Supply chain risk identification method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a supply chain risk identification method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring supply chain data associated with a to-be-analyzed supply chain; preprocessing the supply chain data to obtain preprocessed supply chain data; determining a centralized trend value and a discrete value of the preprocessed supply chain data; determining the data type of the preprocessed supply chain data according to the centralized trend value and the discrete value; according to the data type, performing normalization processing on the preprocessed supply chain data to obtain target supply chain data corresponding to the to-be-analyzed supply chain; determining the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword; and determining a risk identification result of the to-be-analyzed supply chain according to a difference between the risk similarity and a preset risk similarity threshold. By adopting the method, the identification accuracy of the supply chain risk can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a supply chain risk identification method, apparatus, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] At present, in order to ensure the stability of the supply chain, it is crucial to accurately identify the risks of the supply chain.

[0003] In traditional technology, manual investigation is generally used in the process of supply chain risk identification; however, this method has subjective factors and is prone to errors, resulting in low accuracy in identifying supply chain risks. Summary of the invention

[0004] Based on this, it is necessary to provide a supply chain risk identification method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve the accuracy of supply chain risk identification in response to the above technical problems.

[0005] In a first aspect, the present application provides a supply chain risk identification method, comprising:

[0006] Obtain supply chain data associated with the supply chain to be analyzed;

[0007] Preprocessing the supply chain data to obtain preprocessed supply chain data;

[0008] Determining the central tendency value and the dispersion value of the preprocessed supply chain data;

[0009] Determining the data type of the preprocessed supply chain data according to the central tendency value and the discrete value;

[0010] According to the data type, the preprocessed supply chain data is normalized to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type;

[0011] Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword;

[0012] According to the difference between the risk similarity and a preset risk similarity threshold, a risk identification result of the supply chain to be analyzed is determined.

[0013] In one embodiment, preprocessing the supply chain data to obtain preprocessed supply chain data includes:

[0014] In the case where the supply chain data is image data, segmenting the supply chain data to obtain a plurality of sub-supply chain data;

[0015] Determining matrix information corresponding to the supply chain data according to grayscale values ​​corresponding to the plurality of sub-supply chain data;

[0016] The matrix information is preprocessed to obtain the preprocessed supply chain data.

[0017] In one embodiment, determining the central tendency value and the dispersion value of the pre-processed supply chain data includes:

[0018] Obtaining an average value of the preprocessed supply chain data, and obtaining a difference between paired data in the preprocessed supply chain data; the paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data;

[0019] Based on the average value of the preprocessed supply chain data, the variance value of the preprocessed supply chain data is determined as the central tendency value of the preprocessed supply chain data, and based on the difference between the paired data in the preprocessed supply chain data, the discrete value of the preprocessed supply chain data is determined.

[0020] In one embodiment, determining the data type of the pre-processed supply chain data according to the central tendency value and the discrete value includes:

[0021] Obtaining sample supply chain data, and determining a sample central tendency value and a sample discrete value of the sample supply chain data;

[0022] Determining a first ratio between the central tendency value and the sample central tendency value, and determining a second ratio between the discrete value and the sample discrete value;

[0023] When the first ratio belongs to a first ratio interval and the second ratio belongs to a second ratio interval, using the first data type as the data type of the preprocessed supply chain data;

[0024] or,

[0025] When the first ratio does not belong to the first ratio interval, or the second ratio does not belong to the second ratio interval, the second data type is used as the data type of the preprocessed supply chain data.

[0026] In one embodiment, determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword includes:

[0027] Obtaining a preset word bag, and determining an index value of the preset word bag under the preset risk keyword;

[0028] The risk similarity of the target supply chain data is determined according to the index value of the target supply chain data under the preset risk keyword and the index value of the preset word bag under the preset risk keyword.

[0029] In one embodiment, determining the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and a preset risk similarity threshold includes:

[0030] When the risk similarity is greater than or equal to the preset risk similarity threshold, determining that the risk identification result of the supply chain to be analyzed is a first risk level;

[0031] or,

[0032] When the risk similarity is less than the preset risk similarity threshold, determining that the risk identification result of the supply chain to be analyzed is a second risk level;

[0033] After determining the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and the preset risk similarity threshold, the method further includes:

[0034] When the risk identification result of the supply chain to be analyzed is the first risk level, generating early warning information corresponding to the supply chain to be analyzed;

[0035] The early warning information is sent to a target terminal associated with the supply chain to be analyzed.

[0036] In a second aspect, the present application also provides a supply chain risk identification device, including:

[0037] A data acquisition module, used to acquire supply chain data associated with the supply chain to be analyzed;

[0038] A first processing module, used for preprocessing the supply chain data to obtain preprocessed supply chain data;

[0039] A data determination module, used to determine the central tendency value and discrete value of the pre-processed supply chain data;

[0040] A type determination module, used to determine the data type of the pre-processed supply chain data according to the central tendency value and the discrete value;

[0041] A second processing module is used to normalize the pre-processed supply chain data according to the data type to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple pre-processed supply chain data of the same data type;

[0042] A similarity determination module, configured to determine the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword;

[0043] The result determination module is used to determine the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and a preset risk similarity threshold.

[0044] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0045] Obtain supply chain data associated with the supply chain to be analyzed;

[0046] Preprocessing the supply chain data to obtain preprocessed supply chain data;

[0047] Determining the central tendency value and the dispersion value of the preprocessed supply chain data;

[0048] Determining the data type of the preprocessed supply chain data according to the central tendency value and the discrete value;

[0049] According to the data type, the preprocessed supply chain data is normalized to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type;

[0050] Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword;

[0051] According to the difference between the risk similarity and a preset risk similarity threshold, a risk identification result of the supply chain to be analyzed is determined.

