Position recommendation method and device, electronic equipment, readable medium and program product

Abstract

The embodiment provides a position recommendation method and device, electronic equipment and a computer readable storage medium, and relates to the field of big data. The method comprises the following steps: obtaining job-seeking information of a target user; determining a first position category to which the job-seeking information belongs; determining a second position category which has an association relationship with the first position category; and determining a to-be-recommended position according to the first position category and the second position category. The embodiment avoids recommending only positions containing the literal meaning of the keywords to the user, and can recommend comprehensive positions meeting the requirements of the user to the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data, in particular, the present application relates to a position recommendation method and device, electronic equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the rapid development of computer network technology, more and more job seekers and recruiters begin to use the Internet for online job hunting or online recruitment, which can greatly realize the talent exchange in today's society. As a third-party platform, the recruitment website and recruitment APP provide such an exchange platform for job seekers and recruiters.

[0003] The existing scheme recommends positions to users according to the set position keywords of the user to match the recruitment information corresponding to the position, and then determines the display order or display position of the recruitment information of each recruiter according to the publication time of the recruitment information, the activity of the recruiter corresponding to the recruitment information and the keyword matching degree, and then recommends the recruitment information to the user according to the display order or display position of each recruitment information, such as a job seeker user A searching for a "new media operation" position. After calculation in the background of the third-party platform, the recruitment information published by the recruiter recruiting "new media operation" is matched, and then the recruitment information of each recruiter is displayed to user A according to the activity of each recruiter, the publication time of the recruitment information and the keyword matching degree.

[0004] Obviously, the above-mentioned position recommendation has great limitations, such as user A searching for "new media operation", the search logic will only output positions containing "new", "media" and "operation" after segmentation, and positions such as WeChat operation and Weibo operation will not appear. However, the talents of these positions have basically the same portrait, so it can be seen that the recommended positions of the existing scheme are not comprehensive and the recommended positions are relatively narrow. SUMMARY

[0005] The embodiments of the present application provide a position recommendation method, device, electronic equipment, computer readable storage medium and computer program product, which can solve the problem of incomplete position recommendation. The technical scheme is as follows:

[0006] According to an aspect of an embodiment of the present application, a position recommendation method is provided, which comprises:

[0007] Obtaining the job seeking information of a target user;

[0008] Determining a first position category to which the job seeking information belongs;

[0009] Determining a second position category having an association relationship with the first position category;

[0010] determine the to-be-recommended positions according to the first position category and the second position category.

[0011] In a possible implementation, the first position category to which the job seeking information belongs is determined, including:

[0012] The job seeking information is input into a pre-established first position identification model to obtain a first position category output by the first position identification model; the first position identification model is trained by taking the job seeking information of a sample user as a training sample and taking the first position category to which the job seeking information of the sample user belongs as a training label.

[0013] In a possible implementation, the second position category having an association relationship with the first position category is determined, including:

[0014] The second position category having an association relationship with the first position category is determined from a pre-established position data dictionary; the position data dictionary includes each first position category and a second position category having an association relationship with each corresponding first position category.

[0015] In a possible implementation, the to-be-recommended positions are determined according to the first position category and the second position category, and the method further includes:

[0016] obtaining each recruitment position and position information corresponding to the recruitment position in a database;

[0017] inputting the position information of each recruitment position into a pre-established second position model to obtain a third position category output by the second position model; the second position model is trained by taking recruitment information of a sample recruitment position as a training sample and taking a third position category to which the sample recruitment position belongs as a training label;

[0018] establishing an association relationship between each recruitment position and the third position category corresponding to each recruitment position, and storing each recruitment position, the third position category corresponding to each recruitment position, and the association relationship between each recruitment position and the third position category in a database.

[0019] In a possible implementation, the to-be-recommended positions corresponding to the first position category and the second position category are respectively determined, and the method further includes:

[0020] finding a third position category identical to the first position category from the database, obtaining a recruitment position corresponding to the third position category from the database according to the third position category and the association relationship between the third position category and the recruitment position, and determining the recruitment position corresponding to the third position category as the to-be-recommended position corresponding to the first position category;

[0021] The third position category same as the second position category is searched from the database, the recruitment position corresponding to the third position category is obtained from the database according to the third position category and the association relationship between the third position category and the recruitment position, and the recruitment position corresponding to the third position category is determined as the to-be-recommended position corresponding to the second position category.

[0022] In a possible implementation, the to-be-recommended position is determined according to the first position category and the second position category, and then the method further includes:

[0023] The to-be-recommended position and the recruitment information of the to-be-recommended position are recommended to the target user.

[0024] In a possible implementation, the to-be-recommended position is recommended to the target user, and the method includes:

[0025] The recommendation order of each to-be-recommended position is determined.

[0026] The to-be-recommended position is recommended to the target user according to the recommendation order.

[0027] In a possible implementation, the recommendation order of each to-be-recommended position is determined, and the method includes:

[0028] At least one influence factor and an influence weight corresponding to each influence factor are obtained, the influence factor being a factor influencing the recommendation order of the to-be-recommended position.

[0029] The influence value of the at least one influence factor is calculated.

[0030] The recommendation order of each to-be-recommended position is determined according to the influence value of the at least one influence factor and the influence weight corresponding to each influence factor.

[0031] According to another aspect of the embodiments of the present application, a position recommendation device is provided, and the device includes:

[0032] The obtaining module is configured to obtain the job-hunting information of the target user.

[0033] The first position category determining module is configured to determine the first position category to which the job-hunting information belongs.

[0034] The second position category determining module is configured to determine the second position category having an association relationship with the first position category.

