Career Assessment Method Based on Big Model

Abstract

The present invention is applicable to the field of career assessment technology, and in particular relates to a career assessment method based on a large model, the method comprising: S100: obtaining a self-evaluation filled out by the assessment subject on a career assessment questionnaire, extracting questions from the career assessment questionnaire, obtaining chat records of the assessment subject based on a preset crawling authority, and inputting the chat records into a pre-built semantic understanding model, outputting a segment in the chat record with the same semantics as the question, which is defined as a clear segment. By determining the clear segment, the present invention can determine the answer to the situational question, while enhancing the flexibility of the assessment, promoting the self-awareness of the assessment subject, and simplifying the assessment process. By determining the target segment, the answer to the related question can be determined, further improving the accuracy of the assessment. By determining the distinguishing items, the deviation in the self-evaluation can be compared, which can improve the self-awareness of the assessment subject and enhance the reliability of the assessment results.

Description

Technical Field

[0001] The present invention relates to the technical field of career assessment, and in particular to a career assessment method based on a large model. Background Art

[0002] Career assessment is an important means to help the assessed person understand his or her career inclinations, interests, abilities and values. Career assessment usually requires the use of questionnaires and tests. By analyzing the assessment results, the assessed person can identify the career direction that suits him or her. At the same time, companies can also provide personalized career development suggestions to employees or customers based on the assessment results to optimize talent allocation.

[0003] However, since career assessment needs to be conducted through questionnaires and tests, there are relatively large subjective factors. When filling out questionnaires or tests, the assessment subjects are easily affected by personal emotions and environmental factors, which may cause the results to deviate from the true career inclination or ability level; therefore, "how to use the chat records between the assessment subjects and the evaluators to correct the assessment results" is the technical problem that the present invention needs to solve. Summary of the Invention

[0004] The purpose of the present invention is to provide a career assessment method based on a large model to solve the problem raised in the above background technology of "how to use the chat records between the assessment subject and the assessor to correct the assessment results."

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A career assessment method based on a large model, the method comprising:

[0007] S100: Obtain the self-evaluation completed by the assessment subject on the career assessment questionnaire, extract the questions in the career assessment questionnaire, obtain the chat history of the assessment subject based on the preset crawling permissions, and input the chat history into a pre-built semantic understanding model. Output is the segments in the chat history that have the same semantics as the questions, which are defined as explicit segments. The questions are divided into scenario questions and related questions, and the answers to the scenario questions are traversed from the explicit segments.

[0008] S200: creating a queue corresponding to each of the related questions, inputting the chat records and related questions into the semantic understanding model, outputting segments with similar semantics to the related questions, defining them as similar segments, and determining the similarity of the similar segments. The similar segments are placed in a queue and arranged in descending order of similarity, and determining whether the similarity of the similar segment ranked first in the queue is greater than a preset threshold; if so, defining the similar segment ranked first as a target segment, and using the target segment to determine the answer to the related question; if not, finding the evaluator corresponding to the target segment, sending the related question to the evaluator, and receiving the social evaluation uploaded by the evaluator;

[0009] S300: Synchronize the answers and social evaluations into corresponding queues, integrate all queues and answers to situational questions to obtain social evaluations, compare the self-evaluation and social evaluations, determine the distinguishing items, and push the distinguishing items to a preset terminal.

[0010] Furthermore, the S100 includes:

[0011] Obtaining behavioral data of the assessment subject, where the behavioral data at least includes: historical assessment results and work experience;

[0012] The behavioral data were normalized and the self-assessments were corrected.

[0013] Furthermore, the S100 further includes:

[0014] Obtaining a friend list of the evaluation subject, and dividing the friend list into several levels;

[0015] The time and scope of the crawling authority are configured, and a corresponding relationship between the crawling authority and different levels is established.

[0016] Furthermore, the S100 further includes:

[0017] Numbering the questions, and inputting the questions into the semantic understanding model in sequence according to the numbers, outputting segments with the same semantics as the questions, and synchronizing the numbers;

[0018] The output segment is determined as a clear segment, and the mapping between the title, number and clear segment is edited.

[0019] Furthermore, the S200 includes:

[0020] Creating a semantic embedding model and linking it with the semantic understanding model, inputting the chat records and related questions into the semantic understanding model, and outputting similar segments, where one related question corresponds to several similar segments;

[0021] Using the semantic embedding model, similar segments with strong sentiment values ​​are deleted.

