Method for determining matching parameters between user and enterprise, electronic device and program product

Abstract

The method, electronic device and program product for determining matching parameters between a user and an enterprise provided by the present disclosure relate to deep learning technology, and include: obtaining resume data of a user and recruitment information of an enterprise; determining a first feature and a second feature according to the resume data and the recruitment information; determining a first parameter value according to a preset first weight of the user for the enterprise and the first feature; determining a second parameter value according to a preset second weight of the enterprise for the user and the second feature; the first parameter value and the second parameter value are used to determine a matching result between the user and the enterprise. In the solution provided by the present disclosure, features can be extracted according to the resume data and the recruitment information, and these features can be processed by using the preset first weight and second weight to obtain a two-way evaluation result between the enterprise and the user, thereby assisting the enterprise in making recruitment decisions.

Description

Technical Field

[0001] The present disclosure relates to deep learning technology in artificial intelligence technology, and particularly to a method for determining matching parameters between a user and an enterprise, an electronic device, and a program product. Background Art

[0002] With the development of network technology, many services can be carried out online. For example, a recruiting enterprise can post recruitment information on the network, and an applicant user can submit a resume on the network. Therefore, a large amount of data of recruiting enterprises and applicant users has been accumulated in the recruitment platform.

[0003] To improve the recruitment efficiency, these data can be analyzed to assist the recruiting enterprise in making decisions. Currently, the resume of the applicant user and the recruitment information of the enterprise can be analyzed to obtain the result of whether the user and the enterprise match.

[0004] However, making a recruitment decision only based on this matching result is still not accurate enough. Summary of the Invention

[0005] The present disclosure provides a method for determining matching parameters between a user and an enterprise, an electronic device, and a program product, so as to more accurately assist the enterprise in making a recruitment decision.

[0006] According to a first aspect of the present disclosure, there is provided a method for determining matching parameters between a user and an enterprise, including:

[0007] Obtain the resume data of the user and the recruitment information of the enterprise;

[0008] Determine a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to characterize the evaluation information of the user on the enterprise, and the second feature is used to characterize the evaluation information of the enterprise on the user;

[0009] Determine a first parameter value according to a preset first weight of the user on the enterprise and the first feature; determine a second parameter value according to a preset second weight of the enterprise on the user and the second feature, where the first parameter value is used to characterize the matching degree of the user to the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise to the user;

[0010] The first parameter value and the second parameter value are used to determine the matching result between the user and the enterprise.

[0011] According to a second aspect of the present disclosure, there is provided a method for determining weights between a user and an enterprise, including:

[0012] Obtain a training data set, a first weight of a user for an enterprise to be trained, and a second weight of the enterprise for the user to be trained; wherein, the training data set includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise;

[0013] According to the first weight, the second weight, the resume data, and the recruitment information, predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise;

[0014] According to the true admission record, the true acceptance record, the predicted admission record, and the predicted acceptance record, optimize the first weight and the second weight;

[0015] The optimized first weight and second weight that meet the preset conditions are used to determine the matching degree between the user and the enterprise.

[0016] According to the third aspect of the present disclosure, there is provided a device for determining matching parameters between a user and an enterprise, including:

[0017] An acquisition unit for acquiring the resume data of the user and the recruitment information of the enterprise;

[0018] A feature determination unit for determining a first feature and a second feature according to the resume data and the recruitment information, wherein the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user;

[0019] A parameter determination unit for determining a first parameter value according to a preset first weight of the user for the enterprise and the first feature; determining a second parameter value according to a preset second weight of the enterprise for the user and the second feature, where the first parameter value is used to characterize the matching degree of the user to the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise to the user;

[0020] The first parameter value and the second parameter value are used to determine the matching result between the user and the enterprise.

[0021] According to the fourth aspect of the present disclosure, there is provided a device for determining weights between a user and an enterprise, including:

[0022] An acquisition unit for acquiring a training data set, a first weight of a user for an enterprise to be trained, and a second weight of the enterprise for the user to be trained; wherein, the training data set includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise;

[0023] A prediction unit for predicting a predicted admission record of the enterprise sending an admission notice to the user and a predicted acceptance record of the user accepting the admission notice of the enterprise according to the first weight, the second weight, the resume data, and the recruitment information;

[0024] A training unit for optimizing the first weight and the second weight according to the true admission record, the true acceptance record, the predicted admission record, and the predicted acceptance record;

[0025] The optimized first weight and second weight that meet the preset conditions are used to determine the matching degree between the user and the enterprise.

[0026] According to a fifth aspect of the present disclosure, there is provided an electronic device, including:

[0027] At least one processor; and

[0028] A memory communicatively connected to the at least one processor; wherein,

[0029] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described in the first aspect or the second aspect.

[0030] According to a sixth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method described in the first aspect or the second aspect.

[0031] According to a seventh aspect of the present disclosure, there is provided a computer program product, the computer program product includes: a computer program, the computer program is stored in a readable storage medium, and at least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the electronic device executes the method described in the first aspect or the second aspect.

[0032] The method, electronic device, and program product for determining matching parameters between a user and an enterprise provided by the present disclosure include: obtaining the resume data of the user and the recruitment information of the enterprise; determining a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to represent the evaluation information of the user on the enterprise, and the second feature is used to represent the evaluation information of the enterprise on the user; determining a first parameter value according to a preset first weight of the user on the enterprise and the first feature; determining a second parameter value according to a preset second weight of the enterprise on the user and the second feature, where the first parameter value is used to represent the matching degree of the user to the enterprise, and the second parameter value is used to represent the matching degree of the enterprise to the user; the first parameter value and the second parameter value are used to determine the matching result between the user and the enterprise. In the solution provided by the present disclosure, features can be extracted according to the resume data and the recruitment information, and these features can be processed using the preset first weight and second weight to obtain a two-way evaluation result between the enterprise and the user, thereby assisting the enterprise in formulating recruitment decisions.

[0033] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0035] Figure 1 is a schematic flowchart of a method for determining matching parameters between a user and an enterprise shown in an exemplary embodiment of the present disclosure;

[0036] Figure 2 is a schematic flowchart of a method for determining matching parameters between a user and an enterprise shown in another exemplary embodiment of the present disclosure;

[0037] Figure 3 is a schematic flowchart of a method for determining weights between a user and an enterprise shown in an exemplary embodiment of the present disclosure;

[0038] Figure 4 is a schematic flowchart of a method for determining weights between a user and an enterprise shown in another exemplary embodiment of the present disclosure;

[0039] Figure 5 is a schematic diagram of a process for training weights shown in an exemplary embodiment of the present disclosure;

[0040] Figure 6 is a schematic structural diagram of a device for determining matching parameters between a user and an enterprise shown in an exemplary embodiment of the present disclosure;

[0041] Figure 7This is a structural schematic diagram of a device for determining matching parameters between a user and an enterprise, shown in another exemplary embodiment of the present disclosure;

[0042] Figure 8 This is a structural diagram of a device for determining a weight between a user and an enterprise according to an exemplary embodiment of the present disclosure;

[0043] Figure 9 A schematic diagram of a structure of a device for determining a weight between a user and an enterprise shown in another exemplary embodiment of the present disclosure;

[0044] Figure 10 The block diagram is a block diagram of an electronic device for implementing the method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0045] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0046] In order to assist enterprises in recruiting talents, the resumes of talents can be matched with the job requirements of the enterprise, so that the human resources department of the enterprise can determine the suitable talents for the positions based on the matching results.

