A multi-transaction review expert configurable extraction method, system, device and medium

Abstract

The application discloses a multi-item review expert configurable extraction method, system, device and medium, and relates to the technical field of computer software and service. In order to solve the problem that the traditional expert extraction technology cannot deal with multi-item and complex business scenarios, the scheme comprises the following steps: based on the extraction scene demand, configuring the extraction rule group, the precondition rule, the trigger rule, the "and rule group", the "or rule group" and the terminal rule of the candidate expert; configuring the judgment process of the precondition rule and the trigger rule in the extraction rule group; based on the configured extraction rule group, the judgment process of the precondition rule and the trigger rule in the extraction rule group, extracting the expert who meets the precondition rule and the trigger rule from the candidate expert set through a preset expert extraction algorithm, and outputting the extraction result. The application can configure the extraction conditions of different items, and improve the efficiency and standardization of the extraction process.

Description

Technical Field

[0001] This invention relates to the field of computer software and services technology, specifically to a method, system, device, and medium for configurable extraction of multi-item review experts. Background Technology

[0002] In production activities such as project procurement, bidding, and expert review, it is often necessary to select third-party experts or personnel. To ensure the rationality and standardization of the selection process, expert extraction techniques are often used. Most existing expert extraction techniques follow the principles of randomness and avoidance, which can ensure the rationality and effectiveness of the selection to a certain extent. However, these techniques are mainly suitable for business systems with a simple range of tasks, and are difficult to handle situations with complex tasks and large volumes of business.

[0003] In multi-task business systems, different tasks often have specific requirements for the third-party personnel (such as experts) selected. Some tasks may only require experts with specific professional backgrounds, while others may consider additional conditions such as work experience, age, and gender. Traditional extraction techniques struggle to effectively extract personnel based on these personalized needs. When dealing with multi-task review scenarios, manual intervention is often required to set extraction conditions separately for different business scenarios, and even to perform customized development. All of these significantly increase the operational difficulty and time costs. Summary of the Invention

[0004] To address the shortcomings of existing personnel (expert) extraction technologies in review systems, this invention provides a configurable extraction method, system, device, and medium for multi-item review experts, enabling configurability of extraction conditions for different items, thereby improving the efficiency and standardization of the extraction process.

[0005] Firstly, the present invention provides a configurable extraction method for multi-item review experts, and the technical solution adopted to solve the above-mentioned technical problem is as follows: A configurable extraction method for multi-item review experts includes the following steps: S1. Based on the extraction scenario requirements, configure the extraction rule group, precondition rules, trigger rules, "AND rule group", "OR rule group" and terminal rules for candidate experts. Among them: the extraction rule group includes precondition rules and trigger rules; both precondition rules and trigger rules are composed of "AND rule group" and / or "OR rule group"; the terminal rules include four attributes: query tag, matching tag, matching relationship and matching method. S2. Configure the judgment process for the pre-rules and triggering rules in the extraction rule group; S3. Based on the configured extraction rule group and the judgment process of the pre-rules and triggering rules in the extraction rule group, the experts who simultaneously meet the pre-rules and triggering rules are extracted from the candidate expert set through the preset expert extraction algorithm, and the extraction results are output.

[0006] Optionally, in step S1, the extraction rule group refers to the complete set of rules constructed to adapt to the expert label requirements of the specified matter. It is the highest level rule unit, containing a set of pre-rules and at least one set of triggering rules. The extraction rule group completes the entire process of candidate expert extraction through the coordinated execution of the pre-rules and triggering rules. Pre-selection rules are the admission verification rules for candidate experts to enter the selection process. As a prerequisite for triggering rule matching, they consist of one or more nested combinations of "AND rule group" and "OR rule group". They cannot be set to correspond to the number of people to be selected and are only used as conditional filtering. Triggering rules are core rules used to accurately screen candidates who meet the requirements of the item tags after the candidates have passed the pre-rule verification. They consist of one or more nested combinations of "AND rule group" and "OR rule group". Each triggering rule must set the corresponding number of people to be selected. An "AND rule group" is composed of two or more terminal rules combined by a logical AND relationship. The "AND rule group" will only be matched if all terminal rules in the group meet the matching requirements. An "OR rule group" is composed of two or more terminal rules combined according to a logical OR relationship. When any one or more terminal rules in the group meet the matching requirements, the "OR rule group" will be matched successfully. The terminal rule refers to the smallest logical unit of expert tag matching, which cannot be further divided. It defines the specific matching standard of expert tags under a single dimension through four attributes: query tag, matching tag, matching relationship, and matching method.

[0007] Further optionally, in step S1, the terminal rule includes four attributes: query tag, matching tag, matching relationship, and matching method, wherein: The query tag refers to the target attribute that needs to be filtered. Matching tags refer to the specific values ​​required for filtering; The matching method refers to the association rules between query tags and matching tags, which are used to clarify "how to use matching tags to filter the attributes corresponding to query tags"; Matching relationship refers to the specific sub-type of matching method, and its range of options is determined by the type of query tag; Matching methods include fixed value matching and dynamic matching. Fixed value matching means that the matching tag itself represents the specific value required for filtering, while dynamic matching means that the matching tag only participates in the extraction process as a prompt field.

[0008] Optionally, in step S1, based on the extraction scenario requirements, it supports configuring extraction rule groups for candidate experts at the event level or business level, enabling flexible configuration of extraction conditions: At the item level, define extraction rule groups and bind each item to a fixed extraction rule group so that all business under that item is extracted by experts based on that extraction rule. Define extraction rule groups at the business level and bind each business to a fixed extraction rule group. This is suitable for scenarios where the business involves multiple extractions in the process or requires third-party system calls.

[0009] Further optionally, step S2 specifically includes: S2.1 Receive a set of candidate experts containing different labels as input; S2.2 First, the candidate expert set is filtered and preliminarily judged according to the pre-condition rules, and then the candidate expert set after the preliminary judgment is judged again according to the triggering rules. S2.3 Output a Boolean value to indicate whether each candidate expert meets all the filtering conditions set in the pre-rules and trigger rules; Wherein: a Boolean value of true indicates that the candidate expert meets all the screening conditions, and a Boolean value of false indicates that the candidate expert does not meet the screening conditions; and candidate experts who fail the preliminary rule judgment will directly output a Boolean value of false and will not enter the secondary judgment stage of triggering rules.

[0010] Optionally, step S3 is executed, which uses a preset expert extraction algorithm to extract experts from the candidate expert set who simultaneously meet the preconditions and triggering rules, and outputs the extraction results. This process specifically includes: S3.1 Receive the candidate expert set, the pre-rule set, the trigger rule set, and business information as input; S3.2. Divide the candidate expert set into segments and process them in batches. S3.3 For each expert in each batch of candidate experts, determine in turn whether they meet the prerequisite rules and triggering rules; S3.4 Add the qualified experts to the selected expert set and update the number of selected experts that triggered the rule; S3.5 Output the selected expert set as the extraction result.

[0011] Secondly, this invention provides a configurable expert extraction system for multi-item review, and the technical solution adopted to solve the above-mentioned technical problems is as follows: A configurable expert extraction system for multi-item review, used to implement the method described in the first aspect, specifically includes: The rule configuration module is used to configure the extraction rule groups, precondition rules, trigger rules, AND rule groups, OR rule groups, and terminal rules for candidate experts based on the extraction scenario requirements. Among them, the extraction rule groups include precondition rules and trigger rules; both precondition rules and trigger rules are composed of AND rule groups and / or OR rule groups; the terminal rules include four attributes: query tag, matching tag, matching relationship, and matching method. The rule determination configuration module is used to configure the determination process for extracting prerequisite rules and triggering rules from the rule group; The rule execution module is used to extract experts from the candidate expert set that simultaneously meet the pre-defined rules and triggering rules based on the configured extraction rule group, the judgment process of the pre-defined rules and triggering rules in the extraction rule group, and the preset expert extraction algorithm, and output the extraction results.

[0012] Thirdly, the present invention also provides a configurable extraction device for multi-item review experts, which includes: a memory and at least one processor; The memory contains computer programs; The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the method as described in the first aspect.

[0013] Fourthly, the present invention also provides a computer-readable storage medium storing a computer program that can be executed by a processor to implement the method as described in the first aspect.

[0014] The present invention provides a configurable extraction method, system, device, and medium for multi-item review experts, which has the following advantages compared with the prior art: This invention enables flexible configuration of extraction conditions by configuring various extraction rules, including end rules, AND rule groups, OR rule groups, trigger rules, and precondition rules. During the extraction process, experts who meet the conditions are automatically selected according to the configured rules, which significantly improves the extraction efficiency and standardization. It solves the problem that traditional expert extraction technology is difficult to cope with multiple matters and complex business scenarios in the fields of government service informatization and expert review management. This invention supports configuring extraction rule groups at the event or business level, enhancing the flexibility and adaptability of rule extraction; by tightly binding extraction rules with events or business, it improves the security and availability of the interface and promotes seamless integration with other business systems. Attached Figure Description

[0015] Appendix Figure 1 This is the end-rule entity relationship diagram configured by the method described in this invention; Appendix Figure 2This is a flowchart illustrating the determination of the pre-rules / triggering rules configured by the method described in this invention; Appendix Figure 3 This is an example diagram illustrating the configuration of extraction rule groups at the event level using the method described in this invention; Appendix Figure 4 This is an example diagram illustrating the configuration of extraction rule groups at the business level using the method described in this invention; Appendix Figure 5 This is a block diagram of the module connection of the system described in this invention. Detailed Implementation

[0016] To make the technical solution, the technical problem solved, and the technical effect of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with specific embodiments.

[0017] Example 1: This example proposes a configurable extraction method for multi-item review experts, which includes the following steps: S1. Based on the extraction scenario requirements, configure the extraction rule group, pre-extraction rule, triggering rule, "AND rule group", "OR rule group" and terminal rule for candidate experts. Among them: the extraction rule group includes pre-extraction rule and triggering rule; both pre-extraction rule and triggering rule are composed of "AND rule group" and / or "OR rule group"; the terminal rule includes four attributes: query tag, matching tag, matching relationship and matching method.

[0018] Specifically, (1) the extraction rule group refers to the complete set of rules constructed to adapt to the expert label requirements of the specified matter. It is the highest level rule unit, which includes a set of pre-rules and at least one set of triggering rules. The extraction rule group completes the whole process of candidate expert extraction through the coordinated execution of pre-rules and triggering rules. (2) Pre-rules are the admission verification rules for candidate experts to enter the extraction process. As a prerequisite for triggering rule matching, they are composed of one or more nested combinations of "AND rule group" and "OR rule group". They cannot be set to the corresponding number of people to be extracted and are only used as conditional filtering. (3) Triggering rules are core rules used to accurately screen candidates who meet the requirements of the item label after the candidate experts have passed the pre-rule verification. They consist of one or more nested combinations of "AND rule group" and "OR rule group". Each triggering rule must set the corresponding number of people to be selected. (4) An “AND rule group” is composed of two or more terminal rules combined by a logical AND relationship. The “AND rule group” will be matched only if all terminal rules in the group meet the matching requirements. (5) An “OR rule group” is composed of two or more end rules combined according to a logical OR relationship. When any one or more end rules in the group meet the matching requirements, the “OR rule group” will be matched. (6) Reference Appendix Figure 1The final rule refers to the smallest logical unit of expert tag matching, which cannot be further subdivided. It clarifies the specific matching criteria for expert tags under a single dimension through four attributes: query tag, matching tag, matching relationship, and matching method. Among them: The query tags refer to the target attributes that need to be filtered, such as age, gender, etc. Matching tags refer to specific filtering requirements, such as age 40, gender female, etc. Matching method refers to the association rule between query tags and matching tags, which is used to clarify "how to use matching tags to filter the attributes corresponding to query tags". For example, for the age tag, it displays "not lower than" and "not higher than", and for the gender tag, it displays "same" and "different". Matching relationship refers to the specific sub-type of matching method, and its range of options is determined by the type of query tag; Matching methods include fixed-value matching and dynamic matching. Fixed-value matching means that the matching tag itself represents the specific requirements for screening, such as 40 years old or female. Dynamic matching means that the matching tag only participates in the extraction process as a suggestive field, such as applicant's age or applicant's gender.

[0019] It should be added that, see attached reference. Figure 3 , 4 Based on the extraction scenario requirements, it supports configuring candidate expert extraction rule groups at the event level or business level, enabling flexible configuration of extraction conditions: At the item level, define extraction rule groups and bind each item to a fixed extraction rule group so that all business under that item is extracted by experts based on that extraction rule. Define extraction rule groups at the business level and bind each business to a fixed extraction rule group. This is suitable for scenarios where the business involves multiple extractions in the process or requires third-party system calls.

[0020] S2. Configure the judgment process for the pre-rules and triggering rules in the extraction rule group, refer to the appendix. Figure 2 The specific process is as follows: S2.1 Receive a set of candidate experts containing different labels as input; S2.2 First, the candidate expert set is filtered and preliminarily judged according to the pre-condition rules, and then the candidate expert set after the preliminary judgment is judged again according to the triggering rules. S2.3 Output a Boolean value to indicate whether each candidate expert meets all the filtering conditions set in the pre-rules and trigger rules; Wherein: a Boolean value of true indicates that the candidate expert meets all the screening conditions, and a Boolean value of false indicates that the candidate expert does not meet the screening conditions; and candidate experts who fail the preliminary rule judgment will directly output a Boolean value of false and will not enter the secondary judgment stage of triggering rules.

[0021] S3. Based on the configured extraction rule group and the determination process of the pre-defined rules and triggering rules in the extraction rule group, the process uses a preset expert extraction algorithm to extract experts from the candidate expert set who simultaneously meet the pre-defined rules and triggering rules, and outputs the extraction results. This process specifically includes: S3.1 Receive the candidate expert set, the pre-rule set, the trigger rule set, and business information as input; S3.2. Divide the candidate expert set into segments and process them in batches. S3.3 For each expert in each batch of candidate experts, determine in turn whether they meet the prerequisite rules and triggering rules; S3.4 Add the qualified experts to the selected expert set and update the number of selected experts that triggered the rule; S3.5 Output the selected expert set as the extraction result.

[0022] Based on the method described in this embodiment, taking rule configuration at the item level as an example, when an item is launched, the rule group extraction configuration needs to be performed on the configuration page.

[0023] For example, there is a project called "Construction of a Municipal Key Laboratory of Internal Medicine" that needs to be launched. According to policy requirements, rule configuration is performed. First, rule groups are extracted and configured. The configuration information is shown in Table 1.

[0024] Table 1. Configuring extraction rule groups (taking one pre-rule and two trigger rules as an example).

[0025] Then, configure the precondition rules and trigger rules. The configuration information is shown in Tables 2 to 4.

[0026] Table 2 Configuration Rules (requiring a minimum of a bachelor's degree, the employer cannot be the project applicant, and at least 10 years of work experience) or (Taking the title of "Outstanding Expert" as an example)

[0027] Table 3. Rules for configuring the digestive field (taking the requirement of being engaged in the field of digestive diseases and having at least 5 assessment experiences as an example).

[0028] Table 4. Rules for configuring the respiratory field (requiring candidates to have experience in the respiratory disease field and at least 5 assessments). or (Taking a master's degree as an example)

[0029] After the information configuration is completed, all business items in the business system that fall under the category of "construction of a municipal-level key internal medicine laboratory" will have experts selected according to the rules configured for that item. If there are enough qualified doctors in the expert database, 7 people will be selected, of which 2 people will meet the public rules and digestive field rules in the item, and another 5 people will meet the public rules and respiratory field rules in the item.

