CN118673201A - Enterprise service matching method and system based on large language model - Google Patents
Enterprise service matching method and system based on large language model Download PDFInfo
- Publication number
- CN118673201A CN118673201A CN202411142347.XA CN202411142347A CN118673201A CN 118673201 A CN118673201 A CN 118673201A CN 202411142347 A CN202411142347 A CN 202411142347A CN 118673201 A CN118673201 A CN 118673201A
- Authority
- CN
- China
- Prior art keywords
- enterprise
- service
- recruitment
- target
- target enterprise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 230000007115 recruitment Effects 0.000 claims abstract description 140
- 230000006870 function Effects 0.000 claims abstract description 117
- 238000003058 natural language processing Methods 0.000 claims abstract description 36
- 239000002245 particle Substances 0.000 claims description 21
- 238000003860 storage Methods 0.000 claims description 14
- 230000007717 exclusion Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000001419 dependent effect Effects 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 29
- 238000013439 planning Methods 0.000 description 12
- 238000011160 research Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 238000012946 outsourcing Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an enterprise service matching method and system based on a large language model, belongs to the field of computers, and solves the problem that the conventional enterprise service matching mode is highly dependent on a large amount of data generated by a user in an enterprise service platform as a reference, and the real requirements of the enterprise user are difficult to accurately match in the initial stage of using the enterprise service platform by the user. The method comprises the following steps: based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise; capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform; and carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Description
Technical Field
The application relates to the technical field of computers, in particular to an enterprise service matching method and system based on a large language model.
Background
With the rapid development of economy and the aggravation of market competition, enterprises face more and more challenges and opportunities. To accommodate these changes, enterprise competitiveness is improved and enterprise service platforms are built. With the diversification and complexity of business, there is an increasing demand for services such as law, finance, tax, financing, and intellectual property. Enterprises have different dependence degrees on external professional services in different development stages and business scenes, and personalized and accurate service recommendation is required. The conventional enterprise service platform is generally used for recommending the business or based on data such as consultation and browsing behaviors of a user in the service platform, so that possible service interest points of the user are analyzed, and finally service matching and recommendation are performed.
Disclosure of Invention
The embodiment of the application provides an enterprise service matching method and system based on a large language model, which can solve the problems that the conventional enterprise service platform is common in service recommendation of enterprises or based on data such as consultation and browsing behaviors of users in the service platform, so that possible service interest points of the users are analyzed, and finally service matching and recommendation are performed, but the method is highly dependent on a large amount of data generated by the users in the enterprise service platform as a reference, and the real demands of the users of the enterprises are difficult to accurately match in the initial stage of using the enterprise service platform by the users.
A first aspect of an embodiment of the present application provides an enterprise service matching method based on a large language model, including:
based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise;
capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform;
And carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Optionally, the method further comprises:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
Optionally, the method further comprises:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
Optionally, the method further comprises:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
Optionally, the method further comprises:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
Optionally, the method further comprises:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
Optionally, the method further comprises: and optimizing the matched service items through a particle swarm optimization algorithm, and determining a target service item.
A second aspect of an embodiment of the present application provides an enterprise service matching system based on a large language model, including:
the determining unit is used for extracting enterprise identification information based on the user registration basic information of the enterprise service platform so as to determine a target enterprise;
The grabbing unit is used for grabbing recruitment information associated with the target enterprise on a recruitment website by utilizing the enterprise identification information while a user browses the enterprise service platform;
And the matching unit is used for carrying out natural language processing on recruitment information by utilizing the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match the service item for the target enterprise based on the function type.
A third aspect of the embodiments of the present application provides an electronic device, including a memory, and a processor, where the processor is configured to implement the steps of the above-described large language model-based enterprise service matching method when executing a computer program stored in the memory.
A fourth aspect of the embodiments of the present application provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the large language model based enterprise service matching method described above.
