Supply chain information retrieval method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a supply chain information retrieval method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: preprocessing to-be-processed supply chain information to obtain preprocessed supply chain information; performing index construction processing on each piece of preprocessed supply chain information to obtain reverse index information; querying the reverse index information according to target retrieval demand information sent by the terminal to obtain candidate supply chain information corresponding to the target retrieval demand information; determining the similarity between each piece of candidate supply chain information and the target retrieval demand information; according to a preset similarity and a similarity between each piece of candidate supply chain information and the target retrieval demand information, determining grade information of each piece of candidate supply chain information; and according to the grade information of each piece of candidate supply chain information, determining target supply chain information corresponding to the target retrieval demand information from each piece of candidate supply chain information. By adopting the method, the retrieval efficiency of the supply chain information can be improved.

Description

Technical Field

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

[0002] At present, as the supply chain system becomes increasingly complex, how to quickly retrieve supply chain information becomes extremely important.

[0003] In traditional technology, in the process of supply chain information retrieval, the general method is to manually check each supply chain information in turn; however, this method is cumbersome and requires a lot of time and manpower, resulting in low efficiency in retrieval of supply chain information. Summary of the invention

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

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

[0006] Obtain pending supply chain information;

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

[0008] Performing index construction processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information;

[0009] According to the target retrieval requirement information sent by the terminal, query the inverted index information to obtain the candidate supply chain information corresponding to the target retrieval requirement information;

[0010] Determining the similarity between each of the candidate supply chain information and the target search demand information;

[0011] Determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information;

[0012] According to the level information of each candidate supply chain information, the target supply chain information corresponding to the target search requirement information is determined from each candidate supply chain information.

[0013] In one embodiment, the step of determining the level information of each candidate supply chain information based on the preset similarity and the similarity between each candidate supply chain information and the target search requirement information includes:

[0014] When the similarity between the candidate supply chain information and the target search requirement information is greater than the preset similarity, the first level information is used as the level information corresponding to the candidate supply chain information;

[0015] or,

[0016] When the similarity between the candidate supply chain information and the target search requirement information is equal to the preset similarity, the second level information is used as the level information corresponding to the candidate supply chain information;

[0017] or,

[0018] When the similarity between the candidate supply chain information and the target retrieval requirement information is less than the preset similarity, the third level information is used as the level information corresponding to the candidate supply chain information.

[0019] In one embodiment, determining the target supply chain information corresponding to the target search requirement information from each of the candidate supply chain information according to the level information of each of the candidate supply chain information includes:

[0020] In the case that there is candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, the candidate supply chain information whose corresponding level information is the first level information is used as the target supply chain information corresponding to the target search requirement information;

[0021] or,

[0022] In the case that there is no candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, and there is candidate supply chain information whose corresponding level information is the second level information, the candidate supply chain information whose corresponding level information is the second level information is used as the target supply chain information corresponding to the target search requirement information;

[0023] or,

[0024] When there is no candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, and there is no candidate supply chain information whose corresponding level information is the second level information, determine the first database where the supply chain information is located, obtain new supply chain information to be processed from a second database associated with the first database, and jump to the step of preprocessing the supply chain information to obtain the preprocessed supply chain information, until there is candidate supply chain information whose corresponding level information is the first level information or the second level information in each of the candidate supply chain information obtained.

[0025] In one embodiment, determining the similarity between each candidate supply chain information and the target search requirement information includes:

[0026] Determine a first number corresponding to each of the candidate supply chain information and a second number corresponding to the target search demand information;

[0027] The similarity between each of the candidate supply chain information and the target retrieval requirement information is determined according to the first number and the second number.

[0028] In one embodiment, before querying the inverted index information according to the target search requirement information sent by the terminal to obtain the candidate supply chain information corresponding to the target search requirement information, the method further includes:

[0029] Obtaining product information, supplier information, and product inventory information sent by the terminal;

[0030] De-noising the product information, the supplier information and the product inventory information to obtain processed product information, processed supplier information and processed product inventory information;

[0031] The processed product information, the processed supplier information and the processed product inventory information are all used as the target retrieval demand information.

[0032] In one embodiment, preprocessing the supply chain information to obtain preprocessed supply chain information includes:

[0033] Identifying abnormal information in the supply chain information;

[0034] Determining associated information corresponding to the abnormal information in the supply chain information;

[0035] The abnormal information and the associated information are deleted from the supply chain information to obtain the pre-processed supply chain information.

[0036] In a second aspect, the present application also provides a supply chain information retrieval device, comprising:

[0037] An information acquisition module, used to acquire supply chain information to be processed;

[0038] An information preprocessing module, used to preprocess the supply chain information to obtain preprocessed supply chain information;

[0039] An index building module, used to perform index building processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information;

[0040] An information query module, configured to query the inverted index information according to the target retrieval requirement information sent by the terminal, and obtain candidate supply chain information corresponding to the target retrieval requirement information;

[0041] A similarity determination module, used to determine the similarity between each candidate supply chain information and the target search requirement information;

[0042] A level determination module, used to determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information;

[0043] The target determination module is used to determine the target supply chain information corresponding to the target search demand information from each of the candidate supply chain information according to the level information of each of the candidate supply chain information.

