Enterprise service matching method and system based on large language model

Abstract

The present application provides a method and system for matching enterprise services based on a large language model, which belongs to the field of computer science and solves the problem that the current enterprise service matching method is highly dependent on a large amount of data generated by users in the enterprise service platform as a reference, and it is difficult to accurately match the real needs of enterprise users in the early stage of using the enterprise service platform. The method includes: extracting enterprise identification information based on the basic information of user registration on the enterprise service platform to determine the target enterprise; using the enterprise identification information to capture the recruitment information associated with the target enterprise on the recruitment website while the user browses the enterprise service platform; using the large language model to perform natural language processing on the recruitment information, identify the functional type of the functional positions in the target enterprise, and match the service items for the target enterprise based on the functional type.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an enterprise service matching method and system based on a large language model. Background Art

[0002] With the rapid development of the economy and the intensification of market competition, enterprises are facing more and more challenges and opportunities. In order to adapt to these changes and improve the competitiveness of enterprises, the construction of enterprise service platforms came into being. With the diversification and complexity of corporate business, the demand for legal, financial, tax, investment and financing, and intellectual property services continues to increase. Enterprises rely on external professional services to different degrees at different stages of development and business scenarios, and require personalized and accurate service recommendations. At present, when making business recommendations to enterprises, enterprise service platforms generally still base their recommendations on data such as users' consultation and browsing behaviors on the service platform, and then analyze users' possible service business interests, and finally match and recommend service businesses. However, this method is highly dependent on the large amount of data generated by users on the enterprise service platform as a reference. It is difficult to accurately match the real needs of enterprise users in the early stages of users' use of the enterprise service platform. Summary of the invention

[0003] The embodiments of the present application provide an enterprise service matching method and system based on a large language model, which can solve the problem that current enterprise service platforms generally make service recommendations to enterprises based on data such as users' consulting and browsing behaviors in the service platform, and then analyze users' possible service interests, and finally match and recommend services. However, this method is highly dependent on a large amount of data generated by users in the enterprise service platform as a reference, and it is difficult to accurately match the real needs of enterprise users in the early stages of users using the enterprise service platform.

[0004] A first aspect of an embodiment of the present application provides an enterprise service matching method based on a large language model, comprising:

[0005] Based on the basic user registration information of the enterprise service platform, extract the enterprise identification information to determine the target enterprise;

[0006] While the user is browsing the enterprise service platform, using the enterprise identification information to crawl the recruitment information associated with the target enterprise on the recruitment website;

[0007] The recruitment information is processed by natural language using a large language model to identify the functional types of the functional positions being recruited by the target enterprise, so as to match service projects for the target enterprise based on the functional types.

[0008] Optionally, it also includes:

[0009] Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise;

[0010] Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type;

[0011] In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

[0012] Optionally, it also includes:

[0013] Obtaining historical recruitment information of the target enterprise;

[0014] When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

[0015] Optionally, it also includes:

[0016] Obtain the release time of the functional positions currently being recruited by the target enterprise;

[0017] The matching of service items for the target enterprise based on the functional type includes:

[0018] Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or,

[0019] Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements;

[0020] The matching of service items for the target enterprise based on the functional type includes:

[0021] Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

[0022] Optionally, it also includes:

[0023] A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

[0024] Optionally, also include:

[0025] Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types;

[0026] In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

[0027] Optionally, the method further includes: optimizing the matched service items by using a particle swarm optimization algorithm to determine the target service items.

[0028] A second aspect of the embodiment of the present application provides an enterprise service matching system based on a large language model, including:

[0029] A determination unit, used to extract enterprise identification information based on user registration basic information of the enterprise service platform to determine the target enterprise;

[0030] A capture unit, used to capture the recruitment information associated with the target enterprise on the recruitment website by using the enterprise identification information while the user is browsing the enterprise service platform;

[0031] The matching unit is used to perform natural language processing on the recruitment information using a large language model, identify the functional types of the functional positions being recruited by the target enterprise, and match service items for the target enterprise based on the functional types.

[0032] A third aspect of an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the processor is configured to implement the steps of the above-mentioned enterprise service matching method based on a large language model when executing a computer program stored in the memory.

[0033] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned enterprise service matching method based on a large language model.

