Quality evaluation model construction method based on graph theory characteristics

Abstract

The invention discloses a quality evaluation model construction method based on graph theory features, and the method comprises the steps: constructing a multi-evaluation object quality evaluation model data set, and obtaining a directed graph representing evaluation objects; constructing a second-layer quality evaluation model; carrying out measurement evaluation on object attributes representing in-degree nodes; constructing a quality model of a first-layer quality evaluation model, and obtaining an evaluation result of the first-layer model; carrying out the comprehensive quality evaluation of the evaluation object, and forming a topological graph representing the field quality evaluation; and performing loop execution to form a global quality evaluation topological graph of all the evaluation objects in the quality evaluation model representation field. According to the method, better quality evaluation generalization ability can be provided, and the evaluation accuracy and conformity can be more effectively improved compared with an existing quality evaluation model; by establishing a feature association rule with an external object, the quality evaluation model and the external object have a specific representation relationship in the aspect of application, and the application ductility of the evaluation quality model is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data modeling quality assessment models, and in particular to a method for constructing a quality assessment model based on graph theory features. Background Art

[0002] The current general quality assessment model is based on standardized measurement data, and provides more objective measurement and assessment capabilities in a fixed measurement mode through a determined quality model, specified quality (traditional assessment algorithm and indicator weight algorithm), etc.

[0003] This quality assessment model has the defects of high data dependence, dynamic configurability of quality model mode, and fixed measurement process, which leads to high quality assessment complexity, poor flexibility of measurement process, and high difficulty in domain customization. The simple data application model oriented towards evaluation results limits the diversity of quality assessment model applications.

[0004] In terms of the field, higher requirements are placed on the complexity of quality assessment objectives and the diversity of applications. The current general quality assessment model cannot meet the field application requirements in terms of its internal element composition and measurement process.

[0005] Therefore, it is necessary to provide a flexible and polymorphic quality model through configurable quality models and multi-quality model combinations based on the traditional standardized definitions and specifications of the current quality assessment model, and to improve the measurement process by introducing advanced technologies and algorithms such as data, machine learning, AHP, etc. to meet the requirements of real-time assessment and complex decision-making capabilities of the quality assessment model. At the same time, the relationship between the quality assessment model and the representation of external objects should be established according to the characteristic rules, so as to achieve the representation of quality assessment and evaluation results with the help of the rich expression capabilities of external objects (such as topological maps and reports) and realize field applications. Summary of the invention

[0006] In view of the above problems, in order to meet the future application development requirements of quality assessment models, the purpose of the present invention is to provide a method for constructing a quality assessment model based on graph theory features. The specific scheme includes:

[0007] A method for constructing a quality assessment model based on graph theory features, comprising the steps of:

[0008] S1, construct a data set of a quality assessment model for multiple assessment objects and obtain a directed graph representing the assessment objects;

[0009] S2, constructs the second-level quality assessment model that characterizes the object attributes of the in-degree nodes of the directed graph;

[0010] S3, determining the quality assessment procedure of the second-layer quality assessment model, performing metric assessment on the object attributes representing the in-degree nodes, and obtaining the second-layer model assessment result;

[0011] S4, constructing a quality model of the first-level quality assessment model that represents the in-degree nodes of the directed graph, performing metric assessment on the in-degree nodes, and obtaining the first-level model assessment result;

[0012] S5, performing a comprehensive quality assessment of the assessment object based on the second-layer model assessment results and the first-layer model assessment results, obtaining the assessment results, using the multi-assessment object quality assessment model to characterize the data and the assessment results to set the attribute values ​​of various nodes in the directed graph, and forming a topological graph representing the quality assessment of the domain;

[0013] S6, for the quality assessment model representation information of multiple assessment objects, steps S1 to S5 are executed cyclically to form a global quality assessment topology map of all assessment objects in the quality assessment model representation field.

