cost node sequences; For the second optimal path, extract the total duration T of the second optimal path min and key duration node sequences; Remove duplicate nodes from the key cost node sequence and the key duration node sequence, and compare the cost of each node in the key cost node sequence with the total cost C min The ratio of is set as the weight of the node, and the duration of each node in the key duration node sequence is compared with the total duration T min The ratio of is set as the weight of the node; the weights are sorted, and the optimal path to the target is obtained according to the sorted nodes.

8. An electronic device, characterized in that: include: processor; A memory storing a program, wherein the program comprises instructions which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer-readable storage medium stores instructions or a computer program, and when the instructions or the computer program are executed on a device, the device is caused to execute the method according to any one of claims 1 to 6.

Images