Rule Engine-Based Data Evaluation Collaboration Method and System

Abstract

The present invention discloses a data evaluation collaboration method and system based on a rule engine, which relates to the technical field of data processing. The method includes: parsing and identifying a first target information group of a first evaluation institution among multiple evaluation institutions to obtain first evaluation data of the first evaluation institution on a target user; reading a predetermined integration strategy and integrating and fusing the first evaluation data according to the predetermined integration strategy to obtain target integrated data; displaying the target integrated data through a front-end user interface of the target user to obtain target effective evaluation data; and analyzing the target effective evaluation data in combination with a backend processing center to generate a target evaluation report. The technical problem in the prior art that the lack of a unified standard for data evaluation leads to low evaluation efficiency and low accuracy of evaluation results is solved. By using the rule engine to achieve unified parsing of multi-party evaluation data, the technical effects of improving evaluation efficiency and accuracy are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a data evaluation collaboration method and system based on a rule engine. Background Art

[0002] With the development of modern data processing technologies, data evaluation plays a key role in many fields. However, most existing evaluation systems rely on customized programming, resulting in high development costs, poor flexibility, and difficulty in adapting to diverse business requirements. In addition, the process of processing evaluation results in traditional systems usually requires manual intervention, which is error-prone and inefficient. When dealing with multi-party evaluation data, these systems lack unified parsing and integration standards, leading to inconsistent evaluation results and affecting the accuracy and efficiency of data evaluation. Summary of the Invention

[0003] This application provides a data evaluation collaboration method and system based on a rule engine, which solves the technical problem in the prior art that the lack of a unified standard for data evaluation leads to low evaluation efficiency and accuracy of evaluation results.

[0004] In view of the above problems, this application provides a data evaluation collaboration method and system based on a rule engine.

[0005] In the first aspect of this application, a data evaluation collaboration method based on a rule engine is provided. The method includes:

[0006] Analyze and identify the first target information group of the first evaluation agency among the multi-party evaluation agencies to obtain the first evaluation data of the first evaluation agency for the target user; read a predetermined integration strategy, and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain target integrated data; display the target integrated data through the front-end user interface of the target user to obtain target valid evaluation data; combine with the back-end processing center to analyze the target valid evaluation data and generate a target evaluation report.

[0007] In the second aspect of this application, a data evaluation collaboration system based on a rule engine is provided. The system includes:

[0008] Parsing and recognition module, which is used to parse and recognize the first target information group of the first evaluation agency in the multi-party evaluation agencies to obtain the first evaluation data of the target user by the first evaluation agency; Fusion module, which is used to read a predetermined integration strategy and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain target integration data; Display module, which is used to display the target integration data through the front-end user interface of the target user to obtain target effective evaluation data; Analysis module, which is used to analyze the target effective evaluation data in combination with the back-end processing center to generate a target evaluation report.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, parse and recognize the first target information group of the first evaluation agency in the multi-party evaluation agencies to obtain the first evaluation data of the target user by the first evaluation agency. Then, read the predetermined integration strategy and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain target integration data. Further, display the target integration data through the front-end user interface of the target user to obtain target effective evaluation data. Finally, analyze the target effective evaluation data in combination with the back-end processing center to generate a target evaluation report. This solves the technical problem in the prior art that the lack of a unified standard for data evaluation leads to low evaluation efficiency and accuracy of evaluation results. By using a rule engine to achieve unified parsing of multi-party evaluation data, the technical effects of improving evaluation efficiency and accuracy are achieved. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0012] Figure 1 Schematic flowchart of the data evaluation collaboration method based on a rule engine provided in an embodiment of this application;

[0013] Figure 2 Schematic structural diagram of the data evaluation collaboration system based on a rule engine provided in an embodiment of this application.

[0014] Description of the reference numerals: Parsing and recognition module 11, Fusion module 12, Display module 13, Analysis module 14. Detailed Embodiments

[0015] By providing a data evaluation collaboration method and system based on a rule engine, this application solves the technical problem in the prior art that the lack of a unified standard for data evaluation leads to low evaluation efficiency and accuracy of evaluation results.

