A trustworthy evaluation method and system for network knowledge in the transportation field

Abstract

The present invention discloses a trustworthy assessment method and system for transportation network knowledge, comprising the following steps: acquiring transportation network knowledge; classifying the transportation network knowledge according to its source; acquiring data information influencing the trustworthiness of each type of network knowledge; performing a trustworthiness assessment on each type of network knowledge based on the data information to obtain a trustworthiness characteristic value for each type of network knowledge; obtaining a total trustworthiness value for the transportation network knowledge based on the trustworthiness characteristic value for each type of network knowledge; and determining the trustworthiness level of the transportation network knowledge based on the total trustworthiness value. This method improves the accuracy of trustworthiness assessment of network knowledge.

Description

Technical Field

[0001] The present invention relates to the technical field of network knowledge credibility evaluation, and in particular to a method and system for credibility evaluation of network knowledge in the transportation field. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Online knowledge describes traffic facts through multimedia formats such as text, images, audio, and video. Due to its ease of sharing, dissemination, and relative freedom of expression, the credibility of existing online knowledge is inevitably lacking. This makes it difficult for users of online knowledge in the urban transportation sector to filter out credible knowledge, potentially causing harm to users. The urban transportation sector encompasses diverse application scenarios with significantly different requirements for knowledge credibility, such as legislative bodies' access to legal and regulatory knowledge, the general public's acquisition of basic traffic safety tips, drivers' demand for driving practices and safety experience, and experts' demand for safety information. To provide credible knowledge services that meet diverse needs in the urban transportation sector, knowledge credibility assessment has become a key issue that needs to be addressed. Currently, research on knowledge credibility is still in its infancy, both domestically and internationally. There are no models for online knowledge credibility attributes, methods for evaluating online knowledge credibility, or standards or specifications for grading online knowledge credibility assessment. In the existing technology, some use the hierarchical analysis method to determine the weight of the trust attribute of network information, and conduct trust evaluation of network information or data through questionnaires. Some use representation learning to represent knowledge as low-dimensional vectors, and detect noise in knowledge graphs by the distance between vectors. There are also some other methods to quantify the credibility of knowledge graphs in urban fields. These methods can perform trust evaluation on network information and network data, and can also denoise knowledge graphs. However, a relatively scientific evaluation method and system for the credibility of network knowledge has not been formed. At the same time, when evaluating network knowledge, the existing methods do not consider the impact of the knowledge source on the trust evaluation of network knowledge, resulting in a low accuracy rate for the trust evaluation of network knowledge. Summary of the Invention

[0004] In order to solve the above problems, the present invention proposes a method and system for trustworthy assessment of network knowledge in the transportation field. Network knowledge is classified according to its source, and a trustworthy assessment is performed on each type of network knowledge. On this basis, the total trustworthy value of the network knowledge is obtained. When the total trustworthy value is used to perform trustworthy assessment on network knowledge, the accuracy of the trustworthy assessment is improved.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] First, a trustworthy evaluation method for network knowledge in the transportation field is proposed, including:

[0007] Acquire network knowledge in the transportation field;

[0008] Classify network knowledge in the transportation field according to its sources;

[0009] Obtain data information that affects the trustworthiness of each type of network knowledge;

[0010] Conduct a credibility assessment on each type of network knowledge based on data information to obtain the credibility characteristic value of each type of network knowledge;

[0011] According to the trustworthy characteristic value of each type of network knowledge, the total trustworthy value of network knowledge in the transportation field is obtained;

[0012] According to the total credibility value, the credibility level of network knowledge in the transportation field is determined.

[0013] Secondly, a trustworthy evaluation system for network knowledge in the transportation field is proposed, which includes:

[0014] Knowledge acquisition module, used to acquire network knowledge in the transportation field;

[0015] Knowledge classification module, used to classify network knowledge in the transportation field according to its source;

[0016] A data information acquisition module is used to obtain data information that affects the trustworthiness of each type of network knowledge;

[0017] A trustworthy characteristic value acquisition module is used to perform a trustworthy evaluation on each type of network knowledge based on data information and obtain a trustworthy characteristic value for each type of network knowledge;

[0018] A total credibility value acquisition module is used to obtain the total credibility value of network knowledge in the transportation field based on the credibility characteristic value of each type of network knowledge;

[0019] The trust level assessment module is used to determine the trust level of network knowledge in the transportation field based on the total trust value.

