Supplier qualification requirement recommendation method, system and device and storage medium

Abstract

The invention provides a supplier qualification requirement recommendation method, system and device and a storage medium, and a project information extraction agent module generates project structured information according to project description information; the qualification type recommendation agent module determines a plurality of preferable qualification types and the matching degree with the target project according to the project structured information; a qualification type combination algorithm module determines a target qualification type according to the matching degree to construct a qualification type combination; the qualification grade judgment agent module determines the lowest grade requirement of each target qualification type according to the grade division standard of each target qualification type and the project structured information; and the qualification grade recommendation module takes the target qualification type and the lowest grade requirement as the supplier qualification requirement of the target project for recommendation. By the adoption of the scheme, automatic and intelligent recommendation of the supplier qualification is achieved, the recommendation accuracy and efficiency are improved, and optimization of customized evaluation recommendation and resource configuration is achieved.

Description

Technical Field

[0001] The present invention relates to the field of computer model technology, and in particular to a method, system, device and storage medium for recommending supplier qualification requirements. Background Art

[0002] In supply chain management, selecting the right supplier is a key link to ensure product quality, reduce costs and improve corporate competitiveness. The supplier's qualification requirements are an important basis for evaluating whether the supplier meets the needs of the enterprise. Traditional supplier qualification evaluation methods often rely on manual review and judgment, but in the study, it was found that the above traditional supplier qualification evaluation methods have the following defects: First, the traditional supplier qualification evaluation method relies on manual review, which is easily affected by the subjective factors of the auditor, resulting in inconsistent and unfair evaluation results; secondly, manual review of supplier qualifications requires a lot of time and energy, which reduces work efficiency; at the same time, traditional evaluation methods often only focus on the basic qualifications of suppliers, while ignoring some specific qualification requirements closely related to the project, resulting in incomplete evaluation results. In addition, traditional evaluation methods lack flexibility and cannot be customized according to the characteristics and needs of different projects. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a method, system, device and storage medium for recommending supplier qualification requirements, so as to realize automated and intelligent recommendation of supplier qualifications, which not only improves the accuracy and efficiency of recommendations, but also realizes customized evaluation recommendations and optimization of resource allocation, thereby improving the overall level of supply chain management.

[0004] In a first aspect, an embodiment of the present application provides a method for recommending supplier qualification requirements, which is applied to a supplier qualification recommendation system. The system includes a project information extraction agent module, a qualification type recommendation agent module, a qualification type combination algorithm module, a qualification level determination agent module, and a qualification level recommendation module. The method includes:

[0005] The project information extraction agent module generates project structured information of the target project according to the project description information of the target project;

[0006] The qualification type recommendation agent module determines a number of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project;

[0007] The qualification type combination algorithm module determines a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project;

[0008] The qualification level determination agent module determines the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information;

[0009] The qualification level recommendation module recommends the target qualification type combination and the minimum level requirement of each target qualification type in the target qualification type combination as the supplier qualification requirement of the target project.

[0010] Optionally, generating the project structured information of the target project according to the project description information of the target project includes:

[0011] Configure the project structured extraction prompt word template;

[0012] Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information;

[0013] The project prompt words are used as the big model input, and the big model interface is called to obtain the project structured information.

[0014] Optionally, the determining of a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, includes:

[0015] Calculate the similarity between each optional qualification type and the project structured information respectively;

[0016] Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types;

[0017] Configure the qualification recommendation prompt word template;

[0018] Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type;

[0019] Each qualification prompt word is used as a large model input, and the large model interface is called to obtain each preferred qualification type and the matching degree between each preferred qualification type and the target project.

[0020] Optionally, determining the minimum grade requirement of each target qualification type according to the grade classification standard of each target qualification type in the target qualification type combination and the project structured information includes:

[0021] For each target qualification type, determining in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type;

[0022] The minimum qualification level satisfied by the project structured information is determined as the minimum level requirement for each target qualification type.

