A knowledge graph construction method and device based on material reserve information

Abstract

The application discloses a kind of knowledge graph construction method and device based on material reserve information, the method includes obtaining material reserve information and material classification information;The material reserve information is preprocessed, and preprocessed material reserve information is obtained;The preprocessed material reserve information and the material classification information are handled, and material reserve knowledge graph information is obtained. Visible, this embodiment can accurately and efficiently obtain the material reserve knowledge graph information of material reserve information by combining the category, similarity and semantic information of material reserve information, which is beneficial to realize the correlation analysis of materials, thereby providing strong support for the rational allocation and emergency management of materials, and further improving the optimization efficiency and emergency response efficiency of material reserve and supply chain management.

Description

Technical Field

[0001] This invention relates to the field of materials management and information processing technology, and in particular to a method and apparatus for constructing a knowledge graph based on materials reserve information. Background Technology

[0002] Modern materials management faces challenges from increasingly complex supply chains and growing demand for emergency reserves, particularly in areas such as data fragmentation, insufficient intelligent analysis, slow response times, and difficulties in establishing material relationships. Current materials management methods primarily rely on manual statistics, fixed rule matching, and simple database retrieval, leading to scattered materials information, inaccurate decision-making, and untimely responses, easily resulting in overstocking or shortages. Furthermore, the functions, uses, and substitutability relationships between materials are difficult to automatically identify and analyze, impacting the optimal allocation and efficiency of emergency deployment. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a method and apparatus for constructing a knowledge graph based on material reserve information. By combining the category, similarity and semantic information of material reserve information, the material reserve knowledge graph information can be obtained accurately and efficiently, which is conducive to realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and thus improving the optimization efficiency of material reserve and supply chain management and emergency response efficiency.

[0004] To address the aforementioned technical problems, a first aspect of this invention discloses a method for constructing a knowledge graph based on material reserve information, the method comprising:

[0005] S1, obtain material reserve information and material classification information;

[0006] S2, preprocess the material reserve information to obtain preprocessed material reserve information;

[0007] S3, process the preprocessed material reserve information and the material classification information to obtain material reserve knowledge graph information.

[0008] As an optional implementation, in the first aspect of the present invention, the preprocessing of the material reserve information to obtain preprocessed material reserve information includes:

[0009] S21, Remove stop words from the material reserve information to obtain the first material reserve preprocessing information;

[0010] S22, Remove special characters from the first material reserve preprocessing information to obtain the second material reserve preprocessing information;

[0011] S23, The second material reserve preprocessing information is processed in a unified format to obtain the third material reserve preprocessing information;

[0012] S24, perform synonym conversion on the third material reserve preprocessing information to obtain preprocessed material reserve information.

[0013] As an optional implementation, in the first aspect of the present invention, processing the preprocessed material reserve information and the material classification information to obtain material reserve knowledge graph information includes:

[0014] S31, Obtain the material reserve training dataset;

[0015] S32, process the material reserve training dataset and the preprocessed material reserve information to obtain material reserve relationship information;

[0016] S33, process the material reserve relationship information and the material classification information to obtain material reserve knowledge graph information.

[0017] As an optional implementation, in the first aspect of the present invention, processing the material reserve training dataset and the preprocessed material reserve information to obtain material reserve relationship information includes:

[0018] S321, Process the pre-processed material reserve information to obtain the material reserve information to be processed;

[0019] S322, Process the material reserve information to be processed and the material reserve training dataset to obtain material reserve sequence information;

[0020] S323, Process the material reserve sequence information to obtain material reserve relationship information.

[0021] As an optional implementation, in the first aspect of the present invention, processing the pre-processed material reserve information to obtain the material reserve information to be processed includes:

[0022] S3211, Perform feature word extraction processing on the preprocessed material reserve information to obtain material reserve feature word information;

[0023] S3212, Process the material reserve feature word information and the preprocessed material reserve information to obtain a material reserve feature word vector set;

[0024] S3213, Using the material reserve semantic calculation model, the feature word vector set of the material reserve is calculated and processed to obtain the material reserve information to be processed;

[0025] The semantic calculation model for material reserves is as follows:

[0026]

[0027] In the formula, V represents the reserve information of the materials to be processed. i1 CXL is the semantic vector of the i1th material reserve in the material reserve information to be processed, and CXL is the set of feature word vectors of the material reserve. i1 and CXL j1 Let i and j be the i-th and j-th material reserve feature word vectors in the set of material reserve feature word vectors, respectively; N1 is the number of material reserve feature word vectors in the set of material reserve feature word vectors; δ1 is the first weight parameter; and ∈ represents the semantic deviation vector information of material reserves. i1 This refers to the i1th semantic deviation vector of material reserves in the semantic deviation vector information.