[0020] In a third aspect, an electronic device is proposed, comprising a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps described in a method for trustworthy assessment of network knowledge in the transportation field are completed.

[0021] In a fourth aspect, a computer-readable storage medium is proposed for storing computer instructions. When the computer instructions are executed by a processor, the steps described in a method for trustworthy assessment of network knowledge in the transportation field are completed.

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] 1. The present invention classifies network knowledge according to its sources and performs a credibility assessment on each type of network knowledge. On this basis, the total credibility value of the network knowledge is obtained. The total credibility value is used to perform a credibility assessment on the network knowledge, taking into account the influence of the source of network knowledge on the credibility assessment of network knowledge, thereby improving the accuracy of the credibility assessment of network knowledge.

[0024] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0026] Figure 1 This is a flow chart of the method disclosed in Example 1. DETAILED DESCRIPTION

[0027] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0028] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0029] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0030] Example 1

[0031] In order to improve the accuracy of network knowledge trust evaluation, in this embodiment, a network knowledge trust evaluation method in the transportation field is proposed. Figure 1 As shown, including:

[0032] Acquire network knowledge in the transportation field;

[0033] Classify network knowledge in the transportation field according to its sources;

[0034] Obtain data information that affects the trustworthiness of each type of network knowledge;

[0035] Conduct a credibility assessment on each type of network knowledge based on data information to obtain the credibility characteristic value of each type of network knowledge;

[0036] According to the trustworthy characteristic value of each type of network knowledge, the total trustworthy value of network knowledge in the transportation field is obtained;

[0037] According to the total credibility value, the credibility level of network knowledge in the transportation field is determined.

[0038] A method for evaluating the credibility of network knowledge in the transportation field disclosed in this embodiment is described in detail.

[0039] A method for evaluating the credibility of network knowledge in the transportation field includes:

[0040] S1: Acquire network knowledge in the transportation field.

[0041] The network knowledge obtained in the field of transportation is all authorized and from legal sources, including text, pictures, audio and video, etc.

[0042] S2: Classify network knowledge in the transportation field according to its sources.

[0043] Sources of online knowledge include government departments, scientific research institutions, personal publications, corporate organizations, and marketing accounts.

[0044] According to the sources of the above network knowledge, the network knowledge in the transportation field is classified to obtain network knowledge from government departments, network knowledge from scientific research institutions, network knowledge from individuals, network knowledge from corporate institutions and marketing accounts, etc.

[0045] S3: Obtain data information that affects the trustworthy characteristics of each type of network knowledge, perform a trustworthy evaluation on each type of network knowledge based on the data information, and obtain a trustworthy characteristic value for each type of network knowledge.

[0046] Based on the trustworthy characteristics of different types of network knowledge, data information on the impact of each type of network knowledge on the trustworthy characteristics is obtained.

[0047] Among them, the credibility characteristic of network knowledge from government departments is authority A, and the data information that affects authority A is the department's administrative level.

[0048] Authority is determined based on the department's administrative level, which is the average of the department's administrative level scores and is calculated using formula (1):

[0049]

[0050] Among them, g A It is the sum of the administrative grade scores of each department.

[0051] The final authority is as low as 0.2 and as high as 1.

[0052] The trustworthiness of network knowledge from scientific research institutions is quality Q e , practicality P and timeliness T p Since the network knowledge of scientific research institutions includes academic papers and invention patents, the credibility characteristics of academic papers include: quality Q e and practicality P. The data information that affects the credibility of academic papers includes: paper status S e , Paper Level L e 、The number of paper downloads P d and citation count P q Specific impact quality Q e The data information is the paper status S e With paper level L e ; The data information that affects the practicality P is the download volume P of the paper d and citation count P q ; Credible features of invention patents include timeliness T p , affecting timeliness T p The data information includes: Patent status S p , and the specific information is shown in Table 2-4.

