Resume delivery result sending method, device and equipment and computer readable medium

By using pre-trained language models to generate job demand information and demand matching relationship information, the problem of missing high-quality positions and inaccurate results of the interviewees under massive recruitment unit information is solved, and the accuracy of job matching and result communication is achieved.

CN119005927APending Publication Date: 2024-11-22BEIJING CAIDODUI INFORMATION TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202411140834.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Faced with the massive amount of job recruitment information, the interviewee may miss a better job recruitment unit, and the interview results are not accurate enough, which makes it difficult for the interviewee to understand the results.

Method used

The first pre-trained language model is used to generate the recruiting unit information set corresponding to the job demand information, and the second largest language model is used to generate the demand matching relationship information between the delivery resume and the demand information of the recruiting unit, and the job is carried out through the demand matching relationship information. Filter and result link package send.

Benefits of technology

It achieves accurate matching of job recruitment units and clear communication of interview results, ensuring that the interviewees find positions that meet their own needs and understand the reasons for the interview results.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005927A_ABST
    Figure CN119005927A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a resume delivery result sending method and device, equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: in response to received object post demand information, generating a post recruitment unit information set; in response to the received resume delivery information, for each post recruitment unit information, executing a sending step: generating demand matching relationship information by using a second large language model; sending the demand matching relationship information and the delivery resume to at least one associated terminal; in response to the received at least one reply result, linking and packaging the at least one reply result, the at least one piece of unit demand information and the at least one piece of demand matching relationship information; and sending the resume delivery link to the use terminal. According to the embodiment, the corresponding post recruitment unit can be accurately and efficiently matched for the target interview object, and the reply result and the relevant information of the post recruitment unit can be effectively sent to the target interview object.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a resume delivery result sending method, apparatus, device, and computer-readable medium. Background Art

[0002] Currently, submitting a resume can help interviewees find their ideal job. The methods of submitting resumes include but are not limited to: submitting paper resumes, submitting resumes via email, and uploading and submitting electronic resumes. For the submission of resumes, the usual method is: first, the interviewee selects the corresponding job recruitment unit information in the target resume application and submits the resume. Then, the interviewee receives the interview result issued by the job recruitment unit.

[0003] However, when the above method is adopted, the following technical problems often occur:

[0004] Faced with a vast amount of information on job recruiting units, interviewees may miss out on better job recruiting units that better meet their job requirements, and they may have doubts about the interview results issued by the job recruiting units, making it impossible for interviewees to understand more clearly the reasons for issuing the interview results.

[0005] In the process of using technical solutions to determine demand matching relationship information, it is critical to accurately generate demand matching relationship information based on the at least one resume keyword content vector and the at least one recruiting unit keyword content vector. Regarding the determination of demand matching relationship information, the following technical problems often exist:

[0006] The determined demand matching relationship information is not accurate enough, resulting in erroneous recruitment events in subsequent job recruitment units.

[0007] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0008] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0009] Some embodiments of the present disclosure propose methods, devices, electronic devices and computer-readable media for sending resume delivery results to solve one or more of the technical problems mentioned in the above background technology section.

[0010] In a first aspect, some embodiments of the present disclosure provide a method for sending resume delivery results, comprising: in response to receiving target job requirement information input by a target interviewee in a target recruitment interface, using a pre-trained first language model to generate a job recruitment unit information set corresponding to the target job requirement information; in response to receiving resume delivery information initiated by the target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the at least one job recruitment unit information, performing the following sending steps: using a pre-trained second language model to generate demand matching relationship information between the delivered resume corresponding to the target interviewee and the unit requirement information corresponding to the job recruitment unit information, wherein In the embodiment, the at least one information about a job recruitment unit is a subset of the information set about the job recruitment unit; the demand matching relationship information and the submitted resume are sent to at least one associated terminal corresponding to the at least one information about the job recruitment unit; in response to receiving at least one reply result for the at least one information about the job recruitment unit, the at least one reply result, the at least one unit demand information and the obtained at least one demand matching relationship information are linked and packaged to generate a resume submission link, wherein the link content corresponding to the resume submission link includes: a job recruitment unit jump link that supports jumping to a communication interface corresponding to the job recruitment unit information; the resume submission link is sent to the user terminal corresponding to the target interviewee

[0011] In a second aspect, some embodiments of the present disclosure provide a resume delivery result sending device, including: a generation unit, configured to generate a job recruitment unit information set corresponding to the above-mentioned target job requirement information input by the target interviewee in the target recruitment interface using a pre-trained first language model in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface; an execution unit, configured to execute the following sending steps for each job recruitment unit information in the at least one job recruitment unit information in response to receiving the resume delivery information initiated by the target interviewee for at least one job recruitment unit information: using a pre-trained second language model, generating demand matching relationship information between the delivered resume corresponding to the target interviewee and the unit requirement information corresponding to the above-mentioned job recruitment unit information, wherein The at least one job recruitment unit information is a subset of the above job recruitment unit information set; the above demand matching relationship information and the above submitted resume are sent to at least one associated terminal corresponding to the at least one job recruitment unit information; a link packaging unit is configured to respond to receiving at least one reply result for the at least one job recruitment unit information, link and package the at least one reply result, at least one unit demand information and the obtained at least one demand matching relationship information to generate a resume submission link, wherein the link content corresponding to the above resume submission link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information; a sending unit is configured to send the resume submission link to the user terminal corresponding to the above target interviewee.

