A method and device for displaying combined labels of recruitment objects

Abstract

The embodiment of this specification discloses a method and device for displaying a combination label of a recruitment object. The scheme includes: obtaining text information to be identified, wherein the text information includes recruitment information and application information; identifying the text information to generate multiple entities, and determining the type mark corresponding to each entity; determining the association relationship between the multiple entities, and generating a combination label according to the association relationship; determining the group of the combination label according to the type mark, and displaying the combination label in groups in the form of an operable control, thereby providing accurate combination labels for both parties as a reference, so that both parties of the recruitment can timely and accurately understand the core needs of the other party, and improve recruitment efficiency.

Description

Technical Field

[0001] The present invention relates to the field of intelligent recruitment technology, and in particular to a method and device for displaying combined labels of recruitment objects. Background Art

[0002] With the development of mobile Internet, the application of intelligent recruitment technology is becoming more and more widespread. When a job seeker is recruiting, he usually publishes a corresponding recruitment information first, and then receives some application information. In this process, both parties need to process the information, extract the core information that can reflect the key needs of both parties, and display it so that both parties can quickly understand whether there is a match. In addition, the recruiter can also adjust the display of this core information at any time according to the position. At present, there is a lack of extraction and display of the core information of both parties, and the efficiency is low.

[0003] Based on this, a more efficient solution for displaying the combined labels of recruitment targets is needed. Summary of the invention

[0004] The embodiments of this specification provide a method, device and storage medium for displaying combined labels of recruitment objects, so as to solve the following technical problems: a more secure and reliable risk detection solution for third-party mini-programs is needed.

[0005] To solve the above technical problems, one or more embodiments of this specification are implemented as follows:

[0006] In a first aspect, an embodiment of the present specification provides a method for displaying a combination label of a recruitment object, comprising: obtaining text information to be identified, wherein the text information includes recruitment information and application information; identifying the text information to generate multiple entities, and determining a type tag corresponding to each entity; determining an association relationship between the multiple entities, and generating a combination label based on the association relationship; determining a group of the combination label based on the type tag, and displaying the combination label in groups in the form of operable controls.

[0007] In a second aspect, one or more embodiments of this specification provide an electronic device, including:

[0008] at least one processor; and,

[0009] a memory communicatively connected to the at least one processor; wherein,

[0010] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0011] In a third aspect, an embodiment of the present specification provides a non-volatile computer storage medium storing computer executable instructions. When a computer reads the computer executable instructions in the storage medium, the instructions enable one or more processors to execute the method described in the first aspect.

[0012] At least one of the above-mentioned technical solutions adopted in one or more embodiments of the present specification can achieve the following beneficial effects: by acquiring text information to be identified, wherein the text information includes recruitment information and application information; identifying the text information to generate multiple entities, and determining the type tag corresponding to each entity; determining the association relationship between the multiple entities, and generating a combination label according to the association relationship; determining the group of the combination label according to the type tag, and displaying the combination label in the form of operable controls, thereby providing accurate combination labels for both parties as a reference, so that both parties of the recruitment can timely and accurately understand the core needs of the other party, thereby improving recruitment efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0014] Figure 1 A flowchart of a risk detection method based on dynamic and static analysis of mini-programs provided in one or more embodiments of this specification;

[0015] Figure 2 A schematic diagram of an entity type provided in an embodiment of this specification;

[0016] Figure 3 A schematic diagram illustrating a clickable control provided in an embodiment of this specification;

[0017] Figure 4 A schematic diagram of displaying a clickable control provided in an embodiment of this specification;

[0018] Figure 5 The present invention provides a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The embodiments of this specification provide a method, device and storage medium for displaying combined labels of recruitment objects.

[0020] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0021] In the current recruitment platform, when the recruiter releases a recruitment information, it usually also provides some simple tags, such as "xx certificate required", "experience not limited" or "legal background", etc. However, this type of label is a simple label obtained by word segmentation from the information, and on the other hand, the recruiter cannot perform further operations on these labels. In addition, when the applicant submits the corresponding application information, the platform basically does not extract the corresponding information from the applicant, and the recruiter still needs to perform manual information processing, which reduces the efficiency of both parties. Based on this, the embodiment of this specification provides a more efficient display scheme for the combined labels of recruitment objects.