In summary, according to the enterprise service matching method based on the large language model provided by the embodiment of the application, the enterprise identification information is extracted through the user registration basic information based on the enterprise service platform so as to determine the target enterprise; capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform; and carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type. Therefore, the enterprise user is not required to predict and analyze the user demands after a great amount of behavior data is generated by the service platform, and the potential demands of the user can be actively and timely mined. By capturing recruitment information of the enterprise and performing function type identification, the system can accurately know the current requirements of the enterprise, so that service items related to the enterprise are recommended. For example, an enterprise is recruiting marketers, and the system may recommend market research services, advertising services, marketing training, and the like. The system automatically captures and processes recruitment information while a user browses the platform, and ensures the instantaneity and accuracy of the recommended information. Reduces manual intervention and improves efficiency. Through accurate matching and recommending of services, enterprise users can quickly find out required services, and user experience and satisfaction are improved. Meanwhile, the automatic recommendation process also reduces the operation burden of the user. The accurate service recommendation function is a bright spot of the enterprise service platform, can attract more enterprise users, and improves the competitiveness and user viscosity of the platform.
Accordingly, the system, the electronic device and the computer readable storage medium provided by the embodiment of the invention also have the technical effects.
Drawings
FIG. 1 is a schematic flow diagram of a possible enterprise service matching method based on a large language model according to an embodiment of the present application;
FIG. 2 is a schematic block diagram of a possible large language model-based enterprise service matching system according to an embodiment of the present application;
FIG. 3 is a schematic diagram of a possible large language model-based hardware architecture of an enterprise service matching system according to an embodiment of the present application;
FIG. 4 is a schematic block diagram of one possible electronic device according to an embodiment of the present application;
Fig. 5 is a schematic block diagram of one possible computer-readable storage medium provided by an embodiment of the present application.
Detailed Description
The embodiment of the application provides an enterprise service matching method and related equipment based on a large language model, which can solve the problems that the conventional enterprise service platform is common in service recommendation of enterprises or based on data such as consultation and browsing behaviors of users in the service platform, so that possible service interest points of the users are analyzed, and finally service matching and recommendation are performed, but the method is highly dependent on a large amount of data generated by the users in the enterprise service platform as a reference, and the real demands of the enterprise users are difficult to accurately match in the initial stage of using the enterprise service platform by the users.
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus. The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments.
Referring to fig. 1, a flowchart of an enterprise service matching method based on a large language model according to an embodiment of the present application may specifically include:
S110-S130。
S110, extracting enterprise identification information based on user registration basic information of the enterprise service platform to determine a target enterprise.
Illustratively, on the enterprise service platform, the enterprise user needs to fill in basic information of the enterprise when registering, including enterprise name, word size, address, contact information, and the like. This information will be used as identification information for data crawling at external websites.
S120, capturing recruitment information associated with the target enterprise in a recruitment website by utilizing the enterprise identification information while the user browses the enterprise service platform.
Illustratively, while the user is browsing the enterprise service platform, the system will utilize the extracted enterprise identification information to capture recruitment information for the target enterprise on multiple recruitment websites (e.g., intelligent recruitment, forward carefree recruitment, etc.). This step requires the use of web crawler technology to obtain recruitment information by means of API or web page parsing, etc.
And S130, carrying out natural language processing on recruitment information by using a large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Illustratively, the captured recruitment information is text data that requires parsing using natural language processing techniques. First HTML tags, stop words, segmentation, etc. may be removed. Key entities in the recruitment information, such as job names, job responsibilities, skill requirements, etc., are then identified. And finally, identifying the job type (such as finance, human resources, marketing and the like) of the recruitment post according to the pre-trained large language model. Based on the identified job type, the system will match the corresponding service item on the enterprise service platform. The service item library of the platform needs to be classified in advance and organized according to function types so as to be matched quickly. And recommending the matched service items to enterprise users through the platform. The recommendation mode can be a pop-up prompt, a message notification, a page recommendation module and the like.
Taking the identified post function type as a marketing post as an example, a certain enterprise registers on an enterprise service platform and fills in the enterprise name ABC technology. The system captures the following recruitment information on the recruitment website by using the enterprise name: recruitment position: a marketing manager; job duty: is responsible for market research, advertisement popularization, brand management and the like; skill requirements: has market marketing experience and is familiar with various popularization channels. The system recognizes that the post belongs to the "marketing" function type through natural language processing technology. According to the matching rules, the system recommends the following service items: market research service: helping enterprises to conduct market analysis and user research; advertisement promotion service: providing advertisement design, delivery and effect monitoring; brand management training: brand management related training courses are provided.