[0012] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0013] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the resume delivery result sending method of some embodiments of the present disclosure, not only can the corresponding job recruitment unit be matched for the target interviewee accurately and efficiently, but also the reply result and the relevant information of the job recruitment unit can be effectively sent to the target interviewee. Specifically, the reason why the relevant job recruitment unit is not accurate enough and the corresponding reason for the interview result is not clear enough is that in the face of a large amount of job recruitment unit information, the interviewee may miss a job recruitment unit with better quality and more in line with the job requirements of the interviewee, and the interviewee may have doubts about the interview result issued by the job recruitment unit, and the interviewee cannot understand the reason for the issuance of the interview result more clearly. Based on this, the resume delivery result sending method of some embodiments of the present disclosure, first, in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface, uses the pre-trained first language model to generate the job recruitment unit information set corresponding to the above-mentioned target job requirement information. Here, using the first language model, it is possible to accurately and efficiently match the appropriate job recruitment unit information according to the target job requirements, avoiding the situation that the interviewee may miss a job recruitment unit with better quality and more in line with the job requirements of the interviewee in the face of a large amount of job recruitment unit information. Then, in response to receiving the resume submission information initiated by the above-mentioned target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the above-mentioned at least one job recruitment unit information, the following sending steps are performed: the first step is to use the pre-trained second largest language model to accurately and efficiently generate the demand matching relationship information between the submitted resume corresponding to the above-mentioned target interviewee and the unit demand information corresponding to the above-mentioned job recruitment unit information. Among them, the above-mentioned at least one job recruitment unit information is a subset of the above-mentioned job recruitment unit information set. Here, through the demand matching relationship information, the job recruitment unit can explicitly consider the degree of match between the interviewee and the job recruitment unit, which helps the job recruitment unit to achieve more accurate object screening. The second step is to send the above-mentioned demand matching relationship information and the above-mentioned submitted resume to at least one associated terminal corresponding to the above-mentioned at least one job recruitment unit information, so as to facilitate the at least one job recruitment unit information to effectively screen the interviewees. Next, in response to receiving at least one reply result for the at least one job recruitment unit information, the at least one reply result, at least one unit requirement information and at least one requirement matching relationship information obtained are linked and packaged to generate a resume delivery link, so that the target interviewee can understand the resume delivery result and the interviewee can more clearly understand the reason for issuing the interview result. Among them, the link content corresponding to the resume delivery link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information. Finally, the resume delivery link is sent to the user terminal corresponding to the target interviewee.In summary, by using the first language model and the second language model, not only can more job recruitment unit information be considered for the target interviewee to screen out high-quality job recruitment unit information, but also the demand matching degree between the job recruitment unit and the interviewee can be accurately generated, ensuring that the interviewee finds the job recruitment unit that suits him / her, and the job recruitment unit finds the person who meets his / her own job recruitment needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0016] Figure 1 It is a flowchart of some embodiments of the resume delivery result sending method according to the present disclosure;

[0017] Figure 2 It is a structural schematic diagram of some embodiments of the resume delivery result sending device according to the present disclosure;

[0018] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0021] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0022] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0023] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0024] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0025] refer to Figure 1 , shows a process 100 of some embodiments of the resume delivery result sending method according to the present disclosure. The resume delivery result sending method includes the following steps:

[0026] Step 101, in response to receiving target job requirement information input by a target interviewee in a target recruitment interface, using a pre-trained first language model, generate a job recruitment unit information set corresponding to the target job requirement information.

[0027] In some embodiments, in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface, the execution subject (e.g., electronic device) of the resume delivery result sending method can use the pre-trained first language model to generate a job recruitment unit information set corresponding to the target job requirement information. Among them, the target interviewee can be a subject to be interviewed. The target recruitment interface can be the main interface in the recruitment application. The recruitment application can be an application platform that supports the target interviewee to find a recruitment unit. The target job requirement information can be the unit requirement information of the target interviewee for the job recruitment unit being sought. For example, the target job requirement information can be "required to have two days off a week, require five insurances and one housing fund, require a salary not less than 1**0, and require the job recruitment unit to be in ** area". The first language model can be a neural network model related to natural language processing. The first language model can be a neural network model that generates a job recruitment unit information set that meets the requirements of the target interviewee. In practice, the first language model can be a large language model (LLM, Large Language Model). The job recruitment unit information in the job recruitment unit information set is the unit information of the job recruitment unit that meets the job requirements of the target interviewee. In practice, the job recruiting unit information may be the unit identifier corresponding to the job recruiting unit.

[0028] In some optional implementations of some embodiments, the above-mentioned use of the pre-trained first language model to generate the job recruitment unit information set corresponding to the above-mentioned object job requirement information may include the following steps:

[0029] In the first step, the above-mentioned object job requirement information is input into the above-mentioned first language model to generate a job requirement keyword set. Among them, the job requirement keywords can be work-related keywords that the target interview object is looking for a job. For example, the job requirement keyword set may include: "five insurances and one housing fund", "two days off a week", "salary 1**0", "** area".

[0030] In the second step, each job requirement keyword in the above-mentioned job requirement keyword set is classified by keyword necessity to generate a job requirement keyword group sequence. Among them, the importance and priority of the keyword groups corresponding to each job requirement keyword group in the job requirement keyword group sequence are different. In practice, each job requirement keyword group in the job requirement keyword group sequence is arranged in order from high to low according to the importance and priority. For example, the job requirement keyword group sequence includes: the first job requirement keyword group, the second job requirement keyword group, the third job requirement keyword group and the fourth job requirement keyword group. The importance and priority corresponding to the first job requirement keyword group are higher than the importance and priority corresponding to the second job requirement keyword group. The importance and priority corresponding to the second job requirement keyword group are higher than the importance and priority corresponding to the third job requirement keyword group. The importance and priority corresponding to the third job requirement keyword group are higher than the importance and priority corresponding to the fourth job requirement keyword group.