[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 pending supply chain information;

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

[0047] Performing index construction processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information;

[0048] According to the target retrieval requirement information sent by the terminal, query the inverted index information to obtain the candidate supply chain information corresponding to the target retrieval requirement information;

[0049] Determining the similarity between each of the candidate supply chain information and the target search demand information;

[0050] Determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information;

[0051] According to the level information of each candidate supply chain information, the target supply chain information corresponding to the target search requirement information is determined from each candidate supply chain information.

[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 pending supply chain information;

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

[0055] Performing index construction processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information;

[0056] According to the target retrieval requirement information sent by the terminal, query the inverted index information to obtain the candidate supply chain information corresponding to the target retrieval requirement information;

[0057] Determining the similarity between each of the candidate supply chain information and the target search demand information;

[0058] Determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information;

[0059] According to the level information of each candidate supply chain information, the target supply chain information corresponding to the target search requirement information is determined from each candidate supply chain information.

[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 pending supply chain information;

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

[0063] Performing index construction processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information;

[0064] According to the target retrieval requirement information sent by the terminal, query the inverted index information to obtain the candidate supply chain information corresponding to the target retrieval requirement information;

[0065] Determining the similarity between each of the candidate supply chain information and the target search demand information;

[0066] Determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information;

[0067] According to the level information of each candidate supply chain information, the target supply chain information corresponding to the target search requirement information is determined from each candidate supply chain information.

[0068] The above-mentioned supply chain information retrieval method, device, computer equipment, storage medium and computer program product first obtain the supply chain information to be processed, and pre-process the supply chain information to obtain the pre-processed supply chain information, and then perform index construction processing on each pre-processed supply chain information to obtain inverted index information. Then, according to the target retrieval requirement information sent by the terminal, the inverted index information is queried to obtain the candidate supply chain information corresponding to the target retrieval requirement information, and the similarity between each candidate supply chain information and the target retrieval requirement information is determined. Then, according to the preset similarity and the similarity between each candidate supply chain information and the target retrieval requirement information, the level information of each candidate supply chain information is determined. Finally, according to the level information of each candidate supply chain information, the target supply chain information corresponding to the target retrieval requirement information is determined from each candidate supply chain information. In this way, in the process of supply chain information retrieval, the supply chain information is preprocessed and indexed, and the level information of each candidate supply chain information is directly determined according to the similarity between each supply chain information and the target retrieval demand information, so that the target supply chain information corresponding to the target retrieval demand information sent by the terminal can be quickly obtained, which greatly accelerates the overall retrieval process and is conducive to improving the retrieval efficiency of the supply chain information; moreover, the entire process does not require human intervention, avoiding the cumbersome method of manually checking each supply chain information in turn, which requires a lot of time and manpower, resulting in the defect of low retrieval efficiency of the supply chain information, and further improves the retrieval efficiency of the supply chain information. 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 is a flow chart of a supply chain information retrieval method in one embodiment;

[0071] Figure 2 is a flow chart of a supply chain information retrieval method in another embodiment;

[0072] Figure 3 It is a flowchart of a fuzzy matching supply chain information retrieval enhancement method in one embodiment;

[0073] Figure 4 is a structural block diagram of a supply chain information retrieval 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 information retrieval 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 tablet computers; 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 information to be processed.

[0079] The supply chain information includes at least product information, supplier information and product inventory information.

[0080] Exemplarily, the server responds to the supply chain information retrieval instruction and determines the database system corresponding to the supply chain information retrieval instruction; then, the server obtains the supply chain information in the database system as the supply chain information to be processed.

[0081] Step S102, preprocessing the supply chain information to obtain preprocessed supply chain information.

[0082] The pre-processed supply chain information refers to the supply chain information after pre-processing.

[0083] Exemplarily, the server identifies abnormal information in the supply chain information; then, the server preprocesses the abnormal information in the supply chain information to obtain preprocessed supply chain information.

[0084] Step S103, index construction processing is performed on each pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information.

[0085] The search requirement information is used to represent the search requirements corresponding to the product information, supplier information and product inventory information.

[0086] Among them, the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information. For example, the pre-processed supply chain information is (supply chain 1: product information a, supplier information b and product inventory information c; supply chain 2: product information a, supplier information d and product inventory information e), then the inverted index information is (product information a: supply chain 1, supply chain 2; supplier information b: supply chain 1; product inventory information c: supply chain 1; supplier information d: supply chain 2; product inventory information e: supply chain 2).

[0087] Exemplarily, the server determines the retrieval requirement information contained in the preprocessed supply chain information as candidate retrieval requirement information; then, the server performs index construction processing on each preprocessed supply chain information according to the preset index construction instructions, and obtains the preprocessed supply chain information corresponding to each candidate retrieval requirement information as inverted index information.

[0088] Step S104, querying the inverted index information according to the target search requirement information sent by the terminal, and obtaining the candidate supply chain information corresponding to the target search requirement information.

[0089] The target retrieval requirement information refers to the retrieval requirement information sent by the terminal.

[0090] The candidate supply chain information is used to represent the supply chain information corresponding to the target retrieval demand information in the inverted index information.