[0052] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0053] Obtain supply chain data associated with the supply chain to be analyzed;

[0054] Preprocessing the supply chain data to obtain preprocessed supply chain data;

[0055] Determining the central tendency value and the dispersion value of the preprocessed supply chain data;

[0056] Determining the data type of the preprocessed supply chain data according to the central tendency value and the discrete value;

[0057] According to the data type, the preprocessed supply chain data is normalized to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type;

[0058] Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword;

[0059] According to the difference between the risk similarity and a preset risk similarity threshold, a risk identification result of the supply chain to be analyzed is determined.

[0060] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0061] Obtain supply chain data associated with the supply chain to be analyzed;

[0062] Preprocessing the supply chain data to obtain preprocessed supply chain data;

[0063] Determining the central tendency value and the dispersion value of the preprocessed supply chain data;

[0064] Determining the data type of the preprocessed supply chain data according to the central tendency value and the discrete value;

[0065] According to the data type, the preprocessed supply chain data is normalized to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type;

[0066] Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword;

[0067] According to the difference between the risk similarity and a preset risk similarity threshold, a risk identification result of the supply chain to be analyzed is determined.

[0068] The above-mentioned supply chain risk identification method, device, computer equipment, storage medium and computer program product first obtain the supply chain data associated with the supply chain to be analyzed, and preprocess the supply chain data to obtain the preprocessed supply chain data, and then determine the central tendency value and discrete value of the preprocessed supply chain data, and determine the data type of the preprocessed supply chain data based on the central tendency value and discrete value. Then, according to the data type, the preprocessed supply chain data is normalized to obtain the target supply chain data corresponding to the supply chain to be analyzed, and then, according to the indicator value of the target supply chain data under the preset risk keyword, the risk similarity of the target supply chain data is determined. Finally, according to the difference between the risk similarity and the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined. In this way, in the process of supply chain risk identification, by preprocessing the supply chain data associated with the supply chain to be analyzed and normalizing it according to the data type of the preprocessed supply chain data, the target supply chain data corresponding to the supply chain to be analyzed can be accurately obtained, and then the risk similarity of the target supply chain data can be accurately determined, so that the risk identification result of the supply chain to be analyzed is more accurate, which is conducive to improving the accuracy of supply chain risk identification; moreover, the entire process does not require human intervention, avoiding the subjective factors in manual investigation, which is prone to errors and leads to low supply chain risk identification accuracy, thereby further improving the accuracy of supply chain risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0070] Figure 1 A schematic diagram of a supply chain risk identification method in one embodiment;

[0071] Figure 2 A schematic diagram of a flow chart of a supply chain risk identification method in another embodiment;

[0072] Figure 3 A schematic diagram of a flow chart of a retrieval method for supply chain risk warning in one embodiment;

[0073] Figure 4 is a structural block diagram of a supply chain risk identification device in one embodiment;

[0074] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0075] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0076] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0077] In an exemplary embodiment, Figure 1 As shown, a supply chain risk identification method is provided. This embodiment uses the method applied to a server as an example for illustration; it is understandable that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptops, smart phones and tablets; the server can be implemented as an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0078] Step S101, obtaining supply chain data associated with the supply chain to be analyzed.

[0079] Among them, the supply chain to be analyzed refers to the supply chain that requires risk identification.

[0080] Among them, supply chain data includes customer data (such as customer name, customer type, etc.) and product data (such as product name, product model, etc.).

[0081] Exemplarily, the server determines supply chain characteristics (such as the number of supply chain links) corresponding to multiple candidate supply chains; then, the server selects candidate supply chains whose corresponding supply chain characteristics meet preset supply chain characteristics (such as the number of supply chain links is greater than 10) from the multiple candidate supply chains as the supply chains to be analyzed; then, the server obtains the customer data and product data corresponding to the supply chain to be analyzed from the database, both of which are used as supply chain data associated with the supply chain to be analyzed.

[0082] Step S102, preprocessing the supply chain data to obtain preprocessed supply chain data.

[0083] Among them, preprocessed supply chain data refers to the supply chain data that has been preprocessed.

[0084] Exemplarily, the server performs data deduplication, missing value filling, and outlier processing on the supply chain data to obtain preprocessed supply chain data as the preprocessed supply chain data.

[0085] Step S103, determining the central tendency value and the discrete value of the pre-processed supply chain data.

[0086] Among them, the central tendency value is used to indicate the degree of central tendency of the preprocessed supply chain data.

[0087] The discrete value is used to indicate the discrete degree of the supply chain data after preprocessing.

[0088] Exemplarily, the server inputs the preprocessed supply chain data into a central tendency prediction model to obtain a central tendency value of the preprocessed supply chain data; then, the server inputs the preprocessed supply chain data into a discrete prediction model to obtain a discrete value of the preprocessed supply chain data.

[0089] Step S104, determining the data type of the pre-processed supply chain data according to the central tendency value and the discrete value.

[0090] Among them, the data type is used to indicate the data type of the pre-processed supply chain data, including normal distribution type data, non-normal distribution type data, etc.

[0091] Exemplarily, the server constructs a target correspondence between central tendency values, discrete values, and data types; then, the server queries the target correspondence based on the central tendency values ​​and discrete values, and obtains the data type corresponding to the central tendency values ​​and discrete values ​​as the data type of the preprocessed supply chain data.

[0092] Step S105, normalizing the preprocessed supply chain data according to the data type to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, and each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type.

[0093] The target supply chain data includes multiple groups of supply chain data sets, and each group of supply chain data sets includes multiple pre-processed supply chain data of the same data type.

[0094] Exemplarily, the server normalizes the preprocessed supply chain data according to the data type of the preprocessed supply chain data to obtain multiple preprocessed supply chain data of the same data type as multiple groups of supply chain data sets; then, the server uses the multiple groups of supply chain data sets as target supply chain data corresponding to the supply chain to be analyzed.

[0095] Step S106, determining the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword.

[0096] Among them, the preset risk keywords refer to pre-set risk keywords, such as "decreased orders", "shortage of raw materials", etc. It should be noted that the preset risk keywords depend on the circumstances.