[0022] like Figure 1 As shown, Figure 1 A flowchart of a method for displaying combined labels of recruitment objects provided in one or more embodiments of this specification.

[0023] Figure 1 The process in may include the following steps:

[0024] S102, obtaining text information to be identified, wherein the text information includes recruitment information and application information.

[0025] Recruitment information and application information are usually in text form. Recruitment information is obtained when the recruiter publishes the job information, and application information can be obtained based on the resume submitted by the applicant and the information generated in the subsequent text or voice communication.

[0026] S104, identifying the text information to generate multiple entities, and determining a type tag corresponding to each entity.

[0027] The basic methods for entity recognition of recruitment information and application information are the same, but there are some differences in the specific details. In terms of the framework, both recruitment information and application information can be segmented, divided into sentences, parsed, semantically classified, and the semantic type of each sentence can be identified; for any sentence, the entity contained in the sentence is identified, and the type tag corresponding to the entity is determined according to the semantic type of the sentence. Thus, the corresponding entity is identified.

[0028] Specifically, for recruitment information, the recruitment object label can be automatically extracted through the recruitment text parsing algorithm. That is, the recruitment information is first classified at the sentence level to calibrate the semantic type of the recruitment text. The supported types include: job responsibilities, job requirements, salary conditions, company introduction, application instructions, basic information, etc. A sentence can have multiple semantic types.

[0029] For example, for a sentence "Have 5-10 years of experience working in the freight forwarding industry on US-Canada routes, including at least 3 years in a management position", the semantic types of the sentence can be "job responsibilities" and "job requirements".

[0030] After determining the semantic type of the recruitment text, we can use the knowledge graph to perform entity recognition (NER) on the sentence, mine the potential entities of the sentence for job responsibilities and job requirements, and mark the types. The type tags are used to characterize the recruitment characteristics of the identified entities.

[0031] Supported type tags include: capability tags, project tags, industry tags, etc., tag level entities (understand, master, familiar, etc.), tag years entities (more than 3 years, 5-10 years, etc.), tag relationship entities (one of, or, etc., not considered, declined), etc. Figure 2 As shown, Figure 2 A schematic diagram of an entity type provided in an embodiment of this specification.

[0032] In addition, for job application information, due to the unstructured nature of the resume, the application information needs to be sorted out first, including resume information OCR, original candidate clue list description information, conversation text provided by the applicant, voice recording to complete text recognition, etc.

[0033] Then, the application information is segmented according to the text features to obtain multiple sub-application information, and the sub-application information is divided into sentences. The text features here include font differences, text concentration, alignment, contextual semantic relationships, etc. Each sub-application information corresponds to a paragraph of text in the application information.

[0034] Furthermore, the sub-application information can be segmented into sentences and the semantic classification of the application information can be marked. The supported types include: basic information, educational background, work experience, project experience, self-description, etc.

[0035] After determining the semantic type of the application text, the knowledge graph can be used to perform entity recognition on the sentence. For different sentence classifications, relevant candidate combinations of application entities can be extracted from paragraphs of different categories, such as extracting skill labels from work resumes and project experiences, and extracting soft skill labels from self-descriptions.

[0036] Specifically, since the job application information has been divided into multiple sub-application information, for each sub-application information, it may be possible to obtain multiple available candidate entities. Then, it is necessary to sort the candidate entities, and this sorting competition is performed in segments (i.e., with each sub-application information as the boundary), and generally the candidate entities with the topK scores (for example, K=1) are selected as the entities corresponding to the sub-application information.

[0037] That is, for any sub-application information, multiple candidate entities are identified; for any candidate entity, the score S of the candidate entity is calculated according to the word frequency f, the pre-calculated classification relevance r and the relevance deviation b corresponding to the candidate entity; the candidate entities are sorted according to their scores, and the candidate entities at the top of the sort are determined as the multiple entities corresponding to the sub-application information. Among them, the word frequency f is the number of times the word corresponding to the candidate entity appears in the sub-application information; the classification relevance r is the relevance between the category and the position to which the type tag corresponding to the candidate entity belongs; the relevance deviation n represents the degree of deviation between the statistical distribution of the characteristics of this category and the statistical distribution of the characteristics of the position, and the relevance and relevance deviation can be pre-calculated based on the statistical distribution of the characteristics of this category.