[0028] As an optional implementation, in the first aspect of the present invention, processing the material reserve sequence information to obtain material reserve relationship information includes:

[0029] S3231, Using a material reserve similarity calculation model, the material reserve sequence information is calculated and processed to obtain material reserve similarity information;

[0030] The similarity calculation model for the material reserves is as follows:

[0031]

[0032] In the formula, XSD represents the similarity information of the material reserves. i3,j3 WZCB is the material reserve similarity value between the i3rd material and the j3rd material in the material reserve similarity information. i3 and WZCB j3 These are the i3rd and j3rd material reserve sequences in the material reserve sequence information, respectively, where |·| represents the magnitude of the vector, and θ1 represents the first similarity offset parameter;

[0033] S3232, Perform category matching processing on the material reserve similarity information to obtain material reserve category information;

[0034] S3233, Calculate and process the material reserve category information to obtain material reserve relationship information.

[0035] As an optional implementation, in the first aspect of the present invention, processing the material reserve relationship information and the material classification information to obtain material reserve knowledge graph information includes:

[0036] S331, Process the material reserve relationship information and the material classification information to obtain material classification sequence information;

[0037] S332, The material classification sequence information and the material reserve relationship information are fused to obtain a material classification matrix;

[0038] S333, The material classification matrix is ​​integrated and processed to obtain material reserve knowledge graph information.

[0039] A second aspect of this invention discloses a knowledge graph construction device based on material reserve information, the device comprising:

[0040] The acquisition module is used to acquire material reserve information and material classification information;

[0041] The preprocessing module is used to preprocess the material reserve information to obtain preprocessed material reserve information;

[0042] The calculation module is used to process the preprocessed material reserve information and the material classification information to obtain material reserve knowledge graph information.

[0043] A third aspect of this invention discloses another knowledge graph construction device based on material reserve information, the device comprising:

[0044] processor;

[0045] A memory coupled to the processor stores executable program code;

[0046] The processor calls the executable program code stored in the memory to execute some or all of the steps of the knowledge graph construction method based on material reserve information disclosed in the first aspect of the present invention.

[0047] The fourth aspect of the present invention discloses a computer-readable storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps of the knowledge graph construction method based on material reserve information disclosed in the first aspect of the present invention.

[0048] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0049] In this embodiment of the invention, material reserve information and material classification information are acquired; the material reserve information is preprocessed to obtain preprocessed material reserve information; the preprocessed material reserve information and the material classification information are further processed to obtain material reserve knowledge graph information. It is evident that this embodiment, by combining the category, similarity, and semantic information of material reserve information, can accurately and efficiently obtain material reserve knowledge graph information, which is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and ultimately improving the optimization efficiency of material reserves and supply chain management, as well as emergency response efficiency. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a method for constructing a knowledge graph based on material reserve information, as disclosed in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of a knowledge graph construction device based on material reserve information disclosed in an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of another knowledge graph construction device based on material reserve information disclosed in an embodiment of the present invention. Detailed Implementation

[0054] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0055] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, 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 may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] This invention discloses a method and apparatus for constructing a knowledge graph based on material reserve information. By combining the category, similarity, and semantic information of material reserve information, it can accurately and efficiently obtain material reserve knowledge graph information, which is conducive to realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and thus improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency. Detailed descriptions follow.

[0058] Example 1

[0059] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for constructing a knowledge graph based on material reserve information, as disclosed in an embodiment of the present invention. Figure 1 The described knowledge graph construction method based on material reserve information is applied in a knowledge graph construction device based on material reserve information, such as a local server or cloud server for optimized management of knowledge graph construction based on material reserve information. This invention does not limit the application of this method. Figure 1 As shown, the knowledge graph construction method based on material reserve information can include the following operations:

[0060] S1, obtain material reserve information and material classification information;

[0061] It should be noted that material reserve information refers to all structured and unstructured data related to materials, covering the basic attributes, reserve status, supply chain information, etc. Material classification information is used to organize and classify materials hierarchically, ensuring that the storage, management, and retrieval of different categories of materials are more standardized, and providing structured data support for the construction of knowledge graphs.