[0030] Example 2: Refer to Appendix Figure 5 This embodiment proposes a configurable expert extraction system for multi-item review, which is used to implement the method described in Embodiment 1, specifically including: The rule configuration module is used to configure the extraction rule groups, precondition rules, trigger rules, AND rule groups, OR rule groups, and terminal rules for candidate experts based on the extraction scenario requirements. Among them, the extraction rule groups include precondition rules and trigger rules; both precondition rules and trigger rules are composed of AND rule groups and / or OR rule groups; the terminal rules include four attributes: query tag, matching tag, matching relationship, and matching method. The rule determination configuration module is used to configure the determination process for extracting prerequisite rules and triggering rules from the rule group; The rule execution module is used to extract experts from the candidate expert set that simultaneously meet the pre-defined rules and triggering rules based on the configured extraction rule group, the judgment process of the pre-defined rules and triggering rules in the extraction rule group, and the preset expert extraction algorithm, and output the extraction results.

[0031] Example 3: This example also provides a configurable extraction device for multi-item review experts, including: a memory and a processor; The memory stores the instructions executed by the computer. The processor executes computer execution instructions stored in the memory, causing the processor to perform the method described in Embodiment 1.

[0032] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can be a microprocessor or any conventional processor.

[0033] Memory is used to store computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, at least one application program required for a function, etc.; the data storage area can store data created based on the use of the terminal, etc. In addition, memory can also include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart memory cards (SMC), secure digital cards (SD cards), flash memory cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0034] Example 4: This example also provides a computer-readable storage medium storing a plurality of instructions, which are loaded by a processor to cause the processor to execute the method described in Example 1.

[0035] Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the method described in Embodiment 1 is stored, and the computer (or CPU or MPU) of the system or apparatus reads and executes the program code stored in the storage medium.

[0036] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0037] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0038] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0039] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0040] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A configurable extraction method for multi-item review experts, characterized in that, Includes the following steps: S1. Based on the extraction scenario requirements, configure the extraction rule group, pre-extraction rules, triggering rules, "AND rule group", "OR rule group", and terminal rules for candidate experts. Among them: the extraction rule group includes pre-extraction rules and triggering rules; both pre-extraction rules and triggering rules are composed of "AND rule group" and / or "OR rule group"; the terminal rules include four attributes: query tag, matching tag, matching relationship, and matching method. S2. Configure the judgment process for the pre-rules and triggering rules in the extraction rule group; S3. Based on the configured extraction rule group and the judgment process of the pre-rules and triggering rules in the extraction rule group, the experts who simultaneously meet the pre-rules and triggering rules are extracted from the candidate expert set through the preset expert extraction algorithm, and the extraction results are output.

2. The method for configurable extraction of multi-item review experts according to claim 1, characterized in that, In step S1, the extraction rule group refers to the complete set of rules constructed to adapt to the expert label requirements of the specified matter. It is the highest level rule unit, which includes a set of pre-rules and at least one set of triggering rules. The extraction rule group completes the entire process of candidate expert extraction through the coordinated execution of the pre-rules and triggering rules. Pre-selection rules are the admission verification rules for candidate experts to enter the selection process. As a prerequisite for triggering rule matching, they consist of one or more nested combinations of "AND rule group" and "OR rule group". They cannot be set to correspond to the number of people to be selected and are only used as conditional filtering. Triggering rules are core rules used to accurately screen candidates who meet the requirements of the item tags after the candidates have passed the pre-rule verification. They consist of one or more nested combinations of "AND rule group" and "OR rule group". Each triggering rule must set the corresponding number of people to be selected. An "AND rule group" is composed of two or more terminal rules combined by a logical AND relationship. The "AND rule group" will only be matched if all terminal rules in the group meet the matching requirements. An "OR rule group" is composed of two or more end rules combined according to a logical OR relationship. When any one or more end rules in the group meet the matching requirements, the "OR rule group" will be matched successfully. The terminal rule refers to the smallest logical unit of expert tag matching, which cannot be further divided. It defines the specific matching standard of expert tags under a single dimension through four attributes: query tag, matching tag, matching relationship, and matching method.

