A method and device for calculating dynamic weights of inventory material guarantee evaluation indicators

Abstract

The present invention discloses a method and device for calculating dynamic weights of inventory material support evaluation indicators. The method includes obtaining a task set, a capability set, and an indicator set for inventory material support; the task set includes N task information; the capability set includes M capability information; the indicator set includes T indicator information; M, N, and T are all positive integers; performing fusion processing on the task set, the capability set, and the indicator set to obtain a semantic vector information set; and performing analysis processing on the semantic vector information set to obtain inventory material support capability evaluation indicator weight information. It can be seen that this application is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the indicator weight allocation of the inventory material support evaluation index system more reasonable and capable of dynamically reflecting the differences of different support tasks in the process of inventory material support capability evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory material support evaluation, and particularly to a method and device for calculating dynamic weights of inventory material support evaluation indicators. Background Art

[0002] Inventory material support evaluation is essentially a decision-making problem of an index system composed of multiple indicators. The reasonable allocation of evaluation indicator weights is the basis and premise for the accurate evaluation of the index system. In the process of constructing an inventory material support evaluation index system, it is often necessary to select evaluation indicators from multiple perspectives. Due to different perspectives on guarantee tasks, the weights of each evaluation indicator will also vary with different guarantee tasks. The magnitude of the weight is directly related to the accuracy and authenticity of the evaluation of inventory material support capabilities.

[0003] For a long time, inventory material support evaluation has relied on various decision-making methods to select a single indicator or a few indicators, and set static indicator weights to form an index system with fixed indicator weights, and then conduct an evaluation of inventory material support. There are some problems with the traditional inventory material support evaluation method: (1) When the number of task types increases, different tasks may have different priorities, urgency levels, and resource requirements, and the levels and dimensions of the inventory material support evaluation index system also become cumbersome. The traditional simple tree structure can no longer display the complex relationships among tasks, capabilities, and indicators. (2) The dynamic changes in the weights of each indicator under different inventory material support tasks are not considered, and the indicator weights are set statically, making it difficult to reflect or evaluate dynamically and specifically according to the differences in specific support tasks during the process of evaluating inventory material support capabilities. For example, in the daily support state, inventory material support is more inclined to maintain the stability and sustainability of the inventory, while in the emergency support state, inventory material support is more inclined to rapid response and coordinated supply capabilities. (3) When constructing an inventory material support evaluation system, if only the method of directly associating upper and lower level indicators one by one is adopted, the complex cross-correlation relationships between upper and lower level indicators may be ignored. For example, some secondary indicators are actually related to multiple primary indicators to varying degrees, but in the weight calculation, they may only be associated with a relatively more important primary indicator. Although this simplified processing method improves the convenience of operation, it may also cause limitations and lack of comprehensiveness and accuracy in the evaluation results. Therefore, in order to more comprehensively reflect the multi-dimensionality and complexity of the evaluation object, it is particularly important to calculate indicator weights by more carefully considering and processing these cross-correlation relationships and dynamically obtaining the weights of each indicator based on the correlation relationships among different support tasks, capabilities, and indicators in the process of inventory material support to reflect the differences in different support tasks. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for calculating the dynamic weight of inventory material support evaluation indicators, which is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the weight distribution of the inventory material support evaluation indicator system more reasonable, and being able to dynamically reflect the differences of different support tasks in the process of evaluating the inventory material support ability, and solving the problem that the weights of the inventory material support evaluation indicators are static under different tasks.

[0005] To solve the above technical problem, in the first aspect of the embodiments of the present invention, a method for calculating the dynamic weight of inventory material support evaluation indicators is disclosed, and the method includes:

[0006] S1, obtaining a task set, an ability set, and an indicator set for inventory material support; the task set includes N task information; the ability set includes M ability information; the indicator set includes T indicator information; M, N, and T are all positive integers;

[0007] S2, performing a fusion process on the task set, the ability set, and the indicator set to obtain a semantic vector information set;

[0008] S3, performing an analysis process on the semantic vector information set to obtain the weight information of the inventory material support ability evaluation indicators.

[0009] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing a fusion process on the task set, the ability set, and the indicator set to obtain a semantic vector information set includes:

[0010] S21, extracting feature words from the task set, the ability set, and the indicator set to obtain a task feature word set, an ability feature word set, and an indicator feature word set;

[0011] S22, performing a feature vector analysis process on the task feature word set, the ability feature word set, and the indicator feature word set to obtain a task feature word vector set, an ability feature word vector set, and an indicator feature word vector set;

[0012] S23, performing a fusion process on the task feature word vector set, the ability feature word vector set, and the indicator feature word vector set to obtain a semantic vector information set.

[0013] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing a fusion process on the task feature word vector set, the ability feature word vector set, and the indicator feature word vector set to obtain a semantic vector information set includes:

[0014] S231. Use the inventory material support semantic calculation model to perform calculation processing on the task feature word vector set, the ability feature word vector set, and the index feature word vector set to obtain task semantic vector information, ability semantic vector information, and index semantic vector information;

[0015] Among them, the inventory material support semantic calculation model is:

[0016]

[0017] In the formula, V(r), V(c), and V(z) are the task semantic vector information, the ability semantic vector information, and the index semantic vector information respectively. V(r i1 ) is the semantic vector corresponding to the i1-th task information in the task semantic vector information. V(c i2 ) is the semantic vector corresponding to the i2-th ability information in the ability semantic vector information. V(z i3 ) is the semantic vector corresponding to the i3-th index information in the index semantic vector information. is the l1-th feature word vector of the i1-th task information in the task feature word vector set. is the l2-th feature word vector of the i2-th ability information in the ability feature word vector set. is the l3-th feature word vector of the i3-th index information in the index feature word vector set. a i1 is the number of feature words corresponding to the i1-th task information in the task feature word vector set. b i2 is the number of feature words corresponding to the i2-th ability information in the ability feature word vector set. c i3 is the number of feature words corresponding to the i3-th index information in the index feature word vector set. N, M, and T are respectively the number of task information in the task feature word vector set, the number of ability information in the ability feature word vector set, and the number of index information in the index feature word vector set. δ1, δ3, and δ3 are the first weight parameter, the second weight parameter, and the third weight parameter respectively.