[0038] When there are n candidate entities, the score of each candidate entity can be calculated as follows: Where n is the total number of entities, 1≤i≤n. , and sort them from high to low, and extract the winning entity of each segment with the lowest threshold (ie, the lowest score) and the maximum number of labels (eg, 1).

[0039] In addition, when determining the time entities involved in the application information (including education experience, work experience or project experience, etc.), since they may be distributed in multiple natural segments (for example, project experience is often scattered in different segments in a resume). Based on this, the following method can be used to determine the length of the time entity: determine the time entity corresponding to any sub-application information, and determine the length of the time entity; merge multiple time entities with the same type of mark to generate a merged entity, wherein the length of the merged entity is the sum of the lengths of the multiple time entities with the same type of mark, so as to accurately identify the length of this type of time entity contained in the application information.

[0040] S106: Determine the association relationship between the multiple entities, and generate a combined label according to the association relationship.

[0041] Whether it is recruitment information or application information, after the entity is determined, it is possible to determine whether there is an association relationship between entities based on the semantics of the entity context. After the association relationship is established, the corresponding label combination can be generated based on the association relationship and saved in the background. In recruitment information, it is usually possible to combine the label years entity with industry labels, project labels, or soft skill labels.

[0042] like Figure 2 As shown in the diagram, the two "label years entities" are associated with other entities, which generates corresponding combined labels: "5-10 years in freight forwarding industry", "5-10 years of experience in US-Canada routes" and "at least 3 years of management experience". Similar combined labels can also be generated for job application information.

[0043] S108, determining the group of the combination tags according to the type mark, and displaying the combination tags in groups in the form of operable controls.

[0044] For each combined tag, the group to which it belongs can be determined based on the entities and their associations contained in the combined tag. For example, it can be determined that it belongs to the "hard skills" group based on the industry tags or project tags it contains.

[0045] Among them, the initial icon of the operable control is determined based on the following method: determining the content contained in the combined label, wherein the content includes the association relationship between the entities, the positive and negative nature of the entity conditions, or the weight value in the entity; determining the initial icon of the operable control based on the content.

[0046] For example, thumbs up and down are used to represent positive conditions or negative negation conditions; for label content, multiple parallel ones can use the symbol "|" to represent that their corresponding association relationship is "OR"; the weight of the entity is represented by the crescent to the full moon, from small to large, 1-5, and the full moon represents a necessary condition; Figure 3 As shown, Figure 3 This is a schematic diagram of a clickable control provided in the embodiment of this specification. In practice, the specific icon to be used can be selected according to different positions or entities.

[0047] After the initial icon is determined, the combined label of the recruiter or the combined label of the applicant is displayed in the interface. The user can operate the initial icon after the display (including clicking, long pressing, dragging or entering a value, etc.).

[0048] like Figure 4 As shown, Figure 4A schematic diagram of a display of a clickable control provided in an embodiment of the present specification. In the schematic diagram, corresponding multiple operable controls are displayed under different groups of "hard skills" and soft skills. The recruiter can perform operations such as adding (clicking the + sign in the diagram) or deleting (clicking the × sign in the diagram) the operable space. For two combined labels under the same group, if possible (that is, the two are in a parallel relationship), the recruiter can also merge the two labels into one by dragging, or; the recruiter can split the control containing the parallel relationship by clicking on it; or, the recruiter can adjust the label weight individually by clicking on the icon for the label weight, etc.

[0049] For applicants, when they browse the job information provided by the employer, the controls corresponding to these combined tags will also be displayed in the interface, so that the applicants can directly understand the employer's needs, but the applicants will not be able to operate these controls.

[0050] In addition, when a recruiter browses a candidate's application information, the combined tags corresponding to the recruiter and the combined tags corresponding to the candidate can be displayed simultaneously in the interface. In addition, in this process, the displayed combined tags should have a large correlation.

[0051] Specifically, the following method can be used to determine whether there is a correlation between the two: determine a first distribution of the combined labels corresponding to the recruitment information, and determine a second distribution of the combined labels corresponding to the application information; calculate the correlation between the first distribution and the second distribution, and display the combined labels corresponding to the application information according to the correlation. This correlation can be determined by calculating the correlation coefficient of the two distributions, which can specifically include methods such as Pearson correlation coefficient or calculating chi-square test.

