Work log intelligent auditing and optimizing method and system based on artificial intelligence

Abstract

The invention discloses a work log intelligent auditing and optimizing method and system based on artificial intelligence, and relates to the technical field of artificial intelligence, and the method comprises the following steps: obtaining a work log; performing key term extraction on the work log to identify a key entity; calculating a semantic matching degree of the key entity; generating grading suggestions according to the semantic matching degree and pushing the grading suggestions to a front end; and the employee carries out modification according to the suggestions presented by the front end, and submits to the system after modification is completed. The problem that in the prior art, the log content quality is low can be solved.

Description

Technical Field

[0001] This invention belongs to the field of artificial intelligence technology, specifically relating to an intelligent auditing and optimization method and system for work logs based on artificial intelligence. Background Technology

[0002] In today's world, where information and intelligent technologies are deeply integrated into enterprise operations, work logs have become a core carrier of internal knowledge management. They not only record employees' daily work activities, problem-solving processes, and experience summaries, but also serve as crucial evidence for information synchronization, knowledge accumulation, and efficient decision-making in team collaboration. As enterprises expand and business complexity increases, how to leverage work logs to achieve cross-position and cross-process knowledge reuse and reduce repetitive labor costs has become a key issue for improving operational efficiency. Currently, most enterprises have recognized the importance of standardized work log management, but existing technological systems still face significant bottlenecks in adapting to diverse needs and ensuring content quality.

[0003] Existing work log management systems primarily collect log content through preset templates or free text, relying on manual input and review for their core technology. For example, some companies use Excel spreadsheets or simple online forms as log submission tools, with department heads conducting periodic spot checks; a few systems introduce basic format validation functions, which can only detect missing fields or abnormal character lengths. The design logic of these technical solutions focuses on the "completeness of the recording behavior" rather than the "validity of the recorded content," leading to numerous problems in practical applications.

[0004] However, existing technologies suffer from the following problems: First, log optimization lacks precise guidance, resulting in low content quality; second, the review process is inefficient and lacks quantifiable evaluation criteria; third, establishing and implementing a unified standard format is difficult. These issues lead to low-quality generated log content. Summary of the Invention

[0005] The purpose of this invention is to provide an intelligent auditing and optimization method and system for work logs based on artificial intelligence, which can improve the problem of low quality of log content in existing technologies.

[0006] To solve the above-mentioned technical problems, the present invention is implemented as follows: In a first aspect, embodiments of the present invention provide an intelligent auditing and optimization method for work logs based on artificial intelligence, the method comprising: Get the work log; Extract key terms from work logs to identify key entities; Calculate the semantic matching degree of key entities; Based on semantic matching, hierarchical suggestions are generated and pushed to the front end; Employees make modifications based on the suggestions presented on the front end, and then submit the modifications to the system.

[0007] Optional, the specific steps for extracting key terms include: inputting a set of log texts, which consists of multiple log texts; when a log text is in the terminology database, adding the log text to the keyword set; and semantically segmenting the log text into multiple parts, with each part being a key term.

[0008] Optionally, the specific steps for calculating the semantic matching degree of key entities include: The submitted work logs are subject to automated review and quantitative evaluation. The automated review includes: format verification, which checks whether the text format conforms to the preset format rules of the corresponding work group to obtain a content format score; content completeness verification, which counts the number of key information points in the log content that match the standard text to obtain a content completeness score; and content standardization verification, which calculates the average semantic similarity between the log content and the standard text through semantic vector comparison to obtain a content standardization score. Based on preset weights, the content format score, content completeness score, and content standardization score are weighted and calculated to obtain the semantic matching degree.

[0009] Optionally, the mathematical expression for semantic matching degree is: Semantic matching degree = 0.6 × completeness + 0.3 × normality + 0.1 × content format score.