[0031] The third step is to obtain the keyword phrases required by the recruitment unit corresponding to each full-scale job recruitment unit information in the full-scale job recruitment unit information set, and obtain the keyword phrase set required by the recruitment unit. Among them, the keyword phrases required by the recruitment unit are pre-generated based on the first language model mentioned above. The information of each job recruitment unit in the full-scale job recruitment unit information set can be the unit information of all units that have publicly conducted job recruitment. The keyword phrases required by the recruitment unit can be the various keywords for the job recruitment by the job recruitment unit.

[0032] Step 4: For each piece of full-scale job recruitment unit information in the above-mentioned full-scale job recruitment unit information set, execute the following second generation step:

[0033] Sub-step 1, determining the keyword group required by the recruiting unit corresponding to the above-mentioned full amount of job recruiting unit information as the keyword group required by the target recruiting unit.

[0034] Sub-step 2: classify the target recruitment unit demand keywords in the target recruitment unit demand keyword group by keyword necessity to obtain a recruitment unit demand keyword group sequence. The specific implementation method will not be repeated here.

[0035] Sub-step 3, executing keyword matching information for the keyword group sequence required by the recruitment unit and the keyword group sequence required by the position. The keyword matching information can represent the keyword similarity between the keyword group sequence required by the recruitment unit and the keyword group sequence required by the position. The keyword matching information can be information in numerical form, and the larger the numerical value, the higher the similarity.

[0036] Step 5: Filter out a subset of keyword matching information whose corresponding keyword matching information meets a preset matching condition from the obtained keyword matching information set as the target keyword matching information subset. The preset matching condition may be that the corresponding value of the keyword matching information is greater than a preset value.

[0037] The sixth step is to use the job recruitment unit information set corresponding to the target keyword matching information subset as the job recruitment unit information set corresponding to the object job requirement information.

[0038] Optionally, the above-mentioned execution of the keyword matching information for the above-mentioned recruitment unit requirement keyword group sequence and the above-mentioned job requirement keyword group sequence may include the following steps:

[0039] The first step is to keyword match the first target recruitment unit requirement keyword group in the above recruitment unit requirement keyword group sequence with the first target job requirement keyword group in the above job requirement keyword group sequence to generate a first matching score. The first target recruitment unit requirement keyword group is the recruitment unit requirement keyword group of the first priority level in the above recruitment unit requirement keyword group sequence, and the first target job requirement keyword group is the job requirement keyword group of the first priority level in the above job requirement keyword group sequence. The first matching score can represent the degree of keyword similarity between keyword groups under the first priority level. The first priority level can be the highest priority level.

[0040] In the second step, in response to determining that the above-mentioned first matching score is greater than the first numerical value, the second target recruitment unit requirement keyword group in the above-mentioned recruitment unit requirement keyword group sequence is keyword matched with the second target job requirement keyword group in the above-mentioned job requirement keyword group sequence to generate a second matching score. Among them, the above-mentioned second target recruitment unit requirement keyword group is a recruitment unit requirement keyword group of the second priority level in the above-mentioned recruitment unit requirement keyword group sequence, and the above-mentioned second target job requirement keyword group is a job requirement keyword group of the second priority level in the above-mentioned job requirement keyword group sequence. The second matching score can characterize the degree of keyword similarity between keyword groups under the second priority level. The first priority level is higher than the second priority level. The importance of the corresponding second target job requirement keyword group is lower than that of the first target job requirement keyword group. The importance of the second target recruitment unit requirement keyword group is lower than that of the first target recruitment unit requirement keyword group. The first numerical value can be a preset numerical value.

[0041] In the third step, in response to determining that the above-mentioned second matching score is greater than the second value, the third target recruitment unit demand keyword group in the above-mentioned recruitment unit demand keyword group sequence is keyword matched with the third target job demand keyword group in the above-mentioned job demand keyword group sequence to generate a third matching score. Among them, the above-mentioned third target recruitment unit demand keyword group is a recruitment unit demand keyword group with the third priority level in the above-mentioned recruitment unit demand keyword group sequence, and the above-mentioned third target job demand keyword group is a job demand keyword group with the third priority level in the above-mentioned job demand keyword group sequence. The corresponding importance of the third target recruitment unit demand keyword group is lower than that of the second target recruitment unit demand keyword group. The corresponding importance of the third target job demand keyword group is lower than that of the second target job demand keyword group. The third matching score can characterize the degree of keyword similarity between keyword groups under the third priority level. The first priority level is higher than the second priority level. The second priority level is higher than the third priority level.

[0042] In step 4, in response to determining that the third matching score is greater than a third value, weighted summing processing is performed on the first matching score, the second matching score and the third matching score to generate a weighted summing score as keyword matching information, wherein the third value may be a preset value.

[0043] Step 102, in response to receiving the resume delivery information initiated by the target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the at least one job recruitment unit information, the following sending steps are performed:

[0044] Step 1021, using the pre-trained second language model, generates demand matching relationship information between the submitted resume corresponding to the above-mentioned target interviewee and the unit demand information corresponding to the above-mentioned job recruitment unit information.

[0045] In some embodiments, the execution subject may use the pre-trained second largest language model to generate demand matching relationship information between the submitted resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information. The submitted resume may be a resume submitted by the target interviewee. The unit demand information may be the recruitment requirement information released by the unit corresponding to the job recruitment unit information. In practice, the unit demand information may include: recruitment education requirement information, recruitment age requirement information, recruitment skill requirement information, and recruitment certificate requirement information. The demand matching relationship information may characterize the information on the close degree of information matching between the resume content corresponding to the submitted resume and the unit demand information. The close degree of information matching may be the degree of recruitment compliance between the resume content and the unit demand information. The second largest language model may be a neural network model related to natural language processing. The second largest language model may be a neural network model that generates an information matching relationship between the submitted resume and the unit demand information. In practice, the first largest language model may be a large language model (LLM, Large Language Model). The at least one job recruitment unit information is a subset of the above-mentioned job recruitment unit information set.