[0035] The to-be-recommended position determining module is configured to determine the to-be-recommended position according to the first position category and the second position category.

[0036] According to another aspect of the embodiments of the present application, an electronic device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method provided in the first aspect when executing the program.

[0037] According to still another aspect of the embodiments of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executable on a processor to implement the steps of the method provided in the first aspect.

[0038] According to still another aspect of the embodiments of the present application, a computer program product is provided, which comprises computer instructions stored in a computer readable storage medium, and the computer instructions are read by a processor of a computer device from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to implement the steps of the method provided in the first aspect.

[0039] The technical scheme provided by the embodiments of the present application has the beneficial effects that: the embodiments of the present application obtain the job seeking information of the target user, determine the first position category to which the job seeking information belongs, determine the second position category having an association relationship with the first position category, and determine the recommended position to be the recommended position according to the first position category and the second position category, thereby avoiding recommending only the positions containing the literal meaning of the keywords to the user, and being capable of recommending comprehensive positions meeting the requirements of the user to the user. BRIEF DESCRIPTION OF DRAWINGS

[0040] In order to more clearly illustrate the technical scheme in the embodiments of the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced.

[0041] Figure 1 A flowchart of a position recommendation method provided by the embodiments of the present application;

[0042] Figure 2 A first position category and a second position category having an association relationship with the first position category provided by the embodiments of the present application;

[0043] Figure 3 A schematic diagram of determining the third position category of each recruitment position provided by the embodiments of the present application;

[0044] Figure 4 A structural schematic diagram of a position recommendation device provided by the embodiments of the present application;

[0045] Figure 5 A structural schematic diagram of an electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0046] The embodiments of the present application will be described below in conjunction with the accompanying drawings. It should be understood that the embodiments described below in conjunction with the accompanying drawings are exemplary descriptions of the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions of the embodiments of the present application.

[0047] Those skilled in the art can understand that the singular forms "a", "an" and "the" used herein include plural forms unless specifically stated otherwise. It should be further understood that the terms "include" and "contain" used in the embodiments of the present application mean that the corresponding features can be implemented as the presented features, information, data, steps, operations, elements and / or components, but do not exclude other features, information, data, steps, operations, elements, components and / or their combinations supported by the present technology. It should be understood that when we say that an element is "connected" or "coupled" to another element, the element can be directly connected or coupled to the other element, or can mean that the element and the other element establish a connection relationship through an intermediate element. In addition, "connection" or "coupling" used herein can include wireless connection or wireless coupling. The term "and / or" used herein indicates at least one of the items defined by the term, for example, "A and / or B" indicates implementation as "A", or implementation as "A", or implementation as "A and B".

[0048] In order to make the purpose, technical solutions and advantages of the present application clearer, the embodiments of the present application will be described in further detail below in conjunction with the accompanying drawings.

[0049] Firstly, several terms related to the present application are introduced and explained:

[0050] Data dictionary refers to the definition and description of data items, data structures, data flow, data storage, processing logic, etc. The purpose is to make detailed explanations of all elements of the data flowchart. Use data dictionary for simple modeling project. In short, data dictionary is a collection of information describing data, which is a collection of definitions of all data elements used in the system.

[0051] Nowadays, online job hunting by job seekers and online recruitment of employees by employers have become mainstream. For job seekers, job seekers can fill in their resumes on recruitment websites or recruitment APPs, search for job keywords, and the recruitment website or recruitment APP as a third-party platform will recommend the recruitment information published by the employers to the user according to the keywords and resume information input by the job seeker, for example, the job seeker user A searches for "new media operation" as a position, and the third-party platform calculates in the back end and publishes the recruitment information of the employers who recruit "new media operation", and then displays the recruitment information of each employer to user A according to the activity of each employer, the time of publishing the recruitment information and the keyword matching degree.

[0052] It is obvious that the above-mentioned position recommendation has great limitations, such as user A searches for "new media operation", and the search logic will only output positions containing "new", "media" and "operation" after segmentation, and positions such as WeChat operation and Weibo operation will not appear. However, the three are only different in name, but the essence of the positions is the same. Therefore, it can be seen that the positions recommended by the existing scheme are not comprehensive, and the recommended positions are relatively narrow.

[0053] The position recommendation method, device, electronic equipment, computer readable storage medium and computer program product provided by the present application aim to solve the above technical problems of the prior art.

[0054] The technical solutions of the embodiments of the present application and the technical effects generated by the technical solutions of the present application will be described below through the description of several exemplary embodiments. It should be pointed out that the following embodiments can be mutually referenced, borrowed or combined. For the same terms, similar features and similar implementation steps in different embodiments, they will not be described repeatedly.

[0055] A position recommendation method is provided in the embodiments of the present application, as shown in Figure 1 The method comprises the following steps:

[0056] In step S101, the job search information of a target user is obtained.

[0057] The target user in the embodiments of the present application refers to a job seeker, that is, a user who intends to find a job online.

[0058] The job search information in the embodiments of the present application refers to the resume information of the target user, and the job search information of the target user is the basis for recommending positions to the target user, which can include the job search preference or intention of the target user, the work experience of the target user, etc. When the target user has a job search preference or intention, the job search preference or intention of the user can be taken as the core recommendation basis. When there is no job search preference or intention, the recent work experience of the target user can be taken as the core recommendation basis.

[0059] Specifically, for example, the job search information of user A includes: job search intention: software development; intended salary: 10000-12000; work experience:

[0060] Work experience 1:

[0061] Time: September 2010-June 2016

[0062] Company: A Company

[0063] Position: Java engineer

[0064] Description: Use Java for back-end development...