Taking the identified post function type financial tax post as an example, a certain enterprise registers on an enterprise service platform and fills in the enterprise name of XYZ manufacturing company. The system captures the following recruitment information on the recruitment website by using the enterprise name: recruitment position: a financial manager; job duty: responsible for financial planning, budget management, tax planning, etc.; skill requirements: accounting and financial management related backgrounds are familiar with financial statement, tax policy and the like; the system recognizes that the post belongs to the "financial" function type through natural language processing techniques. According to the matching rules, the system recommends the following service items, such as financial planning services: financial planning, budgeting, and management services are provided to help enterprises optimize funds use. Tax preparation service: the tax planning scheme is provided, legal tax saving of enterprises is facilitated, and tax risks are reduced. Accounting billing service: daily accounting and billing services are provided, and accurate and timely financial data is ensured. Financial statement analysis service: and the analysis and interpretation of the financial statement are provided, so that enterprises are helped to know the operating conditions and make scientific decisions.
In summary, according to the enterprise service matching method based on the large language model provided by the embodiment of the application, the enterprise identification information is extracted through the user registration basic information based on the enterprise service platform so as to determine the target enterprise; capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform; and carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type. Therefore, the enterprise user is not required to predict and analyze the user demands after a great amount of behavior data is generated by the service platform, and the potential demands of the user can be actively and timely mined. By capturing recruitment information of the enterprise and performing function type identification, the system can accurately know the current requirements of the enterprise, so that service items related to the enterprise are recommended. For example, an enterprise is recruiting marketers, and the system may recommend market research services, advertising services, marketing training, and the like. The system automatically captures and processes recruitment information while a user browses the platform, and ensures the instantaneity and accuracy of the recommended information. Reduces manual intervention and improves efficiency. Through accurate matching and recommending of services, enterprise users can quickly find out required services, and user experience and satisfaction are improved. Meanwhile, the automatic recommendation process also reduces the operation burden of the user. The accurate service recommendation function is a bright spot of the enterprise service platform, can attract more enterprise users, and improves the competitiveness and user viscosity of the platform.
In some examples, further comprising:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
By means of deep analysis of the post responsibility information, the system can accurately know specific requirements of enterprises, particularly identify responsibilities of a service provider management type, and accurately recommend corresponding service items. For example, if an enterprise recruits a position responsible for outsourcing management, the system recommends the corresponding outsourcing services and management tools. If it is determined from the analysis that the enterprise is an external server desiring to recruit to complete the corresponding business, the corresponding business is not screened and managed solely for recruitment. Then, it is likely that the target enterprise does not have a large service requirement on the business corresponding to the job-like post.
In some examples, further comprising:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
For example, historical recruitment information for an enterprise may be queried to analyze whether the enterprise has recruited a particular post. Whether the posts are filled is determined, and if some posts are never recruited, it may be indicated that the enterprise has outsourcing requirements for service items corresponding to the functions of the posts.
In some examples, further comprising:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
By means of deep analysis of post responsibility information and release time, the system can accurately know specific requirements of enterprises, particularly identify responsibilities of service provider management types, and accurately recommend corresponding service items. For example, if the enterprise recruits a position responsible for outsourcing management, the system recommends the corresponding outsourcing service and management tool and considers the release time of the recruitment information to ensure that the recommended service items are up-to-date and most relevant.
Illustratively, taking marketing class posts as an example, an enterprise registers on an enterprise service platform and fills in the enterprise name "ABC technology". The system captures the following recruitment information on the recruitment website by using the enterprise name: recruitment position: a marketing manager; job duty: is responsible for market research, advertisement popularization, brand management and the like; release time: 2024, 6, 1; the analysis recruitment types are: and (5) emergency recruitment. The system recognizes that the post belongs to the "marketing" function type through natural language processing technology, and further analyzes that the responsibility type is the "service provider management type" and the recruitment type is the "emergency recruitment". According to the matching rules, the system recommends the following service items: market research service: helping businesses conduct market analysis and user research, and preferentially recommending service providers that can respond quickly. Advertisement promotion service: advertisement design, delivery, and effectiveness monitoring are provided, with preference for rapidly implemented advertisement services. Brand management advisory services: and providing consultation and service related to brand management, assisting in managing external brand promotion service providers, and preferentially recommending service providers with efficient responses.