[0023] In a second aspect, an embodiment of the present application provides a supplier qualification recommendation system, the system comprising a project information extraction agent module, a qualification type recommendation agent module, a qualification type combination algorithm module, a qualification level determination agent module and a qualification level recommendation module;

[0024] The project information extraction agent module is used to generate project structured information of the target project according to the project description information of the target project;

[0025] The qualification type recommendation agent module is used to determine a number of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project;

[0026] The qualification type combination algorithm module is used to determine a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project;

[0027] The qualification level determination agent module is used to determine the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information;

[0028] The qualification level recommendation module is used to recommend the target qualification type combination and the minimum level requirements of each target qualification type in the target qualification type combination as the supplier qualification requirements of the target project.

[0029] Optionally, generating the project structured information of the target project according to the project description information of the target project includes:

[0030] Configure the project structured extraction prompt word template;

[0031] Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information;

[0032] The project prompt words are used as the big model input, and the big model interface is called to obtain the project structured information.

[0033] Optionally, the determining of a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, includes:

[0034] Calculate the similarity between each optional qualification type and the project structured information respectively;

[0035] Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types;

[0036] Configure the qualification recommendation prompt word template;

[0037] Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type;

[0038] Each qualification prompt word is used as a large model input, and the large model interface is called to obtain each preferred qualification type and the matching degree between each preferred qualification type and the target project.

[0039] Optionally, determining the minimum grade requirement of each target qualification type according to the grade classification standard of each target qualification type in the target qualification type combination and the project structured information includes:

[0040] For each target qualification type, determining in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type;

[0041] The minimum qualification level satisfied by the project structured information is determined as the minimum level requirement for each target qualification type.

[0042] In a third aspect, an embodiment of the present application provides a computer device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the supplier qualification recommendation method described in any optional implementation manner of the first aspect are performed.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the supplier qualification recommendation method described in any optional implementation manner in the above-mentioned first aspect are executed.

[0044] The technical solution provided by this application includes but is not limited to the following beneficial effects:

[0045] This application uses a large language model to collaboratively recommend supplier qualifications by designing intelligent agents with different functions. It can not only give the recommendation results of qualification type or qualification type combination and qualification level, but also output the large model recommendation analysis process and basis, which reduces the requirements for professionalism and experience of relevant personnel and the error rate, and improves the execution efficiency, quality and compliance of related procurement. At the same time, through the intelligent system, the qualifications of suppliers can be evaluated more objectively and comprehensively, reducing the interference of human factors and improving the accuracy of evaluation and recommendation results. In addition, the automated evaluation process can greatly shorten the evaluation time, improve work efficiency, and enable enterprises to screen suitable suppliers more quickly. This application can customize the qualification requirements of suppliers according to the characteristics and needs of different projects to ensure the pertinence and effectiveness of the evaluation results. At the same time, the intelligent supplier qualification recommendation system can record and track the evaluation process in real time, improve the transparency of the supply chain, and reduce risks. By accurately evaluating the qualifications of suppliers, enterprises can allocate resources more reasonably, ensure that limited resources are invested in the most potential suppliers, and improve the overall benefits of the supply chain.

[0046] To sum up, the supplier qualification requirement recommendation method provided in this application realizes the automation and intelligent evaluation of supplier qualifications through an intelligent system, which not only improves the accuracy and efficiency of the evaluation, but also realizes customized evaluation and optimization of resource allocation, thereby improving the overall level of supply chain management.

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0049] Figure 1 A flowchart of a method for recommending supplier qualification requirements provided by the first embodiment of the present invention is shown;

[0050] Figure 2 A flowchart of a method for generating project structured information provided by the first embodiment of the present invention is shown;

[0051] Figure 3 A flow chart of a method for determining a matching degree provided in Embodiment 1 of the present invention is shown;

[0052] Figure 4A flowchart of a method for determining a minimum level requirement provided by the first embodiment of the present invention is shown;

[0053] Figure 5 A schematic diagram showing the structure of a supplier qualification recommendation system provided by Embodiment 2 of the present invention is shown;

[0054] Figure 6 A schematic diagram of the structure of a computer device provided in Embodiment 3 of the present invention is shown. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0056] Embodiment 1

[0057] To facilitate understanding of this application, Figure 1 The flowchart of a method for recommending supplier qualification requirements provided in the first embodiment of the present invention is shown to describe the contents of the first embodiment of the present application in detail.

[0058] See also Figure 1 As shown, Figure 1 A flowchart of a method for recommending supplier qualification requirements provided by the first embodiment of the present invention is shown, wherein the method is applied to a supplier qualification recommendation system, the system includes a project information extraction agent module, a qualification type recommendation agent module, a qualification type combination algorithm module, a qualification level determination agent module and a qualification level recommendation module, and the method includes steps S101 to S105:

[0059] S101: The project information extraction agent module generates project structured information of the target project according to the project description information of the target project.

[0060] Specifically, the project information extraction agent module extracts the project structured information required for qualification recommendation based on the project description information and qualification requirements of the target project. Project structured information includes project type, project scale, level and degree of construction object, project scope, project specific requirements and information related to the qualification type setting. The project information extraction agent module uses prompt word templates to organize the extraction requirements, needs and rules, and uses the reasoning ability of the large language model pre-configured in the supplier qualification recommendation system to obtain the extraction results, that is, the project structured information, and save and send it to the subsequent processing module. The large language model configured in this system has extensive natural language understanding and reasoning capabilities, and can analyze problems and give results or conclusions based on prompt word requirements and facts.

[0061] S102: The qualification type recommendation agent module determines a number of preferred qualification types from various optional qualification types according to the project structured information, as well as the matching degree between each preferred qualification type and the target project.

[0062] Specifically, the qualification type recommendation agent module is used for project structured information to determine several (one to three) preferred qualification types from several optional qualification types in each vector knowledge base, the matching degree between each preferred qualification type and the project, and the analysis process to determine the preferred qualification type.

[0063] The degree of qualification type matching is expressed as a score of 1-5, and the higher the score, the higher the degree of matching. The recommended analysis process is the reason and basis for the recommendation given by the large model based on the context information, which is used by relevant personnel to evaluate the credibility and reliability of the recommendation results. The qualification type recommendation agent module uses prompt word templates to organize project structured information and query related qualification types. It uses the reasoning ability of the large language model to obtain recommendation results, namely several preferred qualification types, and the degree of matching between each preferred qualification type and the target project, and saves and sends them to the subsequent processing module. The vector knowledge base is pre-configured in the system, and indexes the description information of all qualification types and their business scope in a vector manner.

[0064] When there are many qualification types and their business descriptions, all of them are put into the prompt word to check the word limit of the large model. It is necessary to select the most relevant and most likely part of the qualification types as candidate qualification types and put them into the prompt word template. Therefore, this application uses a vector knowledge base to store and index qualification types. Since vector indexing belongs to semantic query, it can match more relevant qualification types compared to keyword matching, thereby improving the relevance of candidate qualification type selection.

[0065] S103: The qualification type combination algorithm module determines a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project.

[0066] Specifically, the qualification type combination algorithm module selects different target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project. The target qualification type combination is to determine which qualification types can undertake the target project alone and whether a combination of multiple qualification types is required to meet the requirements of the target project among the recommended qualification types according to the recommended qualification types and matching scores. Different qualification categories use different combination rules, and the combination rules of all qualification categories are preset in the algorithm module.

[0067] This application also provides a possible combination rule of qualification categories, which is as follows:

[0068] If the recommended qualification has only one sequence of qualification categories, N (the maximum recommended number, such as N=2, indicating that the recommended qualification types are at most 2) are selected from the qualification types with a matching score greater than or equal to s (configurable parameter, such as s=4) as the final recommended qualification types. If the recommended qualification is a quality and capital category of multiple sequences, N (the maximum recommended number, such as N=2, indicating that the recommended qualification types are at most 2) are selected from the qualification types with a matching score greater than or equal to s (configurable parameter, such as s=4) in each sequence as part of the final recommended qualification types. In addition, if two qualification sequences can be combined (such as A and B, that is, two qualifications are required to meet the requirements), the N qualification types recommended by them are combined in pairs and also serve as part of the final recommended qualifications. A sequence refers to a type of qualification. For example, the construction qualification includes a general contracting sequence and a professional contracting sequence. Both the general contracting sequence and the professional contracting sequence contain multiple qualification types. The two sequences can be combined, such as a project requiring a supplier to have the qualifications of a general contracting first and a professional contracting second. By calculating the combination of qualification types based on the output type and matching degree information, it is possible to meet the situations where multiple qualification types can be used to contract projects (or relationships) or where a project requires multiple qualifications to be contracted (and relationships).