[0097] Among them, the indicator value is used to represent the specific value of the target supply chain data under the preset risk keyword. For example, the indicator value under the preset risk keyword "order reduction" is "the year-on-year / month-on-month decline in order quantity", and the indicator value under the preset risk keyword "raw material shortage" is "the number of days that raw material inventory can last".

[0098] Among them, risk similarity is used to indicate the risk similarity of target supply chain data.

[0099] Exemplarily, the server queries the correspondence between the indicator value and the risk similarity according to the indicator value of the target supply chain data under the preset risk keyword, and obtains the risk similarity corresponding to the indicator value as the risk similarity of the target supply chain data.

[0100] Step S107: determining the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and the preset risk similarity threshold.

[0101] The preset risk similarity threshold refers to a pre-set risk similarity threshold, such as 80%. It should be noted that the preset risk similarity threshold depends on the circumstances.

[0102] Among them, the risk identification result is used to indicate the risk level of the supply chain to be analyzed.

[0103] Exemplarily, the difference between the server risk similarity and the preset risk similarity threshold is used for judgment; when the difference between the risk similarity and the preset risk similarity threshold meets the preset conditions, the risk identification result of the supply chain to be analyzed is determined to be a high risk level; when the difference between the risk similarity and the preset risk similarity threshold does not meet the preset conditions, the risk identification result of the supply chain to be analyzed is determined to be a low risk level.

[0104] In the above supply chain risk identification method, the supply chain data associated with the supply chain to be analyzed is first obtained, and the supply chain data is preprocessed to obtain the preprocessed supply chain data, and then the central tendency value and discrete value of the preprocessed supply chain data are determined, and the data type of the preprocessed supply chain data is determined based on the central tendency value and the discrete value. Next, the preprocessed supply chain data is normalized according to the data type to obtain the target supply chain data corresponding to the supply chain to be analyzed, and then, based on the indicator value of the target supply chain data under the preset risk keyword, the risk similarity of the target supply chain data is determined. Finally, based on the difference between the risk similarity and the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined. In this way, in the process of supply chain risk identification, by preprocessing the supply chain data associated with the supply chain to be analyzed and normalizing it according to the data type of the preprocessed supply chain data, the target supply chain data corresponding to the supply chain to be analyzed can be accurately obtained, and then the risk similarity of the target supply chain data can be accurately determined, so that the risk identification result of the supply chain to be analyzed is more accurate, which is conducive to improving the accuracy of supply chain risk identification; moreover, the entire process does not require human intervention, avoiding the subjective factors in manual investigation, which is prone to errors and leads to low supply chain risk identification accuracy, thereby further improving the accuracy of supply chain risk identification.

[0105] In an exemplary embodiment, the above step S102 pre-processes the supply chain data to obtain pre-processed supply chain data, which specifically includes the following contents: when the supply chain data is image data, segmenting the supply chain data to obtain multiple sub-supply chain data; determining the matrix information corresponding to the supply chain data according to the grayscale values ​​corresponding to the multiple sub-supply chain data; pre-processing the matrix information to obtain pre-processed supply chain data.

[0106] Among them, segmentation processing refers to the processing process of obtaining corresponding data of multiple sub-supply chains based on supply chain data.

[0107] Among them, the sub-supply chain data is used to represent part of the supply chain data in the supply chain data.

[0108] Among them, the grayscale value is used to represent the brightness information of the pixel points in the sub-supply chain data.

[0109] The matrix information is used to represent the digital matrix corresponding to the supply chain data.

[0110] Exemplarily, the server makes a judgment on the supply chain data; when the supply chain data is image data, the server segments the supply chain data to obtain a plurality of sub-supply chain data after segmentation; then, the server determines the brightness information of the pixels in the plurality of sub-supply chain data as the grayscale values ​​corresponding to the plurality of sub-supply chain data; then, the server determines the element values ​​in the digital matrix corresponding to the supply chain data according to the grayscale values ​​corresponding to the plurality of sub-supply chain data as the matrix information corresponding to the supply chain data; finally, the server performs data deduplication, missing value filling and outlier processing on the matrix information to obtain the preprocessed matrix information as the preprocessed supply chain data.

[0111] It should be noted that the data deduplication of the matrix information includes the following: arranging all data coordinates (x, y) in the matrix information into one column; searching for the repetition between the first coordinate and the subsequent coordinates, if repeated, deleting the subsequent coordinates; after the search is completed, searching for the repetition between the second coordinate and the subsequent coordinates, if repeated, deleting the subsequent coordinates; repeating the above steps until all data coordinates have been detected.

[0112] It should be noted that filling missing values ​​in matrix information includes the following: arranging all data coordinates (x, y) in the matrix information into one column; retrieving all data coordinates (x, y), and if x or y is missing, filling in the data at that position, and the data collected is the mean of the adjacent data at the same position.

[0113] It should be noted that the outlier processing of the matrix information includes the following: arranging all data coordinates (x, y) in the matrix information into one column; calculating the deviation value k between the data coordinate (x, y) and the adjacent data coordinates (a, b) and (c, d); when the deviation value k is greater than 100%, the data coordinate (x, y) is an outlier, and the data coordinate (x, y) is replaced by the mean of the adjacent data.

[0114] It should be noted that the calculation formula of the above deviation value k is:

[0115] , formula (1)

[0116] In this embodiment, when the supply chain data belongs to image data, it is segmented to obtain multiple sub-supply chain data, so that subsequent analysis can be more targeted; and, the matrix information corresponding to the supply chain data is determined based on the grayscale values ​​corresponding to the multiple sub-supply chain data, so that the grayscale values ​​in the image data can be converted into structured data in matrix form, which is conducive to improving the effect of data preprocessing.

[0117] In an exemplary embodiment, the above step S103, determining the central tendency value and discrete value of the preprocessed supply chain data, specifically includes the following contents: obtaining the average value of the preprocessed supply chain data, and obtaining the difference between the paired data in the preprocessed supply chain data; the paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data; according to the average value of the preprocessed supply chain data, determining the variance value of the preprocessed supply chain data as the central tendency value of the preprocessed supply chain data, and determining the discrete value of the preprocessed supply chain data according to the difference between the paired data in the preprocessed supply chain data.