[0052] That is to say, in the case of fixed labels corresponding to recruitment information, combined labels corresponding to application information that is as relevant as possible are provided for display, which is equivalent to pre-processing the relevant conditions of the applicants before the recruiter conducts screening, thereby improving the recruiter's recruitment efficiency.

[0053] By acquiring text information to be identified, wherein the text information includes recruitment information and application information; identifying the text information to generate multiple entities, and determining the type tag corresponding to each entity; determining the association relationship between the multiple entities, and generating a combination label according to the association relationship; determining the group of the combination label according to the type label, and displaying the combination label in the form of operable controls, thereby providing both parties with accurate combination labels as a reference, so that both parties of the recruitment can timely and accurately understand the core needs of the other party, thereby improving the recruitment efficiency.

[0054] In the second aspect, based on the same idea, one or more embodiments of this specification also provide a device corresponding to the above method, such as Figure 5 As shown, Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification, the device includes:

[0055] at least one processor; and,

[0056] a memory communicatively connected to the at least one processor; wherein,

[0057] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0058] In the third aspect, based on the same idea, the embodiment of this specification also provides a non-volatile computer storage medium corresponding to the above method, storing computer executable instructions. When the computer reads the computer executable instructions in the storage medium, the instructions enable one or more processors to execute the method described in the first aspect.

[0059] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0060] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0061] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0062] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0063] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A method for displaying a combination label of a recruitment object, comprising: Acquire text information to be identified, wherein the text information includes recruitment information and application information; Recognize the text information to generate multiple entities, and determine the type tag corresponding to each entity; Determine the association relationship between the multiple entities, and generate a combined label according to the association relationship; The group of the combination tags is determined according to the type mark, and the combination tags are displayed in groups in the form of operable controls.

2. The method of claim 1, wherein: The method further comprises: In response to the user's operation, splitting or merging the operable controls in the same group of the display interface; Alternatively, in response to the user's operation, the variable properties of the operable controls are adjusted in the display interface.

3. The method of claim 1, wherein: Recognizing the text information to generate multiple entities and determining a type tag corresponding to each entity includes: Segment the text information and identify the semantic type of each sentence; For any sentence, the entity contained in the sentence is identified, and the type tag corresponding to the entity is determined according to the semantic type of the sentence.

4. The method of claim 3, wherein: Segmenting the text information includes: Segment the application information according to text features to obtain multiple sub-application information; The sub-application information is divided into sentences respectively.

5. The method of claim 3, wherein: Recognize the text information to generate multiple entities, including: For any sub-application information, multiple candidate entities are identified; For any candidate entity, calculate the score S of the candidate entity according to the word frequency f, the pre-calculated classification relevance r and the relevance deviation b corresponding to the candidate entity; The candidate entities are sorted according to their scores, and the candidate entities at the top of the sort are determined as the multiple entities corresponding to the sub-application information.

6. The method of claim 5, wherein: Calculating the score of the candidate entity according to the word frequency f, the pre-calculated classification relevance r and the relevance deviation b corresponding to the candidate entity, including: Taking the segmented label combination of the candidate as the comparison object, the score of the i-th candidate entity is calculated using the following formula: Where n is the total number of entities, 1≤i≤n.

7. The method of claim 1, wherein: The method further comprises: Determine a first distribution of combined labels corresponding to the recruitment information, and determine a second distribution of combined labels corresponding to the application information; The correlation between the first distribution and the second distribution is calculated, and the combined label corresponding to the application information is displayed according to the correlation.

8. The method of claim 5, wherein: Recognize the text information to generate multiple entities, including: Determine a time entity corresponding to any sub-application information, and determine the duration of the time entity; A plurality of time-type entities with the same type of tags are merged to generate a merged entity, wherein the duration of the merged entity is the sum of the durations of the plurality of time-type entities with the same type of tags.

9. The method of claim 1, wherein: The initial icon of the operable control is determined based on the following methods, including: Determine the content contained in the combined tag, wherein the content includes the association relationship between the entities, the positive or negative nature of the entity condition, or the weight value of the entity; An initial icon of the operable control is determined according to the content.

10. An electronic device comprising: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 9.

Images