[0022] Furthermore, the S200 further includes:

[0023] Determining the confidence value of the self-assessment and dividing the confidence value into the related questions;

[0024] Based on the confidence value, the threshold is offset.

[0025] Furthermore, the S200 further includes:

[0026] A multi-friend evaluation mechanism is embedded in the queue. When the similarity of the target segment is less than a set value, a preset number of similar segments are selected from the front of the queue.

[0027] Based on the similar segments, a multi-friend dialogue is established, a group evaluation of the related questions is extracted, and the social evaluation is adjusted using the group evaluation.

[0028] Furthermore, the S300 includes:

[0029] Using an existing personality analysis model, the chat records are integrated to determine the personality label of the assessment subject and insert it into the distinguishing item;

[0030] A preset item comparison table is queried to determine an assessment suggestion, wherein the item comparison table is composed of personality label items and assessment suggestion items.

[0031] Furthermore, the S300 further includes:

[0032] The chat record or target segment corresponding to the distinguishing item is found, a reference is generated, and the reference is sent to a preset terminal.

[0033] Furthermore, the method further comprises:

[0034] receiving feedback from the assessment subject regarding the distinguishing items, correcting the self-assessment, and generating a career assessment form;

[0035] Construct a career assessment model, input the career assessment form into the career assessment model, identify career preferences, and configure career development strategies.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] By splitting the questions, the evaluation errors can be greatly reduced and the accuracy of social evaluation can be improved. By determining clear segments, the answers to situational questions can be determined, the flexibility of the evaluation can be enhanced, the self-awareness of the evaluation subjects can be promoted, and the evaluation process can be simplified. By determining the target segments, the answers to related questions can be determined, further improving the accuracy of the evaluation. By determining the distinguishing items, the deviations in self-evaluation can be compared, which greatly improves the self-awareness of the evaluation subjects and enhances the reliability of the evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A flowchart of a large-model-based career assessment method provided by an embodiment of the present invention;

[0039] Figure 2 A block diagram of the first sub-process of the large-model-based career assessment method provided in an embodiment of the present invention;

[0040] Figure 3 A second sub-flow diagram of the large-model-based career assessment method provided in an embodiment of the present invention;

[0041] Figure 4 This is a block diagram of the third sub-process of the large-model-based career assessment method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0043] In Example 1, Figure 1 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown and described in detail below:

[0044] S100: Obtain the self-evaluation filled out by the assessment subject on the career assessment questionnaire, extract the questions in the career assessment questionnaire, obtain the chat history of the assessment subject based on the preset crawling authority, and input the chat history into a pre-built semantic understanding model, and output the fragments in the chat history that have the same semantics as the questions, which are defined as clear fragments, and divide the questions into situational questions and related questions, and traverse the answers to the situational questions from the clear fragments.

[0045] Before the implementation of this application, it is necessary to organize the test takers to chat with multiple evaluators. The content of the chat has no clear direction, and the chat content is recorded with the permission of both parties.

[0046] Through testing, the test results of the evaluation subject on the career evaluation questionnaire are determined, and the test results are determined as self-evaluation; the questions in the career evaluation questionnaire are extracted, the capture permission of the evaluation subject's chat history is obtained, and the captured chat history is input into the semantic understanding model, wherein the semantic understanding model is a natural language processing model in the existing technology, which is mainly used to calculate the similarity between two text fragments. The specific calculation method can be cosine similarity, Euclidean distance, etc.

[0047] The semantic understanding model compares the question and the chat record, outputs the fragments in the chat record that have the same semantics as the question, and determines the obtained fragments as clear fragments, determines the question corresponding to the clear fragment as a situational question, and determines the part of the question other than the situational question as a related question; uses the clear fragment to determine the answer to the situational question.

[0048] S200: Create a queue corresponding to the related questions one by one, input the chat records and related questions into the semantic understanding model, output a segment with similar semantics to the related questions, define it as a similar segment and determine the similarity of the similar segment, put the similar segment into a queue, and arrange them in descending order of similarity, and judge whether the similarity of the similar segment ranked first in the queue is greater than a preset threshold; if so, define the similar segment ranked first as a target segment, and use the target segment to determine the answer to the related question; if not, find the evaluator corresponding to the target segment, send the related question to the evaluator, and receive the social evaluation uploaded by the evaluator.

[0049] A queue is created for each related question, and the chat history and related questions are input into the semantic understanding model again. The output is a fragment with similar semantics to the related question, namely a similar fragment, and the similarity between each similar fragment and the related question is output at the same time. The greater the similarity, the higher the consistency between the question and the similar fragment in terms of semantic themes, keywords and structure, and the lower the difficulty of using similar fragments to determine the answer to the related question. The order of similar fragments in the queue is adjusted according to the order of similarity from large to small.

[0050] If the similarity of the first-ranked similar segment is greater than a preset threshold, the first-ranked similar segment is defined as the target segment, and the target segment and the related question are input into the pre-built machine learning model to output the answer to the related question.

[0051] If the similarity of the first-ranked similar segment is less than or equal to a preset threshold, the evaluator corresponding to the target segment is found, and the associated question is sent to the evaluator for the evaluator to perform social evaluation on the associated question.

[0052] For example, a certain career assessment test paper is divided into 10 questions, of which four questions numbered 2, 3, 7 and 9 are related questions. Taking the related question numbered 2 as an example, find the fragments in the chat record whose similarity is greater than the threshold, that is, similar fragments. It should be noted that there may be one or more similar fragments; sort the similar fragments in descending order of similarity, and form a queue, and determine the similar fragment ranked first as the target fragment. If the similarity of the target fragment is greater than the threshold, it means that the answer to related question 2 can be determined based on this target fragment; conversely, if the target fragment is less than or equal to the threshold, it means that the answer to related question 2 cannot be determined based on the chat record at this time, then it is necessary to determine the evaluator of the target fragment in the chat record, send related question 2 to the evaluator, and determine the social evaluation.

[0053] S300: Synchronize the answers and social evaluations into corresponding queues, integrate all queues and answers to situational questions to obtain social evaluations, compare the self-evaluation and social evaluations, determine the distinguishing items, and push the distinguishing items to a preset terminal.

[0054] Determine the answers or social evaluations of all related questions, and integrate the answers to the situational questions. By comparing them with the self-evaluation of the subject, find out the questions where there are differences between the self-evaluation and the social evaluation, that is, the distinguishing items. The distinguishing items also indicate that there are differences between the self-evaluation of the subject on the corresponding questions in the career assessment questionnaire and the social evaluation given by the evaluator. Send the distinguishing items to the preset terminal and re-determine the answers to the distinguishing items, where the preset terminal can be the terminal of the subject.

[0055] In Example 2, Figure 2 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S100 is described in detail below:

[0056] S101: Obtaining behavioral data of the evaluation subject, wherein the behavioral data at least includes: historical evaluation results and work experience.

[0057] In addition to determining the self-evaluation based on the subjects' completed results, the behavioral data of the subjects should be obtained, and the self-evaluation should also be revised based on the subjects' behavioral data. This is because the filling out of the career assessment questionnaire is relatively random, and revising the self-evaluation can greatly improve the accuracy of the assessment results.

[0058] S102: Standardize the behavior data and revise the self-evaluation.

[0059] Before using behavioral data to correct self-evaluation, behavioral data from multiple sources need to be standardized. The specific standardization process should be determined according to the specific source.

[0060] In Example 3, Figure 2 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S100 is further described in detail below.

[0061] S103: Editing the friend list of the evaluation subject, and dividing the friend list into several levels.

[0062] The friend list here refers to the collection of evaluators who chat with the evaluation subject, and the friend list of the evaluation subject is divided into several levels.

[0063] S104: configuring the time and scope of the crawling authority, and establishing a corresponding relationship between the crawling authority and different levels.

[0064] Determine the time and scope of crawling permissions for each level; for example, only chat records within a fixed time period within a certain level in the friend list can be crawled.

[0065] In Example 4, Figure 2 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S100 is further described in detail below.

[0066] S105: Numbering the questions, and inputting the questions into the semantic understanding model in sequence according to the numbers, outputting segments with the same semantics as the questions, and synchronizing the numbers.

[0067] The questions are numbered and input into the semantic understanding model in the order of the numbers. Each question is compared with the chat record in turn, and the output is a fragment with the same semantics as the question. At the same time, the number of each fragment is determined, so as to establish a correspondence between the fragment and the question.

[0068] S106: Determine the output segment as a clear segment, and edit the mapping between the title, number and clear segment.

[0069] In the above process, the segments output by the semantic understanding model are identified as clear segments; the number of each question and the number of each clear segment are recorded.

[0070] In Example 5, Figure 3 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S200 is described in detail below.

[0071] S201: Create a semantic embedding model and link it with the semantic understanding model, input the chat records and related questions into the semantic understanding model, and output similar segments, where one related question corresponds to several similar segments.

[0072] Using the semantic understanding model, we find segments in the chat history that have similar semantics to the related questions and identify them as similar segments. Common sense tells us that a related question may correspond to one similar segment or multiple similar segments.

[0073] S202: Utilizing the semantic embedding model, delete similar segments with strong sentiment values.

[0074] A semantic embedding model is established, and the sentiment value of each similar segment is calculated using the semantic embedding model. If the sentiment value is greater than a preset threshold, it is called a strong sentiment value. The step of calculating the sentiment value of similar segments includes at least: querying a preset sentiment dictionary to determine the sentiment value of a single word in the similar segment, and performing weighted summation to determine the total sentiment value of all words; then using the semantic embedding model to determine the sentiment value of the sentence in the similar segment, superimposing the sentiment values ​​of the similar segment, and deleting the similar segment with a strong sentiment value from the queue.

[0075] In Example 6, Figure 3 The implementation process of the career assessment method based on the large model provided by the embodiment of the present invention is shown. S200 is further described in detail below.

[0076] S203: Determine the confidence value of the self-assessment, and divide the confidence value into the related questions.

[0077] During the self-evaluation process of the assessment subject, the assessment subject's confidence value for each question is determined, where the confidence value is the assessment subject's degree of confidence in each question. The higher the confidence value, the more certain the assessment subject is about the answer to the corresponding related question.

[0078] S204: Deviate from the threshold based on the confidence value.

[0079] Based on the confidence value, the answers to the corresponding related questions are deviated; for example, if the assessment subject has a high confidence value for a certain related question, the threshold of the corresponding queue should be lowered.

[0080] In Example 7, Figure 3 The implementation process of the career assessment method based on the large model provided by the embodiment of the present invention is shown. S200 is further described in detail below.

[0081] S205: embedding a multi-friend evaluation mechanism into the queue, and when the similarity of the target segment is less than a set value, selecting a preset number of similar segments from the front of the queue.

[0082] A multi-friend evaluation mechanism is embedded in the queue. If the similarity of the target segment is less than a set value, it will be evaluated by multiple evaluators. The set value is pre-determined by professionals, and the selection range will be expanded to select multiple similar segments from the front of the queue.

[0083] S206: Based on the similar segments, a multi-friend dialogue is established, a group evaluation of the related questions is extracted, and the social evaluation is adjusted using the group evaluation.

[0084] The evaluators corresponding to multiple similar fragments are traced back, and a multi-friend dialogue is established. The corresponding related questions are sent to the multi-friend dialogue, the collected feedback is determined as a group evaluation, and the social evaluation is adjusted.

[0085] In actual use, if the related questions are sent to a certain evaluator, the subjective factors of the social evaluation will be relatively large, which will also cause the social evaluation to deviate from the true value; therefore, sending the related questions to multiple evaluators and having the evaluators who received the related questions conduct the evaluation can improve the authenticity of the social evaluation.

[0086] In Example 8, Figure 4 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S300 is described in detail below.

[0087] S301: Utilizing an existing personality analysis model, the chat records are integrated to determine the personality label of the evaluation subject, and the label is inserted into the distinguishing item.

[0088] Utilize the personality analysis model in the existing technology to determine the personality label of the evaluation subject according to the chat records of the evaluation subject, and adjust the self-evaluation of the evaluation subject.

[0089] S302: Query a preset item comparison table to determine an evaluation suggestion, wherein the item comparison table consists of personality label items and evaluation suggestion items.

[0090] After determining the personality label of the assessment subject, we query the item comparison table, determine the assessment suggestions, and give suggestions on the assessment subject's career planning. This suggestion is also the assessment suggestion.

[0091] In Example 9, Figure 4 The implementation process of the career assessment method based on a large model provided by an embodiment of the present invention is shown. S300 is further described in detail below.

[0092] S303: Find the chat record or target segment corresponding to the distinguishing item, generate a reference, and send the reference to a preset terminal.

[0093] By comparing the self-evaluation of the evaluation subject, the social evaluation given by the evaluator and the answers to the related questions determined using the chat records, the distinguishing items can be obtained, and the chat records or social evaluations corresponding to the distinguishing items can be found and sent to the preset terminal, where the preset terminal is the evaluation subject's terminal.