[0062] S2. Preprocess the material reserve information to obtain preprocessed material reserve information;

[0063] S3. Process the preprocessed material reserve information and material classification information to obtain material reserve knowledge graph information.

[0064] It should be noted that the material reserve knowledge graph information is a multi-dimensional structured representation information based on the material reserve information, which is used to represent entity, attribute and relationship information between materials, so as to provide strong support for the reasonable allocation of materials and emergency management, and further improve the optimization efficiency of material reserve and supply chain management and the emergency response efficiency.

[0065] It can be seen that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial to realizing the correlation analysis of materials, thus providing strong support for the reasonable allocation of materials and emergency management, and further improving the optimization efficiency of material reserve and supply chain management and the emergency response efficiency.

[0066] In an optional embodiment, preprocessing the material reserve information to obtain preprocessed material reserve information includes:

[0067] S21. Perform stop word removal processing on the material reserve information to obtain the first preprocessed material reserve information;

[0068] It should be noted that the above stop word removal processing can be performed using tools or algorithms such as SpaCy and NLTK. Specifically, the embodiments of the present invention do not make any limitations.

[0069] It should be noted that by removing stop words, such as removing "de", "shi", "le", etc., the key material information is made more prominent, improving the accuracy of subsequent feature extraction and classification.

[0070] S22. Perform special character removal processing on the first preprocessed material reserve information to obtain the second preprocessed material reserve information;

[0071] It should be noted that the above special character removal processing can be performed using the re.sub() method in Python to batch clean useless information such as punctuation marks and web links. The specific processing method is not specifically limited in the embodiments of the present invention.

[0072] It should be noted that through the above processing, interfering characters such as #, *, / , @, and % can be removed, improving the normalization degree of the data and ensuring that the model is not affected by irrelevant characters.

[0073] S23. Perform format unification processing on the second preprocessed material reserve information to obtain the third preprocessed material reserve information;

[0074] It should be noted that the above format uniform processing can be performed using tools or algorithms such as NLTK and SpaCy. Specifically, the embodiments of the present invention do not limit the specific processing.

[0075] It should be noted that by standardizing the format, we ensure that data matching will not result in inconsistencies due to different capitalization or units.

[0076] S24, perform synonym conversion on the third material reserve preprocessing information to obtain preprocessed material reserve information.

[0077] It should be noted that the above synonym conversion processing can be performed using tools or algorithms such as NLTK and Word2Vec. In particular, the embodiments of the present invention do not impose specific limitations.

[0078] It should be noted that the above processing ensures that data analysis and knowledge graph construction will not fail to match due to different expressions.

[0079] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0080] In another optional embodiment, the pre-processed material reserve information and material classification information are processed to obtain material reserve knowledge graph information, including:

[0081] S31, Obtain the material reserve training dataset;

[0082] It should be noted that the material reserve training dataset is a structured and cleaned collection of data containing text, classification, relationship and attribute information related to material reserves, which is used to train the model to generate material reserve relationship information.

[0083] S32, process the material reserve training dataset and preprocessed material reserve information to obtain material reserve relationship information;

[0084] S33 processes the information on material reserve relationships and material classification to obtain material reserve knowledge graph information.

[0085] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0086] In another optional embodiment, the material reserve training dataset and preprocessed material reserve information are processed to obtain material reserve relationship information, including:

[0087] S321, Process the pre-processed material reserve information to obtain the material reserve information to be processed;

[0088] S322, Process the material reserve information to be processed and the material reserve training dataset to obtain material reserve sequence information;

[0089] S323 processes the material reserve sequence information to obtain material reserve relationship information.

[0090] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0091] In an optional embodiment, the pre-processed material reserve information is processed to obtain the material reserve information to be processed, including:

[0092] S3211, Perform feature word extraction processing on the pre-processed material reserve information to obtain material reserve feature word information;

[0093] It should be noted that the above feature word extraction process can be performed using tools or algorithms such as TF-IDF, TextRank, or BERT. Specifically, this embodiment of the invention does not limit the specific features extracted.

[0094] It should be noted that the above processing can extract key feature words representing materials and reduce interference from common words. At the same time, it can identify specific information such as material name, quantity, and specifications, ensuring that the multi-dimensional features of materials can be extracted.

[0095] S3212, Process the material reserve feature word information and preprocessed material reserve information to obtain the material reserve feature word vector set;

[0096] It should be noted that the above processing can be performed using tools or algorithms such as Word2Vec, GloVe, or BERT. Specifically, the embodiments of the present invention do not limit the specific processing.