[0046] Optionally, the above-mentioned use of the pre-trained second language model to generate the demand matching relationship information between the submitted resume corresponding to the above-mentioned target interviewee and the unit demand information corresponding to the above-mentioned job recruitment unit information may include the following steps:

[0047] The first step is to extract the structured data set and unstructured data set corresponding to the above-mentioned submitted resume as the first structured data set and the first unstructured data set respectively. Among them, the structured data can be the structured data content in the submitted resume. In practice, the structured data set may include: the name information of the interviewee, the school of the interviewee, the age of the interviewee, and the address information of the interviewee. The first unstructured data set may include: the internship experience information of the interviewee, the advantages introduction information of the interviewee, and the project experience information of the interviewee.

[0048] The second step is to transform the first unstructured data in the first unstructured data set into data in a structured form to generate second structured data, thereby obtaining a second structured data set.

[0049] As an example, the above-mentioned execution entity can use a deep learning model to perform data cleaning, heterogeneous data, and semantic understanding on the first unstructured data in sequence to generate second structured data.

[0050] The third step is to extract the structured data set and the unstructured data set corresponding to the above unit demand information as the third structured data set and the second unstructured data set respectively. The third structured data set may include: unit welfare information, unit address information, and unit salary information. The second unstructured data set may include: unit required skill information, unit required certificate information, and unit required school information.

[0051] The fourth step is to transform the second unstructured data in the second unstructured data set into data in a structured form to generate fourth structured data, thereby obtaining a fourth structured data set.

[0052] As an example, the above-mentioned execution entity can use a deep learning model to perform data cleaning, heterogeneous data, and semantic understanding on the second unstructured data in sequence to generate fourth structured data.

[0053] The fifth step is to combine the first structured data set and the second structured data set to generate a first combined structured data set.

[0054] The sixth step is to combine the third structured data set and the fourth structured data set to generate a second combined structured data set.

[0055] In the seventh step, the first combined structured data set and the second combined structured data set are input into the second largest language model to generate the demand matching relationship information.

[0056] Step 1022: Send the demand matching relationship information and the submitted resume to at least one associated terminal corresponding to the at least one job recruitment unit information.

[0057] In some embodiments, the execution entity may send the demand matching relationship information and the submitted resume to at least one associated terminal corresponding to the at least one job recruitment unit information. There is a one-to-one correspondence between the job recruitment unit information in the at least one job recruitment unit information and the associated terminal in the at least one associated terminal. The associated terminal may be a user terminal of the unit corresponding to the job recruitment unit information.

[0058] Step 103, in response to receiving at least one reply result for the above-mentioned at least one job recruitment unit information, the above-mentioned at least one reply result, at least one unit requirement information and at least one requirement matching relationship information obtained are linked and packaged to generate a resume delivery link.

[0059] In some embodiments, in response to receiving at least one reply result for the at least one job recruitment unit information, the execution entity may link and package the at least one reply result, at least one unit demand information, and at least one demand matching relationship information obtained to generate a resume delivery link. Among them, there is a one-to-one correspondence between the job recruitment unit information in the at least one job recruitment unit information and the reply result in the at least one reply result. The reply result may be a result that characterizes whether the unit corresponding to the job recruitment unit information replies to the target interviewee whether he or she can participate in the subsequent interview. Among them, the link content corresponding to the resume delivery link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information. The job recruitment unit jump link may be a link that jumps to the communication interface between the job recruitment unit and the target interviewee.

[0060] Step 104, sending the resume delivery link to the user terminal corresponding to the target interviewee.

[0061] In some embodiments, the execution subject may send the resume delivery link to the user terminal corresponding to the target interviewee. For example, the user terminal corresponding to the target interviewee may be a mobile terminal used by the target interviewee.

[0062] In some optional implementations of some embodiments, after step 104, the steps further include:

[0063] The first step is to obtain a set of interviewees within a predetermined historical time period. The predetermined historical time period may be a time period under a preset historical time. The interviewees in the interviewee set may be the interviewees who are interviewed within the historical time period.

[0064] The second step is to determine, for each interviewee in the above interviewee set, the recommended evaluation information for the corresponding job recruitment unit information set filled in by the above interviewee. Among them, the recommended evaluation information may include information that characterizes the accuracy of the job recruitment unit information set in recommending each job recruitment unit information, and may also include information on the recommended questions corresponding to the job recruitment unit information set. In practice, the recommended evaluation information may be in the form of a score, and the higher the score, the higher the accuracy of the recommended job recruitment unit information set as the interview unit corresponding to the interviewee. In addition, the recommended evaluation information may also include information in the form of labels. For example, the recommended evaluation information may be one of the following: "very good recommendation", "average recommendation", "not very good recommendation", "very poor recommendation".

[0065] The third step is to generate a recommended optimization direction information set based on the obtained recommended evaluation information set, wherein the recommended optimization direction information may be an optimization direction point for recommending unit information for the job recruitment unit information set.

[0066] As an example, first, the execution subject may summarize the recommendation questions of each recommendation evaluation information in the recommendation evaluation information set to generate a summary question. Then, the optimization direction point corresponding to the summary question is queried from the association table as the recommendation optimization direction information to obtain the recommendation optimization direction information set.

[0067] The fourth step is to perform model training on the first language model according to the recommended optimization direction information set to obtain the trained first language model.