[0091] Exemplarily, the server establishes a network path with the terminal; then, the server receives the retrieval demand information sent by the terminal through the network path as the target retrieval demand information; then, the server queries the inverted index information according to the target retrieval demand information, and obtains the supply chain information corresponding to the target retrieval demand information as the candidate supply chain information.

[0092] Step S105: determining the similarity between each candidate supply chain information and the target search requirement information.

[0093] Among them, similarity is used to indicate the degree of association between candidate supply chain information and target retrieval demand information.

[0094] Exemplarily, the server inputs each candidate supply chain information and the target retrieval demand information into the feature extraction model respectively, and obtains the feature vector corresponding to each candidate supply chain information and the feature vector corresponding to the target retrieval demand information through the feature extraction model; then, the server obtains the cosine similarity between each candidate supply chain information and the target retrieval demand information based on the feature vector corresponding to each candidate supply chain information and the feature vector corresponding to the target retrieval demand information, as the similarity between each candidate supply chain information and the target retrieval demand information.

[0095] Step S106, determining the level information of each candidate supply chain information according to the preset similarity and the similarity between each candidate supply chain information and the target search requirement information.

[0096] The preset similarity refers to a preset similarity threshold, such as 80%. It should be noted that the preset similarity depends on the situation.

[0097] The grade information is used to indicate the priority of each candidate supply chain information, including excellent, good and poor.

[0098] Exemplarily, the server compares the similarity between each candidate supply chain information and the target retrieval demand information with the preset similarity to obtain the comparison result corresponding to each candidate supply chain information; then, the server queries the correspondence between the comparison result and the grade information based on the comparison result corresponding to each candidate supply chain information to obtain the grade information of each candidate supply chain information.

[0099] Step S107 , determining target supply chain information corresponding to the target search requirement information from the candidate supply chain information according to the level information of each candidate supply chain information.

[0100] The target supply chain information refers to the supply chain information corresponding to the target retrieval demand information.

[0101] Exemplarily, the server verifies the level information of each candidate supply chain information to obtain a verification result; then, if the verification result is passed, the server determines the supply chain information corresponding to the target retrieval demand information from each candidate supply chain information according to the level information of each candidate supply chain information, as the target supply chain information.

[0102] In the above-mentioned supply chain information retrieval method, the supply chain information to be processed is first obtained, and the supply chain information is preprocessed to obtain the preprocessed supply chain information, and then each preprocessed supply chain information is indexed and constructed to obtain the inverted index information. Then, according to the target retrieval requirement information sent by the terminal, the inverted index information is queried to obtain the candidate supply chain information corresponding to the target retrieval requirement information, and the similarity between each candidate supply chain information and the target retrieval requirement information is determined. Then, according to the preset similarity and the similarity between each candidate supply chain information and the target retrieval requirement information, the rank information of each candidate supply chain information is determined. Finally, according to the rank information of each candidate supply chain information, the target supply chain information corresponding to the target retrieval requirement information is determined from each candidate supply chain information. In this way, in the process of supply chain information retrieval, the supply chain information is preprocessed and indexed, and the level information of each candidate supply chain information is directly determined according to the similarity between each supply chain information and the target retrieval demand information, so that the target supply chain information corresponding to the target retrieval demand information sent by the terminal can be quickly obtained, which greatly accelerates the overall retrieval process and is conducive to improving the retrieval efficiency of the supply chain information; moreover, the entire process does not require human intervention, avoiding the cumbersome method of manually checking each supply chain information in turn, which requires a lot of time and manpower, resulting in the defect of low retrieval efficiency of the supply chain information, and further improves the retrieval efficiency of the supply chain information.

[0103] In an exemplary embodiment, the above step S106 determines the level information of each candidate supply chain information based on a preset similarity and the similarity between each candidate supply chain information and the target retrieval requirement information, and specifically includes the following contents: when the similarity between the candidate supply chain information and the target retrieval requirement information is greater than the preset similarity, the first level information is used as the level information corresponding to the candidate supply chain information; or, when the similarity between the candidate supply chain information and the target retrieval requirement information is equal to the preset similarity, the second level information is used as the level information corresponding to the candidate supply chain information; or, when the similarity between the candidate supply chain information and the target retrieval requirement information is less than the preset similarity, the third level information is used as the level information corresponding to the candidate supply chain information.

[0104] Among them, the first level information refers to excellent.

[0105] Among them, the second level information refers to good.

[0106] Among them, the third level information refers to the difference.

[0107] Exemplarily, the server compares the similarity between each candidate supply chain information and the target retrieval demand information with the preset similarity to obtain a comparison result corresponding to each candidate supply chain information; when the comparison result indicates that the similarity between the candidate supply chain information and the target retrieval demand information is greater than the preset similarity, excellent is used as the grade information corresponding to the candidate supply chain information; when the comparison result indicates that the similarity between the candidate supply chain information and the target retrieval demand information is equal to the preset similarity, good is used as the grade information corresponding to the candidate supply chain information; when the comparison result indicates that the similarity between the candidate supply chain information and the target retrieval demand information is less than the preset similarity, poor is used as the grade information corresponding to the candidate supply chain information.

[0108] In this embodiment, by setting different level information to correspond to different similarities between candidate supply chain information and target retrieval requirement information, the candidate supply chain information can be very accurately distinguished according to the degree of matching with the target retrieval requirement, which is beneficial to improving the accuracy of determining the level information corresponding to the candidate supply chain information.

