Intelligent back-checking resume analysis and verification method and device

Abstract

The application provides a kind of based on intelligent backtracking resume brief analysis verification method, it is related to data processing technology, wherein, method includes: response receives the resignation trigger signal of corresponding staff end, generates backtracking structure tree based on the staff employment information of corresponding staff during by the staff end uploaded by original job end;Response receives the backtracking authorization request sent by staff end, generates temporary key bound with the authorization open information contained in the backtracking authorization request based on the authorization open information;Response receives the backtracking interaction request containing the temporary key sent by backtracking end, carries out check based on the temporary key, and after check, according to the authorization open information, obtains the staff employment information located in backtracking structure tree;Obtain the resume information corresponding to the staff end, verify the resume information with the staff employment information, and generate verification report based on the verification result.The application at least improves the backtracking efficiency.

Description

Technical Field

[0001] This invention relates to data processing technology, and more particularly to an intelligent method and apparatus for background check resume analysis and verification. Background Technology

[0002] Background checks are a core safeguard in the recruitment process for companies to prevent employment risks and ensure recruitment quality. Their results directly impact the accuracy of talent selection and team stability. With increasing talent mobility and the growing prominence of workplace integrity issues, problems such as exaggerated academic credentials and fabricated work experience are becoming more frequent, leading to potential legal disputes and business losses for companies.

[0003] Traditional background check methods rely on manual telephone verification and paper certificate verification. The background check process is cumbersome and time-consuming, with an average completion cycle of 3-5 days. This not only consumes a lot of the human resources department's energy, but may also lead to the loss of high-quality candidates due to process delays.

[0004] Therefore, there is an urgent need to provide an intelligent background check resume analysis and verification method and device that can improve the efficiency of background checks. Summary of the Invention

[0005] In view of the above problems, the present invention is proposed to provide an intelligent background check resume analysis and verification method and apparatus to overcome or at least partially solve the above problems.

[0006] According to one aspect of the present invention, an intelligent background check resume analysis and verification method is provided, characterized in that it includes: The system responds to the resignation trigger signal received from the corresponding employee's end and generates a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer. In response to a background check authorization request sent by an employee, a temporary key bound to the authorization opening information is generated based on the authorization opening information contained in the background check authorization request. The system receives a background check interaction request containing the temporary key sent by the background check unit, performs verification based on the temporary key, and obtains the employee appointment information located in the background check structure tree according to the authorized open information after the verification is successful. Obtain the resume information of the corresponding employee, verify the resume information with the employee's employment information, and generate a verification report based on the verification results.

[0007] Optionally, in the method according to the present invention, the response receiving the resignation trigger signal from the corresponding employee's end, and generating a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employing end, includes: The system responds to the resignation trigger signal received from the corresponding employee's end and obtains the work data and evaluation data uploaded by the original employer during the corresponding employment period from the employee's end. The work data and evaluation data are integrated into employee employment information, and the employee employment information is archived hierarchically to generate a background check structure tree.

[0008] Optionally, in the method according to the present invention, the employee employment information is archived hierarchically to generate a background check structure tree, including: The work data includes all work sub-data corresponding to different work dimensions, and the evaluation data includes all evaluation sub-data corresponding to different evaluation dimensions. Establish an employee node corresponding to the employee's end, and establish a parent node for the corresponding work data and an evaluation parent node for the corresponding evaluation data downwards from the employee node; A working sub-node corresponding to each working sub-data is established downwards along the working parent node, and an evaluation sub-node corresponding to each evaluation sub-data is established downwards along the evaluation parent node, thus obtaining the background check structure tree. Configure an authorization switch identifier for each child node, and determine the access permissions of the corresponding child node by matching the authorization open information based on the authorization switch identifier.

[0009] Optionally, the method according to the present invention further includes: in response to the existence of a work sub-data and an evaluation sub-data corresponding to the same work item and having a project association relationship, based on the background check structure tree, summarizing the work sub-nodes corresponding to the work sub-data and the evaluation sub-nodes corresponding to the evaluation sub-data into the same project association group; In response to the authorization open information matched based on the authorization switch identifier, which only allows the working sub-node to access, the access permission of the evaluation sub-node is simultaneously determined to be allowed. In response to the authorization open information matched based on the authorization switch identifier, which only allows the evaluation sub-node to access, if the access permission of the corresponding working sub-node is not allowed, then the access permission of the evaluation sub-node is determined to be not allowed.

[0010] Optionally, in the method according to the invention, the response to the existence of work sub-data and evaluation sub-data corresponding to the same work item and having a project association relationship includes: Obtain the project identification information carried by the working sub-data and the project identification information carried by the evaluation sub-data; If the project identifier information of any working sub-data is consistent with the project identifier information of any evaluation sub-data, it is determined that the working sub-data and the evaluation sub-data have a project association relationship.

[0011] Optionally, in the method according to the present invention, generating a temporary key bound to the authorization open information based on the authorization open information included in the background check authorization request includes: Obtain the identity identification code corresponding to the employee's terminal, and determine all authorization switch identifiers included in the corresponding authorization open information based on the background check authorization request; Using the request time of the background check authorization request as a random seed, the identity code, all authorization switch identifiers, and the request time are randomly sorted to obtain an information sequence; The information sequence is encrypted and transformed based on a hash algorithm, a temporary key is generated based on the obtained hash string, a preset number of times threshold is configured for the temporary key, and the hash string and the identity code are determined as the verification set of the corresponding temporary key.

[0012] Optionally, in the method according to the present invention, the step of verifying based on the temporary key and, after successful verification, obtaining employee employment information located in the background check structure tree according to the authorized open information includes: The system retrieves the number of times the corresponding temporary key has been used and responds if the number of uses exceeds a preset threshold. If the number of uses exceeds the threshold, the system determines that the verification has failed. Otherwise, it extracts the hash string and identity code from the temporary key. The verification set based on the hash string, identity code and corresponding temporary key is compared, and if the comparison result is that the information is the same, the verification is confirmed to be successful, and the number of uses is accumulated. Determine the authorization open information corresponding to the temporary key, determine the access permissions of the corresponding child node as allowed based on each authorization switch identifier included in the authorization open information, and generate an allowed list to be sent to the background check end based on all the child nodes that are allowed to access. The query intent of the corresponding background check client is determined based on the preset interaction method, and the employee employment information located in the background check structure tree is obtained based on the matching results of the query intent and the allowed list.