[0068] As an example, first, the execution subject may obtain a sample set corresponding to the recommended optimization direction information set, and then perform model training on the first language model according to the sample set to obtain the trained first language model.

[0069] The fifth step is to determine the largest language model after training as the largest language model.

[0070] Optionally, the steps further include:

[0071] The first step is to obtain a job recruitment unit information set within the above-mentioned predetermined historical time period, wherein the job recruitment unit information in the job recruitment unit information set may be unit information that conducts job recruitment within the predetermined historical time period.

[0072] The second step is to determine the matching evaluation information of the target job recruitment unit for each job recruitment unit information in the above job recruitment unit information set and the corresponding demand matching relationship information set. The above job recruitment unit information corresponds to the above target job recruitment unit. The matching evaluation information may be the information after the job recruitment unit evaluates the accuracy of the matching relationship of the demand matching relationship information. In practice, the matching evaluation information may be in the form of a score, and the higher the score, the higher the accuracy of the demand matching relationship information. In addition, the matching evaluation information may also include information in the form of a label. For example, the matching evaluation information may be one of the following: "very good match", "average match", "not very good match", "very poor match".

[0073] In the third step, based on the obtained matching evaluation information set, the second largest language model is trained to obtain the trained second largest language model.

[0074] As an example, the execution subject may generate a positive sample set and a negative sample set according to the matching evaluation information set. Then, the second largest language model is trained according to the positive sample set and the negative sample set to obtain the trained second largest language model.

[0075] The fourth step is to determine the second largest language model after training as the second largest language model.

[0076] In some optional implementations of some embodiments, the use of the pre-trained second language model to generate demand matching relationship information between the submitted resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information may include the following steps:

[0077] The first step is to obtain at least one resume keyword and at least one recruiting unit keyword that are pre-stored. For example, at least one resume keyword includes: name, contact information, awards, key technical points, project highlights. At least one recruiting unit keyword includes: education, recruitment technical requirements, age requirements, and certificate requirements.

[0078] In the second step, the second largest language model is used to filter out at least one resume keyword content corresponding to the at least one resume keyword from the submitted resume. The resume keyword content in the at least one resume keyword content has a one-to-one correspondence with the resume keyword in the at least one resume keyword. The resume keyword content is the word content corresponding to the resume keyword.

[0079] As an example, the execution entity may utilize the character recognition model in the second language model to filter out at least one resume keyword content corresponding to the at least one resume keyword from the submitted resume.

[0080] In the third step, the second largest language model is used to select at least one recruitment unit keyword content corresponding to the at least one recruitment unit keyword from the unit demand information. There is a one-to-one correspondence between the recruitment unit keyword in the at least one recruitment unit keyword and the photo unit keyword content in the at least one recruitment unit keyword content.

[0081] As an example, the execution entity may utilize the character recognition model in the second language model to filter out at least one recruitment unit keyword content corresponding to the at least one recruitment unit keyword from the unit demand information.

[0082] The fourth step is to generate at least one resume keyword content vector corresponding to the at least one resume keyword content, and generate at least one recruiting unit keyword content vector corresponding to the at least one recruiting unit keyword content. There is a one-to-one correspondence between the resume keyword content in the at least one resume keyword content and the resume keyword content vector in the at least one resume keyword content vector. There is a one-to-one correspondence between the recruiting unit keyword content in the at least one recruiting unit keyword content and the recruiting unit keyword content vector in the at least one recruiting unit keyword content vector. The resume keyword content vector can represent the content semantic features of the resume keyword content. The recruiting unit keyword content vector can represent the content semantic features of the recruiting unit keyword content.

[0083] In the fifth step, the vector group similarity determination model included in the second language model is used to generate the vector group similarity between the at least one resume keyword content vector and the at least one recruiting unit keyword content vector as the demand matching relationship information. The vector group similarity determination model may be a model for determining the degree of similarity between two vector groups. The vector group similarity may represent the vector similarity between two vector groups.

[0084] As an example, first, the execution subject may concatenate at least one resume keyword content vector to generate a first concatenated vector. Then, concatenate at least one recruiting unit keyword content vector to generate a second concatenated vector. The first concatenated vector and the second concatenated vector are input into a vector group similarity determination model whose network structure is a convolutional neural network to generate vector group similarity as demand matching relationship information.

[0085] Optionally, using the vector group similarity determination model included in the second largest language model, generating a vector group similarity between the at least one resume keyword content vector and the at least one recruiting unit keyword content vector as demand matching relationship information, including:

[0086] The first step is to divide at least one resume keyword into keyword levels to generate a resume keyword group set. Among them, there is a one-to-one correspondence between the resume keyword groups in the resume keyword group set and the keyword levels in each keyword level. The keyword level represents the importance of the corresponding resume keyword. For example, each keyword level includes: a first keyword level, a second keyword level and a third keyword level. The first keyword level is higher than the second keyword level. The second keyword level is higher than the third keyword level. The corresponding resume keyword group set includes: a first resume keyword group corresponding to the first keyword level, a second resume keyword group corresponding to the second keyword level, and a third resume keyword group corresponding to the third keyword level. The importance of the keywords corresponding to the first resume keyword group is higher than the importance of the keywords corresponding to the second resume keyword group. The importance of the keywords corresponding to the second resume keyword group is higher than the importance of the keywords corresponding to the third resume keyword group.

[0087] The second step is to divide at least one recruiting unit keyword into keyword levels to generate a recruiting unit keyword group set, wherein the recruiting unit keyword groups in the recruiting unit keyword group set and the keyword levels in each keyword level have a one-to-one correspondence.

[0088] The third step is to generate a resume keyword content vector group set corresponding to the resume keyword group set according to at least one resume keyword content vector, wherein there is a one-to-one correspondence between the resume keywords in the resume keyword group set and the resume keyword content vectors in the resume keyword content vector group set.