[0097] It should be noted that the above processing generates semantic vectors that can represent material feature words, which facilitates subsequent tasks such as similarity calculation and classification. At the same time, it can provide context-aware vectors for each material feature word, thereby enhancing the model's ability to handle complex sentences and polysemous words.

[0098] S3213, using the semantic calculation model of material reserves, calculates and processes the feature word vector set of material reserves to obtain the material reserve information to be processed;

[0099] The semantic calculation model for material reserves is as follows:

[0100]

[0101] In the formula, V represents the reserve information of materials to be processed. i1 Let CXL be the semantic vector of the i-th material reserve in the material reserve information to be processed, and let CXL be the set of feature word vectors for the material reserves. i1 and CXL i1 These are the i-th and j-th feature word vectors of material reserves, respectively; N1 is the number of feature word vectors of material reserves in the set; δ1 is the first weight parameter; and ∈ represents the semantic deviation vector information of material reserves. i1 This refers to the i1th semantic deviation vector of material reserves in the semantic deviation vector information.

[0102] It should be noted that the first weight parameter and the semantic deviation vector information of material reserves can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specifics.

[0103] It should be noted that by using the semantic computing model for material reserves, the semantics of the entire material reserve information can be comprehensively considered, and an overall semantic representation of each material reserve can be constructed. This helps to obtain a more accurate semantic representation of material reserves, effectively improves the correlation analysis of material reserve information and the overall performance of the model, and enables subsequent analyses (such as material reserve correlation analysis, knowledge graph construction, etc.) to better understand and process the semantic content of material reserve data.

[0104] It should be noted that the first weight parameter ranges from [0.1, 2], determining the importance of material reserve information in the calculation. A larger first weight parameter makes the semantic vector calculation result have a greater impact on the weighted similarity, thus contributing more to material reserve terms with high semantic similarity. Assigning a larger first weight parameter to material reserve information with high similarity, such as [1.1, 2], highlights the correlation between semantically similar materials and is more suitable for scenarios where there are obvious relationships between material reserves. When the first weight parameter takes a smaller value, such as [0.1, 1.1], the model's contribution to each feature word is more balanced, reducing the influence of highly similar feature words, and is more suitable for scenarios where material reserve information is more diverse and complex.

[0105] It should be noted that the semantic bias vector information of material reserves plays an adjustment and correction role in the above calculations. It can compensate for biases in model training or fine-tune certain material reserve data, helping the model adapt to the distribution of actual data. This can prevent the model from overfitting to certain feature words, help the model better adapt to new data, and improve the model's stability and robustness. For example, Table 1 below shows an example of semantic bias vector information for material reserves:

[0106] Table 1. Example information on semantic deviation vector information of material reserves.

[0107] Material characteristics Semantic bias vector of material reserves (3D vector) Material A [0.1,0.4,0.3] Material B [0.3,0.8,0.2] Material C [0.2,0.1,0.5]

[0108] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0109] In an optional embodiment, the material reserve information to be processed and the material reserve training dataset are processed to obtain material reserve sequence information, including:

[0110] S3221, Using the material reserve training dataset, train the initial model information of the first material reserve to obtain the training result information and the training model information of the first material reserve.

[0111] It should be noted that the initial model information for the first material reserve is the BERT model.

[0112] The above process uses the material reserve training dataset as input to the initial model information of the first material reserve, and trains the model using the initial model information of the first material reserve to obtain the training result information of the first material reserve. The training model information of the first material reserve is the model obtained after training with the material reserve training dataset.

[0113] S3222, calculate and process the training results information of the first material reserve to obtain the loss value of the first material reserve;

[0114] S3223, determine whether the first material reserve loss value is less than the preset first material reserve loss threshold, and obtain the first judgment result;

[0115] It should be noted that the preset first material reserve loss threshold ranges from [0.05, 0.2], but the specific value is not limited in this embodiment of the invention.

[0116] When the first judgment result is negative, determine the first material reserve training model information as the first material reserve initial model information, and re-acquire the material reserve training dataset, and execute S3221;

[0117] The necessary step is to obtain a second material reserve training dataset, which is then used as the primary material reserve training dataset. By updating this dataset, a more accurate optimization model for the first material reserve can be obtained.

