Talent recommendation method and device, equipment and storage medium

Abstract

The invention discloses a talent recommendation method and device, equipment and a storage medium, and relates to the technical field of computers, and the method comprises the steps: after determining that a recruiter and a dialogue model end a dialogue, extracting a key recruitment requirement of the recruiter for a recruitment position from the interactive dialogue of the recruiter and the dialogue model, the dialogue model is obtained by training a large language model according to dialogue content in the recruitment field; updating position portraits of recruitment positions according to the key recruitment requirements; and determining a target talent corresponding to the recruitment position based on the position portrait and the job seeker information. According to the technical scheme, the position portrait of the recruitment position is updated based on the key recruitment requirement extracted from the interactive dialogue between the recruiter and the dialogue model, so that the position portrait contains more and more accurate features, accurate determination of the target talent corresponding to the recruitment position is realized by determining the job seeker information matched with the position portrait, and the recruitment effect is improved. The accuracy of talent recommendation is improved, and the recruitment experience of recruiters is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of computer technology, and in particular to a talent recommendation method, device, equipment and storage medium. Background Art

[0002] With the development of society, enterprises recruit job seekers by posting recruitment information on recruitment platforms. The recruitment information posted by the employer on the recruitment platform usually includes the requirements of the position to be recruited, and the recruitment platform can recommend talents to the employer according to the requirements.

[0003] In the prior art, a recruitment platform can determine job seekers that match the job positions based on the requirements of the job positions and the user profiles of job seekers, and recommend them to the recruiter.

[0004] However, the job information posted by recruiters cannot accurately express the recruitment needs, making it difficult to match suitable talents. Summary of the invention

[0005] The present invention provides a talent recommendation method, device, equipment and storage medium, so as to determine a more accurate recruitment demand of a recruiter according to a dialogue model, and recommend talents that better match the recruitment demand to the recruiter according to the more accurate recruitment demand.

[0006] In a first aspect, an embodiment of the present invention provides a talent recommendation method, comprising:

[0007] After determining that the recruiter and the dialogue model have finished the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field;

[0008] Update the job profile of the recruitment position according to the key recruitment requirements;

[0009] The target talent corresponding to the recruitment position is determined based on the position portrait and job seeker information.

[0010] The technical solution of an embodiment of the present invention provides a talent recommendation method, including: after determining that the recruiter has ended the conversation with the dialogue model, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field; updating the job profile of the recruitment position according to the key recruitment requirements; and determining the target talent corresponding to the recruitment position based on the job profile and job seeker information. In the above technical solution, the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field. By guiding the dialogue of the recruiter, more detailed and rich information about the recruitment position can be obtained from the recruiter. Therefore, after determining that the recruiter and the dialogue model have ended the dialogue, the interactive dialogue between the recruiter and the dialogue model contains more detailed and rich information about the recruitment position. By extracting information from the interactive dialogue between the recruiter and the dialogue model, key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the key recruitment requirements of the recruiter for the recruitment position can be determined. The original position portrait of the recruitment position determined based on the description information of the recruitment position provided by the recruiter cannot fully reflect the recruitment needs of the recruiter. Therefore, the position portrait of the recruitment position can be updated based on the key recruitment requirements, so that the position portrait can contain more features and more comprehensively display the recruitment needs of the recruiter for the recruitment position. By determining the correlation between the features contained in the position portrait and the content corresponding to each feature in the job seeker information, the job seeker information matching the position portrait is determined, and then the target talent corresponding to the recruitment position is determined, so as to achieve accurate determination of the target talent corresponding to the recruitment position, improve the accuracy of talent recommendation, and improve the recruitment experience of the recruiter.

[0011] Furthermore, the key recruitment requirements of the recruiter for the recruitment position are extracted from the interactive dialogue between the recruiter and the dialogue model, including:

[0012] The interactive dialogue is input into a pre-trained information extraction model so that the information extraction model outputs the multi-dimensional key recruitment requirements corresponding to the interactive dialogue, wherein the information extraction model is obtained by training a hybrid expert model based on the dialogue content and the multi-dimensional key recruitment requirements corresponding to the dialogue content.