[0089] The fourth step is to generate a recruitment unit keyword content vector group set corresponding to the recruitment unit keyword group set according to at least one recruitment unit keyword content vector, wherein the recruitment unit keywords in the recruitment unit keyword group set and the recruitment unit keyword content vectors in the recruitment unit keyword content vector group set have a one-to-one correspondence.

[0090] In the fifth step, for each keyword level in each keyword level, the following generation steps are performed:

[0091] Sub-step 1: determine the resume keyword content vector group and the recruiting unit keyword content vector group corresponding to the above keyword level, and use them as the target resume keyword content vector group and the target recruiting unit keyword content vector group respectively.

[0092] Sub-step 2: randomly splicing each target resume keyword content vector in the above target resume keyword content vector group to generate a first splicing vector set.

[0093] Sub-step 3: randomly splicing the target recruiting unit keyword content vectors in the above target recruiting unit keyword content vector group to generate a second splicing vector set.

[0094] Sub-step 4: Input each first splicing vector in the first splicing vector set and each second splicing vector in the second splicing vector set into a vector group similarity determination model to generate a vector similarity set. The vector group similarity determination model may be a convolutional layer with a predetermined number of layers connected in series. The predetermined number corresponds to the keyword level.

[0095] Sub-step 5, selecting the maximum vector similarity from the vector similarity set as the target vector similarity.

[0096] Step 6: Determine the level weight corresponding to each keyword level in the above keyword levels to obtain each level weight. The level weight can represent the importance of the keyword set corresponding to the keyword level. The higher the corresponding level of the keyword level, the greater the corresponding level weight.

[0097] In the seventh step, weighted summation is performed on the weights of each level and the similarities of each target vector obtained above to generate a weighted sum value as the demand matching relationship information.

[0098] The content in "some optional implementations of some embodiments" as an inventive point of the present disclosure solves the technical problem mentioned in the background technology that "the determined demand matching relationship information is not accurate enough, resulting in erroneous recruitment events in subsequent job recruitment units." Based on this, the present disclosure divides the resume keyword content vector and the recruitment unit keyword content vector into levels according to each keyword level, and then determines the vector cosine distance of each vector at each level, thereby fully considering the similarity between each vector at different levels and accurately generating demand matching relationship information.

[0099] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the resume delivery result sending method of some embodiments of the present disclosure, not only can the corresponding job recruitment unit be matched for the target interviewee accurately and efficiently, but also the reply result and the relevant information of the job recruitment unit can be effectively sent to the target interviewee. Specifically, the reason why the relevant job recruitment unit is not accurate enough and the corresponding reason for the interview result is not clear enough is that in the face of a large amount of job recruitment unit information, the interviewee may miss a job recruitment unit with better quality and more in line with the job requirements of the interviewee, and the interviewee may have doubts about the interview result issued by the job recruitment unit, and the interviewee cannot understand the reason for the issuance of the interview result more clearly. Based on this, the resume delivery result sending method of some embodiments of the present disclosure, first, in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface, uses the pre-trained first language model to generate the job recruitment unit information set corresponding to the above-mentioned target job requirement information. Here, using the first language model, it is possible to accurately and efficiently match the appropriate job recruitment unit information according to the target job requirements, avoiding the situation that the interviewee may miss a job recruitment unit with better quality and more in line with the job requirements of the interviewee in the face of a large amount of job recruitment unit information. Then, in response to receiving the resume submission information initiated by the above-mentioned target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the above-mentioned at least one job recruitment unit information, the following sending steps are performed: the first step is to use the pre-trained second largest language model to accurately and efficiently generate the demand matching relationship information between the submitted resume corresponding to the above-mentioned target interviewee and the unit demand information corresponding to the above-mentioned job recruitment unit information. Among them, the above-mentioned at least one job recruitment unit information is a subset of the above-mentioned job recruitment unit information set. Here, through the demand matching relationship information, the job recruitment unit can explicitly consider the degree of match between the interviewee and the job recruitment unit, which helps the job recruitment unit to achieve more accurate object screening. The second step is to send the above-mentioned demand matching relationship information and the above-mentioned submitted resume to at least one associated terminal corresponding to the above-mentioned at least one job recruitment unit information, so as to facilitate the at least one job recruitment unit information to effectively screen the interviewees. Next, in response to receiving at least one reply result for the at least one job recruitment unit information, the at least one reply result, at least one unit requirement information and at least one requirement matching relationship information obtained are linked and packaged to generate a resume delivery link, so that the target interviewee can understand the resume delivery result and the interviewee can more clearly understand the reason for issuing the interview result. Among them, the link content corresponding to the resume delivery link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information. Finally, the resume delivery link is sent to the user terminal corresponding to the target interviewee.In summary, by using the first language model and the second language model, not only can more job recruitment unit information be considered for the target interviewee to screen out high-quality job recruitment unit information, but also the demand matching degree between the job recruitment unit and the interviewee can be accurately generated, ensuring that the interviewee finds the job recruitment unit that suits him / her, and the job recruitment unit finds the person who meets his / her own job recruitment needs.

[0100] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a resume delivery result sending device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the resume delivery result sending device can be specifically applied to various electronic devices.