[0014] Furthermore, the step S1 comprises:

[0015] S11, the first-level quality assessment model representation data information includes: the assessment object, the assessed object, and the assessment weights between the assessment object and each assessed object;

[0016] The second-level quality assessment model represents data information including: assessment indicators, assessment weight algorithms, assessment algorithms and measurement data associated with each assessed object;

[0017] S12, constructing a directed graph representing the first-layer quality assessment model, including: in-degree nodes representing the assessment object entity and attributes of the first-layer quality assessment model; each out-degree node representing the assessed object entity and attributes; and weighted directed edges representing the weight between the assessment object and the assessed object; wherein the assessed object attributes include the second-layer quality assessment model object;

[0018] Furthermore, the step S2 comprises:

[0019] Determine the quality measurement relationship of the second-level quality assessment model, and construct the quality model of the second-level quality assessment model according to the quality measurement relationship requirements. The second-level quality assessment model measures the quality of the assessed object based on the weight algorithm and the assessment algorithm to obtain the assessment results.

[0020] Furthermore, the step S3 comprises:

[0021] S31, according to the quality assessment procedure, select a quality model of the second-layer quality assessment model, calculate the quality measure of the quality model, set a weight algorithm and an assessment algorithm, perform a quality metric assessment on the second-layer quality assessment model according to the quality assessment procedure requirements, and obtain a quality assessment result;

[0022] S32, setting the measurement result of the second-layer quality assessment model as the attribute value of the in-degree node object.

[0023] Furthermore, the step S4 comprises:

[0024] S41, organizing the first-layer quality assessment model representation information according to the directed graph to construct a quality model of the first-layer quality assessment model;

[0025] S42, measuring the first-layer quality assessment model according to the quality assessment procedure to obtain the first-layer model assessment result;

[0026] S43, performing evaluation according to the evaluation criteria and the first-layer model evaluation results and the second-layer model evaluation results to determine the evaluation results of the quality evaluation model.

[0027] Furthermore, the step S5 comprises:

[0028] The first-level quality assessment model representation information is used to completely set the directed graph attribute values, forming a quality assessment topology graph between the domain assessment object and each assessed object.

[0029] Furthermore, the step S6 comprises:

[0030] S61, obtaining data information of all multi-assessment object quality assessment models;

[0031] S62, for all the multi-assessment object quality assessment model representation information, loop through steps S1 to S5 to form a global domain quality assessment topology map represented by all the multi-assessment object quality assessment model representations.

[0032] The present invention also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor reads and executes the computer program from the storage medium to execute any of the methods described above.

[0033] The present invention also discloses a non-transitory computer-readable storage medium, on which a computer program is stored. After the computer program is run, any of the methods described above is executed.

[0034] Beneficial effects of the present invention:

[0035] The present invention integrates advanced technologies and theoretical methods into the constituent elements of existing quality assessment models, so that the domain quality assessment model has internal characteristics such as flexible definition of quality models, rich weights and assessment algorithms, and diverse assessment modes, which can provide better quality assessment generalization capabilities and can more effectively improve assessment accuracy and compliance than existing quality assessment models; by establishing feature association rules with external things, the quality assessment model and external things have a specific representation relationship in application, thereby improving the application scalability of the assessment quality model. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A flow chart of a method for constructing a quality assessment model based on graph theory features of the present invention;

[0037] Figure 2 A data structure diagram representing the multi-layer quality assessment model of the present invention;

[0038] Figure 3 A directed graph representing the first-level quality assessment model of the present invention;

[0039] Figure 4 is a quality measurement relationship diagram of the quality assessment model of the present invention;

[0040] Figure 5 is a quality model diagram of the second-level quality assessment model of the present invention;

[0041] Figure 6 is a flow chart of the quality assessment procedure of the present invention;

[0042] Figure 7 A quality model diagram of the first-level quality assessment model of the present invention;

[0043] Figure 8 A mapping relationship diagram of the first-layer quality assessment model of the directed graph of the present invention representing information;

[0044] Fig. 9 It is a schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0045] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar symbols throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0046] In terms of the field, higher requirements are placed on the complexity of quality assessment objectives and the diversity of applications. The current general quality assessment model cannot meet the field application requirements in terms of its internal element composition and measurement process.

[0047] In view of the above problems, the present invention provides a method for constructing a quality assessment model based on graph theory features. Figure 1 A flow chart of a method for constructing a quality assessment model based on graph theory features provided by an embodiment of the present invention, the method comprising:

[0048] Firstly, a data set of a quality assessment model with multiple assessment objects is constructed to obtain a directed graph representing the assessment objects;

[0049] In order to verify the feasibility and effectiveness of the method for constructing a domain quality assessment model based on graph theory features and to demonstrate the assessment effect and extension representation, N (N≤3) multi-layer assessment models can be used. In an embodiment of the present invention, a two-layer quality assessment model is used to characterize simulation data information, and simulation domain indicator system data is used.