Illustratively, a financial tax type post is taken as an example, and a certain enterprise registers on an enterprise service platform and fills in the enterprise name "ABC technology". The system captures the following recruitment information on the recruitment website by using the enterprise name: recruitment position: a financial manager; job duty: responsible for financial planning, budget management, tax planning, etc.; release time: 2024, 6, 5; recruitment type: and (5) conventional recruitment. The system recognizes that the post belongs to a financial function type through a natural language processing technology, and further analyzes that the responsibility type is an autonomous service type and the recruitment type is a conventional recruitment. According to the matching rules, the system recommends the following service items: financial planning service: financial planning, budgeting, and management services are provided to help enterprises optimize funds use. Tax preparation service: the tax planning scheme is provided, legal tax saving of enterprises is facilitated, and tax risks are reduced. Accounting billing service: daily accounting and billing services are provided, and accurate and timely financial data is ensured.
Then, the forecast target enterprise ABC technology currently demands more enterprise services for market research services, advertising promotion services, and brand management consultation services than financial planning services, tax planning services, and accounting services.
In some examples, further comprising:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
Illustratively, the post responsibility information of the target enterprise is deeply analyzed by using a large language model, and a personalized service recommended call is generated according to the function type, the responsibility type, the recruitment type and the emergency degree.
In some examples, further comprising:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
Illustratively, the large language model is utilized to generate auxiliary questions for target enterprise service item matching for the target function type through the instant messaging function of the recruitment website. These issues are intended to further understand the specific needs and priorities of the enterprises. The system sends auxiliary questions to the enterprise through the instant messaging function, and collects feedback information of the enterprise on the questions. These feedback messages may include clarification of specific service requirements, acknowledgement of priorities, etc. And matching corresponding service items for the target enterprise according to the function type, the responsibility type, the recruitment type, the emergency degree and the feedback information of the enterprise on the auxiliary problems of the target enterprise. And deep analysis is carried out on the post responsibility information and the feedback information of the target enterprise by using the large language model, so that personalized service recommended speaking information is generated. And recommending the matched service items and the generated recommended telephone to the enterprise user through the platform. The recommendation mode can be a pop-up prompt, a message notification, a page recommendation module and the like. Therefore, the system can recommend the service item more accurately by generating and utilizing the auxiliary problem to further know the specific requirements of the enterprise, and ensure that the recommended service item is matched with the actual requirements of the enterprise. Personalized recommended utterances can also better convey the value of the recommended services.
In some examples, further comprising:
And optimizing the matched service items through a particle swarm optimization algorithm, and determining a target service item.
Illustratively, in the enterprise service platform, for a certain target enterprise, enterprise a, several service items need to be recommended. The goal of the recommendation is to maximize the relevance of the service items while minimizing the urgency of the enterprise's needs. Let the recommended service item set be s= { S1, S2,...
First, two objective functions are defined: service item relevance f 1, urgency of enterprise demand f 2.
Wherein, the higher the service project correlation is, the better the lower the emergency degree of the enterprise demand is. An optimal solution can be found by PSO so that both objective functions are optimized at the same time. Defining parameters Ri: the service item s i has a correlation with the enterprise A, and the value range is 0,1, and the larger the service item s i is, the higher the correlation is. U i: the degree of urgency of enterprise A for service item s i is in the range of [0,1], with smaller values indicating lower degrees of urgency. In particle swarm optimization, each particle represents one possible service item recommendation combination. Let N particles be present, the position xj= (x j1,xj2,...,xjn) of each particle, where x ji represents the selection weight of particle j for service item s i. The velocity update formula for the particles is as follows:
vji(t+1)=w⋅vji(t)+c1⋅r1⋅(pji(t)−xji(t))+c2⋅r2⋅(gi(t)−xji(t))
Wherein w is an inertial weight and represents the influence degree of the current speed of the particles; c 1 and c 2 are learning factors, and represent the learning ability of the particles to the self optimal position and the group optimal position; r 1 and r 2 are random numbers, and the value range is [0,1]; p ji (t) is the historical optimal position of particle j in the ith dimension. g i (t) is the global optimum.