[0018] S232. Perform merging processing on the task semantic vector information, the ability semantic vector information, and the index semantic vector information to obtain a semantic vector information set.

[0019] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the analyzing and processing the semantic vector information set to obtain the weight information of the inventory material support ability evaluation index includes:

[0020] S31. Use the first similarity calculation model to calculate and process the semantic vector information set to obtain ability similarity information and index similarity information;

[0021] Among them, the first similarity calculation model:

[0022]

[0023] In the formula, S(V(c j1 ), V(c j2 )) is the similarity value between the j1-th ability information and the j2-th ability information in the ability similarity information, S(V(z j3 ), V(z j4 )) is the similarity value between the j3-th index information and the j4-th index information in the index similarity information, V(c j1 ) and V(c j2 ) respectively represent the semantic vectors corresponding to the j1-th and j2-th ability information of the ability semantic vector information in the semantic vector information set, V(z j3 ), V(z j4 ) respectively represent the semantic vectors corresponding to the j1-th and j2-th index information of the index semantic vector information in the semantic vector information set, M and T respectively represent the number of ability information in the ability semantic vector information and the number of index information in the index semantic vector information, θ1 and θ2 respectively represent the first similarity value offset constant and the second similarity value offset constant, · represents the vector inner product, and || represents the vector norm;

[0024] S32. Use the ability similarity information and the index similarity information to construct an ability judgment matrix and an index judgment matrix;

[0025] S33. Analyze and process the ability judgment matrix and the index judgment matrix to obtain ability weight coefficient information and index weight coefficient information;

[0026] S34. Analyze and process the semantic vector information set to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information;

[0027] S35. Calculate and process the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information.

[0028] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the analyzing and processing the ability judgment matrix and the index judgment matrix to obtain ability weight coefficient information and index weight coefficient information includes:

[0029] S331. Solve the eigenvectors of the ability judgment matrix and the index judgment matrix to obtain ability eigenvector information and index eigenvector information;

[0030] S332. Use the eigenvector normalization model to perform normalization processing on the ability eigenvector information and the index eigenvector information respectively to obtain ability weight coefficient information and index weight coefficient information;

[0031] Among them, the eigenvector normalization model is:

[0032]

[0033] In the formula, ρ ′c and ρ ′z respectively represent the ability weight coefficient information and the index weight coefficient information, is the weight coefficient corresponding to the k1-th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the k2-th index information in the index weight coefficient information, is the eigenvector corresponding to the k1-th ability information in the ability eigenvector information, is the eigenvector corresponding to the k2-th index information in the index eigenvector information, M is the number of ability information in the ability eigenvector information, and T is the number of index information in the index eigenvector information.

[0034] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the analyzing and processing the semantic vector information set to obtain the first-layer edge weight coefficient information and the second-layer edge weight coefficient information includes:

[0035] S341. Perform calculation processing on the semantic vector information set to obtain first-layer edge similarity information and second-layer edge similarity information;

[0036] S342. Preset s = 1;

[0037] S343. Determine whether the s-th similarity value in the first-layer edge similarity information is less than a preset first similarity threshold to obtain a first judgment result;

[0038] When the first judgment result is yes, update the similarity value to 0 to obtain the updated first-layer edge similarity information, and determine the updated first-layer edge similarity information as the third-layer edge similarity information, and execute S344;

[0039] When the first judgment result is no, execute S344;

[0040] S344. Determine whether the s is equal to the number of the similarity values in the first-layer edge similarity information, and obtain a second judgment result;

[0041] When the second judgment result is yes, execute S345;

[0042] When the second judgment result is no, execute S343;

[0043] S345. Perform a calculation process on the second-layer edge similarity information and a preset second similarity threshold to obtain fourth-layer edge similarity information;

[0044] S346. Perform a normalization process on the third-layer edge similarity information and the fourth-layer edge similarity information respectively to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information.

[0045] As an optional implementation manner, in the first aspect of the embodiments of the present invention, the performing a calculation process on the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information includes:

[0046] Use an inventory material support weight calculation model to perform a calculation process on the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information;

[0047] Among them, the inventory material support weight calculation model is:

[0048]

[0049] 1≤d1≤N;

[0050] 1≤d2≤T;

[0051] 1≤d3≤M;

[0052] In the formula, P is the inventory material support ability evaluation index weight information, P d1,d2 is the weight of the d2nd index information of the d1st task information in the inventory material support ability evaluation index weight information, ρ(V(r d1 ),V(c d3 )) is the similarity value between the d1st task information and the d3rd ability information in the first-layer edge weight coefficient information, ρ(V(c d3 ),V(z d2 )) is the similarity value between the d3rd ability information and the d2nd index information in the second-layer edge weight coefficient information, is the weight coefficient corresponding to the d3-th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the d2-th index information in the index weight coefficient information, N is the number of task information in the first-layer edge weight coefficient information, T is the number of index information in the second-layer edge weight coefficient information, M is the number of index information in the first-layer edge weight coefficient information, ∈ d1 is the constant coefficient of the d1-th task information.