[0013] Furthermore, the hybrid expert model is composed of a gated network and a plurality of expert networks, and the number of the expert networks included in the hybrid expert model is not less than the number of dimensions of the key recruitment requirements. Accordingly, the step of the information extraction model determining the multi-dimensional key recruitment requirements corresponding to the interactive dialogue includes:

[0014] The information extraction model extracts the initial recruitment requirements of each dimension of the interactive dialogue based on each of the expert networks;

[0015] After the information extraction model determines the weights of each expert network for the key recruitment requirements of each dimension based on the gating network, the multi-dimensional key recruitment requirements are determined according to the initial recruitment requirements of each dimension extracted by each expert network and the weights of each expert network for the key recruitment requirements of each dimension.

[0016] Furthermore, before updating the job profile of the recruitment position according to the key recruitment requirements, it also includes:

[0017] An original job profile of the job is determined based on the description information of the job provided by the recruiter.

[0018] Furthermore, the job profile of the recruitment position is updated according to the key recruitment requirements, including:

[0019] The key recruitment requirements and the original job profile are integrated to obtain an updated job profile.

[0020] Furthermore, after updating the job profile of the recruitment position according to the key recruitment requirements, it also includes:

[0021] determining behavioral recruitment requirements based on the user behavior data of the recruiter;

[0022] The behavioral recruitment requirements and the updated job profile are integrated to obtain an optimized job profile.

[0023] Further, determining the target talent corresponding to the recruitment position based on the position portrait and the job seeker information includes:

[0024] Determining the matching degree between the job seeker information and the optimized job profile;

[0025] The job seekers corresponding to the job seeker information are ranked based on the matching degree, and a preset number of job seekers ranked high are determined as the target talents corresponding to the recruitment position.

[0026] In a second aspect, an embodiment of the present invention further provides a talent recommendation device, comprising:

[0027] An extraction module, used to extract the key recruitment requirements of the recruiter for the recruitment position from the interactive dialogue between the recruiter and the dialogue model after determining that the dialogue between the recruiter and the dialogue model ends, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field;

[0028] An updating module, used to update the job profile of the recruitment position according to the key recruitment requirements;

[0029] A determination module is used to determine the target talent corresponding to the recruitment position based on the position portrait and job seeker information.

[0030] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0031] at least one processor; and a memory communicatively coupled to the at least one processor;

[0032] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the talent recommendation method as described in any one of the first aspects.

[0033] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute the talent recommendation method as described in any one of the first aspects.

[0034] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the talent recommendation method provided in the first aspect.

[0035] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the talent recommendation device, or may be packaged separately from the processor of the talent recommendation device, which is not limited in this application.

[0036] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0037] In this application, the name of the talent recommendation device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0038] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flow chart of a talent recommendation method provided by an embodiment of the present invention;

[0041] Figure 2 A flowchart of another talent recommendation method provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the structure of a talent recommendation device provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0045] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0046] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0047] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application 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 limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0048] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0049] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0050] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0051] Figure 1 This is a flow chart of a talent recommendation method provided by an embodiment of the present invention. This embodiment is applicable to the situation where it is necessary to provide a recruiter with talents that are more suitable for the recruitment position. The method can be executed by a talent recommendation device, such as Figure 1 As shown, the specific steps include:

[0052] Step 110: After determining that the recruiter and the dialogue model have finished the dialogue, extract the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model.

[0053] The dialogue model is obtained by training a large language model based on dialogue content in the recruitment field.

[0054] Specifically, the dialogue model obtained by training the large language model with dialogue content in the recruitment field can guide recruiters to provide more detailed and rich recruitment content. After the user terminal corresponding to the recruiter receives the initial recruitment content input by the recruiter, it sends the initial recruitment content to the recruitment platform. The recruitment platform can determine the reply statement corresponding to the initial recruitment content based on the dialogue model, and send the reply statement to the user terminal. The reply statement can be used to guide the recruiter to provide more detailed and rich information about the recruitment position. For example, it can guide the recruiter to provide residence requirements, industry background requirements and position direction for the recruitment position.