The current location of the particle updates the formula as follows:
xji(t+1)=xji(t)+vji(t+1)
The fitness function f is defined to evaluate the particle's merit. In combination with the objective function in the application scenario, the fitness function may be defined as:
f(xj)=α∑n i=1Ri⋅xji−β∑n i=1Ui⋅xji
Where α and β are weighting factors used to balance the importance of service item relevance and enterprise demand urgency. The position and velocity of the particles are randomly initialized. The fitness value of each particle is calculated from the fitness function f (x j). The historical optimal position p ji (t) of the particle and the global optimal position g i (t) of the population are updated. The speed and position of each particle are updated according to the speed update formula and the position update formula. Until a termination condition is met (e.g., a maximum number of iterations is reached or the fitness value does not change 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 scheme, so that balance can be achieved between maximizing service item correlation and minimizing the emergency degree of enterprise requirements. By the method, the recommendation of the enterprise service items can be optimized by effectively utilizing the particle swarm optimization algorithm, so that the recommendation result meets the business requirements of enterprises and can timely respond to emergency requirements.
The enterprise service matching method based on the large language model in the embodiment of the application is described above, and the enterprise service matching system based on the large language model in the embodiment of the application is described below.
Referring to FIG. 2, one embodiment of an enterprise service matching system based on a large language model is described in an embodiment of the present application and may include:
a determining unit 201, configured to extract enterprise identification information based on user registration basic information of an enterprise service platform, so as to determine a target enterprise;
a capturing unit 202, configured to capture recruitment information associated with the target enterprise on a recruitment website by using enterprise identification information while the user browses the enterprise service platform;
And the matching unit 203 is configured to perform natural language processing on the recruitment information by using the large language model, and identify a role type of the target enterprise in the job position of the recruitment role class, so as to match a service item for the target enterprise based on the role type.
In summary, in the enterprise service matching system based on the large language model provided in the above embodiment, the enterprise identification information is extracted through the user registration basic information based on the enterprise service platform, so as to determine the target enterprise; capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform; and carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type. Therefore, the enterprise user is not required to predict and analyze the user demands after a great amount of behavior data is generated by the service platform, and the potential demands of the user can be actively and timely mined. By capturing recruitment information of the enterprise and performing function type identification, the system can accurately know the current requirements of the enterprise, so that service items related to the enterprise are recommended. For example, an enterprise is recruiting marketers, and the system may recommend market research services, advertising services, marketing training, and the like. The system automatically captures and processes recruitment information while a user browses the platform, and ensures the instantaneity and accuracy of the recommended information. Reduces manual intervention and improves efficiency. Through accurate matching and recommending of services, enterprise users can quickly find out required services, and user experience and satisfaction are improved. Meanwhile, the automatic recommendation process also reduces the operation burden of the user. The accurate service recommendation function is a bright spot of the enterprise service platform, can attract more enterprise users, and improves the competitiveness and user viscosity of the platform.
While fig. 2 above describes the large language model-based enterprise service matching system in the embodiment of the present application from the perspective of a modularized functional entity, the large language model-based enterprise service matching system in the embodiment of the present application is described in detail below from the perspective of hardware processing, referring to fig. 3, an embodiment of the large language model-based enterprise service matching system 300 in the embodiment of the present application includes:
Input device 301, output device 302, processor 303, and memory 304, wherein the number of processors 303 may be one or more, one processor 303 being exemplified in fig. 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 by a bus or other means, where a bus connection is illustrated in FIG. 3.
Wherein, by calling the operation instruction stored in the memory 304, the processor 303 is configured to execute the following steps:
based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise;
capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform;
And carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Optionally, the method further comprises:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
Optionally, the method further comprises:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
Optionally, the method further comprises:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
Optionally, the method further comprises:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
Optionally, the method further comprises:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
The processor 303 is further configured to execute any of the embodiments corresponding to fig. 1 by calling the operation instructions stored in the memory 304.
Referring to fig. 4, fig. 4 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the application.
As shown in fig. 4, an embodiment of the present application provides an electronic device, including a memory 410, a processor 420, and a computer program 411 stored on the memory 420 and executable on the processor 420, wherein the processor 420 implements the following steps when executing the computer program 411:
based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise;
capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform;
And carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Optionally, the method further comprises:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
Optionally, the method further comprises:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
Optionally, the method further comprises:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
Optionally, the method further comprises:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
Optionally, the method further comprises:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
In a specific implementation, when the processor 420 executes the computer program 411, any implementation of the embodiment corresponding to fig. 1 may be implemented.