[0047] Currently, the methods to assist enterprises in making recruitment decisions include making decisions based on matching algorithms. In this solution, natural language processing technology is needed to match talent resumes with job requirements and make decisions based on the matching situation.

[0048] However, the matching results determined in this scheme only measure the "matching degree" between talents and positions, but largely ignore the willingness of talents, making the decisions based on the matching results inaccurate and resulting in low recruitment efficiency.

[0049] In order to solve the above technical problems, in the solution provided by the present disclosure, the matching degree of the user to the enterprise and the matching degree of the enterprise to the user are determined based on the user's resume data and the enterprise's recruitment information, so as to measure the matching degree between the enterprise and the user from a two-way perspective. This method considers not only whether the user's resume meets the job requirements, but also whether the company's situation meets the user's job-seeking intentions. Therefore, this method can obtain more accurate matching results between enterprises and talents, thereby improving recruitment efficiency.

[0050] Figure 1 This is a flowchart of a method for determining matching parameters between a user and an enterprise, shown as an exemplary embodiment of the present disclosure.

[0051] As Figure 1 shown, the method for determining the matching parameters between users and enterprises provided by the present disclosure includes:

[0052] Step 101, obtaining the resume data of the user and the recruitment information of the enterprise.

[0053] Among them, the method provided by the present disclosure can be executed by an electronic device with computing capabilities. The electronic device can be a server or a user terminal.

[0054] If the solution provided by the present disclosure is executed by the server, the user can operate the user terminal to send the resume data of the user and the recruitment information of the enterprise to the server, so that the server obtains the resume data and the recruitment information.

[0055] If the solution provided by the present disclosure is executed by the user terminal, the user can operate the user terminal to enable the user terminal to obtain the resume data and the recruitment information. For example, the user can operate in the interface of the terminal device to select the resume data of the user and the recruitment information of the enterprise, so that the user terminal can process the resume data and the recruitment information based on the solution provided by the present disclosure.

[0056] Specifically, after the electronic device obtains the resume data of the user and the recruitment information of the enterprise, it can be processed by the solution provided by the present disclosure. For example, the solution provided by the present disclosure can be encapsulated into a software, and the resume data of the user and the recruitment information of the enterprise can be processed through this software.

[0057] Step 102, determining a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to characterize the evaluation information of the user on the enterprise, and the second feature is used to characterize the evaluation information of the enterprise on the user.

[0058] Furthermore, the electronic device can extract features from the resume data and the recruitment information, and then determine the first feature and the second feature among them.

[0059] In practical applications, the electronic device can directly extract features from the resume data, can also extract features from the recruitment information, and can also determine the similarity information between the resume data and the recruitment information and use it as a type of feature. Based on this, the electronic device can obtain multiple features.

[0060] Some features can belong to both the first feature and the second feature.

[0061] Among them, the electronic device can determine the first feature from the multiple extracted features, and the first feature is used to characterize the evaluation information of the user on the enterprise; the electronic device can determine the second feature from the multiple extracted features, and the second feature is used to characterize the evaluation information of the enterprise on the user.

[0062] For example, the first feature includes, for example, the matching degree of the job resume text, the composition of department employees, etc.; the second feature includes, for example, the matching degree of the writing style of the job resume, the education background of the talent, the interview score, etc.

[0063] By determining the information for characterizing the user's evaluation of the enterprise and the information for characterizing the enterprise's evaluation of the user, it is possible to determine the user's evaluation result of the enterprise and the enterprise's evaluation result of the user based on this information, and then it is possible to determine the matching degree between the enterprise and the user from two directions.

[0064] Step 103, determine the first parameter value according to the preset first weight of the user for the enterprise and the first feature; determine the second parameter value according to the preset second weight of the enterprise for the user and the second feature; the first parameter value is used to characterize the matching degree of the user for the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise for the user.

[0065] Specifically, the first weight of the user for the enterprise and the second weight of the enterprise for the user can be preset in the electronic device.

[0066] Furthermore, the first weight and the second weight can be obtained through machine learning technology training.

[0067] Training data can be prepared in advance. The training data can include the user's resume data, the enterprise's recruitment information, the information of the enterprise sending out the employment notice, and the information of the user accepting the employment notice. The first feature and the second feature can be extracted according to the resume data and the recruitment information, and then according to these features and the preset first weight and second weight, the matching degree between the enterprise and the user can be determined, and according to this matching degree, the information of the enterprise sending out the employment notice can be predicted, and the information of the user accepting the employment notice can be predicted. Furthermore, the first weight and the second weight can be optimized by combining the real information of the enterprise sending out the employment notice and the user accepting the employment notice in the training data. Through multiple iterations, the values of the first weight and the second weight can be obtained.

[0068] In actual application, the electronic device can use the product of the first weight and the first feature as the first parameter value; use the product of the second weight and the second feature as the second parameter value.

[0069] The first parameter value obtained through the first weight and the first feature can determine the matching degree of the user for the enterprise, so as to obtain the user's evaluation result of the enterprise. The second parameter value obtained through the second weight and the second feature can determine the matching degree of the enterprise for the user, so as to obtain the enterprise's evaluation result of the user. Thus, a two-way evaluation result between the enterprise and the user can be obtained.

[0070] For example, if the first parameter value is large, it indicates that the user has a high evaluation of the enterprise, and this user will accept the employment notice from the enterprise. If the second parameter value is large, it indicates that the enterprise has a high evaluation of the user, and this enterprise will send an employment notice to the user. Therefore, through these two parameters, a two-way evaluation result between the user and the enterprise can be obtained.

[0071] In an alternative implementation, the first parameter value and the second parameter value can be displayed on the user terminal, so that the user can determine the matching result between the user and the enterprise based on the first parameter value and the second parameter value. For example, if both values are high, it can be determined that the enterprise and the user are relatively well-matched.

[0072] In an alternative implementation, a first threshold and a second threshold can be set. If the first parameter value is greater than the first threshold, it can be determined that this user will accept the employment notice from the enterprise. If the second parameter value is greater than the second threshold, it can be determined that this enterprise will send an employment notice to the user.

[0073] If it is predicted that the user will accept the employment notice from the enterprise and this enterprise will also send an employment notice to the user, it can be determined that the matching result between this enterprise and the user is a match. If it is predicted that the user will not accept the employment notice from the enterprise, or this enterprise will not send an employment notice to the user, it can be determined that the matching result between this enterprise and the user is a mismatch.