[0109] In an exemplary embodiment, the above step S107, according to the level information of each candidate supply chain information, determines the target supply chain information corresponding to the target retrieval requirement information from each candidate supply chain information, specifically including the following contents: when there is candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, the candidate supply chain information whose corresponding level information is first level information is used as the target supply chain information corresponding to the target retrieval requirement information; or, when there is no candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, and there is candidate supply chain information whose corresponding level information is second level information, the candidate supply chain information whose corresponding level information is second level information is used as the target supply chain information corresponding to the target retrieval requirement information; or, when there is no candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, and there is no candidate supply chain information whose corresponding level information is second level information, determines the first database where the supply chain information is located, obtains new supply chain information to be processed from a second database associated with the first database, and jumps to the step of preprocessing the supply chain information to obtain the preprocessed supply chain information, until there is candidate supply chain information whose corresponding level information is first level information or second level information in each candidate supply chain information obtained.

[0110] The first database refers to the database where the supply chain information is located.

[0111] The second database refers to other databases except the first database.

[0112] Exemplarily, the server judges each candidate supply chain information according to the grade information of each candidate supply chain information; when there is candidate supply chain information whose corresponding grade information is first-grade information among each candidate supply chain information, the candidate supply chain information whose corresponding grade information is first-grade information among each candidate supply chain information is used as the target supply chain information corresponding to the target retrieval demand information; when there is no candidate supply chain information whose corresponding grade information is first-grade information among each candidate supply chain information, and there is candidate supply chain information whose corresponding grade information is second-grade information, the candidate supply chain information whose corresponding grade information is second-grade information among each candidate supply chain information is used as the target supply chain information corresponding to the target retrieval demand information; when there is no candidate supply chain information whose corresponding grade information is first-grade information among each candidate supply chain information, and there is no candidate supply chain information whose corresponding grade information is second-grade information, the first database where the supply chain information is located is determined, new supply chain information to be processed is obtained from a second database associated with the first database, and the step of preprocessing the supply chain information to obtain the preprocessed supply chain information is jumped to the step of preprocessing the supply chain information to obtain the preprocessed supply chain information, until there is candidate supply chain information whose corresponding grade information is first-grade information or second-grade information among each candidate supply chain information obtained.

[0113] In this embodiment, the candidate supply chain information is hierarchically screened according to the hierarchical information, thereby avoiding comprehensive processing of all candidate supply chain information, thereby improving the efficiency of overall information processing; moreover, when there is no candidate supply chain information that meets the requirements, re-retrieval from the associated database is beneficial to ensuring the continuity of information supply.

[0114] In an exemplary embodiment, the above step S105 determines the similarity between each candidate supply chain information and the target retrieval requirement information, and specifically includes the following contents: determining the first number corresponding to each candidate supply chain information and the second number corresponding to the target retrieval requirement information; based on the first number and the second number, determining the similarity between each candidate supply chain information and the target retrieval requirement information.

[0115] The first number refers to the number corresponding to each candidate supply chain information.

[0116] The second number refers to the number corresponding to the target retrieval requirement information.

[0117] Exemplarily, the server extracts the target inverted index information corresponding to the target retrieval requirement information from the inverted index information; then, the server determines the first number corresponding to each candidate supply chain information and the second number corresponding to the target retrieval requirement information based on the target inverted index information; then, the server performs quotient processing on the first number and the second number to obtain the quotient corresponding to the first number and the second number as the similarity between each candidate supply chain information and the target retrieval requirement information.

[0118] For example, the inverted index information is (product information a: supply chain 1, supply chain 2; supplier information b: supply chain 1; product inventory information c: supply chain 1; supplier information d: supply chain 2; product inventory information e: supply chain 2), and the target inverted index information corresponding to the target retrieval demand information (product information a, supplier information b, product inventory information c) is (product information a: supply chain 1, supply chain 2; supplier information b: supply chain 1; product inventory information c: supply chain 1); the number of supply chain 1 appearances in the target inverted index information is 3, the number of supply chain 2 appearances is 1, and the number of target retrieval demand information appearances is 3. Then the similarity between supply chain 1 and the target retrieval demand information is 3 / 3=1, and the similarity between supply chain 2 and the target retrieval demand information is 1 / 3.

[0119] In this embodiment, by determining the first number corresponding to each candidate supply chain information and the second number corresponding to the target retrieval demand information, and determining the similarity between them based on these two numbers, a quantitative evaluation of the degree of matching between the candidate supply chain information and the target retrieval demand information is achieved, thereby more carefully screening out the supply chain information that best matches the target retrieval demand.

[0120] In an exemplary embodiment, the above-mentioned step S104, before querying the inverted index information according to the target retrieval demand information sent by the terminal to obtain the candidate supply chain information corresponding to the target retrieval demand information, specifically includes the following contents: obtaining the product information, supplier information and product inventory information sent by the terminal; denoising the product information, supplier information and product inventory information to obtain processed product information, processed supplier information and processed product inventory information; and using the processed product information, processed supplier information and processed product inventory information as the target retrieval demand information.

[0121] Among them, product information is used to represent product-related information in the supply chain system.