[0034] In summary, the enterprise service matching method based on a large language model provided in the embodiment of the present application extracts enterprise identification information based on the basic information of user registration on the enterprise service platform to determine the target enterprise; while the user browses the enterprise service platform, the enterprise identification information is used to capture the recruitment information associated with the target enterprise on the recruitment website; the large language model is used to perform natural language processing on the recruitment information to identify the functional type of the functional position being recruited by the target enterprise, so as to match the service project for the target enterprise based on the functional type. As a result, it is not necessary for enterprise users to generate a large amount of behavioral data on the service platform before predicting and analyzing user needs, and the potential needs of users can be proactively and timely mined. By capturing the recruitment information of the enterprise and identifying the functional type, the system can accurately understand the current needs of the enterprise, thereby recommending related service projects. For example, if a company is recruiting marketing personnel, the system can recommend market research services, advertising promotion services, marketing training, etc. While the user is browsing the platform, the system automatically captures and processes the recruitment information to ensure the real-time and accuracy of the recommended information. Reduce manual intervention and improve efficiency. Through accurate matching and recommendation services, enterprise users can quickly find the required services, improving user experience and satisfaction. At the same time, the automated recommendation process also reduces the user's operating burden. The accurate service recommendation function is a highlight of the enterprise service platform, which can attract more corporate users and enhance the platform's competitiveness and user stickiness.

[0035] Correspondingly, the system, electronic device, and computer-readable storage medium provided by the embodiments of the present invention also have the above-mentioned technical effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flowchart of a possible enterprise service matching method based on a large language model provided in an embodiment of the present application;

[0037] Figure 2 A schematic structural block diagram of a possible enterprise service matching system based on a large language model provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of the hardware structure of a possible enterprise service matching system based on a large language model provided in an embodiment of the present application;

[0039] Figure 4 A schematic structural block diagram of a possible electronic device provided in an embodiment of the present application;

[0040] Figure 5 A schematic structural block diagram of a possible computer-readable storage medium provided for an embodiment of the present application. DETAILED DESCRIPTION

[0041] The embodiment of the present application provides an enterprise service matching method and related equipment based on a large language model, which can solve the problem that the current enterprise service platform generally recommends services to enterprises based on data such as users' consulting and browsing behaviors in the service platform, and then analyzes the users' possible service interests, and finally matches and recommends services. However, this method is highly dependent on the large amount of data generated by users in the enterprise service platform as a reference, and it is difficult to accurately match the real needs of enterprise users in the early stages of users using the enterprise service platform.

[0042] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0043] See also Figure 1 , which is a flow chart of an enterprise service matching method based on a large language model provided in an embodiment of the present application, which may specifically include:

[0044] S110-S130.

[0045] S110, extracting enterprise identification information based on user registration basic information of the enterprise service platform to determine the target enterprise.

[0046] For example, on the enterprise service platform, when registering, enterprise users need to fill in the basic information of the enterprise, including enterprise name, business size, address, contact information, etc. This information will be used as identification information for data crawling on external websites.

[0047] S120, while the user is browsing the enterprise service platform, the enterprise identification information is used to crawl the recruitment information associated with the target enterprise on the recruitment website.

[0048] For example, while the user is browsing the enterprise service platform, the system will use the extracted enterprise identification information to crawl the recruitment information of the target enterprise on multiple recruitment websites (such as Zhaopin.com, 51Job.com, Liepin.com, etc.). This step requires the use of web crawler technology to obtain recruitment information through API or web page parsing.

[0049] S130, using a large language model to perform natural language processing on the recruitment information, identifying the functional types of the functional positions being recruited by the target enterprise, and matching service items for the target enterprise based on the functional types.

[0050] Exemplarily, the captured recruitment information is text data and needs to be parsed using natural language processing technology. First, HTML tags, stop words, and word segmentation can be removed. Then, key entities in the recruitment information are identified, such as job titles, job responsibilities, skill requirements, etc. Finally, the functional type of the recruitment position (such as finance, human resources, marketing, etc.) is identified based on the pre-trained large language model. Based on the identified functional type, the system will match the corresponding service items on the enterprise service platform. The platform's service project library needs to be pre-classified and organized according to functional type for quick matching. The matched service items are recommended to enterprise users through the platform. The recommendation method can be a pop-up prompt, message notification, page recommendation module, etc.