[0074] In an alternative implementation, the matching result can also be displayed on the user terminal. For example, if the electronic device is a server, the server can send the matching result to the user terminal so that the user terminal displays the matching result.

[0075] The method for determining the matching parameters between a user and an enterprise provided by the present disclosure includes: obtaining the resume data of the user and the recruitment information of the enterprise; determining a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to characterize the evaluation information of the user on the enterprise, and the second feature is used to characterize the evaluation information of the enterprise on the user; determining a first parameter value according to the preset first weight of the user on the enterprise and the first feature; determining a second parameter value according to the preset second weight of the enterprise on the user and the second feature, the first parameter value is used to characterize the matching degree of the user to the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise to the user; the first parameter value and the second parameter value are used to determine the matching result between the user and the enterprise. In the method provided by the present disclosure, features can be extracted according to the resume data and the recruitment information, and these features can be processed by using the preset first weight and second weight to obtain a two-way evaluation result between the enterprise and the user, thereby assisting the enterprise in making recruitment decisions.

[0076] Figure 2Schematic flowchart of a method for determining matching parameters between a user and an enterprise according to another exemplary embodiment of the present disclosure.

[0077] As Figure 2 shown, the method for determining matching parameters between a user and an enterprise provided by the present disclosure includes:

[0078] Step 201, obtain the resume data of the user and the recruitment information of the enterprise.

[0079] The implementation manner of step 201 is similar to that of step 101, and will not be elaborated here.

[0080] Step 202, extract features from the resume data and the recruitment information.

[0081] Step 203, determine the first feature of the user for the enterprise and the second feature of the enterprise for the user according to the extracted features; wherein, the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user.

[0082] Among them, the resume data includes a lot of information, and the recruitment information also includes a lot of information. Therefore, a large number of features can be extracted from the resume data and the recruitment information.

[0083] For example, the educational background feature, work experience feature, job hunting intention feature, etc. of the user can be extracted from the resume data. For another example, the department composition information of the enterprise, the job requirement feature of the enterprise, etc. can be extracted from the recruitment information.

[0084] Specifically, according to the large number of extracted features, the first feature of the user for the enterprise and the second feature of the enterprise for the user can be determined. Among them, the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user.

[0085] Further, the electronic device can screen out the evaluation features of the user for the enterprise from the large number of extracted features. And determine the first feature according to these features, and can also screen out the evaluation features of the enterprise for the user, and determine the second feature according to these features.

[0086] Through this implementation manner, the electronic device can determine the first feature of the user for the enterprise and the second feature of the enterprise for the user according to the resume data and the recruitment information, so as to obtain the two-way evaluation features between the user and the enterprise, and further can determine the two-way evaluation result between the user and the enterprise according to the first feature and the second feature.

[0087] In an optional implementation manner, the electronic device can perform standardization processing on the extracted features to obtain the standardized features.

[0088] Among them, the standardization processes for different features are also different. For example, the similarity between resume data and recruitment information can be determined as a feature, and this feature can be directly used as the standardized feature.

[0089] For another example, for the educational background features extracted by the user, the user's educational background and school can be encoded in the form of one-hot encoding. Usually, a student has at most three experiences of undergraduate, master, and doctorate, and then the school categories can be divided into five levels: Tsinghua and Peking Universities, C9, 985, 211, and others. A 3*5 = 15-dimensional 0-1 vector is generated. For example, if a user graduated with a master's degree, the undergraduate degree was from a 985 school, and the master's degree was from Tsinghua University, then his representation is [0,0,1,0,0,1,0,0,0,0,0,0,0,0,0]. The 1 in the third position represents the undergraduate 985, and the 1 in the 6th dimension represents the master's degree from Tsinghua and Peking Universities.

[0090] Specifically, among the standardized features, the evaluation features of the user for the enterprise and the evaluation features of the enterprise for the user can be screened out. The evaluation features of the user for the enterprise can be processed to obtain the first feature. For example, these features can be concatenated to obtain the first feature. The evaluation features of the enterprise for the user can also be processed to obtain the second feature. For example, these features can be concatenated to obtain the second feature.

[0091] By standardizing the extracted features and then determining the first feature and the second feature, the first feature and the second feature are also standardized features, so that the first feature and the second feature can be calculated to obtain the two-way evaluation results between the enterprise and the user.

[0092] Furthermore, the key standardized features include any one of the following:

[0093] The cosine similarity between resume data and recruitment information;

[0094] The educational background feature vector of the user; the educational background feature vector is used to represent the educational background of the user at each stage;

[0095] The employee composition vector, which is used to represent the employee composition information of the enterprise.

[0096] Among them, in the solution provided by the present disclosure, various types of features can be obtained, so that features from multiple angles can be extracted, and then the first feature and the second feature for the mutual evaluation between the user and the enterprise from multiple angles can be obtained.

[0097] Step 204: Determine the product of the first weight and the first feature as the first parameter value of the user for the enterprise; determine the product of the second weight and the second feature as the second parameter value of the user for the enterprise; the first parameter value is used to represent the matching degree of the user for the enterprise, and the second parameter value is used to represent the matching degree of the enterprise for the user.

[0098] In practical applications, the electronic device may use the product of the first weight and the first feature as the first parameter value. The first weight is used to determine the user's evaluation result of the enterprise. Through the first weight, the first feature of the user for the enterprise can be processed to determine which information of the enterprise the user pays more attention to.

[0099] The electronic device may use the product of the second weight and the second feature as the second parameter value. The second weight is used to determine the enterprise's evaluation result of the user. Through the second weight, the second feature of the enterprise for the user can be processed to determine which information of the user the enterprise pays more attention to.

[0100] In this way, a two-way evaluation result between the enterprise and the user can be obtained, and then the enterprise can make recruitment decisions based on these evaluation results to improve recruitment efficiency.

[0101] Step 205: Generate and send recommendation information according to the first parameter and the second parameter.

[0102] Among them, after the electronic device generates the first parameter and the second parameter, it can also generate recommendation information. If the user terminal executes the method provided by the present disclosure, the user terminal can directly display the generated recommendation information. If the server executes the method provided by the present disclosure, the server can send the recommendation information to the user terminal.

[0103] The recommendation information may include, for example, the result of whether the user matches the enterprise, and may also include the user's evaluation result of the enterprise, the enterprise's evaluation result of the user, etc.

[0104] Through this implementation manner, the employees in the enterprise responsible for personnel management can timely understand the two-way evaluation result between the user and the enterprise, and then assist the enterprise in making recruitment decisions.

[0105] In an optional implementation manner, the terminal device of the enterprise may send the resume information of multiple users and the recruitment information of the enterprise to the server. Then the server can determine the first parameter and the second parameter of each user and the enterprise, and then determine the two-way evaluation result between the enterprise and the user, and further obtain the users matching the enterprise. In this implementation manner, the server can send recommendation information to the terminal device of the enterprise, and the recommendation information may include the user information of the users matching the enterprise.

