Audit expert selection matching method and management system

Abstract

The embodiment of the invention relates to the information technology, in particular to an auditing expert selection matching method and a management system. The method comprises the following steps: establishing an abstract extraction model of each expert, and associating auditing item types; reading data of a to-be-audited item, extracting an abstract of the data of the to-be-audited item by using the abstract extraction model corresponding to the type of the audited item, and recording the abstract as an item abstract; establishing a simulation auditing model of each expert; reading project information of the to-be-audited project, and generating a confusion abstract and confusion information according to the project abstract and the project information of the to-be-audited project; inputting the confusion abstract and the confusion information into a simulation auditing model of each expert to obtain a confusion auditing text; comparing with the auditing rule of the corresponding auditing item type to obtain an auditing result; when the auditing result is consistent with the preset auditing result, corresponding experts are brought into a to-be-selected library; and selecting a predetermined number of experts as auditing experts of the to-be-audited project.

Description

Technical Field

[0001] Multiple embodiments of this specification relate to information technology, and specifically to a method and management system for selecting and matching audit experts. Background Art

[0002] In various scientific research, engineering and technology development projects, the introduction of external or internal professionals to conduct independent evaluation of the project can provide an objective basis for decision-making. The core of expert review is to review all aspects of the project with the help of the knowledge and experience of authoritative people in a specific field. These experts usually come from academia, industry or other institutions with relevant professional knowledge and rich practical experience. They can examine the project from different angles and put forward review opinions, which helps to control the overall level of the project. When a project enters the review stage, the organizer will carefully select review experts based on the nature and technical requirements of the project. The selection process not only considers the professional background of the candidates, but also evaluates their past work experience, research results and whether they have the ability to deal with similar complex problems. In addition, in order to ensure the fairness of the review, it is necessary to exclude people with direct interests in the project to avoid possible conflicts of interest. After the review experts are selected, they will receive detailed project materials, including but not limited to project proposals, technical documents, progress reports, etc. The experts will carefully study these materials, and then conduct in-depth analysis of the scientific rationality, technical innovation, feasibility and other aspects of the project, and give review opinions and explanations. Summary of the invention

[0003] Multiple embodiments of this specification describe an audit expert selection and matching method and management system.

[0004] In a first aspect, the embodiments of this specification provide a method for selecting and matching audit experts, including the steps of: Build a summary extraction model for each expert and associate it with the audit project type; Read the information of the project to be reviewed, and use the summary extraction model corresponding to the review project type to extract the summary of the information of the project to be reviewed, and record it as the project summary; Establishing a simulation audit model for each expert, wherein the input of the simulation audit model is the project summary and project information, and the output is a formatted text containing predetermined fields, which is recorded as the audit text; Reading the project information of the project to be reviewed, and generating an obfuscated summary and obfuscated information according to the project summary and the project information of the project to be reviewed, wherein the obfuscated summary and the obfuscated information have a known predetermined review result; Inputting the obfuscated summary and obfuscated information into the simulated audit model of each expert to obtain an obfuscated audit text; Compare the audit text and the obfuscated audit text with the audit rules of the corresponding audit item types to obtain the audit results; When the audit result is consistent with the predetermined audit result, the corresponding expert is included in the candidate pool; A predetermined number of experts are randomly selected from the candidate pool as review experts for the items to be reviewed.

[0005] In a second aspect, the embodiments of this specification provide a system for selecting and matching audit experts, including: The extraction module builds a summary extraction model for each expert and associates it with the audit project type; A summary module reads the information of the project to be reviewed, and uses a summary extraction model corresponding to the review project type to extract a summary of the information of the project to be reviewed, which is recorded as a project summary; The audit module establishes a simulated audit model for each expert, wherein the input of the simulated audit model is the project summary and project information, and the output is a formatted text containing predetermined fields, which is recorded as the audit text; an obfuscation module, which reads the project information of the project to be reviewed, and generates an obfuscated summary and obfuscated information according to the project summary and project information of the project to be reviewed, wherein the obfuscated summary and obfuscated information have a known predetermined review result; The obfuscation review module inputs the obfuscation summary and obfuscation information into the simulation review model of each expert to obtain an obfuscation review text; A comparison module compares the audit text and the obfuscated audit text with the audit rules of the corresponding audit item type to obtain the audit result; A selection module, when the audit result matches the predetermined audit result, the corresponding expert is included in the selection pool; The selection module randomly selects a predetermined number of experts from the candidate pool as review experts for the items to be reviewed.

[0006] In a third aspect, an embodiment of this specification provides an electronic device, including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method described in any one of the above aspects.

[0007] In a fourth aspect, an embodiment of the present specification provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the above aspects.

[0008] In a fifth aspect, an embodiment of this specification provides a computer program product, including a computer program, which implements the method described in any of the above aspects when executed by a processor.

[0009] The beneficial effects brought by the technical solutions provided by some embodiments of this specification include at least: In multiple embodiments of the present specification, the audit expert selection and matching method and management system provided, by establishing a summary extraction model for each expert, can not only facilitate the expert to obtain the project summary that suits or prefers them, which is convenient for their audit, but also associates the audit project type, and achieves the effect of distinguishing the expert's technical field and project type through the summary extraction model. On the other hand, the summary extraction model can also be used to distinguish between subdivided technical fields, making the screening of the expert's technical background more refined and convenient, and achieving a better match between the expert's technical background and the project to be audited, which helps to improve the audit effect. By establishing a simulated audit model, it can not only be used to screen experts, but also to predict the audit results, which is helpful for the arrangement of audit activities.

[0010] Other features and advantages of the various embodiments of the present specification will be further disclosed in the following detailed description and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 A schematic diagram is provided for the application scenario of the embodiments of this specification.

[0013] Figure 2 A schematic diagram of the selection and matching of audit experts provided in the embodiments of this specification.

[0014] Figure 3 A schematic diagram of the application architecture of the audit expert selection and matching method provided in the embodiments of this specification.

[0015] Figure 4 A schematic diagram of the interactive interface provided in the embodiments of this specification.

[0016] Figure 5 A flowchart of the audit expert selection and matching method provided in the embodiments of this specification.

[0017] Figure 6 This is a flow chart of a method for establishing a summary extraction model provided in an embodiment of this specification.

[0018] Figure 7 A flowchart of a method for establishing a simulation audit model provided in an embodiment of this specification.

[0019] Figure 8 A schematic diagram of the audit expert selection and matching management system provided in the embodiments of this specification.

[0020] Fig. 9 A schematic diagram of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0021] The following is an explanation and description of the technical solutions of the embodiments of this specification in conjunction with the drawings of the embodiments of this specification, but the following embodiments are only preferred embodiments of this specification, not all. Based on the embodiments in the implementation mode, other embodiments obtained by those skilled in the art without creative work are all within the scope of protection of this specification.

[0022] The terms "first", "second", "third", etc. in the description and claims of this specification and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0023] In the following description, terms such as "inside", "outside", "up", "down", "left", "right", etc. that indicate directions or positional relationships are only used to facilitate the description of the embodiments and simplify the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as a limitation of this specification.

[0024] The data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection of relevant data complies with the relevant laws, regulations and standards of relevant countries and regions.

[0025] Before describing the technical solution in this specification, an introduction is given to the application scenarios and related technologies of the technical solution.

[0026] Expert review project activities are to evaluate submitted research plans, results or applications. In the expert review project activities, it is necessary to determine the purpose, scope, and standards and principles to be followed. For example, in the allocation of scientific research funds, the purpose of the review is to select the most promising research topics; while in the process of formulating technical standards, more attention is paid to the feasibility and safety of the plan.

[0027] When forming an audit team, it is crucial to select the right audit expert11. Audit experts11 should be scholars or professionals with profound attainments and good reputation in a specific field. When selecting audit experts11, it is often necessary to consider multiple factors such as their professional background, research interests, past performance, etc., and try to avoid conflicts of interest.

[0028] The project materials 20 usually include a detailed description of the project, expected goals, technical roadmap, budget arrangements, etc. The review experts 11 will score or rate each project based on established standards, usually focusing on innovation, feasibility, impact and benefits. The review experts 11 may also make constructive comments and suggestions to help improve the project. Finally, the review conclusion will be formed after summarizing and analyzing the opinions of all review experts 11. This conclusion is not only the key basis for determining whether the project will be supported, but also provides guidance for subsequent improvements and perfection.