Since the electronic device described in this embodiment is a device used for implementing an enterprise service matching system based on a large language model in this embodiment of the present application, based on the method described in this embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device in this embodiment and various modifications thereof, so how the electronic device implements the method in this embodiment of the present application will not be described in detail herein, and only those devices used by those skilled in the art to implement the method in this embodiment of the present application are within the scope of the present application.
Referring to fig. 5, fig. 5 is a schematic diagram of an embodiment of a computer readable storage medium according to an embodiment of the application.
As shown in fig. 5, the present embodiment provides a computer-readable storage medium 500 having stored thereon a computer program 511, which computer program 511 when executed by a processor implements the steps of:
based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise;
capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform;
And carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
Optionally, the method further comprises:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
Optionally, the method further comprises:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
Optionally, the method further comprises:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
Optionally, the method further comprises:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
Optionally, the method further comprises:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. 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, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be stored by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Drive (SSD)), etc.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of 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.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution or in part in the form of a software product stored in a storage medium, including instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims (10)
1. An enterprise service matching method based on a large language model, the method comprising:
based on user registration basic information of the enterprise service platform, extracting enterprise identification information to determine a target enterprise;
capturing recruitment information associated with the target enterprise in a recruitment website by utilizing enterprise identification information while a user browses an enterprise service platform;
And carrying out natural language processing on recruitment information by using the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match a service item for the target enterprise based on the function type.
2. The method as recited in claim 1, further comprising:
acquiring post responsibility information corresponding to different function types of the target enterprise on-duty posts;
Performing natural language processing on the post responsibility information by using a large language model, and analyzing and predicting responsibility types of the target enterprise in the post of the job class, wherein the responsibility types comprise a service provider management type and an autonomous service type;
and under the condition that the responsibility type of the first function type in the post of the job-taking class of the target enterprise is a service provider management type, matching a service item for the target enterprise based on the business content associated with the first function type.
3. The method as recited in claim 1, further comprising:
Acquiring historical recruitment information of the target enterprise;
and predicting the target enterprise service exclusion type based on the business content associated with the second function type under the condition that the second function type of the target enterprise has historical recruitment information and no recruitment information exists, so as to filter matched service items for the target enterprise.
4. The method as recited in claim 1, further comprising:
acquiring the release time of the target enterprise in the job position;
the matching service item for the target enterprise based on the role type comprises the following steps:
Matching service items for the target enterprise based on the job types and the corresponding release time at job positions; and/or the number of the groups of groups,
Natural language processing is carried out on recruitment information by utilizing a large language model, recruitment types of the target enterprises in the positions of the recruitment functions are identified, and the recruitment types are used for distinguishing the emergency degree of the position demands;
the matching service item for the target enterprise based on the role type comprises the following steps:
and matching service items for the target enterprise based on the job type and the emergency degree of the corresponding on-position requirement.
5. The method as recited in claim 1, further comprising:
And performing natural language processing on the post responsibility information of the target enterprise by using the large language model, and determining service recommended conversation information of the enterprise service platform aiming at the target enterprise.
6. The method according to any one of claims 1 to 5, further comprising:
generating an auxiliary problem of target enterprise service item matching aiming at a target function type through an instant messaging function of a recruitment website by utilizing a large language model;
And responding the feedback message of the auxiliary problem to the target enterprise, and matching a service item for the target enterprise based on the target function type and the feedback message.
7. The method according to any one of claims 1 to 5, further comprising:
And optimizing the matched service items through a particle swarm optimization algorithm, and determining a target service item.
8. An enterprise service matching system based on a large language model, the system comprising:
the determining unit is used for extracting enterprise identification information based on the user registration basic information of the enterprise service platform so as to determine a target enterprise;
The grabbing unit is used for grabbing recruitment information associated with the target enterprise on a recruitment website by utilizing the enterprise identification information while a user browses the enterprise service platform;
And the matching unit is used for carrying out natural language processing on recruitment information by utilizing the large language model, and identifying the function type of the target enterprise in the job position of the recruitment function class so as to match the service item for the target enterprise based on the function type.
9. An electronic device comprising at least one processor and at least one memory coupled to the processor, wherein the processor is configured to invoke program instructions in the memory to perform the large language model based enterprise service matching method of any of claims 1-7.