[0106] In another alternative embodiment, the user's terminal device may send the user's resume information and the recruitment information of multiple enterprises to the server. Then, the server may determine the first parameter and the second parameter of the user and each enterprise, and then determine the two-way evaluation result between the enterprise and the user, and further obtain the enterprises matching the user. In this embodiment, the server may send recommendation information to the user's terminal device, and the recommendation information may include the enterprise information of the enterprises matching the user.

[0107] Through this embodiment, the server may, according to the information sent by the terminal device, feedback the recommendation information corresponding to the information to the terminal device, so as to send the user information of the users matching the enterprise to the terminal device of the enterprise in a targeted manner, and may also send the enterprise information of the enterprises matching the user to the terminal device of the user in a targeted manner, enabling the personnel in the enterprise responsible for human resources management to directly understand the information of the personnel who may receive the admission notice, and also enabling the user to directly understand the information of the enterprises that may send the admission notice to themselves.

[0108] Figure 3 Schematic flow diagram of the method for determining weights between a user and an enterprise shown in an exemplary embodiment of the present disclosure.

[0109] As Figure 3 shown, the method for determining weights between a user and an enterprise provided by the present disclosure includes:

[0110] Step 301, obtain a training data set, the first weight of the user for the enterprise to be trained, and the second weight of the enterprise for the user to be trained; wherein, the training data set includes the user's resume data, the enterprise's recruitment information, the true admission records of the enterprise sending admission notices to the user, and the true acceptance records of the user accepting the enterprise's admission notices.

[0111] Among them, the method provided by the present disclosure may be executed by an electronic device with computing capabilities. The electronic device may use the training data set to train the first weight and the second weight, and the first weight and the second weight may be applied in the Figure 1 、 2 shown solutions.

[0112] Specifically, the training data set may include the user's resume data, the enterprise's recruitment information, the true admission records of the enterprise sending admission notices to the user, and the true acceptance records of the user accepting the enterprise's admission notices.

[0113] Furthermore, the training data set may include the resume data of multiple users and may also include the recruitment information of multiple enterprises. These data may be the data actually published on the recruitment platform.

[0114] In actual application, the training dataset may also include real admission records of enterprises sending admission notices to users. For example, if the training dataset includes recruitment information of enterprises A, B, and C, and also includes resume data of users A, B, and C, then the real admission records may include that A sends an admission notice to A, and may also include the record that B sends an admission notice to B.

[0115] Among them, the training dataset may also include real acceptance records. For example, it may include the records that A accepts the admission notice from A, and B accepts the admission notice from B.

[0116] Specifically, the real admission records and real acceptance records can be used as label data for the training process, and the first weight and the second weight can be optimized by using the real admission records and real acceptance records.

[0117] Furthermore, the first weight and the second weight can be preset, and the first weight and the second weight can be optimized by using the training dataset. Through iterative optimization, the first weight and the second weight that meet the conditions can be obtained.

[0118] Step 302, according to the first weight, the second weight, the resume data, and the recruitment information, predict the predicted admission record of the enterprise sending an admission notice to the user, and the predicted acceptance record of the user accepting the admission notice of the enterprise.

[0119] In actual application, the electronic device can process the resume data and the recruitment information, extract the features in the resume data and the recruitment information, and process the extracted features by using the current first weight and the second weight to obtain the two-way evaluation results between the enterprise and the user. For example, the two-way evaluation results between enterprise A and user A, between enterprise A and user B, between enterprise A and user C can be obtained, and the two-way evaluation results between enterprise B and user A can also be obtained, etc.

[0120] Among them, the electronic device can determine the predicted admission record and the predicted acceptance record according to the determined two-way evaluation results between the enterprise and the user.

[0121] Specifically, the predicted admission record is used to represent the information of the predicted enterprise sending an admission notice to the user, and the predicted acceptance record is used to represent the information of the predicted user accepting the admission notice of the enterprise. For example, it is predicted that enterprise A will send an admission notice to user A, and for another example, it is predicted that A does not accept the admission notice from enterprise A.

[0122] In actual application, for each combination of each enterprise and each user, it can be predicted whether the enterprise will send an admission notice to the user, and it can also be predicted whether the user will accept the admission notice of the user.

[0123] Step 303: Optimize the first weight and the second weight according to the true admission record, true acceptance record, predicted admission record, and predicted acceptance record; the optimized first weight and second weight that meet the preset conditions are used to determine the matching degree between the user and the enterprise.

[0124] Further, the electronic device can compare the true admission record with the predicted admission record, and can also compare the true acceptance record with the predicted acceptance record, so as to optimize the first weight and the second weight according to the comparison results.

[0125] In practical applications, the true admission record and the true acceptance record can be used as labeled data, so that it can be determined whether the result predicted by the electronic device is accurate based on this labeled data. If not, the first weight and the second weight can be optimized based on the difference between the labeled data and the predicted result.

[0126] Among them, a preset condition can also be set. When the optimized first weight and second weight meet this preset condition, the iteration can be stopped to obtain the first weight and the second weight that can be applied in the Figure 1 and Figure 2 The method shown is used to determine the matching degree between the user and the enterprise.

[0127] Figure 4 This is a schematic flowchart of the method for determining weights between a user and an enterprise shown in another exemplary embodiment of the present disclosure.

[0128] As Figure 4 shown, the method for determining weights between a user and an enterprise provided by the present disclosure includes:

[0129] Step 401: Obtain a training data set, the first weight of the user for the enterprise to be trained, and the second weight of the enterprise for the user to be trained; among them, the training data set includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise.

[0130] The implementation manner of step 401 is similar to that of step 301 and will not be elaborated here.

[0131] Step 402: Determine the first feature of the user for the enterprise and the second feature of the enterprise for the user according to the resume data and the recruitment information.

[0132] Among them, the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user.

[0133] Specifically, the electronic device can extract key features according to the resume data and the recruitment information; then determine the first feature of the user for the enterprise and the second feature of the enterprise for the user from the key features.

[0134] Among them, the resume data includes a lot of information, and the recruitment information also includes a lot of information. Therefore, a large number of features can be extracted from the resume data and the recruitment information.

[0135] For example, the educational background feature, work experience feature, job hunting intention feature, etc. of the user can be extracted from the resume data. For another example, the department composition information of the enterprise, the job demand feature of the enterprise, etc. can be extracted from the recruitment information.

[0136] Specifically, based on the large number of extracted features, the first feature of the user for the enterprise and the second feature of the enterprise for the user can be determined. Among them, the first feature is used to represent the evaluation information of the user for the enterprise, and the second feature is used to represent the evaluation information of the enterprise for the user.

[0137] Furthermore, the electronic device can screen out the evaluation features of the user for the enterprise from the large number of extracted features, and determine the first feature according to these features. It can also screen out the evaluation features of the enterprise for the user and determine the second feature according to these features.

