Credibility evaluation method and device, equipment, medium and program product

Abstract

The invention provides a credibility evaluation method and device, equipment, a medium and a program product, and aims to solve the problem of relatively low accuracy of entity credibility evaluation in related technologies. The method comprises the following steps: acquiring an evaluation index set of a target product used by a user, wherein the evaluation index set comprises at least two sub-index sets in a user participation degree, a user contribution degree, a user loyalty degree and a user portrait; a target judgment matrix of the evaluation index set and a preset evaluation grade set is constructed, the preset evaluation grade set comprises a plurality of credibility grades, and the target judgment matrix is used for representing association degrees between the plurality of credibility grades and each sub-index set in the evaluation index set; and determining a target credibility grade of the user according to the target judgment matrix and the weight of each sub-index set in the evaluation index set. According to the invention, the accuracy of credibility evaluation can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, and particularly relates to a credibility evaluation method and device, equipment, medium and program product. BACKGROUND

[0002] At present, the credibility evaluation of entities in a data flow process mainly depends on traditional security authentication mechanisms, such as digital certificates, identity verification, etc. Among them, the digital certificate authentication verifies the identity of an entity by issuing a digital certificate, and the identity verification verifies the identity of an entity by a method such as a username and password, a biological feature, etc. These methods can ensure the authenticity of the identity of an entity to a certain extent, but in a complex data flow process, a single identity authentication leads to low accuracy of entity credibility evaluation. SUMMARY

[0003] The present application provides a credibility evaluation method, device, equipment, medium and program product to solve the problem of low accuracy of entity credibility evaluation in related technologies.

[0004] To solve the above technical problems, the present application is implemented as follows:

[0005] In a first aspect, the present application provides a credibility evaluation method, comprising:

[0006] obtaining an evaluation index set of a user using a target product, the evaluation index set comprising at least two sub-index sets of user participation, user contribution, user loyalty and user portrait, wherein the user participation represents the activity level of the user using the target product, the user contribution represents the positive influence of the user on the target product, and the user loyalty represents the degree of dependence of the user on the target product;

[0007] constructing a target judgment matrix of the evaluation index set and a preset evaluation level set, the preset evaluation level set comprising a plurality of credibility levels, and the target judgment matrix being used to represent the association degrees of the plurality of credibility levels and each sub-index set in the evaluation index set;

[0008] determining a target credibility level of the user according to the target judgment matrix and the weights of each sub-index set in the evaluation index set.

[0009] Optionally, the determining the target credibility level of the user according to the target judgment matrix and the weights of each sub-index set in the evaluation index set comprises:

[0010] performing a point multiplication operation on the first weight vector corresponding to each sub indicator set in the evaluation indicator set and the target judgment matrix to obtain a score vector of the user, wherein an element in the first weight vector is a weight of each sub indicator set in the evaluation indicator set;

[0011] determining a target credibility level of the user as a credibility level corresponding to a target element in the score vector, wherein the target element is an element with the maximum value in the score vector.

[0012] Optionally, the constructing the target judgment matrix of the evaluation indicator set and the preset evaluation level set comprises:

[0013] constructing a first judgment matrix of the first evaluation sub indicator set and the preset evaluation level set based on a first preset correlation degree function corresponding to the first evaluation sub indicator set to obtain the first judgment matrix corresponding to each sub indicator set in the evaluation indicator set, the first evaluation sub indicator set being any sub indicator set in the evaluation indicator set;

[0014] performing a merging operation on the first judgment matrix corresponding to each sub indicator set in the evaluation indicator set to obtain the target judgment matrix.

[0015] Optionally, the first evaluation sub indicator set comprises at least one indicator, and the constructing the first judgment matrix of the first evaluation sub indicator set and the preset evaluation level set based on the first preset correlation degree function comprises:

[0016] determining a target correlation degree of the plurality of credibility levels and the at least one indicator based on the first preset correlation degree function;

[0017] constructing a second judgment matrix of the first evaluation sub indicator set and the preset evaluation level set based on the target correlation degree;

[0018] determining the first judgment matrix based on the second judgment matrix and a second weight vector corresponding to the first evaluation sub indicator set, wherein an element in the second weight vector is a weight of each indicator of the first evaluation sub indicator set.

