Industrial chain security early warning method, device, equipment and computer readable medium
By structuring the original feature data of the industrial chain, and comprehensively considering the generation of early warning information after multiple indicators, the problems of early warning information accuracy and waste of network resources in the existing technology are solved, and higher intuitiveness and accuracy are achieved sex.
Patent Information
- Application Number
- CN202311622302.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-30
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2043-11-30
AI Technical Summary
When the existing technology generates security warning information in the industrial chain, the accuracy of the existing technology depends on training data, which has poor intuitiveness and interpretability, and the data source is insufficient, resulting in the accuracy of the warning information and waste of network resources.
By obtaining the original feature data of the target industrial chain, performing structured processing, generating a collection of node feature information, including entity features, industrial technology attributes and regional attributes, the completeness, security, toughness, stability and reliability are generated after summary processing. Indicators, comprehensively consider these indicators to generate early warning information, and avoid using machine learning or deep learning models.
It improves the intuitiveness and accuracy of early warning information, reduces the waste of network resources, and comprehensively considers multiple indicators to generate early warning information, reduces the sending of wrong early warnings, and improves the reliability of the industrial chain security early warning.
Smart Images

Figure CN117649199B_ABST
Abstract
Description
Technical Field
[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to industrial chain security early warning methods, devices, equipment, and computer-readable media. Background Art
[0002] The industrial chain refers to a series of interdependent and interrelated production processes and value chain links between multiple enterprises or organizations. With the rapid development of information technology, the security issues of the industrial chain have become increasingly prominent. The security indicators in the industrial chain have become the focus of attention of enterprises and institutions to ensure the reliability, stability and sustainable development of the entire industrial chain. At present, the main modeling based on machine learning, deep learning models or methods is used to predict the early warning information of the industrial chain, so as to warn the industrial chain and send the early warning information to related institutions. Before training the machine learning or deep learning model, the original data related to the industrial chain needs to be structured. At present, the main method is to structure the original data based on the existing large model.
[0003] However, the inventors have found that when the above method is used to generate safety warning information for the industrial chain, the following technical problems often occur:
[0004] First, the accuracy of the safety warning information of the industrial chain predicted by the machine learning or deep learning model is highly dependent on the training data, and there is no process data. The safety warning assessment value is directly obtained, which is less intuitive and interpretable. In addition, the data sources used in the modeling of the existing methods are not sufficient, and the angles and indicators considered are not comprehensive, resulting in poor accuracy of the generated industrial chain safety warning information. And when the wrong safety warning information of each industrial chain is sent to the relevant institutions, it causes a waste of network resources.
[0005] Second, when using the existing big model to perform structured processing on the original data, due to the small amount of labeled data in the vertical fields related to the industrial chain, the current big model is directly used when training the relationship extraction model, resulting in low accuracy in the relationship extraction of the original data, which in turn leads to low accuracy in the structured processing of the original data of the industrial chain based on the extracted relationships, and then leads to low accuracy in the early warning information generated for the industrial chain based on the structured data.
[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention
[0007] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.
[0008] Some embodiments of the present disclosure propose industrial chain security early warning methods, devices, electronic devices and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.
[0009] In a first aspect, some embodiments of the present disclosure provide an industrial chain security early warning method, the method comprising: acquiring each original feature data associated with each target industrial chain; performing structured processing on the above-mentioned each original feature data to obtain each node feature information set, wherein the node feature information set in the above-mentioned each node feature information set corresponds to the target industrial chain in the above-mentioned each target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in the above-mentioned each entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information; summarizing the industrial technology attribute information included in the above-mentioned each node feature information set to obtain summarized industrial technology attribute information; for each target industrial chain in the above-mentioned each target industrial chain, performing the following steps: determining the node feature information set corresponding to the above-mentioned target industrial chain as the target node feature information set; generating the integrity index information corresponding to the above-mentioned target industrial chain according to the various regional attribute information included in the various entity feature information included in the above-mentioned target node feature information set; generating the integrity index information corresponding to the above-mentioned target industrial chain according to the above Generate safety index information corresponding to the above-mentioned target industrial chain based on each regional attribute information included in each entity feature information included in the target node feature information set; generate toughness index information corresponding to the above-mentioned target industrial chain based on the above-mentioned aggregated industrial technology attribute information and each industrial technology attribute information included in the above-mentioned target node feature information set; generate stability index information corresponding to the above-mentioned target industrial chain based on each level attribute information included in each entity feature information included in the above-mentioned target node feature information set; generate reliability index information corresponding to the above-mentioned target industrial chain based on each level attribute information and each value object information included in each entity feature information included in the above-mentioned target node feature information set; generate early warning information corresponding to the above-mentioned target industrial chain based on the above-mentioned completeness index information, the above-mentioned safety index information, the above-mentioned toughness index information, the above-mentioned stability index information and the above-mentioned reliability index information; in response to determining that the above-mentioned early warning information meets the preset early warning condition, send the above-mentioned early warning information to the associated entity terminal to warn the above-mentioned target industrial chain, and control the associated remote playback device to play the early warning prompt information corresponding to the above-mentioned early warning information in voice.
[0010] In a second aspect, some embodiments of the present disclosure provide an industrial chain security early warning device, the device comprising: an acquisition unit, configured to acquire each original feature data associated with each target industrial chain; a structured processing unit, configured to perform structured processing on the above-mentioned each original feature data to obtain each node feature information set, wherein the node feature information set in the above-mentioned each node feature information set corresponds to the target industrial chain in the above-mentioned each target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in the above-mentioned each entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information; a summary unit, configured to summarize the industrial technology attribute information included in the above-mentioned each node feature information set to obtain summarized industrial technology attribute information; an execution unit, configured to perform the following steps for each target industrial chain in the above-mentioned each target industrial chain: determine the node feature information set corresponding to the above-mentioned target industrial chain as the target node feature information set; generate the corresponding above target industrial chain according to the regional attribute information included in the each entity feature information included in the above-mentioned target node feature information set The completeness index information of the target industrial chain is generated; according to each regional attribute information included in each entity feature information included in the target node feature information set, the safety index information corresponding to the target industrial chain is generated; according to the above-mentioned aggregated industrial technology attribute information and each industrial technology attribute information included in the target node feature information set, the toughness index information corresponding to the target industrial chain is generated; according to each level attribute information included in each entity feature information included in the target node feature information set, the stability index information corresponding to the target industrial chain is generated; according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set, the reliability index information corresponding to the target industrial chain is generated; according to the above completeness index information, the safety index information, the toughness index information, the stability index information and the reliability index information, the warning information corresponding to the target industrial chain is generated; in response to determining that the warning information meets the preset warning condition, the warning information is sent to the associated entity terminal to warn the target industrial chain, and the associated remote playback device is controlled to play the warning prompt information corresponding to the warning information.
[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.
[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method described in any implementation manner of the above-mentioned first aspect is implemented.