[0138] In an alternative embodiment, the electronic device can perform normalization processing on the extracted features to obtain the normalized features.

[0139] Among them, the normalization processing process for different features is also different. For example, the similarity between the resume data and the recruitment information can be determined as a feature, and this feature can be directly used as the normalized feature.

[0140] For another example, for the educational background feature extracted by the user, the educational background and school of the user can be encoded in the form of one-hot encoding. Usually, a student has at most three experiences of undergraduate, master, and doctorate, and then the school categories can be divided into five categories: Tsinghua and Peking Universities, C9, 985, 211, and others. Then a 3*5 = 15-dimensional 0-1 vector is generated. For example, if a user graduates with a master's degree, the undergraduate degree is from a 985 school, and the master's degree is from Tsinghua University, then his representation is [0,0,1,0,0,1,0,0,0,0,0,0,0,0,0]. The 1 in the third position represents the undergraduate 985, and the 1 in the 6th dimension represents the master's degree from Tsinghua and Peking Universities.

[0141] Specifically, the evaluation features of the user for the enterprise and the evaluation features of the user for the enterprise can be screened out from the normalized features. The evaluation features of the user for the enterprise can be processed to obtain the first feature. For example, these features can be concatenated to obtain the first feature. The evaluation features of the enterprise for the user can also be processed to obtain the second feature. For example, these features can be concatenated to obtain the second feature.

[0142] Furthermore, the key normalized features include any one of the following:

[0143] Cosine similarity between resume data and recruitment information;

[0144] Educational characteristics vector of the user; the educational characteristics vector is used to characterize the educational status of the user at each stage;

[0145] Employee composition vector, which is used to characterize the employee composition information of the enterprise.

[0146] Step 403: Determine the first parameter value of the user for the enterprise according to the first weight and the first feature; determine the second parameter value of the enterprise for the user according to the second weight and the second feature.

[0147] Among them, the first parameter value is used to characterize the matching degree of the user for the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise for the user.

[0148] Specifically, the electronic device can generate the first parameter value and the second parameter value by using the current first weight and the second weight. Specifically, the product of the first weight and the first feature can be determined as the first parameter value of the user for the enterprise, and the product of the second weight and the second feature can be determined as the second parameter value of the user for the enterprise.

[0149] The current first weight is used to predict the evaluation result of the user for the enterprise. Through the first weight, the first feature of the user for the enterprise can be processed, so as to predict which information of the enterprise the user pays more attention to.

[0150] The current second weight is used to predict the evaluation result of the enterprise for the user. Through the second weight, the second feature of the enterprise for the user can be processed, so as to predict which information of the user the enterprise pays more attention to.

[0151] Step 404: Predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first parameter value and the second parameter value.

[0152] Among them, the electronic device can predict whether the enterprise will send an admission notice to the user according to the matching degree of the user for the enterprise and the matching degree of the enterprise for the user, so as to obtain the predicted admission record, and can also predict whether the user will accept the admission notice of the enterprise, so as to obtain the predicted acceptance record.

[0153] For example, if the first parameter value is large, it means that the user has a high evaluation of the enterprise, and this user will accept the admission notice of the enterprise. If the second parameter value is large, it means that the enterprise has a high evaluation of the user, and this enterprise will send an admission notice to the user. Based on this, the prediction result can be obtained.

[0154] Further, the matching result between the user and the enterprise can be determined according to the first parameter values of each user for each enterprise and the second parameter values of each enterprise for each user.

[0155] Specifically, the matching result between the user and the enterprise can also be determined by the Gale-Shapley algorithm.

[0156] The Gale-Shapley algorithm, abbreviated as the "GS algorithm" and also known as the "deferred-acceptance algorithm", is a market mechanism designed by Gale and Shapley to find a stable matching. This algorithm can determine the combination of stable matches based on the information of each object Ai on one side of the market and the information of each object Bj on the other side.

[0157] Further, through the Gale-Shapley algorithm, the matching result between the user and the enterprise can be obtained. For example, which enterprises will send admission notices to which users and which users will accept the admission notices sent by which enterprises.

[0158] In actual application, the electronic device can also predict the predicted admission record of the enterprise sending the admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the matching result. Specifically, the predicted admission record can be generated according to the information in the matching result about which enterprises will send admission notices to which users. The predicted acceptance record can also be generated according to the information in the matching result about which users will accept the admission notices of which enterprises.

[0159] Step 405, determine the first loss function according to the real admission record and the predicted admission record.

[0160] Among them, the electronic device can determine the first loss function according to the real admission record and the predicted admission record. The first loss function is used to characterize the loss function in the link of the enterprise sending the admission notice to the user.

[0161] Specifically, the first loss function

[0162] Further, refers to the user who has received the admission notice from department d j but actually has not received it; is the user who has actually received the admission notice from enterprise d j but is predicted not to receive it. respectively represent the second parameter values of d j for and .

[0163] Step 406: Determine the second loss function according to the true acceptance record and the predicted acceptance record.

[0164] In practical applications, the electronic device can determine the second loss function according to the true acceptance record and the predicted acceptance record. The second loss function is used to characterize the loss function in the link of accepting the admission notice sent by the enterprise.

[0165] Second loss function

[0166] Among them, is the enterprise for which it is predicted that user u i received the notice record but actually did not receive it; is the enterprise for which it is actually the case that user u i received the notice record but was predicted not to receive it. respectively represent the first parameter values of u i for and .

[0167] Step 407: Optimize the first weight and the second weight according to the first loss function and the second loss function.

[0168] Specifically, the electronic device can optimize the current first weight and second weight according to the first loss function and the second loss function to obtain the optimized first weight and second weight.

[0169] Furthermore, the electronic device can perform gradient backpropagation according to the first loss function and the second loss function, thereby optimizing the first weight and the second weight.

[0170] In practical applications, the electronic device can determine the total loss function according to the first loss function and the second loss function, and then optimize the first weight and the second weight based on the total loss function.

[0171] Among them, the total loss function loss = γ·loss sending +(1 - γ)·loss accepting

[0172] where γ is a hyperparameter.

[0173] In an alternative implementation, during each training iteration, the matching result between the user and the enterprise can be determined according to the first parameter and the second parameter. In this implementation, the condition for stopping the training iteration can include: the currently determined matching result is the same as the matching result determined in the previous time.

[0174] For example, if the matching result determined in the nth iteration is the same as the matching result determined in the (n + 1)th iteration, the electronic device can stop the iteration and no longer optimize the first weight and the second weight.

[0175] Figure 5 Schematic diagram of the process for training weights shown in an exemplary embodiment of the present disclosure.

[0176] As Figure 5 shown, the electronic device can obtain the recruitment information 51 of the enterprise, and can also obtain the resume data 52 of the user, extract features based on the recruitment information 51 and the resume data 52, and then obtain the first feature 53 and the second feature 54.