[0013] Optionally, in the method according to the present invention, the step of identifying the query intent of the corresponding background check end based on a preset interaction method, and obtaining the employee employment information located in the background check structure tree based on the matching result of the query intent and the allowed list, includes: The default interaction mode is voice call mode. Voice recognition technology is used to convert the voice questions from the background check terminal into query text, and the extracted working keywords in the query text are identified as the query intent. If the similarity between the query intent and any sub-node in the allowed list is greater than a preset similarity, the query intent and the allowed list are considered to be matched successfully. Based on the employee's employment information, the retrieved employee employment information corresponding to the sub-node is used as feedback information and broadcasted via voice. Otherwise, the preset rejection information is used as feedback information and broadcasted via voice.

[0014] Optionally, in the method according to the present invention, the step of identifying the query intent of the corresponding background check end based on a preset interaction method, and obtaining the employee employment information located in the background check structure tree based on the matching result of the query intent and the allowed list, includes: The default interaction mode is port access mode, and the node selection information of the query command obtained from the corresponding background check terminal is determined as the query intent. The response determines that the child node selected by the corresponding node based on the query intent is the same as any child node in the allowed list. If the query intent and the allowed list match successfully, the employee employment information of the retrieved corresponding child node is sent to the background check terminal as feedback information. Otherwise, the preset rejection information is sent to the background check terminal as feedback information.

[0015] Optionally, in the method according to the present invention, verifying the resume information with the employee employment information includes: Hide all child nodes in the background check structure tree that are outside the allowed list to obtain the verification structure tree; The resume information is divided into nodes based on the corresponding verification structure tree to obtain each partition node; The response determines that any partitioning node has a node mapping relationship with the child node corresponding to the employee's employment information based on the verification structure tree. It compares the employee's employment information with the partitioning data corresponding to the partitioning node, and determines that the employee's employment information is consistent with the partitioning data based on the comparison result. Based on the verification structure tree, it marks the child node as having passed the verification, and otherwise marks it as having failed the verification. If any partition node does not have a node mapping relationship with the child node corresponding to the employee's employment information, the missing third tag is verified based on the verification structure tree.

[0016] Optionally, in the method according to the present invention, generating a verification report based on the verification result includes: Establish an interaction record table corresponding to the preset interaction methods, and based on the interaction record table, create interaction record bars according to the query intent and feedback information of the corresponding child node; Generate a verification report, wherein the verification report includes a first area for filling the interaction record table, a second area for filling the verification structure tree, and a third area for filling the resume information.

[0017] According to another aspect of the present invention, an intelligent background check resume analysis and verification device is provided, comprising: The data accumulation module is used to respond to the resignation trigger signal received from the corresponding employee's end and generate a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer. The authorization control module is used to respond to background check authorization requests sent by employees, and generate a temporary key bound to the authorization opening information based on the authorization opening information contained in the background check authorization request; The interaction execution module is used to respond to receiving a background check interaction request containing the temporary key sent by the background check terminal, perform verification based on the temporary key, and after the verification is successful, obtain the employee appointment information located in the background check structure tree according to the authorized open information. The verification report module is used to obtain the resume information of the corresponding employee, verify the resume information with the employee's employment information, and generate a verification report based on the verification results.

[0018] The beneficial effects of this invention are as follows: 1. This invention generates a background check structure tree when an employee leaves the company. It relies on the original employment information uploaded by the original employer to store work and evaluation data in a fixed manner, avoiding the risk of information being forgotten or tampered with after the employee leaves the company. This ensures the objectivity and accuracy of background check data from the source and provides a reliable benchmark for verification.

[0019] 2. This invention generates and binds temporary keys based on authorized open information, and with refined authorization control, it only opens information within the scope of employee authorization to the background check end, effectively preventing privacy leakage and fully complying with relevant regulations on personal information protection.

[0020] 3. This invention achieves unmanned background check process through automated verification of temporary keys, dual-mode interactive information retrieval, and node-based intelligent verification of resume and employment information. It completely replaces the traditional manual telephone verification and manual comparison mode, compressing the background check cycle from several days to hours and significantly reducing the energy input of the human resources department.

[0021] 4. Based on the node-based verification and three-category marking system of the background check structure tree, this invention clearly presents the consistency, inconsistency, and missing information. Combined with the structured verification report, the background check results are clear at a glance, helping companies quickly identify resume fraud, scientifically select talents, and reduce employment risks. Attached Figure Description

[0022] Figure 1 A flowchart of an intelligent background check resume analysis and verification method according to an embodiment of the present invention is shown; Figure 2 A schematic diagram of the background check structure tree in this embodiment is shown; Figure 3 A structural block diagram of an intelligent background check resume analysis and verification device according to another embodiment of the present invention is shown. Detailed Implementation

[0023] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0024] To address the problems existing in the prior art, the inventors proposed the solution of this invention. One embodiment of this invention provides an intelligent background check resume analysis and verification method. This method can be executed on a computing device, which can be understood as a terminal or server with data processing capabilities, such as an enterprise human resources server, a background check service platform server, or a computer.

[0025] Figure 1 A flowchart of an intelligent background check resume analysis and verification method according to an embodiment of the present invention is shown, as follows: Figure 1 As shown, the method proposed in this embodiment begins with step S1, which includes the following: S1. Response: Receive the resignation trigger signal from the corresponding employee's end and generate a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer.