[0053] A second aspect of an embodiment of the present invention discloses a device for calculating the dynamic weight of inventory material support evaluation indicators, the device includes:

[0054] An acquisition module, configured to acquire a task set, an ability set, and an index set of inventory material support; the task set includes N task information; the ability set includes M ability information; the index set includes T index information; M, N, and T are all positive integers;

[0055] A first calculation module, configured to perform fusion processing on the task set, the ability set, and the index set to obtain a semantic vector information set;

[0056] A second calculation module, configured to perform analysis processing on the semantic vector information set to obtain inventory material support ability evaluation index weight information.

[0057] A third aspect of an embodiment of the present invention discloses another device for calculating the dynamic weight of inventory material support evaluation indicators, the device includes:

[0058] A processor;

[0059] A memory coupled to the processor and storing executable program code;

[0060] The processor calls the executable program code stored in the memory to execute some or all of the steps of the method for calculating the dynamic weight of inventory material support evaluation indicators disclosed in the first aspect of the embodiment of the present invention.

[0061] A computer-readable storage medium stores computer instructions, and when the computer instructions are called, they are used to execute some or all of the steps of the method for calculating the dynamic weight of inventory material support evaluation indicators disclosed in the first aspect of the embodiment of the present invention.

[0062] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0063] In an embodiment of the present invention, a task set, a capability set, and an index set for inventory material support are obtained; the task set includes N task information; the capability set includes M capability information; the index set includes T index information; M, N, and T are all positive integers; the task set, the capability set, and the index set are fused to obtain a semantic vector information set; the semantic vector information set is analyzed to obtain the weight information of the inventory material support capability evaluation index. It can be seen that this application is beneficial to associating different inventory material support capabilities and indexes according to different tasks, making the distribution of the index weights of the inventory material support evaluation index system more reasonable, and being able to dynamically reflect the differences of different support tasks in the process of inventory material support capability evaluation, solving the problem that the weights of the inventory material support evaluation indexes under different tasks are static and unchanged. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0065] Figure 1 It is a schematic flowchart of a method for calculating dynamic weights of inventory material support evaluation indexes disclosed in an embodiment of the present invention;

[0066] Figure 2 It is a schematic structural diagram of a device for calculating dynamic weights of inventory material support evaluation indexes disclosed in an embodiment of the present invention;

[0067] Figure 3 It is a schematic structural diagram of another device for calculating dynamic weights of inventory material support evaluation indexes disclosed in an embodiment of the present invention;

[0068] Figure 4 It is a schematic diagram of a "task-capability-index" hypernetwork for inventory material support evaluation disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0070] In the description of the present invention, the claims and the above-mentioned drawings, the terms "first", "second", etc. are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products or devices.

[0071] Reference to "embodiment" herein means that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0072] It should be noted that since the method of the embodiments of the present application is executed in a computer device, the processing objects of each computer device exist in the form of data or information. For example, the ability is essentially the data information corresponding to the ability. It can be understood that in subsequent embodiments, if tasks, indicators, weights, coefficients, etc. are mentioned, they all exist as corresponding data and information for the computer device to process, and specific details are not elaborated here.

[0073] The present invention discloses a method and device for calculating dynamic weights of inventory material support evaluation indicators, which is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the distribution of indicator weights in the inventory material support evaluation indicator system more reasonable. The following will be described in detail respectively.

[0074] Embodiment 1

[0075] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for calculating dynamic weights of inventory material support evaluation indicators disclosed in an embodiment of the present invention. Among them, Figure 1 The method for calculating dynamic weights of inventory material support evaluation indicators described is applied to a device for calculating dynamic weights of inventory material support evaluation indicators, such as a local server or a cloud server for optimized management of calculating dynamic weights of inventory material support evaluation indicators, etc., which is not limited in the embodiments of the present invention. As Figure 1 shown, the method for calculating dynamic weights of inventory material support evaluation indicators may include the following operations:

[0076] S1. Obtain the task set, ability set, and indicator set for inventory material support; the task set includes N task information; the ability set includes M ability information; the indicator set includes T indicator information; M, N, and T are all positive integers;

[0077] It should be noted that the task set, ability set, and indicator set are obtained by analyzing and evaluating the support capabilities and indicators required for the support tasks received during the inventory material management and support process. The task set, ability set, and indicator set are as follows:

[0078] Task set R = {r i}i = 1, 2, 3, 4,..., N;

[0079] Ability set C = {c j}j = 1, 2, 3, 4,..., M;

[0080] Indicator set Z = {z k}k = 1, 2, 3, 4,..., T;

[0081] Exemplarily, inventory material support includes 2 task information: daily support task r1 and emergency support task r2. The ability set involves a total of 3 ability information, namely ability c1, ability c2, and ability c3. The indicator set includes a total of 6 indicator information, which are respectively represented as indicator z1, indicator z2, indicator z3, indicator z4, indicator z5, and indicator z6. Each set is as follows:

[0082] Task set R = {r1, r2};

[0083] Ability set C = {c1, c2, c3};

[0084] Indicator set Z = {z1, z2, z3, z4, z5, z6};

[0085] S2. Perform fusion processing on the task set, the ability set, and the indicator set to obtain a semantic vector information set;

[0086] S3. Analyze and process the semantic vector information set to obtain the weight information of the inventory material support ability evaluation indicators.

[0087] It can be seen that implementing the method for calculating the dynamic weight of the inventory material support evaluation indicators described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the distribution of the indicator weights in the inventory material support evaluation index system more reasonable.