[0118] The paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data.

[0119] Exemplarily, the server obtains the average value of the preprocessed supply chain data; then, the server pairs any two sub-preprocessed supply chain data in the preprocessed supply chain data to obtain paired data in the preprocessed supply chain data, and obtains the difference between the paired data in the preprocessed supply chain data; then, the server queries the correspondence between the average value and the variance value based on the average value of the preprocessed supply chain data, and obtains the variance value of the preprocessed supply chain data as the central tendency value of the preprocessed supply chain data; then, the server sums the difference between the paired data in the preprocessed supply chain data to obtain the discrete value of the preprocessed supply chain data.

[0120] For example, the server can determine the variance value of the preprocessed supply chain data by the following formula:

[0121] , formula (2)

[0122] Where D is the variance value of the preprocessed supply chain data, n is the number of preprocessed supply chain data, is the value of the preprocessed supply chain data, and a is the average value of the preprocessed supply chain data.

[0123] In this embodiment, by determining the central tendency value and discrete value of the pre-processed supply chain data, the central tendency degree and discrete degree of the pre-processed supply chain data can be accurately evaluated, providing accurate data reference for subsequent supply chain risk identification and processing, thereby ensuring the stable operation of the supply chain.

[0124] In an exemplary embodiment, the above step S104 determines the data type of the preprocessed supply chain data based on the central tendency value and the discrete value, and specifically includes the following contents: obtaining sample supply chain data, and determining the sample central tendency value and the sample discrete value of the sample supply chain data; determining a first ratio between the central tendency value and the sample central tendency value, and determining a second ratio between the discrete value and the sample discrete value; when the first ratio belongs to a first ratio interval and the second ratio belongs to a second ratio interval, using the first data type as the data type of the preprocessed supply chain data; or, when the first ratio does not belong to the first ratio interval, or the second ratio does not belong to the second ratio interval, using the second data type as the data type of the preprocessed supply chain data.

[0125] The sample supply chain data refers to the reference data corresponding to the data type of the preprocessed supply chain data.

[0126] The sample central tendency value refers to the central tendency value corresponding to the sample supply chain data.

[0127] The sample discrete value refers to the discrete value corresponding to the sample supply chain data.

[0128] The first ratio refers to the ratio between the central tendency value and the sample central tendency value.

[0129] The second ratio refers to the ratio between the discrete value and the sample discrete value.

[0130] The first ratio interval refers to a preset ratio interval used to judge the first ratio. It should be noted that the first ratio interval depends on the situation.

[0131] The second ratio interval refers to a preset ratio interval used to judge the second ratio. It should be noted that the second ratio interval depends on the situation.

[0132] The first data type may refer to normal distribution type data.

[0133] The second data type may refer to non-normal distribution type data.

[0134] Exemplarily, the server obtains sample supply chain data from a database; then, the server determines the central tendency value and discrete value of the sample supply chain data as the sample central tendency value and the sample discrete value, respectively; then, the server determines the ratio between the central tendency value and the sample central tendency value as the first ratio, and determines the ratio between the discrete value and the sample discrete value as the second ratio; then, the server judges the first ratio and the second ratio; when the first ratio belongs to a first ratio interval and the second ratio belongs to a second ratio interval, the server uses the first data type as the data type of the preprocessed supply chain data; when the first ratio does not belong to the first ratio interval, or the second ratio does not belong to the second ratio interval, the server uses the second data type as the data type of the preprocessed supply chain data.

[0135] In this embodiment, sample supply chain data is obtained and its sample central trend value and sample discrete value are determined, and then compared with the supply chain data to be processed to determine the data type of the pre-processed supply chain data, so that the determination of the data type is more in line with the actual data situation, thereby laying the foundation for taking more targeted processing measures for different data types in the future.

[0136] In an exemplary embodiment, the above step S106 determines the risk similarity of the target supply chain data based on the index value of the target supply chain data under the preset risk keywords, and specifically includes the following contents: obtaining a preset word bag, and determining the index value of the preset word bag under the preset risk keywords; determining the risk similarity of the target supply chain data based on the index value of the target supply chain data under the preset risk keywords, and the index value of the preset word bag under the preset risk keywords.

[0137] Among them, the preset word bag refers to the risk-sensitive word bag. It should be noted that the risk-sensitive word bag contains key words that may expose the enterprise to risks. Generally, the risk words are summarized by the enterprise's expert database and kept confidential to prevent competitors from stealing them. Several risk feature keywords are used to search the supply chain information data and calculate the risk similarity. The supply chain information data containing more risk key words is high-risk data, and an early warning needs to be issued to remind the staff to perform encryption operations to maintain the security of the enterprise.

[0138] Exemplarily, in response to an instruction to determine the risk similarity of target supply chain data, the server obtains a preset word bag and determines an index value of the preset word bag under a preset risk keyword; then, the server performs a difference processing on the index value of the target supply chain data under the preset risk keyword and the index value of the preset word bag under the preset risk keyword to obtain a difference; then, the server determines the risk similarity of the target supply chain data based on the difference.

[0139] For example, the server can determine the risk similarity of the target supply chain data by the following formula:

[0140] , formula (3)

[0141] in, is the risk similarity of the target supply chain data, is the jth indicator value of the i-th preset risk keyword of the target supply chain data, is the jth index value of the i-th preset risk keyword in the preset word bag, and n is the total number corresponding to the index value.

[0142] In this embodiment, the risk similarity of the target supply chain data is determined by respectively obtaining the index values ​​of the target supply chain data and the preset word bag under the preset risk keywords, so that it is possible to focus on specific keywords closely related to the risk for analysis, thereby making the risk assessment more accurately centered around key risk factors, which is conducive to improving the accuracy of determining the risk similarity of the target supply chain data.