[0026] For example, in this embodiment, the server of the background check service platform can receive employee departure information synchronized from the original employer's human resources management system, generate a departure trigger signal for the corresponding employee, and further, based on the departure trigger signal, the server can send a data retrieval instruction to the original employer to obtain the employee employment information uploaded by the original employer during the employee's employment period, and generate a standardized background check structure tree based on the employee employment information. Here, the employee refers to the personal operating terminal corresponding to the departing employee, which is the owner and authorizing entity of the background check information; the original employer refers to the human resources management system terminal corresponding to the company where the employee worked before leaving, which is the legitimate provider of the employee employment information; and the background check terminal refers to the human resources background check operating terminal corresponding to the new company where the employee intends to join, which is the initiator and verifier of the background check action.

[0027] It can be noted that in this embodiment, the background check structure tree is obtained based on the employee's departure process, which can fix and persistently store the employee's employment information. This solves the problem in traditional background checks where the original contact person leaves or the information is forgotten many years after the employee leaves the company, resulting in no background check data to be found. At the same time, the employee employment information uploaded by the original employer has the immutability based on the employee's perspective, which ensures the authenticity of the background check information from the source, and provides an accurate and reliable data foundation for subsequent automated background checks and verifications.

[0028] Furthermore, in this embodiment, the aforementioned "responding to the resignation trigger signal received from the corresponding employee's end, and generating a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employing end" may also include the following steps: The system responds to the resignation trigger signal received from the corresponding employee's end and obtains the work data and evaluation data uploaded by the original employer during the corresponding employment period from the employee's end. The work data and evaluation data are integrated into employee employment information, and the employee employment information is archived hierarchically to generate a background check structure tree.

[0029] For example, in this embodiment, the employee employment information uploaded by the original employment client can be divided into two main categories of data. One category is standardized work data, including structured data that can be automatically synchronized by the human resources system, such as the employee's start date, end date, job position, department, salary standard, projects under responsibility, and job duties. The other category is non-standardized evaluation data, including unstructured data manually entered, such as the performance evaluation of the employee's immediate supervisor, the collaboration evaluation of project colleagues, and performance appraisal results. Here, the server integrates the two types of data into complete employee employment information and converts the scattered employment information into a structured background check tree structure through hierarchical archiving. This allows each piece of employment information to have a corresponding hierarchical affiliation, thereby providing a clear structural foundation for subsequent refined authorization and control.

[0030] Furthermore, in this embodiment, the aforementioned "hierarchical archiving of employee employment information to generate a background check structure tree" may also include the following steps: The work data includes all work sub-data corresponding to different work dimensions, and the evaluation data includes all evaluation sub-data corresponding to different evaluation dimensions. Establish an employee node corresponding to the employee's end, and establish a parent node for the corresponding work data and an evaluation parent node for the corresponding evaluation data downwards from the employee node; A working sub-node corresponding to each working sub-data is established downwards along the working parent node, and an evaluation sub-node corresponding to each evaluation sub-data is established downwards along the evaluation parent node, thus obtaining the background check structure tree. Configure an authorization switch identifier for each child node, and determine the access permissions of the corresponding child node by matching the authorization open information based on the authorization switch identifier.

[0031] For example, in this embodiment, the hierarchical construction of the background check structure tree can be specifically implemented based on the following method steps: First, the server can perform dimensional splitting on the integrated work data to extract all work sub-data corresponding to different work dimensions. For example, work sub-data corresponding to job information, work sub-data corresponding to project experience, and work sub-data corresponding to salary information. At the same time, it can also perform dimensional splitting on the evaluation data to extract all evaluation sub-data corresponding to different evaluation dimensions. For example, evaluation sub-data corresponding to superior evaluation, evaluation sub-data corresponding to colleague evaluation, and evaluation sub-data corresponding to project evaluation. This allows each piece of detailed job information to correspond to an independent sub-data unit. Next, based on the employee's unique identity information, the server establishes an employee node corresponding to the employee's end, which serves as the root node of the background check structure tree. It then splits down the employee node into two first-level parent nodes: the work parent node corresponding to all work data and the evaluation parent node corresponding to all evaluation data, thereby realizing the major classification of job information. Subsequently, the server moves downwards along the parent node of the work data, creating independent child nodes for each work data item. Simultaneously, it moves downwards along the parent node of the evaluation data, creating independent child nodes for each evaluation data item, ultimately forming a complete background check structure tree. This can be explained as follows: Figure 2 This embodiment shows a hierarchical diagram of the background check structure tree, based on Figure 2 As can be seen from the content, the background check structure tree has the employee node as the root node, with a work parent node and an evaluation parent node under it. Each of these parent nodes has multiple sub-nodes for work and evaluation. Among these, in... Figure 2 In the example, the background check structure tree includes employee node A, work parent node B, and efficiency parent node C. The work parent node B includes work child nodes B1, B2, B3, and B4 corresponding to different work dimensions, and the efficiency parent node C includes efficiency child nodes C1, C2, C3, and C4 corresponding to different efficiency dimensions. Finally, the server can configure a unique authorization switch identifier for each child node in the background check structure tree. It can be noted that the authorization switch identifier is used to mark the authorization number of the corresponding child node. Subsequently, the access permissions of each child node can be determined by matching the authorization open information with the authorization switch identifier.

[0032] It can be noted that this embodiment, through the hierarchical background check structure tree design, can transform scattered employee employment information into standardized and manageable structured data. Configuring an independent authorization switch identifier for each child node also achieves refined access control of background check information. Employees can independently choose the information dimensions that are open, avoiding the leakage of unauthorized information, while providing a clear basis for subsequent matching of authorized and open information.