[0065] Work Experience 2: July 2016 - Present

[0066] Company: Company B

[0067] Position: Research and Development Supervisor

[0068] Description: Through...

[0069] In this embodiment of the application, the user's job application information is obtained after obtaining the user's authorization.

[0070] Step S102: Determine the first job category to which the job posting belongs.

[0071] In this embodiment of the application, after obtaining authorization from the target user, the job search information of the target user is obtained, and the first job category to which the job search information belongs is determined.

[0072] In this embodiment of the application, the first job category is obtained directly from the user's job search information. For example, if the user's job search intention is "Java development" and their work experience includes words such as "Java engineer", "Java developer", and "Java backend", the first job category can be determined as "Java" based on this job search information.

[0073] It should be emphasized that the first job category in this application embodiment refers to the job category to which the job application information of the target user belongs. The first job category is not the same as the job name, but may be the same as the job name.

[0074] Step S103: Determine the second job category that is related to the first job category.

[0075] In this embodiment of the application, the first job category is obtained directly from the job search information of the target user, and the second job category is a job category that is related to the first job category. The talent profile corresponding to the second job category has a high degree of similarity with the talent profile corresponding to the first job category. If the similarity between the talent profile corresponding to a certain job category and the talent profile corresponding to the first job category is higher than the preset similarity, then the job category can be determined to be a second job category that is related to the first job category.

[0076] like Figure 2 As shown, it exemplifies a first job category and a second job category that are related to the first job category. If the first job category is backend development, then the second job categories that are related to the first job category backend development include Python, Node.js, C, GoLang, C++, Java, PHP, etc.; if the first job category is PHP, then the second job categories that are related to the first job category include backend development.

[0077] In step S104, the position to be recommended is determined according to the first position category and the second position category.

[0078] According to the embodiments of the present application, if the position category of a certain recruitment position is the first position category or the second position category, the recruitment position can be determined as the position to be recommended.

[0079] For example, the first position category is Java, and the second position category includes python, Node.js, C language, GoLang, C++, java, and PHP. Then, the recruitment position with the position category of Java can be determined as the position to be recommended, and the recruitment position with the position category of python, Node.js, C language, GoLang, C++, java, and PHP can also be determined as the position to be recommended.

[0080] According to the embodiments of the present application, the job-seeking information of a target user is obtained, the first position category to which the job-seeking information belongs is determined, the second position category having an association relationship with the first position category is determined, and the position to be recommended is determined according to the first position category and the second position category. Thus, the position to be recommended can be recommended to the user comprehensively and meet the requirements of the user.

[0081] The embodiments of the present application provide a possible implementation manner for determining the first position category to which the job-seeking information belongs, which includes:

[0082] The job-seeking information is input into a pre-established first position identification model to obtain the first position category output by the first position identification model. The first position identification model is trained by taking the job-seeking information of a sample user as a training sample and taking the first position category to which the job-seeking information of the sample user belongs as a training label.

[0083] The first position category refers to the position category corresponding to the job-seeking information, such as the first position category of "Java engineer, Java development, Java research and development, Java senior development engineer, and Java backend" being "Java".

[0084] The first identification model of the embodiment of the present application is trained by taking the job-seeking information of a sample user as a training sample and taking the first position category to which the job-seeking information of the sample user belongs as a training label. Specifically, for example, if the job-seeking information of a sample user includes information such as "Java engineer", "Java development", "Java research and development", "Java senior development engineer", and "Java backend", the corresponding training label is "Java", that is, the corresponding first position category is "Java", and for example, if the job-seeking information of a user includes information such as "backend development", "backend development using Java", and "backend research and development", the corresponding training label is "backend", that is, the obtained first position category is "backend".

[0085] In the training of the first identification model, each first position category is obtained from a large amount of job-seeking information of sample users, and after the model training is completed, the first position category to which the job-seeking information of a user belongs can be identified.

[0086] The embodiment of the present application provides a possible implementation manner for determining a second position category having an association relationship with the first position category, which includes:

[0087] The second position category having an association relationship with the first position category is determined from a pre-constructed position data dictionary. The position data dictionary includes each first position category and a second position category having an association relationship with each corresponding first position category.

[0088] The embodiment of the present application includes each first position category and a second position category having an association relationship with each first position category in the data dictionary. The names of the first position category and the second position category may not be the same, but the similarity of the talent portraits between the two is high, such as Figure 2 as shown, Figure 2 The displayed content is the content stored in the data dictionary. If the first position category is backend development, the second position category having an association relationship with the first position category backend development includes python, Node.js, C language, GoLang, C++, Java, PHP, and the like. The second position category corresponding to other first position categories will not be exemplified here.

[0089] The embodiment of the present application provides a possible implementation manner, as shown in Figure 3 which exemplarily shows a flowchart for determining a third position category of each recruitment position. The first position category and the second position category are used to determine a to-be-recommended position, and the process further includes:

[0090] In step S301, each recruitment position and the position information corresponding to the recruitment position in the database are obtained.

[0091] When a recruitment party recruits a position, the recruitment party publishes position information of the corresponding recruitment position on a third-party platform, the position information including a position name, recruitment requirements, etc. After the recruitment party publishes the recruitment position and the position information corresponding to the recruitment position on the third-party platform, the information is stored in a database corresponding to the third-party platform, and each recruitment position and the position information corresponding to the recruitment position can be obtained from the database.

[0092] In step S302, the position information of each recruitment position is input into a second position model established in advance to obtain a third position category output by the second position model. The second position model is trained by taking recruitment information of a sample recruitment position as a training sample and taking a third position category to which the sample recruitment position belongs as a training label.