[0088] In an optional embodiment, the performing fusion processing on the task set, the ability set, and the indicator set to obtain a semantic vector information set includes:

[0089] S21. Extract feature words from the task set, the ability set, and the metric set to obtain a task feature word set, an ability feature word set, and a metric feature word set;

[0090] It should be noted that the above extraction of feature words from the task set, the ability set, and the metric set is to extract the feature words of the task description corresponding to the task information in the task set, the feature words of the ability description corresponding to the ability information in the ability set, and the feature words of the metric description corresponding to the metric information in the metric set. Exemplarily, if the task information is "daily guarantee task", its corresponding description is "According to demand forecasting and inventory situation, formulate and execute a replenishment plan, and ensure that the warehouse environment is suitable, materials are stored in an orderly manner, and easy to access"; the ability information is "emergency response ability", and its corresponding description is "In case of an emergency, be able to quickly make procurement and distribution decisions"; the metric information is "emergency response time", and its corresponding description is "Measure the time required from the emergence of sudden demand to the completion of material distribution."

[0091] It should be noted that the above extraction of feature words is to perform word segmentation processing on the task description corresponding to the task information in the task set, the ability description corresponding to the ability information in the ability set, and the metric description corresponding to the metric information in the metric set through a Chinese word segmentation tool (such as: jieba, HANLP), and use the TF-IDF algorithm to extract the core descriptive feature words of the task information, the ability information, and the metric information.

[0092] Exemplarily, the respective feature word sets in the obtained task feature word set, ability feature word set, and metric feature word set are as follows:

[0093]

[0094] Feature word set of the 6th metric z6:

[0095] S22. Perform feature vector analysis processing on the task feature word set, the ability feature word set, and the metric feature word set to obtain a task feature word vector set, an ability feature word vector set, and a metric feature word vector set;

[0096] It should be noted that the above feature vector analysis is obtained by using the BERT algorithm for feature word vector extraction.

[0097] Exemplarily, the feature word vectors in the obtained task feature word vector set, ability feature word vector set, and metric feature word vector set are as follows:

[0098] The feature word vectors of the 1st task r1 are respectively:

[0099] The characteristic word vectors of the second task r2 are respectively:

[0100] The characteristic word vectors of the first ability c1 are respectively:

[0101] The characteristic word vectors of the second ability c2 are respectively:

[0102] The characteristic word vectors of the third ability c3 are respectively:

[0103] The characteristic word vectors of the first index z1 are respectively:

[0104] The characteristic word vectors of the second index z2 are respectively:

[0105] The characteristic word vectors of the third index z3 are respectively:

[0106] The characteristic word vectors of the fourth index z4 are respectively:

[0107] The characteristic word vectors of the fifth index z5 are respectively:

[0108] The characteristic word vectors of the sixth index z6 are respectively:

[0109] S23. Perform fusion processing on the task characteristic word vector set, the ability characteristic word vector set, and the index characteristic word vector set to obtain a semantic vector information set.

[0110] It can be seen that implementing the dynamic weight calculation method for inventory material support evaluation indicators described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the index weight allocation of the inventory material support evaluation index system more reasonable.

[0111] In another optional embodiment, the performing fusion processing on the task characteristic word vector set, the ability characteristic word vector set, and the index characteristic word vector set to obtain a semantic vector information set includes:

[0112] S231. Use the inventory material support semantic computing model to perform computational processing on the task feature word vector set, the ability feature word vector set, and the index feature word vector set to obtain task semantic vector information, ability semantic vector information, and index semantic vector information;

[0113] Among them, the inventory material support semantic computing model is:

[0114]

[0115] In the formula, V(r), V(c), and V(z) are the task semantic vector information, the ability semantic vector information, and the index semantic vector information respectively. V(r i1 ) is the semantic vector corresponding to the i1-th task information in the task semantic vector information. V(c i2 ) is the semantic vector corresponding to the i2-th ability information in the ability semantic vector information. V(z i3 ) is the semantic vector corresponding to the i3-th index information in the index semantic vector information. is the l1-th feature word vector of the i1-th task information in the task feature word vector set. is the l2-th feature word vector of the i2-th ability information in the ability feature word vector set. is the l3-th feature word vector of the i3-th index information in the index feature word vector set. a i1 is the number of feature words corresponding to the i1-th task information in the task feature word vector set. b i2 is the number of feature words corresponding to the i2-th ability information in the ability feature word vector set. c i3 is the number of feature words corresponding to the i3-th index information in the index feature word vector set. N, M, and T are respectively the number of task information in the task feature word vector set, the number of ability information in the ability feature word vector set, and the number of index information in the index feature word vector set. δ1, δ3, and δ3 are the first weight parameter, the second weight parameter, and the third weight parameter respectively.

[0116] It should be noted that the first weight parameter, the second weight parameter, and the third weight parameter can be set by the user or obtained from historical data. The embodiments of the present invention do not make specific limitations.

[0117] S232. Perform merging processing on the task semantic vector information, the ability semantic vector information, and the index semantic vector information to obtain a semantic vector information set.

[0118] It should be noted that in the above merging process, the task semantic vector information, the ability semantic vector information, and the index semantic vector information are used as subsets of the semantic vector information set. For example, if the task semantic vector information, the ability semantic vector information, and the index semantic vector information are x1, x2, and x3 respectively, the merged semantic vector information set is {x1, x2, x3};

[0119] It should be noted that after obtaining the task semantic vector information, the ability semantic vector information, and the index semantic vector information, an inventory material support task, ability, index graph network and an inventory material support "task - ability - index" hypernetwork will be constructed. Among them, task information, ability information, and index information are used as nodes in their respective graph network structures. The "task" graph network uses task information as nodes, and there are only task nodes in the task graph network; the "ability" graph network uses ability information as nodes, and the connections between ability nodes represent the relationships between different abilities, which are called ability edges; the "index" graph network uses index information as nodes, and the connections between index nodes represent the relationships between different indexes, which are called index edges. According to the semantic similarity values, connections are respectively established between the "task" nodes and the "ability" nodes in the "task" graph network and the "ability" graph network, and between the "ability" nodes and the "index" nodes in the "ability" graph network and the "index" graph network. Such connections are called layer edges, and the "task node - layer edge - ability node - layer edge - index node" is called a link, and the "task - ability - index" hypernetwork is output. As Figure 4 shown, the "task node - layer edge - ability node - layer edge - index node" is called a link.