[0033] Furthermore, it should be noted that in background check practice, certain work data and evaluation data are often strongly correlated around the same work project, and together they constitute a complete description of an employee's performance. For example, the project development responsibilities and project outcome evaluations of technical employees, and the activity execution content and collaboration effect feedback of operational employees, all need to be considered together to comprehensively judge the employee's actual work ability and performance. Therefore, if only the two types of data are independently authorized and controlled, it may lead to problems such as only opening work data resulting in a lack of evaluation background, or only opening evaluation data resulting in a lack of evidence for the content, which may cause the background checker to misinterpret the information and affect the accuracy of the background check results. Based on this, this embodiment further includes the following steps: In response to the existence of work sub-data and evaluation sub-data corresponding to the same work project and having a project association relationship, based on the background check structure tree, the work sub-nodes corresponding to the work sub-data and the evaluation sub-nodes corresponding to the evaluation sub-data are aggregated into the same project association group. In response to the authorization open information matched based on the authorization switch identifier, which only allows the working sub-node to access, the access permission of the evaluation sub-node is simultaneously determined to be allowed. In response to the authorization open information matched based on the authorization switch identifier, which only allows the evaluation sub-node to access, if the access permission of the corresponding working sub-node is not allowed, then the access permission of the evaluation sub-node is determined to be not allowed.

[0034] For example, in this embodiment, for work data and evaluation data corresponding to the same work project, linkage authorization control can be achieved through project association groups. The specific implementation method is as follows: First, the server identifies the work sub-data and evaluation sub-data that have project-related relationships in the background check structure tree. For example, a certain work sub-data is: XX Commercial Plaza Project Manager, and the corresponding evaluation sub-data is: XX Commercial Plaza Project Performance Evaluation. It can be seen that the two correspond to the same work project, that is, they have a project-related relationship. At this time, the server can summarize the corresponding work sub-nodes and evaluation sub-nodes into the same project-related group to achieve the binding of related nodes. Next, the server can configure two-way authorization rules for the project association group: In one scenario, if an employee's authorized access information is only allowed to work sub-nodes within the project's associated group, it indicates that the employee has already accessed the project's core work information. Since the corresponding evaluation information is a supplementary explanation of the project's performance, access permissions for the corresponding evaluation sub-nodes can be opened simultaneously. This avoids additional leakage of sensitive information and ensures the integrity of the background check information, preventing the background checker from only obtaining work data and failing to fully understand the employee's performance. In another scenario, if an employee's authorized access information is only permitted to evaluation sub-nodes within the project's associated group, while the corresponding work sub-nodes are not authorized to access it, the evaluation sub-data will lack the corresponding project background support. In this case, the background investigation team will not be able to accurately understand the specific scenario of the evaluation content, which may lead to information misunderstanding. At the same time, it does not comply with the principle of minimum necessary authorization. Therefore, the access permission of the evaluation sub-node will be set to not be allowed to avoid invalid and distorted information transmission.

[0035] It can be noted that this embodiment solves the problems of isolated and distorted background check information and misunderstanding caused by independent node authorization in the prior art by using the two-way authorization rules of the corresponding project association group. Under the premise of protecting employee privacy and security and following the authorization intention, it maximizes the integrity and accuracy of background check information, so that the information obtained by the background check end can truly and comprehensively reflect the employee's performance, and further improve the reference value of the background check results.

[0036] Furthermore, in this embodiment, the aforementioned "responding to the existence of work sub-data and evaluation sub-data corresponding to the same work item and having a project association relationship" may further include the following steps: Obtain the project identification information carried by the working sub-data and the project identification information carried by the evaluation sub-data; If the project identifier information of any working sub-data is consistent with the project identifier information of any evaluation sub-data, it is determined that the working sub-data and the evaluation sub-data have a project association relationship.

[0037] For example, in this embodiment, the determination of project association is based on unique project identification information. That is, when the original job client uploads work data and evaluation data, it will configure unique project identification information for each project's corresponding work sub-data and evaluation sub-data. Here, the project identification information can be a unique identifier such as project number or project unique code. The server compares the project identification information of the work sub-data and the evaluation sub-data, and when the project identification information of the two is completely consistent, it can determine that the two correspond to the same work project and have a project association relationship.

[0038] It can be explained that using project identification information as the sole criterion for judgment can make the determination of project associations accurate and reproducible, avoid association errors caused by differences in project name descriptions, and also enable automatic binding of associated nodes without manual intervention, further improving the automation level of background check structure tree construction.

[0039] Step S2 includes the following: responding to a background check authorization request sent by an employee, and generating a temporary key bound to the authorization open information based on the authorization open information contained in the background check authorization request.

[0040] For example, in this embodiment, when an employee is about to join a new company and needs to grant background check permissions to the background check server, the employee can send a background check authorization request to the server through the employee's client. The background check authorization request includes authorization information that the employee selects independently. Specifically, the authorization information is a set of authorization switch identifiers corresponding to the sub-nodes that the employee allows the background check server to access. After receiving the background check authorization request, the server can generate a temporary key that is uniquely bound to the authorization scope based on the authorization information and synchronize the temporary key to the employee's client. The employee's client then forwards the temporary key to the background check server, which serves as the sole legal credential for the background check server to access the background check information.

[0041] It can be explained that the temporary key is uniquely bound to the authorized open information, ensuring that the background check end can only obtain the corresponding background check information within the scope authorized by the employee. This prevents the risk of the background check end accessing information beyond the scope from the root. At the same time, the temporary key has time limit and usage limit, avoiding the risk of long-term information leakage caused by key leakage, and greatly improving the compliance and security of the background check process.

[0042] Furthermore, in this embodiment, the aforementioned "generating a temporary key bound to the authorization open information based on the authorization open information contained in the background check authorization request" may further include the following steps: Obtain the identity identification code corresponding to the employee's terminal, and determine all authorization switch identifiers included in the corresponding authorization open information based on the background check authorization request; Using the request time of the background check authorization request as a random seed, the identity code, all authorization switch identifiers, and the request time are randomly sorted to obtain an information sequence; The information sequence is encrypted and transformed based on a hash algorithm, a temporary key is generated based on the obtained hash string, a preset number of times threshold is configured for the temporary key, and the hash string and the identity code are determined as the verification set of the corresponding temporary key.