[0051] Taking the identified job function type as a marketing job as an example, a company registered on the enterprise service platform and filled in the company name "ABC Technology". The system used the company name to capture the following recruitment information on the recruitment website: Recruitment position: Marketing manager; Job responsibilities: responsible for market research, advertising promotion, brand management, etc.; Skill requirements: Have marketing experience and be familiar with various promotion channels. The system identified that the position belongs to the "marketing" function type through natural language processing technology. According to the matching rules, the system recommended the following service items: Market research service: help companies conduct market analysis and user research; Advertising promotion service: provide advertising design, delivery and effect monitoring; Brand management training: provide brand management related training courses.

[0052] Taking the identified job function type of finance and taxation as an example, a company registered on the enterprise service platform and filled in the company name "XYZ Manufacturing Company". The system used the company name to capture the following recruitment information on the recruitment website: Recruitment position: Financial Manager; Job responsibilities: Responsible for financial planning, budget management, tax planning, etc.; Skill requirements: Have a background in accounting and financial management, familiar with financial statements, tax policies, etc.; The system identified that the position belongs to the "finance" function type through natural language processing technology. According to the matching rules, the system recommends the following service items, such as financial planning services: Provide financial planning, budget preparation and management services to help companies optimize the use of funds. Tax planning services: Provide tax planning solutions to help companies save taxes legally and reduce tax risks. Accounting and bookkeeping services: Provide daily accounting and bookkeeping services to ensure that financial data is accurate and timely. Financial statement analysis services: Provide analysis and interpretation of financial statements to help companies understand their operating conditions and make scientific decisions.

[0053] In summary, the enterprise service matching method based on the large language model provided in the above embodiment of the present application extracts enterprise identification information based on the basic information of user registration on the enterprise service platform to determine the target enterprise; while the user browses the enterprise service platform, the enterprise identification information is used to capture the recruitment information associated with the target enterprise on the recruitment website; the large language model is used to perform natural language processing on the recruitment information to identify the functional type of the functional position of the target enterprise in recruitment, so as to match the service project for the target enterprise based on the functional type. As a result, it is not necessary for enterprise users to generate a large amount of behavioral data on the service platform before predicting and analyzing user needs, and the potential needs of users can be proactively and timely mined. By capturing the recruitment information of the enterprise and identifying the functional type, the system can accurately understand the current needs of the enterprise, so as to recommend related service projects. For example, if a company is recruiting marketing personnel, the system can recommend market research services, advertising promotion services, marketing training, etc. While the user is browsing the platform, the system automatically captures and processes the recruitment information to ensure the real-time and accuracy of the recommended information. Reduce manual intervention and improve efficiency. Through accurate matching and recommendation services, enterprise users can quickly find the required services, which improves user experience and satisfaction. At the same time, the automated recommendation process also reduces the user's operating burden. The accurate service recommendation function is a highlight of the enterprise service platform, which can attract more corporate users and enhance the platform's competitiveness and user stickiness.

[0054] In some examples, this also includes:

[0055] Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise;

[0056] Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type;

[0057] In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

[0058] For example, through in-depth analysis of job responsibilities information, the system can more accurately understand the specific needs of the enterprise, especially identify the responsibilities of the service provider management type, and accurately recommend corresponding service projects. For example, if the enterprise is recruiting for a position responsible for outsourcing management, the system will recommend corresponding outsourcing services and management tools. If it is determined based on the analysis that the enterprise hopes to recruit people to complete the corresponding business, rather than just to recruit people to screen and manage external service providers for the corresponding business. Then, it is very likely that the target enterprise does not have a large service demand for the business corresponding to this functional position.

[0059] In some examples, this also includes:

[0060] Obtaining historical recruitment information of the target enterprise;

[0061] When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

[0062] For example, the historical recruitment information of the enterprise can be queried to analyze whether the enterprise has ever recruited for specific positions and whether these positions have been filled. If certain positions have never been recruited, it may indicate that the enterprise has outsourcing needs for the service items corresponding to the functions of these positions.

[0063] In some examples, this also includes:

[0064] Obtain the release time of the functional positions currently being recruited by the target enterprise;

[0065] The matching of service items for the target enterprise based on the functional type includes:

[0066] Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or,

[0067] Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements;

[0068] The matching of service items for the target enterprise based on the functional type includes:

[0069] Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

[0070] For example, through in-depth analysis of job responsibilities and posting time, the system can more accurately understand the specific needs of the enterprise, especially identify the management responsibilities of the service provider, and accurately recommend corresponding service projects. For example, if the enterprise is recruiting for a position responsible for outsourcing management, the system will recommend corresponding outsourcing services and management tools, and take into account the posting time of the recruitment information to ensure that the recommended service projects are the latest and most relevant.