10. A storage medium comprising a stored program, wherein the program, when run, controls a device in which the storage medium resides to perform the large language model-based enterprise service matching method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411142347.XA CN118673201A (en) | 2024-08-20 | 2024-08-20 | Enterprise service matching method and system based on large language model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411142347.XA CN118673201A (en) | 2024-08-20 | 2024-08-20 | Enterprise service matching method and system based on large language model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118673201A true CN118673201A (en) | 2024-09-20 |
Family
ID=92721464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411142347.XA Pending CN118673201A (en) | 2024-08-20 | 2024-08-20 | Enterprise service matching method and system based on large language model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118673201A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993045A (en) * | 2017-10-12 | 2018-05-04 | 如是科技（大连）有限公司 | Pricing method and device are put in recruitment on someone's head |
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN116186285A (en) * | 2023-02-17 | 2023-05-30 | 广州探迹科技有限公司 | Intellectual property service recommendation method, system and medium based on enterprise knowledge graph |
| CN118194880A (en) * | 2024-03-18 | 2024-06-14 | 零犀(北京)科技有限公司 | Method and device for recommending speaking operation based on large model, storage medium and electronic equipment |
| CN118503547A (en) * | 2024-07-18 | 2024-08-16 | 北京华普亿方科技集团股份有限公司 | Artificial intelligence-based person post intelligent matching method and system |
-
2024
- 2024-08-20 CN CN202411142347.XA patent/CN118673201A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993045A (en) * | 2017-10-12 | 2018-05-04 | 如是科技（大连）有限公司 | Pricing method and device are put in recruitment on someone's head |
| CN113343091A (en) * | 2021-06-22 | 2021-09-03 | 力合科创集团有限公司 | Industrial and enterprise oriented science and technology service recommendation calculation method, medium and program |
| CN116186285A (en) * | 2023-02-17 | 2023-05-30 | 广州探迹科技有限公司 | Intellectual property service recommendation method, system and medium based on enterprise knowledge graph |
| CN118194880A (en) * | 2024-03-18 | 2024-06-14 | 零犀(北京)科技有限公司 | Method and device for recommending speaking operation based on large model, storage medium and electronic equipment |
| CN118503547A (en) * | 2024-07-18 | 2024-08-16 | 北京华普亿方科技集团股份有限公司 | Artificial intelligence-based person post intelligent matching method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220414688A1 (en) | Predictive analytics for leads generation and engagement recommendations | |
| WO2017190610A1 (en) | Target user orientation method and device, and computer storage medium | |
| CN107818344A (en) | The method and system that user behavior is classified and predicted | |
| US20110258045A1 (en) | Inventory management | |
| CN111898023A (en) | Message pushing method and device, readable storage medium and computing equipment | |
| CN104823188A (en) | Customized predictors for user actions in online system | |
| CN111930366B (en) | Rule engine implementation method and system based on JIT real-time compilation | |
| CN110310163A (en) | A kind of accurate method, equipment and readable medium for formulating marketing strategy | |
| US20230214679A1 (en) | Extracting and classifying entities from digital content items | |
| CN109978033A (en) | The method and apparatus of the building of biconditional operation people's identification model and biconditional operation people identification | |
| CN115222433A (en) | Information recommendation method and device and storage medium | |
| CN112070564B (en) | Advertisement pulling method, device and system and electronic equipment | |
| Khan et al. | Effects of time-inconsistent preferences on information technology infrastructure investments with growth options | |
| CN112819024B (en) | Model processing method, user data processing method and device and computer equipment | |
| US10394804B1 (en) | Method and system for increasing internet traffic to a question and answer customer support system | |
| US6921266B2 (en) | Training-curriculum creating system, server, method and computer program for creating a training curriculum | |
| CN114169418A (en) | Label recommendation model training method and device, and label obtaining method and device | |
| WO2021186338A1 (en) | System and method for determining solution for problem in organization | |
| US20140195462A1 (en) | Data management system and tool | |
| CN118673201A (en) | Enterprise service matching method and system based on large language model | |
| CN115168603B (en) | Automatic feedback response method, device and storage medium for color ring back tone service process | |
| CN116127189A (en) | User operation method, device, equipment and computer storage medium | |
| CN113592549A (en) | Conversion rate prediction method and device and electronic equipment | |
| CN114463085A (en) | Universal communication interaction method and device for automatic marketing, electronic equipment and storage medium | |
| CN114445043A (en) | Open ecological cloud ERP-based heterogeneous graph user demand accurate discovery method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |