Talent review method, device, equipment, medium and computer program product

Abstract

The invention provides a talent review method, device and equipment, a medium and a computer program product, and the method comprises the steps: grouping candidates and experts according to the attribute information of the candidates and the attribute information of the experts; traversing all the groups according to the attributes of the to-be-reviewed task to obtain candidate groups matched with the attributes of the to-be-reviewed task; traversing the subject attributes of the experts in the candidate group according to the subject attributes of the candidates to obtain an expert group matched with the subject attributes of the candidates; and extracting a main examination expert from the expert group, and sending invitation information to an account of the main examination expert. According to the method, the candidates and the experts can be automatically grouped according to the review project structure, then the candidate experts are screened according to the attributes of the review project, and the experts similar to the candidates in discipline are screened from the candidate experts according to the discipline attributes of the candidates, so that the discipline matching degree of the candidates and the experts is improved; and the efficiency of extracting the experts in the talent review project is also improved.

Description

Technical Field

[0001] The present invention relates to the field of data classification technology, and in particular to a talent evaluation method, device, equipment, medium and computer program product. Background Art

[0002] Talent evaluation is an important mechanism for improving competitiveness in modern corporate organizations. With the development of organizations, corporate activities are gradually developing in the direction of refinement and complexity. The evaluation of talents often cannot rely on only one or two experts to complete the evaluation. For example, for the evaluation of talents with interdisciplinary backgrounds, it is unfair to rely on only experts in one technical field to complete the evaluation. At present, talent evaluation is still mainly carried out by manual screening and assignment of experts. On the one hand, this method is arbitrary and cannot provide candidates with highly matched evaluation experts. On the other hand, it is inefficient. As the organization grows and develops, the expert pool within the organization is also increasing. When there are many evaluation projects, it often takes more manpower and time to manually screen experts. It can be seen that how to improve the matching between experts and candidates has become a problem that needs to be solved in this field. Summary of the invention

[0003] The present invention provides a talent evaluation method, device, equipment, medium and computer program product, which are used to solve the defect of the prior art that the matching degree between the candidate's field and the expert's field is not accurate enough in talent evaluation, and realize fast, accurate and automatic matching between candidates and experts.

[0004] The present invention provides a talent evaluation method, comprising the following steps.

[0005] Grouping candidates and experts according to their attribute information and expert attribute information; Traverse all groups according to the attributes of the task to be reviewed to obtain candidate groups that match the attributes of the task to be reviewed; According to the subject attributes of the candidate, traverse the subject attributes of the experts in the candidate group to obtain an expert group that matches the subject attributes of the candidate; A chief review expert is selected from the expert group, and an invitation message is sent to the account of the chief review expert.

[0006] According to a talent evaluation method provided by the present invention, the subject attributes include first-level subject attributes and second-level subject attributes; after grouping the candidates and the experts according to the attribute information of the candidates and the attribute information of the experts, the method further includes: Candidates and experts within each group are subcontracted based on their disciplinary relevance; After traversing the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group matching the subject attributes of the candidate, the method further includes: According to the first-level subject attribute of the candidate and the second-level subject attribute of the candidate, the expert group and / or all experts in each sub-contract are traversed to determine the expert group that matches the first-level subject attribute or the second-level subject attribute.

[0007] According to a talent evaluation method provided by the present invention, after traversing the expert group and / or all experts in each sub-contract according to the first-level subject attribute of the candidate and the second-level subject attribute of the candidate to determine the expert group matching the first-level subject attribute or the second-level subject attribute, the method further includes: Determining the subject accuracy of each expert according to the matching degree of the first-level subject attributes or the second-level subject attributes between the candidate and each expert in the expert group; The step of selecting a chief expert from the expert group and sending an invitation message to the chief expert's account includes: The chief review expert is selected from the expert group according to the subject accuracy ranking of each expert, and an invitation message is sent to the account of the chief review expert.