[0013] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the industrial chain security early warning method of some embodiments of the present disclosure, the intuitiveness and accuracy of the generated early warning information are improved, and the waste of network resources is reduced. Specifically, the reasons for the poor intuitiveness and accuracy of the generated early warning information and the waste of network resources are that the accuracy of the security early warning information of the industrial chain predicted by the model based on machine learning or deep learning is highly dependent on the training data, and there is no process data, and the security early warning evaluation value is directly obtained, which has poor intuitiveness and interpretability. In addition, the data source used in the modeling of the existing method is not sufficient, and the angles and indicators considered are not comprehensive enough, resulting in poor accuracy of the generated industrial chain security early warning information. And when the wrong security early warning information of each industrial chain is sent to the associated agency, it causes a waste of network resources. Based on this, the industrial chain security early warning method of some embodiments of the present disclosure first obtains each original feature data associated with each target industrial chain. Thus, each original feature data associated with each target industrial chain can be obtained. Then, the above-mentioned original feature data are subjected to structured processing to obtain each node feature information set, wherein the node feature information set in the above-mentioned node feature information set corresponds to the target industrial chain in the above-mentioned target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in the above-mentioned entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information. Thus, each node feature information set corresponding to each target industrial chain can be obtained. Afterwards, the industrial technology attribute information included in the above-mentioned node feature information set is aggregated to obtain aggregated industrial technology attribute information. Thus, aggregated industrial technology attribute information can be obtained. Then, for each target industrial chain in the above-mentioned target industrial chains, the following steps are performed: First, the node feature information set corresponding to the above-mentioned target industrial chain is determined as the target node feature information set. Thus, the target node feature information set can be obtained. Then, according to each regional attribute information included in each entity feature information included in the above-mentioned target node feature information set, the integrity index information corresponding to the above-mentioned target industrial chain is generated. Thus, the integrity index information of the target industrial chain can be obtained. Afterwards, based on the various regional attribute information included in the various entity feature information included in the above target node feature information set, the security index information corresponding to the above target industrial chain is generated. Thus, the security index information of the target industrial chain can be obtained. Next, based on the above-mentioned summarized industrial technology attribute information and the various industrial technology attribute information included in the above target node feature information set, the toughness index information corresponding to the above target industrial chain is generated. Thus, the toughness index information of the target industrial chain can be obtained.Then, according to each level attribute information included in each entity feature information included in the target node feature information set, the stability index information corresponding to the target industrial chain is generated. Thus, the stability index information of the target industrial chain can be obtained. Afterwards, according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set, the reliability index information corresponding to the target industrial chain is generated. Thus, the reliability index information of the target industrial chain can be obtained. Afterwards, according to the integrity index information, the safety index information, the toughness index information, the stability index information and the reliability index information, the early warning information corresponding to the target industrial chain is generated. Thus, the early warning information of the target industrial chain can be obtained. Finally, in response to determining that the early warning information meets the preset early warning condition, the early warning information is sent to the associated entity terminal to warn the target industrial chain, and the associated remote playback device is controlled to play the early warning prompt information corresponding to the early warning information. Thus, the early warning operation can be performed on the target industrial chain. The industrial chain security early warning method implemented can comprehensively consider the five types of indicators of the target industrial chain, namely, integrity, safety, toughness, stability and reliability, to generate early warning information, and considers the indicators more comprehensively. And no machine learning or deep learning model is used to predict the early warning information, thereby improving the intuitiveness and accuracy of the generated early warning information. And because the situation of sending wrong early warning information is reduced, the waste of network resources is reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.
[0015] Figure 1 is a flow chart of some embodiments of the industrial chain security early warning method according to the present disclosure;
[0016] Figure 2 It is a structural schematic diagram of some embodiments of the industrial chain safety early warning device according to the present disclosure;
[0017] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION
[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.
[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.
[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".
[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.
[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.
[0024] Figure 1 The process 100 of some embodiments of the industrial chain security early warning method according to the present disclosure is shown. The industrial chain security early warning method includes the following steps:
[0025] Step 101, obtaining various original feature data associated with each target industrial chain.
[0026] In some embodiments, the execution subject (such as a computing device) of the industrial chain security early warning method can obtain various original feature data associated with each target industrial chain. Among them, the above-mentioned target industrial chains can be target cities or various industrial chains existing in the country. The above-mentioned target city can be any city in the country. The target industrial chain in the above-mentioned target industrial chains can be but not limited to: Internet of Things industrial chain, medical industrial chain, nuclear power industrial chain, food industrial chain. The above-mentioned original feature data can be text data associated with the above-mentioned target industrial chains. For example, the data type of text data can be but not limited to: news text, financial text, legal text, science and technology text, product text. In practice, the above-mentioned execution subject can obtain the original feature data associated with each target industrial chain from the associated website and / or database.
[0027] Step 102, perform structured processing on each original feature data to obtain a feature information set of each node.
[0028] In some embodiments, the execution subject may perform structured processing on each of the original feature data to obtain each node feature information set. Among them, the node feature information set in each of the node feature information sets may correspond to the target industry chain in each of the target industry chains. The node feature information set in each of the node feature information sets may represent each link of the target industry chain. For example, each link may include but is not limited to: design link, procurement link, production link, sales link, and logistics link. The node feature information in the node feature information set may include each entity feature information, industrial technology attribute information, and node category information. The entity feature information in each of the entity feature information may represent the enterprise-related information associated with each link in each link of the target industry chain. The entity feature information in each of the entity feature information may include entity name information, each business classification information, grade attribute information, regional attribute information, and value object information. The industrial technology attribute information may represent the number of industrial technology knowledge information associated with each link in each link of the target industry chain. For example, the industrial technology knowledge information may be a patent. The node category information may represent the industrial chain link corresponding to the node feature information. For example, the industrial chain link may be a production link. The entity name information may represent the enterprise name. The value object information may represent the enterprise value information. For example, the enterprise value information may be market value. The above-mentioned hierarchical attribute information may represent the scale level of the enterprise. For example, the hierarchical attribute information may be high-tech enterprises, specialized and new enterprises, listed companies, China's top 500 or the world's top 500. The above-mentioned geographical attribute information may be the registered address of the enterprise. The above-mentioned various business classification information may represent the various links of the industrial chain covered by the enterprise. In practice, the above-mentioned execution subject may perform structured processing on the above-mentioned various original feature data in various ways to obtain a set of feature information of each node.
[0029] In some optional implementations of some embodiments, the execution subject may perform structured processing on the above-mentioned original feature data through the following steps to obtain feature information sets of each node:
[0030] The first step is to obtain a sample set and a test set. Among them, the samples in the sample set may include sample original feature data, each feature entity information and each feature entity relationship information. The test set may include each test original feature data. The feature entity information in each feature entity information may be an industrial chain entity, a node category entity, a node name entity, a value object entity, a level attribute entity, a regional attribute entity, an industrial technology entity or a business category entity. The sample original feature data may be annotated original feature data. Each feature entity information may represent each entity annotated from the original feature data. Each feature entity relationship information may represent each entity relationship annotated from the original feature data. Each test original feature data may be the original feature data of the feature entity information and feature entity relationship information to be identified. The industrial chain entity may represent the name of the industrial chain. The node category entity may represent the link of the industrial chain. The node name entity may represent the name of an enterprise or company. The value object entity may represent the value information of an enterprise. The regional attribute entity may represent the registered address of an enterprise. The industrial technology entity may represent the patent name. The business category entity may represent the industrial chain link covered by the enterprise.
[0031] In the second step, the samples in the above sample set, the test data in the above test set and the preset relationship template information are used as input, and each characteristic entity relationship information is used as output to train an entity feature information extraction model. Among them, the above entity feature information extraction model can characterize the relationship between the characteristic entity information and each characteristic entity relationship information. The above preset relationship template information can characterize each entity relationship template. As an example, when one entity is "XXX" and the other entity is "YYY", the entity relationship template can be "What is the relationship between XXX and YYY?".
[0032] The third step is to input the above-mentioned original feature data into the above-mentioned entity feature information extraction model to obtain each entity feature relationship information set. Among them, the entity feature relationship information set in the above-mentioned entity feature relationship information set can represent each entity feature relationship extracted from the original feature data of the entity. The above-mentioned entity feature relationship can represent the association relationship between each entity.
[0033] The fourth step is to map each entity feature relationship information set in the above-mentioned entity feature relationship information sets as an entity node and each entity feature relationship information as an entity node connection relationship into a preset network structure diagram. Among them, the above-mentioned preset network structure diagram can be a network topology diagram. In practice, the above-mentioned execution entity can determine the industrial chain entity as an industrial chain entity node. Determine the node category entity as a node category entity node. Determine the node name entity as a node name entity node. Determine the value object entity as a value object entity node. Determine the level attribute entity as a level attribute entity node. Determine the regional attribute entity as a regional attribute entity node. Determine the industrial technology entity as an industrial technology entity node. Determine the business category entity as a business category entity node.
[0034] Step 5: For each of the industrial chain entity nodes included in the preset network structure diagram, perform the following steps:
[0035] In the first sub-step, each node category entity node connected to the above-mentioned industrial chain entity node in the preset network structure diagram is determined as each target node category entity node.