[0177] Among them, the electronic device can also determine a first parameter value 57 and a second parameter value 58 respectively according to the features 53, 54 and the current first weight 55 and second weight 56, so as to stably match the user and the enterprise according to the first parameter value and the second parameter value.

[0178] Specifically, the electronic device can obtain a prediction result 59 according to the first parameter value 57 and the second parameter value 58, and then construct a loss function 61 according to the prediction result 59 and the true result 60, and further optimize the first weight 54 and the second weight 55 based on the loss function 61. The true result 60 can include true admission records and true acceptance records.

[0179] Figure 6 Schematic diagram of the structure of a device for determining matching parameters between a user and an enterprise shown in an exemplary embodiment of the present disclosure.

[0180] The device 600 for determining matching parameters between a user and an enterprise provided by the present disclosure includes:

[0181] An acquisition unit 610, configured to acquire the resume data of the user and the recruitment information of the enterprise;

[0182] A feature determination unit 620, configured to determine a first feature and a second feature according to the resume data and the recruitment information, where the first feature is used to characterize the evaluation information of the user on the enterprise, and the second feature is used to characterize the evaluation information of the enterprise on the user;

[0183] A parameter determination unit 630, configured to determine a first parameter value according to a preset first weight of the user on the enterprise and the first feature; determine a second parameter value according to a preset second weight of the enterprise on the user and the second feature, where the first parameter value is used to characterize the matching degree of the user to the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise to the user;

[0184] The first parameter value and the second parameter value are used to determine the matching result between the user and the enterprise.

[0185] Figure 7 Schematic diagram of the structure of a device for determining matching parameters between a user and an enterprise shown in another exemplary embodiment of the present disclosure.

[0186] The determination device 700 for the matching parameters between users and enterprises provided by the present disclosure, wherein, Figure 7 the obtaining unit 710 in is similar to Figure 6 the obtaining unit 610 in, the feature determination unit 720 is similar to the feature determination unit 620, and the parameter determination unit 730 is similar to Figure 6 the parameter determination unit 630 in.

[0187] Among them, the feature determination unit 720 includes:

[0188] A feature extraction module 721, configured to extract features from the resume data and the recruitment information;

[0189] A feature determination module 722, configured to determine a first feature of the user for the enterprise and a second feature of the enterprise for the user according to the features.

[0190] Optionally, the feature determination module 722 is specifically configured to:

[0191] Perform normalization processing on the features to obtain normalized features;

[0192] Determine the first feature and the second feature according to the normalized features.

[0193] Optionally, the normalized key features include any one of the following:

[0194] The cosine similarity between the resume data and the recruitment information;

[0195] The educational background feature vector of the user; the educational background feature vector is used to characterize the educational background of the user at each stage;

[0196] The employee composition vector, and the employee composition vector is used to characterize the employee composition information of the enterprise.

[0197] Optionally, the parameter determination unit 730 includes:

[0198] A first parameter determination module 731, configured to determine the product of the first weight and the first feature as the first parameter value of the user for the enterprise;

[0199] The parameter determination unit 730 includes:

[0200] A second parameter determination module 732, configured to determine the product of the second weight and the second feature as the second parameter value of the user for the enterprise.

[0201] Optionally, the device further includes: a recommendation unit 740, configured to generate and send recommendation information according to the first parameter and the second parameter.

[0202] If the recommendation information represents user information of a user matching the enterprise, the recommendation unit 740 is specifically configured to: send the recommendation information to the terminal device of the enterprise;

[0203] Or, if the recommendation information represents enterprise information of an enterprise matching the user, the recommendation unit 740 is specifically configured to: send the recommendation information to the terminal device of the user.

[0204] Figure 8 FIG. is a schematic structural diagram of a weight determination device between a user and an enterprise according to an exemplary embodiment of the present disclosure.

[0205] As Figure 8 shown, the weight determination device 800 between a user and an enterprise provided by the present disclosure includes:

[0206] An acquisition unit 810, configured to acquire a training data set, a first weight of a user for an enterprise to be trained, and a second weight of the enterprise for the user to be trained; wherein, the training data set includes resume data of the user, recruitment information of the enterprise, a true admission record of the enterprise sending an admission notice to the user, and a true acceptance record of the user accepting the admission notice of the enterprise;

[0207] A prediction unit 820, configured to predict a predicted admission record of the enterprise sending an admission notice to the user and a predicted acceptance record of the user accepting the admission notice of the enterprise according to the first weight, the second weight, the resume data, and the recruitment information;

[0208] A training unit 830, configured to optimize the first weight and the second weight according to the true admission record, the true acceptance record, the predicted admission record, and the predicted acceptance record;

[0209] The optimized first weight and second weight that meet the preset conditions are used to determine the matching degree between the user and the enterprise.

[0210] Figure 9 FIG. is a schematic structural diagram of a weight determination device between a user and an enterprise according to another exemplary embodiment of the present disclosure.

[0211] As Figure 9 shown, in the weight determination device 900 between a user and an enterprise provided by the present disclosure, the acquisition unit 910 is similar to Figure 8 the acquisition unit 810 shown in Figure 8Similar to the prediction unit 820 shown in Figure 8 the training unit 930 is similar to the training unit 830 shown in

[0212] Based on the embodiment shown in Figure 8 the prediction unit 920 includes:

[0213] A feature determination module 921, configured to determine a first feature of the user for the enterprise and a second feature of the enterprise for the user according to the resume data and the recruitment information;

[0214] A parameter determination module 922, configured to determine a first parameter value of the user for the enterprise according to the first weight and the first feature; determine a second parameter value of the enterprise for the user according to the second weight and the second feature;

[0215] A prediction module 923, configured to predict a predicted admission record of the enterprise sending an admission notice to the user and a predicted acceptance record of the user accepting the admission notice of the enterprise according to the first parameter value and the second parameter value.

[0216] Wherein, the feature determination module 921 is specifically configured to:

[0217] Extract features according to the resume data and the recruitment information;

[0218] Determine a first feature of the user for the enterprise and a second feature of the enterprise for the user from the features.

[0219] Wherein, the feature determination module 921 is specifically configured to:

[0220] Perform normalization processing on the features to obtain normalized features;

[0221] Determine the first feature and the second feature according to the normalized features.

[0222] Optionally, in the device, the parameter determination module 922 is specifically configured to:

[0223] Determine the product of the first weight and the first feature as the first parameter value of the user for the enterprise;

[0224] Determine the product of the second weight and the second feature as the second parameter value of the user for the enterprise.

[0225] Wherein, the prediction module 923 is specifically configured to:

[0226] Determine a matching result between the user and the enterprise according to the first parameter values of each user for each enterprise and the second parameter values of each enterprise for each user;

[0227] Predict a predicted admission record in which the enterprise sends an admission notice to the user according to the matching result, and a predicted acceptance record in which the user accepts the admission notice of the enterprise.