[0043] For example, in this embodiment, the generation of the temporary key can be specifically implemented based on the following method steps: First, the server obtains the unique identification code corresponding to the employee. This identification code can be a unique identification code such as the employee's ID card number or unique employee number. At the same time, based on the background check authorization request, the server parses out all the authorization switch flags contained in the authorization open information selected by the employee to clarify the specific scope of this authorization. Next, the server uses the request time of the background check authorization request as a random seed to randomly shuffle and sort the identity code, all authorization switch identifiers, and the request time to obtain a fixed and reproducible information sequence. It can be noted that, in this embodiment, using the request time as a random seed not only ensures the randomness of the information sequence generated each time and improves the key's anti-cracking capability, but also allows the same information sequence to be restored based on the request time in the verification process, ensuring the reproducibility of the verification process and solving the problem that pure random sorting cannot perform bidirectional verification. Subsequently, the server encrypts and transforms the information sequence using a preset hash algorithm to generate a unique hash string. A temporary key is generated based on this hash string, and a preset number of uses threshold is configured for this temporary key. This preset number of uses threshold can be set manually according to actual business needs. This embodiment does not make a specific limitation on this. For example, it can be set to 1 time, that is, the temporary key is a one-time key that is valid only once and becomes invalid immediately after use, further preventing the risk of information leakage caused by key reuse. Finally, the server will generate a hash string and the employee's identification code, determine the verification set corresponding to the temporary key, and store it in the server as the verification basis when the background check client initiates a request.

[0044] For example, in this embodiment, the encryption conversion based on a hash algorithm can be implemented using existing technology, wherein the hash algorithm can be, for example, the SHA-256 algorithm.

[0045] It can be explained that the temporary key generated in the above manner is uniquely bound to the employee's identity, the scope of authorization, and the application time. Even if different employees have the same number of authorized nodes, they will generate completely different temporary keys due to differences in identity identification codes and request times. This completely avoids the security vulnerability of the key being disconnected from the scope of authorization. At the same time, the irreversibility of the hash algorithm also ensures that the key cannot be cracked or tampered with, greatly improving the security of the background check authorization process.

[0046] Step S3 includes the following: responding to a background check interaction request sent by the background check terminal containing the temporary key, performing verification based on the temporary key, and after successful verification, obtaining the employee appointment information located in the background check structure tree according to the authorized open information.

[0047] For example, in this embodiment, after the background check terminal obtains the temporary key forwarded by the employee, it can send a background check interaction request containing the temporary key to the server. After receiving the request, the server can first verify the legality and validity of the temporary key. Only after the verification is successful will the server retrieve the employee's employment information within the corresponding authorization range from the background check structure tree based on the authorization open information bound to the temporary key and feed it back to the background check terminal.

[0048] Furthermore, in this embodiment, the aforementioned "verification based on the temporary key, and after successful verification, obtaining employee appointment information located in the background check structure tree according to the authorized open information" may further include the following steps: The system retrieves the number of times the corresponding temporary key has been used and responds if the number of uses exceeds a preset threshold. If the number of uses exceeds the threshold, the system determines that the verification has failed. Otherwise, it extracts the hash string and identity code from the temporary key. The verification set based on the hash string, identity code and corresponding temporary key is compared, and if the comparison result is that the information is the same, the verification is confirmed to be successful, and the number of uses is accumulated. Determine the authorization open information corresponding to the temporary key, determine the access permissions of the corresponding child node as allowed based on each authorization switch identifier included in the authorization open information, and generate an allowed list to be sent to the background check end based on all the child nodes that are allowed to access. The query intent of the corresponding background check client is determined based on the preset interaction method, and the employee employment information located in the background check structure tree is obtained based on the matching results of the query intent and the allowed list.

[0049] For example, in this embodiment, the verification of the temporary key and the retrieval of information can be specifically implemented based on the following method steps: First, after receiving the temporary key sent by the background check client, the server can retrieve the historical usage count corresponding to the temporary key. If the historical usage count has exceeded the preset threshold, it means that the key has expired, the verification fails directly, and the background check interaction request is rejected. If it has not exceeded the preset threshold, the hash string and identity code contained in the temporary key can be extracted to proceed to the next step of verification. Next, the server compares the extracted hash string and identity code with the pre-stored verification set corresponding to the temporary key. If the two are exactly the same, it means that the temporary key is a valid key that has not been tampered with, and the verification is confirmed to be successful. At the same time, the usage count of the temporary key is incremented by 1. If the two are not the same, it means that the key is invalid or has been tampered with, the verification is confirmed to be unsuccessful, and the request is rejected. Subsequently, the server can retrieve the authorization access information bound to the temporary key, and determine all child nodes corresponding to the authorization switch identifiers contained in the authorization access information as nodes that are allowed to access. At the same time, an access list is generated based on all the accessible child nodes. It can be noted that the generated access list can be used to clearly inform the background check client of the scope of information that can be queried this time, avoiding invalid queries by the background check client. Finally, the server can identify the query intent of the background check client based on the preset interaction method selected by the background check client, and further retrieve the employee appointment information within the corresponding authorized scope in the background check structure tree by matching the query intent with the allowed list.

[0050] It can be noted that, in this embodiment, by using a dual verification mechanism of usage count verification and content consistency verification, the security of the temporary key is thoroughly guaranteed, avoiding the risk of information leakage caused by key reuse and tampering. The generation of the allowed list provides a clear scope guide for the background check end's query, and also provides a judgment benchmark for subsequent query intent matching, ensuring that only information within the authorized scope can be retrieved, further strengthening the control effect of refined authorization.

[0051] Furthermore, in this embodiment, the aforementioned "identifying the query intent of the corresponding background check client based on a preset interaction method, and obtaining employee employment information located in the background check structure tree based on the matching result of the query intent and the allowed list" may further include the following steps: The default interaction mode is voice call mode. Voice recognition technology is used to convert the voice questions from the background check terminal into query text, and the extracted working keywords in the query text are identified as the query intent. If the similarity between the query intent and any sub-node in the allowed list is greater than a preset similarity, the query intent and the allowed list are considered to be matched successfully. Based on the employee's employment information, the retrieved employee employment information corresponding to the sub-node is used as feedback information and broadcasted via voice. Otherwise, the preset rejection information is used as feedback information and broadcasted via voice.