[0055] After receiving the confirmation message of the end of the conversation sent by the user terminal, it can be determined that the recruiter and the conversation model have ended the conversation. At this time, the recruiter's key recruitment requirements for the recruitment position can be extracted from the interactive conversation between the recruiter and the conversation model. Specifically, information extraction can be performed on the interactive conversation between the recruiter and the conversation model. For example, information extraction can be performed on the interactive conversation between the recruiter and the conversation model based on a large model with information extraction capabilities, that is, the interactive conversation between the recruiter and the conversation model can be input into the large model with information extraction capabilities, so that the large model with information extraction capabilities can extract information from the interactive conversation between the recruiter and the conversation model to determine the key recruitment requirements corresponding to the interactive conversation between the recruiter and the conversation model.

[0056] In an embodiment of the present invention, the dialogue model is obtained by training a large language model based on dialogue content in the recruitment field. By guiding the recruiter's dialogue, the recruiter can obtain more detailed and rich information about the recruitment position. That is, the interactive dialogue of the dialogue model contains more detailed and rich information about the recruitment position by the recruiter. By extracting information from the interactive dialogue between the recruiter and the dialogue model through a large model with information extraction capability, key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the key recruitment requirements of the recruiter for the recruitment position can be determined.

[0057] Step 120: Update the job profile of the recruitment position according to the key recruitment requirements.

[0058] The original job profile of a job position is determined based on the job description information provided by the recruiter. Since the job description information provided by the recruiter is not very accurate, the original job profile of the job position determined based on the job description information provided by the recruiter cannot fully reflect the recruiter's recruitment needs. Therefore, the original job profile of the job position needs to be updated.

[0059] Specifically, the interactive dialogue between the recruiter and the dialogue model contains more detailed and rich information about the recruitment position. The key recruitment requirements of the recruiter for the recruitment position determined by extracting information from the interactive dialogue between the recruiter and the dialogue model through a large model with information extraction capabilities can reflect the recruiter's more precise needs. Therefore, the job profile of the recruitment position can be updated based on the key recruitment requirements. Specifically, the job profile of the recruitment position can be updated by integrating the key recruitment requirements and the original job profile.

[0060] In the embodiment of the present invention, the job profile of the recruitment position is updated through key recruitment requirements, so that the job profile can include more features and more comprehensively display the recruitment needs of the recruiter for the recruitment position.

[0061] Step 130: Determine the target talent corresponding to the recruitment position based on the position portrait and job seeker information.

[0062] Specifically, job seekers can be screened based on the characteristics contained in the job profile and the job seeker information of each job seeker, and the job seekers corresponding to the job seeker information that meet a preset number of characteristics can be determined as target talents corresponding to the recruitment position. The job profile contains multiple characteristics, so for each job seeker information, the content corresponding to each characteristic can be determined in the job seeker information, and the correlation between each characteristic and the content corresponding to each characteristic in the job seeker information can be determined. If the correlation between the characteristics of a preset ratio and the content corresponding to the characteristics in the job seeker information is greater than a preset threshold, the job seeker corresponding to the job seeker information is determined to be the target talent corresponding to the recruitment position.

[0063] The specific values ​​of the preset ratio and the preset threshold can be set according to actual needs and are not specifically limited here.

[0064] In an embodiment of the present invention, by determining the correlation between the features included in the job profile and the content corresponding to each feature in the job applicant information, it is possible to determine the job applicant information that matches the job profile, and then determine the target talent corresponding to the recruitment position, thereby achieving accurate determination of the target talent corresponding to the recruitment position, improving the accuracy of talent recommendation, and enhancing the recruitment experience of the recruiter.

[0065] The talent recommendation method provided by an embodiment of the present invention includes: after determining that the recruiter and the dialogue model have ended the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field; updating the job profile of the recruitment position according to the key recruitment requirements; and determining the target talent corresponding to the recruitment position based on the job profile and job seeker information. In the above technical solution, the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field. By guiding the dialogue of the recruiter, more detailed and rich information about the recruitment position can be obtained from the recruiter. Therefore, after determining that the recruiter and the dialogue model have ended the dialogue, the interactive dialogue between the recruiter and the dialogue model contains more detailed and rich information about the recruitment position. By extracting information from the interactive dialogue between the recruiter and the dialogue model, key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the key recruitment requirements of the recruiter for the recruitment position can be determined. The original position portrait of the recruitment position determined based on the description information of the recruitment position provided by the recruiter cannot fully reflect the recruitment needs of the recruiter. Therefore, the position portrait of the recruitment position can be updated based on the key recruitment requirements, so that the position portrait can contain more features and more comprehensively display the recruitment needs of the recruiter for the recruitment position. By determining the correlation between the features contained in the position portrait and the content corresponding to each feature in the job seeker information, the job seeker information matching the position portrait is determined, and then the target talent corresponding to the recruitment position is determined, so as to achieve accurate determination of the target talent corresponding to the recruitment position, improve the accuracy of talent recommendation, and improve the recruitment experience of the recruiter.