[0120] It can be seen that implementing the inventory material support evaluation index dynamic weight calculation method described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indexes according to different tasks, making the index weight allocation of the inventory material support evaluation index system more reasonable.

[0121] In another alternative embodiment, the analysis and processing of the semantic vector information set to obtain the inventory material support ability evaluation index weight information includes:

[0122] S31, using the first similarity calculation model to perform calculation processing on the semantic vector information set to obtain ability similarity information and index similarity information;

[0123] Among them, the first similarity calculation model:

[0124]

[0125] In the formula, S(V(c j1 ),V(c j2)) is the similarity value between the j1-th ability information and the j2-th ability information in the ability similarity information, S(V(z j3 ),V(z j4 )) is the similarity value between the j3-th index information and the j4-th index information in the index similarity information, V(c j1 ) and V(c j2 ) respectively represent the semantic vectors corresponding to the j1-th and j2-th ability information in the ability semantic vector information in the semantic vector information set, V(z j3 ),V(z j4 ) respectively represent the semantic vectors corresponding to the j1-th and j2-th index information in the index semantic vector information in the semantic vector information set, M and T respectively represent the number of ability information in the ability semantic vector information and the number of index information in the index semantic vector information, θ1 and θ2 respectively represent the first similarity value offset constant and the second similarity value offset constant, · represents the vector inner product, || represents the vector norm;

[0126] It should be noted that the first similarity value offset constant and the second similarity value offset constant can be set by the user or obtained through other means, and the embodiments of the present invention do not make specific limitations.

[0127] It should be noted that the similarity value mentioned above refers to the semantic similarity value.

[0128] Exemplarily, taking the semantic similarity values between the 1st index and the 2nd index, the 1st index and the 3rd index, and the 1st index and the 4th index as examples, assuming they are 0.8, 0.2, and 0.5 respectively, where the larger the value of the semantic similarity value S, the more similar the two semantic vectors are.

[0129] S32. Using the ability similarity information and the index similarity information, an ability judgment matrix and an index judgment matrix are constructed;

[0130] It should be noted that the above ability judgment matrix and index judgment matrix are as follows:

[0131]

[0132] In the formula, A c is the ability judgment matrix, A z is the index judgment matrix, M is the number of ability information, T is the number of index information, S(V(c M ),V(c M )) represents the similarity value between the M-th ability information and the M-th ability information, S(V(z T ),V(z T)) represents the similarity value between the T-th index information and the T-th index information.

[0133] S33. Analyze and process the ability judgment matrix and the index judgment matrix to obtain ability weight coefficient information and index weight coefficient information;

[0134] S34. Analyze and process the semantic vector information set to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information;

[0135] S35. Perform calculation processing on the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information.

[0136] It can be seen that implementing the dynamic weight calculation method for inventory material support evaluation indicators described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the index weight allocation of the inventory material support evaluation index system more reasonable.

[0137] In an optional embodiment, the analyzing and processing the ability judgment matrix and the index judgment matrix to obtain ability weight coefficient information and index weight coefficient information includes:

[0138] S331. Solve the eigenvectors of the ability judgment matrix and the index judgment matrix to obtain ability eigenvector information and index eigenvector information;

[0139] It should be noted that the above ability weight coefficient information is the eigenvector obtained by finding the maximum eigenvalue for each row in the ability judgment matrix; the above index weight coefficient information is the eigenvector obtained by finding the maximum eigenvalue for each row in the index judgment matrix. The obtained ability weight coefficient information and index weight coefficient information are as follows;

[0140]

[0141] In the above formula, ρ AC represents the ability eigenvector information, ρ AZ represents the index eigenvector information, M is the number of ability information, T is the number of index information, is the eigenvector corresponding to the M-th ability information in the ability eigenvector information, represents the eigenvector corresponding to the T-th index information in the index eigenvector information.

[0142] S332. Use the eigenvector normalization model to perform normalization processing on the ability eigenvector information and the index eigenvector information respectively to obtain the ability weight coefficient information and the index weight coefficient information;

[0143] Among them, the eigenvector normalization model is:

[0144]

[0145] In the formula, ρ′ c and ρ′ z respectively represent the ability weight coefficient information and the index weight coefficient information, is the weight coefficient corresponding to the k1-th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the k2-th index information in the index weight coefficient information, is the eigenvector corresponding to the k1-th ability information in the ability eigenvector information, is the eigenvector corresponding to the k2-th index information in the index eigenvector information, M is the number of ability information in the ability eigenvector information, and T is the number of index information in the index eigenvector information.

[0146] It can be seen that implementing the dynamic weight calculation method for inventory material support evaluation indicators described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the distribution of indicator weights in the inventory material support evaluation indicator system more reasonable.