[0010] Secondly, embodiments of the present invention provide an intelligent auditing and optimization system for work logs based on artificial intelligence, the system comprising: The log acquisition module is used to acquire work logs; The entity recognition module is used to extract key terms from the work logs in order to identify key entities; The semantic matching degree calculation module is used to calculate the semantic matching degree of key entities; The suggestion generation module is used to generate tiered suggestions based on semantic matching degree and push them to the front end; The modification module allows employees to make changes based on the suggestions presented on the front end, and then submit the changes to the system.

[0011] Thirdly, embodiments of the present invention provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as described in the first aspect.

[0012] Fourthly, embodiments of the present invention provide a readable storage medium on which a program or instructions are stored, and when the program or instructions are executed by a processor, the steps of the method as described in the first aspect are implemented.

[0013] Compared with existing technologies, the beneficial effects of the intelligent auditing and optimization method for work logs based on artificial intelligence provided by this invention are as follows: First, existing systems can only provide vague feedback on log issues, such as "format error" or "incomplete content," leaving employees feeling like blind men describing an elephant when making corrections. This invention, however, utilizes AI semantic analysis modules for word segmentation, entity recognition, and semantic matching to accurately pinpoint differences between logs and standard text. For example, when a marketing log lacks "customer budget" information, the system will directly prompt "Please supplement the customer budget range (e.g., 'annual budget 500,000-800,000')," clearly linking it to the standard requirement that "customer requirements must include budget-related information." This makes the direction for employee corrections clear, completely resolving the problem of repeated revisions caused by vague feedback in traditional systems and significantly improving the stability of log content quality.

[0014] Secondly, under the manual review model, a single manager typically reviews fewer than 50 logs per day, and the results are heavily influenced by subjective factors; some automated review systems can only verify format compliance. The AI ​​review engine of this invention can process logs in seconds, far exceeding the efficiency of manual review. Simultaneously, it innovates a "compliance index" quantitative system, generating a precise score (e.g., 72.3%) for each log entry through weighted calculations based on multiple dimensions such as content completeness and standardization (e.g., completeness 60%, standardization 30%, format matching 10%). This indicator not only allows employees to clearly identify areas for improvement but also enables managers to track team log quality trends in real time, completely resolving the pain points of inefficient review and lack of quantitative basis.

[0015] Third, traditional unified templates either suffer from information gaps due to rigidity or reduced efficiency due to redundancy, while custom templates often lead to standard chaos due to lack of control. This invention, through a visual configuration module, allows administrators to create personalized text standards (without format restrictions) for different workgroups (such as R&D and marketing), while an AI review engine ensures the rigid implementation of these standards. For example, the R&D team's standard can be set to "must include technical parameters and test results," while the marketing team's standard can be set to "must describe the customer's industry and feedback." This satisfies the business characteristics of each team and, through a unified AI verification logic, forms reusable knowledge assets, enabling efficient cross-team information exchange. Attached Figure Description

[0016] Figure 1 This is a flowchart of an intelligent auditing and optimization method for work logs based on artificial intelligence, provided in the first embodiment of the present invention; Figure 2 This is a flowchart illustrating the AI ​​semantic parsing provided in the first embodiment of the present invention; Figure 3 This diagram illustrates the workflow of the AI ​​review engine provided in the first embodiment of the present invention. Figure 4 This is an internal structure diagram of an AI-based intelligent auditing and optimization system for work logs provided in the second embodiment of the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] The terms "first," "second," etc., used in the specification and claims of this invention are used to distinguish similar objects and are not used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0019] The following description, in conjunction with the accompanying drawings, details an artificial intelligence-based intelligent auditing and optimization method and system for work logs provided by the present invention through specific embodiments and application scenarios.

[0020] Example 1 Please see Figure 1 This represents a flowchart of an intelligent auditing and optimization method for work logs based on artificial intelligence provided by the present invention, including steps S1 to S5.