[0122] Among them, supplier information is used to represent product-related information in the supply chain system.

[0123] Among them, product inventory information is used to represent product-related information in the supply chain system.

[0124] The processed product information refers to the product information after denoising.

[0125] The processed supplier information refers to the supplier information after denoising.

[0126] The processed product inventory information refers to the product inventory information after denoising.

[0127] Exemplarily, the server establishes a network path with the terminal; then, the server receives product information, supplier information and product inventory information sent by the terminal through the network path; then, the server identifies noise information in the product information, supplier information and product inventory information, and based on the noise information, denoises the product information, supplier information and product inventory information to obtain processed product information, processed supplier information and processed product inventory information; then, the server combines the processed product information, processed supplier information and processed product inventory information in a preset combination method to obtain combined information, and uses the combined information as target retrieval demand information.

[0128] In this embodiment, by denoising the product information, supplier information and product inventory information sent by the terminal, interference factors, erroneous data or redundant information that may exist in the original information can be effectively removed, thereby making the processed information more accurate, thereby providing a high-quality data foundation for subsequent processing.

[0129] In an exemplary embodiment, the above step S102 pre-processes the supply chain information to obtain pre-processed supply chain information, which specifically includes the following contents: identifying abnormal information in the supply chain information; determining the associated information corresponding to the abnormal information in the supply chain information; deleting the abnormal information and the associated information from the supply chain information to obtain the pre-processed supply chain information.

[0130] Among them, abnormal information is used to indicate supply chain information with obvious errors (such as the degree of deviation is greater than the preset degree of deviation).

[0131] The associated information is used to indicate information associated with the abnormal information.

[0132] Exemplarily, the server determines the degree of deviation of each sub-supply chain information in the supply chain information, and screens out the sub-supply chain information with a degree of deviation greater than a preset degree of deviation from the supply chain information as abnormal information in the supply chain information; then, the server uses the information associated with the abnormal information as the associated information corresponding to the abnormal information in the supply chain information; for example, in supply chain 1 (product information a, supplier information b and product inventory information c), product information a is abnormal information, and supplier information b and product inventory information c are associated information; then, the server deletes the abnormal information and associated information from the supply chain information to obtain the pre-processed supply chain information.

[0133] Furthermore, the server can also search for missing values ​​in the supply chain information based on the heat map corresponding to the supply chain information, determine the missing information in the supply chain information, and analyze and process the supply chain information based on the missing value type of the missing information to determine the filling information corresponding to the missing information; then, the server performs data filling processing on the missing information based on the filling information to obtain the pre-processed supply chain information.

[0134] In this embodiment, by identifying and deleting abnormal information and its related information in the supply chain information, erroneous or interfering data that may be caused by data entry errors, measurement errors, special circumstances, etc. can be effectively removed, thereby improving the data quality of the entire supply chain information and providing a more reliable basis for subsequent analysis based on these data.

[0135] In an exemplary embodiment, Figure 2 As shown, another supply chain information retrieval method is provided, which is described by taking the method applied to a server as an example, and includes the following steps:

[0136] Step S201, obtaining supply chain information to be processed.

[0137] Step S202, identifying abnormal information in the supply chain information; determining associated information corresponding to the abnormal information in the supply chain information; deleting the abnormal information and associated information from the supply chain information to obtain pre-processed supply chain information.

[0138] Step S203, index construction processing is performed on each pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information.

[0139] Step S204, obtaining product information, supplier information and product inventory information sent by the terminal; denoising the product information, supplier information and product inventory information to obtain processed product information, processed supplier information and processed product inventory information; using the processed product information, processed supplier information and processed product inventory information as target retrieval demand information.

[0140] Step S205: query the inverted index information according to the target search requirement information sent by the terminal to obtain the candidate supply chain information corresponding to the target search requirement information.

[0141] Step S206, determining a first number corresponding to each candidate supply chain information and a second number corresponding to the target search requirement information; and determining the similarity between each candidate supply chain information and the target search requirement information based on the first number and the second number.

[0142] Step S207: when the similarity between the candidate supply chain information and the target search requirement information is greater than a preset similarity, the first level information is used as the level information corresponding to the candidate supply chain information.

[0143] Step S208: When the similarity between the candidate supply chain information and the target search requirement information is equal to the preset similarity, the second level information is used as the level information corresponding to the candidate supply chain information.

[0144] Step S209: When the similarity between the candidate supply chain information and the target search requirement information is less than a preset similarity, the third level information is used as the level information corresponding to the candidate supply chain information.

[0145] Step S210 , when there is candidate supply chain information whose corresponding level information is first level information among the candidate supply chain information, the candidate supply chain information whose corresponding level information is first level information is used as the target supply chain information corresponding to the target search demand information.

[0146] Step S211, when there is no candidate supply chain information whose corresponding level information is the first level information in each candidate supply chain information, and there is candidate supply chain information whose corresponding level information is the second level information, the candidate supply chain information whose corresponding level information is the second level information is used as the target supply chain information corresponding to the target retrieval demand information.