[0019] Optionally, the user participation degree comprises at least one indicator of a use duration, an access frequency, a sharing frequency and a comment frequency of a target product by the user;

[0020] the user contribution degree comprises a recommendation rate of the target product by the user;

[0021] the user loyalty degree comprises at least one indicator of a repurchase rate, a renewal rate, a retention rate and a recommendation frequency of the target product by the user;

[0022] The user portrait includes at least one index of user information, browsing conversion rate, access time period information, access address information, and access frequency.

[0023] In a second aspect, the embodiments of the present application provide a credibility evaluation device, comprising:

[0024] The acquisition module is configured to acquire a set of evaluation indexes of a user using a target product, the set of evaluation indexes including at least two sub-index sets of user engagement, user contribution, user loyalty, and user portrait, wherein the user engagement represents an active degree of the user using the target product, the user contribution represents a positive influence of the user on the target product, and the user loyalty represents a degree of dependence of the user on the target product.

[0025] The construction module is configured to construct a target judgment matrix of the set of evaluation indexes and a set of preset evaluation levels, the set of preset evaluation levels including a plurality of credibility levels, and the target judgment matrix being used to represent an association degree of each sub-index set in the set of evaluation indexes with the plurality of credibility levels.

[0026] The determination module is configured to determine a target credibility level of the user according to the target judgment matrix and weights of each sub-index set in the set of evaluation indexes.

[0027] Optionally, the determination module includes:

[0028] The operation unit is configured to perform a dot product operation on a first weight vector corresponding to each sub-index set in the set of evaluation indexes and the target judgment matrix to obtain a score vector of the user, wherein an element in the first weight vector is a weight of each sub-index set in the set of evaluation indexes.

[0029] The determination unit is configured to determine a credibility level corresponding to a target element in the score vector as the target credibility level of the user, wherein the target element is an element with the maximum value in the score vector.

[0030] Optionally, the construction module includes:

[0031] The construction unit is configured to construct a first judgment matrix of a first evaluation sub-index set and the set of preset evaluation levels based on a first preset association degree function corresponding to the first evaluation sub-index set to obtain a first judgment matrix corresponding to each sub-index set in the set of evaluation indexes, the first evaluation sub-index set being any sub-index set in the set of evaluation indexes.

[0032] The merging unit is configured to merge the first judgment matrices corresponding to each sub-index set in the set of evaluation indexes to obtain the target judgment matrix.

[0033] Optionally, the first evaluation sub-index set includes at least one index, and the construction unit is specifically configured to:

[0034] determine target correlation degrees of the plurality of credibility levels and the at least one index based on the first preset correlation function;

[0035] construct a second judgment matrix of the first evaluation sub-index set and the preset evaluation level set based on the target correlation degrees.

[0036] determine a first judgment matrix based on the second judgment matrix and a second weight vector corresponding to the first evaluation sub-index set, wherein elements in the second weight vector are weights of respective indexes of the first evaluation sub-index set.

[0037] Optionally, the user participation degree includes at least one index of a use duration, an access frequency, a sharing frequency, and a comment frequency of the user on the target product.

[0038] The user contribution degree includes a recommendation rate of the user on the target product.

[0039] The user loyalty degree includes at least one index of a repurchase rate, a renewal rate, a retention rate, and a recommendation frequency of the user on the target product.

[0040] The user portrait includes at least one index of user information, a browsing conversion rate, access time period information, access address information, and an access frequency.

[0041] In a third aspect, an embodiment of the present application provides an electronic device, including a processor, the processor being configured to:

[0042] obtain an evaluation index set of a user using a target product, the evaluation index set including at least two sub-index sets of a user participation degree, a user contribution degree, a user loyalty degree, and a user portrait, wherein the user participation degree represents an active degree of the user using the target product, the user contribution degree represents a positive influence of the user on the target product, and the user loyalty degree represents a dependence degree of the user on the target product;

[0043] construct a target judgment matrix of the evaluation index set and a preset evaluation level set, the preset evaluation level set including a plurality of credibility levels, and the target judgment matrix being used to represent correlation degrees of the plurality of credibility levels and respective sub-index sets in the evaluation index set;

[0044] determine a target credibility level of the user according to the target judgment matrix and weights of respective sub-index sets in the evaluation index set.

[0045] Optionally, the processor is specifically configured to:

[0046] perform a point multiplication operation on the first weight vector corresponding to each sub indicator set in the evaluation indicator set and the target judgment matrix to obtain a score vector of the user, wherein an element in the first weight vector is a weight of each sub indicator set in the evaluation indicator set;

[0047] determine a target credibility level of the user as a credibility level corresponding to a target element in the score vector, wherein the target element is an element with the maximum value in the score vector.