[0021] S1: Retrieve work logs; Specifically, the process of obtaining work logs includes: the specific process of receiving work log content in any text format submitted by the user through the front-end interface, along with the identification information of the work group to which the log belongs, including: S11. After logging into the system, employees select their work group (e.g., "Marketing Department 1"). The front-end calls the interface to load the standard log format in plain text for that work group (example: "Customer requirements description should include industry type and budget range; cooperation progress should include communication time and consensus reached"). S12. The front end provides a blank text input box for employees to fill in logs, and displays the loaded plain text standard next to the input box as a reference. No formatting constraints are set throughout the process. S2: Extract key terms from the work logs to identify key entities; Specifically, the key term extraction process includes: inputting a set of log texts, which consists of multiple log texts; when a log text is in the terminology database, adding that log text to the keyword set; and semantically segmenting the log text into multiple parts, with each part being a key term (e.g., "e-commerce" corresponds to the entity "industry," while the entity "budget" is detected as missing). Specifically, the steps for identifying key entities include entity type extraction and missing entity detection. The specific steps for entity type extraction include: extracting entity types from standard text based on LLM and separating them with commas to obtain the entity types.

[0022] Further, the specific steps of missing data detection include: comparing the missingness of entity types and entity lists based on LLM, and outputting the missing data detection results. For example, if the standard input text is: "must include industry / budget / solution", and the log text is "AI solution used in the education industry", the output will be in JSON format, as follows: { "Entities": [("Education Industry","Industry"), ("AI Solutions","Solutions")], "Missing": ["Budget"] } S3: Calculate the semantic matching degree of key entities.

[0023] Specifically, the steps for calculating the semantic matching degree of key entities include: The submitted work logs are subject to automated review and quantitative evaluation. The automated review includes: format verification, which checks whether the text format conforms to the preset format rules of the corresponding work group to obtain a content format score; content completeness verification, which counts the number of key information points in the log content that match the standard text to obtain a content completeness score; and content standardization verification, which calculates the average semantic similarity between the log content and the standard text through semantic vector comparison to obtain a content standardization score. Based on preset weights, the content format score, content completeness score, and content standardization score are weighted and calculated to obtain the semantic matching score. The mathematical expression for the semantic matching score is: Semantic matching score = 0.6 × completeness + 0.3 × standardization + 0.1 × content format score.

[0024] The completeness calculation process includes: clearly defining the standard requirements for entities, with the entity expression being: ["Project Background", "Technical Solution", "Budget Details", "Risk Analysis"]. Identified entities include: Project Background: "Developing a medical management system for a hospital" (lacking client scale); Technical Solution: "Adopting a microservice architecture" (lacking implementation methodology); Budget Details: "Budget approximately 3 million yuan" (lacking cost breakdown); Risk Analysis: "Data security issues" (only 1 risk). Furthermore, the process of calculating the standardization score includes: setting four reasons for deduction. When the entity type is project background and the customer scale is not specified, the score is 0.6. When the entity type is technical solution and the implementation method is not described, the score is 0.5. When the entity type does not have budget details and the amount is not broken down, the score is 0.7. When the entity type is risk analysis and only one risk is identified, the score is 0.8. The content standardization score at this time is: (0.6+0.5+0.7+0.8) / 4 = 0.65.

[0025] Furthermore, the process of calculating the content format score includes: when a compliant item has a second-level heading, the score is 1; when a violation occurs, i.e. there are no blank lines between paragraphs or a date field is missing, the content format score is: 1 - 0.1 × 2 = 0.8. Furthermore, the mathematical expression for the semantic matching degree is: 0.6×0.6 + 0.3×0.65 + 0.1×0.8 = 63.5%.

[0026] S4: Generate hierarchical suggestions based on semantic matching degree and push them to the front end; Specifically, this invention generates suggestions based on semantic matching degree grading: when the matching degree is <70%, it identifies missing items (e.g., "the customer's budget range was not mentioned"), and when the matching degree is 70%-90%, it suggests optimization details (e.g., "It is recommended to supplement the specific budget range, example: budget approximately 500,000-800,000"). Furthermore, before generating tiered suggestions and pushing them to the front-end interface to guide employees in making modifications, it also includes: The system receives a log submission request (including the workgroup identifier and log content) and assigns a unique UUID to the log (e.g., "L20240715001"). The UUID undergoes three levels of verification: format verification, content completeness verification, and content standardization verification. Format verification checks whether the text format conforms to the corresponding working group standards using preset rules (e.g., whether titles are correctly labeled and paragraph breaks are standardized). If the format does not meet the standards, the format matching score is 0. Content completeness verification compares the submitted content with the key information points extracted from the working group's standard text (e.g., "customer needs" includes "industry" and "budget"), counts the number of information points covered in the log, and calculates the completeness score (e.g., if the standard contains 5 information points and the log contains 3, then the completeness score = 3 / 5 × 100% = 60%). Content standardization verification analyzes the degree of matching between the submitted content and the standard text through semantic vector comparison, calculating the average similarity score (e.g., if the two parts of the text match 80% and 70% respectively, then the standardization score = (80% + 70%) / 2 = 75%). Furthermore, the score is calculated based on 60% content completeness, 30% content standardization, and 10% format matching (e.g., 60%×60% + 75%×30% + 100%×10%≈68.5%). If the total score of the three-level verification is greater than 68.5%, the three-level verification passes; otherwise, it fails.

[0027] Furthermore, once the three-level verification is passed, the review results (including the compliance index and optimization suggestions) are stored in the database and simultaneously pushed to employees for modification. After modifying the content, employees initiate a re-review until the compliance index reaches the preset threshold.

[0028] S5: Employees modify the system based on the suggestions presented on the front end, and then submit the modifications to the system.

[0029] Specifically, the steps for employees to modify the system based on the suggestions presented on the front end include: the system administrator logs in through the visual configuration module, creates a workgroup, for example, "R&D Group 1", enters the name and department, and submits and saves. Furthermore, in the text editing area, enter "The R&D log must include two parts: 1. Description of technical issues; 2. Solution and test results", set the compliance index threshold to 85%, click "Save", and the configuration result will be stored in the structured storage module; Furthermore, when employees submit logs, the standard execution module loads the "R&D Group 1" standard from the structured storage module to verify the logs; Furthermore, if the logs are missing "test results", the standard execution module returns an error message (such as "Please supplement the test results of the solution"), forcing employees to modify them to meet the standards.

[0030] Example 2 Please see Figure 4The second embodiment of the present invention provides an intelligent auditing and optimization system for work logs based on artificial intelligence, comprising: Log acquisition module 100 is used to acquire work logs; The entity recognition module 200 is used to extract key terms from the work log in order to identify key entities; The semantic matching degree calculation module 300 is used to calculate the semantic matching degree of key entities; It is recommended to generate module 400, which is used to generate hierarchical suggestions based on semantic matching degree and push them to the front end; Modify module 500, which is used by employees to make modifications based on the suggestions presented on the front end, and then submit the modifications to the system.

[0031] Please see Figure 2 The workflow is as follows: Employees log in to the system and select their workgroup. The system loads the corresponding standard text and displays it next to the input area. After entering any format log in the text input box, they click the submit button to send the log to the log submission front-end module. The log submission front-end module receives and forwards the log to the AI ​​semantic analysis module for processing. The AI ​​semantic analysis module extracts key terms through word segmentation, identifies key entities with missing items, and calculates the semantic matching degree. Then, it is processed by the optimization suggestion generation module, which generates hierarchical suggestions based on the matching degree. At this point, the AI ​​processing flow ends. The hierarchical suggestions are then input to the real-time feedback module, which pushes the suggestions to the front-end, highlighting the parts that need to be modified. Employees view and modify the log, and then submit it again after making the modifications.

[0032] Please see Figure 3 The workflow is as follows: Employees submit modified logs, the system automatically assigns a unique UUID, and then initiates an automated review process. During the automated review process, the system verifies the completeness and compliance of the content. The data is then input into the compliance index calculation module for processing. A score is calculated based on weights, and the review results are saved in real time through the data storage module. When the compliance index is greater than or equal to 80%, a review approval message is displayed. Otherwise, the logs are input into the re-review interaction module, which displays the current score and missing items, and provides specific suggestions for modification. Employees modify the logs according to these suggestions and resubmit them. The logs are then returned to the AI ​​review engine for re-review until the compliance index is less than 80%. Only then will the review be approved.