[0147] In an alternative embodiment, the analyzing and processing the semantic vector information set to obtain the first-layer edge weight coefficient information and the second-layer edge weight coefficient information includes:

[0148] S341. Perform calculation processing on the semantic vector information set to obtain the first-layer edge similarity information and the second-layer edge similarity information;

[0149] It should be noted that the above-mentioned performing calculation processing on the semantic vector information set to obtain the first-layer edge similarity information and the second-layer edge similarity information is obtained by using the second similarity calculation model;

[0150] Among them, the second similarity calculation model is:

[0151]

[0152] In the formula, S(V(r j5 ),V(c j6 )) is the similarity value between the j5-th task information and the j6-th ability information in the first-layer edge similarity information, S(V(c j7),V(z j8 )) is the similarity value between the j7th ability information and the j8th index information in the second-layer edge similarity information, V(r j5 ) and V(c j6 ) respectively represent the semantic vector corresponding to the j5th task information of the task semantic vector information and the semantic vector corresponding to the j6th ability information of the ability semantic vector information in the semantic vector information set, V(c j7 ) and V(z j8 ) respectively represent the semantic vector corresponding to the j7th ability information of the ability semantic vector information and the semantic vector corresponding to the j8th index information of the index semantic vector information in the semantic vector information set, N, M, and T respectively represent the number of task information in the task semantic vector information, the number of ability information in the ability semantic vector information, and the number of index information in the index semantic vector information, θ3 and θ4 respectively represent the third similarity value offset constant and the fourth similarity value offset constant, · represents the vector inner product, || represents the vector norm;

[0153] It should be noted that the third similarity value offset constant and the fourth similarity value offset constant can be set by the user or obtained through other means, and the embodiments of the present invention do not make specific limitations.

[0154] It should be noted that the similarity value mentioned above refers to the semantic similarity value.

[0155] S342, preset s = 1;

[0156] S343, determine whether the s-th similarity value in the first-layer edge similarity information is less than a preset first similarity threshold to obtain a first judgment result;

[0157] When the first judgment result is yes, update the similarity value to 0 to obtain the updated first-layer edge similarity information, and determine the updated first-layer edge similarity information as the third-layer edge similarity information, and execute S344;

[0158] When the first judgment result is no, execute S344;

[0159] S344, determine whether s is equal to the number of similarity values in the first-layer edge similarity information to obtain a second judgment result;

[0160] When the second judgment result is yes, execute S345;

[0161] When the second judgment result is no, execute S343;

[0162] S345. Calculate and process the second-layer edge similarity information and a preset second similarity threshold to obtain fourth-layer edge similarity information;

[0163] It should be noted that calculating and processing the second-layer edge similarity information and a preset second similarity threshold to obtain fourth-layer edge similarity information is to compare the size of each similarity value in the second-layer edge similarity information with the preset second similarity threshold. When a certain similarity value in the second-layer edge similarity information is less than the preset second similarity threshold, update this similarity value to 0. After all judgments and updates are completed, fourth-layer edge similarity information is obtained.

[0164] S346. Normalize the third-layer edge similarity information and the fourth-layer edge similarity information respectively to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information.

[0165] It can be seen that implementing the dynamic weight calculation method for inventory material support evaluation indicators described in this embodiment of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the index weight distribution of the inventory material support evaluation index system more reasonable.

[0166] In an optional embodiment, the calculating and processing the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information includes:

[0167] Use an inventory material support weight calculation model to calculate and process the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain inventory material support ability evaluation index weight information;

[0168] Among them, the inventory material support weight calculation model is:

[0169]

[0170] 1 ≤ d1 ≤ N;

[0171] 1 ≤ d2 ≤ T;

[0172] 1 ≤ d3 ≤ M;

[0173] In the formula, P is the inventory material support ability evaluation index weight information, and P d1,d2 is the weight of the d2nd index information of the d1st task information in the inventory material support ability evaluation index weight information, ρ(V(r d1 ), V(c d3)) is the similarity value between the d1-th task information and the d3-th ability information in the first-layer edge weight coefficient information, ρ(V(c d3 ), V(z d2 )) is the similarity value between the d3-th ability information and the d2-th index information in the second-layer edge weight coefficient information, is the weight coefficient corresponding to the d3-th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the d2-th index information in the index weight coefficient information, N is the number of task information in the first-layer edge weight coefficient information, T is the number of index information in the second-layer edge weight coefficient information, M is the number of index information in the first-layer edge weight coefficient information, ∈ d1 is the constant coefficient of the d1-th task information.

[0174] It should be noted that ∈ d1 can be set by the user or obtained through other means, and the embodiments of the present invention do not make specific limitations, where 1 ≤ d1 ≤ N.

[0175] It can be seen that implementing the inventory material support evaluation index dynamic weight calculation method described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators according to different tasks, making the index weight allocation of the inventory material support evaluation index system more reasonable.

[0176] Embodiment 2

[0177] Please refer to Figure 2 , Figure 2 which is a schematic structural diagram of an inventory material support evaluation index dynamic weight calculation device disclosed in the embodiments of the present invention. Among them, Figure 2 the described inventory material support evaluation index dynamic weight calculation device is applied to an optimization system for inventory material support evaluation index dynamic weight calculation, such as a local server or a cloud server for inventory material support evaluation index dynamic weight calculation, etc., and the embodiments of the present invention do not make limitations. As Figure 2 shown, the inventory material support evaluation index dynamic weight calculation device includes:

[0178] An acquisition module 201, configured to acquire a task set, an ability set, and an index set of inventory material support; the task set includes N task information; the ability set includes M ability information; the index set includes T index information; M, N, and T are all positive integers;

[0179] A first calculation module 202, configured to perform fusion processing on the task set, the ability set, and the index set to obtain a semantic vector information set;

[0180] A second calculation module 203, configured to analyze and process the semantic vector information set to obtain inventory material support ability evaluation index weight information.

[0181] It can be seen that implementing the inventory material support evaluation index dynamic weight calculation device described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators with different tasks, making the distribution of the index weights in the inventory material support evaluation index system more reasonable.