[0066] Figure 2 This is a flow chart of another talent recommendation method provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:

[0067] Step 210: After determining that the recruiter and the dialogue model have finished the dialogue, extract the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model.

[0068] The dialogue model is obtained by training a large language model based on dialogue content in the recruitment field.

[0069] In one implementation, extracting the key recruitment requirements of the recruiter for the recruitment position from the interactive dialogue between the recruiter and the dialogue model includes:

[0070] The interactive dialogue is input into a pre-trained information extraction model so that the information extraction model outputs the multi-dimensional key recruitment requirements corresponding to the interactive dialogue, wherein the information extraction model is obtained by training a hybrid expert model based on the dialogue content and the multi-dimensional key recruitment requirements corresponding to the dialogue content.

[0071] The information extraction model obtained by training the hybrid expert model based on the conversation content and the multi-dimensional key recruitment requirements corresponding to the conversation content can determine the multi-dimensional key recruitment requirements corresponding to the conversation content. In practical applications, for each dimension of key recruitment requirements, a data set can be prepared and annotated separately. The data set can include the conversation content and the key recruitment requirements corresponding to the conversation content. The data set corresponding to the key recruitment requirements of each dimension is used as a training set to train the hybrid expert model, and an information extraction model that can determine the multi-dimensional key recruitment requirements corresponding to the conversation content can be obtained.

[0072] Specifically, the user conducts a dialogue with the dialogue model based on the user terminal, and the dialogue model can guide the recruiter to provide more detailed and rich recruitment content. After determining that the dialogue end confirmation information sent by the user terminal is received, it can be determined that the recruiter and the dialogue model have ended the dialogue. At this time, the recruiter's key recruitment requirements for the recruitment position can be extracted from the interactive dialogue between the recruiter and the dialogue model. Specifically, information extraction can be performed on the interactive dialogue between the recruiter and the dialogue model based on a large model with information extraction capabilities. In order to obtain multi-dimensional multi-dimensional key recruitment requirements, multi-dimensional information extraction can be performed on the interactive dialogue between the recruiter and the dialogue model based on an information extraction model with multi-dimensional information extraction capabilities. Therefore, the interactive dialogue between the recruiter and the dialogue model can be input into the information extraction model, so that the information extraction model determines the multi-dimensional key recruitment requirements corresponding to the interactive dialogue between the recruiter and the dialogue model by performing multi-dimensional information extraction on the interactive dialogue between the recruiter and the dialogue model.

[0073] Furthermore, the hybrid expert model is composed of a gated network and a plurality of expert networks, and the number of the expert networks included in the hybrid expert model is not less than the number of dimensions of the key recruitment requirements. Accordingly, the step of the information extraction model determining the multi-dimensional key recruitment requirements corresponding to the interactive dialogue includes:

[0074] The information extraction model extracts the initial recruitment requirements for each dimension of the interactive dialogue based on each expert network; after the information extraction model determines the weight of each expert network for the key recruitment requirements for each dimension based on the gating network, the multi-dimensional key recruitment requirements are determined according to the initial recruitment requirements for each dimension extracted by each expert network and the weight of each expert network for the key recruitment requirements for each dimension.

[0075] The hybrid expert model of the trained information extraction model is composed of a gating network and multiple expert networks. The number of expert networks included in the hybrid expert model is not less than the number of dimensions of the key recruitment requirements. Each expert network is used to extract information from interactive dialogues based on each dimension, and the gating network is used to determine the weight of each expert network for the key recruitment requirements of each dimension.