[0093] The first identification model is trained by taking the job-seeking information of a sample user as a training sample and taking a first position category to which the sample user belongs as a training label, and the first identification model can identify the first position category to which the job-seeking information of the target user belongs.

[0094] In addition to the first identification model, the second identification model is also provided in the embodiment of the application, and the second identification model is trained by taking recruitment information of a recruitment position as a training sample and taking a third position category to which the recruitment position belongs as a training label. The position information of the recruitment position is input into the second identification model to obtain a third position category output by the second identification model.

[0095] Specifically, for example, the recruitment position of the recruitment party is a Java engineer, and the recruitment information is “position name: Java engineer recruitment requirements: proficient in Java programming...”, and the third position category corresponding to the recruitment position is “Java”.

[0096] The first position category refers to a position category to which the target user belongs, the second position category refers to a position category having an association relationship with the first position category, and the third position category refers to a position category to which the recruitment position belongs. The first position category, the second position category, and the third position category are all position categories, but the objects are different.

[0097] In step S303, an association relationship between each recruitment position and each third position category corresponding to the recruitment position is established, and each recruitment position, each third position category corresponding to the recruitment position, and the association relationship between each recruitment position and the third position category are stored in a database.

[0098] After the third position category to which each recruitment position belongs is determined, the embodiment of the application establishes an association relationship between each recruitment position and each third position category corresponding to the recruitment position, and stores the association relationship between each third position category in a database.

[0099] The embodiment of the application provides a possible implementation, respectively determining the to-be-recommended positions corresponding to the first position category and the second position category, and further comprising:

[0100] finding a third position category same as the first position category from the database, and obtaining the recruitment positions corresponding to the third position category from the database according to the third position category and the association relationship between the third position category and the recruitment positions, and determining the recruitment positions corresponding to the third position category as the to-be-recommended positions corresponding to the first position category;

[0101] finding a third position category same as the second position category from the database, and obtaining the recruitment positions corresponding to the third position category from the database according to the third position category and the association relationship between the third position category and the recruitment positions, and determining the recruitment positions corresponding to the third position category as the to-be-recommended positions corresponding to the second position category.

[0102] The embodiment of the application determines the to-be-recommended positions corresponding to the first position category and the second position category after determining the first position category to which the job-seeking information of the target user belongs and the second position category having the association relationship with the first position category.

[0103] Specifically, a third position category same as the first position category can be found from the database, for example, the first position category to which the job-seeking information of the target belongs is “Java”, and the third position category with the same position category “Java” can be directly found from the database through the indexing mode. After determining the third position category same as the first position category, the recruitment positions corresponding to the third position category are obtained from the database according to the third position category and the association relationship between the third position category and the recruitment positions. The recruitment positions corresponding to the third position category are multiple, for example, the recruitment position of the recruitment party A is a java engineer, the recruitment position of the recruitment party B is also a java engineer, and the recruitment position of the recruitment party C is a java research and development engineer, and the like. After determining the recruitment positions corresponding to the third position category, the recruitment positions corresponding to the third position category are determined as the to-be-recommended positions corresponding to the first position category.

[0104] Similarly, the third position category same as the second position category can be found from the database. The way of finding the third position category same as the second position category is the same as the way of finding the third position category same as the first position category, and the embodiment of the application will not be described here.

[0105] The embodiment of the application finds the third position category same as the first position category and the second position category from the database respectively, and determines the recruitment positions corresponding to the third position category as the to-be-recommended positions.

[0106] The embodiment of the present application provides a possible implementation manner, and the recommended position is determined according to the first position category and the second position category, and then the embodiment further comprises the following steps:

[0107] The position to be recommended and the recruitment information of the position to be recommended are recommended to the target user.

[0108] The embodiment of the present application recommends the position to be recommended and the recruitment information of the position to be recommended to the target user after determining the position to be recommended.

[0109] In addition, the present application can filter the position to be recommended before recommending the position to be recommended, and filter out the position to be recommended which does not meet the condition, for example, if it is determined that the A company belongs to the position to be recommended, the recruitment information of the A company can be directly filtered out when the user A is the m department of the A company and the position recommendation is performed.

[0110] The embodiment of the present application provides a possible implementation manner, and the position to be recommended is recommended to the target user, comprising the following steps:

[0111] Determining the recommendation order of each position to be recommended;

[0112] The position to be recommended is recommended to the target user according to the recommendation order.

[0113] The embodiment of the present application determines the recommendation order of each position to be recommended after determining each position to be recommended, and the position to be recommended is recommended to the target user according to the recommendation order of the position to be recommended, and the detailed content is seen in the subsequent part.

[0114] The embodiment of the present application provides a possible implementation manner, and the recommendation order of each position to be recommended is determined, comprising the following steps:

[0115] At least one influence factor and the influence weight corresponding to each influence factor are obtained; the influence factor refers to a factor influencing the recommendation order of the position to be recommended;

[0116] The influence value of at least one influence factor is calculated;

[0117] The recommendation order of each position to be recommended is determined according to the influence value of at least one influence factor and the influence weight corresponding to each influence factor.

[0118] The embodiment of the present application refers to the factor influencing the recommendation order of the position to be recommended as an influence factor. In fact, the recommendation order of the position to be recommended is influenced by multiple factors, that is, one position to be recommended is influenced by multiple influence factors.