[0069] S104: The qualification level determination agent module determines the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information.

[0070] Specifically, the qualification level determination intelligent agent module determines the level that each qualification type is suitable for undertaking the project, that is, the minimum level requirement, based on the qualification type finally determined by the qualification type combination algorithm module, according to the project structured information and the corresponding qualification type level classification standards.

[0071] A qualification level database is pre-configured, which is used to store the levels and level classification standards corresponding to all qualification types, as well as the scale classification standards of the projects involved in the qualification type. The qualification level determination agent module uses prompt word templates to organize project structured information and the levels and standards corresponding to the queried qualification types, and uses the reasoning ability of the large language model to obtain recommendation results and analysis basis, which are saved and sent to subsequent modules for processing. When the qualification level determination agent module determines the level of each qualification type, it starts from the lowest level and determines it in sequence. Once a certain level is met, it will no longer judge the higher level, but will judge the level as the most appropriate qualification level, that is, the minimum level requirement.

[0072] S105: The qualification level recommendation module recommends the target qualification type combination and the minimum level requirement of each target qualification type in the target qualification type combination as the supplier qualification requirement of the target project.

[0073] Specifically, the recommendation results and recommendation process information are output, and the recommendation results include each target qualification type and its combination method, that is, the target qualification type combination, and also include the minimum level requirements of each target qualification type. The recommendation process information includes the analysis process and basis output by each intelligent agent module through large language model reasoning. Since it can not only give the recommendation results of qualification type or qualification type combination and qualification level, but also output the large model recommendation analysis process and basis, the analysis process and basis can assist relevant personnel in evaluating the credibility and reliability of the results.

[0074] In an alternative embodiment, see Figure 2 As shown, Figure 2 A flowchart of a method for generating project structured information provided by the first embodiment of the present invention is shown, wherein the method for generating the project structured information of the target project according to the project description information of the target project comprises steps S201 to S203:

[0075] S201: configuring a project structured extraction prompt word template.

[0076] Specifically, an example of a project structured extraction prompt word template is as follows:

[0077] Based on project information and requirements, extract project information related to qualification recommendation.

[0078] ##Project Information

[0079] {Fill in the input project description}

[0080] ## Requirements and background information

[0081] {Description of information such as extraction requirements and qualification-related concepts}

[0082] ##Output content

[0083] According to the project overview or construction scale, accurately understand and extract the project-related information involved in this bidding scope, such as project name, project budget or investment amount, project content and scope, project quantity and scale, standards, etc., and list them one by one.

[0084] Note: Only the project content and scope are listed in the project description. You cannot guess or analyze the role of the project on your own.

[0085] S202: Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information.

[0086] Specifically, the project information is a text description, which obtains the project description information of the target project, the requirements of each qualification type for the project information, and the output rules, fills in the project structured extraction prompt word template, and assembles the project prompt words.

[0087] S203: taking the project prompt words as a large model input, and calling a large model interface to obtain the project structured information.

[0088] Specifically, the project prompt word is used as a message, the large model interface is called, and the reply of the large model understanding result is received and parsed to obtain the project structured information.

[0089] In an alternative embodiment, see Figure 3 As shown, Figure 3 A flowchart of a matching degree determination method provided in the first embodiment of the present invention is shown, wherein the method of determining a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, comprises steps S301 to S305:

[0090] S301: Calculate the similarity between each optional qualification type and the project structured information respectively.

[0091] Specifically, the description information of each optional qualification type and the project structured information are respectively subjected to text vectorization processing to obtain a first text vector of each optional qualification type and a second text vector of the project structured information. For each optional qualification type, the similarity between the first text vector of the optional qualification type and the second text vector of the project structured information is calculated, including but not limited to cosine similarity and Euclidean distance, to obtain the similarity between the optional qualification type and the project structured information.

[0092] S302: Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types.

[0093] Specifically, the optional qualification types whose similarity exceeds a preset value are determined as candidate qualification types; or, several optional qualification types with the highest similarity are determined as candidate qualification types.