[0076] Specifically, the information extraction model can first extract the initial recruitment requirements for each dimension of the interactive dialogue based on each expert network, and secondly, determine the weight of each expert network in determining the key recruitment requirements for each dimension based on the gating network. Then, the multi-dimensional key recruitment requirements can be determined based on the initial recruitment requirements for each dimension extracted by each expert network and the weight of each expert network in determining the key recruitment requirements for each dimension.

[0077] For example, for the key recruitment requirements of any dimension, the information extraction model can first extract the initial recruitment requirements of the interactive dialogue in this dimension based on each expert network, and then determine the weight of each expert network in determining the key recruitment requirements of this dimension based on the gating network. Finally, the key recruitment requirements of this dimension are determined based on the initial recruitment requirements of this dimension extracted by each expert network and the weight of each expert network in determining the key recruitment requirements of this dimension.

[0078] In the embodiment of the present invention, multi-dimensional information extraction is performed on the interactive dialogue between the recruiter and the dialogue model through the information extraction model, so that multi-dimensional key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the multi-dimensional key recruitment requirements of the recruiter for the recruitment position can be determined.

[0079] Step 220: Determine the original job profile of the job according to the description information of the job provided by the recruiter.

[0080] Specifically, the original job profile of the recruitment position is determined based on the descriptive information of the recruitment position provided by the recruiter. Specifically, the original job profile of the recruitment position can be determined by determining the feature values ​​corresponding to preset feature attributes in the descriptive information of the recruitment position provided by the recruiter, or by inputting the descriptive information of the recruitment position provided by the recruiter into a pre-trained multidimensional information extraction model so that the multidimensional information extraction model determines the multidimensional key information corresponding to the descriptive information of the recruitment position provided by the recruiter, and the original job profile of the recruitment position is determined based on the multidimensional key information.

[0081] In the embodiment of the present invention, the original job profile of the recruitment position is determined according to the description information of the recruitment position by the recruiter.

[0082] Step 230: The key recruitment requirements and the original job profile are integrated to obtain an updated job profile.

[0083] Specifically, the job profile of the recruitment position is updated by fusing the multi-dimensional key recruitment requirements and the original job profile to obtain an updated job profile. For example, if the original job profile contains the corresponding content of the key recruitment requirements of the current dimension, the corresponding content of the key recruitment requirements of the current dimension in the original job profile can be updated. If the original job profile does not contain the corresponding content of the key recruitment requirements of the current dimension, the key recruitment requirements of the current dimension can be added to the original job profile. By updating or adding the original job profile with the multi-dimensional key recruitment requirements, an updated job profile can be obtained.

[0084] In the embodiment of the present invention, the job profile of the recruitment position is updated through key recruitment requirements, so that the job profile can contain more and more accurate features, and more comprehensively and accurately display the recruitment needs of the recruiter for the recruitment position.

[0085] Step 240: determine behavioral recruitment requirements based on the user behavior data of the recruiter; integrate the behavioral recruitment requirements and the updated job profile to obtain an optimized job profile.

[0086] Among them, the user behavior data of the recruiter can be understood as the user behavior data of the recruiter based on the recruitment platform, which may include click data on resumes of various types of talents, such as click frequency, click time, and dwell time.

[0087] Specifically, the user behavior data of the recruiter in the historical time period is obtained, and the behavioral recruitment requirements are determined by analyzing the user behavior data. For example, the talent characteristics corresponding to the resumes of the top N categories in click frequency, the top M categories in click time, and the top Q categories in stay time can be determined as the behavioral recruitment requirements of the recruiter, where N, M, and Q are all natural numbers. The specific values ​​are not limited here and can be set according to actual needs.

[0088] In order to further improve the accuracy of the job profile, the optimized job profile can be obtained by integrating the behavioral recruitment requirements and the updated job profile. As mentioned above, if the updated job profile has content corresponding to the current behavioral recruitment requirements, the content corresponding to the current behavioral recruitment requirements in the updated job profile can be updated. If the content corresponding to the current behavioral recruitment requirements does not exist in the updated job profile, the content corresponding to the current behavioral recruitment requirements can be added to the updated job profile. By updating or adding the updated job profile through behavioral recruitment requirements, a more accurate job profile can be obtained.