[0071] For example, taking marketing positions as an example, a company registered on the enterprise service platform and filled in the company name "ABC Technology". The system used the company name to capture the following recruitment information on the recruitment website: Recruitment position: Marketing manager; Job responsibilities: responsible for market research, advertising promotion, brand management, etc.; Release time: June 1, 2024; Analysis of recruitment type: Emergency recruitment. The system identified that the position belongs to the "marketing" function type through natural language processing technology, and further analyzed the responsibility type as "service provider management type" and the recruitment type as "urgent recruitment". According to the matching rules, the system recommended the following service items: Market research service: Help companies conduct market analysis and user research, and give priority to service providers who can respond quickly. Advertising promotion service: Provide advertising design, delivery and effect monitoring, and give priority to advertising services that are quickly implemented. Brand management consulting service: Provide brand management-related consulting and services, assist in the management of external brand promotion service providers, and give priority to service providers with efficient responses.

[0072] For example, taking finance and taxation positions as an example, a company registered on the enterprise service platform and filled in the company name "ABC Technology". The system used the company name to capture the following recruitment information on the recruitment website: Recruitment position: Financial Manager; Job Responsibilities: Responsible for financial planning, budget management, tax planning, etc.; Release Time: June 5, 2024; Recruitment Type: Regular Recruitment. The system identified that the position belongs to the "finance" function type through natural language processing technology, and further analyzed the responsibility type as "autonomous service type" and the recruitment type as "regular recruitment". According to the matching rules, the system recommended the following service items: Financial planning services: Provide financial planning, budget preparation and management services to help companies optimize the use of funds. Tax planning services: Provide tax planning solutions to help companies legally save taxes and reduce tax risks. Accounting and bookkeeping services: Provide daily accounting and bookkeeping services to ensure that financial data is accurate and timely.

[0073] Then, it is predicted that the target enterprise ABC Technology currently has a greater demand for market research services, advertising promotion services and brand management consulting services than financial planning services, tax planning services and accounting services.

[0074] In some examples, this also includes:

[0075] A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

[0076] For example, a large language model is used to conduct an in-depth analysis of the target company's job responsibility information, and generate personalized service recommendation scripts based on the function type, responsibility type, recruitment type and urgency.

[0077] In some examples, this also includes:

[0078] Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types;

[0079] In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

[0080] Exemplarily, a large language model is used to generate auxiliary questions for matching target enterprise service projects of target functional types through the instant messaging function of recruitment websites. These questions are intended to further understand the specific needs and priorities of the enterprise. The system sends auxiliary questions to the enterprise through the instant messaging function and collects feedback messages from the enterprise on these questions. These feedback messages may include clarification of specific service needs, confirmation of priorities, etc. According to the functional type, responsibility type, recruitment type, urgency, and feedback messages of the enterprise on the auxiliary questions of the target enterprise, the corresponding service projects are matched for the target enterprise. The large language model is used to conduct in-depth analysis of the job responsibility information and feedback messages of the target enterprise to generate personalized service recommendation speech information. The matched service projects and the generated recommendation speech are recommended to enterprise users through the platform. The recommendation method can be a pop-up prompt, message notification, page recommendation module, etc. Therefore, by generating and using auxiliary questions to further understand the specific needs of the enterprise, the system can recommend service projects more accurately and ensure that the recommended service projects are highly matched with the actual needs of the enterprise. Personalized recommendation speech can also better convey the value of the recommended service.

[0081] In some examples, this also includes:

[0082] The matched service items are optimized through the particle swarm optimization algorithm to determine the target service items.

[0083] For example, in an enterprise service platform, for a target enterprise, enterprise A, several service items need to be recommended. The goal of recommendation is to maximize the relevance of the service items while minimizing the urgency of the enterprise's needs. Assume that the set of recommended service items is S={s1,s2,...,sn}.

[0084] First, define two objective functions: service item relevance f1 and enterprise demand urgency f2.