[0008] According to a talent evaluation method provided by the present invention, the subject attributes of the experts in the candidate group are traversed according to the subject attributes of the candidate to obtain an expert group matching the subject attributes of the candidate, including: According to the subject attributes of the candidate, traverse the subject attributes of the experts in the candidate group to obtain a plurality of experts matching the subject attributes of the candidate; Experts having an avoidance relationship with the candidate are eliminated from the multiple experts, and the remaining experts serve as the expert group.

[0009] According to a talent evaluation method provided by the present invention, the attribute information includes award attributes; and grouping the candidates and experts according to the attribute information of the candidates and the attribute information of the experts includes: The candidates and the experts are grouped according to the award attributes of the candidates and the award attributes of the experts.

[0010] According to a talent review method provided by the present invention, after extracting a chief review expert from the expert group and sending an invitation message to the chief review expert's account, the method further includes: Receiving the real-name authentication information returned by the account of the chief review expert; The final chief review expert is determined based on the real-name authentication information.

[0011] The present invention also provides a talent evaluation device, comprising: A grouping module is used to group candidates and experts according to their attribute information and expert attribute information; A candidate group determination module is used to traverse all groups according to the attributes of the task to be reviewed and obtain candidate groups that match the attributes of the task to be reviewed; An expert group selection module is used to traverse the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group that matches the subject attributes of the candidate; The chief review expert extraction module is used to extract the chief review expert from the expert group and send an invitation message to the chief review expert's account.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any one of the talent evaluation methods described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the talent evaluation method described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, including a computer program, wherein when the computer program is executed by a processor, the talent evaluation method described above is implemented.

[0015] The talent review method, device, equipment, medium and computer program product provided by the present invention group candidates and experts according to the attribute information of the candidates and the attribute information of the experts; traverse all groups according to the attributes of the task to be reviewed to obtain candidate groups that match the attributes of the task to be reviewed; traverse the subject attributes of the experts in the candidate groups according to the subject attributes of the candidates to obtain an expert group that matches the subject attributes of the candidates; extract the chief expert from the expert group, and send an invitation message to the account of the chief expert. The method can realize automatic grouping of candidates and experts according to the review project structure, and then screen candidate experts according to the review project attributes, and screen experts with similar subjects to the candidates from the candidate experts according to the subject attributes of the candidates, thereby improving the subject matching degree between candidates and experts, and also improving the efficiency of extracting experts in the talent review project. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is one of the flow charts of the talent evaluation method provided by the present invention.

[0018] Figure 2 It is a structural diagram of the group numbering provided by the present invention.

[0019] Figure 3 It is a schematic diagram of the relationship structure between the grouping and subpackaging provided by the present invention.

[0020] Figure 4 It is a schematic diagram of the identification of the expert hit accuracy provided by the present invention.

[0021] Figure 5 This is the second flow chart of the talent evaluation method provided by the present invention.

[0022] Figure 6 It is a structural schematic diagram of the talent evaluation device provided by the present invention.

[0023] Figure 7 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Combine the following Figure 1-Figure 7 Specific embodiments of the present invention are described.

[0026] Figure 1 It is one of the flow charts of the talent evaluation method provided by the present invention, such as Figure 1 As shown, the method includes the following: Step 101, grouping candidates and experts according to their attribute information and expert attribute information; Among them, candidates refer to participants in the award review, such as lecturers participating in physics teaching competitions, and experts refer to reviewers with certain qualifications. Attribute information includes the names of the projects and sub-projects involved in the review.

[0027] Specifically, when a talent review project is launched, candidates will be grouped after they apply. Since a talent review project may include multiple sub-projects (or sub-awards), they can be grouped according to project categories. Specifically, candidates and experts are grouped by number first. Each candidate must have a unique review number in the same review stage. Examples of numbers are as follows: Figure 2 As shown, the automatic numbering rules are as follows: (1) Group identification: Arrange in ascending alphabetical order; (2) Connector: hyphen (omitted if there is only one sub-award in this stage); (3) Sub-award ID: generated based on the sub-award ID (Sub-award ID) (omitted if there is only one sub-award at this stage); (4) Serial number: The candidates are sorted in order of their first subject code and the first letter of their name. The default number is 2 digits, which can be increased (i.e., if there are more than 99 candidates in a group, the serial number will be increased to 3 digits, and so on).