[0033] The intelligent auditing and optimization system for work logs based on artificial intelligence, as described in this embodiment of the invention, can be a device, a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. For example, a mobile electronic device can refer to a mobile phone, tablet computer, laptop computer, PDA, in-vehicle electronic device, wearable device, ultra-mobile personal computer (UMPC), netbook, or personal digital assistant (PDA), etc., while a non-mobile electronic device can refer to a server, network attached storage (NAS), personal computer (PC), television (TV), ATM, or self-service machine, etc. This embodiment of the invention does not impose specific limitations.

[0034] The AI-based intelligent auditing and optimization system for work logs in this embodiment of the invention can refer to a device with an operating system. This operating system can refer to Android, iOS, or other possible operating systems; this embodiment of the invention does not impose specific limitations.

[0035] The present invention provides an intelligent auditing and optimization system for work logs based on artificial intelligence, which can achieve... Figures 1 to 3 The various processes of an AI-based intelligent auditing and optimization method for work logs, as described in the method embodiments, will not be repeated here to avoid repetition.

[0036] Optionally, embodiments of the present invention also provide an electronic device, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the various processes of the above-described embodiment of an intelligent auditing and optimization method for work logs based on artificial intelligence, and can achieve the same technical effect. To avoid repetition, further details are omitted here.

[0037] This invention also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described embodiment of an intelligent auditing and optimization method for work logs based on artificial intelligence, and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0038] The processor refers to the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0039] It should be noted that, in this invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of this invention is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0040] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0041] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of the present invention.

Claims

1. A method for intelligent review and optimization of work logs based on artificial intelligence, characterized in that, include: Get the work log; Key terms are extracted from the work logs to identify key entities; Calculate the semantic matching degree of the key entities; Based on the semantic matching degree, a hierarchical suggestion is generated and pushed to the front end; Employees make modifications based on the suggestions presented on the front end, and then submit the modifications to the system.

2. The method for intelligent review and optimization of work logs based on artificial intelligence according to claim 1, characterized in that, The specific steps for extracting the key terms include: inputting a set of log texts, which consists of multiple log texts; when a log text is in the terminology database, adding the log text to the keyword set; and semantically segmenting the log text into multiple parts, with each part being a key term.

3. The method for intelligent review and optimization of work logs based on artificial intelligence according to claim 1, characterized in that, The specific steps for calculating the semantic matching degree of the key entity include: The submitted work log content is subject to automated review and quantitative evaluation. The automated review includes: format verification, which checks whether the text format conforms to the preset format rules of the corresponding working group to obtain a content format score; content completeness verification, which counts the number of key information points in the log content that match the standard text to obtain a content completeness score; and content standardization verification, which calculates the average semantic similarity between the log content and the standard text through semantic vector comparison to obtain a content standardization score. Based on preset weights, the content format score, the content completeness score, and the content standardization score are weighted and calculated to obtain the semantic matching degree.

4. The method for intelligent review and optimization of work logs based on artificial intelligence according to claim 3, characterized in that, The mathematical expression for the semantic matching degree is: Semantic matching degree = 0.6 × Completeness + 0.3 × Standardization + 0.1 × Content format score.

5. An intelligent auditing and optimization system for work logs based on artificial intelligence, characterized in that: include: The log acquisition module is used to acquire work logs; An entity recognition module is used to extract key terms from the work log in order to identify key entities; A semantic matching degree calculation module is used to calculate the semantic matching degree of the key entities; The suggestion generation module is used to generate hierarchical suggestions based on the semantic matching degree and push them to the front end; The modification module is used by employees to make changes based on the suggestions presented on the front end, and then submit the changes to the system.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method as described in any one of claims 1 to 4.

Images