[0029] The selection and matching of audit experts 11 is an important part of modern scientific research management, project evaluation and academic evaluation system. In the early stage, the selection of audit experts 11 mainly relied on the personal experience and personal network of the organizer or person in charge, which was inefficient and easily affected by subjective factors. With the rapid development of information technology, the selection and matching technology of audit experts 11 has also experienced a transformation from manual selection to intelligent matching. Please refer to the attached Figure 1 , the expert selection and matching is to select and match a number of suitable audit experts 11 for each project from the expert database 10. The current selection of audit experts 11 is still only matched based on the professional background of the experts, etc., and there is still a lack of basis for judging the audit effect, and the matching is not precise enough.

[0030] To this end, this manual provides a method for selecting and matching audit experts11. Figure 2 , extracting the project summary 21 from the data 20 of the audited project and associating it with the project information 22. Generate the obfuscated summary 23 and obfuscated information 24 based on the project summary 21 and the project information 22. Input the project summary 21, the project information 22, the obfuscated summary 23 and the obfuscated information 24 into the simulated audit model 30 constructed for each audit expert 11, and select and match the experts based on the output results of the simulated audit model 30. Since the simulated audit model 30 is established for each expert, it can reflect the expert's professional knowledge scope and review ability, thereby having a more accurate knowledge matching and selection effect.

[0031] The audit expert selection and matching method provided in this manual is used for Figure 3 The system architecture shown, Figure 3FIG. 4 is a schematic diagram of a system architecture in an embodiment of the present application. The system architecture includes a server 40 and a terminal device 50, and an interactive interface 51 is provided on the terminal device 50. Figure 4 . Among them, the interactive interface 51 can be run on the terminal device 50 in the form of a browser, or in the form of an independent application (APP), etc. The specific display form of the client is not limited here. The server 40 involved in this application can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and big data and artificial intelligence platforms. The terminal device 50 can be a smart phone, a tablet computer, a laptop, a PDA, a personal computer, a smart speaker, a smart TV, a smart watch, a car device, a wearable device, etc., but is not limited to this. The terminal device 50 and the server 40 can be directly or indirectly connected by wired or wireless communication, which is not limited in this application. The number of servers 40 and terminal devices 50 is also not limited.

[0032] For details, please refer to the attached Figure 5 The audit expert 11 selection and matching method includes the following steps: Step S101) Establish a summary extraction model for each expert and associate it with the audit project type.

[0033] In this embodiment, a summary extraction model is established for each expert, and each summary extraction model is associated with an audit project type. That is to say, each expert will establish a summary extraction model when reviewing an audit project type. Specifically, when expert A is used to review the natural fund application project, a summary extraction model is established, and the audit project type associated with the summary extraction model is the natural fund application project in the software field. When expert A is used to review ITSS certification, a summary extraction model is also established, and the audit project type associated with the summary extraction model is the ITSS certification project. When expert B is used to review the natural fund application project, a summary extraction model is established, and the audit project type associated with the summary extraction model is the natural fund application project in the precision manufacturing field. It can be seen that the knowledge background of expert A is the software field, and the knowledge background of expert B is the mechanical manufacturing field. And when expert A accepts the review of different projects, although the review is also based on his knowledge in the software field, the extracted summaries are different, so different summary extraction models are established.

[0034] The establishment of the summary extraction model mainly relies on the collection and use of sample data. Specifically, the method of establishing the summary extraction model for each expert and associating the audit project type includes the following steps: Go through each audit item type in turn and perform the following steps. Figure 6 ,include: Step S201 ) Read the data 20 of multiple projects under the current audit project type, and generate multiple project summaries 21 for each data 20 .

[0035] Among the generated multiple project summaries 21, some project summaries 21 more comprehensively reflect the key contents of the document 20, while some project summaries 21 only reflect part of the key contents of the document 20. Although some project summaries 21 comprehensively reflect the key contents of the document 20, the expressions such as words and sentences used are not accurate enough, and even have some errors. These project summaries 21 are all shown to the experts.

[0036] Step S202) Receive the marks of the reflectivity scores of some of the project summaries 21. Some of these project summaries 21 have manually marked reflectivity scores. The reflectivity scores are sourced from staff, who are experts who have been stored in the database, or experts or scholars who have been determined to be in the corresponding field.

[0037] Step S203) When an expert enters the database, the project information 20 is displayed to the expert, and then multiple project summaries 21 of the project are displayed to the expert. When an expert enters the database, a summary extraction model is established for the expert, and multiple summary extraction models are established. The audit project type associated with each summary extraction model is different. At the same time, the audit project type associated with the expert's summary extraction model also determines the field that the expert can audit, that is, determines the expert's field.

[0038] Step S204) Receive the reflectivity score of the project abstract 21 provided by the expert. The experts in the database score the reflectivity of the given project abstract 21. At this time, the project abstract 21 displayed to the experts is regardless of the technical field or the type of the audited project.

[0039] In fact, depending on whether the audit project type itself has a technical field, there are the following situations: when the audit project type itself is oriented to multiple technical fields, such as the natural research fund application project, it involves the software field, chemical field, mechanical manufacturing field, and also involves mathematical research, social research, etc., which has a relatively broad technical field. The ITSS certification project is a project exclusively in the software field.

[0040] At this time, the expert A will be shown the materials 20 and project abstracts 21 of natural research fund application projects in multiple fields. For the materials 20 and multiple project abstracts 21 of projects in the software field, the expert A can mark the reflectivity scores more accurately. However, for the materials 20 and project abstracts 21 of natural research fund application projects in non-software fields, such as the chemical industry, the expert A cannot accurately mark the reflectivity scores of the project abstracts 21 because he cannot understand them.

[0041] Step S205) Obtain the closeness of the expert's reflection score to the project summary 21 with the reflection score mark.

[0042] Thus, in step S205), when the data 20 and the project abstract 21 of the project in the field of chemical engineering marked by expert A are scored for reflection, the reflection score will be inaccurate. At this time, when compared with the project abstracts 21 that have been manually marked for reflection scores in advance, it will be found that the proximity is low. It can be concluded that expert A is not suitable for the natural fund application project in the field of chemical engineering. That is, when the audit project type is "natural fund application project in the field of chemical engineering", the abstract extraction model belonging to expert A will not be selected, and expert A will not be selected. Similarly, the data 20 and the project abstract 21 of the project in the field of software marked by expert A will be more accurate in reflection scores. At this time, compared with those reflection scores that have been manually marked in advance, the proximity is higher. It can be concluded that when the audit project type is "natural fund application project in the field of software", expert A is likely to be selected.

[0043] Step S206) When the proximity is greater than a preset threshold, the expert is associated with the current audit project type. That is, when the proximity corresponding to expert A is greater than a preset threshold, expert A will be associated with the "Natural Science Foundation Application Project in the Software Field".

[0044] Step S207) According to the expert's reflection rating of the project abstract 21 without reflection rating mark, sample data is established, and the sample data includes the document 20, the project abstract 21 and the reflection rating. The reflection rating of the project abstract 21 in the software field without reflection rating mark by expert A represents the abstract extraction result with the characteristics of expert A. Based on this, sample data is established, so that a summary extraction model suitable for expert A can be trained based on the sample data. In the subsequent steps, the summary extraction model trained with these sample data will be associated with the "Natural Science Foundation Application Project in the Software Field" and will also be associated with expert A. Similarly, the reflection rating of expert A for the document 20 and its project abstract 21 belonging to the "ITSS Certification Project" will also be closer to the previously marked reflection rating than the threshold. Therefore, sample data in the field of "ITSS Certification Project" can be obtained in the future, and the summary extraction model trained with these sample data will be associated with the "ITSS Certification Project" and will also be associated with expert A.

[0045] Step S208) Obtain a summary extraction model based on the sample data and associate the current audit project type and the expert.

[0046] On the other hand, in another embodiment, the method for obtaining a summary extraction model according to the sample data includes: A machine learning model is established and trained using the sample data, and a summary extraction model is obtained according to the machine learning model.

[0047] On the other hand, in another embodiment, the method for obtaining a summary extraction model according to the sample data includes: A natural language task is generated according to the sample data, the natural language task is input into a pre-connected large language model, and a summary extraction model is obtained according to the large language model.

[0048] On the other hand, in another embodiment, the method for obtaining a summary extraction model according to the sample data includes: Generate a natural language task according to the sample data, and input the natural language task into a pre-connected large language model; A machine learning model is established, and the large language model is used to guide training, and a summary extraction model is obtained according to the trained machine learning model.

[0049] Alternatively, other technologies disclosed in the art may be used to obtain a summary extraction model based on sample data.

[0050] Step S102 ) Read the document 20 of the project to be reviewed, and use the summary extraction model corresponding to the review project type to extract the summary of the document 20 of the project to be reviewed, which is recorded as the project summary 21 .