[0101] like Figure 2 As shown, a resume delivery result sending device 200 includes: a generating unit 201, an executing unit 202, a link packaging unit 203 and a sending unit 204. The generating unit 201 is configured to generate a job recruitment unit information set corresponding to the above-mentioned target job requirement information in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface by using the pre-trained first language model; the executing unit 202 is configured to perform the following sending steps for each job recruitment unit information in the at least one job recruitment unit information in response to receiving the resume delivery information initiated by the above-mentioned target interviewee for at least one job recruitment unit information: using the pre-trained second language model, generating the demand matching relationship information between the delivered resume corresponding to the above-mentioned target interviewee and the unit requirement information corresponding to the above-mentioned job recruitment unit information, wherein the above-mentioned at least one job recruitment unit information is A subset of the above-mentioned job recruitment unit information set; sending the above-mentioned demand matching relationship information and the above-mentioned submitted resume to at least one associated terminal corresponding to the above-mentioned at least one job recruitment unit information; a link packaging unit 203 is configured to respond to receiving at least one reply result for the above-mentioned at least one job recruitment unit information, and link and package the above-mentioned at least one reply result, at least one unit demand information and the obtained at least one demand matching relationship information to generate a resume delivery link, wherein the link content corresponding to the above-mentioned resume delivery link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information; a sending unit 204 is configured to send the above-mentioned resume delivery link to the user terminal corresponding to the above-mentioned target interviewee.

[0102] It is understandable that the units recorded in the resume delivery result sending device 200 and the reference Figure 1Therefore, the operations, features and beneficial effects described above for the method are also applicable to the resume delivery result sending device 200 and the units contained therein, and will not be repeated here.

[0103] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0104] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0105] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0106] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0107] It should be noted that the computer-readable medium in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may 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 of computer-readable storage media may include, but are not limited to: 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 some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium 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. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0108] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0109] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently and not be installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: in response to receiving the target job requirement information input by the target interviewee in the target recruitment interface, use the pre-trained first language model to generate a job recruitment unit information set corresponding to the above-mentioned target job requirement information; in response to receiving the resume delivery information initiated by the above-mentioned target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the above-mentioned at least one job recruitment unit information, perform the following sending steps: use the pre-trained second language model to generate the demand between the delivered resume corresponding to the above-mentioned target interviewee and the unit requirement information corresponding to the above-mentioned job recruitment unit information; Matching relationship information, wherein the at least one job recruitment unit information is a subset of the above job recruitment unit information set; sending the above demand matching relationship information and the above submitted resume to at least one associated terminal corresponding to the above at least one job recruitment unit information; in response to receiving at least one reply result for the above at least one job recruitment unit information, linking and packaging the at least one reply result, at least one unit demand information and the obtained at least one demand matching relationship information to generate a resume delivery link, wherein the link content corresponding to the above resume delivery link includes: a job recruitment unit jump link that supports jumping to the communication interface corresponding to the job recruitment unit information; sending the above resume delivery link to the user terminal corresponding to the above target interview object

[0110] Computer program code for performing the operations of some embodiments of the present disclosure 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 cases involving a remote computer, the remote computer may be connected to the user's computer via 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).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be arranged in a processor, for example, may be described as: a processor includes a generation unit, an execution unit, a link packaging unit and a sending unit. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances. For example, the sending unit may also be described as "a unit that sends the above resume delivery link to the user terminal corresponding to the above target interview object".

[0113] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0114] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A method for sending resume delivery results, comprising: In response to receiving target job requirement information input by the target interviewee on the target recruitment interface, using the pre-trained first language model, generating a job recruitment unit information set corresponding to the target job requirement information; In response to receiving resume delivery information initiated by the target interviewee for at least one job recruitment unit information, for each job recruitment unit information in the at least one job recruitment unit information, the following sending steps are performed: Using the pre-trained second language model, generating demand matching relationship information between the submitted resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information, wherein the at least one job recruitment unit information is a subset of the job recruitment unit information set; Sending the demand matching relationship information and the submitted resume to at least one associated terminal corresponding to the at least one job recruiting unit information; In response to receiving at least one reply result for the at least one job recruitment unit information, the at least one reply result, the at least one unit requirement information and the obtained at least one requirement matching relationship information are linked and packaged to generate a resume delivery link, wherein the link content corresponding to the resume delivery link includes: a job recruitment unit jump link that supports jumping to a communication interface corresponding to the job recruitment unit information; The resume delivery link is sent to the user terminal corresponding to the target interview object.

2. The method according to claim 1, wherein: The method further comprises: Get the interview object set within a predetermined historical time period; For each interviewee in the interviewee set, determining the recommended evaluation information filled out by the interviewee for the corresponding job recruitment unit information set; Generate a recommendation optimization direction information set based on the obtained recommendation evaluation information set; Performing model training on the first largest language model according to the recommended optimization direction information set to obtain a trained first largest language model; The largest language model after training is determined as the largest language model.

3. The method according to claim 2, wherein: The method further comprises: Obtaining a set of information about job recruiting units within the predetermined historical time period; For each post recruiting unit information in the post recruiting unit information set, determining the matching evaluation information of the target post recruiting unit corresponding to the corresponding demand matching relationship information set, wherein the post recruiting unit information corresponds to the target post recruiting unit; According to the obtained matching evaluation information set, model training is performed on the second largest language model to obtain the trained second largest language model; The second largest language model after training is determined as the second largest language model.