[0147] Step S212, when there is no candidate supply chain information whose corresponding level information is the first level information in each candidate supply chain information, and there is no candidate supply chain information whose corresponding level information is the second level information, determine the first database where the supply chain information is located, obtain new supply chain information to be processed from the second database associated with the first database, and jump to step S202 until there is candidate supply chain information whose corresponding level information is the first level information or the second level information in each candidate supply chain information obtained.

[0148] In the above-mentioned supply chain information retrieval method, during the process of supply chain information retrieval, the supply chain information is preprocessed and indexed, and the level information of each candidate supply chain information is directly determined according to the similarity between each supply chain information and the target retrieval demand information, so that the target supply chain information corresponding to the target retrieval demand information sent by the terminal can be quickly obtained, which greatly accelerates the overall retrieval process and is conducive to improving the retrieval efficiency of the supply chain information; moreover, the entire process does not require human intervention, avoiding the cumbersome method of manually checking each supply chain information in turn, which requires a lot of time and manpower, resulting in the defect of low retrieval efficiency of the supply chain information, and further improves the retrieval efficiency of the supply chain information.

[0149] In an exemplary embodiment, in order to more clearly illustrate the supply chain information retrieval method provided in the embodiment of the present application, the supply chain information retrieval method is specifically described below with a specific embodiment. In one embodiment, Figure 3As shown, the present application also provides a supply chain information retrieval enhancement method based on fuzzy matching. In the process of supply chain information retrieval, the user's retrieval demand information is first obtained, and the user's retrieval demand information includes product information, supplier information and product inventory information. Then, based on the database system, data reading and processing are performed on the database system to obtain supply chain information, and based on the supply chain information, data preprocessing is performed to obtain normal supply chain information. The data preprocessing includes removing outliers, supplementing missing values, and normalizing data. Then, an index is constructed based on the normal supply chain information to obtain an inverted index. Then, based on the fuzzy matching algorithm, information retrieval is performed on the inverted index through the user's retrieval demand information to obtain a similarity weight. Finally, a comparison and judgment is performed based on the similarity weight and a set first threshold to determine the best retrieval information. Specifically, it includes the following contents: obtaining the user's search demand information, which includes product information, supplier information and product inventory information; based on the database system, performing data reading and processing on the database system to obtain supply chain information; based on the supply chain information, performing data preprocessing to obtain normal supply chain information, which includes removing outliers, supplementing missing values ​​and normalizing data; constructing an index based on the normal supply chain information to obtain an inverted index; based on a fuzzy matching algorithm, performing information retrieval on the inverted index through the user's search demand information to obtain a similarity weight; performing comparative judgment based on the similarity weight and setting a first threshold to determine the best search information.

[0150] It is understandable that the same product may have multiple suppliers. When the suppliers are different, the product effects may be different. Therefore, in order to enable users to buy ideal products, the supply chain information is analyzed through product information, supplier information and product inventory information, and words in the supply chain information that are not related to product information, supplier information and product inventory information are eliminated, making subsequent information retrieval faster and shortening the retrieval time.

[0151] Based on the supply chain information, data preprocessing is performed to obtain normal supply chain information, which specifically includes the following steps: traversing the data according to the supply chain information to determine the location of the data outlier; based on the location of the data outlier, deleting the data associated with the location of the data outlier to obtain the first preprocessed data; based on the heat map, searching for missing values ​​on the first preprocessed data to determine the location of the missing value; analyzing and processing the supply chain information based on the missing value type to obtain the filled data; filling the missing value location with data based on the filled data to obtain the second preprocessed data; based on data normalization, unifying the data format of the second preprocessed data to obtain normal supply chain information.

[0152] There will be data outliers in the supply chain information, which will interfere with subsequent retrieval. Therefore, it is necessary to remove the data outliers and delete the data associated with the data outliers.

[0153] There may be missing values ​​in the supply chain information. By analyzing the data associated with the missing values, we can determine the fill-in data to make the data complete, expand the supply chain information, and expand the scope of subsequent retrieval.

[0154] In order to make retrieval more convenient, the format of data is unified, such as date, unit, etc.

[0155] The index is constructed based on normal supply chain information, and obtaining the inverted index specifically includes the following steps: content decomposition is performed based on normal supply chain information to obtain vocabulary information; based on part-of-speech information, the vocabulary information is deduplicated and standardized to obtain retrieval information vocabulary; an inverted list is constructed; based on the retrieval information vocabulary, the inverted list is filled with content to obtain the inverted index.

[0156] It is understandable that the inverted index is (product information, supplier information, product inventory information), but only one of these parameters may be the same, so it is necessary to search based on specific keywords.

[0157] Based on the part-of-speech information, the vocabulary information is deduplicated and standardized, and the acquisition of retrieval information vocabulary specifically includes the following steps: removing stop words according to the vocabulary information to obtain a first processing vocabulary set; standardizing according to the user's retrieval demand information and the first processing vocabulary set to obtain irrelevant part-of-speech information; filtering the first processing vocabulary set based on the irrelevant part-of-speech information to obtain retrieval information vocabulary.

[0158] In this embodiment, in order to make subsequent search operations faster, irrelevant words need to be deleted. For example, if the user's search requirement information is origin, supplier, production date, etc., then the words in the supply chain information that are irrelevant to the origin, supplier, and production date need to be deleted, thereby reducing the content of the supply chain information and freeing up memory space, making subsequent search time shorter.