[0119] The existing scheme only determines the display order or display position of the recruitment information of each recruitment party according to the publishing time of the recruitment information, the activity of the recruitment party corresponding to the recruitment information and the keyword matching degree when recommending a position, ignores the influence of other factors, and thus the recommended order of the recommended recruitment information for the user often does not meet the needs of the user.

[0120] The influence factors of the embodiments of the present application include but are not limited to: position similarity (the position similarity is the similarity between the content of the job-seeking information and the content of the recruitment information of the recruitment position), education background, school, company, time when the recruitment party publishes the recruitment position, activity of the recruitment party, etc.

[0121] Each influence factor has its corresponding influence weight, and the influence weights corresponding to different influence factors can be different, for example, the influence weight corresponding to the similarity between the content of the job-seeking information and the content of the recruitment information of the recruitment position is 0.5, the influence weight corresponding to the school is 0.01, the influence weight corresponding to the education background is 0.01, the influence weight corresponding to the company is 0.01, the influence weight corresponding to the time information when the recruitment party publishes the recruitment position is 0.05, and the influence weight corresponding to the activity of the recruitment party is 0.04, etc. The influence weights of the influence factors can be set according to actual conditions.

[0122] Different influence factors also have different influence values. Taking the education background as an example, the influence value of the education background is 1 point at the highest level, the education background of the target user in the job-seeking information of the target user is a master degree, the education background requirement in the recruitment information corresponding to the recruitment position a to be recommended is a junior college degree or above, the education background requirement in the recruitment information corresponding to the recruitment position b to be recommended is a bachelor degree or above, and the education background requirement in the recruitment information corresponding to the recruitment position c to be recommended is a master degree or above. Therefore, the influence values of the education background corresponding to the recruitment position a to be recommended, the recruitment position b to be recommended and the recruitment position c to be recommended are set to 0.6 points, 0.8 points and 1 point respectively.

[0123] Taking the position similarity as an example, the value of the position similarity is the influence value of the position similarity, and the process of calculating the value of the position similarity is as follows:

[0124] At least one target keyword is extracted from the job-seeking information of the user, and the target keyword is a characteristic word that can be used as a first position category, such as an industry word, a skill word, etc.

[0125] The process of extracting the target keyword is as follows: cutting the job-seeking information to obtain each word, the cutting software can be used for cutting; labeling the category of each word, including industry word, skill word, meaningless word and general word, etc.; eliminating meaningless words and general words to obtain industry words and skill words.

[0126] After obtaining the at least one target keyword, the number of occurrences (term frequency) of each target keyword in the job information is obtained, the pre-calculated inverse document frequency index idf of each target keyword is obtained, the characteristic value of each target keyword is calculated according to the number of occurrences of each target keyword in the resume and the idf of each target keyword, and the characteristic value of the job information of the target user is calculated according to the characteristic value of each target keyword.

[0127] In addition, it is worth noting that the number of occurrences of the target keyword in the job information is not necessarily equal to the actual number of occurrences of the target keyword in the job information. For general text, the more the number of occurrences of the target keyword, the more important the target keyword is. However, for the job information of the job seeker, when the actual number of occurrences of the target keyword is greater than the preset number of occurrences, it can be indicated that the target keyword is more important, and the actual number of occurrences of the target keyword can be calculated. The number of occurrences of the target keyword can be replaced by the preset number of occurrences to simplify the subsequent calculation.

[0128] Specifically, assuming that the target keywords extracted from the job information of the target user are travel and e-commerce, the number of occurrences of travel is 1, the number of occurrences of e-commerce is 2, the idf of travel is 3, and the idf of e-commerce is 2. The characteristic score of e-commerce can be calculated as =√g(tf)*idf =√2*2, and the characteristic score of travel can be calculated as =√g(tf)*idf =√1*3. Then the characteristic value of the job information of the user can be calculated as ∑g(tf)*idf =√1*3+√2*2, where g(tf) is the number of occurrences of the target keyword, and idf is the inverse document frequency index of the target keyword.

[0129] The number of occurrences of each target keyword in the recruitment information of the recommended position is obtained, the recruitment information of the recommended position includes the position name and the recruitment requirement, the characteristic value of each target keyword is calculated according to the number of occurrences of each target keyword in the position name and the recruitment requirement and the idf of each target keyword, and then the characteristic value of each recruitment position is calculated.

[0130] Similarly, it is worth noting that the more the number of occurrences of the target keyword in the position name and the recruitment requirement, the higher the importance of the target keyword. However, in actual calculation, the actual number of occurrences of the target keyword does not need to be used in the calculation. If the actual number of occurrences of a target keyword in the position name and the recruitment requirement exceeds the preset number of occurrences, the number of occurrences of the target keyword is directly defaulted to the preset number of occurrences, wherein the number of occurrences in the position name remains unchanged, and the number of occurrences in the position requirement is the preset number of occurrences minus the number of occurrences in the position name. In this way, the calculation of the characteristic score is simplified.

[0131] Specifically, it is assumed that the number of occurrences of the target keyword e-commerce in the position name of the recruitment information of a to-be-recommended position is 1, the actual number of occurrences of the target keyword e-commerce in the recruitment requirements is 3, and the number of occurrences of the target keyword travel is 1. Since the number of occurrences of the target keyword e-commerce is 1+3>=3, it is determined that the number of occurrences of the target keyword e-commerce in the position name is 1, and the number of occurrences of the target keyword e-commerce in the recruitment requirements is 2. It can be determined that the feature score of the target keyword e-commerce is =title(t)*idf+√g(tf) 名称 *idf+√g(tf) 要求 *idf+√g(tf) 名称 *idf=1.5*2+√1*2+√2*2, the feature score of the target keyword travel is √1*3, and thus it can be determined that the feature score of the to-be-recommended position is: 1.5*2+√1*2+√2*2+√1*3 where title(t) represents the weight of the position name, g(tf) 要求 represents the number of occurrences of the target keyword in the position name; g(tf) 要求 represents the number of occurrences of the target keyword in the recruitment requirements, and idf is the inverse text frequency index.