[0036] The second sub-step is to perform the following steps for each target node category entity node in the above target node category entity nodes:
[0037] The first execution step is to determine each node name entity node connected to the target node category entity node in the preset network structure diagram as each target entity node. Among them, each target entity node can represent each enterprise or company in the industrial chain link corresponding to the target node category entity node.
[0038] The second execution step is to execute the following steps for each of the above target entity nodes:
[0039] The first sub-execution step is to determine the value object node connected to the target entity node in the preset network structure diagram as the value object information.
[0040] The second sub-execution step is to determine the level attribute nodes connected to the target entity node in the preset network structure diagram as the level attribute information.
[0041] The third sub-execution step is to determine the regional attribute node connected to the target entity node in the preset network structure diagram as the regional attribute information.
[0042] The fourth sub-execution step is to determine each service classification node connected to the target entity node in the preset network structure diagram as each service classification information.
[0043] The fifth sub-execution step is to determine the target entity node as entity name information.
[0044] The sixth sub-execution step is to determine the determined entity name information, value object information, level attribute information, regional attribute information and each business classification information as entity feature information.
[0045] The third execution step is to determine the number of each industrial technology entity connected to the above-mentioned target node category entity node in the preset network structure diagram as the industrial technology attribute information.
[0046] The fourth execution step is to determine the target node category entity node as the node category information.
[0047] The fifth execution step is to determine the determined entity feature information, industrial technology attribute information and node category information as node feature information.
[0048] The third sub-step is to determine the determined individual node feature information as a node feature information set.
[0049] In some optional implementations of some embodiments, the execution subject may train an entity feature information extraction model by taking the samples in the sample set, the test data in the test set and the preset relationship template information as input and taking each feature entity relationship information as output through the following steps:
[0050] In the first step, for each sample in the sample set, perform the following steps:
[0051] In the first sub-step, each entity information and each characteristic entity relationship information included in the original characteristic data of the sample entity included in the above sample are replaced, and the original characteristic data of the sample entity after the replacement is obtained as the target sample entity characteristic data. Among them, the above target sample entity characteristic data can be the characteristic entity relationship information after the replacement. In practice, the above execution entity can replace each entity information and each characteristic entity relationship information included in the original characteristic data of the sample entity with a preset character string, and obtain the original characteristic data of the sample entity after the replacement is obtained as the target sample entity characteristic data. Here, the specific setting of the above preset character string is not limited.
[0052] The second sub-step is to determine the target sample entity feature data and each feature entity relationship information of the sample as the target sample.
[0053] The second step is to determine the obtained target samples as a target sample set, wherein the target sample set may be the target samples after replacement processing.
[0054] The third step is to perform the following training steps based on the target sample set:
[0055] In the first sub-step, the preset relationship template information and the target sample entity feature data of at least one target sample in the target sample set are input into the initial relationship extraction model to obtain each predicted feature entity relationship information corresponding to the target sample entity feature data of the at least one target sample. The initial relationship extraction model may be a neural network model. For example, the neural network model may be a BERT model.
[0056] The second sub-step is to determine whether the initial relationship extraction model reaches the optimization target based on the above-mentioned predicted feature entity relationship information and the feature entity relationship information of the above-mentioned at least one target sample. Among them, the above-mentioned optimization target can represent that the loss rate of the initial relationship extraction model reaches a preset loss rate threshold. Here, there is no limitation on the specific setting of the above-mentioned preset loss rate threshold. The above-mentioned loss rate can be the slope of each loss value corresponding to the initial relationship extraction model. In practice, the above-mentioned execution entity can use the cross entropy loss function to determine the loss value of the initial relationship extraction model.
[0057] The third sub-step, in response to determining that the initial relation extraction model achieves the above-mentioned optimization goal, determines the initial relation extraction model as the trained relation extraction model.
[0058] The fourth step is to input the original feature data of each test entity included in the above test set into the above relationship extraction model to obtain each set of entity relationship information to be verified. Among them, the set of entity relationship information to be verified in the above set of entity relationship information to be verified can represent each entity relationship information extracted from the original feature data of the test entity.
[0059] In step 5, in response to determining that the number of target samples in the target samples does not meet a preset number condition, performing the following steps:
[0060] In the first sub-step, the test set is annotated according to each updated characteristic entity relationship information set corresponding to each of the entity relationship information sets to be verified, and the annotated test set is obtained as an expanded sample set. The each of the updated characteristic entity relationship information sets may be each of the entity relationship information sets to be verified after manual verification and correction. In practice, for each test data in the test set, in response to determining that the test data includes the characteristic entity information and characteristic entity relationship information in each of the updated characteristic entity relationship information sets, the execution subject may perform BIO annotation on each of the characteristic entity information and each of the characteristic entity relationship information in each of the updated characteristic entity relationship information sets included in the test data.
[0061] The second sub-step is to add the expanded sample set to the target sample set to expand the target sample set.
[0062] The third sub-step is to obtain the validation set again. The execution subject may obtain the validation set again from the associated database. The preset quantity condition may be that the number of target samples in the target samples is greater than a preset threshold. Here, the specific setting of the preset threshold is not limited.
[0063] In the fourth sub-step, the expanded target sample set is used as the target sample set, and the above training step is performed again based on the target sample set and the validation set.
[0064] In a sixth step, in response to determining that the number of target samples in the target sample set meets a preset number condition, the above relationship extraction model is determined as an entity feature information extraction model.
[0065] Optionally, in response to determining that the initial relationship extraction model does not achieve the above optimization goal, the above execution entity may also adjust the parameters of the initial relationship extraction model, and use the target sample set composed of unused target samples to perform the above training step again. In practice, the above execution entity may use a gradient descent method to adjust the parameters of the initial relationship extraction model.
[0066] The above technical solution and its related contents, as an inventive point of the embodiment of the present disclosure, solve the technical problem 2 mentioned in the background technology, "the accuracy of the early warning information of the generated industrial chain is low". The factors that lead to the low accuracy of the early warning information of the generated industrial chain are often as follows: when the original data is structured based on the existing large model, due to the small amount of annotated data in the vertical field related to the industrial chain, when the relationship extraction model is trained, the current existing large model is directly used, resulting in low accuracy of the relationship extraction of the original data, which leads to low accuracy of the structured processing of the original data of the industrial chain according to the extracted relationship, and then leads to low accuracy of the early warning information of the industrial chain generated according to the structured data. If the above factors are solved, the effect of improving the accuracy of the generated early warning information can be achieved. In order to achieve this effect, the present disclosure introduces a method of guiding the output of the relationship extraction model with preset relationship template information. When the annotated data set is small, the method of fine-tuning the large model and the preset relationship template information is adopted, and the expanded data set is re-annotated according to the entity relationship information after manual review, so as to improve the accuracy of the trained relationship extraction model for entity relationship extraction, thereby improving the accuracy of the structured processing of the original data, thereby improving the accuracy of the early warning information of the industrial chain generated according to the structured data.
[0067] Step 103, summarize the industrial technology attribute information included in each node feature information set to obtain summarized industrial technology attribute information.
[0068] In some embodiments, the execution subject may aggregate the industrial technology attribute information included in the above-mentioned node feature information sets to obtain aggregated industrial technology attribute information. The aggregated industrial technology attribute information may represent the total number of patents included in each target industrial chain. In practice, the execution subject may aggregate the industrial technology attribute information included in the above-mentioned node feature information sets to obtain aggregated industrial technology attribute information through the following steps:
[0069] In the first step, for each node feature information set in the above node feature information sets, the sum of each industry technology attribute information included in each node feature information in the above node feature information set is determined as the target industry technology attribute information to obtain each target industry technology attribute information. Among them, the above target industry technology attribute information can represent the total amount of each patent in each industry chain.
[0070] In the second step, the sum of the obtained technological attribute information of each target industry is determined as the summary industrial technological attribute information.
[0071] Step 104: for each target industrial chain in each target industrial chain, perform the following steps:
[0072] Step 1041: determine the node feature information set corresponding to the target industrial chain as the target node feature information set.