[0016] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in this application without creative efforts belong to the scope of protection of this application.

[0017] It should be noted that the terms "include" and "have" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products, or devices.

[0018] Embodiment 1, as Figure 1 shown, this application provides a data evaluation collaboration method based on a rule engine. The data evaluation collaboration method based on a rule engine is applied to a data evaluation collaboration system based on a rule engine. The data evaluation collaboration system based on a rule engine is associated with multiple evaluation agencies. Among them, the method includes:

[0019] Parse and identify the first target information group of the first evaluation agency among the multiple evaluation agencies to obtain the first evaluation data of the first evaluation agency on the target user.

[0020] The multiple evaluation agencies share information among multiple parties through cloud information sharing technology. Select one evaluation agency from the multiple evaluation agencies as the first evaluation agency, identify and determine the first target information group provided by the first evaluation agency. The first target information group contains various forms of data, such as text information, evaluation forms, index values, etc., covering the preliminary evaluation results of the evaluation agency on the target user. Through in-depth parsing of the first target information group, that is, disassembling and processing the data, converting the data from an unstructured or semi-structured state (such as natural language description, PDF file, etc.) into structured data that the system can recognize; on the basis of parsing, identify the data related to evaluation from the first target information group, including the score, grade, evaluation, feedback, etc. of the target user. After parsing and identification are completed, the data obtained and sorted out from the first evaluation agency becomes the first evaluation data.

[0021] Furthermore, it includes:

[0022] The first target information group includes first text information, first table information, and first picture information; first data is obtained from the first text information; character recognition is performed on the first table information to obtain second data; key points preset for the first picture are recognized to obtain third data; the first data, the second data, and the third data form the first evaluation data.

[0023] Specifically, the first target information group includes first text information, first table information, and first picture information. Among them, the first text information refers to the pure text content from the first evaluation agency, which may include written reports, descriptive texts, or evaluations of target users. The first table information refers to structured table data, usually containing various indicators and numerical values, reflecting the quantitative information collected during the evaluation process, such as scores, measurement results, etc. The first picture information may include images of target users, medical images taken, scanned pictures, etc. For pure text information, useful evaluation data can be extracted through natural language processing (NLP) techniques. For example, from a text describing the health status of a target user, key health-related indicators can be extracted, or certain specific keywords can be classified and scored. The structured data generated from the processed text information is called the first data. The processing of table information can be achieved through OCR (Optical Character Recognition) technology to recognize and extract the text and numerical values in the table. OCR technology can convert the table in picture form into operable digital data. By performing character recognition and data extraction on the information in the table, the second data is generated, and the second data contains the specific numerical values and corresponding explanations of each field in the table. Image recognition processing is performed on the first picture information, and information related to the evaluation can be extracted according to preset key points (such as specific regions, signs, symbols, etc. in the picture). The structured data generated by recognizing the key points in the picture is called the third data. The first data, the second data, and the third data are integrated to form the complete first evaluation data. The first evaluation data combines different types of evaluation information, covering text, table, and image information, providing a rich and comprehensive basis for subsequent data fusion and analysis.

[0024] Read a predetermined integration strategy, and perform integration and fusion on the first evaluation data according to the predetermined integration strategy to obtain target integration data.

[0025] The predetermined integration strategy is a set of rules set when processing data from multiple evaluation agencies, used to guide how to integrate and fuse data from different sources and different types. These strategies may include data cleaning rules, data conversion rules, data matching rules, etc. The integration strategy may be formulated based on multiple factors, including business rules, industry standards, customer requirements, data types and weights of different evaluation agencies, etc.

[0026] Clean the first evaluation data according to the cleaning rules in the predetermined integration strategy, including removing duplicate data, handling missing values, correcting incorrect data, etc.; convert the first evaluation data into a unified format and standard for subsequent data integration; match and associate data from different sources according to the matching rules in the predetermined integration strategy; based on data cleaning, conversion, and matching, fuse the first evaluation data according to the fusion rules in the predetermined integration strategy to obtain the target integrated data.

[0027] Display the target integrated data through the front-end user interface of the target user to obtain the target valid evaluation data.

[0028] The front-end user interface is the main platform for the system to interact with users. Usually, it is a graphical interface through which users can view, input, and operate evaluation data; the target user is usually the user of the evaluation object or the relevant evaluation party, such as an individual being evaluated, a doctor, a rehabilitation therapist, or a manager. Through the front-end interface, the target user can intuitively see the evaluation data and results related to them.

[0029] Specifically, convert the target integrated data into a format that the front-end user interface can recognize and display; filter and sort the target integrated data according to user needs so that users can quickly find key information; use visualization means such as charts and graphs to convert the target integrated data into intuitive and easy-to-understand visual information; load the preprocessed target integrated data into the front-end user interface, and according to the user's operations, confirm and extract the target valid evaluation data, which are the judgments or decisions made by the user based on the target integrated data.

[0030] Furthermore, it includes:

[0031] Obtain the second evaluation data, where the second evaluation data refers to the data obtained by parsing and identifying the second target information group of the second evaluation institution's evaluation of the target user. Among them, the second evaluation institution refers to any institution different from the first evaluation institution among the multiple evaluation institutions; extract the first index in the predetermined evaluation indicators; sequentially match the parameters corresponding to the first index in the first evaluation data and the second evaluation data, denoted as the first index parameter and the second index parameter respectively; according to the user decision-making mechanism in the predetermined integration strategy, obtain the first decision result of the target user for the first index; according to the first decision result, use the first index parameter or the second index parameter as the first integration parameter of the first index; form the target valid evaluation data based on the first integration parameter.

[0032] Select a second evaluation agency different from the first evaluation agency from multiple evaluation agencies; obtain the second target information group generated after the second evaluation agency evaluates the target user; parse and identify the second target information group to obtain the second evaluation data. The predetermined evaluation indicators are a series of parameters or indicators preset by the system during the evaluation process to unify the evaluation criteria; select a specific indicator from the predetermined evaluation indicators as the object to be processed currently, denoted as the first indicator; sequentially search for the specific parameters corresponding to the first indicator in the first evaluation data and the second evaluation data. For example, if the first indicator is the user's heart rate, the values related to the heart rate will be extracted from the first evaluation data and the second evaluation data respectively; the parameters extracted from different evaluation agencies are denoted as the first indicator parameter (from the first evaluation data) and the second indicator parameter (from the second evaluation data).

[0033] In the predetermined integration strategy, there is a decision-making mechanism involving user participation, allowing the target user to make choices or judgments among multiple parameters. For example, if there are differences in the evaluation results of different evaluation agencies, the user can participate in the decision-making to select which result is more credible or applicable. Through the front-end user interface or other interaction methods, obtain the first decision result of the target user for the first indicator. The first decision result refers to the optimal parameter of the first indicator selected by the user through the decision-making mechanism; according to the first decision result of the user, select one from the first indicator parameter or the second indicator parameter as the final first integration parameter. Repeat the above steps for each indicator in the predetermined evaluation indicators to obtain a series of integration parameters; based on these integration parameters, form the target effective evaluation data. The target effective evaluation data contains the integration results of all predetermined evaluation indicators and is an important basis for subsequent decision-making and analysis.

[0034] Furthermore, it also includes:

[0035] Judge whether the first indicator belongs to the predetermined basic feature category; if it belongs, activate the user decision-making mechanism in the predetermined integration strategy, and obtain the first integration parameter of the first indicator according to the user decision-making mechanism; if it does not belong, judge whether the first indicator belongs to the predetermined test feature range; if it belongs, activate the fuzzy decision-making mechanism in the predetermined integration strategy, and take the average of the first indicator parameter and the second indicator parameter as the first integration parameter of the first indicator.

[0036] Specifically, it is determined whether the first indicator belongs to the category of predetermined basic features, which are usually relatively simple, direct, and easy-to-evaluate indicators such as age, gender, etc.; if the first indicator belongs to the category of predetermined basic features, the user decision-making mechanism in the predetermined integration strategy is activated, and the first integration parameter of the first indicator is obtained according to the user decision-making mechanism, that is, the user is allowed to participate in the decision-making and select the most suitable parameter as the final integration parameter. If the first indicator does not belong to the category of predetermined basic features, it is further determined whether it belongs to the range of predetermined test features, which may involve more complex evaluation criteria or require more professional judgment, such as blood pressure, and its result is not unique and can only be used as a range reference; if the first indicator belongs to the range of predetermined test features, the fuzzy decision-making mechanism in the predetermined integration strategy is activated. Fuzzy decision-making allows a certain degree of flexibility to take a compromise value among multiple data instead of strictly selecting a single parameter; under the fuzzy decision-making mechanism, the average value of the first indicator parameter (from the first evaluation data) and the second indicator parameter (from the second evaluation data) is taken as the final first integration parameter.

[0037] Furthermore, it is determined whether the first indicator belongs to the range of predetermined test features. After that, it also includes that if it does not belong, the first indicator parameter and the second indicator parameter are displayed in a predetermined form as the first integration parameter.

[0038] If the first indicator belongs to neither the category of predetermined basic features nor the range of predetermined test features, the first indicator parameter and the second indicator parameter are displayed in a predetermined form (such as a table, chart, text, etc.) as the first integration parameter. This means that in this case, a single integration parameter is not directly calculated, but the parameters provided by the two evaluation agencies are presented to the user simultaneously so that they can make a judgment according to the specific situation.

[0039] Combined with the back-end processing center, the target effective evaluation data is analyzed to generate a target evaluation report.

[0040] The back-end processing center is used to further analyze the target effective evaluation data displayed on the front end, and then extract useful information and patterns from these data to generate a target evaluation report. The target evaluation report is the final output result of the analysis process and is used to display the evaluation result of the target user.

[0041] Furthermore, the back-end processing center includes a Drools rule engine and a template engine. The data evaluation and collaboration method based on the rule engine includes:

[0042] Analyze the target effective evaluation data according to the preset rule library in the Drools rule engine to obtain a target evaluation result; perform templatization processing on the target evaluation result according to the template engine to obtain the target evaluation report.

[0043] The back-end processing center includes a Drools rule engine and a template engine. The Drools rule engine is a rule-based inference engine that can perform logical judgment and reasoning on data according to a predefined rule library. During the data evaluation process, the Drools rule engine is responsible for automatically analyzing the evaluation data and obtaining specific evaluation conclusions. The template engine is used to output the analyzed evaluation results in a preset template format, generating a structured report. The template engine is used to organize the data into a readable evaluation report that conforms to a specific format, facilitating display and understanding.

[0044] The preset rule library in the Drools rule engine is a predefined set of rules. These rules are designed according to business logic or domain-specific evaluation criteria. Each rule specifies how to process data under specific conditions and generates an evaluation result. For example, in health assessment, the rule library may contain the definition of the standard range for indicators such as blood pressure and heart rate. If a user's blood pressure exceeds the standard range, it will be determined as a hypertension risk according to the rule library, and the corresponding evaluation conclusion will be output. During the data evaluation collaboration process, the Drools rule engine automatically analyzes and calculates the target valid evaluation data according to the preset rule library. The working principle of the rule engine is based on a premise-condition-action inference mechanism. For example, if a certain indicator meets a specific condition (such as a value exceeding a certain threshold), the corresponding action will be executed. After the analysis by the rule engine, the target evaluation result is generated, and the target evaluation result directly reflects the current state of the target user.

[0045] The template engine is responsible for formatting the evaluation results output by the Drools rule engine according to the pre-designed template. The template is a standardized evaluation report structure, usually including the display of evaluation indicators (specific values and evaluation conclusions for each evaluation item), summary and suggestions (overall evaluation conclusions generated based on the analysis results, as well as possible improvement suggestions or further action plans), and charts and data visualization (charts generated according to the evaluation results). The evaluation results processed by the template engine generate a complete target evaluation report. The target evaluation report is a structured and standardized document that can clearly present the comprehensive evaluation of the target user.

[0046] The collaborative effect of the Drools rule engine and the template engine in the back-end processing center enables the system to efficiently and automatically analyze the evaluation data and display the analysis results in a structured form. In this way, the system can not only provide accurate evaluation results but also generate an evaluation report that is easy to understand, providing intuitive decision support for users and relevant personnel.

[0047] Furthermore, the back-end processing center further includes a database, where the database is used to archive and back up the target effective evaluation data.

[0048] The back-end processing center also includes a database, which is responsible for archiving and backing up the target effective evaluation data. Archiving means saving the evaluation data into the database to ensure that these data can be stored for a long time and maintain integrity. Backing up is to prevent data loss or damage by copying and storing the evaluation data in a safe location. The target effective evaluation data is the result of being collected through the front-end interface and analyzed by the Drools rule engine. After the evaluation process ends, these data still have important reference value, so they need to be stored and backed up for subsequent queries.

[0049] In summary, the embodiments of the present application have at least the following technical effects:

[0050] First, parse and identify the first target information group of the first evaluation agency among multiple evaluation agencies to obtain the first evaluation data of the first evaluation agency for the target user. Then, read the predetermined integration strategy and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain the target integration data. Further, display the target integration data through the front-end user interface of the target user to obtain the target effective evaluation data. Finally, analyze the target effective evaluation data in combination with the back-end processing center to generate the target evaluation report. It solves the technical problem in the prior art that the lack of a unified standard for data evaluation leads to low evaluation efficiency and accuracy of evaluation results. By using the rule engine to achieve unified parsing of multi-party evaluation data, the technical effects of improving evaluation efficiency and accuracy are achieved.

[0051] Embodiment 2, based on the same inventive concept as the data evaluation collaboration method based on the rule engine in the foregoing embodiment, as Figure 2 shown, the present application provides a data evaluation collaboration system based on the rule engine, where the system includes:

[0052] A parsing and identifying module 11, which is used to parse and identify the first target information group of the first evaluation agency among multiple evaluation agencies to obtain the first evaluation data of the first evaluation agency for the target user; a fusion module 12, which is used to read the predetermined integration strategy and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain the target integration data; a display module 13, which is used to display the target integration data through the front-end user interface of the target user to obtain the target effective evaluation data; an analysis module 14, which is used to analyze the target effective evaluation data in combination with the back-end processing center to generate the target evaluation report.

[0053] Further, the parsing and recognition module 11 is used to execute the following method:

[0054] The first target information group includes first text information, first table information, and first picture information; obtaining first data according to the first text information; performing character recognition on the first table information to obtain second data; recognizing preset key points of the first picture to obtain third data; the first data, the second data, and the third data form the first evaluation data.

[0055] Further, the display module 13 is used to execute the following method:

[0056] Obtain second evaluation data, where the second evaluation data refers to data obtained by parsing and recognizing a second target information group for evaluating the target user by a second evaluation institution, and the second evaluation institution refers to any institution different from the first evaluation institution among the multiple evaluation institutions; extract a first index from the predetermined evaluation indexes; sequentially match parameters corresponding to the first index in the first evaluation data and the second evaluation data, and denote them as a first index parameter and a second index parameter respectively; according to the user decision-making mechanism in the predetermined integration strategy, obtain a first decision result of the target user for the first index; according to the first decision result, use the first index parameter or the second index parameter as the first integration parameter of the first index; based on the first integration parameter, form the target effective evaluation data.

[0057] Further, the display module 13 is used to execute the following method:

[0058] Judge whether the first index belongs to the predetermined basic feature category; if it belongs, activate the user decision-making mechanism in the predetermined integration strategy, and obtain the first integration parameter of the first index according to the user decision-making mechanism; if it does not belong, judge whether the first index belongs to the predetermined test feature range; if it belongs, activate the fuzzy decision-making mechanism in the predetermined integration strategy, and take the average of the first index parameter and the second index parameter as the first integration parameter of the first index.

[0059] Further, the display module 13 is used to execute the following method:

[0060] If it does not belong, display the first index parameter and the second index parameter in a predetermined form as the first integration parameter.