[0048] Optionally, the processor is specifically configured to:

[0049] construct a first judgment matrix of the first evaluation sub indicator set and the preset evaluation level set based on a first preset correlation degree function corresponding to the first evaluation sub indicator set to obtain the first judgment matrix corresponding to each sub indicator set in the evaluation indicator set, the first evaluation sub indicator set being any sub indicator set in the evaluation indicator set;

[0050] merge the first judgment matrix corresponding to each sub indicator set in the evaluation indicator set to obtain the target judgment matrix.

[0051] Optionally, the first evaluation sub indicator set includes at least one indicator, and the processor is specifically configured to:

[0052] determine a target correlation degree of the plurality of credibility levels and the at least one indicator based on the first preset correlation degree function;

[0053] construct a second judgment matrix of the first evaluation sub indicator set and the preset evaluation level set based on the target correlation degree;

[0054] determine the first judgment matrix based on the second judgment matrix and a second weight vector corresponding to the first evaluation sub indicator set, wherein an element in the second weight vector is a weight of each indicator of the first evaluation sub indicator set.

[0055] Optionally, the user engagement includes at least one indicator of a use duration, an access frequency, a sharing frequency and a comment frequency of the user to the target product;

[0056] The user contribution degree includes a recommendation rate of the user to the target product.

[0057] The user loyalty includes at least one indicator of a repurchase rate, a renewal rate, a retention rate and a recommendation frequency of the user to the target product.

[0058] The user portrait includes at least one index of user information, browsing conversion rate, access time period information, access address information, and access frequency.

[0059] In a fourth aspect, an electronic device is provided, which includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the program is executed by the processor, the steps of the credibility evaluation method according to the first aspect are implemented.

[0060] In a fifth aspect, a computer readable storage medium is provided, which stores a computer program, and when the computer program is executed by a processor, the steps of the credibility evaluation method according to the first aspect are implemented.

[0061] In a sixth aspect, a computer program product is provided, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of the credibility evaluation method according to the first aspect are implemented.

[0062] In the embodiments of the present application, a set of evaluation indexes of a user using a target product is obtained, the set of evaluation indexes including at least two sub-index sets of user participation, user contribution, user loyalty, and user portrait, wherein the user participation represents the activity degree of the user using the target product, the user contribution represents the positive influence of the user on the target product, and the user loyalty represents the dependence degree of the user on the target product; a target judgment matrix of the set of evaluation indexes and a set of preset evaluation levels is constructed, the set of preset evaluation levels including a plurality of credibility levels, and the target judgment matrix is used to represent the association degrees of the plurality of credibility levels and each sub-index set in the set of evaluation indexes; and a target credibility level of the user is determined according to the target judgment matrix and the weights of each sub-index set in the set of evaluation indexes. In this way, by comprehensively evaluating the user entity behavior from multiple dimensions such as user participation, user contribution, user loyalty, and user portrait, the credibility of the user entity can be more comprehensively evaluated, and by using the judgment matrix for comprehensive evaluation and giving a comprehensive score to each user entity, the uncertainty and fuzziness in the evaluation indexes can be processed, so that the accuracy and reliability of the credibility evaluation can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0064] Figure 1 is a flowchart of a trustworthiness evaluation method provided by an embodiment of the present application;

[0065] Figure 2 is a schematic diagram of a subject evaluation architecture in a DSSN provided by an embodiment of the present application;

[0066] Figure 3 is a structural schematic diagram of a trustworthiness evaluation device provided by an embodiment of the present application;

[0067] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0069] The terms “first”, “second”, and the like in the embodiments of the present application are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, a method, a system, a product, or an apparatus that includes a series of steps or units does not necessarily have to include only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, the method, the product, or the apparatus. In addition, “and / or” is used in the present application to represent at least one of the connected objects, for example, A and / or B and / or C represents seven cases including A alone, B alone, C alone, A and B both exist, B and C both exist, A and C both exist, and A, B and C all exist.