[0028] Optionally, during the judging phase, each sub-award may be created as a group.

[0029] Step 102, traverse all groups according to the attributes of the task to be reviewed, and obtain candidate groups that match the attributes of the task to be reviewed; Among them, the task to be reviewed refers to the award (or sub-award) to be reviewed. The attribute of the task to be reviewed refers to the subject distribution attribute, region, age distribution, etc. of the task, and the appropriate attribute can be selected according to the actual situation.

[0030] Specifically, by extracting an expert group that matches the attributes of the task to be reviewed from the above groupings, the core attributes can be considered: award identification, region, subject distribution, and age range. For example, if the subject distribution attribute is selected as the standard, experts with the same or similar subject attributes as the task to be reviewed can be selected from the above groupings. Specifically, the similarity between the subject of each expert and the subject of the task to be reviewed can be traversed from the above groupings, and a specified number of candidate experts can be determined based on the similarity to form a candidate group. Among them, the specified number can be flexibly selected according to the actual situation, for example, it can be determined as an integer multiple of the number of experts finally invited.

[0031] Step 103, according to the subject attributes of the candidate, traverse the subject attributes of the experts in the candidate group to obtain an expert group that matches the subject attributes of the candidate; Specifically, experts with similar subject attributes to the candidates can be selected from the above candidate groups. Experts in the above candidate groups can be traversed according to priority (for example, the first-level disciplines and second-level disciplines to which the candidates belong are different priorities) and grouping order (the projects and sub-projects to which the candidates belong are different groups). If the conditions (for example, similarity) are met, it is considered a hit, and the hit object enters the hit object pool, i.e., the expert group. During the traversal process, experts are extracted according to the first-level priority, and then extracted according to the second-level priority, and finally all the extracted results are assembled into an expert group.

[0032] Step 104, selecting a chief review expert from the expert group and sending an invitation message to the chief review expert's account.

[0033] Specifically, calculate the number of review objects for each expert (calculated by the review stage parameter: the minimum number of review experts for the candidate); set the ranking for the candidates in each expert's group, and set the review experts for the candidates with the highest ranking (from the first place to the number of review objects) (the current behavior is to give priority to the same discipline as the expert). Send an invitation message to the review expert's account.

[0034] In the above embodiment, candidates and experts are grouped according to the attribute information of the candidates and the attribute information of the experts; all groups are traversed according to the attributes of the task to be reviewed to obtain candidate groups that match the attributes of the task to be reviewed; the subject attributes of the experts in the candidate groups are traversed according to the subject attributes of the candidates to obtain an expert group that matches the subject attributes of the candidates; the chief expert is extracted from the expert group, and an invitation message is sent to the account of the chief expert. This method can realize automatic grouping of candidates and experts according to the review project structure, and then screen candidate experts according to the review project attributes, and screen experts with similar subjects to the candidates from the candidate experts according to the candidate's subject attributes, thereby improving the subject matching degree between candidates and experts, and also improving the efficiency of extracting experts in talent review projects.

[0035] In one embodiment, the above-mentioned subject attributes include first-level subject attributes and second-level subject attributes; after the above-mentioned step 102, it also includes: sub-contracting the candidates and experts in each group according to the subject association between the candidates and the experts; after the above-mentioned step 103, it also includes: traversing the expert group and / or all the experts in each sub-contract according to the first-level subject attributes of the candidate and the second-level subject attributes of the candidate, and determining the expert group that matches the first-level subject attributes or the second-level subject attributes.

[0036] Optionally, it also includes: determining the subject accuracy of each expert based on the first-level subject attribute matching degree or the second-level subject attribute matching degree between the candidate and each expert in the expert group; sorting the experts according to their subject accuracy, extracting the chief expert from the expert group, and sending an invitation message to the account of the chief expert.