[0073] In some embodiments, the execution subject may determine the node feature information set corresponding to the target industrial chain as the target node feature information set, wherein the target node feature information set may represent each link of the target industrial chain.
[0074] Step 1042: Generate completeness index information of the corresponding target industrial chain according to each piece of regional attribute information included in each entity feature information included in the target node feature information set.
[0075] In some embodiments, the execution subject may generate the completeness index information corresponding to the target industrial chain according to the regional attribute information included in the entity feature information included in the target node feature information set. The completeness index information may be the completeness index of the target industrial chain. In practice, the execution subject may adopt various methods to generate the completeness index information corresponding to the target industrial chain according to the regional attribute information included in the entity feature information included in the target node feature information set.
[0076] In some optional implementations of some embodiments, the execution subject may generate the integrity index information corresponding to the target industrial chain according to each regional attribute information included in each entity feature information included in the target node feature information set through the following steps:
[0077] In the first step, for each target node feature information in the target node feature information set, perform the following steps:
[0078] In response to determining that there is entity feature information whose regional attribute information satisfies the preset regional condition among the entity feature information included in the target node feature information, the target node feature information is determined as the aggregated target node feature information. The preset regional condition may be that the regional attribute information included in the entity feature information is within a preset area. The preset area may be a target city or a country. The aggregated target node feature information may represent the links of the target industrial chain that can be supported by enterprises in the preset area.
[0079] The second step is to determine the number of aggregated target node feature information in each determined aggregated target node feature information as the number of nodes that the target regional entity can support. The number of nodes that the target regional entity can support can represent the number of links that all enterprises in the above preset area in the above target industrial chain can support.
[0080] The third step is to determine the number of target node characteristic information in the target node characteristic information set as the number of nodes. The number of nodes can represent the number of links in the target industrial chain.
[0081] The fourth step is to determine the ratio of the number of nodes that the target regional entity can support to the number of nodes as the completeness index information corresponding to the target industrial chain.
[0082] Step 1043, generating safety index information corresponding to the target industrial chain according to each piece of regional attribute information included in each entity feature information included in the target node feature information set.
[0083] In some embodiments, the execution subject may generate the security index information corresponding to the target industrial chain according to the regional attribute information included in the entity feature information included in the target node feature information set. The security index information may represent the security index of the target industrial chain. In practice, the execution subject may adopt various methods to generate the security index information corresponding to the target industrial chain according to the regional attribute information included in the entity feature information included in the target node feature information set.
[0084] In some optional implementations of some embodiments, the execution subject may generate security index information corresponding to the target industrial chain according to each regional attribute information included in each entity feature information included in the target node feature information set through the following steps:
[0085] In the first step, for each target node feature information in the target node feature information set, perform the following steps:
[0086] The first sub-step is to obtain the information related to the flow of each item of each entity name information included in the entity characteristic information included in the target node characteristic information. Among them, the information related to the flow of each item can be the flow ratio of each item produced by each enterprise represented by the entity name information. For example, the flow ratio of items can be the market share. In practice, the execution entity can obtain the information related to the flow of each item of each entity name information included in the entity characteristic information included in the target node characteristic information from the associated website.
[0087] The second sub-step is to determine, based on the various regional attribute information included in the above-mentioned various entity feature information, the various entity feature information that meets the above-mentioned preset regional conditions as the various target regional entity feature information. Among them, the above-mentioned various target regional entity feature information can be the various entity feature information of enterprises represented by regional attribute information within the above-mentioned preset area. In practice, the above-mentioned execution entity can determine the various entity feature information of enterprises represented by regional attribute information within the above-mentioned preset area in the above-mentioned various entity feature information as the various target regional entity feature information.
[0088] The third sub-step is to determine the item circulation information corresponding to the entity characteristic information of each target region as the item circulation related information of each target region. The item circulation related information of each target region may represent the item circulation ratio of each item produced by the enterprise in the preset region.
[0089] In the fourth sub-step, the ratio of the amount of the target area item circulation related information in the above-mentioned target area item circulation related information to the amount of the item circulation related information in the above-mentioned individual item circulation related information is determined as the node security index information corresponding to the above-mentioned target node characteristic information. The above-mentioned node security index information can represent the security of the link of the target industrial chain corresponding to the above-mentioned target node characteristic information.
[0090] In the second step, the average value of the obtained safety index information of each node is determined as the safety index information corresponding to the above-mentioned target industrial chain.
[0091] Step 1044, generating toughness index information corresponding to the target industrial chain based on the summarized industrial technology attribute information and the technological attribute information of each industry included in the target node feature information set.
[0092] In some embodiments, the execution subject may generate the toughness index information corresponding to the target industrial chain based on the summarized industrial technology attribute information and the individual industrial technology attribute information included in the target node feature information set. The toughness index information may characterize the toughness index of the target industrial chain. In practice, the execution subject may determine the ratio of the sum of the individual industrial technology attribute information included in the target node feature information set to the summarized industrial technology attribute information as the toughness index information corresponding to the target industrial chain.
[0093] Step 1045, generating stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set.
[0094] In some embodiments, the execution subject may generate stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set. The stability index information may characterize the stability index of the target industrial chain. In practice, the execution subject may adopt various methods to generate stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set.
[0095] In some optional implementations of some embodiments, the execution subject may generate stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set through the following steps:
[0096] The first step is to classify and process each entity feature information included in the target node feature information set according to each level attribute information included in each entity feature information included in the target node feature information set, and obtain a first entity feature information set, a second entity feature information set, a third entity feature information set, a fourth entity feature information set, and a fifth entity feature information set. Among them, the first entity feature information set can represent each enterprise whose level attribute information is a high-tech enterprise. The second entity feature information set can represent each enterprise whose level attribute information is a specialized, refined, and new enterprise. The third entity feature information set can represent each enterprise whose level attribute information is a listed enterprise. The fourth entity feature information set can represent each enterprise whose level attribute information is within a first preset ranking range. For example, the first preset ranking range can be China's top 500. The fifth entity feature information set can represent each enterprise whose level attribute information is within a second preset ranking range. For example, the second preset ranking range can be the world's top 500.
[0097] In the second step, the number of the first entity feature information in the first entity feature information set, the number of the second entity feature information in the second entity feature information set, the number of the third entity feature information in the third entity feature information set, the number of the fourth entity feature information in the fourth entity feature information set, and the number of the fifth entity feature information in the fifth entity feature information set are respectively determined as the first target value, the second target value, the third target value, the fourth target value, and the fifth target value.
[0098] The third step is to determine the difference between the first target value and the second target value as the first difference. The first difference may represent the difference between the number of high-tech enterprises and the number of specialized and new enterprises associated with the target industry.
[0099] The fourth step is to determine the difference between the second target value and the third target value as the second difference. The second difference may represent the difference between the number of specialized, sophisticated, and innovative enterprises and the number of listed enterprises associated with the target industry.
[0100] Step 5: Determine the difference between the third target value and the fourth target value as the third difference value. The third difference value may represent the difference between the number of listed companies associated with the target industry and the number of China's top 500 companies.
[0101] In step 6, the difference between the fourth target value and the fifth target value is determined as the fourth difference value. The fourth difference value may represent the difference between the number of China's top 500 companies and the number of the world's top 500 companies associated with the target industry.
[0102] In the seventh step, the first difference, the second difference, the third difference and the fourth difference are divided into intervals according to the preset interval division information to obtain the first interval, the second interval, the third interval and the fourth interval. The preset interval division information may include a first preset interval division threshold, a second preset interval division threshold and a third preset interval division threshold. In practice, in response to determining that the first difference is less than the first preset interval division threshold, the first preset interval is determined as the first interval. In response to determining that the first difference is greater than or equal to the first preset interval division threshold and less than the second preset interval division threshold, the second preset interval is determined as the first interval. In response to determining that the first difference is greater than or equal to the second preset interval division threshold and less than the third preset interval division threshold, the third preset interval is determined as the first interval. In response to determining that the first difference is greater than or equal to the second preset interval division threshold and less than the third preset interval division threshold, the fourth preset interval is determined as the first interval. Here, the steps of determining the second interval, the third interval and the fourth interval can refer to the steps of determining the first interval in step 1045, which will not be repeated here.