[0051] According to the above scheme, a summary extraction model for each expert is established, and each summary extraction model is associated with an expert and an audit project type. For the document 20 of the project to be audited, a summary extraction model of the corresponding type can be selected according to the audit project type. In step S102), there are multiple summary extraction models that meet the audit project type, and each summary extraction model is associated with an expert. At this time, the selection and matching of experts has not been completed. Therefore, in step S102), a summary extraction model is actually randomly selected without considering whether the associated expert will be selected, nor the differences between summary extraction models associated with different experts. It is believed that most of the summary extraction models of this audit project type can generally extract the project summary 21 of the document 20.

[0052] Step S103 ) A simulation audit model 30 is established for each expert. The input of the simulation audit model 30 is the project summary 21 and the project information 22 , and the output is a formatted text containing predetermined fields, which is recorded as the audit text 31 .

[0053] Project information 22 includes project name, project purpose, project planned start time, project cycle, project executives, project budget, etc. There may be overlapping parts between project information 22 and project summary 21, which does not affect the implementation of this embodiment. For example, the project name usually appears in the document 20, and thus will be extracted by the summary extraction model and put into the project summary 21. However, the project cycle may not be extracted as a keyword by the summary extraction model. The combination of project summary 21 and project information 22 can provide more comprehensive content for review.

[0054] The audit text 31 is a formatted text. For example, the formatted text is a KV value pair, such as project name: XX project, project budget: 1 million yuan, project executives: {A, B, C, D}, project planned start time: 2023, project success probability: 80%, project executive professional matching: 68%, project expected benefit evaluation: high expected benefit, etc. Among them, the project name, project budget, project executives, and project planned start time can be obtained directly from the project summary 21 or project information 22. The probability of project success, the professional matching of project executives, and the expected benefit evaluation of the project require an expert simulation model to obtain. In essence, the corresponding experts rely on their knowledge and judgment ability to give results, form sample data, and then train the simulation audit model 30 with the sample data.

[0055] For details, please refer to the attached Figure 7 , the method of establishing the simulated audit model 30 of each expert includes: Step S301) displays the information 20 of multiple projects under the audit project type and the fields included in the audit text 31 to the expert.

[0056] Step S302) Receive the value of the field filled in by the expert and obtain the review text 31.

[0057] For example, experts fill in the project success probability, professional matching degree of project executives, and expected project benefit evaluation of each project based on the data 20. Samples are generated in subsequent steps.

[0058] Step S303 ) Use the corresponding abstract extraction model to extract the abstract of the document 20 to obtain the project abstract 21 .

[0059] Step S304 ) Obtain the project information 22 of the project, and obtain a sample according to the project summary 21 , the project information 22 and the review text 31 .

[0060] Step S305) Use the pre-connected large language model to learn the sample, and obtain the simulated audit model 30 based on the large language model.

[0061] After obtaining the sample, the sample is learned using the pre-connected large language model, so that the large language model can learn the knowledge contained in the sample, and then can achieve the effect of simulated audit, that is, can obtain the simulated audit model 30. On the one hand, the learned large language model can be directly used as the simulated audit model 30. On the other hand, a machine learning model can be further specially trained as the simulated audit model 30. Specifically, according to the large language model, the method for obtaining the simulated audit model 30 includes: Establish and use the project summary 21 and project information 22 to train an autoencoder model, and obtain a feature extraction model based on the autoencoder model; Generate multiple project summaries 21 and project information 22; Obtaining the review text 31 of the project summary 21 and the project information 22 according to the large language model; Using the feature extraction model to extract features of the project summary 21 and project information 22, and associating the features with the review text 31 as an extended sample; A machine learning model is established and trained using the extended sample, and a simulation audit model 30 is obtained based on the trained machine learning model.

[0062] Step S104) Read the project information 22 of the project to be audited, and generate a confused summary 23 and confused information 24 according to the project summary 21 and the project information 22 of the project to be audited, wherein the confused summary 23 and the confused information 24 have a known predetermined audit result. The confused summary 23 and the confused information 24 can be obtained by partially modifying the project summary 21 and the project information 22. Exemplarily, the keywords related to the project background introduction in the project summary 21 are replaced with other irrelevant keywords to generate a confused summary 23. At the same time, the project executors in the project information 22 are replaced with personnel in other professional fields, so that non-professionals carry out the project, and the confused information 24 is generated. It can be seen that if the simulation audit model 30 is appropriate, that is, it can distinguish between the project summary 21 and the confused summary 23, and can distinguish between the project information 22 and the confused information 24, then the simulation audit model 30 can output the correct audit result.