[0053] Table 2 Paper status

[0054] <![CDATA[Paper status S e > <![CDATA[fraction (g Se )]]> Unpublished 1 point Under review 2 points Published 3 points

[0055] Table 3 Paper level

[0056] <![CDATA[Paper level L e > <![CDATA[fraction (g Le )]]> T class 6 points Category A 5 points Category B 4 points Category C 3 points Class D 2 points Category E 1 point Other categories have been published 0 points Unpublished and under review 0 points <![CDATA[Paper level L e > <![CDATA[fraction (g Le )]]> T class 6 points Category A 5 points Category B 4 points Category C 3 points Class D 2 points Category E 1 point Other categories have been published 0 points Unpublished and under review 0 points

[0057] Table 4 Patent status

[0058] <![CDATA[Patent Status S p > <![CDATA[fraction (g p )]]> Not applied for 1 point termination 2 points Substantive Examination 3 points Grant 4 points

[0059] Quality e According to the paper status S e With paper level L e , calculated using formula (2).

[0060]

[0061] Practicality P is based on the number of downloads of the paper P d and citation count P q , calculated using formula (3).

[0062]

[0063] Timeliness T p According to patent status S p, calculated using formula (4).

[0064]

[0065] Individuals include: experienced drivers, technology enthusiasts, road builders, travel experts, etc. The network knowledge published by individuals includes the knowledge content published on the network related to: driving skills, road maintenance knowledge, traffic technology knowledge, traffic development history knowledge, etc. The credibility characteristic of network knowledge published by selected source individuals is quality Q p . Impact on quality Q p The factors include influence i and feedback b; the data information involved includes: number of personal fans N i 、Total number of platform users N p 、N number of user likes t 、N number of collections c 、Number of positive reviews f and the total number of reviews N e .

[0066] In calculating the quality Q p When first passing the number of personal fans N i 、Total number of platform users N p The influence i is calculated by formula (5), and the total number of platform users N p 、N number of user likes t 、N number of collections c 、Number of positive reviews f , total number of evaluations N e The feedback b is calculated by using formula (6), and the quality Q is calculated by using influence i, feedback b and formula (7). p .

[0067]

[0068]

[0069] Q p =i*0.4+b*0.6 (7)

[0070] The trustworthiness of network knowledge from corporate organizations and marketing accounts is reliability R, and the data information that affects reliability R is account type k. m 、Number of advertisements a and the number of goods N m .

[0071] By account type k m 、Number of advertisements carried a 、Number of goods carried m The reliability R is calculated using formula (8).

[0072]

[0073] Among them, k m Is the account type, if the account is a merchant account, k m When it is 0, the account is not a merchant account. m is 1.

[0074] S4: According to the trustworthy characteristic value of each type of network knowledge, the total trustworthy value of the network knowledge in the transportation field is obtained.

[0075] Formula (9) is used to normalize the trust characteristic value of each type of network knowledge to obtain the total trust value C of network knowledge in the transportation field.

[0076]

[0077] Among them, α1, α2, α3, α4, α5, and α6 are authority A, quality Q, and e , Practicality P, Timeliness of invention patent T p , quality Q p and the weight of reliability R, which is obtained by expert scoring based on the hierarchical analysis method, and α1+α2+α3+α4+α5+α6=1.

[0078] S5: Determine the credibility level of network knowledge in the transportation field based on the total credibility value C.

[0079] The credibility of knowledge is divided into five credibility levels, namely weak credibility, relatively weak credibility, medium credibility, relatively strong credibility and strong credibility.

[0080] The trust levels are divided according to the following standards:

[0081] If the total credibility value C of the network knowledge is lower than the first set value, the network knowledge is defined as a weak credibility level, and the first set value is selected as 0.2;

[0082] If the total credibility value C of the network knowledge is between the first set value and the second set value, the network knowledge is defined as a weak credibility level, and the second set value is selected as 0.4;

[0083] If the total credibility value C of the network knowledge is between the second set value and the third set value, the network knowledge is defined as medium credibility, and the third set value is selected as 0.6;

[0084] If the total credibility value C of the network knowledge is between the third set value and the fourth set value, the network knowledge is defined as a higher credibility level, and the fourth set value is selected as 0.8;

[0085] If the total credibility value C of the network knowledge is higher than the fourth set value, the network knowledge is defined as a high credibility level.