[0103] In the eighth step, the interval scores corresponding to the first interval, the second interval, the third interval and the fourth interval are determined to obtain the first score, the second score, the third score and the fourth score. In practice, the execution subject may determine the score corresponding to the first interval in the preset interval score information table as the first score. The score corresponding to the second interval in the preset interval score information table is determined as the second score. The score corresponding to the third interval in the preset interval score information table is determined as the third score. The score corresponding to the fourth interval in the preset interval score information table is determined as the fourth score. The preset interval score information table may characterize the relationship between the interval and the score. It should be noted that the larger the upper boundary of the interval, the lower the score, which characterizes the worse stability of the industrial chain. As an example, the preset interval score information in the preset interval score information table may be "interval: [10,20), score: 10; interval: [20,30), score: 5".
[0104] In a ninth step, an average value of the first score, the second score, the third score and the fourth score is determined as the stability index information corresponding to the target industrial chain.
[0105] In some optional implementations of some embodiments, the execution subject may classify the target aggregated entity feature information according to the level attribute information included in each target aggregated entity feature information in the target aggregated entity feature information set to obtain a first entity feature information set, a second entity feature information set, a third entity feature information set, a fourth entity feature information set, and a fifth entity feature information set through the following steps:
[0106] In the first step, the first preset entity feature information set, the second preset entity feature information set, the third preset entity feature information set, the fourth preset entity feature information set and the fifth preset entity feature information set are cleared.
[0107] In the second step, for each target summary entity feature information in the target summary entity feature information set, perform the following steps:
[0108] In a first sub-step, in response to determining that the level attribute information included in the target aggregated entity feature information satisfies a first preset level condition, the target aggregated entity feature information is added to a first preset entity feature information set. The first preset level condition may be that the level attribute information included in the entity feature information is a high-tech enterprise.
[0109] In a second sub-step, in response to determining that the level attribute information included in the target aggregated entity feature information satisfies a second preset level condition, the target aggregated entity feature information is added to a second preset entity feature information set. The second preset level condition may be that the level attribute information included in the entity feature information is a specialized, refined, special and innovative enterprise.
[0110] In a third sub-step, in response to determining that the level attribute information included in the target aggregated entity feature information satisfies a third preset level condition, the target aggregated entity feature information is added to a third preset entity feature information set. The third preset level condition may be that the level attribute information included in the entity feature information is a listed company.
[0111] In a fourth sub-step, in response to determining that the level attribute information included in the target aggregated entity feature information satisfies a fourth preset level condition, the target aggregated entity feature information is added to a fourth preset entity feature information set. The fourth preset level condition may be that the level attribute information included in the entity feature information is a China Fortune 500 company.
[0112] In a fifth sub-step, in response to determining that the level attribute information included in the target aggregated entity feature information satisfies a fifth preset level condition, the target aggregated entity feature information is added to a fifth preset entity feature information set. The fifth preset level condition may be that the level attribute information included in the entity feature information is a Fortune 500 company.
[0113] In the third step, the obtained first preset entity feature information set, second preset entity feature information set, third preset entity feature information set, fourth preset entity feature information set and fifth preset entity feature information set are respectively determined as the first entity feature information set, the second entity feature information set, the third entity feature information set, the fourth entity feature information set and the fifth entity feature information set.
[0114] Step 1046, generating reliability index information corresponding to the target industrial chain according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set.
[0115] In some embodiments, the execution subject may generate the reliability index information corresponding to the target industrial chain according to the various level attribute information and various value object information included in the entity feature information included in the target node feature information set. The reliability index information may characterize the reliability index of the target industrial chain. In practice, the execution subject may adopt various methods to generate the reliability index information corresponding to the target industrial chain according to the various level attribute information and various value object information included in the entity feature information included in the target node feature information set.
[0116] In some optional implementations of some embodiments, the execution subject may generate reliability index information corresponding to the target industrial chain according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set through the following steps:
[0117] In the first step, for each target node feature information in the target node feature information set, perform the following steps:
[0118] The first sub-step is to determine the first value weight information corresponding to each value object information included in each entity feature information included in the target node feature information according to the preset weight constraint information. The preset weight constraint information may be a value object information interval and weight relationship table. The value object information interval and weight relationship table may represent the relationship between the value object information interval and the weight. The value object information interval and weight relationship in the value object information interval and weight relationship table may include the value object information interval and the weight corresponding to the value object information interval. For example, the value object information interval and weight relationship table may be "value object information interval: [0, 10 billion), weight: 1; value object information interval: [10 billion, 100 billion), weight: 2; value object information interval: [100 billion, +∞), weight: 3". The first value weight information may represent the weights of each value object information included in each entity feature information included in the target node feature information. In practice, the execution subject may determine the weights corresponding to each value object information interval corresponding to each value object information in the value object information interval and weight relationship table as the first value weight information.
[0119] The second sub-step is to cluster the above-mentioned first value weight information to obtain various first value weight information sets. Among them, the various first value weight information included in the first value weight information set are the same. In practice, the above-mentioned execution subject can combine the identical first value weight information in the above-mentioned various first value weight information into a first value weight information set to obtain various first value weight information sets.
[0120] The third sub-step is to determine the product of the number of first value weight information in each first value weight information set in each of the above first value weight information sets and the above first value weight information as the first target weight information to obtain each first target weight information. The above each first target weight information can represent the enterprise weight of each different value level.
[0121] The fourth sub-step is to determine the sum of the obtained first target weight information as the first node volume index information corresponding to the target node characteristic information. The first node volume index information can represent the enterprise volume index of the link corresponding to the target node characteristic information in the target industrial chain.
[0122] The fifth sub-step is to determine, according to each level attribute information included in each entity feature information included in the target node feature information set, each entity feature information that meets the preset level condition among each entity feature information included in the target node feature information set as each target level entity feature information. The preset level condition may be that the level attribute information included in the entity feature information is a listed company. In practice, the execution entity may determine each entity feature information whose level attribute information is a listed company among each entity feature information included in the target node feature information set as each target level entity feature information.
[0123] The sixth sub-step is to determine the second value weight information corresponding to each value object information included in each target level entity feature information according to the preset weight constraint information. The second value weight information can represent the weights of listed companies of different value levels. Here, the step of determining each second value weight information can refer to the step of determining each first value weight information in step 1046, which will not be repeated here.
[0124] The seventh sub-step is to cluster the above-mentioned second value weight information to obtain a set of second value weight information, wherein the second value weight information included in the set of second value weight information are all the same.
[0125] In the eighth sub-step, the product of the number of second value weight information in each second value weight information set in each of the above second value weight information sets and the above second value weight information is determined as the second target weight information to obtain each second target weight information. The above each second target weight information can represent the weights of listed companies of different value magnitudes.
[0126] The ninth sub-step is to determine the sum of the obtained second target weight information as the second node volume index information corresponding to the target node characteristic information. The second node volume index information can represent the volume index of the listed companies in the link corresponding to the target node characteristic information in the target industrial chain.
[0127] In a tenth sub-step, the ratio of the second node volume index information to the first node volume index information is determined as the node participation index information corresponding to the target node characteristic information. The node participation index information can represent the participation of listed companies in the link corresponding to the target node characteristic information in the target industrial chain.
[0128] The second step is to determine the average of the determined volume index information of each second node as the volume index information corresponding to the above target industrial chain. The volume index information of the above target industrial chain can represent the volume of listed companies in the above target industrial chain.
[0129] The third step is to determine the average of the determined participation index information of each node as the participation index information corresponding to the above target industrial chain. The participation index information of the above target industrial chain can represent the participation of listed companies in the above target industrial chain.
[0130] The fourth step is to perform weighted summation on the volume index information and the participation index information to obtain the reliability index information corresponding to the target industrial chain. Here, the specific setting of the weights of the volume index information and the participation index information is not limited.