[0063] On the contrary, if the technical background of an expert does not match the technology of the current project to be reviewed, the simulation review model 30 corresponding to the expert will not be able to correctly distinguish the project summary 21, project information 22, and the obfuscated summary 23, obfuscated information 24, and will output an erroneous review result, so that the expert can be excluded from the review of the project to be reviewed.

[0064] It is worth noting that even if the expert is in the same field as the project to be audited, there are differences in the sub-fields, which causes the expert's simulated audit model 30 to be unable to correctly distinguish between the project summary 21, project information 22, and the confused summary 23, confused information 24, and will output an incorrect audit result. For example, the same software field is also divided into sub-fields such as the embedded software field, the operating system software field, the application software field, and the web application software field. If the project to be audited is in the operating system software field, then expert D, who is also in the software field but has a knowledge structure of embedded development, is not competent for the audit of the project to be audited in the operating system software field. The summary extraction model corresponding to expert D cannot correctly extract the project summary 21 of the material 20 in the operating system software field. Specifically, this is because expert D cannot provide a correct reflectivity score in step S204).

[0065] Step S105 ) Input the obfuscated summary 23 and obfuscated information 24 into each expert's simulated audit model 30 to obtain an obfuscated audit text 32 .

[0066] Exemplarily, the abstract extraction model of "Natural Science Foundation Application Project in Software Field" associated with expert C is selected to obtain the project abstract 21 of the data 20 of the project to be reviewed. Then, after associating the project information 22, it is input into the simulation review model 30 of each expert, that is, into the simulation review model 30 of expert A, expert B, expert C, expert D, etc.

[0067] Step S106) The audit text 31 and the obfuscated audit text 32 are respectively compared with the audit rules of the corresponding audit project type to obtain the audit results. Exemplary audit rules include: Rule 1, the probability of project success must be greater than or equal to 60%; Rule 2, the professional matching degree of project executors must be greater than or equal to 75%; Rule 3, the expected benefit evaluation of the project must be high.

[0068] Step S107) When the audit result matches the predetermined audit result, the corresponding expert is included in the candidate pool 12.

[0069] When the expert's simulated audit model 30 is suitable for the project to be audited, it will give a correct audit result and can correctly distinguish the audit results of the project summary 21, project information 22, and the confused summary 23 and confused information 24. The result can be obtained through steps S106) to S107). After all suitable experts are included in the candidate library 12, the next step is performed.

[0070] Step S108) Randomly select a predetermined number of experts from the candidate pool 12 as the review experts 11 for the project to be reviewed. Randomly selecting a predetermined number of experts from the candidate pool 12 as the review experts 11 for the project to be reviewed can ensure fairness.

[0071] Specifically, the method of randomly selecting a predetermined number of experts from the candidate pool 12 as the audit experts 11 for the project to be audited includes: Randomly selecting more than a predetermined number of experts from the candidate pool 12; Extract the project summary 21 from the data 20 of the project to be reviewed using the summary extraction model corresponding to the selected expert; Clustering the project summaries 21 using a clustering algorithm to obtain cluster centers; sorting all experts in ascending order of distance from the cluster center; Experts are selected in order as audit experts 11 for the items to be audited until a predetermined number is reached.

[0072] The summary extraction model corresponding to the expert extracts the summary from the data 20 of the project to be reviewed, and further selection is performed based on the summary, so that more appropriate and suitable experts can be further selected as the review experts 11 of the project to be reviewed.