[0052] For example, in this embodiment, for the most commonly used voice call mode in traditional background checks, automated interaction can be achieved in the following way: First, the server receives a voice access request from the background check client. After confirming that it is a background check interaction request, it can answer the call and then guide the background check client to enter a temporary key through voice. After the key verification is completed, the server can obtain the corresponding voice questions from the background check client. Next, the server can use existing mature speech recognition technology to convert the voice questions from the background check client into processable query text, and further use existing mature natural language processing technology to extract work keywords from the query text, such as start date, position and project experience, and further determine the work keywords as the background check client's query intent. Subsequently, the server can compare the extracted query intent with all child nodes in the allowed list for similarity. This similarity comparison can be achieved through the cosine similarity algorithm, and the preset similarity can be set manually according to actual business needs. This embodiment does not make specific limitations on this. For example, it can be set to 85%. Furthermore, when the comparison similarity obtained based on the similarity comparison is greater than the preset similarity, it indicates that the query content of the background check end is within the authorized range, and the match is confirmed to be successful. At this time, the server can retrieve the employee employment information of the corresponding child node from the background check structure tree, and can convert it into voice data for broadcast using existing mature speech synthesis technology. If the similarity is less than or equal to the preset similarity, or the query content is not within the allowed list, the match is determined to fail, and the server will broadcast a preset rejection message. The preset rejection message may be: The content you requested is not within the scope of this authorization, and we cannot provide you with relevant information.

[0053] It can be noted that, in this embodiment, the interaction based on the voice call mode is fully adapted to the traditional background check business habits. The background check end does not need to change the original background check process to realize automated background check inquiries and responses. No manual intervention is required from the original end, which greatly reduces labor costs. At the same time, through keyword matching and permission list verification, it is ensured that only information within the authorized scope will be broadcast, completely avoiding the risk of information leakage beyond the scope.

[0054] Furthermore, in this embodiment, the aforementioned "identifying the query intent of the corresponding background check client based on a preset interaction method, and obtaining employee employment information located in the background check structure tree based on the matching result of the query intent and the allowed list" may further include the following steps: The default interaction mode is port access mode, and the node selection information of the query command obtained from the corresponding background check terminal is determined as the query intent. The response determines that the child node selected by the corresponding node based on the query intent is the same as any child node in the allowed list. If the query intent and the allowed list match successfully, the employee employment information of the retrieved corresponding child node is sent to the background check terminal as feedback information. Otherwise, the preset rejection information is sent to the background check terminal as feedback information.

[0055] For example, in this embodiment, for online background check requirements, automated interaction can be achieved through port access mode: First, the background check end can determine the query command entered by the background check end based on the preset online background check port after entering a temporary key to complete key verification. Next, the server determines the query intent by selecting the node information in the query command, and compares the selected child nodes with the allowed list. If all the child nodes selected by the background check client are within the allowed list, the match is successful, and the server can retrieve the employee employment information of the corresponding child node from the background check structure tree and feed it back to the background check client's operation interface in the form of text, table, etc. If the child node selected by the background check client is not within the allowed list, the match is failed, and the server can send the preset rejection information back to the background check client.

[0056] It can be noted that the port access mode is adapted to the online and large-scale background check requirements, enabling the background check client to obtain background check information in batches. The query process is more efficient and the information display is more intuitive. It complements the voice call mode, covers the vast majority of background check business scenarios, and greatly improves the scenario adaptability of this solution.

[0057] Step S4 includes the following: obtaining the resume information corresponding to the employee, verifying the resume information with the employee's employment information, and generating a verification report based on the verification results.

[0058] For example, in this embodiment, after completing the background check process at the corresponding background check end, in order to verify the information at the employee end, the server can further obtain the resume information of the employee uploaded by the background check end, and then verify the consistency of the resume information with the employee's employment information in the background check structure tree that was previously retrieved, so as to generate a verification report based on the verification results. This allows the background check end to quickly locate abnormal content in the resume information through the verification report, without the need for manual word-by-word comparison, which greatly improves the efficiency and accuracy of resume verification.

[0059] It can be noted that this embodiment realizes automated verification of resume authenticity, replacing the traditional manual comparison process. It solves the problems of low efficiency, easy omissions, and difficulty in traceability of manual verification. At the same time, it completes information retrieval and verification based on the same background check structure tree, ensuring the consistency between the verification benchmark and the background check information, making the verification results more accurate and more valuable for reference.

[0060] Furthermore, in this embodiment, the aforementioned "verifying the resume information with the employee's employment information" may further include the following steps: Hide all child nodes in the background check structure tree that are outside the allowed list to obtain the verification structure tree; The resume information is divided into nodes based on the corresponding verification structure tree to obtain each partition node; The response determines that any partitioning node has a node mapping relationship with the child node corresponding to the employee's employment information based on the verification structure tree. It compares the employee's employment information with the partitioning data corresponding to the partitioning node, and determines that the employee's employment information is consistent with the partitioning data based on the comparison result. Based on the verification structure tree, it marks the child node as having passed the verification, and otherwise marks it as having failed the verification. If any partition node does not have a node mapping relationship with the child node corresponding to the employee's employment information, the missing third tag is verified based on the verification structure tree.