[0182] Embodiment III

[0183] Please refer to Figure 3 , Figure 3 which is a schematic structural diagram of another inventory material support evaluation index dynamic weight calculation device disclosed in the embodiments of the present invention. Among them, Figure 3 the described inventory material support evaluation index dynamic weight calculation device is applied in an optimization system for calculating the dynamic weights of inventory material support evaluation indexes, such as a local server or a cloud server for calculating the dynamic weights of inventory material support evaluation indexes, etc., which is not limited in the embodiments of the present invention. As Figure 3 shown, the inventory material support evaluation index dynamic weight calculation device includes:

[0184] A processor 301;

[0185] A memory 302 coupled to the processor 301 and storing executable program code;

[0186] The processor 301 calls the executable program code stored in the memory 302 to execute some or all of the steps of the inventory material support evaluation index dynamic weight calculation method described in Embodiment I.

[0187] It can be seen that implementing the inventory material support evaluation index dynamic weight calculation device described in the embodiments of the present invention is beneficial to associating different inventory material support capabilities and indicators with different tasks, making the distribution of the index weights in the inventory material support evaluation index system more reasonable.

[0188] Embodiment IV

[0189] The embodiments of the present invention disclose a computer-readable storage medium storing computer instructions, which are used to execute some or all of the steps of the inventory material support evaluation index dynamic weight calculation method described in Embodiment I when the computer instructions are called.

[0190] Embodiment V

[0191] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps in the method for calculating the dynamic weight of the inventory material support evaluation index described in Embodiment 1.

[0192] The system embodiments described above are only illustrative. The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0193] Through the above specific description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc memories, a magnetic disk memory, a tape memory, or any other computer-readable medium capable of carrying or storing data.

[0194] Finally, it should be noted that: The method and device for calculating the dynamic weight of inventory material support evaluation indicators disclosed in the embodiments of the present invention only disclose the preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than limiting them; Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: They can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; And these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A dynamic weight calculation method for inventory material guarantee evaluation indicators, characterized in that, The method includes: S1. Obtain a task set, a capability set, and an index set for inventory material support; the task set includes N task information; the capability set includes M capability information; the index set includes T index information; M, N, and T are all positive integers; S2. Perform fusion processing on the task set, the capability set, and the index set to obtain a semantic vector information set; S3. Analyze and process the semantic vector information set to obtain weight information of inventory material support capability evaluation indicators; The performing fusion processing on the task set, the capability set, and the index set to obtain a semantic vector information set includes: S21. Extract feature words from the task set, the capability set, and the index set to obtain a task feature word set, a capability feature word set, and an index feature word set; S22. Perform feature vector analysis processing on the task feature word set, the capability feature word set, and the index feature word set to obtain a task feature word vector set, a capability feature word vector set, and an index feature word vector set; S23. Perform fusion processing on the task feature word vector set, the capability feature word vector set, and the index feature word vector set to obtain a semantic vector information set; The performing fusion processing on the task feature word vector set, the capability feature word vector set, and the index feature word vector set to obtain a semantic vector information set includes: S231. Use an inventory material support semantic calculation model to perform calculation processing on the task feature word vector set, the capability feature word vector set, and the index feature word vector set to obtain task semantic vector information, capability semantic vector information, and index semantic vector information; Among them, the inventory material support semantic calculation model is: Wherein, V(r), V(c), and V(z) are the task semantic vector information, the ability semantic vector information, and the index semantic vector information, and V(r i1 ) is the semantic vector corresponding to the i1-th task information in the task semantic vector information, V(c i2 ) is the semantic vector corresponding to the i2-th ability information in the ability semantic vector information, V(z i3 ) is the semantic vector corresponding to the i3-th index information in the index semantic vector information, is the l1-th feature word vector of the i1-th task information in the task feature word vector set, is the l2-th feature word vector of the i2-th ability information in the ability feature word vector set, is the l3-th feature word vector of the i3-th index information in the index feature word vector set, a i1 is the number of feature words corresponding to the i1-th task information in the task feature word vector set, b i2 is the number of feature words corresponding to the i2-th ability information in the ability feature word vector set, c i3 is the number of feature words corresponding to the i3-th index information in the index feature word vector set, N, M, and T are respectively the number of task information in the task feature word vector set, the number of ability information in the ability feature word vector set, and the number of index information in the index feature word vector set, and δ1, δ2, and δ3 are respectively the first weight parameter, the second weight parameter, and the third weight parameter; S232. Perform merging processing on the task semantic vector information, the capability semantic vector information, and the index semantic vector information to obtain a semantic vector information set; The analyzing and processing the semantic vector information set to obtain weight information of inventory material support capability evaluation indicators includes: S31. Use a first similarity calculation model to perform calculation processing on the semantic vector information set to obtain capability similarity information and index similarity information; Among them, the first similarity calculation model: Wherein, S(V(c j1 ), V(c j2 )) is the similarity value between the j1-th ability information and the j2-th ability information in the ability similarity information, S(V(z j3 ), V(z j4 )) is the similarity value between the j3-th index information and the j4-th index information in the index similarity information, V(c j1 ) and V(c j2 ) respectively represent the semantic vectors corresponding to the j1-th and j2-th ability information of the ability semantic vector information in the semantic vector information set, V(z j3 ), V(z j4 ) respectively represent the semantic vectors corresponding to the j3-th and j4-th index information of the index semantic vector information in the semantic vector information set, M and T respectively represent the number of ability information in the ability semantic vector information and the number of index information in the index semantic vector information, θ1 and θ2 respectively represent the first similarity value offset constant and the second similarity value offset constant, · represents the vector inner product, || represents the vector norm; S32. Use the capability similarity information and the index similarity information to construct a capability judgment matrix and an index judgment matrix; S33. Analyze and process the capability judgment matrix and the index judgment matrix to obtain capability weight coefficient information and index weight coefficient information; S34. Analyze and process the semantic vector information set to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information; S35. Perform calculation processing on the capability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information, and the second-layer edge weight coefficient information to obtain weight information of inventory material support capability evaluation indicators; The analyzing and processing the semantic vector information set to obtain first-layer edge weight coefficient information and second-layer edge weight coefficient information includes: S341. Calculate and process the semantic vector information set to obtain the first-layer edge similarity information and the second-layer edge similarity information; S342. Preset s = 1; S343. Determine whether the s-th similarity value in the first-layer edge similarity information is less than a preset first similarity threshold to obtain a first judgment result; When the first judgment result is yes, update the similarity value to 0 to obtain the updated first-layer edge similarity information, and determine the updated first-layer edge similarity information as the third-layer edge similarity information, and execute S344; When the first judgment result is no, execute S344; S344. Determine whether s is equal to the number of similarity values in the first-layer edge similarity information to obtain a second judgment result; When the second judgment result is yes, execute S345; When the second judgment result is no, execute S343; S345. Calculate and process the second-layer edge similarity information and a preset second similarity threshold to obtain the fourth-layer edge similarity information; S346. Normalize the third-layer edge similarity information and the fourth-layer edge similarity information respectively to obtain the first-layer edge weight coefficient information and the second-layer edge weight coefficient information; The calculating and processing the semantic vector information set to obtain the first-layer edge similarity information and the second-layer edge similarity information includes: Using a second similarity calculation model to calculate and process the semantic vector information set to obtain the first-layer edge similarity information and the second-layer edge similarity information; Wherein the second similarity calculation model is: where S(V(r j5 ), V(c j6 )) is the similarity value between the j5 - th task information and the j6 - th ability information in the edge similarity information of the first layer, S(V(c j7 ), V(z j8 )) is the similarity value between the j7 - th ability information and the j8 - th index information in the edge similarity information of the second layer, V(r j5 ) and V(c j6 ) respectively represent the semantic vectors corresponding to the j5 - th task information of the task semantic vector information and the j6 - th ability information of the ability semantic vector information in the semantic vector information set, V(c j7 ) and V(z j8 ) respectively represent the semantic vectors corresponding to the j7 - th ability information of the ability semantic vector information and the j8 - th index information of the index semantic vector information in the semantic vector information set, N, M, and T respectively represent the number of task information in the task semantic vector information, the number of ability information in the ability semantic vector information, and the number of index information in the index semantic vector information, θ3 and θ4 respectively represent the third similarity value offset constant and the fourth similarity value offset constant, · represents the vector inner product, and || represents the vector norm.