[0143] In an exemplary embodiment, the above step S107 determines the risk identification result of the supply chain to be analyzed based on the difference between the risk similarity and the preset risk similarity threshold, and specifically includes the following contents: when the risk similarity is greater than or equal to the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined to be the first risk level; or, when the risk similarity is less than the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined to be the second risk level.

[0144] Then, the above step S107, after determining the risk identification result of the supply chain to be analyzed based on the difference between the risk similarity and the preset risk similarity threshold, specifically includes the following contents: when the risk identification result of the supply chain to be analyzed is the first risk level, generating early warning information corresponding to the supply chain to be analyzed; and sending the early warning information to the target terminal associated with the supply chain to be analyzed.

[0145] Among them, the first risk level refers to the high risk level.

[0146] Among them, the second risk level refers to the low risk level.

[0147] Among them, the early warning information is used to indicate the prompt information corresponding to the possible risks in the supply chain to be analyzed.

[0148] The target terminal refers to the terminal associated with the supply chain to be analyzed.

[0149] Exemplarily, the server compares the risk similarity with a preset risk similarity threshold to obtain a comparison result; when the comparison result indicates that the risk similarity is greater than or equal to the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined to be a first risk level; when the comparison result indicates that the risk similarity is less than the preset risk similarity threshold, the risk identification result of the supply chain to be analyzed is determined to be a second risk level; then, when the risk identification result of the supply chain to be analyzed is the first risk level, the server obtains a supply chain identifier (such as a supply chain number) of the supply chain to be analyzed, and generates early warning information corresponding to the supply chain to be analyzed based on the supply chain identifier; then, the server determines a terminal associated with the supply chain to be analyzed as a target terminal, and sends the early warning information to the target terminal.

[0150] In this embodiment, the risk identification result of the supply chain to be analyzed is clearly divided into a first risk level and a second risk level based on the comparison result between the risk similarity and a preset risk similarity threshold; moreover, when the risk identification result of the supply chain to be analyzed is determined to be the first risk level, early warning information corresponding to the supply chain to be analyzed can be automatically generated, thereby ensuring the timeliness and accuracy of the early warning information.

[0151] In an exemplary embodiment, Figure 2 As shown, another supply chain risk identification method is provided, which is described by taking the application of the method to a server as an example, and includes the following steps:

[0152] Step S201, obtaining supply chain data associated with the supply chain to be analyzed.

[0153] Step S202, when the supply chain data is image data, segment the supply chain data to obtain multiple sub-supply chain data; determine the matrix information corresponding to the supply chain data according to the grayscale values ​​corresponding to the multiple sub-supply chain data; pre-process the matrix information to obtain pre-processed supply chain data.

[0154] Step S203, obtaining an average value of the preprocessed supply chain data, and obtaining a difference between paired data in the preprocessed supply chain data; the paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data.

[0155] Step S204, determining the variance value of the preprocessed supply chain data based on the average value of the preprocessed supply chain data as the central tendency value of the preprocessed supply chain data, and determining the discrete value of the preprocessed supply chain data based on the difference between the paired data in the preprocessed supply chain data.

[0156] Step S205, obtain sample supply chain data, and determine the sample central tendency value and sample discrete value of the sample supply chain data; determine a first ratio between the central tendency value and the sample central tendency value, and determine a second ratio between the discrete value and the sample discrete value.

[0157] Step S206: When the first ratio belongs to the first ratio interval and the second ratio belongs to the second ratio interval, the first data type is used as the data type of the preprocessed supply chain data.

[0158] Step S207: when the first ratio does not belong to the first ratio interval or the second ratio does not belong to the second ratio interval, the second data type is used as the data type of the preprocessed supply chain data.

[0159] Step S208, normalizing the preprocessed supply chain data according to the data type to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, and each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type.

[0160] Step S209, obtain a preset word bag and determine the index value of the preset word bag under the preset risk keyword; determine the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword and the index value of the preset word bag under the preset risk keyword.

[0161] Step S210: When the risk similarity is greater than or equal to a preset risk similarity threshold, it is determined that the risk identification result of the supply chain to be analyzed is a first risk level.

[0162] Step S211: when the risk similarity is less than a preset risk similarity threshold, it is determined that the risk identification result of the supply chain to be analyzed is a second risk level.

[0163] In the above supply chain risk identification method, in the process of supply chain risk identification, by preprocessing the supply chain data associated with the supply chain to be analyzed, and normalizing the data type of the preprocessed supply chain data, the target supply chain data corresponding to the supply chain to be analyzed can be accurately obtained, and then the risk similarity of the target supply chain data can be accurately determined, so that the risk identification result of the supply chain to be analyzed is more accurate, which is conducive to improving the accuracy of supply chain risk identification; moreover, the entire process does not require human intervention, avoiding the subjective factors and prone to errors in manual investigation, resulting in low supply chain risk identification accuracy, and further improving the accuracy of supply chain risk identification.

[0164] In an exemplary embodiment, in order to more clearly illustrate the supply chain risk identification method provided in the embodiment of the present application, the supply chain risk identification method is specifically described below with a specific embodiment. Figure 3 As shown, the present application also provides a retrieval method for supply chain risk warning. In the process of risk identification of the supply chain, the supply chain information data is first retrieved from the historical database, and then the supply chain information data is converted. The structured data is converted into binary numbers, and the unstructured data uses the truncation method to generate a digital matrix corresponding to the unstructured data, and the converted data is preprocessed. The preprocessing includes data deduplication, missing value filling and outlier processing. Then, the central trend and discrete degree of the preprocessed supply chain information data are calculated, and data fusion processing is performed to obtain several groups of the same data type. Then, a word bag containing risk sensitivity is obtained from the database, and feature extraction is performed on the risk sensitivity word bag to obtain several risk feature keywords. Finally, several risk feature keywords are used for retrieval, and the risk similarity of the same type of supply chain information data is calculated, and a warning is issued for high-risk data information. Specifically including the following contents:

[0165] A retrieval method for supply chain risk warning comprises: retrieving supply chain information data from a historical database, the supply chain information data comprising basic customer information and product information; converting the supply chain information data, converting structured data into binary numbers, and using a truncation method for unstructured data to generate a digital matrix corresponding to the unstructured data; preprocessing the converted data, the preprocessing comprising data deduplication, missing value filling and outlier processing; calculating the central tendency and discrete degree of the preprocessed supply chain information data, and performing data fusion processing to obtain several groups of the same data type; obtaining a word bag containing risk sensitivity in a database, performing feature extraction on the risk sensitivity word bag, and obtaining several risk feature keywords; using several risk feature keywords for retrieval, calculating the risk similarity of the same type of supply chain information data, and issuing an early warning for high-risk data information.