[0094] S303: Configure a qualification recommendation prompt word template.

[0095] Specifically, the example of the qualification recommendation prompt word template is as follows:

[0096] Please determine the most suitable qualification type for the project based on the business scope and project information of {qualification category name}

[0097] ##The qualification type and business scope of {qualification category name} are as follows

[0098] {Query the matching candidate qualification type and its business scope description from the vector knowledge base}

[0099] ##Project Information

[0100] {Project structured extracted information}

[0101] ##Recommended Rules

[0102] {Description of recommendation rules, given in list form. Generally includes the number of recommended qualifications, recommendation principles, matching scoring rules, score range, etc. The setting of rules is related to the characteristics of the qualification category and the macro model used}

[0103] Output format

[0104] Analysis process: First, analyze the types of qualifications that can be contracted for the project and determine a maximum of three qualification types (can be less than three)

[0105] Qualification Type 1: The first qualification type suitable for contracting the project

[0106] Score 1: The matching score between the contractable part of the project and the contractable content of the qualification (total score is 5). Only the score value is output.

[0107] Reason 1: Reason for contracting the project in whole or in part

[0108] Qualification Type 2: The second qualification type suitable for contracting this project

[0109] Score 2: The matching score between the contractable part of the project and the contractable content of the qualification (out of 5), only the score value is output

[0110] Reason 3: Reasons for contracting the project in whole or in part

[0111] Qualification Type 3: The third qualification type suitable for contracting this project

[0112] Score 3: The matching score of the contractable part of the project with its qualification contract content (total score 5), only the score value is output

[0113] Reason 3: Reason for contracting the project in whole or in part.

[0114] S304: Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type.

[0115] Specifically, each candidate qualification type and project structured information is filled into the qualification recommendation prompt word template to assemble the qualification prompt words for the qualification type recommendation.

[0116] S305: taking each qualification prompt word as a large model input, calling the large model interface to obtain each preferred qualification type, and the matching degree between each preferred qualification type and the target project.

[0117] Specifically, the above-mentioned qualification prompt words are used as messages, and the big model interface is called to receive the reply of the big model's understanding results. The reply results are parsed to extract the recommended preferred qualification types and their matching degree, which is reflected in the matching score (the score is 1-5, and the larger the score, the greater the matching degree), and the recommendation analysis basis information.

[0118] In an alternative embodiment, see Figure 4 As shown, Figure 4 A flowchart of a method for determining a minimum level requirement provided in the first embodiment of the present invention is shown, wherein the minimum level requirement of each target qualification type is determined according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information, including steps S401 to S402:

[0119] S401: For each target qualification type, determine in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type.

[0120] Specifically, for each qualification type, the corresponding qualification level type and level standard are obtained from the pre-configured qualification level database. According to the level type, it is determined from low to high whether it meets the project requirements.

[0121] Furthermore, a qualification level prompt word template is configured, and the structured information of the project department, the qualification level to be determined, the level classification standards and the engineering scale standards (if any) and other information are filled into the qualification level prompt word template to assemble the level prompt words for qualification level judgment.

[0122] The following is an example of a qualification level prompt word template:

[0123] Based on the permitted business contracting scope of the {qualification type name} {level name} qualification of {qualification category name} and the engineering scale classification standard of {qualification type name}, determine whether the qualification of this level can undertake the following projects:

[0124] ##Project Information

[0125] {Project structured information}

[0126] ##Permitted business scope:

[0127] {Qualification type specifies the scope of business contracting permitted by this level, such as different levels of qualifications allow for different scales of projects. Usually comes from documents issued by administrative departments or industry associations}

[0128] ##Standards for project scale classification in this qualification type:

[0129] {The classification standards for the projects or businesses involved in this qualification type. Generally comes from documents issued by administrative departments or industry associations}

[0130] ##Judgment rules

[0131] 1. Based on the given project information, the scale of the project is judged only based on the engineering scale classification standards. If there is no restriction in the engineering scale classification standards, it is deemed that it does not exceed the minimum scale limit.