[0070] For the convenience of understanding, some contents related to the embodiments of the present application are described below:

[0071] In the related art, in the process of complex data flow, a single identity authentication is difficult to comprehensively evaluate the trustworthiness of an entity. In addition, the evaluation method in the related art often lacks dynamic monitoring and comprehensive evaluation of the behavior of the entity, and is difficult to adapt to the changing data environment in the Internet of Things. In actual application, the following problems exist:

[0072] 1. Singularity: the evaluation method in the related art often only focuses on the identity authentication of the entity, and lacks comprehensive evaluation of the behavior of the entity.

[0073] 2. Static: The evaluation methods in related technologies are mostly static, which cannot adapt to the dynamic changing data environment in networking.

[0074] 3. Lack of systematicness: The evaluation methods in related technologies lack systematic evaluation indicators and comprehensive evaluation methods, making it difficult to comprehensively evaluate the credibility of entities.

[0075] In the embodiments of the present application, a credibility evaluation method, device, equipment, medium and program product are provided to solve the problem of low accuracy of entity credibility evaluation in related technologies.

[0076] Referring to Figure 1 , Figure 1 is a flowchart of a credibility evaluation method provided by the embodiments of the present application, as Figure 1 indicated, the method comprises the following steps:

[0077] Step 101, obtaining an evaluation indicator set of a user using a target product, the evaluation indicator set comprising at least two sub-indicator sets of user engagement, user contribution, user loyalty and user portrait, wherein the user engagement represents the activity level of the user using the target product, the user contribution represents the positive influence of the user on the target product, and the user loyalty represents the degree of dependence of the user on the target product.

[0078] In this step, the above-mentioned target product can be any type of digital product (such as application software (Application Program, APP), website), service or functional module.

[0079] The above-mentioned evaluation indicator set can be key data for measuring the interaction quality between the user and the target product. The multiple sub-indicator sets included in the evaluation indicator set can be understood as evaluation standards of different dimensions. For example, if the target product is a social media APP, the evaluation indicator set can include daily average use time (i.e. user engagement), user-generated content quantity (i.e. user contribution), continuous login days (i.e. user loyalty), user registration information (i.e. user portrait), etc.

[0080] The above-mentioned user engagement can represent the activity level of the user using the target product, which can be determined by behavior frequency, duration or interaction complexity, etc.

[0081] The above-mentioned user contribution can represent the positive influence of the user on the target product, which can include the positive value brought by user behavior to the product, such as content creation, word-of-mouth spread, etc. For example, in a short video platform, the user publishes high-quality content and obtains a high number of likes, and in a forum community, writes in-depth comments or answers questions from others.

[0082] The user loyalty can represent a degree of dependence of the user on the target product, which can be determined by long-term behavior, payment habits, or cross-scene binding, etc.

[0083] The user portrait can be a set of user tags constructed based on user registration information, behavior data, and preferences, etc.

[0084] It can be understood that the evaluation index set can also include other sub-index sets, which are not limited by the present application.

[0085] Step 102, constructing a target judgment matrix of the evaluation index set and a preset evaluation level set, the preset evaluation level set including a plurality of credibility levels, the target judgment matrix being used to represent the association degrees of the plurality of credibility levels and each sub-index set in the evaluation index set.

[0086] In this step, the preset evaluation level set can be a pre-defined user credibility level classification, for example, three levels of high, medium, and low, or four levels of credible, medium credible, low credible, and not credible.

[0087] The target judgment matrix includes a plurality of elements, and each element value represents the association degree of a certain credibility level and a certain sub-index set in the evaluation index set. The association degree can be determined according to a pre-set association degree function, which can be designed according to actual conditions.

[0088] Step 103, determining a target credibility level of the user according to the target judgment matrix and the weights of each sub-index set in the evaluation index set.

[0089] In this step, the weights of each sub-index set in the evaluation index set can be pre-set, which can be allocated by a domain expert according to business objectives, or calculated by correlating user behavior with the final credibility level.

[0090] The target credibility level can be determined according to the actual performance of the user in each sub-index set, in combination with the target judgment matrix and the weights. Specifically, a comprehensive score of the user can be calculated based on the target judgment matrix and the weights of each sub-index set in the evaluation index set, the comprehensive score including a score corresponding to each credibility level, and the target credibility level is determined based on the comprehensive score.