[0037] Specifically, the present application supports sub-packaging on the basis of grouping. The relationship between grouping and sub-packaging is as follows: Figure 3 As shown, the subcontracting is mainly based on the subject distribution of candidates and experts. Generally speaking, subjects can be divided into first-level subjects and second-level subjects. When traversing experts, this application can set the hit accuracy according to first-level subjects and second-level subjects. It will traverse the subject attributes of experts in the order of targeted subjects (i.e., the subjects of the candidates), set the experts who meet the targeted subjects as hit experts, and record the hit accuracy of each expert and the targeted subject. Hit accuracy means the level at which the expert hits the targeted subject. The following Table 1 is a description of hit accuracy: Table 1 Description of hit accuracy

[0038] like Figure 4 As shown, in Figure 4 It means that after the experts and candidates are grouped and sub-packaged, the hit accuracy of each expert is recorded simultaneously during the expert extraction process. For example, when the first-level discipline to which the extracted expert belongs has the highest match with the targeted discipline (that is, the target discipline to which the candidate belongs), the hit accuracy of the expert is recorded as T1; when the discipline to which the extracted expert belongs is "not a first-level discipline hit" but a targeted discipline, the hit accuracy of the expert is recorded as T2, and so on.

[0039] It should be noted that in the above Table 1, “valued” means there is someone (i.e. there is an expert number), and “no value” means there is no one (i.e. there is no expert number).

[0040] The traversal will be performed in the order shown in Table 2 below: Table 2 Traversal logic

[0041] The above embodiment realizes the refined classification of candidates and experts through the grouping and sub-packaging mechanism, which is conducive to the accurate matching between accurate candidates and experts.

[0042] In one embodiment, the above step 103 includes: according to the subject attributes of the candidate, traversing the subject attributes of the experts in the candidate group to obtain multiple experts matching the subject attributes of the candidate; eliminating experts who have an avoidance relationship with the candidate from the multiple experts, and the remaining experts serve as the expert group.

[0043] Specifically, the present application takes avoidance relationships into consideration during the traversal process and will apply the following avoidance rules. When any of the following conditions is met, no hit will be recorded.

[0044] (1) The object data status is deactivated or deleted; (2) The object extraction status is not extracted; (3) Adjustment rules: The current activity has a nomination record (the original candidate in the group had a nomination relationship with the expert); (4) Adjustment rules: The name is the same as the name of the candidate in the current stage (the name, ID number or mobile phone number of the candidate and the expert in the group is the same); (5) New rule: My mobile phone number is empty; (6) New rule: The work unit of the candidate is the same as the current grouping / subcontracting candidate.

[0045] In one embodiment, the above step 104 further includes: receiving identity authentication information returned by the account of the chief review expert; and determining the final chief review expert according to the identity authentication information.

[0046] Specifically, the logic of expert invitation is: invite in batches according to the difference in the number of invitations to be made. The rules are as follows: 1. The first batch of invited persons: experts with the highest hit accuracy in each group to be invited.

[0047] 2. Invitation difference: the number of experts to be invited by each group minus the number of experts who have accepted the invitation.

[0048] 3. Real-name authentication: During the invitation process, if the expert accepts the invitation, the real-name authentication step will be carried out at the same time. Real-name authentication adopts a three-factor authentication mechanism: the name, ID number, and mobile phone number are all real and registered by the same person, which is considered to be authenticated.

[0049] 4. Review experts who accept the invitation and undergo real-name authentication will automatically become review experts for this stage.

[0050] In the above embodiment, an invitation message is sent to the account of the chief review expert. After the chief review expert accepts the invitation and the identity is successfully authenticated, the final chief review expert is determined, thereby ensuring the validity of the review project and preventing someone from impersonating an expert to conduct the review.

[0051] In one embodiment, if Figure 5 As shown, Figure 5 This is the second flow chart of the talent review method, which shows the complete process of the talent review method provided by this application.