[0132] The feature scores of other to-be-recommended positions can be calculated by using the above method, which will not be calculated one by one in this embodiment of the application.

[0133] After determining the feature score of the job-seeking information of the target user and the feature score of the to-be-recommended position, the feature score of the job-seeking information of the target user and the feature score of the to-be-recommended position are normalized to obtain the similarity of each position, so that the similarity comparison can be performed. The specific normalization means is not limited in this embodiment of the application.

[0134] Specifically, it is assumed that the feature score of the job-seeking information of the target user is 5, the feature score after normalization processing is 1, the feature score of the to-be-recommended position a is 4, the feature score after normalization processing is 0.8, the feature score of the to-be-recommended position b is 5, the feature score after normalization processing is 1, the feature score of the to-be-recommended position c is 6, the feature score after normalization processing is 1, and the feature score of the to-be-recommended position d is 3, the feature score after normalization processing is 0.6. That is, the influence values between the recruitment information of the to-be-recommended position and the job-seeking information of the target user are 1, 0.8, 1, 1, and 0.6 respectively.

[0135] In this embodiment of the application, the influence values of at least one influence factor and the influence weights of each influence factor are determined to determine the recommendation values of each to-be-recommended position. The recommendation order of each to-be-recommended position is determined according to the recommendation values of each to-be-recommended position.

[0136] Continuing the above example, the influence value of the education of the recommended position a, the recommended position b and the recommended position c is 0.6, 0.8 and 1 respectively, the influence weight of the influence factor education is 0.01; the influence value between the recommended position a, the recommended position b and the recommended position c and the job seeking information is 0.8, 1 and 1 respectively, the influence weight of the position similarity is 0.5, the influence value of the activity of the recommended position a, the recommended position b and the recommended position c is 0.7, 0.6 and 0.9 respectively, the influence weight corresponding to the activity of the employer is 0.04, and the influence of other influence factors is not exemplified here.

[0137] The recommendation value of the recommended position a, the recommended position b and the recommended position c can be calculated as follows:

[0138] The recommendation value of the recommended position a is 0.6*0.01+0.8*0.5+0.7*0.04=0.434;

[0139] The recommendation value of the recommended position b is 0.8*0.01+1*0.5+0.6*0.04=0.532;

[0140] The recommendation value of the recommended position c is 1*0.01+1*0.5+0.9*0.04=0.546.

[0141] Thus, the recommendation order of the recommended position a, the recommended position b and the recommended position c can be determined as recommended position c>recommended position b>recommended position a from early to late.

[0142] According to the influence value of at least one influence factor and the influence weight corresponding to each influence factor, the embodiment of the present application determines the recommendation order of each recommended position, and recommends each recommended position to the target user according to the recommendation order, so that the obtained sorting result is more in line with the actual situation of the user by considering more influence factors.

[0143] The embodiment of the present application provides a position recommendation device, as shown in Figure 4 The position device 40 can include:

[0144] The acquisition module 410 is configured to acquire the job seeking information of the target user.

[0145] The first position category determination module 420 is configured to determine the first position category to which the job seeking information belongs.

[0146] The second position category determination module 430 is configured to determine the second position category having an association relationship with the first position category.

[0147] The recommended position determination module 440 is configured to determine the recommended position according to the first position category and the second position category.

[0148] The embodiment of the application avoids recommending only positions containing literal meanings of keywords to the user, and can recommend comprehensive positions meeting requirements of the user to the user.

[0149] The embodiment of the application provides a possible implementation manner, and the first position category determining module is specifically configured to input the job-seeking information into a pre-established first position recognition model to obtain a first position category output by the first position recognition model.

[0150] The embodiment of the application provides a possible implementation manner, and the second position category determining module is specifically configured to determine a second position category having an association relationship with the first position category from a pre-constructed position data dictionary.

[0151] The embodiment of the application provides a possible implementation manner, and the device further comprises a third position category determining module, which comprises:

[0152] The position information obtaining submodule is configured to obtain each recruitment position and position information corresponding to the recruitment position in the database.

[0153] The third position category determining submodule is configured to input the position information of each recruitment position into a pre-established second position model to obtain a third position category output by the second position model.

[0154] The storage submodule is configured to establish an association relationship between each recruitment position and the third position category corresponding to each recruitment position, and store each recruitment position, the third position category corresponding to each recruitment position, and the association relationship between each recruitment position and the third position category into the database.

[0155] The embodiment of the application provides a possible implementation manner, and the to-be-recommended position determining module comprises:

[0156] The first to-be-recommended position determining submodule is configured to: find a third position category same as the first position category from the database, and acquire a recruitment position corresponding to the third position category from the database according to the third position category and an association relationship between the third position category and the recruitment position, and determine the recruitment position corresponding to the third position category as the to-be-recommended position corresponding to the first position category.

[0157] The second to-be-recommended position determining submodule is configured to: find a third position category same as the second position category from the database, and acquire a recruitment position corresponding to the third position category from the database according to the third position category and an association relationship between the third position category and the recruitment position, and determine the recruitment position corresponding to the third position category as the to-be-recommended position corresponding to the second position category.