[0050] The first-level domain quality assessment model information is used to construct and characterize a directed graph; the second-level domain quality assessment model is designed for the attribute objects representing each in-degree node of the directed graph.

[0051] The first-level quality assessment model represents data information, such as Figure 2 Shown are: the evaluation object, the evaluated object, and the evaluation weights between the evaluation object and each evaluated object.

[0052] The second-level quality assessment model represents data information including: assessment indicators associated with each assessed object, assessment weight algorithm, assessment algorithm and measurement data.

[0053] like Figure 3 As shown, a directed graph representing the first-level quality assessment model is constructed, including: the in-degree nodes are represented as the assessment object entities and attributes of the first-level quality assessment model; each out-degree node is represented as the assessed object entity and attribute, and the weighted directed edge is represented as the weight between the assessment object and the assessed object; wherein the assessed object attribute includes the second-level quality assessment model object.

[0054] Then, a second-level quality assessment model is constructed to characterize the object attributes of the in-degree nodes of the directed graph. Figure 4 As shown, the quality measurement relationship of the second-layer quality assessment model is determined, and the quality model of the second-layer quality assessment model is constructed according to the quality measurement relationship requirements. The second-layer quality assessment model measures the quality of the assessed object based on the weight algorithm and the assessment algorithm to obtain the assessment result.

[0055] The second-level quality assessment model outlines quality characteristics, which can be evaluated using quality measures defined by applying measurement functions to quality measure elements, each of which is generated by related target entities.

[0056] According to the requirements of quality measurement relationship, the following is constructed based on the field evaluation indicator system: Figure 5 The quality model of the second-level quality assessment model shown includes n quality characteristics, each of which can be decomposed into multiple sub-characteristics. The quality measures for establishing the quality model are shown in Table 1.

[0057] Table 1 Quality measurement table of quality model

[0058]

[0059] Then, the quality assessment procedure of the second-layer quality assessment model is determined, and the object attributes representing the in-degree nodes are measured and evaluated to obtain the second-layer model assessment result.

[0060] According to Figure 6 The quality assessment procedure flow shown requires that the second-layer quality assessment model be measured to obtain the assessment result. According to the quality assessment procedure, the quality model of the second-layer quality assessment model is selected, the quality measure of the quality model is calculated, the weight algorithm and the assessment algorithm are set, and the quality metric assessment of the second-layer quality assessment model is performed according to the quality assessment procedure requirements to obtain the quality assessment result; the measurement result of the second-layer quality assessment model is set as the attribute value of the in-degree node object.

[0061] The detailed measurement process includes: Figure 5 The quality model of the second-level evaluation model shown in FIG. 1 calculates the quality measures of the quality characteristics in the quality model shown in Table 1 according to the measurement collection data, and obtains a quality measure set, which is one of the input data of the quality model measurement.

[0062] Select a weight calculation algorithm or a combination of multiple weight calculation algorithms as shown in Table 2 to calculate and obtain the weight information of the quality model and quality measurement, including two weight calculation methods: the quality model and quality measurement as a whole adopt the same weight calculation method, and the quality characteristics and quality measurements of each layer of the quality model adopt specified weight calculation methods respectively.

[0063] Table 2 Calculation methods or methods in the quality model area

[0064]

[0065] The quality model is measured using the evaluation algorithm shown in Table 3: the evaluation results of the upper-layer quality characteristics are obtained by calculating the evaluation results of the lower-layer sub-characteristic set associated with the upper-layer quality characteristics, and a normalized calculation method is used until the final measurement result of the quality model is obtained.

[0066] Table 3 Evaluation algorithm function details

[0067]

[0068] There are two evaluation algorithm measurement methods: the overall quality model is measured by the same quality evaluation algorithm, and different upper-level quality characteristics in the quality model are measured by specifying different lower-level sub-characteristic evaluation algorithms.