[0052] First, establish an expert database for the talent review project; then, select experts from the expert database in turn according to certain selection rules. The selection rules can be to determine the total number of experts to be drawn based on the set number of experts to be invited and the selection multiple (for example, the total number is the number of experts to be invited × the selection multiple). The selection process can be carried out in multiple batches.

[0053] It should be noted that each time the candidate experts are drawn, they need to be excluded and avoided; among the experts after exclusion and avoidance, the attribute information of each expert is traversed, and the correlation between each expert and the candidate is judged based on the attribute information of each expert. If the correlation is high, the expert can be considered to be hit and enter the hit object pool, and the hit accuracy of the expert is recorded according to the above-mentioned grouping / sub-packaging rules; among them, the extraction process is clocked, first all groups are extracted according to the first-level priority, and then downgraded to the second-level priority to extract experts in all groups, and so on; after each traversal cycle (whether a round of traversal is completed is determined by judging whether the number boundary of the expert library is reached), the expert number will be randomly output from the hit object pool as the extraction result.

[0054] The above embodiment, by setting a traversal algorithm to complete expert extraction, can quickly screen out experts who are highly relevant to the review task and highly relevant to the attribute distribution information of candidate talents (such as subject distribution information) from a large number of experts, thereby ensuring fairness and efficiency of subsequent reviews.

[0055] The talent evaluation device provided by the present invention is described below. The talent evaluation device described below and the talent evaluation method described above can be referenced to each other.

[0056] A grouping module 601 is used to group candidates and experts according to the attribute information of the candidates and the attribute information of the experts; A candidate group determination module 602 is used to traverse all groups according to the attributes of the task to be reviewed and obtain candidate groups that match the attributes of the task to be reviewed; The expert group selection module 603 is used to traverse the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group that matches the subject attributes of the candidate; The chief review expert extraction module 604 is used to extract the chief review expert from the expert group and send an invitation message to the chief review expert's account.

[0057] In one embodiment, the subject attributes include first-level subject attributes and second-level subject attributes; the group division module 601 is also used to: subcontract the candidates and experts in each group according to the subject correlation between the candidates and the experts; the expert group selection module 603 is also used to: traverse the expert group and / or all experts in each subcontract according to the first-level subject attributes of the candidate and the second-level subject attributes of the candidate, and determine the expert group that matches the first-level subject attributes or the second-level subject attributes.

[0058] In one embodiment, the expert group selection module 603 is further used to: determine the subject accuracy of each expert according to the matching degree of the first-level subject attribute or the second-level subject attribute between the candidate and each expert in the expert group; The chief review expert extraction module 604 is further used to: extract the chief review expert from the expert group according to the subject accuracy ranking of each expert, and send an invitation message to the account of the chief review expert.

[0059] In one embodiment, the expert group selection module 603 is further used to: traverse the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain multiple experts that match the subject attributes of the candidate; eliminate experts who have an avoidance relationship with the candidate from the multiple experts, and the remaining experts serve as the expert group.

[0060] In one embodiment, the attribute information includes award attributes; the grouping module 601 is further used to group the candidates and the experts according to the award attributes of the candidates and the award attributes of the experts.

[0061] In one embodiment, the chief review expert extraction module 604 is further used to: receive the real-name authentication information returned by the chief review expert's account; and determine the final chief review expert based on the real-name authentication information.

[0062] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the talent review method, which includes: grouping the candidates and the experts according to the attribute information of the candidates and the attribute information of the experts; traversing all the groups according to the attributes of the tasks to be reviewed to obtain the candidate groups that match the attributes of the tasks to be reviewed; traversing the subject attributes of the experts in the candidate groups according to the subject attributes of the candidates to obtain the expert group that matches the subject attributes of the candidates; extracting the chief review expert from the expert group and sending an invitation message to the account of the chief review expert.

[0063] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0064] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the talent review method provided by the above methods, which includes: grouping candidates and experts according to the attribute information of the candidates and the attribute information of the experts; traversing all groups according to the attributes of the tasks to be reviewed to obtain candidate groups that match the attributes of the tasks to be reviewed; traversing the subject attributes of the experts in the candidate groups according to the subject attributes of the candidates to obtain an expert group that matches the subject attributes of the candidates; extracting the chief review expert from the expert group, and sending an invitation message to the account of the chief review expert.