[0132] 2. Note: In the above classification standards, "above" includes the number itself, while "below" does not include the number itself. For example, "embankment level below level 3" does not include level 3; "total investment exceeds RMB 50 million" includes RMB 50 million; "navigable tonnage exceeds 1,000 tons" includes 1,000 tons.

[0133] Output format

[0134] Detailed analysis: Please extract the key information of the project first and analyze it strictly according to the judgment rules

[0135] Conclusion: Yes, No

[0136] Take the above level prompt words as messages, call the big model interface, and receive the big model's response to the understanding results. Parse the response results to extract information on whether it meets the project requirements and the basis for analysis. If a certain level meets the requirements, there is no need to determine a higher qualification level. If not, continue to determine higher levels until the highest level.

[0137] S402: Determine the minimum qualification level met by the project structured information as the minimum level requirement of each target qualification type.

[0138] Specifically, the level determination of qualification types is not to give all level information to the big model and determine the qualification level at one time, but to use a method of determining each level from the lowest to the highest. This is because the qualification level cannot be set too high or too low, and the minimum qualification required by the project must be met. If the big model is allowed to make a one-time determination, it will appear that the big model believes that a higher level meets the project requirements, and thus make a determination higher than the actual required level, reducing the overall accuracy.

[0139] Embodiment 2

[0140] See also Figure 5 As shown, Figure 5 The schematic diagram of the structure of a supplier qualification recommendation system provided by the second embodiment of the present invention is shown, wherein the system includes a project information extraction agent module 501, a qualification type recommendation agent module 502, a qualification type combination algorithm module 503, a qualification level determination agent module 504 and a qualification level recommendation module 505;

[0141] The project information extraction agent module is used to generate project structured information of the target project according to the project description information of the target project;

[0142] The qualification type recommendation agent module is used to determine a number of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project;

[0143] The qualification type combination algorithm module is used to determine a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project;

[0144] The qualification level determination agent module is used to determine the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information;

[0145] The qualification level recommendation module is used to recommend the target qualification type combination and the minimum level requirements of each target qualification type in the target qualification type combination as the supplier qualification requirements of the target project.

[0146] In an optional implementation manner, generating the project structured information of the target project according to the project description information of the target project includes:

[0147] Configure the project structured extraction prompt word template;

[0148] Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information;

[0149] The project prompt words are used as the big model input, and the big model interface is called to obtain the project structured information.

[0150] In an optional implementation scheme, determining a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, includes:

[0151] Calculate the similarity between each optional qualification type and the project structured information respectively;

[0152] Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types;

[0153] Configure the qualification recommendation prompt word template;

[0154] Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type;

[0155] Each qualification prompt word is used as a large model input, and the large model interface is called to obtain each preferred qualification type and the matching degree between each preferred qualification type and the target project.

[0156] In an optional implementation manner, determining the minimum grade requirement of each target qualification type according to the grade classification standard of each target qualification type in the target qualification type combination and the project structured information includes:

[0157] For each target qualification type, determining in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type;

[0158] The minimum qualification level satisfied by the project structured information is determined as the minimum level requirement for each target qualification type.

[0159] Embodiment 3

[0160] Based on the same application concept, see Figure 6 As shown, Figure 6 FIG. 4 shows a schematic diagram of the structure of a computer device provided by Embodiment 3 of the present invention, wherein: Figure 6 As shown, a computer device 600 provided in Embodiment 3 of the present application includes:

[0161] A processor 601, a memory 602 and a bus 603, wherein the memory 602 stores machine-readable instructions executable by the processor 601. When the computer device 600 is running, the processor 601 communicates with the memory 602 via the bus 603. When the processor 601 is running, the machine-readable instructions execute the steps of the supplier qualification recommendation method shown in the above-mentioned embodiment 1.

[0162] Embodiment 4

[0163] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the supplier qualification recommendation method described in any one of the above embodiments are executed.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0165] The computer program product for recommending supplier qualifications provided in an embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can be found in the method embodiment, which will not be repeated here.

[0166] The supplier qualification recommendation system provided in the embodiment of the present invention can be specific hardware on the device or software or firmware installed on the device. The system provided in the embodiment of the present invention has the same implementation principle and technical effects as the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the system embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment. Technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can all refer to the corresponding processes in the aforementioned method embodiment, and will not be repeated here.