[0118] When the first judgment result is yes, the first material reserve training model information is determined to be the first material reserve optimization model;

[0119] S3224, Using the first material reserve optimization model, the material reserve information to be processed is calculated and processed to obtain the material reserve sequence information;

[0120] It should be noted that the above calculation process uses the information on the material reserves to be processed as input to the first material reserve optimization model. The material reserve sequence information is then calculated using this model. This sequence is a set of material reserves arranged according to time, status, or other relevant dimensions. This sequence reflects the changes in the state of material reserves at different times or under different conditions and is often used for subsequent analysis, prediction, optimization, and decision-making.

[0121] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0122] In an optional embodiment, the training result information of the first material reserve is calculated and processed to obtain the loss value of the first material reserve, including:

[0123] Using the first material reserve loss function calculation model, the training result information of the first material reserve is calculated and processed to obtain the first material reserve loss value;

[0124] The calculation model for the first material reserve loss function is as follows:

[0125]

[0126] In the formula, WZSS represents the first material reserve loss value, YY represents the first material reserve real label information corresponding to the first material reserve training result information, YYZ represents the first material reserve training result information, M2 and N2 represent the number of category information in the first material reserve training result information and the number of first material reserve training result values ​​corresponding to the category information in the first material reserve training result information, respectively, and YY j i and YYZ j i δ2 represents the i2nd true label value of the j2nd category in the true label information of the first material reserve corresponding to the category information in the training result information of the first material reserve, and the i2nd training result value of the j2nd category in the training result information of the first material reserve, respectively. δ2 is the second weight parameter.

[0127] It should be noted that the second weight parameter can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specific weight parameter.

[0128] It should be noted that the first material reserve loss function calculation model, by adjusting the model parameters, enables the material reserve model to more accurately predict material reserve information on a given training dataset. This can help improve inventory management, supply chain configuration, demand forecasting, and other aspects.

[0129] It should be noted that the value of the second weight parameter is between [0.1, 3], and it is used to control the contribution of each part in the calculation model of the first material reserve loss function. Adjusting this parameter helps to optimize the performance of the model and ensure that the loss function not only focuses on the prediction accuracy, but also takes into account other factors, such as class balance.

[0130] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0131] In an optional embodiment, the material reserve sequence information is processed to obtain material reserve relationship information, including:

[0132] S3231, Using the material reserve similarity calculation model, the material reserve sequence information is calculated and processed to obtain material reserve similarity information;

[0133] The similarity calculation model for material reserves is as follows:

[0134]

[0135] In the formula, XSD represents the similarity information of material reserves. i3,j3 WZCB represents the similarity value between the i3rd and j3rd materials in the material reserve similarity information. i3 and WZCB j3 These are the i3rd and j3rd material reserve sequences in the material reserve sequence information, respectively, where |·| represents the magnitude of the vector, and θ1 represents the first similarity offset parameter;

[0136] It should be noted that the first similarity offset parameter can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specific parameters.

[0137] It should be noted that the material reserve similarity calculation model can measure the similarity between two material reserve sequences, thereby helping to understand the relationship between different material reserves.

[0138] It should be noted that the value range of the first similarity offset parameter is between [1,5], which can make the obtained material reserve similarity information more in line with business needs. For example, in some cases, it is necessary to strengthen the similarity of certain features, while in other cases, it may be necessary to weaken them.

[0139] S3232, Perform category matching processing on the similarity information of material reserves to obtain the category information of material reserves;

[0140] It should be noted that the above category matching processing can be performed using algorithms or tools such as K-means, hierarchical clustering, or DBSCAN. Specifically, the embodiments of the present invention do not limit the specific methods used.

[0141] It should be noted that by using category matching, material reserves can be managed more effectively, ensuring that the required materials can be quickly and accurately dispatched when needed, thereby improving response efficiency.

[0142] S3233 calculates and processes the material reserve category information to obtain material reserve relationship information.

[0143] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0144] In an optional embodiment, the material reserve category information is calculated and processed to obtain material reserve relationship information, including:

[0145] S32331, Obtain the material reserve category dataset;

[0146] It should be noted that the dataset used to train and validate the machine learning model aims to learn the classification features of material reserve information through this dataset, and then make predictions, classifications, or optimization decisions on new data. This dataset not only contains basic information about the materials, but also includes a classification label for each material, which the model uses to learn how to assign materials to categories based on different features.