[0061] Further, the analysis module 14 is used to execute the following method:

[0062] The backend processing center includes a Drools rule engine and a template engine; the target valid evaluation data is analyzed according to a preset rule library in the Drools rule engine to obtain a target evaluation result; the target evaluation result is subjected to templating processing according to the template engine to obtain the target evaluation report.

[0063] Further, the analysis module 14 is configured to execute the following method:

[0064] The backend processing center further includes a database, wherein the database is used to archive and back up the target valid evaluation data.

[0065] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above specific embodiments of the present specification have been described. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0067] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A data evaluation collaborative method based on a rule engine, characterized in that: The data evaluation collaboration method based on the rule engine is applied to a data evaluation collaboration system based on the rule engine. The data evaluation collaboration system based on the rule engine is associated with multiple evaluation agencies. The data evaluation collaboration method based on the rule engine includes: Parsing and identifying a first target information group of a first evaluation agency among the multiple evaluation agencies to obtain first evaluation data of the first evaluation agency on the target user; Reading a predetermined integration strategy, and integrating and fusing the first evaluation data according to the predetermined integration strategy to obtain target integrated data; The target integrated data is displayed through the front-end user interface of the target user to obtain target effective evaluation data; Analyze the target effective evaluation data in conjunction with the back-end processing center to generate a target evaluation report; Acquire second evaluation data, where the second evaluation data refers to data obtained by parsing and identifying a second target information group for evaluating the target user by a second evaluation agency, wherein the second evaluation agency refers to any one of the multiple evaluation agencies that is different from the first evaluation agency; Extracting a first indicator among predetermined evaluation indicators; Matching parameters corresponding to the first indicator in the first evaluation data and the second evaluation data in sequence, recording them as first indicator parameters and second indicator parameters respectively; Determining whether the first indicator belongs to the predetermined basic feature category; If yes, activating the user decision mechanism in the predetermined integration strategy, and obtaining the first integration parameter of the first indicator according to the user decision mechanism; If not, determining whether the first indicator belongs to a predetermined test feature range; If yes, activate the fuzzy decision mechanism in the predetermined integration strategy, and take the average of the first indicator parameter and the second indicator parameter as the first integration parameter of the first indicator according to the fuzzy decision mechanism; wherein determining whether the first indicator belongs to a predetermined test feature range, and then further comprising, if not, displaying the first indicator parameter and the second indicator parameter in a predetermined form as the first integrated parameter; Build the target effective evaluation data based on the first integrated parameter; The backend processing center includes a Drools rule engine and a template engine, and the rule engine-based data evaluation collaborative method includes: Analyze the target effective evaluation data according to the preset rule base in the Drools rule engine to obtain a target evaluation result; The target assessment result is templated according to the template engine to obtain the target assessment report.

2. The data evaluation collaborative method based on rule engine according to claim 1 is characterized in that: include: The first target information group includes first text information, first table information and first picture information; Obtaining first data according to the first text information; Performing text recognition on the first table information to obtain second data; Identify preset key points of the first image to obtain third data; The first data, the second data and the third data constitute the first evaluation data.

3. The data evaluation collaborative method based on rule engine according to claim 1 is characterized in that: The back-end processing center also includes a database, wherein the database is used to archive and back up the target effective evaluation data.

4. Data evaluation collaborative system based on rule engine, characterized by: The system for implementing the rule engine-based data evaluation collaborative method according to any one of claims 1 to 3 comprises: A parsing and identifying module, the parsing and identifying module is used to parse and identify a first target information group of a first evaluation agency among the multiple evaluation agencies, and obtain first evaluation data of the first evaluation agency on the target user; A fusion module, the fusion module is used to read a predetermined integration strategy, and integrate and fuse the first evaluation data according to the predetermined integration strategy to obtain target integrated data; A display module, the display module is used to display the target integrated data through the front-end user interface of the target user to obtain target effective evaluation data; The analysis module is used to analyze the target effective evaluation data in conjunction with the back-end processing center to generate a target evaluation report.

Images