[0094] In Example 10, different from Example 1, in this embodiment of the present invention, the method further includes:

[0095] receiving feedback from the assessment subject regarding the distinguishing items, correcting the self-assessment, and generating a career assessment form;

[0096] Construct a career assessment model, input the career assessment form into the career assessment model, identify misunderstandings, and configure career development strategies.

[0097] After sending the distinguishing items to the evaluated subjects, the evaluated subjects will adjust their self-evaluation, use the changes in the self-evaluation before and after the adjustment to generate a career evaluation form, and input the career evaluation form into the career evaluation model to identify the parts of the evaluated subjects' misunderstanding of their own evaluation; use the self-evaluation to generate a career development strategy, and use the misunderstanding to adjust the career development strategy.

[0098] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The career assessment method based on the large model is characterized by: The method comprises: S100: Obtain the self-evaluation completed by the assessment subject on the career assessment questionnaire, extract the questions in the career assessment questionnaire, obtain the chat history of the assessment subject based on the preset crawling permissions, and input the chat history into a pre-built semantic understanding model. Output is the segments in the chat history that have the same semantics as the questions, which are defined as explicit segments. The questions are divided into scenario questions and related questions, and the answers to the scenario questions are traversed from the explicit segments. S200: creating a queue corresponding to each of the related questions, inputting the chat records and related questions into the semantic understanding model, outputting segments with similar semantics to the related questions, defining them as similar segments, and determining the similarity of the similar segments. The similar segments are placed in a queue and arranged in descending order of similarity, and determining whether the similarity of the similar segment ranked first in the queue is greater than a preset threshold; if so, defining the similar segment ranked first as a target segment, and using the target segment to determine the answer to the related question; if not, finding the evaluator corresponding to the target segment, sending the related question to the evaluator, and receiving the social evaluation uploaded by the evaluator; S300: Synchronizing the answers and social evaluations to corresponding queues, integrating all queues and answers to the scenario questions to obtain social evaluations, comparing the self-evaluation and the social evaluations, determining differences, and pushing the differences to a preset terminal; The S200 includes: Creating a semantic embedding model and linking it with the semantic understanding model, inputting the chat records and related questions into the semantic understanding model, and outputting similar segments, where one related question corresponds to several similar segments; Using the semantic embedding model, similar segments with strong sentiment values ​​are deleted; The S200 further includes: Determining the confidence value of the self-assessment and dividing the confidence value into the related questions; Deviating the threshold based on the confidence value; The S200 further includes: A multi-friend evaluation mechanism is embedded in the queue. When the similarity of the target segment is less than a set value, a preset number of similar segments are selected from the front of the queue. Based on the similar segments, a multi-friend conversation is established, a group evaluation of the related questions is extracted, and the social evaluation is adjusted using the group evaluation; The S300 includes: Using an existing personality analysis model, the chat records are integrated to determine the personality label of the assessment subject and insert it into the distinguishing item; Querying a preset item comparison table to determine assessment suggestions, wherein the item comparison table consists of personality label items and assessment suggestion items; The S300 further includes: Finding the chat record or target segment corresponding to the distinguishing item, generating a reference, and sending the reference to a preset terminal; The method further comprises: receiving feedback from the assessment subject regarding the distinguishing items, correcting the self-assessment, and generating a career assessment form; Construct a career assessment model, input the career assessment form into the career assessment model, identify career preferences, and configure career development strategies.

2. The career assessment method based on a large model according to claim 1 is characterized in that: The S100 includes: Obtaining behavioral data of the assessment subject, where the behavioral data at least includes: historical assessment results and work experience; The behavioral data were normalized and the self-assessments were corrected.

3. The career assessment method based on a large model according to claim 1 is characterized in that: The S100 further includes: Obtaining a friend list of the evaluation subject, and dividing the friend list into several levels; The time and scope of the crawling authority are configured, and a corresponding relationship between the crawling authority and different levels is established.

4. The career assessment method based on a large model according to claim 1 is characterized in that: The S100 further includes: Numbering the questions, and inputting the questions into the semantic understanding model in sequence according to the numbers, outputting segments with the same semantics as the questions, and synchronizing the numbers; The output segment is determined as a clear segment, and the mapping between the title, number and clear segment is edited.

Images