2. The dynamic weight calculation method for inventory material support evaluation indicators according to claim 1, characterized in that, The analyzing and processing the ability judgment matrix and the index judgment matrix to obtain the ability weight coefficient information and the index weight coefficient information includes: S331. Solve the eigenvectors of the ability judgment matrix and the index judgment matrix to obtain the ability eigenvector information and the index eigenvector information; S332. Use an eigenvector normalization model to normalize the ability eigenvector information and the index eigenvector information respectively to obtain the ability weight coefficient information and the index weight coefficient information; Wherein, the eigenvector normalization model is: Where ρ ′c and ρ ′z respectively represent the ability weight coefficient information and the index weight coefficient information, is the weight coefficient corresponding to the k1-th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the k2-th index information in the index weight coefficient information, is the feature vector corresponding to the k1-th ability information in the ability feature vector information, is the feature vector corresponding to the k2-th index information in the index feature vector information, M is the number of ability information in the ability feature vector information, and T is the number of index information in the index feature vector information.

3. The dynamic weight calculation method for inventory material support evaluation indicators according to claim 1, characterized in that The calculating and processing the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information and the second-layer edge weight coefficient information to obtain the inventory material support ability evaluation index weight information includes: Using an inventory material support weight calculation model to calculate and process the ability weight coefficient information, the index weight coefficient information, the first-layer edge weight coefficient information and the second-layer edge weight coefficient information to obtain the inventory material support ability evaluation index weight information; Wherein, the inventory material support weight calculation model is: where P is the weight information of the inventory material support ability evaluation index, and P d1,d2 is the weight of the d2 - th index information of the d1 - th task information in the weight information of the inventory material support ability evaluation index, ρ(V(r d1 ), V(c d3 )) is the similarity value between the d1 - th task information and the d3 - th ability information in the first - layer edge weight coefficient information, ρ(V(c d3 ), V(z d2 )) is the similarity value between the d3 - th ability information and the d2 - th index information in the second - layer edge weight coefficient information, is the weight coefficient corresponding to the d3 - th ability information in the ability weight coefficient information, is the weight coefficient corresponding to the d2 - th index information in the index weight coefficient information, N is the number of task information in the first - layer edge weight coefficient information, T is the number of index information in the second - layer edge weight coefficient information, M is the number of ability information in the first - layer edge weight coefficient information, ∈ d1 is the constant coefficient of the d1 - th task information.

4. An apparatus for calculating dynamic weights of inventory material support evaluation indicators, characterized in that, The device includes: A processor; A memory coupled to the processor and storing executable program code; The processor calls the executable program code stored in the memory and executes the inventory material support evaluation index dynamic weight calculation method according to any one of claims 1-3.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when called, are used to execute the method for calculating the dynamic weight of the evaluation index for inventory material support according to any one of claims 1-3.

Images