[0228] Among them, the preset conditions include:

[0229] The currently determined matching result is the same as the previously determined matching result.

[0230] Among them, the training unit 930 includes:

[0231] The first function determination module 931 is used to determine a first loss function according to the true admission record and the predicted admission record;

[0232] The second function determination module 932 is used to determine a second loss function according to the true acceptance record and the predicted acceptance record;

[0233] The optimization module 933 is used to optimize the first weight and the second weight according to the first loss function and the second loss function.

[0234] The present disclosure provides a method for determining matching parameters between a user and an enterprise, an electronic device, and a program product, which are applied to the deep learning technology in artificial intelligence technology to more accurately assist enterprises in formulating recruitment decisions.

[0235] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information and other processes all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0236] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0237] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which includes: a computer program, the computer program is stored in a readable storage medium, at least one processor of the electronic device can read the computer program from the readable storage medium, and at least one processor executes the computer program to enable the electronic device to execute the solution provided in any of the above embodiments.

[0238] Figure 10FIG. shows a schematic block diagram of an exemplary electronic device 1000 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0239] As Figure 10 shown, the device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0240] A plurality of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a magnetic disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0241] The computing unit 1001 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 executes the various methods and processes described above, such as the method for determining the matching parameters between a user and an enterprise or the method for determining the weight between a user and an enterprise. For example, in some embodiments, the method for determining the matching parameters of the matching result between a user and an enterprise or the method for determining the weight between a user and an enterprise can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method for determining the matching parameters of the matching result between a user and an enterprise or the method for determining the weight between a user and an enterprise described above can be executed. Alternatively, in other embodiments, the computing unit 1001 can be configured to execute the method for determining the matching parameters of the matching result between a user and an enterprise or the method for determining the weight between a user and an enterprise by any other suitable means (e.g., by means of firmware).

[0242] The various embodiments of the systems and techniques described above in this article can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0243] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing devices, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0244] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0245] In order to provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and the input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0246] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend, middleware, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), and the Internet.

[0247] A computer system can include a client and a server. The client and the server are generally remote from each other and typically interact via a communication network. The client - server relationship is created by computer programs running on the respective computers and having a client - server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services ("Virtual Private Server", or simply "VPS"). The server can also be a server of a distributed system, or a server combined with blockchain.

[0248] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this is not limited herein.

[0249] The above - mentioned specific implementation manners do not constitute a limitation on the protection scope of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub - combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the protection scope of this disclosure.

Claims

1. A method for determining matching parameters between a user and an enterprise, comprising: Obtaining the resume data of the user and the recruitment information of the enterprise; Extracting a plurality of features from the resume data and the recruitment information, and determining a first feature and a second feature from the plurality of features, wherein the first feature is used to characterize the evaluation information of the user on the enterprise, and the second feature is used to characterize the evaluation information of the enterprise on the user; the first feature includes the composition of employees in the department; the second feature includes the interview score; Determining a first parameter value according to a preset first weight of the user on the enterprise and the first feature; determining a second parameter value according to a preset second weight of the enterprise on the user and the second feature, the first parameter value characterizes the matching degree of the user to the enterprise, and the second parameter value characterizes the matching degree of the enterprise to the user; the first weight and the second weight are obtained through machine learning technology training, and the training data includes the resume data of the user, the recruitment information of the enterprise, the true recruitment record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise; If the first parameter value is greater than a first threshold and the second parameter value is greater than a second threshold, it is determined that the user and the enterprise match.

2. The method according to claim 1, wherein The determining the first feature and the second feature includes: Extracting features from the resume data and the recruitment information; According to the features, determining the first feature of the user on the enterprise and the second feature of the enterprise on the user.

3. The method according to claim 2, wherein, The according to the features, determining the first feature of the user on the enterprise and the second feature of the enterprise on the user includes: Performing standardization processing on the features to obtain standardized features; Determining the first feature and the second feature according to the standardized features.

4. The method according to claim 3, wherein The standardized key features include any one of the following: The cosine similarity between the resume data and the recruitment information; The educational background feature vector of the user; the educational background feature vector is used to characterize the educational background of the user at each stage; The employee composition vector, which is used to characterize the employee composition information of the enterprise.

5. According to the method of claim 1, wherein, The determining the first parameter value of the user on the enterprise according to a preset first weight of the user on the enterprise and the first feature includes: Determining the product of the first weight and the first feature as the first parameter value of the user on the enterprise; The determining the second parameter value of the user on the enterprise according to a preset second weight of the enterprise on the user and the second feature includes: Determining the product of the second weight and the second feature as the second parameter value of the user on the enterprise.

6. According to the method of any one of claims 1-5, further comprising: Generating and sending a recommendation message according to the first parameter and the second parameter.

7. According to the method described in claim 6, where the recommended information represents user information of a user matching the enterprise, sending the recommended information includes: Sending the recommendation message to the terminal device of the enterprise; Or, if the recommendation message characterizes the enterprise information of the enterprise matching the user, sending the recommendation message includes: sending the recommendation message to the terminal device of the user.

8. A method for determining weights between a user and an enterprise, comprising: Obtain a training data set, a first weight of the user for the enterprise to be trained, and a second weight of the enterprise for the user to be trained; wherein, the training data set includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise; Predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first weight, the second weight, the resume data, and the recruitment information; Optimize the first weight and the second weight according to the true admission record, the true acceptance record, the predicted admission record, and the predicted acceptance record; Extract multiple features from the resume data and the recruitment information, and determine a first feature and a second feature from the multiple features, wherein the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user; the first feature includes the composition of department employees; the second feature includes the interview score; Determine a first parameter value according to the first weight and the first feature; determine a second parameter value according to the second weight and the second feature, the first parameter value characterizes the matching degree of the user for the enterprise, and the second parameter value characterizes the matching degree of the enterprise for the user; If the first parameter value is greater than a first threshold and the second parameter value is greater than a second threshold, it is determined that the user and the enterprise match.

9. The method according to claim 8, wherein The predicting the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first weight, the second weight, the resume data, and the recruitment information includes: Determine a first feature of the user for the enterprise and a second feature of the enterprise for the user according to the resume data and the recruitment information; Determine the first parameter value of the user for the enterprise according to the first weight and the first feature; determine the second parameter value of the enterprise for the user according to the second weight and the second feature; Predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first parameter value and the second parameter value.

10. The method according to claim 9, wherein, The determining a first feature of the user for the enterprise and a second feature of the enterprise for the user according to the resume data and the recruitment information includes: Extract features from the resume data and the recruitment information; Determine a first feature of the user for the enterprise and a second feature of the enterprise for the user among the features.

11. The method according to claim 10, wherein, The determining a first feature of the user for the enterprise and a second feature of the enterprise for the user among the features includes: Perform standardization processing on the features to obtain standardized features; Determine the first feature and the second feature according to the standardized features.