[0061] For example, in this embodiment, the automated verification of resume information can be implemented based on the following method steps: First, before initiating the verification process, the server performs node filtering and hiding on the complete background check structure tree based on the generated allowed list. As mentioned above, the allowed list contains the authorization switch identifiers corresponding to all child nodes that the employee has authorized to access. Based on this, the server can traverse all child nodes in the background check structure tree and mark all child nodes whose authorization switch identifiers are not included in the allowed list as hidden. Only the child nodes in the allowed list and their corresponding hierarchical relationships are retained to form the verification structure tree. This ensures that the verification process revolves only around the information dimension authorized by the employee. Unauthorized child nodes will not participate in any verification operations, preventing the risk of leakage of unauthorized information from the root and avoiding irrelevant information from interfering with the verification results, making the verification focus more concentrated. Next, after the server obtains the resume information from the corresponding employee, it will use the verification structure tree as the sole benchmark to perform structured decomposition and node division of the resume information. It can be explained that the decomposition process will call the natural language processing module to first identify the information modules in the resume information, such as work experience, project experience, job responsibilities, etc., and then according to the child node dimension of the verification structure tree, the resume information will be split into partition nodes that correspond one-to-one with the child nodes. For example, if the verification structure tree includes child nodes corresponding to the job information and the start date, the start date of a certain job experience will be matched based on the resume information to form a partition node. Subsequently, the server establishes a mapping relationship between partition nodes and child nodes in the verification structure tree. It then determines whether each partition node has dimensional consistency with the child nodes in the verification structure tree. If a partition node and a child node in the verification structure tree have a dimensional match (e.g., both are the same project name), then it is determined that the two have a node mapping relationship. The server further extracts the employee employment information corresponding to the child node and compares it with the resume data in the partition node. If the comparison result is completely consistent, the server will mark the child node as having passed the verification based on the verification structure tree. If the comparison result is different, it will mark the corresponding verification as having failed. Finally, the server will traverse all child nodes in the verification structure tree. If a certain child node has no corresponding matching item in the partitioning node, that is, the resume information is missing information content corresponding to the child node, then the third tag corresponding to the missing verification can be marked on the child node based on the verification structure tree.

[0062] Furthermore, in this embodiment, the aforementioned "generating a verification report based on the verification results" may further include the following steps: Establish an interaction record table corresponding to the preset interaction methods, and based on the interaction record table, create interaction record bars according to the query intent and feedback information of the corresponding child node; Generate a verification report, wherein the verification report includes a first area for filling the interaction record table, a second area for filling the verification structure tree, and a third area for filling the resume information.

[0063] For example, in this embodiment, the generation of the verification report can be specifically implemented based on the following method steps: First, the server can establish a corresponding interaction record table based on the preset interaction method used in this background check, and generate independent interaction record bars for each round of query intent and corresponding feedback information in chronological order during this background check process, and archive them completely into the interaction record table to ensure that the entire interaction process of this background check is traceable; Next, the server can generate a verification report with a corresponding preset report template. This verification report can be set with three areas. The first area can be used to fill in the interaction record table of this background check to record the interaction details of the entire background check process for the background checker to review and trace. The second area can be used to fill in the verification structure tree. The verification structure tree includes a first marker, a second marker, and a third marker to display the verification results. Filling in the verification structure tree can also clearly show the scope of information authorized in this case. The third area can be used to fill in the resume information of the corresponding employee to record the execution background of this background check.

[0064] It can be explained that the three-region verification report design not only fully records the interactive process of the entire background check, but also clearly presents the core results of resume verification, while restoring the complete structure of the background check information, making the verification report traceable, readable and complete.

[0065] Another embodiment of the present invention provides an intelligent background check resume analysis and verification device. Figure 3 Its corresponding structural block diagram, such as Figure 3 As shown, the device includes: The data accumulation module is used to respond to the resignation trigger signal received from the corresponding employee's end and generate a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer. The authorization control module is used to respond to background check authorization requests sent by employees, and generate a temporary key bound to the authorization opening information based on the authorization opening information contained in the background check authorization request; The interaction execution module is used to respond to receiving a background check interaction request containing the temporary key sent by the background check terminal, perform verification based on the temporary key, and after the verification is successful, obtain the employee appointment information located in the background check structure tree according to the authorized open information. The verification report module is used to obtain the resume information of the corresponding employee, verify the resume information with the employee's employment information, and generate a verification report based on the verification results.

[0066] In the specification provided herein, the algorithms and displays are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with the examples of this invention. The required structure for constructing such systems is apparent from the above description. Furthermore, this invention is not directed to any particular programming language. It should be understood that the contents of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing preferred embodiments of the invention.

[0067] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0068] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof.

[0069] Those skilled in the art will understand that modules, units, or components of the devices disclosed in the examples herein can be arranged in the devices described in this embodiment, or alternatively, can be located in one or more devices different from the devices in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0070] Those skilled in the art will understand that the modules in the device of the embodiment can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or components in the embodiment can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components.

[0071] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.

[0072] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0073] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0074] Although the invention has been described with respect to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and edibility purposes, and not for the purpose of explaining or limiting the subject matter of the invention.

Claims

1. A method for background check and resume analysis based on intelligence, characterized in that, include: The system responds to the resignation trigger signal received from the corresponding employee's end and generates a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer. In response to a background check authorization request sent by an employee, a temporary key bound to the authorization opening information is generated based on the authorization opening information contained in the background check authorization request. The system receives a background check interaction request containing the temporary key sent by the background check unit, performs verification based on the temporary key, and obtains the employee appointment information located in the background check structure tree according to the authorized open information after the verification is successful. Obtain the resume information of the corresponding employee, verify the resume information with the employee's employment information, and generate a verification report based on the verification results.

2. The method according to claim 1, characterized in that, The response receives a resignation trigger signal from the corresponding employee's end, and generates a background check structure tree based on the employee's employment information during their employment period uploaded by the original employer, including: The system responds to the resignation trigger signal received from the corresponding employee's end and obtains the work data and evaluation data uploaded by the original employer during the corresponding employment period from the employee's end. The work data and evaluation data are integrated into employee employment information, and the employee employment information is archived hierarchically to generate a background check structure tree.

3. The method according to claim 2, characterized in that, The employee employment information is archived hierarchically to generate a background check structure tree, including: The work data includes all work sub-data corresponding to different work dimensions, and the evaluation data includes all evaluation sub-data corresponding to different evaluation dimensions. Establish an employee node corresponding to the employee's end, and establish a parent node for the corresponding work data and an evaluation parent node for the corresponding evaluation data downwards from the employee node; A working sub-node corresponding to each working sub-data is established downwards along the working parent node, and an evaluation sub-node corresponding to each evaluation sub-data is established downwards along the evaluation parent node, thus obtaining the background check structure tree. Configure an authorization switch identifier for each child node, and determine the access permissions of the corresponding child node by matching the authorization open information based on the authorization switch identifier.