[0085] The higher the relevance of the service items, the better, and the lower the urgency of the enterprise needs, the better. PSO can be used to find an optimal solution so that these two objective functions are optimized at the same time. Define the parameter Ri: Service items s i The correlation with enterprise A, the value range is [0,1], the larger the value, the higher the correlation. i :Enterprise A for service items i The urgency of the service is in the range of [0,1]. The smaller the value, the lower the urgency. In particle swarm optimization, each particle represents a possible recommended combination of service items. Assume that there are N particles, and the position of each particle xj=(x j1 ,x j2 ,...,x jn ), where x ji Represents particle j's response to service item s i The particle speed update formula is as follows:

[0086] v ji (t+1)=w·v ji (t)+c1·r1·(p ji (t)-x ji (t))+c2·r2·(g i (t)-x ji (t))

[0087] Among them, w is the inertia weight, which indicates the influence of the current velocity of the particle; c1 and c2 are learning factors, which indicate the learning ability of the particle for its own optimal position and the optimal position of the group; r1 and r2 are random numbers with a value range of [0,1]; p ji (t) is the historical optimal position of particle j in the i-th dimension. i (t) is the global optimal position.

[0088] The particle's current position update formula is as follows:

[0089] x ji (t+1)=x ji (t)+v ji (t+1)

[0090] Define the fitness function f to evaluate the quality of particles. Combined with the objective function in this application scenario, the fitness function can be defined as:

[0091] f(x j ) = α∑ n i=1 Ri·x ji -β∑ n i=1 U i ·x ji

[0092] Among them, α and β are weight factors used to balance the importance of service item relevance and enterprise demand urgency. Randomly initialize the position and speed of the particle. According to the fitness function f(x j ) Calculate the fitness value of each particle. Update the historical optimal position p of the particle ji (t) and the global optimal position g of the group i (t). According to the speed update formula and the position update formula, update the speed and position of each particle. Until the termination condition is met (such as reaching the maximum number of iterations or the fitness value no longer changes significantly). Finally, the service item recommendation combination corresponding to the optimal particle position xbest found by the particle swarm optimization algorithm is the optimal recommendation solution, which can achieve a balance between maximizing the relevance of service items and minimizing the urgency of enterprise needs. Through the above method, the particle swarm optimization algorithm can be effectively used to optimize the recommendation of enterprise service items, so that the recommendation results not only meet the business needs of the enterprise, but also can respond to urgent needs in a timely manner.

[0093] The above describes the enterprise service matching method based on a large language model in an embodiment of the present application. The following describes the enterprise service matching system based on a large language model in an embodiment of the present application.

[0094] See also Figure 2 In the embodiments of the present application, an embodiment of an enterprise service matching system based on a large language model is described, which may include:

[0095] A determination unit 201 is used to extract enterprise identification information based on user registration basic information of the enterprise service platform to determine a target enterprise;

[0096] The capture unit 202 is used to capture the recruitment information associated with the target enterprise on the recruitment website by using the enterprise identification information while the user browses the enterprise service platform;

[0097] The matching unit 203 is used to perform natural language processing on the recruitment information using a large language model, identify the functional types of the functional positions being recruited by the target enterprise, and match service items for the target enterprise based on the functional types.

[0098] In summary, the enterprise service matching system based on the large language model provided in the above embodiment extracts enterprise identification information based on the basic information of user registration on the enterprise service platform to determine the target enterprise; while the user browses the enterprise service platform, the enterprise identification information is used to capture the recruitment information associated with the target enterprise on the recruitment website; the large language model is used to perform natural language processing on the recruitment information to identify the functional type of the functional position being recruited by the target enterprise, so as to match the service items for the target enterprise based on the functional type. As a result, it is not necessary for enterprise users to generate a large amount of behavioral data on the service platform before predicting and analyzing user needs, and the potential needs of users can be proactively and timely mined. By capturing the recruitment information of the enterprise and identifying the functional type, the system can accurately understand the current needs of the enterprise, thereby recommending related service items. For example, if a company is recruiting marketing personnel, the system can recommend market research services, advertising promotion services, marketing training, etc. While the user is browsing the platform, the system automatically captures and processes the recruitment information to ensure the real-time and accuracy of the recommended information. Reduce manual intervention and improve efficiency. Through accurate matching and recommendation services, enterprise users can quickly find the required services, improving user experience and satisfaction. At the same time, the automated recommendation process also reduces the user's operating burden. The accurate service recommendation function is a highlight of the enterprise service platform, which can attract more corporate users and enhance the platform's competitiveness and user stickiness.