[0167] In the embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, device or unit, which can be electrical, mechanical or other forms.

[0168] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, each functional unit in the embodiment provided by the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0170] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0171] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0172] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions described in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or perform equivalent replacements on some of the technical features thereof; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. They should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A method for recommending supplier qualification requirements, characterized in that: Applied to a supplier qualification recommendation system, the system includes a project information extraction agent module, a qualification type recommendation agent module, a qualification type combination algorithm module, a qualification level determination agent module and a qualification level recommendation module, and the method includes: The project information extraction agent module generates project structured information of the target project according to the project description information of the target project; The qualification type recommendation agent module determines a number of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project; The qualification type combination algorithm module determines a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project; The qualification level determination agent module determines the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information; The qualification level recommendation module recommends the target qualification type combination and the minimum level requirement of each target qualification type in the target qualification type combination as the supplier qualification requirement of the target project.

2. The method according to claim 1, characterized in that The step of generating the project structured information of the target project according to the project description information of the target project includes: Configure the project structured extraction prompt word template; Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information; The project prompt words are used as the big model input, and the big model interface is called to obtain the project structured information.

3. The method according to claim 1, characterized in that Determining a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, includes: Calculate the similarity between each optional qualification type and the project structured information respectively; Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types; Configure the qualification recommendation prompt word template; Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type; Each qualification prompt word is used as a large model input, and the large model interface is called to obtain each preferred qualification type and the matching degree between each preferred qualification type and the target project.

4. The method according to claim 1, characterized in that The step of determining the minimum grade requirement of each target qualification type according to the grade classification standard of each target qualification type in the target qualification type combination and the project structured information includes: For each target qualification type, determining in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type; The minimum qualification level satisfied by the project structured information is determined as the minimum level requirement for each target qualification type.

5. A supplier qualification recommendation system, characterized in that: The system includes a project information extraction agent module, a qualification type recommendation agent module, a qualification type combination algorithm module, a qualification level determination agent module and a qualification level recommendation module; The project information extraction agent module is used to generate project structured information of the target project according to the project description information of the target project; The qualification type recommendation agent module is used to determine a number of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project; The qualification type combination algorithm module is used to determine a number of target qualification types to construct a target qualification type combination according to the matching degree between each preferred qualification type and the target project; The qualification level determination agent module is used to determine the minimum level requirement of each target qualification type according to the level classification standard of each target qualification type in the target qualification type combination and the project structured information; The qualification level recommendation module is used to recommend the target qualification type combination and the minimum level requirements of each target qualification type in the target qualification type combination as the supplier qualification requirements of the target project.

6. The system according to claim 5, characterized in that The step of generating the project structured information of the target project according to the project description information of the target project includes: Configure the project structured extraction prompt word template; Filling the project structured extraction prompt word template based on the project description information of the target project to obtain the project prompt words extracted from the project structured information; The project prompt words are used as the big model input, and the big model interface is called to obtain the project structured information.

7. The system according to claim 5, characterized in that Determining a plurality of preferred qualification types from various optional qualification types according to the project structured information, and the matching degree between each preferred qualification type and the target project, includes: Calculate the similarity between each optional qualification type and the project structured information respectively; Determine the optional qualification types whose similarity meets the preset requirements as candidate qualification types; Configure the qualification recommendation prompt word template; Filling the qualification recommendation prompt word template based on each candidate qualification type and the project structured information to obtain the qualification prompt words recommended for each qualification type; Each qualification prompt word is used as a large model input, and the large model interface is called to obtain each preferred qualification type and the matching degree between each preferred qualification type and the target project.

8. The system according to claim 5, characterized in that The step of determining the minimum grade requirement of each target qualification type according to the grade classification standard of each target qualification type in the target qualification type combination and the project structured information includes: For each target qualification type, determining in turn whether the project structured information meets the grade classification standards of each qualification grade of the target qualification type; The minimum qualification level satisfied by the project structured information is determined as the minimum level requirement for each target qualification type.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the supplier qualification recommendation method as described in any one of claims 1 to 4 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the supplier qualification recommendation method as described in any one of claims 1 to 4.

Images