[0166] It is understandable that the supply chain information data stored in the database is not only text data, but also image data. In order to facilitate unified data processing, the data is first converted and then pre-processed to make the supply chain information data more accurate. The data is then fused so that the same type of data is a data group, which makes the data memory smaller and speeds up data processing. The risk-sensitive word bag contains key words that may put the company at risk. Generally, the risk words are summarized by the company's expert database and kept confidential to prevent competitors from stealing. Several risk feature keywords are used to retrieve the supply chain information data, and the risk similarity is calculated. Supply chain information data containing more risk keywords is high-risk data, and an early warning needs to be issued to remind staff to perform encryption operations to maintain the security of the company.

[0167] The conversion of supply chain information data specifically includes the following steps: grid evenly divide the image data; establish a matrix that corresponds one-to-one with the grid points; , that is, the element in the i-th row and j-th column of the matrix The grid point corresponding to the i-th row and j-th column in the grid; the grid point position of the grid corresponds to the position of the point in the image, and the grayscale value of the image point corresponding to the grid point of the grid is assigned to the corresponding element in the grid matrix ; Get the digital matrix corresponding to the unstructured data.

[0168] Data deduplication includes the following steps: arranging all data coordinates (x, y) into a column; searching for the repetition between the first coordinate and the subsequent coordinates, if repeated, deleting the subsequent coordinates; after the search is completed, searching for the repetition between the second coordinate and the subsequent coordinates, if repeated, deleting the subsequent coordinates; repeating the above steps until all data coordinates have been detected.

[0169] Missing value filling includes the following steps: arranging all data coordinates (x, y) into a column; retrieving all data coordinates (x, y), if x or y is missing, fill in the data at that position, and the data collected is the mean of the adjacent data at the same position.

[0170] Outlier processing includes the following steps: arranging all data coordinates (x, y) into a column; calculating the deviation value k between the data coordinate (x, y) and the adjacent data coordinates (a, b) and (c, d); when the deviation value k is greater than 100%, the data coordinate (x, y) is an outlier, and the data coordinate (x, y) is replaced by the mean of the adjacent data.

[0171] The calculation formula of the deviation value is:

[0172] , formula (1)

[0173] Calculating the central tendency and dispersion degree of the preprocessed supply chain information data specifically includes the following steps: calculating the average value of the data in the supply chain information data, and calculating the variance of the data according to the variance formula; setting the variance as the central tendency of the supply chain information data, and assigning a trend identification code to the central tendency; pairing each data in the supply chain information data with the remaining data in the complete data to obtain at least one pairing group; calculating the absolute value of the difference between the two data in each pairing group of the complete data, and accumulating the absolute value of the difference between the two data in all pairing groups to obtain a discrete value; setting the discrete value as the dispersion degree of the data, and assigning a discrete identification code to the dispersion degree.

[0174] The variance formula is as follows:

[0175] , formula (2)

[0176] Where D is the variance, n is the number of data, is the value of the data, and a is the average value of the data.

[0177] The data fusion processing specifically includes the following steps: retrieve the historical data classification and discrimination standard 1 from the database, obtain the range interval of the central tendency ratio and the range interval of the dispersion ratio in the classification and discrimination standard 1; calculate the ratio 1 of the central tendency of the identified complete data to the central tendency mean of the sample data; calculate the ratio 2 of the dispersion degree of the identified complete data to the dispersion mean of the sample data; compare whether the ratio 1 belongs to the range interval of the central tendency ratio; compare whether the ratio 2 belongs to the range interval of the dispersion degree ratio; if the ratio 1 belongs to the range interval of the central tendency ratio and the ratio 2 belongs to the range interval of the dispersion degree ratio, then adjust Use the classification in classification discrimination group one, set the classification to the first classification, and classify the data into the first classification; if ratio one does not belong to the range of the central tendency ratio or ratio two does not belong to the range of the dispersion ratio, call the remaining classification discrimination groups in the data type determination model; find historical data classification discrimination criterion two in the remaining classification discrimination groups, and classification discrimination criterion two satisfies that ratio one of the data belongs to the range of the central tendency ratio of classification discrimination group two and ratio two of the data belongs to the range of the dispersion ratio of classification discrimination group two, call the classification in classification discrimination group two, set the classification to the second classification, and classify the data into the second classification.

[0178] Obtaining several groups of the same data type specifically includes the following steps: obtaining data in the complete data, obtaining the third category to which the data belongs, and obtaining the data type of the data under the third category; according to the data type of the data under the third category, converting the data in the data to the same data type.

[0179] It can be understood that, during fusion, the original data position remains unchanged, but the position of the data group to be fused is not determined. Therefore, the smallest judgment sum is calculated and selected, and the target data group one corresponding to the smallest judgment sum is associated with the data group to be fused, because the two must be the data with the strongest correlation. Therefore, during fusion, the two are set adjacent to each other. Since the position of the target data group one is determined, the fusion position of the data group to be fused is determined.

[0180] The calculation of risk similarity of the same type of supply chain information data specifically includes the following steps:

[0181] , formula (3)

[0182] In the formula, is the risk similarity, is the jth parameter index value of the i-th risk feature keyword of the supply chain information data, is the jth parameter index value of the ith risk feature keyword in the risk sensitivity word bag, and n is the total number of parameter index values ​​of the ith style parameter.

[0183] Issuing an early warning for high-risk data information specifically includes the following steps: comparing the calculated risk similarity value with the risk preset threshold; if the risk similarity value is greater than or equal to the risk preset threshold, the supply chain information data is determined to be high-risk data and an early warning is issued; if the risk similarity value is less than the risk preset threshold, the supply chain information data is determined to be low-risk data and no action is taken.

[0184] A retrieval system for supply chain risk warning comprises: a retrieval module, the retrieval module is used to retrieve supply chain information data from a historical database, the supply chain information data includes basic customer information and product information; a data conversion module, the data conversion module is used to convert the supply chain information data, structured data are all converted into binary numbers, unstructured data use truncation method, and generate a digital matrix corresponding to the unstructured data; a data preprocessing module, the data preprocessing module is used to preprocess the converted data, the preprocessing includes data deduplication, missing value filling and abnormal value processing; a data fusion module, the data fusion module is used to calculate the central tendency and discrete degree of the preprocessed supply chain information data, and perform data fusion processing to obtain several groups of the same data type; a risk feature extraction module, the risk feature extraction module is used to obtain a word bag containing risk sensitivity in the database, perform feature extraction on the risk sensitivity word bag, and obtain several risk feature keywords; a risk warning module, the risk warning module is used to use several risk feature keywords for retrieval, calculate the risk similarity of the same type of supply chain information data, and issue a warning for high-risk data information.

[0185] A retrieval system for supply chain risk warning comprises: a retrieval module, the retrieval module is used to retrieve supply chain information data from a historical database, the supply chain information data includes basic customer information and product information; a data conversion module, the data conversion module is used to convert the supply chain information data, structured data are all converted into binary numbers, unstructured data use truncation method, and generate a digital matrix corresponding to the unstructured data; a data preprocessing module, the data preprocessing module is used to preprocess the converted data, the preprocessing includes data deduplication, missing value filling and abnormal value processing; a data fusion module, the data fusion module is used to calculate the central tendency and discrete degree of the preprocessed supply chain information data, and perform data fusion processing to obtain several groups of the same data type; a risk feature extraction module, the risk feature extraction module is used to obtain a word bag containing risk sensitivity in the database, perform feature extraction on the risk sensitivity word bag, and obtain several risk feature keywords; a risk warning module, the risk warning module is used to use several risk feature keywords for retrieval, calculate the risk similarity of the same type of supply chain information data, and issue a warning for high-risk data information.

[0186] In summary, the supply chain information data stored in the database is not only text data, but also image data. In order to facilitate unified data processing, the data is first converted and then preprocessed to make the supply chain information data more accurate. The data is then fused so that the same type of data is a data group, which makes the data memory smaller and speeds up data processing. The risk-sensitive word bag contains key words that may put the company at risk. Generally, the company's expert database summarizes risk words and keeps them confidential to prevent competitors from stealing them. Several risk feature keywords are used to retrieve the supply chain information data, and the risk similarity is calculated. Supply chain information data containing more risk keywords is high-risk data, and an early warning needs to be issued to remind staff to perform encryption operations to maintain the company's security.

[0187] In the above-mentioned embodiment, during the process of identifying the risks of the supply chain, the supply chain data associated with the supply chain to be analyzed is preprocessed, and normalized according to the data type of the preprocessed supply chain data, so that the target supply chain data corresponding to the supply chain to be analyzed can be accurately obtained, and then the risk similarity of the target supply chain data can be accurately determined, so that the risk identification result of the supply chain to be analyzed is more accurate, which is conducive to improving the accuracy of identifying supply chain risks; moreover, the entire process does not require human intervention, avoiding the defect of subjective factors and prone to errors in manual investigation, resulting in low accuracy in identifying supply chain risks, and further improving the accuracy of identifying supply chain risks.

[0188] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0189] Based on the same inventive concept, the embodiment of the present application also provides a supply chain risk identification device for implementing the supply chain risk identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more supply chain risk identification device embodiments provided below can refer to the limitations of the supply chain risk identification method above, and will not be repeated here.

[0190] In an exemplary embodiment, Figure 4 As shown, a supply chain risk identification device is provided, including: a data acquisition module 401, a first processing module 402, a data determination module 403, a type determination module 404, a second processing module 405, a similarity determination module 406 and a result determination module 407, wherein:

[0191] The data acquisition module 401 is used to acquire supply chain data associated with the supply chain to be analyzed.

[0192] The first processing module 402 is used to pre-process the supply chain data to obtain pre-processed supply chain data.

[0193] The data determination module 403 is used to determine the central tendency value and the discrete value of the pre-processed supply chain data.

[0194] The type determination module 404 is used to determine the data type of the pre-processed supply chain data according to the central tendency value and the discrete value.

[0195] The second processing module 405 is used to normalize the pre-processed supply chain data according to the data type to obtain the target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, and each group of supply chain data sets includes multiple pre-processed supply chain data of the same data type.

[0196] The similarity determination module 406 is used to determine the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword.

[0197] The result determination module 407 is used to determine the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and the preset risk similarity threshold.

[0198] In an exemplary embodiment, the first processing module 402 is also used to segment the supply chain data to obtain multiple sub-supply chain data when the supply chain data belongs to image data; determine the matrix information corresponding to the supply chain data according to the grayscale values ​​corresponding to the multiple sub-supply chain data; and pre-process the matrix information to obtain pre-processed supply chain data.

[0199] In an exemplary embodiment, the data determination module 403 is also used to obtain the average value of the preprocessed supply chain data, and to obtain the difference between the paired data in the preprocessed supply chain data; the paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data; based on the average value of the preprocessed supply chain data, the variance value of the preprocessed supply chain data is determined as the central tendency value of the preprocessed supply chain data, and based on the difference between the paired data in the preprocessed supply chain data, the discrete value of the preprocessed supply chain data is determined.