[0099] above Figure 2 The enterprise service matching system based on a large language model in the embodiment of the present application is described from the perspective of modular functional entities. The enterprise service matching system based on a large language model in the embodiment of the present application is described in detail from the perspective of hardware processing. Please refer to Figure 3 , an embodiment of the enterprise service matching system 300 based on a large language model in the embodiment of the present application includes:

[0100] An input device 301, an output device 302, a processor 303 and a memory 304, wherein the number of the processor 303 can be one or more. Figure 3 In some embodiments of the present application, the input device 301, the output device 502, the processor 303 and the memory 304 may be connected via a bus or other means, wherein: Figure 3 The example of connecting through bus is taken in the following.

[0101] Wherein, by calling the operation instruction stored in the memory 304, the processor 303 is used to perform the following steps:

[0102] Based on the basic user registration information of the enterprise service platform, extract the enterprise identification information to determine the target enterprise;

[0103] While the user is browsing the enterprise service platform, using the enterprise identification information to crawl the recruitment information associated with the target enterprise on the recruitment website;

[0104] The recruitment information is processed by natural language using a large language model to identify the functional types of the functional positions being recruited by the target enterprise, so as to match service projects for the target enterprise based on the functional types.

[0105] Optionally, it also includes:

[0106] Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise;

[0107] Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type;

[0108] In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

[0109] Optionally, it also includes:

[0110] Obtaining historical recruitment information of the target enterprise;

[0111] When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

[0112] Optionally, it also includes:

[0113] Obtain the release time of the functional positions currently being recruited by the target enterprise;

[0114] The matching of service items for the target enterprise based on the functional type includes:

[0115] Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or,

[0116] Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements;

[0117] The matching of service items for the target enterprise based on the functional type includes:

[0118] Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

[0119] Optionally, it also includes:

[0120] A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

[0121] Optionally, also include:

[0122] Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types;

[0123] In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

[0124] By calling the operation instructions stored in the memory 304, the processor 303 is also used to execute Figure 1 Any method in the corresponding embodiment.

[0125] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of an electronic device provided in an embodiment of the present application.

[0126] like Figure 4 As shown, an embodiment of the present application provides an electronic device, including a memory 410, a processor 420, and a computer program 411 stored in the memory 420 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0127] Based on the basic user registration information of the enterprise service platform, extract the enterprise identification information to determine the target enterprise;

[0128] While the user is browsing the enterprise service platform, using the enterprise identification information to crawl the recruitment information associated with the target enterprise on the recruitment website;

[0129] The recruitment information is processed by natural language using a large language model to identify the functional types of the functional positions being recruited by the target enterprise, so as to match service projects for the target enterprise based on the functional types.

[0130] Optionally, it also includes:

[0131] Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise;

[0132] Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type;

[0133] In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

[0134] Optionally, it also includes:

[0135] Obtaining historical recruitment information of the target enterprise;

[0136] When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

[0137] Optionally, it also includes:

[0138] Obtain the release time of the functional positions currently being recruited by the target enterprise;

[0139] The matching of service items for the target enterprise based on the functional type includes:

[0140] Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or,

[0141] Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements;

[0142] The matching of service items for the target enterprise based on the functional type includes:

[0143] Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

[0144] Optionally, it also includes:

[0145] A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

[0146] Optionally, also include:

[0147] Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types;

[0148] In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

[0149] In the specific implementation process, when the processor 420 executes the computer program 411, it can achieve Figure 1 Any implementation manner in the corresponding embodiments.

[0150] Since the electronic device introduced in this embodiment is a device used to implement an enterprise service matching system based on a large language model in the embodiment of the present application, based on the method introduced in the embodiment of the present application, technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0151] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present application.

[0152] like Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 511 is stored. When the computer program 511 is executed by a processor, the following steps are implemented:

[0153] Based on the basic user registration information of the enterprise service platform, extract the enterprise identification information to determine the target enterprise;

[0154] While the user is browsing the enterprise service platform, using the enterprise identification information to crawl the recruitment information associated with the target enterprise on the recruitment website;

[0155] The recruitment information is processed by natural language using a large language model to identify the functional types of the functional positions being recruited by the target enterprise, so as to match service projects for the target enterprise based on the functional types.