[0147] S32332, using the material reserve category dataset, trains the initial model information of the material reserve category to obtain the training result information and the training model information of the material reserve category;

[0148] It should be noted that the initial model information for the material reserve category is a support vector machine.

[0149] It should be noted that the above training process uses the material reserve category dataset as input to the initial model information of the material reserve category, and trains the model using the initial model information of the material reserve category to obtain the training result information of the material reserve category. The training model information of the material reserve category is the model obtained after training with the material reserve category dataset.

[0150] S32333 calculates and processes the training result information of material reserve category to obtain the loss value of material reserve category;

[0151] S32334, determine whether the loss value of the material reserve category is less than the preset loss threshold of the material reserve category, and obtain the second judgment result;

[0152] It should be noted that the preset threshold for loss of material reserve categories is between [0.01, 0.05], but the specific values ​​are not limited in this embodiment of the invention.

[0153] It should be noted that the preset first material reserve loss threshold ranges from [0.05, 0.2], while the preset material reserve category loss threshold ranges from [0.01, 0.05]. This adjustment strategy from "coarse" to "fine" can effectively balance the exploratory and convergent aspects of the training process, so that as the technical solution of this application deepens, while maintaining sufficient exploratory ability, it can converge to a better solution in the later stage, avoiding premature convergence or overfitting.

[0154] When the second judgment result is negative, determine the material reserve category training model information as the material reserve category initial model information, and execute S32331;

[0155] When the second judgment result is yes, the material reserve category training model information is determined to be the material reserve category optimization model information;

[0156] S32335 utilizes the material reserve category optimization model information to calculate and process the material reserve category information, thereby obtaining material reserve relationship information.

[0157] It should be noted that the above calculation process uses material reserve category information as input to the material reserve category optimization model. The model calculates material reserve relationship information, which includes information about the connections, dependencies, optimal configuration schemes, and resource allocation strategies between materials. This relationship information plays a crucial role in material reserve management, especially in emergency management, material allocation, and supply chain management.

[0158] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0159] In an optional embodiment, the training result information of the material reserve category is calculated and processed to obtain the material reserve category loss value, including:

[0160] Using the material reserve category calculation model, the training results of the material reserve category are processed to obtain the material reserve category loss value;

[0161] The calculation model for the material reserve categories is as follows:

[0162]

[0163] In the formula, LBSS represents the loss value of the material reserve category, and LBZ(x i4 ) represents the training result value of the i-th sample in the training result information of the material reserve category, LB(x) i4 ) represents the preset true result value of the i4th sample, N4 represents the number of training result values ​​in the material reserve category training result information, and LBPC represents the preset material reserve category deviation coefficient.

[0164] It should be noted that the preset deviation coefficient for material reserve categories can be set by the user or obtained from historical data. Specifically, this embodiment of the invention does not limit the specific deviation coefficient.

[0165] It should be noted that the material reserve category calculation model guides the optimization process by calculating and weighting the error between the predicted results and the actual labels. Setting the deviation coefficient and squared error helps to adjust and optimize the material reserve model, thereby improving its accuracy and stability in the field of material reserves.

[0166] It should be noted that the preset deviation coefficient for material reserve categories ranges from [0.1, 0.3]. This allows for slight adjustments to the model's deviation, enabling the model to maintain flexibility over a wide range and adapt to different data distributions. It also helps avoid overfitting, which affects whether the model can effectively correct prediction errors and make the model's output closer to the true label.

[0167] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0168] In an optional embodiment, the material reserve relationship information and material classification information are processed to obtain material reserve knowledge graph information, including:

[0169] S331, Process the material reserve relationship information and material classification information to obtain material classification sequence information;

[0170] It should be noted that the above processing can be performed using algorithms or tools such as K-means and decision trees. In particular, the embodiments of the present invention do not limit the specific processing.

[0171] It should be noted that the above processing can extract meaningful material classification sequence information from large-scale material reserve data, thereby improving the efficiency and accuracy of material classification and management.

[0172] S332, integrate the material classification sequence information and material reserve relationship information to obtain the material classification matrix;

[0173] S333 integrates and processes the material classification matrix to obtain material reserve knowledge graph information.

[0174] It should be noted that the above integration process can be performed using DeepWalk, Node2Vec, or GraphSAGE. The specific implementation of this invention is not limited to any particular method.

[0175] It should be noted that through integration and processing, a knowledge graph of material reserves can be constructed. These graphs provide information on materials, material categories, and material relationships, thereby providing strong support for the rational allocation of materials and emergency management, and ultimately improving the optimization efficiency of material reserves and supply chain management, as well as emergency response efficiency.