[0065] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the talent review method provided by the above-mentioned methods, the method comprising: grouping candidates and experts according to the attribute information of the candidates and the attribute information of the experts; traversing all groups according to the attributes of the tasks to be reviewed to obtain candidate groups that match the attributes of the tasks to be reviewed; traversing the subject attributes of the experts in the candidate groups according to the subject attributes of the candidates to obtain an expert group that matches the subject attributes of the candidates; extracting the chief review expert from the expert group, and sending an invitation message to the account of the chief review expert.

[0066] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0067] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A talent evaluation method, characterized in that: Grouping candidates and experts according to their attribute information and expert attribute information; Traverse all groups according to the attributes of the task to be reviewed to obtain candidate groups that match the attributes of the task to be reviewed; According to the subject attributes of the candidate, traverse the subject attributes of the experts in the candidate group to obtain an expert group that matches the subject attributes of the candidate; A chief review expert is selected from the expert group, and an invitation message is sent to the account of the chief review expert.

2. The talent evaluation method according to claim 1, characterized in that: The subject attributes include first-level subject attributes and second-level subject attributes; after grouping the candidates and experts according to the attribute information of the candidates and the attribute information of the experts, the method further includes: Candidates and experts within each group are subcontracted based on their disciplinary relevance; After traversing the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group matching the subject attributes of the candidate, the method further includes: According to the first-level subject attribute of the candidate and the second-level subject attribute of the candidate, the expert group and / or all experts in each sub-contract are traversed to determine the expert group that matches the first-level subject attribute or the second-level subject attribute.

3. The talent evaluation method according to claim 2, characterized in that: After traversing the expert group and / or all experts in each sub-package according to the first-level subject attribute of the candidate and the second-level subject attribute of the candidate to determine the expert group matching the first-level subject attribute or the second-level subject attribute, the method further includes: Determining the subject accuracy of each expert according to the matching degree of the first-level subject attributes or the second-level subject attributes between the candidate and each expert in the expert group; The step of selecting a chief expert from the expert group and sending an invitation message to the chief expert's account includes: The chief review expert is selected from the expert group according to the subject accuracy ranking of each expert, and an invitation message is sent to the account of the chief review expert.

4. The talent evaluation method according to claim 1, characterized in that: The step of traversing the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group matching the subject attributes of the candidate includes: According to the subject attributes of the candidate, traverse the subject attributes of the experts in the candidate group to obtain a plurality of experts matching the subject attributes of the candidate; Experts having an avoidance relationship with the candidate are eliminated from the multiple experts, and the remaining experts serve as the expert group.

5. The talent evaluation method according to claim 1, characterized in that: The attribute information includes award attributes; and grouping the candidates and experts according to the attribute information of the candidates and the attribute information of the experts includes: The candidates and the experts are grouped according to the award attributes of the candidates and the award attributes of the experts.

6. The talent evaluation method according to any one of claims 1 to 5, characterized in that: After extracting the chief expert from the expert group and sending the invitation information to the account of the chief expert, the method further includes: Receiving identity authentication information returned by the account of the chief expert; The final chief review expert is determined based on the identity authentication information.

7. A talent evaluation device, characterized in that: include: A grouping module is used to group candidates and experts according to their attribute information and expert attribute information; A candidate group determination module is used to traverse all groups according to the attributes of the task to be reviewed and obtain candidate groups that match the attributes of the task to be reviewed; An expert group selection module is used to traverse the subject attributes of the experts in the candidate group according to the subject attributes of the candidate to obtain an expert group that matches the subject attributes of the candidate; The chief review expert extraction module is used to extract the chief review expert from the expert group and send an invitation message to the chief review expert's account.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the talent evaluation method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the talent evaluation method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the talent evaluation method according to any one of claims 1 to 6 is implemented.

Images