[0069] The overall quality model adopts the same quality assessment algorithm measurement method scenario example: The two-layer quality model and its quality measurement adopt the weighted sum assessment algorithm for measurement as a whole. The process is as follows:

[0070] The metric elements of the quality measure are weighted and summed to calculate the metric value of the quality sub-characteristic of the quality model. The calculation formula is shown in formula (1).

[0071]

[0072] In the formula:

[0073] V ijk —Measurement value of quality measurement element (the measurement value is obtained by calculating the measurement collection data corresponding to the quality measurement element according to the measurement function);

[0074] W ijk —The weight corresponding to the quality measurement element;

[0075] i—quality model quality characteristic identifier, value = 1, 2, n;

[0076] j—quality model sub-characteristic identifier, value = 1, 2, 3..., n;

[0077] k—quality measurement element identifier, value = 1, 2, 3..., n;

[0078] The weighted sum of the quality model sub-characteristics is performed to calculate the measurement value of the sub-characteristic. The calculation formula is shown in formula (2).

[0079]

[0080] In the formula:

[0081] V ij — metrics of quality model sub-characteristics;

[0082] W ij —weights corresponding to the quality model sub-characteristics;

[0083] i—quality model characteristic identifier, value = 1, 2, 3, n;

[0084] j—Quality model sub-characteristic identifier, value = 1, 2, 3..., n.

[0085] The quality characteristics of the quality model are weighted and summed to calculate the measurement value of the quality characteristics. The calculation formula is shown in formula (3).

[0086]

[0087] In the formula:

[0088] V i — metrics of quality characteristics of the quality model;

[0089] W i —weights corresponding to the quality characteristics of the quality model;

[0090] i—quality characteristic identifier of quality model, value = 1, 2, n;

[0091] V—The final evaluation value of the quality assessment model.

[0092] The overall quality model adopts the same quality assessment algorithm measurement method scenario example: The two-layer quality model and its quality measurement adopt the weighted sum assessment algorithm for measurement as a whole. The process is as follows:

[0093] Different upper-layer quality characteristics in the quality model specify different lower-layer sub-characteristic evaluation algorithms for measurement. Example scenario: In the two-layer quality model and its quality measurement, the sub-characteristics and quality measurement are measured using the same evaluation algorithm (weighted sum evaluation algorithm), and the quality characteristics are measured using the weighted product evaluation algorithm. The measurement process of the quality measurement and the quality model sub-characteristics is the same as the first measurement method. The measurement process of the quality characteristics of the quality model is as follows:

[0094] The quality characteristics of the quality model are weighted and integrated to calculate the measurement value of the quality characteristics. The calculation formula is shown in formula (3).

[0095]

[0096] In the formula:

[0097] V i — metrics of quality characteristics of the quality model;

[0098] W i —weights corresponding to the quality characteristics of the quality model;

[0099] i—quality characteristic identifier of quality model, value = 1, 2, n;

[0100] V—The final evaluation value of the quality assessment model.

[0101] The measurement results of the second-layer quality assessment model are set as the attribute values ​​of the in-degree node object.

[0102] S4, constructing a quality model of the first-level quality assessment model that represents the in-degree nodes of the directed graph, performing metric assessment on the in-degree nodes, and obtaining the first-level model assessment result.

[0103] According to the directed graph, the first-layer quality assessment model representation information is organized to construct the quality model of the first-layer quality assessment model; the first-layer quality assessment model is measured according to the quality assessment procedure to obtain the first-layer model evaluation result; according to the evaluation criteria, the evaluation is performed according to the first-layer model evaluation result and the second-layer model evaluation result to determine the evaluation result of the quality assessment model, specifically:

[0104] According to directed graph theory, by establishing Figure 8 The first-level quality assessment model of the directed graph shown in the figure represents the mapping relationship of information, and constructs Figure 7 The quality model shown in the figure. The quality model construction process is as follows: the quality model is constructed with the out-degree node evaluation object of the directed graph, and the set of evaluated objects of each in-degree node constitutes the quality characteristics of the quality model. The quality model of the first-level quality evaluation model is dynamic and configurable.