[0131] Step 1047, generating early warning information corresponding to the target industrial chain according to the integrity index information, the safety index information, the toughness index information, the stability index information and the reliability index information.
[0132] In some embodiments, the above-mentioned execution entity may generate early warning information corresponding to the above-mentioned target industrial chain based on the above-mentioned completeness index information, the above-mentioned safety index information, the above-mentioned toughness index information, the above-mentioned stability index information and the above-mentioned reliability index information. Among them, the above-mentioned early warning information may characterize the degree of safety risk of the target industrial chain. In practice, the above-mentioned execution entity may perform weighted summation on the above-mentioned completeness index information, the above-mentioned safety index information, the above-mentioned toughness index information, the above-mentioned stability index information and the above-mentioned reliability index information to obtain the early warning information corresponding to the above-mentioned target industrial chain. Here, the specific setting of the weights of the above-mentioned completeness index information, the above-mentioned safety index information, the above-mentioned toughness index information, the above-mentioned stability index information and the above-mentioned reliability index information is not limited.
[0133] Step 1048, in response to determining that the warning information meets the preset warning conditions, the warning information is sent to the associated entity terminal to warn the target industrial chain, and the associated remote playback device is controlled to play the warning prompt information corresponding to the warning information by voice.
[0134] In some embodiments, in response to determining that the above-mentioned warning information meets the preset warning condition, the above-mentioned execution subject may send the above-mentioned warning information to the associated entity terminal to warn the above-mentioned target industrial chain, and control the associated remote playback device to voice play the warning prompt information of the corresponding warning information. Among them, the above-mentioned preset warning condition may be that the above-mentioned warning information is greater than the preset warning threshold. Here, the specific setting of the above-mentioned preset warning threshold is not limited. The above-mentioned entity terminal may be a terminal device of an institution. The above-mentioned remote playback device may be, but is not limited to: an electronic whiteboard, a video conferencing device, and a projector. The above-mentioned warning prompt information may be a prompt information for warning the above-mentioned target industrial chain. It should be noted that timely warning of the security of the target industrial chain can take timely countermeasures when risks occur, thereby ensuring the security and stability of the target industrial chain. Thereby, obstacles to the circulation of goods can be avoided. For example, obstacles to the circulation of goods may be supply chain interruptions and sales chain interruptions.
[0135] Optionally, first, the execution subject may also create a warning knowledge graph corresponding to each target industrial chain according to the feature information set of each node and each warning information corresponding to each target industrial chain. In practice, the execution subject may create a warning knowledge graph corresponding to each target industrial chain according to the feature information set of each node and each warning information corresponding to each target industrial chain through the following steps:
[0136] The first step is to identify the above-mentioned target industrial chains as industrial chain entities.
[0137] The second step is to determine the above-mentioned warning information as each warning entity.
[0138] The third step is to determine each node category information included in the above-mentioned each node feature information set as each node category entity.
[0139] The fourth step is to determine each entity feature information included in the above-mentioned each node feature information set as each enterprise entity.
[0140] In the fifth step, each value object information included in each entity feature information included in each node feature information set is determined as each value object entity.
[0141] In the sixth step, the warning type is determined as the entity relationship between the industrial chain entity and the warning entity.
[0142] In the seventh step, the node type is determined as the entity relationship between the industrial chain entity and the node category entity.
[0143] In the eighth step, the enterprise support node type is determined as the entity relationship between the enterprise entity and the node category entity.
[0144] The ninth step is to determine the value object attributes as the entity relationship between the enterprise entity and the value object entity.
[0145] The tenth step is to associate the determined industrial chain entities, warning entities, node category entities, enterprise entities, and value object entities according to the determined entity relationships to obtain the warning knowledge graph corresponding to the above-mentioned target industrial chains.
[0146] Then, the above warning knowledge graph is stored in the graph database.
[0147] Afterwards, in response to detecting a query request corresponding to the above-mentioned early warning knowledge graph, the associated subgraph corresponding to the above-mentioned query request in the above-mentioned early warning knowledge graph is displayed in a three-dimensional visualization. Among them, the above-mentioned query request can be a network request for querying the above-mentioned early warning knowledge graph. The above-mentioned query request may include a query entity. The above-mentioned query entity may be: an industrial chain entity, a node category entity, an enterprise entity or a value object entity. The above-mentioned associated subgraph may be an associated subgraph corresponding to the above-mentioned query entity in the above-mentioned early warning knowledge graph. In practice, in response to detecting a query request corresponding to the above-mentioned early warning knowledge graph, the above-mentioned execution subject may display the associated subgraph corresponding to the query entity included in the above-mentioned query request using a three-dimensional visualization tool. It should be noted that due to the large amount of information associated with the industrial chain and the redundancy, the database design table structure is complex, resulting in a large consumption of storage resources and a slow data query speed. The storage method of the above-mentioned knowledge graph does not need to design a complex table structure, reduces data redundancy, and thus reduces the waste of storage resources. And the design of the graph structure improves the data query speed. Moreover, the three-dimensional visualization display can improve the intuitiveness of users viewing query results.
[0148] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the industrial chain security early warning method of some embodiments of the present disclosure, the intuitiveness and accuracy of the generated early warning information are improved, and the waste of network resources is reduced. Specifically, the reasons for the poor intuitiveness and accuracy of the generated early warning information and the waste of network resources are that the accuracy of the security early warning information of the industrial chain predicted by the model based on machine learning or deep learning is highly dependent on the training data, and there is no process data, and the security early warning evaluation value is directly obtained, which has poor intuitiveness and interpretability. In addition, the data source used in the modeling of the existing method is not sufficient, and the angles and indicators considered are not comprehensive enough, resulting in poor accuracy of the generated industrial chain security early warning information. And when the wrong security early warning information of each industrial chain is sent to the associated agency, it causes a waste of network resources. Based on this, the industrial chain security early warning method of some embodiments of the present disclosure first obtains each original feature data associated with each target industrial chain. Thus, each original feature data associated with each target industrial chain can be obtained. Then, the above-mentioned original feature data are subjected to structured processing to obtain each node feature information set, wherein the node feature information set in the above-mentioned node feature information set corresponds to the target industrial chain in the above-mentioned target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in the above-mentioned entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information. Thus, each node feature information set corresponding to each target industrial chain can be obtained. Afterwards, the industrial technology attribute information included in the above-mentioned node feature information set is aggregated to obtain aggregated industrial technology attribute information. Thus, aggregated industrial technology attribute information can be obtained. Then, for each target industrial chain in the above-mentioned target industrial chains, the following steps are performed: First, the node feature information set corresponding to the above-mentioned target industrial chain is determined as the target node feature information set. Thus, the target node feature information set can be obtained. Then, according to each regional attribute information included in each entity feature information included in the above-mentioned target node feature information set, the integrity index information corresponding to the above-mentioned target industrial chain is generated. Thus, the integrity index information of the target industrial chain can be obtained. Afterwards, based on the various regional attribute information included in the various entity feature information included in the above target node feature information set, the security index information corresponding to the above target industrial chain is generated. Thus, the security index information of the target industrial chain can be obtained. Next, based on the above-mentioned summarized industrial technology attribute information and the various industrial technology attribute information included in the above target node feature information set, the toughness index information corresponding to the above target industrial chain is generated. Thus, the toughness index information of the target industrial chain can be obtained.Then, according to each level attribute information included in each entity feature information included in the target node feature information set, the stability index information corresponding to the target industrial chain is generated. Thus, the stability index information of the target industrial chain can be obtained. Afterwards, according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set, the reliability index information corresponding to the target industrial chain is generated. Thus, the reliability index information of the target industrial chain can be obtained. Afterwards, according to the integrity index information, the safety index information, the toughness index information, the stability index information and the reliability index information, the early warning information corresponding to the target industrial chain is generated. Thus, the early warning information of the target industrial chain can be obtained. Finally, in response to determining that the early warning information meets the preset early warning condition, the early warning information is sent to the associated entity terminal to warn the target industrial chain, and the associated remote playback device is controlled to play the early warning prompt information corresponding to the early warning information. Thus, the early warning operation can be performed on the target industrial chain. The industrial chain security early warning method implemented can comprehensively consider the five types of indicators of the target industrial chain, namely, integrity, safety, toughness, stability and reliability, to generate early warning information, and considers the indicators more comprehensively. And no machine learning or deep learning model is used to predict the early warning information, thereby improving the intuitiveness and accuracy of the generated early warning information. And because the situation of sending wrong early warning information is reduced, the waste of network resources is reduced.