12. According to the method of claim 9, wherein, The determining the first parameter value of the user for the enterprise according to the first weight and the first feature includes: Determine the product of the first weight and the first feature as the first parameter value of the user for the enterprise; The determining the second parameter value of the enterprise for the user according to the second weight and the second feature includes: Determine the product of the second weight and the second feature as the second parameter value of the user for the enterprise.

13. The method according to claim 9, wherein, The predicting the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first parameter value and the second parameter value includes: Determine the matching result between the user and the enterprise according to the first parameter values of each user for each enterprise and the second parameter values of each enterprise for each user; Predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the matching result.

14. The method according to any one of claims 8 - 13, wherein, The optimizing the first weight and the second weight according to the true admission record, the true acceptance record, the predicted admission record and the predicted acceptance record includes: Determine a first loss function according to the true admission record and the predicted admission record; Determine a second loss function according to the true acceptance record and the predicted acceptance record; Optimize the first weight and the second weight according to the first loss function and the second loss function.

15. A device for determining matching parameters between a user and an enterprise, comprising: An acquisition unit, configured to acquire the resume data of a user and the recruitment information of an enterprise; A feature determination unit, configured to extract a plurality of features from the resume data and the recruitment information, and determine a first feature and a second feature from the plurality of features, wherein the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user; the first feature includes the composition of department employees; the second feature includes the interview score; A parameter determination unit, configured to determine a first parameter value according to a preset first weight of the user for the enterprise and the first feature; determine a second parameter value according to a preset second weight of the enterprise for the user and the second feature, where the first parameter value is used to characterize the matching degree of the user for the enterprise, and the second parameter value is used to characterize the matching degree of the enterprise for the user; the first weight and the second weight are obtained through machine learning technology, and the training data includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise; If the first parameter value is greater than a first threshold and the second parameter value is greater than a second threshold, it is determined that the user and the enterprise are matched.

16. The apparatus according to claim 15, wherein, The feature determination unit includes: A feature extraction module, configured to extract features from the resume data and the recruitment information; A feature determination module, configured to determine a first feature of the user for the enterprise and a second feature of the enterprise for the user according to the features.

17. The apparatus according to claim 16, wherein, The feature determination module is specifically configured to: Perform normalization processing on the features to obtain the normalized features; Determine the first feature and the second feature according to the standardized features.

18. The apparatus according to claim 17, wherein, The standardized key features include any one of the following: The cosine similarity between the resume data and the recruitment information; The educational background feature vector of the user; the educational background feature vector is used to characterize the educational background of the user at each stage; The employee composition vector, which is used to characterize the employee composition information of the enterprise.

19. The apparatus according to claim 15, wherein The parameter determination unit includes: The first parameter determination module is configured to determine the product of the first weight and the first feature as the first parameter value of the user for the enterprise; The parameter determination unit includes: The second parameter determination module is configured to determine the product of the second weight and the second feature as the second parameter value of the user for the enterprise.

20. The device according to any one of claims 15 - 19, further comprising: The recommendation unit is configured to generate and send a recommendation message according to the first parameter and the second parameter.

21. The apparatus according to claim 20, wherein if the recommendation message represents the user information of the user matching the enterprise, the recommendation unit is specifically configured to: send the recommendation message to the terminal device of the enterprise; Or, if the recommendation message represents the enterprise information of the enterprise matching the user, the recommendation unit is specifically configured to: send the recommendation message to the terminal device of the user.

22. A weight determination apparatus between a user and an enterprise, comprising: An acquisition unit, configured to acquire a training data set, a first weight of the user for the enterprise to be trained, and a second weight of the enterprise for the user to be trained; wherein, the training data set includes the resume data of the user, the recruitment information of the enterprise, the true admission record of the enterprise sending an admission notice to the user, and the true acceptance record of the user accepting the admission notice of the enterprise; A prediction unit, configured to predict the predicted admission record of the enterprise sending an admission notice to the user and the predicted acceptance record of the user accepting the admission notice of the enterprise according to the first weight, the second weight, the resume data, and the recruitment information; A training unit, configured to optimize the first weight and the second weight according to the true admission record, the true acceptance record, the predicted admission record, and the predicted acceptance record; Extract a plurality of features from the resume data and the recruitment information, and determine a first feature and a second feature from the plurality of features, wherein the first feature is used to characterize the evaluation information of the user for the enterprise, and the second feature is used to characterize the evaluation information of the enterprise for the user; the first feature includes the department employee composition; the second feature includes the interview score; Determine a first parameter value according to the first weight and the first feature; determine a second parameter value according to the second weight and the second feature, the first parameter value characterizes the matching degree of the user for the enterprise, and the second parameter value characterizes the matching degree of the enterprise for the user; If the first parameter value is greater than the first threshold and the second parameter value is greater than the second threshold, it is determined that the user and the enterprise match.

23. The apparatus according to claim 22, wherein, The prediction unit includes: A feature determination module, configured to determine a first feature of the user with respect to the enterprise and a second feature of the enterprise with respect to the user according to the resume data and the recruitment information; A parameter determination module, configured to determine a first parameter value of the user with respect to the enterprise according to the first weight and the first feature; and determine a second parameter value of the enterprise with respect to the user according to the second weight and the second feature; A prediction module, configured to predict a predicted admission record of the enterprise sending an admission notice to the user and a predicted acceptance record of the user accepting the admission notice of the enterprise according to the first parameter value and the second parameter value.

24. The apparatus according to claim 23, wherein, The feature determination module is specifically configured to: Extract features according to the resume data and the recruitment information; Determine a first feature of the user with respect to the enterprise and a second feature of the enterprise with respect to the user from the features.

25. The apparatus according to claim 24, wherein The feature determination module is specifically configured to: Perform normalization processing on the features to obtain normalized features; Determine the first feature and the second feature according to the normalized features.

26. The apparatus according to claim 23, wherein, The parameter determination module is specifically configured to: Determine the product of the first weight and the first feature as the first parameter value of the user with respect to the enterprise; Determine the product of the second weight and the second feature as the second parameter value of the user with respect to the enterprise.

27. The device according to claim 23, wherein, The prediction module is specifically configured to: Determine a matching result between the user and the enterprise according to the first parameter values of each user with respect to each enterprise and the second parameter values of each enterprise with respect to each user; Predict a predicted admission record of the enterprise sending an admission notice to the user and a predicted acceptance record of the user accepting the admission notice of the enterprise according to the matching result.

28. The apparatus according to any one of claims 22 - 27, wherein, The training unit includes: A first function determination module, configured to determine a first loss function according to the true admission record and the predicted admission record; A second function determination module, configured to determine a second loss function according to the true acceptance record and the predicted acceptance record; An optimization module, configured to optimize the first weight and the second weight according to the first loss function and the second loss function.

29. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1-15.

30. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-14.

31. A computer program product, comprising a computer program, which when executed by a processor implements the steps of the method according to any one of claims 1-14.

Images