[0073] On the other hand, this specification provides a selection and matching management system for audit experts 11, please refer to the attached Figure 8 ,include: Extraction module 100, establishing a summary extraction model for each expert and associating it with the audit project type; The summary module 200 reads the data 20 of the project to be reviewed, and uses the summary extraction model corresponding to the review project type to extract the summary of the data 20 of the project to be reviewed, which is recorded as the project summary 21; The audit module 300 establishes a simulated audit model 30 for each expert, wherein the input of the simulated audit model 30 is the project summary 21 and the project information 22, and the output is a formatted text containing predetermined fields, which is recorded as the audit text 31; The obfuscation module 400 reads the project information 22 of the project to be reviewed, and generates an obfuscated summary 23 and obfuscated information 24 according to the project summary 21 and the project information 22 of the project to be reviewed, wherein the obfuscated summary 23 and the obfuscated information 24 have a known predetermined review result; The obfuscation review module 500 inputs the obfuscation summary 23 and the obfuscation information 24 into the simulation review model 30 of each expert to obtain the obfuscation review text 32; The comparison module 600 compares the audit text 31 and the obfuscated audit text 32 with the audit rules of the corresponding audit item types to obtain the audit results; The selection module 700 includes the corresponding expert in the selection pool 12 when the audit result matches the predetermined audit result; The selection module 800 randomly selects a predetermined number of experts from the candidate library 12 as the review experts 11 for the items to be reviewed.

[0074] See also Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of this specification is shown.

[0075] like Fig. 9As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105 and at least one communication bus 1102. Among them, the communication bus 1102 can be used to realize the connection and communication of the above-mentioned components. Among them, the user interface 1103 may include a button, and the optional user interface may also include a standard wired interface and a wireless interface. Among them, the network interface 1104 may include but is not limited to a Bluetooth module, an NFC module, a Wi-Fi module, etc. Among them, the processor 1101 may include one or more processing cores. The processor 1101 uses various interfaces and lines to connect various parts in the entire electronic device 1100, and executes various functions and processes data of the routing device 1100 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1105, and calling data stored in the memory 1105. Optionally, the processor 1101 can be implemented in at least one hardware form of DSP, FPGA, and PLA. The processor 1101 may integrate one or a combination of CPU, GPU and modem, etc. Among them, the CPU mainly processes the operating system, user interface and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication.

[0076] It is understandable that the above-mentioned modem may not be integrated into the processor 1101, but may be implemented by a separate chip.

[0077] Among them, the memory 1105 may include RAM or ROM. Optionally, the memory 1105 includes a non-transitory computer-readable medium. The memory 1105 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1105 may also be at least one storage device located away from the aforementioned processor 1101. The memory 1105 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application. The processor 1101 may be used to call the application stored in the memory 1105 and execute the methods in the above-mentioned multiple embodiments.

[0078] The embodiments of this specification also provide a computer-readable storage medium, which stores instructions, and when the instructions are executed on a computer or a processor, the computer or the processor executes the multiple steps in the above embodiments. If the components of the above electronic device are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0079] The embodiments of this specification also provide a computer program product, including a computer program, which implements multiple steps in the above embodiments when executed by a processor.

[0080] In the absence of conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0081] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes a plurality of computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of this specification is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, a computer, a server 40 or a data center to another website site, a computer, a server 40 or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server 40, a data center, etc. that includes multiple available media integration. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)), etc.

[0082] When implemented by hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and realize the corresponding function. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit, and its logic function is determined by the user programming the device. The designer programs by himself to "integrate" a digital system on a PLD, without asking a chip manufacturer to design and make a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when writing program development, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL), and HDL is not just one, but many. Those skilled in the art should also be aware that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit to easily obtain the hardware circuit that implements the logic method flow.

[0083] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Without departing from the design spirit of this specification, various modifications and improvements made to the technical solutions of this specification by ordinary technicians in this field should fall within the scope of protection determined by the claims of this specification.

Claims

1. A method for selecting and matching audit experts, characterized in that: Includes steps: Build a summary extraction model for each expert and associate it with the audit project type; Read the information of the project to be reviewed, and use the summary extraction model corresponding to the review project type to extract the summary of the information of the project to be reviewed, and record it as the project summary; Establishing a simulation audit model for each expert, wherein the input of the simulation audit model is the project summary and project information, and the output is a formatted text containing predetermined fields, which is recorded as the audit text; Reading the project information of the project to be reviewed, and generating an obfuscated summary and obfuscated information according to the project summary and the project information of the project to be reviewed, wherein the obfuscated summary and the obfuscated information have a known predetermined review result; Inputting the obfuscated summary and obfuscated information into the simulated audit model of each expert to obtain an obfuscated audit text; Compare the audit text and the obfuscated audit text with the audit rules of the corresponding audit item types to obtain the audit results; When the audit result is consistent with the predetermined audit result, the corresponding expert is included in the candidate pool; A predetermined number of experts are randomly selected from the candidate pool as review experts for the items to be reviewed.