[0105] According to Figure 6 The quality assessment procedure shown measures the first-level quality assessment model and obtains the assessment results. The detailed measurement process is as follows:

[0106] Select as Figure 7 The quality model of the first-level evaluation model shown uses the evaluation results of the evaluated objects of each in-degree node in the directed graph as the measurement collection data of the first-level quality evaluation model;

[0107] According to directed graph theory, the weight of the directed edge is set as the weight of the quality characteristic of the quality model according to the relationship between the directed edge and the in-degree node;

[0108] An example of measuring a quality model using the evaluation algorithm shown in Table 3 is as follows: a weighted sum evaluation algorithm is used to perform weighted summation on the quality characteristics of the quality model to calculate the measurement value of the quality characteristics. The calculation formula is shown in formula (3).

[0109]

[0110] In the formula:

[0111] V i — the measurement values ​​of the quality characteristics of the quality model (the evaluation results of the evaluated object);

[0112] W i —weights corresponding to the quality characteristics of the quality model;

[0113] i—quality characteristic identifier of quality model, value = 1, 2, n;

[0114] V—The final evaluation value of the quality assessment model.

[0115] According to the evaluation criteria example shown in Table 4, the evaluation is performed according to the final evaluation value of the quality assessment model to determine the evaluation level of the first-level quality assessment model.

[0116] Table 4 Examples of evaluation criteria

[0117]

[0118] S5, conduct a comprehensive quality assessment of the assessment object based on the second-layer model assessment results and the first-layer model assessment results, obtain the assessment results, use the multi-assessment object quality assessment model to characterize the data and the assessment results to set the attribute values ​​of various nodes in the directed graph, and form a topological graph that characterizes the quality assessment of the domain.

[0119] The first-level quality assessment model characterization information is used to completely set the attribute values ​​of the directed graph, including: setting the evaluation object, evaluation result, and evaluation result of the out-degree node, setting the evaluated object, evaluation result, and weight of each in-degree node, and forming a quality assessment topology graph between the domain evaluation object and each evaluated object: G i (V i <v i出度 ,(v i1入度 ,v i2入度 ,...,v im入度 )>, E i ).

[0120] S6, for the quality assessment model representation information of multiple assessment objects, steps S1 to S5 are executed cyclically to form a global quality assessment topology map of all assessment objects in the quality assessment model representation field.

[0121] Obtain all the data information of the quality assessment model of multiple assessment objects, and form a global domain quality assessment topology G = (G1, G2, ..., G n ).

[0122] The present invention also provides an electronic device, Fig. 9 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Fig. 9 As shown, the electronic device may include: a processor, a communications interface, a memory, and a communications bus, wherein the processor, the communications interface, and the memory communicate with each other via the communications bus. The processor may call the logic instructions in the memory to execute the following method:

[0123] S1, construct a data set of a quality assessment model for multiple assessment objects and obtain a directed graph representing the assessment objects;

[0124] S2, constructs the second-level quality assessment model that characterizes the object attributes of the in-degree nodes of the directed graph;

[0125] S3, determining the quality assessment procedure of the second-layer quality assessment model, performing metric assessment on the object attributes representing the in-degree nodes, and obtaining the second-layer model assessment result;

[0126] S4, constructing a quality model of the first-level quality assessment model that represents the in-degree nodes of the directed graph, performing metric assessment on the in-degree nodes, and obtaining the first-level model assessment result;

[0127] S5, performing a comprehensive quality assessment of the assessment object based on the second-layer model assessment results and the first-layer model assessment results, obtaining the assessment results, using the multi-assessment object quality assessment model to characterize the data and the assessment results to set the attribute values ​​of various nodes in the directed graph, and forming a topological graph representing the quality assessment of the domain;

[0128] S6, for the quality assessment model representation information of multiple assessment objects, steps S1 to S5 are executed cyclically to form a global quality assessment topology map of all assessment objects in the quality assessment model representation field.