[0158] The application embodiment provides a possible implementation manner, and the apparatus further includes:

[0159] The recommendation module is configured to recommend the to-be-recommended positions and recruitment information of the to-be-recommended positions to the target user.

[0160] The application embodiment provides a possible implementation manner, and the recommendation module includes:

[0161] The recommendation sequence determining submodule is configured to determine the recommendation sequence of each to-be-recommended position.

[0162] The recommendation submodule is configured to recommend each to-be-recommended position to the target user according to the recommendation sequence.

[0163] The application embodiment provides a possible implementation manner, and the recommendation sequence determining submodule includes:

[0164] The influence factor acquisition unit is configured to acquire at least one influence factor and an influence weight corresponding to each influence factor, wherein the influence factor refers to a factor affecting the recommendation sequence of the to-be-recommended position.

[0165] The influence value calculation unit is configured to calculate an influence value of the at least one influence factor.

[0166] The recommendation sequence determining unit is configured to determine the recommendation sequence of each to-be-recommended position according to the influence value of the at least one influence factor and the influence weight corresponding to each influence factor.

[0167] The apparatus of the application embodiment can execute the method provided by the application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of the application embodiment are corresponding to the steps in the method of the application embodiment. The detailed function description of each module of the apparatus can be found in the description of the corresponding method in the foregoing description, and will not be repeated here.

[0168] The embodiment of the present application provides an electronic device, comprising a memory, a processor and a computer program stored in the memory, the processor executes the computer program to realize the steps of the position recommendation method, compared with the prior art, the embodiment of the present application can realize the following: obtaining the job-seeking information of a target user; determining a first position category to which the job-seeking information belongs; determining a second position category having an association relationship with the first position category; and determining a recommended position to be a recommended position according to the first position category and the second position category, thereby avoiding recommending only positions containing literal meanings of keywords to the user, and being capable of recommending comprehensive positions meeting the requirements of the user to the user.

[0169] In an optional embodiment, an electronic device is provided, as shown in Figure 5 Figure 5 The electronic device 5000 shown in the figure comprises a processor 5001 and a memory 5003. The processor 5001 and the memory 5003 are connected, for example, through a bus 5002. Optionally, the electronic device 5000 can further comprise a transceiver 5004, which can be used for data interaction, such as data sending and / or data receiving, between the electronic device and other electronic devices. It should be noted that in actual application, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation on the embodiments of the present application.

[0170] The processor 5001 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure. The processor 5001 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0171] The bus 5002 can comprise a channel for transmitting information between the above-mentioned components. The bus 5002 can be a PCI (Peripheral Component Interconnect, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 5002 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience,​Figure 5 Only one bus or bus type is shown for simplicity, but there can be more than one bus or more than one type of bus.

[0172] The memory 5003 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions; a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions; an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of storing computer instructions and capable of being read by a computer, without limitation.

[0173] The memory 5003 is used to store a computer program for implementing the embodiments of the present application, and is controlled by the processor 5001 to execute. The processor 5001 is used to execute the computer program stored in the memory 5003 to realize the steps shown in the foregoing method embodiments.

[0174] The electronic device package can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), car terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 5 The electronic device shown is merely an example and should not limit the functions and use range of the embodiments of the present disclosure.

[0175] The computer readable storage medium provided by the embodiments of the present application has a computer program stored thereon, and the computer program is executed by a processor to realize the steps and corresponding contents of the foregoing method embodiments. Compared with the prior art, the embodiments of the present application can realize the following: by acquiring the job-seeking information of a target user, determining a first position category to which the job-seeking information belongs, determining a second position category having an association relationship with the first position category, and determining a recommended position to be a recommended position according to the first position category and the second position category, the embodiments of the present application avoid recommending only positions containing the literal meaning of the keywords to the user, and can recommend comprehensive positions meeting the requirements of the user to the user.

[0176] It should be noted that the computer readable medium of the present disclosure described above can be a computer readable signal medium or a computer readable medium or any combination of the above two. The computer readable storage medium may, for example, be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples of computer readable storage media can include, but are not limited to, an electrical connection having 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present disclosure, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take many forms, including but not limited to an electromagnetic signal, an optical signal or any suitable combination of the above. The computer readable signal medium can also be any computer readable medium other than the computer readable storage medium, which can send, propagate or transmit a program for use by or in conjunction with an instruction execution system, device or apparatus. The program code contained in the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, a cable, an RF (radio frequency) or the like, or any suitable combination of the above.

[0177] The embodiment of the present application also provides a computer program product, including a computer program, which can implement the steps and corresponding contents of the foregoing method embodiments when executed by a processor. Compared with the prior art, the embodiment of the present application can achieve the following effects: by acquiring the job seeking information of the target user, determining the first position category to which the job seeking information belongs, determining the second position category having an association relationship with the first position category, and determining the recommended position to be recommended according to the first position category and the second position category, the embodiment of the present application avoids recommending only positions containing the literal meaning of the keyword to the user, and can recommend comprehensive positions meeting the requirements of the user to the user.

[0178] It should be understood that although the various operation steps in the flowcharts of the embodiments of the present application are indicated by arrows, the implementation order of the steps is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of the embodiments of the present application, the implementation steps in each flowchart can be executed in other orders as required. In addition, part or all of the steps in each flowchart can include multiple sub-steps or multiple stages based on the actual implementation scenario. Part or all of the sub-steps or stages can be executed at the same time, and each of the sub-steps or stages can also be executed at different times. In the scenario where the execution times are different, the execution order of the sub-steps or stages can be flexibly configured as required, and the embodiments of the present application do not limit this.