[0156] Optionally, it also includes:

[0157] Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise;

[0158] Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type;

[0159] In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

[0160] Optionally, it also includes:

[0161] Obtaining historical recruitment information of the target enterprise;

[0162] When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

[0163] Optionally, it also includes:

[0164] Obtain the release time of the functional positions currently being recruited by the target enterprise;

[0165] The matching of service items for the target enterprise based on the functional type includes:

[0166] Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or,

[0167] Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements;

[0168] The matching of service items for the target enterprise based on the functional type includes:

[0169] Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

[0170] Optionally, it also includes:

[0171] A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

[0172] Optionally, also include:

[0173] Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types;

[0174] In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

[0175] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0176] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0177] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device 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, such as 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 interfaces, devices or units, which can be electrical, mechanical or other forms.

[0178] 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.

[0179] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0180] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or 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 a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0181] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An enterprise service matching method based on a large language model, characterized in that: The method comprises: Based on the basic user registration information of the enterprise service platform, extract the enterprise identification information to determine the target enterprise; While the user is browsing the enterprise service platform, using the enterprise identification information to crawl the recruitment information associated with the target enterprise on the recruitment website; Using a large language model to perform natural language processing on recruitment information, identifying the functional types of the functional positions being recruited by the target enterprise, and matching service projects for the target enterprise based on the functional types; Also includes: Obtaining job responsibilities information corresponding to different functional types of the functional positions currently recruited by the target enterprise; Use a large language model to perform natural language processing on job responsibilities information, analyze and predict the types of responsibilities of the target company's recruiting functional positions, including service provider management type and autonomous service type; In the case where the responsibility type of the first functional type in the functional positions being recruited by the target enterprise is a service provider management type, service projects are matched for the target enterprise based on the business content associated with the first functional type.

2. The method according to claim 1, characterized in that: Also includes: Obtaining historical recruitment information of the target enterprise; When there is historical recruitment information but no current recruitment information for the second functional type of the target enterprise, the service exclusion type of the target enterprise is predicted based on the business content associated with the second functional type to filter matching service items for the target enterprise.

3. The method according to claim 1, characterized in that Also includes: Obtain the release time of the functional positions currently being recruited by the target enterprise; The matching of service items for the target enterprise based on the functional type includes: Matching service projects for the target enterprise based on the functional type and the release time of the corresponding functional positions being recruited; and / or, Using a large language model to perform natural language processing on recruitment information, identifying the recruitment types of the functional positions being recruited by the target enterprise, wherein the recruitment types are used to distinguish the urgency of the job requirements; The matching of service items for the target enterprise based on the functional type includes: Match service items for the target enterprise based on the function type and the urgency of the corresponding job requirements.

4. The method according to claim 1, characterized in that: Also includes: A large language model is used to perform natural language processing on the job responsibilities information of the target enterprise, and the service recommendation script information for the target enterprise by the enterprise service platform is determined.

5. The method according to any one of claims 1 to 4, characterized in that Also includes: Using the large language model, the instant messaging function of recruitment websites is used to generate auxiliary questions for matching target enterprise service projects with target functional types; In response to the feedback message of the target enterprise to the auxiliary question, a service item is matched for the target enterprise based on the target function type and the feedback message.

6. The method according to any one of claims 1 to 4, characterized in that Also includes: The matched service items are optimized through the particle swarm optimization algorithm to determine the target service items.

7. An enterprise service matching system based on a large language model, characterized in that: According to the method according to any one of claims 1 to 6, the system comprises: A determination unit, used to extract enterprise identification information based on user registration basic information of the enterprise service platform to determine the target enterprise; A capture unit, used to capture the recruitment information associated with the target enterprise on the recruitment website by using the enterprise identification information while the user is browsing the enterprise service platform; The matching unit is used to perform natural language processing on the recruitment information using a large language model, identify the functional types of the functional positions being recruited by the target enterprise, and match service items for the target enterprise based on the functional types.

8. An electronic device, characterized in that: The electronic device includes at least one processor and at least one memory connected to the processor, wherein the processor is used to call program instructions in the memory to execute the enterprise service matching method based on a large language model as described in any one of claims 1 to claim 6.

9. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the enterprise service matching method based on a large language model as described in any one of claims 1 to claim 6.

Images