[0089] In the embodiment of the present invention, the job portrait is further updated through behavioral recruitment requirements, so that the job portrait can be more in line with the user behavior of the recruiter and more comprehensively display the recruitment needs of the recruiter for the recruitment position.

[0090] Step 250: Determine the target talent corresponding to the recruitment position based on the position portrait and job seeker information.

[0091] In one implementation, step 250 may specifically include:

[0092] Determine the matching degree between the job seeker information and the optimized job profile; sort the job seekers corresponding to the job seeker information based on the matching degree, and determine a preset number of job seekers with high rankings as the target talents corresponding to the recruitment position.

[0093] Specifically, first, the similarity between each job seeker information and the optimized job profile can be determined, and the similarity can be determined as the matching degree between each job seeker information and the optimized job profile. Secondly, the job seekers corresponding to each job seeker information can be sorted based on the matching degree. Specifically, the job seekers corresponding to each job seeker information can be sorted in order from large to small matching degree, and then a preset number of job seekers with high rankings can be determined as target talents corresponding to the recruitment position, thereby realizing the determination of target talents corresponding to the recruitment position based on the optimized job profile.

[0094] In an embodiment of the present invention, by determining the matching degree between job seeker information and optimized job profile, the job seeker information matching the job profile is determined, and then the target talent corresponding to the recruitment position is determined, the target talent corresponding to the recruitment position is accurately determined, the accuracy of talent recommendation is improved, and the recruitment experience of the recruiter is improved.

[0095] The talent recommendation method provided by an embodiment of the present invention includes: after determining that the recruiter and the dialogue model have ended the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model; determining the original position portrait of the recruitment position based on the recruiter's description information of the recruitment position; fusing the key recruitment requirements and the original position portrait to obtain an updated position portrait; determining behavioral recruitment requirements based on the recruiter's user behavior data; fusing the behavioral recruitment requirements and the updated position portrait to obtain an optimized position portrait; and determining the target talent corresponding to the recruitment position based on the position portrait and job seeker information. In the above technical solution, the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field. By guiding the recruiter to have a dialogue, the recruiter can obtain more detailed and rich information about the recruitment position. Therefore, after determining that the recruiter has ended the dialogue with the dialogue model, the interactive dialogue between the recruiter and the dialogue model contains more detailed and rich information about the recruitment position. The interactive dialogue between the recruiter and the dialogue model is extracted in multiple dimensions through the information extraction model. Multidimensional key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the multidimensional key recruitment requirements of the recruiter for the recruitment position can be determined, and the original position of the recruitment position can be determined based on the description information of the recruitment position provided by the recruiter. The portrait cannot fully reflect the recruitment needs of the employer. Therefore, the job portrait of the recruitment position can be updated based on the key recruitment requirements, so that the job portrait can contain more and more precise features. The updated job portrait can be further updated based on the behavioral recruitment requirements determined by the employer's user behavior data, so that the job portrait can be more in line with the employer's user behavior and more comprehensively display the employer's recruitment needs for the recruitment position. By determining the matching degree between the job seeker information and the optimized job portrait, the job seeker information matching the job portrait can be determined, and then the target talent corresponding to the recruitment position can be determined. The target talent corresponding to the recruitment position can be accurately determined, the accuracy of talent recommendation can be improved, and the recruitment experience of the employer can be improved.

[0096] In addition, it is convenient for recruiters to send job demand notifications to target talents corresponding to recruitment positions, so as to provide job seekers with recruitment positions that are more suitable for them, and further enhance the job search experience of job seekers.

[0097] Figure 3 This is a schematic diagram of the structure of a talent recommendation device provided by an embodiment of the present invention, which can be applied to situations where it is necessary to provide a recruiter with talents that are more suitable for the recruitment position. The device can be implemented by software and / or hardware and is generally integrated in an electronic device, such as a computer device.

[0098] like Figure 3 As shown, the device comprises:

[0099] An extraction module 310 is used to extract the key recruitment requirements of the recruiter for the recruitment position from the interactive dialogue between the recruiter and the dialogue model after determining that the recruiter and the dialogue model have finished the dialogue, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field;

[0100] An updating module 320, configured to update the job profile of the recruitment position according to the key recruitment requirements;

[0101] The determination module 330 is used to determine the target talent corresponding to the recruitment position based on the position portrait and job seeker information.