[0149] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an industrial chain safety early warning device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.
[0150] like Figure 2As shown, the industrial chain security early warning device 200 of some embodiments includes: an acquisition unit 201, a structured processing unit 202, a summary unit 203 and an execution unit 204. Among them, the acquisition unit 201 is configured to acquire each original feature data associated with each target industrial chain; the structured processing unit 202 is configured to perform structured processing on the above-mentioned original feature data to obtain each node feature information set, wherein the node feature information set in the above-mentioned each node feature information set corresponds to the target industrial chain in the above-mentioned each target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in the above-mentioned each entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information; the aggregation unit 203 is configured to aggregate the industrial technology attribute information included in the above-mentioned each node feature information set to obtain aggregated industrial technology attribute information; the execution unit 204 is configured to perform the following steps for each target industrial chain in the above-mentioned each target industrial chain: determine the node feature information set corresponding to the above-mentioned target industrial chain as the target node feature information set; generate a complete industrial chain corresponding to the above-mentioned target industrial chain according to the regional attribute information included in the each entity feature information included in the above-mentioned target node feature information set According to each of the regional attribute information included in each entity feature information included in the target node feature information set, generate the safety index information corresponding to the target industrial chain; according to the above-mentioned aggregated industrial technology attribute information and each of the industrial technology attribute information included in the target node feature information set, generate the toughness index information corresponding to the target industrial chain; according to each of the level attribute information included in each of the entity feature information included in the target node feature information set, generate the stability index information corresponding to the target industrial chain; according to each of the level attribute information and each of the value object information included in each of the entity feature information included in the target node feature information set, generate the reliability index information corresponding to the target industrial chain; according to the above-mentioned integrity index information, the above-mentioned safety index information, the above-mentioned toughness index information, the above-mentioned stability index information and the above-mentioned reliability index information, generate the warning information corresponding to the target industrial chain; in response to determining that the above-mentioned warning information meets the preset warning condition, send the above-mentioned warning information to the associated entity terminal to warn the target industrial chain, and control the associated remote playback device to play the warning prompt information corresponding to the above-mentioned warning information in voice.
[0151] It is understandable that the units recorded in the industrial chain security early warning device 200 and the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.
[0152] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, a computing device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.
[0153] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.
[0154] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.
[0155] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.
[0156] It should be noted that the computer-readable medium recorded in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
[0157] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.
[0158] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains each original feature data associated with each target industrial chain; performs structured processing on each original feature data to obtain each node feature information set, wherein the node feature information set in each node feature information set corresponds to the target industrial chain in each target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in each entity feature information includes entity name information, each business classification information, grade attribute information, regional attribute information and value object information; summarizes the industrial technology attribute information included in each node feature information set to obtain summarized industrial technology attribute information; for each target industrial chain in each target industrial chain, performs the following steps: determine the node feature information set corresponding to the target industrial chain as the target node feature information set; generate the integrity index corresponding to the target industrial chain according to the regional attribute information included in each entity feature information included in the target node feature information set; The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes. The target node characteristic information set comprises a plurality of target nodes, a plurality of target nodes, and a plurality of target nodes.
[0159] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0160] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0161] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, a structured processing unit, a summary unit, and an execution unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring each original feature data associated with each target industry chain".
[0162] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.
[0163] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.
Claims
1. An industrial chain security early warning method, comprising: Obtain various original feature data associated with each target industrial chain; Performing structured processing on the original feature data to obtain each node feature information set, wherein the node feature information set in each node feature information set corresponds to the target industrial chain in each target industrial chain, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in each entity feature information includes entity name information, each business classification information, level attribute information, regional attribute information and value object information; Summarizing the industrial technology attribute information included in the characteristic information sets of each node to obtain summarized industrial technology attribute information; For each target industrial chain in the target industrial chains, the following steps are performed: Determine the node feature information set corresponding to the target industrial chain as the target node feature information set; Generate completeness index information corresponding to the target industrial chain according to each piece of regional attribute information included in each piece of entity feature information included in the target node feature information set; Generate security index information corresponding to the target industrial chain according to each region attribute information included in each entity feature information included in the target node feature information set; Generate toughness index information corresponding to the target industrial chain according to the summarized industrial technology attribute information and each industrial technology attribute information included in the target node feature information set, and determine the toughness index information corresponding to the target industrial chain by the ratio of the sum of each industrial technology attribute information included in the target node feature information set to the summarized industrial technology attribute information; Generate stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set; Generate reliability index information corresponding to the target industrial chain according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set; Generate early warning information corresponding to the target industrial chain according to the integrity index information, the safety index information, the toughness index information, the stability index information and the reliability index information; In response to determining that the warning information meets the preset warning condition, the warning information is sent to the associated entity terminal to warn the target industrial chain, and the associated remote playback device is controlled to play the warning prompt information corresponding to the warning information by voice; The generating of the integrity index information corresponding to the target industrial chain according to each area attribute information included in each entity feature information included in the target node feature information set includes: For each target node feature information in the target node feature information set, perform the following steps: In response to determining that there is entity feature information whose regional attribute information satisfies a preset regional condition among the entity feature information included in the target node feature information, determining the target node feature information as aggregated target node feature information; Determine the number of aggregated target node feature information in each determined aggregated target node feature information as the number of nodes that the target regional entity can support; Determine the number of target node feature information in the target node feature information set as the number of nodes; Determine the ratio of the number of nodes that the target regional entity can support to the number of nodes as the completeness index information corresponding to the target industrial chain; The step of generating the stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set includes: According to each level attribute information included in each entity feature information included in the target node feature information set, each entity feature information included in the target node feature information set is classified and processed to obtain a first entity feature information set, a second entity feature information set, a third entity feature information set, a fourth entity feature information set and a fifth entity feature information set; Determine the amount of first entity feature information in the first entity feature information set, the amount of second entity feature information in the second entity feature information set, the amount of third entity feature information in the third entity feature information set, the amount of fourth entity feature information in the fourth entity feature information set, and the amount of fifth entity feature information in the fifth entity feature information set as a first target value, a second target value, a third target value, a fourth target value, and a fifth target value, respectively; determining a difference between the first target value and the second target value as a first difference; determining a difference between the second target value and the third target value as a second difference; determining a difference between the third target value and the fourth target value as a third difference; determining a difference between the fourth target value and the fifth target value as a fourth difference; According to preset interval division information, the first difference, the second difference, the third difference and the fourth difference are divided into intervals to obtain a first interval, a second interval, a third interval and a fourth interval; Determine interval scores corresponding to the first interval, the second interval, the third interval, and the fourth interval to obtain a first score, a second score, a third score, and a fourth score; An average value of the first score, the second score, the third score and the fourth score is determined as stability index information corresponding to the target industrial chain.
2. The method according to claim 1, wherein: The method further comprises: Creating a warning knowledge graph corresponding to each target industrial chain according to each node feature information set and each warning information corresponding to each target industrial chain; Storing the early warning knowledge graph in a graph database; In response to detecting a query request corresponding to the early warning knowledge graph, a related sub-graph corresponding to the query request in the early warning knowledge graph is displayed in three-dimensional visualization.
3. The method according to claim 1, wherein: The structural processing of each of the original feature data to obtain a feature information set of each node includes: Obtain a sample set and a test set, wherein the samples in the sample set include original feature data of the samples, information of each feature entity, and relationship information of each feature entity; the test set includes original feature data of each test; the feature entity information in each feature entity information is an industrial chain entity, a node category entity, a node name entity, a value object entity, a level attribute entity, a regional attribute entity, an industrial technology entity, or a business category entity; Taking the samples in the sample set, the test data in the test set and the preset relationship template information as input, and taking the relationship information of each characteristic entity as output, training an entity feature information extraction model; Inputting each of the original feature data into the entity feature information extraction model to obtain each entity feature relationship information set; For each entity feature relationship information set in each entity feature relationship information set, mapping each entity feature relationship information in the entity feature relationship information set as an entity node connection relationship into a preset network structure diagram; For each of the industrial chain entity nodes included in the preset network structure diagram, the following steps are performed: Determine each node category entity node connected to the industrial chain entity node in the preset network structure diagram as each target node category entity node; For each target node category entity node in the target node category entity nodes, the following steps are performed: Determine each node name entity node connected to the target node category entity node in the preset network structure diagram as each target entity node; For each of the target entity nodes, the following steps are performed: Determine the value object node connected to the target entity node in the preset network structure diagram as the value object information; Determine the hierarchical attribute nodes connected to the target entity node in the preset network structure diagram as hierarchical attribute information; Determine the regional attribute node connected to the target entity node in the preset network structure diagram as the regional attribute information; Determine each service classification node connected to the target entity node in the preset network structure diagram as each service classification information; Determine the target entity node as entity name information; Determine the determined entity name information, value object information, level attribute information, regional attribute information and each business classification information as entity feature information; Determine the number of each industrial technology entity connected to the target node category entity node in the preset network structure diagram as industrial technology attribute information; Determine the target node category entity node as node category information; Determine the determined entity feature information, industrial technology attribute information and node category information as node feature information; The determined individual node feature information is determined as a node feature information set.
4. The method according to claim 3, wherein: The generating of the security index information corresponding to the target industrial chain according to each area attribute information included in each entity feature information included in the target node feature information set includes: For each target node feature information in the target node feature information set, perform the following steps: Acquire each item flow related information of each entity name information included in each entity feature information included in the target node feature information; According to each piece of regional attribute information included in each piece of entity feature information, each piece of entity feature information that meets a preset regional condition is determined as each piece of target regional entity feature information; Determine each item circulation information corresponding to each target area entity characteristic information as each target area item circulation related information; Determine the node security index information corresponding to the target node characteristic information by the ratio of the amount of the target area item circulation related information in the item circulation related information of each target area to the amount of the item circulation related information in each item circulation related information; The average value of the obtained safety index information of each node is determined as the safety index information corresponding to the target industrial chain.
5. The method according to claim 4, wherein: The generating of reliability index information corresponding to the target industrial chain according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set includes: For each target node feature information in the target node feature information set, perform the following steps: Determine, according to preset weight constraint information, each first value weight information corresponding to each value object information included in each entity feature information included in the target node feature information; Clustering the various first value weight information to obtain various first value weight information sets, wherein the various first value weight information included in the first value weight information sets are all the same; Determine the product of the number of first value weight information in each first value weight information set in each of the first value weight information sets and the first value weight information as the first target weight information, to obtain each first target weight information; Determine the sum of each first target weight information obtained as the first node volume index information corresponding to the target node feature information; According to each level attribute information included in each entity feature information included in the target node feature information set, each entity feature information that meets a preset level condition among each entity feature information included in the target node feature information set is determined as each target level entity feature information; Determining, according to the preset weight constraint information, each second value weight information corresponding to each value object information included in each target level entity feature information; Clustering the respective second value weight information to obtain respective second value weight information sets, wherein the respective second value weight information included in the second value weight information sets are all the same; Determine the product of the number of second value weight information in each second value weight information set in each second value weight information set and the second value weight information as the second target weight information to obtain each second target weight information; Determining the sum of each obtained second target weight information as the second node volume index information corresponding to the target node feature information; Determine the ratio of the second node volume index information to the first node volume index information as the node participation index information corresponding to the target node feature information; Determine the average of the determined volume index information of each second node as the volume index information corresponding to the target industrial chain; Determine the average of the determined participation index information of each node as the participation index information corresponding to the target industrial chain; The volume index information and the participation index information are weighted and summed to obtain the reliability index information corresponding to the target industrial chain.
6. An industrial chain safety early warning device, comprising: An acquisition unit is configured to acquire each original feature data associated with each target industrial chain; A structured processing unit is configured to perform structured processing on each of the original feature data to obtain each node feature information set, wherein the node feature information set in each of the node feature information sets corresponds to the target industrial chain in each of the target industrial chains, the node feature information in the node feature information set includes each entity feature information, industrial technology attribute information and node category information, and the entity feature information in each of the entity feature information includes entity name information, each business classification information, level attribute information, regional attribute information and value object information; A summarizing unit is configured to summarize the industrial technology attribute information included in the set of characteristic information of each node to obtain summarized industrial technology attribute information; The execution unit is configured to perform the following steps for each target industrial chain in the target industrial chains: determine the node feature information set corresponding to the target industrial chain as the target node feature information set; generate the integrity index information corresponding to the target industrial chain according to the various regional attribute information included in the various entity feature information included in the target node feature information set; generate the security index information corresponding to the target industrial chain according to the various regional attribute information included in the various entity feature information included in the target node feature information set; generate the toughness index information corresponding to the target industrial chain according to the summarized industrial technological attribute information and the various industrial technological attribute information included in the target node feature information set, and determine the ratio of the sum of the various industrial technological attribute information included in the target node feature information set to the summarized industrial technological attribute information as the corresponding target industrial chain. The toughness index information of the target industrial chain; according to each level attribute information included in each entity feature information included in the target node feature information set, generate the stability index information corresponding to the target industrial chain; according to each level attribute information and each value object information included in each entity feature information included in the target node feature information set, generate the reliability index information corresponding to the target industrial chain; according to the integrity index information, the safety index information, the toughness index information, the stability index information and the reliability index information, generate the early warning information corresponding to the target industrial chain; in response to determining that the early warning information meets the preset early warning condition, send the early warning information to the associated entity terminal to warn the target industrial chain, and control the associated remote playback device to play the early warning prompt information corresponding to the early warning information by voice; The generating of the integrity index information corresponding to the target industrial chain according to each area attribute information included in each entity feature information included in the target node feature information set includes: For each target node feature information in the target node feature information set, perform the following steps: In response to determining that there is entity feature information whose regional attribute information satisfies a preset regional condition among the entity feature information included in the target node feature information, determining the target node feature information as aggregated target node feature information; Determine the number of aggregated target node feature information in each determined aggregated target node feature information as the number of nodes that the target regional entity can support; Determine the number of target node feature information in the target node feature information set as the number of nodes; Determine the ratio of the number of nodes that the target regional entity can support to the number of nodes as the completeness index information corresponding to the target industrial chain; The step of generating the stability index information corresponding to the target industrial chain according to each level attribute information included in each entity feature information included in the target node feature information set includes: According to each level attribute information included in each entity feature information included in the target node feature information set, each entity feature information included in the target node feature information set is classified and processed to obtain a first entity feature information set, a second entity feature information set, a third entity feature information set, a fourth entity feature information set and a fifth entity feature information set; Determine the amount of first entity feature information in the first entity feature information set, the amount of second entity feature information in the second entity feature information set, the amount of third entity feature information in the third entity feature information set, the amount of fourth entity feature information in the fourth entity feature information set, and the amount of fifth entity feature information in the fifth entity feature information set as a first target value, a second target value, a third target value, a fourth target value, and a fifth target value, respectively; determining a difference between the first target value and the second target value as a first difference; determining a difference between the second target value and the third target value as a second difference; determining a difference between the third target value and the fourth target value as a third difference; determining a difference between the fourth target value and the fifth target value as a fourth difference; According to preset interval division information, the first difference, the second difference, the third difference and the fourth difference are divided into intervals to obtain a first interval, a second interval, a third interval and a fourth interval; Determine interval scores corresponding to the first interval, the second interval, the third interval, and the fourth interval to obtain a first score, a second score, a third score, and a fourth score; An average value of the first score, the second score, the third score and the fourth score is determined as stability index information corresponding to the target industrial chain.
7. An electronic device comprising: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 5.
8. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.