[0091] It can be understood that the credibility evaluation method can be implemented based on part of the modules of different network elements in a Data Switched Services Network (DSSN) in a data flow circulation and sharing service network, for example, Figure 2is a schematic diagram of a subject evaluation architecture in a DSSN provided by an embodiment of the present application, as shown, mainly related to a subject scoring module in a digital service platform (DSP), the DSP including log processing, subject scoring, policy verification, etc. modules, data transmission, policy verification and transmission termination modules of a data source node (DSN), data reception, data use and log upload modules of a data demand node. Among them, the data demander is the user in the present application, that is, the object to be evaluated. Figure 2

[0092] For example, let the above evaluation index set be U = {u1, u2, u3, u4}, where u1, u2, u3, u4 are user participation, user contribution, user loyalty and user portrait respectively. Let the preset evaluation level set be V = {v1, v2, v3, v4}, where v1, v2, v3, v4 represent four dimensions of trust, medium trust, low trust and untrustworthy respectively. Let the weight set W include the weights of each sub-index set in the above evaluation index set, the weight set A = {a1, a2, a3, a4}, where a i is the weight of u1. Let the target judgment matrix be:

[0093]

[0094] where r ij represents the correlation degree of the i-th trust level to the j-th sub-index set.

[0095] In the embodiments of the present application, by comprehensively evaluating the user entity behavior from multiple dimensions such as user participation, user contribution, user loyalty, user portrait, etc., the trustworthiness of the user entity can be more comprehensively evaluated, and the judgment matrix is used for comprehensive evaluation, and each user entity is scored, which can handle the uncertainty and fuzziness in the evaluation index, thereby improving the accuracy and reliability of the trustworthiness evaluation.

[0096] Optionally, the target trust level of the user is determined according to the target judgment matrix and the weights of each sub-index set in the evaluation index set, comprising:

[0097] The first weight vector corresponding to each sub-index set in the evaluation index set and the target judgment matrix are multiplied to obtain the score vector of the user, wherein the elements in the first weight vector are the weights of each sub-index set in the evaluation index set;

[0098] ​The credibility level corresponding to the target element in the rating vector is determined as the user's target credibility level, wherein the target element is the element with the largest value in the rating vector.

[0099] Specifically, the above dot product operation can be achieved by multiplying the first weight vector by each column of the target judgment matrix and summing the results to obtain the score for each confidence level, i.e., the score F = W * R.

[0100] For example, assuming the calculated user rating vector is 0.959 (high confidence), 0.723 (medium confidence), and 0.411 (low confidence), then the target element is 0.959, which corresponds to a high confidence level, and the user is judged to be at the high confidence level.

[0101] In this implementation, the scores of multiple sub-indicator sets are weighted according to their importance and then comprehensively calculated by using weight vectors and dot product operations. This avoids the bias of a single indicator and can further improve the accuracy and reliability of credibility assessment.

[0102] Optionally, constructing the target judgment matrix of the evaluation index set and the preset evaluation level set includes:

[0103] Based on the first preset correlation function corresponding to the first evaluation sub-index set, a first judgment matrix between the first evaluation sub-index set and the preset evaluation level set is constructed to obtain the first judgment matrix corresponding to each sub-index set in the evaluation index set. The first evaluation sub-index set is any sub-index set in the evaluation index set.

[0104] The target judgment matrix is ​​obtained by merging the first judgment matrices corresponding to each sub-indicator set in the evaluation index set.

[0105] Specifically, the aforementioned first preset correlation function can be defined separately for each sub-indicator set, used to determine the correlation between the indicators in each sub-indicator set and each confidence level. For example, the first preset correlation function can be a linear function, that is, directly dividing the levels according to the score range, or it can be a non-linear function, such as an exponential or logistic function.

[0106] The specific way to merge the first judgment matrices corresponding to each sub-indicator set in the evaluation index set can be to stack multiple first judgment matrices in the row direction, that is, to merge them along the vertical direction to obtain the target judgment matrix.

[0107] In this embodiment, by constructing a first judgment matrix of a first evaluation sub-index set and a preset evaluation level set, and merging the first judgment matrices corresponding to each sub-index set in the evaluation index set, the target judgment matrix is ​​obtained. This allows the judgment matrix and correlation function of each sub-index set to be independently determined and verified according to actual needs, which can adapt to the needs of different business scenarios, thereby improving the accuracy and flexibility of credibility assessment.