[0102] The talent recommendation device provided in this embodiment determines that after the recruiter and the dialogue model have finished the dialogue, the recruiter's key recruitment requirements for the recruitment position are extracted from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field; the job profile of the recruitment position is updated according to the key recruitment requirements; and the target talent corresponding to the recruitment position is determined based on the job profile and job seeker information. In the above technical solution, the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field. By guiding the dialogue of the recruiter, more detailed and rich information about the recruitment position can be obtained from the recruiter. Therefore, after determining that the recruiter and the dialogue model have ended the dialogue, the interactive dialogue between the recruiter and the dialogue model contains more detailed and rich information about the recruitment position. By extracting information from the interactive dialogue between the recruiter and the dialogue model, key information in the interactive dialogue between the recruiter and the dialogue model can be extracted, that is, the key recruitment requirements of the recruiter for the recruitment position can be determined. The original position portrait of the recruitment position determined based on the description information of the recruitment position provided by the recruiter cannot fully reflect the recruitment needs of the recruiter. Therefore, the position portrait of the recruitment position can be updated based on the key recruitment requirements, so that the position portrait can contain more features and more comprehensively display the recruitment needs of the recruiter for the recruitment position. By determining the correlation between the features contained in the position portrait and the content corresponding to each feature in the job seeker information, the job seeker information matching the position portrait is determined, and then the target talent corresponding to the recruitment position is determined, so as to achieve accurate determination of the target talent corresponding to the recruitment position, improve the accuracy of talent recommendation, and improve the recruitment experience of the recruiter.

[0103] Based on the above embodiment, the extraction module 310 is specifically used for:

[0104] After determining that the recruiter has ended the conversation with the dialogue model, the interactive dialogue is input into a pre-trained information extraction model so that the information extraction model outputs the multi-dimensional key recruitment requirements corresponding to the interactive dialogue, wherein the information extraction model is obtained by training a hybrid expert model based on the dialogue content and the multi-dimensional key recruitment requirements corresponding to the dialogue content.

[0105] In one implementation, the hybrid expert model is composed of a gated network and a plurality of expert networks, and the number of the expert networks included in the hybrid expert model is not less than the number of dimensions of the key recruitment requirements. Accordingly, the step of the information extraction model determining the multi-dimensional key recruitment requirements corresponding to the interactive dialogue includes:

[0106] The information extraction model extracts the initial recruitment requirements for each dimension of the interactive dialogue based on each expert network; after the information extraction model determines the weight of each expert network for the key recruitment requirements for each dimension based on the gating network, the multi-dimensional key recruitment requirements are determined according to the initial recruitment requirements for each dimension extracted by each expert network and the weight of each expert network for the key recruitment requirements for each dimension.

[0107] Based on the above embodiment, the device further includes:

[0108] The portrait determination module is used to determine the original job portrait of the recruitment position based on the description information of the recruitment position by the recruiter before updating the job portrait of the recruitment position according to the key recruitment requirements.

[0109] Based on the above embodiment, the update module 320 is specifically used for:

[0110] The key recruitment requirements and the original job profile are integrated to obtain an updated job profile.

[0111] Based on the above embodiment, the device further includes:

[0112] The optimization module is used to determine the behavioral recruitment requirements based on the user behavior data of the recruiter after updating the job profile of the recruitment position according to the key recruitment requirements; and to integrate the behavioral recruitment requirements and the updated job profile to obtain an optimized job profile.

[0113] Based on the above embodiment, the determination module 330 is specifically used for:

[0114] Determine the matching degree between the job seeker information and the optimized job profile; sort the job seekers corresponding to the job seeker information based on the matching degree, and determine a preset number of job seekers with high rankings as the target talents corresponding to the recruitment position.

[0115] The talent recommendation device provided in the embodiment of the present invention can execute the talent recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the talent recommendation method.