[0200] In an exemplary embodiment, the type determination module 404 is also used to obtain sample supply chain data, and determine the sample central trend value and sample discrete value of the sample supply chain data; determine a first ratio between the central trend value and the sample central trend value, and determine a second ratio between the discrete value and the sample discrete value; when the first ratio belongs to a first ratio interval and the second ratio belongs to a second ratio interval, use the first data type as the data type of the preprocessed supply chain data; or, when the first ratio does not belong to the first ratio interval, or the second ratio does not belong to the second ratio interval, use the second data type as the data type of the preprocessed supply chain data.

[0201] In an exemplary embodiment, the similarity determination module 406 is also used to obtain a preset word bag and determine the index value of the preset word bag under the preset risk keyword; based on the index value of the target supply chain data under the preset risk keyword and the index value of the preset word bag under the preset risk keyword, the risk similarity of the target supply chain data is determined.

[0202] In an exemplary embodiment, the result determination module 407 is also used to determine that the risk identification result of the supply chain to be analyzed is a first risk level when the risk similarity is greater than or equal to a preset risk similarity threshold; or, when the risk similarity is less than a preset risk similarity threshold, determine that the risk identification result of the supply chain to be analyzed is a second risk level; the supply chain risk identification device also includes an information sending module, which is used to generate early warning information corresponding to the supply chain to be analyzed when the risk identification result of the supply chain to be analyzed is a first risk level; and send the early warning information to a target terminal associated with the supply chain to be analyzed.

[0203] Each module in the above supply chain risk identification device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.

[0204] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as central tendency values, discrete values, and risk similarity. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a supply chain risk identification method is implemented.

[0205] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0206] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0207] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0208] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0209] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0210] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0211] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A supply chain risk identification method, characterized in that: The method comprises: Obtain supply chain data associated with the supply chain to be analyzed; Preprocessing the supply chain data to obtain preprocessed supply chain data; Determining the central tendency value and the dispersion value of the preprocessed supply chain data; Determining the data type of the preprocessed supply chain data according to the central tendency value and the discrete value; According to the data type, the preprocessed supply chain data is normalized to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple preprocessed supply chain data of the same data type; Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword; According to the difference between the risk similarity and a preset risk similarity threshold, a risk identification result of the supply chain to be analyzed is determined.

2. The method according to claim 1, characterized in that The preprocessing of the supply chain data to obtain preprocessed supply chain data includes: In the case where the supply chain data is image data, segmenting the supply chain data to obtain a plurality of sub-supply chain data; Determining matrix information corresponding to the supply chain data according to grayscale values ​​corresponding to the plurality of sub-supply chain data; The matrix information is preprocessed to obtain the preprocessed supply chain data.

3. The method according to claim 1, characterized in that Determining the central tendency value and the discrete value of the pre-processed supply chain data includes: Obtaining an average value of the preprocessed supply chain data, and obtaining a difference between paired data in the preprocessed supply chain data; the paired data is used to represent any two sub-preprocessed supply chain data in the preprocessed supply chain data; Based on the average value of the preprocessed supply chain data, the variance value of the preprocessed supply chain data is determined as the central tendency value of the preprocessed supply chain data, and based on the difference between the paired data in the preprocessed supply chain data, the discrete value of the preprocessed supply chain data is determined.

4. The method according to claim 1, characterized in that: Determining the data type of the pre-processed supply chain data according to the central tendency value and the discrete value includes: Obtaining sample supply chain data, and determining a sample central tendency value and a sample discrete value of the sample supply chain data; Determining a first ratio between the central tendency value and the sample central tendency value, and determining a second ratio between the discrete value and the sample discrete value; When the first ratio belongs to a first ratio interval and the second ratio belongs to a second ratio interval, using the first data type as the data type of the preprocessed supply chain data; or, When the first ratio does not belong to the first ratio interval, or the second ratio does not belong to the second ratio interval, the second data type is used as the data type of the preprocessed supply chain data.

5. The method according to claim 1, characterized in that Determining the risk similarity of the target supply chain data according to the indicator value of the target supply chain data under the preset risk keyword includes: Obtaining a preset word bag, and determining an index value of the preset word bag under the preset risk keyword; The risk similarity of the target supply chain data is determined according to the index value of the target supply chain data under the preset risk keyword and the index value of the preset word bag under the preset risk keyword.

6. The method according to any one of claims 1 to 5, characterized in that Determining the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and a preset risk similarity threshold includes: When the risk similarity is greater than or equal to the preset risk similarity threshold, determining that the risk identification result of the supply chain to be analyzed is a first risk level; or, When the risk similarity is less than the preset risk similarity threshold, determining that the risk identification result of the supply chain to be analyzed is a second risk level; After determining the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and the preset risk similarity threshold, the method further includes: When the risk identification result of the supply chain to be analyzed is the first risk level, generating early warning information corresponding to the supply chain to be analyzed; The early warning information is sent to a target terminal associated with the supply chain to be analyzed.

7. A supply chain risk identification device, characterized in that: The device comprises: A data acquisition module, used to acquire supply chain data associated with the supply chain to be analyzed; A first processing module, used for preprocessing the supply chain data to obtain preprocessed supply chain data; A data determination module, used to determine the central tendency value and discrete value of the pre-processed supply chain data; A type determination module, used to determine the data type of the pre-processed supply chain data according to the central tendency value and the discrete value; A second processing module is used to normalize the pre-processed supply chain data according to the data type to obtain target supply chain data corresponding to the supply chain to be analyzed; the target supply chain data includes multiple groups of supply chain data sets, each group of supply chain data sets includes multiple pre-processed supply chain data of the same data type; A similarity determination module, configured to determine the risk similarity of the target supply chain data according to the index value of the target supply chain data under the preset risk keyword; The result determination module is used to determine the risk identification result of the supply chain to be analyzed according to the difference between the risk similarity and a preset risk similarity threshold.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images