[0176] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0177] In an optional embodiment, the material classification sequence information and material reserve relationship information are fused to obtain a material classification matrix, including:

[0178] S3321, The material classification sequence information is vectorized to obtain material classification vector information;

[0179] It should be noted that the above vectorization processing can be performed using algorithms or tools such as Word2Vec and TF-IDF. Specifically, the embodiments of the present invention do not limit the specifics.

[0180] It should be noted that vectorization can effectively capture the similarities and semantic relationships between material categories, providing accurate classification and clustering capabilities, and ultimately optimizing material management and supply chain efficiency.

[0181] S3322: Using the material classification matrix calculation model, the material classification vector information and material reserve relationship information are calculated and processed to obtain the material classification matrix;

[0182] The calculation model for the material classification matrix is ​​as follows:

[0183]

[0184] In the formula, WJZ is the material classification matrix, K is the material reserve relationship information, L is the material classification vector information, and K i5,j5 Let L be the relationship vector between the i5th material and the j5th material in the material reserve relationship information. j5 N5 represents the classification vector of the j5th material in the material classification vector information, N5 represents the number of relationship vectors in the material reserve relationship information, and M5 represents the number of classification vectors in the material classification vector information.

[0185] It should be noted that the material classification matrix calculation model helps to understand the relationship between material reserves and classification, providing support for optimizing material management, supply chain scheduling, and emergency response. Through weighted summation and logarithmic transformation, excessive bias towards certain material categories can be avoided, ensuring the balance and stability of the results.

[0186] It is evident that implementing the knowledge graph construction method based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0187] Example 2

[0188] Please see Figure 2 , Figure 2 This is a schematic diagram of a knowledge graph construction device based on material reserve information disclosed in an embodiment of the present invention. Figure 2 The described knowledge graph construction device based on material reserve information is applied to a knowledge graph construction optimization system based on material reserve information, such as a local server or cloud server used for knowledge graph construction based on material reserve information, etc., and the embodiments of the present invention are not limited thereto. Figure 2 As shown, the knowledge graph construction device based on material reserve information includes:

[0189] Module 201 is used to acquire material reserve information and material classification information;

[0190] Preprocessing module 202 is used to preprocess the material reserve information to obtain preprocessed material reserve information;

[0191] The calculation module 203 is used to process the pre-processed material reserve information and material classification information to obtain material reserve knowledge graph information.

[0192] It is evident that implementing the knowledge graph construction device based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0193] Example 3

[0194] Please see Figure 3 , Figure 3 This is a schematic diagram of another knowledge graph construction device based on material reserve information disclosed in an embodiment of the present invention. Figure 3 The described knowledge graph construction device based on material reserve information is applied to a knowledge graph construction optimization system based on material reserve information, such as a local server or cloud server used for knowledge graph construction based on material reserve information, etc., and the embodiments of the present invention are not limited thereto. Figure 3 As shown, the knowledge graph construction device based on material reserve information includes:

[0195] Processor 301;

[0196] A memory 302 containing executable program code is coupled to the processor 301;

[0197] The processor 301 calls the executable program code stored in the memory 302 to execute some or all of the steps of the knowledge graph construction method based on material reserve information in Embodiment 1.

[0198] It is evident that implementing the knowledge graph construction device based on material reserve information described in the embodiments of the present invention is beneficial for realizing the correlation analysis of materials, thereby providing strong support for the rational allocation of materials and emergency management, and further improving the optimization efficiency of material reserves and supply chain management and emergency response efficiency.

[0199] Example 4

[0200] This invention discloses a computer-readable storage medium storing computer instructions. When the computer instructions are invoked, they are used to execute some or all of the steps of the knowledge graph construction method based on material reserve information in Embodiment 1.

[0201] Example 5

[0202] This 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 perform some or all of the steps in the knowledge graph construction method based on material reserve information described in Embodiment 1.