[0116] It is worth noting that in the embodiment of the above-mentioned talent recommendation device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0117] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4 A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0118] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0119] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0120] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0121] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0122] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0123] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0124] The processing unit 16 executes various functional applications and page displays by running the programs stored in the system memory 28, for example, implementing the talent recommendation method provided in the embodiment of the present invention, which includes:

[0125] After determining that the recruiter and the dialogue model have finished the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field;

[0126] Update the job profile of the recruitment position according to the key recruitment requirements;

[0127] The target talent corresponding to the recruitment position is determined based on the position portrait and job seeker information.

[0128] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the talent recommendation method provided by any embodiment of the present invention.

[0129] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a talent recommendation method provided by an embodiment of the present invention is implemented, for example, and the method includes:

[0130] After determining that the recruiter and the dialogue model have finished the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field;

[0131] Update the job profile of the recruitment position according to the key recruitment requirements;

[0132] The target talent corresponding to the recruitment position is determined based on the position portrait and job seeker information.

[0133] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0134] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0135] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0136] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0137] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0138] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0139] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A talent recommendation method, characterized in that: include: After determining that the recruiter and the dialogue model have finished the dialogue, extracting the recruiter's key recruitment requirements for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field; Update the job profile of the recruitment position according to the key recruitment requirements; The target talent corresponding to the recruitment position is determined based on the position portrait and job seeker information.

2. The talent recommendation method according to claim 1, characterized in that: Extract the key recruitment requirements of the recruiter for the recruitment position from the interactive dialogue between the recruiter and the dialogue model, including: The interactive dialogue is input into a pre-trained information extraction model so that the information extraction model outputs the multi-dimensional key recruitment requirements corresponding to the interactive dialogue, wherein the information extraction model is obtained by training a hybrid expert model based on the dialogue content and the multi-dimensional key recruitment requirements corresponding to the dialogue content.

3. The talent recommendation method according to claim 2, characterized in that: The hybrid expert model is composed of a gated network and a plurality of expert networks. The number of the expert networks included in the hybrid expert model is not less than the number of dimensions of the key recruitment requirements. Accordingly, the step of the information extraction model determining the multi-dimensional key recruitment requirements corresponding to the interactive dialogue includes: The information extraction model extracts the initial recruitment requirements of each dimension of the interactive dialogue based on each of the expert networks; After the information extraction model determines the weights of each expert network for the key recruitment requirements of each dimension based on the gating network, the multi-dimensional key recruitment requirements are determined according to the initial recruitment requirements of each dimension extracted by each expert network and the weights of each expert network for the key recruitment requirements of each dimension.

4. The talent recommendation method according to claim 1, characterized in that: Before updating the job profile for the job opening based on the key hiring requirements, also include: An original job profile of the job is determined based on the description information of the job provided by the recruiter.

5. The talent recommendation method according to claim 4, characterized in that: Update the job profile for the job opening based on the key recruitment requirements, including: The key recruitment requirements and the original job profile are integrated to obtain an updated job profile.

6. The talent recommendation method according to claim 5, characterized in that: After updating the job profile of the job opening according to the key recruitment requirements, it also includes: determining behavioral recruitment requirements based on the user behavior data of the recruiter; The behavioral recruitment requirements and the updated job profile are integrated to obtain an optimized job profile.

7. The talent recommendation method according to claim 6, characterized in that: Determining target talents corresponding to the recruitment position based on the position profile and job seeker information includes: Determining the matching degree between the job seeker information and the optimized job profile; The job seekers corresponding to the job seeker information are ranked based on the matching degree, and a preset number of job seekers ranked high are determined as the target talents corresponding to the recruitment position.

8. A talent recommendation device, characterized in that: include: An extraction module is used to extract the key recruitment requirements of the recruiter for the recruitment position from the interactive dialogue between the recruiter and the dialogue model after determining that the recruiter and the dialogue model have finished the dialogue, wherein the dialogue model is obtained by training a large language model based on the dialogue content in the recruitment field; An updating module, used to update the job profile of the recruitment position according to the key recruitment requirements; A determination module is used to determine the target talent corresponding to the recruitment position based on the position portrait and job seeker information.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the talent recommendation method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to execute the talent recommendation method as described in any one of claims 1 to 7 when executed by a computer processor.

Images