[0159] Based on the fuzzy matching algorithm, the inverted index is retrieved through the user's search demand information, and the similarity weight is obtained in the following specific steps: according to the product information, supplier information and product inventory information, the Jaccard similarity algorithm is selected; based on the Jaccard similarity algorithm, the inverted index is retrieved through the product information, supplier information and product inventory information to obtain multiple groups of information sets; based on the product information, supplier information and product inventory information, the multiple groups of information sets are weighted to obtain similarity weights.

[0160] Among them, the specific calculation formula for obtaining the similarity weight is:

[0161] , formula (1)

[0162] In formula (1), is the similarity weight; are different types of information in the user's retrieval demand information; n is the number of different types of information in the user's retrieval demand information; j is the number of information in the information set.

[0163] Based on the similarity weight and the set first threshold, a comparative judgment is performed to determine the best search information, which specifically includes the following steps: based on the similarity weight and the set first threshold, a judgment result is obtained; if the similarity weight is greater than the set first threshold, the information set corresponding to the similarity weight is excellent; if the similarity weight is equal to the set first threshold, the information set corresponding to the similarity weight is good; if the similarity weight is less than the set first threshold, the information set corresponding to the similarity weight is poor; and an analysis is performed based on the judgment result to determine the best search information.

[0164] Analyzing the judgment results and determining the best search information specifically includes the following steps: if there is an excellent information set in the judgment results, the excellent information set is the best search information; if there is no excellent information set in the judgment results, the good information set is the best search information; if there is no excellent information set and good information set in the judgment results, re-select the supply chain information, re-build the inverted index, and re-select the best index information.

[0165] In the above-mentioned embodiment, during the process of supply chain information retrieval, the supply chain information is preprocessed and indexed, and the level information of each candidate supply chain information is directly determined according to the similarity between each supply chain information and the target retrieval demand information, so that the target supply chain information corresponding to the target retrieval demand information sent by the terminal can be quickly obtained, which greatly accelerates the overall retrieval process and is conducive to improving the retrieval efficiency of the supply chain information; moreover, the entire process does not require manual intervention, avoiding the cumbersome method of manually checking each supply chain information in turn, which requires a lot of time and manpower and leads to the defect of low retrieval efficiency of the supply chain information, thereby further improving the retrieval efficiency of the supply chain information.

[0166] 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.

[0167] Based on the same inventive concept, the embodiment of the present application also provides a supply chain information retrieval device for implementing the supply chain information retrieval 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 information retrieval device embodiments provided below can refer to the limitations on the supply chain information retrieval method above, and will not be repeated here.

[0168] In an exemplary embodiment, Figure 4 As shown, a supply chain information retrieval device is provided, including: an information acquisition module 401, an information preprocessing module 402, an index construction module 403, an information query module 404, a similarity determination module 405, a level determination module 406 and a target determination module 407, wherein:

[0169] The information acquisition module 401 is used to acquire supply chain information to be processed.

[0170] The information preprocessing module 402 is used to preprocess the supply chain information to obtain preprocessed supply chain information.

[0171] The index construction module 403 is used to perform index construction processing on each pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information.

[0172] The information query module 404 is used to query the inverted index information according to the target retrieval requirement information sent by the terminal, and obtain the candidate supply chain information corresponding to the target retrieval requirement information.

[0173] The similarity determination module 405 is used to determine the similarity between each candidate supply chain information and the target search requirement information.

[0174] The level determination module 406 is used to determine the level information of each candidate supply chain information according to a preset similarity and the similarity between each candidate supply chain information and the target search requirement information.

[0175] The target determination module 407 is used to determine the target supply chain information corresponding to the target search requirement information from each candidate supply chain information according to the level information of each candidate supply chain information.

[0176] In an exemplary embodiment, the level determination module 406 is also used to use the first level information as the level information corresponding to the candidate supply chain information when the similarity between the candidate supply chain information and the target retrieval requirement information is greater than a preset similarity; or, when the similarity between the candidate supply chain information and the target retrieval requirement information is equal to a preset similarity, use the second level information as the level information corresponding to the candidate supply chain information; or, when the similarity between the candidate supply chain information and the target retrieval requirement information is less than a preset similarity, use the third level information as the level information corresponding to the candidate supply chain information.

[0177] In an exemplary embodiment, the target determination module 407 is also used to, when there is candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, use the candidate supply chain information whose corresponding level information is first level information as the target supply chain information corresponding to the target retrieval demand information; or, when there is no candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, and there is candidate supply chain information whose corresponding level information is second level information, use the candidate supply chain information whose corresponding level information is second level information as the target supply chain information corresponding to the target retrieval demand information; or, when there is no candidate supply chain information whose corresponding level information is first level information in each candidate supply chain information, and there is no candidate supply chain information whose corresponding level information is second level information, determine the first database where the supply chain information is located, obtain new supply chain information to be processed from a second database associated with the first database, and jump to the step of preprocessing the supply chain information to obtain the preprocessed supply chain information, until there is candidate supply chain information whose corresponding level information is first level information or second level information in each candidate supply chain information obtained.