4. The method according to claim 3, characterized in that, Also includes: In response to the existence of work sub-data and evaluation sub-data corresponding to the same work project and having a project association relationship, based on the background check structure tree, the work sub-nodes corresponding to the work sub-data and the evaluation sub-nodes corresponding to the evaluation sub-data are aggregated into the same project association group. In response to the authorization open information matched based on the authorization switch identifier, which only allows the working sub-node to access, the access permission of the evaluation sub-node is simultaneously determined to be allowed. In response to the authorization open information matched based on the authorization switch identifier, which only allows the evaluation sub-node to access, if the access permission of the corresponding working sub-node is not allowed, then the access permission of the evaluation sub-node is determined to be not allowed.

5. The method according to claim 4, characterized in that, The response to the existence of work sub-data and evaluation sub-data corresponding to the same work project and having a project association relationship includes: Obtain the project identification information carried by the working sub-data and the project identification information carried by the evaluation sub-data; If the project identifier information of any working sub-data is consistent with the project identifier information of any evaluation sub-data, it is determined that the working sub-data and the evaluation sub-data have a project association relationship.

6. The method according to claim 2, characterized in that, Based on the authorization open information contained in the background check authorization request, a temporary key bound to the authorization open information is generated, including: Obtain the identity identification code corresponding to the employee's terminal, and determine all authorization switch identifiers included in the corresponding authorization open information based on the background check authorization request; Using the request time of the background check authorization request as a random seed, the identity code, all authorization switch identifiers, and the request time are randomly sorted to obtain an information sequence; The information sequence is encrypted and transformed based on a hash algorithm, a temporary key is generated based on the obtained hash string, a preset number of times threshold is configured for the temporary key, and the hash string and the identity code are determined as the verification set of the corresponding temporary key.

7. The method according to claim 6, characterized in that, The process of verifying based on the temporary key, and obtaining employee employment information from the background check structure tree based on the authorized open information after successful verification, includes: The system retrieves the number of times the corresponding temporary key has been used and responds if the number of uses exceeds a preset threshold. If the number of uses exceeds the threshold, the system determines that the verification has failed. Otherwise, it extracts the hash string and identity code from the temporary key. The verification set based on the hash string, identity code and corresponding temporary key is compared, and if the comparison result is that the information is the same, the verification is confirmed to be successful, and the number of uses is accumulated. Determine the authorization open information corresponding to the temporary key, determine the access permissions of the corresponding child node as allowed based on each authorization switch identifier included in the authorization open information, and generate an allowed list to be sent to the background check end based on all the child nodes that are allowed to access. The query intent of the corresponding background check client is determined based on the preset interaction method, and the employee employment information located in the background check structure tree is obtained based on the matching results of the query intent and the allowed list.

8. The method according to claim 7, characterized in that, The process of identifying the query intent of the corresponding background check client based on a preset interaction method, and obtaining employee employment information located in the background check structure tree based on the matching results of the query intent and the allowed list, includes: The default interaction mode is voice call mode. Voice recognition technology is used to convert the voice questions from the background check terminal into query text, and the extracted working keywords in the query text are identified as the query intent. If the similarity between the query intent and any sub-node in the allowed list is greater than a preset similarity, the query intent and the allowed list are considered to be matched successfully. Based on the employee's employment information, the retrieved employee employment information corresponding to the sub-node is used as feedback information and broadcasted via voice. Otherwise, the preset rejection information is used as feedback information and broadcasted via voice.

9. The method according to claim 7, characterized in that, The process of identifying the query intent of the corresponding background check client based on a preset interaction method, and obtaining employee employment information located in the background check structure tree based on the matching results of the query intent and the allowed list, includes: The default interaction mode is port access mode, and the node selection information of the query command obtained from the corresponding background check terminal is determined as the query intent. The response determines that the child node selected by the corresponding node based on the query intent is the same as any child node in the allowed list. If the query intent and the allowed list match successfully, the employee employment information of the retrieved corresponding child node is sent to the background check terminal as feedback information. Otherwise, the preset rejection information is sent to the background check terminal as feedback information.

10. The method according to claim 8 or 9, characterized in that, The step of verifying the resume information against the employee's employment information includes: Hide all child nodes in the background check structure tree that are outside the allowed list to obtain the verification structure tree; The resume information is divided into nodes based on the corresponding verification structure tree to obtain each partition node; The response determines that any partitioning node has a node mapping relationship with the child node corresponding to the employee's employment information based on the verification structure tree. It compares the employee's employment information with the partitioning data corresponding to the partitioning node, and determines that the employee's employment information is consistent with the partitioning data based on the comparison result. Based on the verification structure tree, it marks the child node as having passed the verification, and otherwise marks it as having failed the verification. If any partition node does not have a node mapping relationship with the child node corresponding to the employee's employment information, the missing third tag is verified based on the verification structure tree.

11. The method according to claim 10, characterized in that, A verification report is generated based on the verification results, including: Establish an interaction record table corresponding to the preset interaction methods, and based on the interaction record table, create interaction record bars according to the query intent and feedback information of the corresponding child node; Generate a verification report, wherein the verification report includes a first area for filling the interaction record table, a second area for filling the verification structure tree, and a third area for filling the resume information.

12. A background check resume analysis and verification device based on intelligence, characterized in that, include: The data accumulation module is used to respond to the resignation trigger signal received from the corresponding employee's end and generate a background check structure tree based on the employee's employment information during the corresponding employment period uploaded by the original employer. The authorization control module is used to respond to background check authorization requests sent by employees, and generate a temporary key bound to the authorization opening information based on the authorization opening information contained in the background check authorization request; The interaction execution module is used to respond to receiving a background check interaction request containing the temporary key sent by the background check terminal, perform verification based on the temporary key, and after the verification is successful, obtain the employee appointment information located in the background check structure tree according to the authorized open information. The verification report module is used to obtain the resume information of the corresponding employee, verify the resume information with the employee's employment information, and generate a verification report based on the verification results.

Images