2. A method for selecting and matching audit experts according to claim 1, characterized in that: The method for establishing a summary extraction model for each expert and associating the audit project type includes the following steps: Go through each audit item type in turn and perform the following steps: Read the data of multiple projects under the current audit project type and generate multiple project summaries for each data; Receive a mark of reflectivity rating for some of the project summaries; When an expert enters the database, the information of the project is displayed to the expert, and then multiple project summaries of the project are displayed to the expert; receiving a reflectivity score of the project summary provided by the expert; Obtaining the proximity of the experts' reflectivity scores to the project summaries with reflectivity score marks; When the proximity is greater than a preset threshold, the expert is associated with the current audit project type; According to the expert's responsiveness score for the project abstract without a responsiveness score mark, sample data is established, wherein the sample data includes the material, the project abstract and the responsiveness score; A summary extraction model is obtained based on the sample data, and the current audit project type and the expert are associated.

3. A method for selecting and matching audit experts according to claim 2, characterized in that: The method for obtaining a summary extraction model according to the sample data includes: Establishing and using the sample data to train a machine learning model, and obtaining a summary extraction model according to the machine learning model; or, The method for obtaining a summary extraction model according to the sample data includes: Generate a natural language task according to the sample data, input the natural language task into a pre-connected large language model, and obtain a summary extraction model according to the large language model; or, The method for obtaining a summary extraction model according to the sample data includes: Generate a natural language task according to the sample data, and input the natural language task into a pre-connected large language model; A machine learning model is established, and the large language model is used to guide training, and a summary extraction model is obtained according to the trained machine learning model.

4. A method for selecting and matching audit experts according to any one of claims 1 to 3, characterized in that: The method of establishing a simulated audit model for each expert includes: Displaying information of multiple projects under the audit project type and fields included in the audit text to the expert; Receive the value of the field filled in by the expert to obtain the audit text; Extract the material summary using the corresponding summary extraction model to obtain a project summary; Obtaining project information of the project, and obtaining a sample according to the project summary, project information and the review text; The sample is learned using a pre-accessed large language model, and a simulated audit model is obtained based on the large language model.

5. A method for selecting and matching audit experts according to claim 4, characterized in that: According to the large language model, the method for obtaining a simulated audit model includes: Establish and use the project summary and project information to train an autoencoder model, and obtain a feature extraction model based on the autoencoder model; Generate multiple project summaries and project information; Obtaining a review text of the project summary and project information according to the large language model; Extract features of the project summary and project information using the feature extraction model, and associate the features with the review text as an extended sample; Establish and use the extended sample to train a machine learning model, and obtain a simulated audit model based on the trained machine learning model.

6. A method for selecting and matching audit experts according to any one of claims 1 to 3, characterized in that: The method of randomly selecting a predetermined number of experts from the candidate pool as review experts for the project to be reviewed includes: Randomly selecting more than a predetermined number of experts from the pool to be selected; Extract the project summaries from the data of the projects to be reviewed using the corresponding summary extraction models of the selected experts; Clustering the project summaries using a clustering algorithm to obtain cluster centers; sorting all experts in ascending order of distance from the cluster center; Experts are selected in order as review experts for the items to be reviewed until the predetermined number is reached.

7. An audit expert selection and matching management system, characterized in that: include: The extraction module builds a summary extraction model for each expert and associates it with the audit project type; A summary module reads the information of the project to be reviewed, and uses a summary extraction model corresponding to the review project type to extract a summary of the information of the project to be reviewed, which is recorded as a project summary; The audit module establishes a simulated audit model for each expert, wherein the input of the simulated audit model is the project summary and project information, and the output is a formatted text containing predetermined fields, which is recorded as the audit text; an obfuscation module, which reads the project information of the project to be reviewed, and generates an obfuscated summary and obfuscated information according to the project summary and project information of the project to be reviewed, wherein the obfuscated summary and obfuscated information have a known predetermined review result; The obfuscation review module inputs the obfuscation summary and obfuscation information into the simulation review model of each expert to obtain an obfuscation review text; A comparison module compares the audit text and the obfuscated audit text with the audit rules of the corresponding audit item type to obtain the audit result; A selection module, when the audit result matches the predetermined audit result, the corresponding expert is included in the selection pool; The selection module randomly selects a predetermined number of experts from the candidate pool as review experts for the items to be reviewed.

8. An electronic device, characterized in that: including a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 6.

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

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

Images