[0178] In an exemplary embodiment, the similarity determination module 405 is also used to determine the first number corresponding to each candidate supply chain information and the second number corresponding to the target retrieval requirement information; based on the first number and the second number, the similarity between each candidate supply chain information and the target retrieval requirement information is determined.

[0179] In an exemplary embodiment, the supply chain information retrieval device also includes a demand determination module, which is used to obtain product information, supplier information and product inventory information sent by the terminal; denoise the product information, supplier information and product inventory information to obtain processed product information, processed supplier information and processed product inventory information; and use the processed product information, processed supplier information and processed product inventory information as target retrieval demand information.

[0180] In an exemplary embodiment, the information preprocessing module 402 is also used to identify abnormal information in the supply chain information; determine the associated information corresponding to the abnormal information in the supply chain information; delete the abnormal information and the associated information from the supply chain information to obtain the preprocessed supply chain information.

[0181] Each module in the above supply chain information retrieval 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.

[0182] 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 supply chain information and target retrieval demand information. 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 information retrieval method is implemented.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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 information retrieval method, characterized in that: The method comprises: Obtain pending supply chain information; Preprocessing the supply chain information to obtain preprocessed supply chain information; Performing index construction processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information; According to the target retrieval requirement information sent by the terminal, query the inverted index information to obtain the candidate supply chain information corresponding to the target retrieval requirement information; Determining the similarity between each of the candidate supply chain information and the target search demand information; Determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information; According to the level information of each candidate supply chain information, the target supply chain information corresponding to the target search requirement information is determined from each candidate supply chain information.

2. The method according to claim 1, characterized in that Determining the level information of each candidate supply chain information according to the preset similarity and the similarity between each candidate supply chain information and the target search requirement information includes: When the similarity between the candidate supply chain information and the target search requirement information is greater than the preset similarity, the first level information is used as the level information corresponding to the candidate supply chain information; or, When the similarity between the candidate supply chain information and the target search requirement information is equal to the preset similarity, the second level information is used as the level information corresponding to the candidate supply chain information; or, When the similarity between the candidate supply chain information and the target retrieval requirement information is less than the preset similarity, the third level information is used as the level information corresponding to the candidate supply chain information.

3. The method according to claim 2, characterized in that The step of determining target supply chain information corresponding to the target search requirement information from each of the candidate supply chain information according to the level information of each of the candidate supply chain information includes: In the case that there is candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, the candidate supply chain information whose corresponding level information is the first level information is used as the target supply chain information corresponding to the target search requirement information; or, In the case that there is no candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, and there is candidate supply chain information whose corresponding level information is the second level information, the candidate supply chain information whose corresponding level information is the second level information is used as the target supply chain information corresponding to the target search requirement information; or, When there is no candidate supply chain information whose corresponding level information is the first level information in each of the candidate supply chain information, and there is no candidate supply chain information whose corresponding level information is the second level information, determine the first database where the supply chain information is located, obtain new supply chain information to be processed from a second database associated with the first database, and jump to the step of preprocessing the supply chain information to obtain the preprocessed supply chain information, until there is candidate supply chain information whose corresponding level information is the first level information or the second level information in each of the candidate supply chain information obtained.

4. The method according to claim 1, characterized in that: The determining of the similarity between each of the candidate supply chain information and the target search requirement information includes: Determine a first number corresponding to each of the candidate supply chain information and a second number corresponding to the target search demand information; The similarity between each of the candidate supply chain information and the target retrieval requirement information is determined according to the first number and the second number.

5. The method according to claim 1, characterized in that Before querying the inverted index information according to the target search requirement information sent by the terminal to obtain the candidate supply chain information corresponding to the target search requirement information, the method further includes: Obtaining product information, supplier information, and product inventory information sent by the terminal; De-noising the product information, the supplier information and the product inventory information to obtain processed product information, processed supplier information and processed product inventory information; The processed product information, the processed supplier information and the processed product inventory information are all used as the target retrieval demand information.

6. The method according to any one of claims 1 to 5, characterized in that The preprocessing of the supply chain information to obtain preprocessed supply chain information includes: Identifying abnormal information in the supply chain information; Determining associated information corresponding to the abnormal information in the supply chain information; The abnormal information and the associated information are deleted from the supply chain information to obtain the pre-processed supply chain information.

7. A supply chain information retrieval device, characterized in that: The device comprises: An information acquisition module, used to acquire supply chain information to be processed; An information preprocessing module, used to preprocess the supply chain information to obtain preprocessed supply chain information; An index building module, used to perform index building processing on each of the pre-processed supply chain information to obtain inverted index information; the inverted index information is used to represent the pre-processed supply chain information corresponding to each candidate retrieval requirement information, and each candidate retrieval requirement information is used to represent the retrieval requirement information contained in the corresponding pre-processed supply chain information; An information query module, configured to query the inverted index information according to the target retrieval requirement information sent by the terminal, and obtain candidate supply chain information corresponding to the target retrieval requirement information; A similarity determination module, used to determine the similarity between each candidate supply chain information and the target search requirement information; A level determination module, used to determine the level information of each candidate supply chain information according to a preset similarity and a similarity between each candidate supply chain information and the target search requirement information; The target determination module is used to determine the target supply chain information corresponding to the target search demand information from each of the candidate supply chain information according to the level information of each of the candidate supply chain information.

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