4. The method according to claim 1, wherein: The method of using the pre-trained first language model to generate a job recruitment unit information set corresponding to the object job requirement information includes: Inputting the target job requirement information into the first language model to generate a job requirement keyword set; Performing keyword necessity classification on each job requirement keyword in the job requirement keyword set to generate a job requirement keyword group sequence; Obtaining a recruitment unit demand keyword group corresponding to each full amount of recruitment unit information in the full amount of recruitment unit information set, to obtain a recruitment unit demand keyword group set, wherein the recruitment unit demand keyword group is pre-generated based on the first largest language model; For each piece of full-quantity job recruitment unit information in the full-quantity job recruitment unit information set, the following second generation step is performed: Determine the keyword group required by the recruiting unit corresponding to the information of all the job recruiting units as the keyword group required by the target recruiting unit; Performing keyword necessity classification on each target recruitment unit demand keyword in the target recruitment unit demand keyword group to obtain a recruitment unit demand keyword group sequence; Execute keyword matching information for the keyword group sequence required by the recruiting unit and the keyword group sequence required by the position; A keyword matching information subset whose corresponding keyword matching information meets the preset matching conditions is screened out from the obtained keyword matching information set as the target keyword matching information subset; and the job recruiting unit information set corresponding to the target keyword matching information subset is used as the job recruiting unit information set corresponding to the target job requirement information.

5. The method according to claim 4, wherein: The executing of keyword matching information for the keyword group sequence required by the recruiting unit and the keyword group sequence required by the position includes: Keyword matching is performed on a first target recruitment unit requirement keyword group in the recruitment unit requirement keyword group sequence and a first target job requirement keyword group in the job requirement keyword group sequence to generate a first matching score, wherein the first target recruitment unit requirement keyword group is a recruitment unit requirement keyword group of the first priority level in the recruitment unit requirement keyword group sequence, and the first target job requirement keyword group is a job requirement keyword group of the first priority level in the job requirement keyword group sequence; In response to determining that the first matching score is greater than the first value, keyword matching is performed on a second target recruitment unit requirement keyword group in the recruitment unit requirement keyword group sequence and a second target job requirement keyword group in the job requirement keyword group sequence to generate a second matching score, wherein the second target recruitment unit requirement keyword group is a recruitment unit requirement keyword group of the second priority level in the recruitment unit requirement keyword group sequence, and the second target job requirement keyword group is a job requirement keyword group of the second priority level in the job requirement keyword group sequence; In response to determining that the second matching score is greater than a second value, keyword matching is performed on a third target recruitment unit requirement keyword group in the recruitment unit requirement keyword group sequence and a third target job requirement keyword group in the job requirement keyword group sequence to generate a third matching score, wherein the third target recruitment unit requirement keyword group is a recruitment unit requirement keyword group of a third priority level in the recruitment unit requirement keyword group sequence, and the third target job requirement keyword group is a job requirement keyword group of the third priority level in the job requirement keyword group sequence; In response to determining that the third matching score is greater than a third value, weighted sum processing is performed on the first matching score, the second matching score, and the third matching score to generate a weighted sum score as keyword matching information.

6. The method according to claim 1, wherein: The method of using the pre-trained second language model to generate demand matching relationship information between the submitted resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information includes: Extracting a structured data set and an unstructured data set corresponding to the submitted resume as a first structured data set and a first unstructured data set, respectively; Converting the first unstructured data in the first unstructured data set into data in a structured form to generate second structured data, thereby obtaining a second structured data set; Extracting a structured data set and an unstructured data set corresponding to the unit demand information as a third structured data set and a second unstructured data set, respectively; Converting the second unstructured data in the second unstructured data set into data in a structured form to generate fourth structured data, thereby obtaining a fourth structured data set; combining the first structured data set and the second structured data set to generate a first combined structured data set; combining the third structured data set and the fourth structured data set to generate a second combined structured data set; The first combined structured data set and the second combined structured data set are input into the second large language model to generate the demand matching relationship information.

7. The method according to claim 1, wherein: The method of using the pre-trained second language model to generate demand matching relationship information between the submitted resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information includes: Obtaining at least one resume keyword and at least one recruiting unit keyword that are pre-stored; Using the second largest language model, at least one resume keyword content corresponding to the at least one resume keyword is filtered out from the submitted resume; Using the second largest language model, at least one recruitment unit keyword content corresponding to the at least one recruitment unit keyword is filtered out from the unit demand information; Generate at least one resume keyword content vector corresponding to the at least one resume keyword content, and generate at least one recruiting unit keyword content vector corresponding to the at least one recruiting unit keyword content; The vector group similarity determination model included in the second largest language model is used to generate the vector group similarity between the at least one resume keyword content vector and the at least one recruiting unit keyword content vector as demand matching relationship information.

8. A resume delivery result sending device, comprising: A generating unit is configured to generate a job recruitment unit information set corresponding to the target job requirement information by using a pre-trained first language model in response to receiving the target job requirement information input by the target interviewee on the target recruitment interface; The execution unit is configured to, in response to receiving resume delivery information initiated by the target interviewee for at least one job recruitment unit information, perform the following sending steps for each job recruitment unit information in the at least one job recruitment unit information: using a pre-trained second language model to generate demand matching relationship information between the delivered resume corresponding to the target interviewee and the unit demand information corresponding to the job recruitment unit information, wherein the at least one job recruitment unit information is a subset of the job recruitment unit information set; sending the demand matching relationship information and the delivered resume to at least one associated terminal corresponding to the at least one job recruitment unit information; The link packaging unit is configured to, in response to receiving at least one reply result for the at least one job recruitment unit information, link and package the at least one reply result, at least one unit requirement information and the obtained at least one requirement matching relationship information to generate a resume delivery link, wherein the link content corresponding to the resume delivery link includes: a job recruitment unit jump link that supports jumping to a communication interface corresponding to the job recruitment unit information; The sending unit is configured to send the resume delivery link to the user terminal corresponding to the target interview object.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Job seeker resume recommendation processing method and system

    CN102117323A

  • Resume screening method and device, terminal and computer readable storage medium

    CN110263818A

  • Resume creation method and apparatus, and electronic device

    CN112541329A

  • Resume recommendation method, post recommendation method and electronic equipment

    CN114691965A

  • Internet information processing method and system, and recording medium

    CN116401459A