[0203] The system embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0204] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0205] Finally, it should be noted that the knowledge graph construction method and apparatus based on material reserve information disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a knowledge graph based on material reserve information, characterized in that, The method includes: S1, obtain material reserve information and material classification information; S2, preprocess the material reserve information to obtain preprocessed material reserve information; S3, process the preprocessed material reserve information and the material classification information to obtain material reserve knowledge graph information, including: S31, Obtain the material reserve training dataset; S32, process the material reserve training dataset and the preprocessed material reserve information to obtain material reserve relationship information; S33, Process the material reserve relationship information and the material classification information to obtain material reserve knowledge graph information, including: S331, Process the material reserve relationship information and the material classification information to obtain material classification sequence information; S332, The material classification sequence information and the material reserve relationship information are fused to obtain a material classification matrix; S333, The material classification matrix is ​​integrated and processed to obtain material reserve knowledge graph information; S332 includes: S3321, The material classification sequence information is vectorized to obtain material classification vector information; S3322, Using the material classification matrix calculation model, the material classification vector information and the material reserve relationship information are calculated and processed to obtain the material classification matrix; The calculation model for the material classification matrix is ​​as follows: In the formula, WJZ is the material classification matrix, K is the material reserve relationship information, L is the material classification vector information, and K i5,j5 Let L be the relationship vector between the i5th material and the j5th material in the material reserve relationship information. j5 N5 is the classification vector of the j5th material in the material classification vector information, N5 is the number of relationship vectors in the material reserve relationship information, and M5 is the number of classification vectors in the material classification vector information.

2. The knowledge graph construction method based on material reserve information according to claim 1, characterized in that, The preprocessing of the material reserve information to obtain preprocessed material reserve information includes: S21, Remove stop words from the material reserve information to obtain the first material reserve preprocessing information; S22, Remove special characters from the first material reserve preprocessing information to obtain the second material reserve preprocessing information; S23, The second material reserve preprocessing information is processed in a unified format to obtain the third material reserve preprocessing information; S24, perform synonym conversion on the third material reserve preprocessing information to obtain preprocessed material reserve information.

3. The knowledge graph construction method based on material reserve information according to claim 1, characterized in that, The process of processing the material reserve training dataset and the preprocessed material reserve information to obtain material reserve relationship information includes: S321, Process the pre-processed material reserve information to obtain the material reserve information to be processed; S322, Process the material reserve information to be processed and the material reserve training dataset to obtain material reserve sequence information; S323, Process the material reserve sequence information to obtain material reserve relationship information.

4. The knowledge graph construction method based on material reserve information according to claim 3, characterized in that, The process of processing the pre-processed material reserve information to obtain the material reserve information to be processed includes: S3211, Perform feature word extraction processing on the preprocessed material reserve information to obtain material reserve feature word information; S3212, Process the material reserve feature word information and the preprocessed material reserve information to obtain a material reserve feature word vector set; S3213, Using the material reserve semantic calculation model, the feature word vector set of the material reserve is calculated and processed to obtain the material reserve information to be processed; The semantic calculation model for material reserves is as follows: In the formula, V represents the reserve information of the materials to be processed. i1 CXL is the semantic vector of the i1th material reserve in the material reserve information to be processed, and CXL is the set of feature word vectors of the material reserve. i1 and CXL j1 Let i and j be the i-th and j-th material reserve feature word vectors in the set of material reserve feature word vectors, respectively; N1 is the number of material reserve feature word vectors in the set of material reserve feature word vectors; δ1 is the first weight parameter; and ∈ represents the semantic deviation vector information of material reserves. i1 This refers to the i1th semantic deviation vector of material reserves in the semantic deviation vector information.

5. The knowledge graph construction method based on material reserve information according to claim 3, characterized in that, The process of processing the material reserve sequence information to obtain material reserve relationship information includes: S3231, Using a material reserve similarity calculation model, the material reserve sequence information is calculated and processed to obtain material reserve similarity information; The similarity calculation model for the material reserves is as follows: In the formula, XSD represents the similarity information of the material reserves. i3,j3 WZCB is the material reserve similarity value between the i3rd material and the j3rd material in the material reserve similarity information. i3 and WZCB j3 These are the i3rd and j3rd material reserve sequences in the material reserve sequence information, respectively, where |·| represents the magnitude of the vector, and θ1 represents the first similarity offset parameter; S3232, Perform category matching processing on the material reserve similarity information to obtain material reserve category information; S3233, Calculate and process the material reserve category information to obtain material reserve relationship information.

6. A knowledge graph construction device based on material reserve information, characterized in that, The device includes: processor; A memory containing executable program code is coupled to the processor; The processor calls the executable program code stored in the memory to execute the knowledge graph construction method based on material reserve information as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, which, when invoked, are used to execute the knowledge graph construction method based on material reserve information as described in any one of claims 1-5.

Images