[0129] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0130] An embodiment of the present invention further provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method provided in each of the above embodiments is implemented, for example, including:

[0131] S1, construct a data set of a quality assessment model for multiple assessment objects and obtain a directed graph representing the assessment objects;

[0132] S2, constructs the second-level quality assessment model that characterizes the object attributes of the in-degree nodes of the directed graph;

[0133] S3, determining the quality assessment procedure of the second-layer quality assessment model, performing metric assessment on the object attributes representing the in-degree nodes, and obtaining the second-layer model assessment result;

[0134] S4, constructing a quality model of the first-level quality assessment model that represents the in-degree nodes of the directed graph, performing metric assessment on the in-degree nodes, and obtaining the first-level model assessment result;

[0135] S5, performing a comprehensive quality assessment of the assessment object based on the second-layer model assessment results and the first-layer model assessment results, obtaining the assessment results, using the multi-assessment object quality assessment model to characterize the data and the assessment results to set the attribute values ​​of various nodes in the directed graph, and forming a topological graph representing the quality assessment of the domain;

[0136] S6, for the quality assessment model representation information of multiple assessment objects, steps S1 to S5 are executed cyclically to form a global quality assessment topology map of all assessment objects in the quality assessment model representation field.

[0137] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0139] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for constructing a quality assessment model based on graph theory features, characterized in that: include: S1, construct a data set of a quality assessment model for multiple assessment objects and obtain a directed graph representing the assessment objects; S2, constructs the second-level quality assessment model that characterizes the object attributes of the in-degree nodes of the directed graph; S3, determining the quality assessment procedure of the second-layer quality assessment model, performing metric assessment on the object attributes representing the in-degree nodes, and obtaining the second-layer model assessment result; S4, constructing a quality model of the first-level quality assessment model that represents the in-degree nodes of the directed graph, performing metric assessment on the in-degree nodes, and obtaining the first-level model assessment result; S5, performing a comprehensive quality assessment of the assessment object based on the second-layer model assessment results and the first-layer model assessment results, obtaining the assessment results, using the multi-assessment object quality assessment model to characterize the data and the assessment results to set the attribute values ​​of various nodes in the directed graph, and forming a topological graph representing the quality assessment of the domain; S6, for the quality assessment model representation information of multiple assessment objects, steps S1 to S5 are executed cyclically to form a global quality assessment topology map of all assessment objects in the quality assessment model representation field.

2. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S1 comprises: S11, the first-level quality assessment model representation data information includes: the assessment object, the assessed object, and the assessment weights between the assessment object and each assessed object; The second-level quality assessment model represents data information including: assessment indicators, assessment weight algorithms, assessment algorithms and measurement data associated with each assessed object; S12, constructing a directed graph representing the first-layer quality assessment model, including: in-degree nodes representing the assessment object entity and attributes of the first-layer quality assessment model; each out-degree node representing the assessed object entity and attributes; and weighted directed edges representing the weight between the assessment object and the assessed object; wherein the assessed object attributes include the second-layer quality assessment model object.

3. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S2 comprises: Determine the quality measurement relationship of the second-level quality assessment model, and construct the quality model of the second-level quality assessment model according to the quality measurement relationship requirements. The second-level quality assessment model measures the quality of the assessed object based on the weight algorithm and the assessment algorithm to obtain the assessment results.

4. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S3 comprises: S31, according to the quality assessment procedure, select a quality model of the second-layer quality assessment model, calculate the quality measure of the quality model, set a weight algorithm and an assessment algorithm, perform a quality metric assessment on the second-layer quality assessment model according to the quality assessment procedure requirements, and obtain a quality assessment result; S32, setting the measurement result of the second-layer quality assessment model as the attribute value of the in-degree node object.

5. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S4 comprises: S41, organizing the first-layer quality assessment model representation information according to the directed graph to construct a quality model of the first-layer quality assessment model; S42, measuring the first-layer quality assessment model according to the quality assessment procedure to obtain the first-layer model assessment result; S43, performing evaluation according to the evaluation criteria and the first-layer model evaluation results and the second-layer model evaluation results to determine the evaluation results of the quality evaluation model.

6. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S5 comprises: The first-level quality assessment model representation information is used to completely set the directed graph attribute values, forming a quality assessment topology graph between the domain assessment object and each assessed object.

7. The method for constructing a quality assessment model based on graph theory features according to claim 1, characterized in that: The step S6 comprises: S61, obtaining data information of all multi-assessment object quality assessment models; S62, for all the multi-assessment object quality assessment model representation information, loop through steps S1 to S5 to form a global domain quality assessment topology map represented by all the multi-assessment object quality assessment model representations.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of a method for constructing a quality assessment model based on graph theory features as described in any one of claims 1 to 7 are implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a method for constructing a quality assessment model based on graph theory features as described in any one of claims 1 to 7 are implemented.

Images