[0086] The trustworthiness assessment method disclosed in this embodiment categorizes network knowledge based on its source. Based on the characteristics of knowledge from different sources, it obtains data that influences the feasibility of knowledge. It then determines the trustworthiness of each type of knowledge and uses the analytic hierarchy process to weight the trustworthiness of each type of knowledge. Combining the calculated trustworthiness and the weights of each trustworthiness, it derives a total trustworthiness value for the network knowledge, ultimately quantifying the trustworthiness of network knowledge in the transportation sector. By considering the impact of different knowledge sources on knowledge, the accuracy of trustworthiness assessment using the total trustworthiness value is improved.

[0087] The object of the trustworthy evaluation method disclosed in this embodiment is in the form of network knowledge, which ensures the original state of knowledge as much as possible. There is no need to process the knowledge into a knowledge graph in the form of triples for evaluation, which saves the knowledge reasoning process and improves the evaluation efficiency.

[0088] Example 2

[0089] In this embodiment, a traffic field network knowledge credibility evaluation system is disclosed, including:

[0090] Knowledge acquisition module, used to acquire network knowledge in the transportation field;

[0091] Knowledge classification module, used to classify network knowledge in the transportation field according to its source;

[0092] A data information acquisition module is used to obtain data information that affects the trustworthiness of each type of network knowledge;

[0093] A trustworthy characteristic value acquisition module is used to perform a trustworthy evaluation on each type of network knowledge based on data information and obtain a trustworthy characteristic value for each type of network knowledge;

[0094] A total credibility value acquisition module is used to obtain the total credibility value of network knowledge in the transportation field based on the credibility characteristic value of each type of network knowledge;

[0095] The trust level assessment module is used to determine the trust level of network knowledge in the transportation field based on the total trust value.

[0096] Example 3

[0097] In this embodiment, an electronic device is disclosed, including a memory and a processor, and computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, the steps described in the method for trustworthy assessment of network knowledge in the transportation field disclosed in Example 1 are completed.

[0098] Example 4

[0099] In this embodiment, a computer-readable storage medium is disclosed for storing computer instructions. When the computer instructions are executed by a processor, the steps of the method for trustworthy assessment of network knowledge in the transportation field disclosed in Example 1 are completed.

[0100] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating the credibility of network knowledge in the transportation field, characterized by: include: Acquire network knowledge in the transportation field; Classify network knowledge in the transportation field according to its sources; Obtain data information that affects the trustworthiness of each type of network knowledge; Conduct a credibility assessment on each type of network knowledge based on the data information to obtain the credibility characteristic value of each type of network knowledge. The credibility characteristic of network knowledge from government departments is authority, which is determined by the department's administrative level and is the average of the department's administrative level scores. The network knowledge from scientific research institutions includes academic papers and invention patents. The credible characteristics of academic papers include: quality Q e and practicality P, the credible characteristics of invention patents include timeliness T p ; Quality e According to the paper status S e With paper level L e , calculated using formula (2); （2） Practicality P is based on the number of downloads of the paper P d and citation count P q , calculated using formula (3); （3） Timeliness T p According to patent status S p , calculated using formula (4); （4） The credibility of network knowledge published by source individuals is quality Q p , affecting the quality Q p The factors include influence i and feedback b; in calculating the quality Q p When first passing the number of personal fans N i 、Total number of platform users N p The influence i is calculated by formula (5), and the total number of platform users N p 、N number of user likes t 、N number of collections c 、Number of positive reviews f , total number of evaluations N e The feedback b is calculated by using formula (6), and the quality Q is calculated by using influence i, feedback b and formula (7). p ; （5） （6） （7） The trustworthiness of network knowledge from corporate organizations and marketing accounts is reliability R, which is determined by account type k. m 、Number of advertisements carried a 、Number of goods carried m The reliability R is calculated using formula (8); （8） According to the trustworthy characteristic value of each type of network knowledge, the total trustworthy value of network knowledge in the transportation field is obtained; According to the total credibility value, the credibility level of network knowledge in the transportation field is determined.

2. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 1, characterized in that: The trustworthy characteristic value of each type of network knowledge is normalized to obtain the total trustworthy value of network knowledge in the transportation field.

3. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 1, characterized in that: When normalizing, the weight of the trustworthy characteristic value of each type of network knowledge is obtained by expert scoring based on the hierarchical analysis method.

4. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 1, characterized in that: The trust levels include weak trust, relatively weak trust, medium trust, relatively strong trust and strong trust.

5. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 1, characterized in that: Sources of knowledge include government departments, scientific research institutions, personal publications, corporate organizations and marketing accounts.

6. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 5, characterized in that: The trustworthy characteristic of network knowledge from government departments is authority; The trustworthy characteristics of network knowledge from scientific research institutions are quality, practicality and timeliness; The trustworthy characteristic of online knowledge published by source individuals is quality; The trustworthy characteristic of network knowledge from corporate organizations and marketing accounts is reliability.

7. A method for evaluating the credibility of network knowledge in the field of transportation according to claim 6, characterized in that: The data and information that affects authority is the administrative level of the department; The data information that affects the quality of network knowledge of the source research institution is the paper status and paper level; The data that influences practicality is the number of downloads and citations of the paper; The data and information that affects timeliness is patent status; Data and information that influence the quality of online knowledge published by source individuals include: number of individual followers, total number of platform users, number of user likes, number of favorites, number of positive reviews, and total number of reviews; The data that affects reliability include account type, number of advertisements, and number of products.

8. A network knowledge trust evaluation system in the field of transportation, characterized by: include: Knowledge acquisition module, used to acquire network knowledge in the transportation field; Knowledge classification module, used to classify network knowledge in the transportation field according to its source; A data information acquisition module is used to obtain data information that affects the trustworthiness of each type of network knowledge; The trust characteristic value acquisition module is used to perform a trust evaluation on each type of network knowledge based on data information and obtain the trust characteristic value of each type of network knowledge. The trust characteristic of network knowledge from government departments is authority, which is determined by the department's administrative level and is the average of the department's administrative level scores. The network knowledge from scientific research institutions includes academic papers and invention patents. The credible characteristics of academic papers include: quality Q e and practicality P, the credible characteristics of invention patents include timeliness T p ; Quality e According to the paper status S e With paper level L e , calculated using formula (2); （2） Practicality P is based on the number of downloads of the paper P d and citation count P q , calculated using formula (3); （3） Timeliness T p According to patent status S p , calculated using formula (4); （4） The credibility of network knowledge published by source individuals is quality Q p , affecting the quality Q p The factors include influence i and feedback b; in calculating the quality Q p When first passing the number of personal fans N i 、Total number of platform users N p The influence i is calculated by formula (5), and the total number of platform users N p 、N number of user likes t 、N number of collections c 、Number of positive reviews f , total number of evaluations N e The feedback b is calculated by using formula (6), and the quality Q is calculated by using influence i, feedback b and formula (7). p ; （5） （6） （7） The trustworthiness of network knowledge from corporate organizations and marketing accounts is reliability R, which is determined by account type k. m 、Number of advertisements carried a 、Number of goods carried m The reliability R is calculated using formula (8); （8） A total credibility value acquisition module is used to obtain the total credibility value of network knowledge in the transportation field based on the credibility characteristic value of each type of network knowledge; The trust level assessment module is used to determine the trust level of network knowledge in the transportation field based on the total trust value.

9. An electronic device, characterized in that: The invention comprises a memory and a processor and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the method for trustworthy evaluation of network knowledge in the transportation field as claimed in any one of claims 1 to 7 are completed.

10. A computer-readable storage medium, characterized in that Used to store computer instructions, which, when executed by a processor, complete the steps of a method for trustworthy assessment of network knowledge in the transportation field as described in any one of claims 1 to 7.

Images