[0179] The above is only an optional implementation of some implementation scenarios of the present application. It should be pointed out that, for those skilled in the art, other similar implementation means based on the technical idea of the present application without departing from the technical concept of the present application also belong to the protection scope of the embodiments of the present application.

Claims

1. A job recommendation method, characterized in that, include: Obtain job search information from target users; Determine the first job category to which the job posting belongs; Identify a second job category that is related to the first job category; The positions to be recommended are determined based on the first job category and the second job category; The step of determining the job to be recommended based on the first job category and the second job category further includes: Obtain at least one influence factor and the influence weight corresponding to each influence factor; the influence factor refers to the factor that affects the recommendation order of the positions to be recommended. Calculate the influence value of the at least one influence factor; The recommendation order of each position to be recommended is determined based on the influence value of the at least one influence factor and the influence weight corresponding to each influence factor. When the influence factor includes job similarity, the influence value of the job similarity is obtained in the following manner: Extract at least one target keyword from the job posting information; Obtain the first and second occurrences of each target keyword in the job posting and the job posting for the position to be recommended. For each target keyword, if the first count is greater than a preset count, then the first feature value of the target keyword is calculated based on the preset count and the inverse document frequency of the target keyword calculated in advance; if the first count is not greater than the preset count, then the first feature value of the target keyword is calculated based on the first count and the inverse document frequency of the target keyword calculated in advance. Calculate the feature value of the job information based on the first feature value of each target keyword; For each keyword, if the second count is greater than the preset count, then the second feature value of the target keyword is calculated based on the preset count and the inverse document frequency of the target keyword; if the second count is not greater than the preset count, then the second feature value of the target keyword is calculated based on the second count and the inverse document frequency of the target keyword. Calculate the feature value of the job to be recommended based on the second feature value of each target keyword; The recommendation value of the job information and the feature value of the job to be recommended are normalized to obtain the influence value of the job similarity.

2. The method according to claim 1, characterized in that, The process of determining the first job category to which the job application information belongs includes: The job search information is input into a pre-established first job recognition model to obtain the first job category output by the first job recognition model; the first job recognition model is trained using the job search information of sample users as training samples and the first job category to which the job search information of sample users belongs as training labels.

3. The method according to claim 1, characterized in that, The determination of a second job category that is associated with the first job category includes: A second job category that is associated with the first job category is determined from a pre-built job data dictionary; the job data dictionary includes each first job category and a second job category that is associated with each corresponding first job category.

4. The method according to claim 1, characterized in that, The step of determining the job to be recommended based on the first job category and the second job category also includes: Retrieve each job posting from the database and the corresponding job information for each job posting; The job information of each job posting is input into a pre-established second job model to obtain the third job category output by the second job model; the second job model is trained using the job information of the sample job postings as training samples and the third job category to which the sample job postings belong as training labels. Establish the relationship between each job posting and its corresponding third job category, and store each job posting, its corresponding third job category, and the relationship between each job posting and its third job category in the database.

5. The method according to claim 4, characterized in that, The step of determining the job to be recommended based on the first job category and the second job category further includes: The database is searched for a third job category that is the same as the first job category. Based on the third job category and the relationship between the third job category and the job posting, the job posting corresponding to the third job category is retrieved from the database. The job posting corresponding to the third job category is determined to be the job posting to be recommended corresponding to the first job category. The database is searched for a third job category that is the same as the second job category. Based on the third job category and the relationship between the third job category and the job posting, the job posting corresponding to the third job category is retrieved from the database. The job posting corresponding to the third job category is determined to be the job posting to be recommended corresponding to the second job category.

6. The method according to claim 1, characterized in that, The step of determining the job to be recommended based on the first job category and the second job category further includes: The job postings and their recruitment information are recommended to the target user.

7. The method according to claim 6, characterized in that, The step of recommending the job to be recommended to the target user includes: Each job posting to be recommended is recommended to the target user according to the recommended order.

8. A job recommendation device, characterized in that, include: The acquisition module is used to acquire job application information from target users; The first job category determination module is used to determine the first job category to which the job application information belongs; The second job category determination module is used to determine a second job category that is related to the first job category. The job recommendation determination module is used to determine the job to be recommended based on the first job category and the second job category; The step of determining the job to be recommended based on the first job category and the second job category further includes: Obtain at least one influence factor and the influence weight corresponding to each influence factor; the influence factor refers to the factor that affects the recommendation order of the positions to be recommended. Calculate the influence value of the at least one influence factor; The recommendation order of each position to be recommended is determined based on the influence value of the at least one influence factor and the influence weight corresponding to each influence factor. When the influence factor includes job similarity, the influence value of the job similarity is obtained in the following manner: Extract at least one target keyword from the job posting information; Obtain the first and second occurrences of each target keyword in the job posting and the job posting for the position to be recommended. For each target keyword, if the first count is greater than a preset count, then the first feature value of the target keyword is calculated based on the preset count and the inverse document frequency of the target keyword calculated in advance; if the first count is not greater than the preset count, then the first feature value of the target keyword is calculated based on the first count and the inverse document frequency of the target keyword calculated in advance. Calculate the feature value of the job information based on the first feature value of each target keyword; For each keyword, if the second count is greater than the preset count, then the second feature value of the target keyword is calculated based on the preset count and the inverse document frequency of the target keyword; if the second count is not greater than the preset count, then the second feature value of the target keyword is calculated based on the second count and the inverse document frequency of the target keyword. Calculate the feature value of the job to be recommended based on the second feature value of each target keyword; The recommendation value of the job information and the feature value of the job to be recommended are normalized to obtain the influence value of the job similarity.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1-7.

Images