3. The method for configurable extraction of multi-item review experts according to claim 2, characterized in that, In step S1, the terminal rule includes four attributes: query tag, matching tag, matching relationship, and matching method, wherein: The query tag refers to the target attribute that needs to be filtered. Matching tags refer to the specific values ​​required for filtering; The matching method refers to the association rules between query tags and matching tags, which are used to clarify "how to use matching tags to filter the attributes corresponding to query tags"; Matching relationship refers to the specific sub-type of matching method, and its range of options is determined by the type of query tag; Matching methods include fixed value matching and dynamic matching. Fixed value matching means that the matching tag itself represents the specific value required for filtering, while dynamic matching means that the matching tag only participates in the extraction process as a prompt field.

4. The method for configurable extraction of multi-item review experts according to claim 2, characterized in that, In step S1, based on the extraction scenario requirements, it supports configuring candidate expert extraction rule groups at the event level or business level, enabling flexible configuration of extraction conditions: At the item level, define extraction rule groups and bind each item to a fixed extraction rule group so that all business under that item is extracted by experts based on that extraction rule. Define extraction rule groups at the business level and bind each business to a fixed extraction rule group. This is suitable for scenarios where the business involves multiple extractions in the process or requires third-party system calls.

5. The method for configurable extraction of multi-item review experts according to claim 2, characterized in that, Step S2 specifically includes: S2.1 Receive a set of candidate experts containing different labels as input; S2.2 First, the candidate expert set is filtered and preliminarily judged according to the pre-condition rules, and then the candidate expert set after the preliminary judgment is judged again according to the triggering rules. S2.3 Output a Boolean value to indicate whether each candidate expert meets all the filtering conditions set in the pre-rules and trigger rules; Wherein: a Boolean value of true indicates that the candidate expert meets all the screening conditions, and a Boolean value of false indicates that the candidate expert does not meet the screening conditions; and candidate experts who fail the preliminary rule judgment will directly output a Boolean value of false and will not enter the secondary judgment stage of triggering rules.

6. The method for configurable extraction of multi-item review experts according to claim 1, characterized in that, Step S3 involves using a preset expert extraction algorithm to extract experts from the candidate expert set who simultaneously meet both the preconditions and the triggering rules, and then outputting the extraction results. This process specifically includes: S3.1 Receive the candidate expert set, the pre-rule set, the trigger rule set, and business information as input; S3.

2. Divide the candidate expert set into segments and process them in batches. S3.3 For each expert in each batch of candidate experts, determine in turn whether they meet the prerequisite rules and triggering rules; S3.4 Add the qualified experts to the selected expert set and update the number of selected experts that triggered the rule; S3.5 Output the selected expert set as the extraction result.

7. A configurable expert extraction system for multi-item review, characterized in that, It is used to implement the method as described in any one of claims 1-6, specifically comprising: The rule configuration module is used to configure the extraction rule groups, pre-extraction rules, triggering rules, AND rule groups, OR rule groups, and terminal rules for candidate experts based on the extraction scenario requirements. Among them, the extraction rule groups include pre-extraction rules and triggering rules; both pre-extraction rules and triggering rules are composed of AND rule groups and / or OR rule groups; the terminal rules include four attributes: query tag, matching tag, matching relationship, and matching method. The rule determination configuration module is used to configure the determination process for extracting prerequisite rules and triggering rules from the rule group; The rule execution module is used to extract experts from the candidate expert set that simultaneously meet the pre-defined rules and triggering rules based on the configured extraction rule group, the judgment process of the pre-defined rules and triggering rules in the extraction rule group, and the preset expert extraction algorithm, and output the extraction results.

8. A configurable expert extraction device for multi-item review, characterized in that, include: Memory and at least one processor; The memory contains computer programs; The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by a processor to implement the method as described in any one of claims 1-6.

Images