[0108] Optionally, the first evaluation sub-index set includes at least one index, and the step of constructing a first judgment matrix between the first evaluation sub-index set and the preset evaluation level set based on a first preset correlation function corresponding to the first evaluation sub-index set includes:

[0109] Based on the first preset correlation function, the target correlation between the multiple credibility levels and the at least one indicator is determined;

[0110] Based on the target correlation, a second judgment matrix is ​​constructed between the first evaluation sub-index set and the preset evaluation level set;

[0111] Based on the second judgment matrix and the second weight vector corresponding to the first evaluation sub-index set, a first judgment matrix is ​​determined, wherein the elements in the second weight vector are the weights of each index in the first evaluation sub-index set.

[0112] Specifically, the aforementioned target correlation degree can be a specific value calculated using a preset correlation degree function, representing the correlation degree between a specific indicator in the first evaluation sub-indicator set and a certain credibility level. The aforementioned second judgment matrix can be a matrix obtained by integrating the target correlation degrees of all specific indicators in the same evaluation sub-indicator set.

[0113] It is understandable that by weighting and merging the correlation degrees of each item in the second judgment matrix, the first judgment matrix is ​​obtained, which is the final mapping relationship between the first evaluation sub-index set and multiple credibility levels.

[0114] In this implementation, the judgment matrix of the sub-indicator set is determined by specific indicators, and then the judgment matrix of the entire evaluation indicator set is determined, realizing a hierarchical design. Furthermore, by designing correlation functions and weights for specific indicators within the first evaluation sub-indicator set, business needs can be accurately reflected, thereby further improving the flexibility of credibility assessment.

[0115] The credibility assessment method described above is illustrated by an example embodiment below:

[0116] 1. Determine the set of evaluation indicators and their weights.

[0117] Set of evaluation indicators:

[0118] U = {u1, u2, u3, u4}, where u1, u2, u3, u4 represent user engagement, user contribution, user loyalty, and user profile, respectively. The weight vector W = [0.4, 0.3, 0.2, 0.1].

[0119] Sub-indicator set:

[0120] u1={u 11 ,u 12 ,u 13}, u 11 ,u 12 ,u 13 These represent average daily usage time, weekly access frequency, and number of shares / comments, respectively. W1 = [0.5, 0.3, 0.2].

[0121] u2={u 21}, u 21 Indicates recommendation rate

[0122] u3={u 31 ,u 32 ,u 33 ,u 34}, u 31 ,u 32 ,u 33 ,u 34 W3 represents repurchase rate, renewal rate, referral score, and monthly retention rate, respectively. W3 = [0.4, 0.3, 0.2, 0.1]

[0123] u4={u 41 ,u 42 ,u 43}, u 41 ,u 42 ,u 43 These represent the institution type, browsing conversion rate, and concentration of visits during specific time periods, respectively. W4 = [0.4, 0.4, 0.2].

[0124] 2. Determine the preset evaluation level set

[0125] The evaluation level set V = {v1, v2, v3, v4}, where v1, v2, v3, v4 represent the four dimensions of trustworthiness, medium trustworthiness, low trustworthiness, and untrustworthiness, respectively.

[0126] 3. Determine the correlation function

[0127] 3.1 Average daily usage time (minutes / day, denoted as x) and corresponding comments mapping using a trapezoidal function:

[0128] Credible:

[0129] Zhongkexin: Low credibility: Unreliable: Weekly visit frequency and number of shares / comments can also be set using the same correlation function.

[0130] 3.2 Repurchase rate (x%) Gaussian function corresponding to comment mapping

[0131] Credible: Zhongkexin: Low credibility: Unreliable:

[0132] 4. Data collection and correlation calculation

[0133] Assume the measured data is as follows:

[0134] u1:u 11 =65min,u 12 =65 times / week, u 13 = 3 times / month

[0135] u2:u 21 =75%, (Recommendation rate = Number of recommendations / Number of purchases)

[0136] u3:u 31 =75%,u 32 =60%,u 33 =12 times, u 34 =85%

[0137] u4:u 41 =Public institutions, u 42 =25%,u 43 =Evening rush hour accounts for 68%

[0138] The judgment matrix for user engagement u1 is:

[0139]

[0140] Sub-factors Therefore, the target judgment matrix is ​​further obtained as follows: The scoring vector is obtained as F = W·R = [0.6314, 0.689, 0.031, 0].

[0141] Final assessment result: 0.689 corresponds to the "Medium Confidence" level.

[0142] Optionally, the user engagement includes at least one of the following metrics: user usage time, access frequency, number of shares, and number of comments on the target product;

[0143] The user contribution rate includes the user's recommendation rate for the target product;

[0144] The user loyalty includes at least one of the following metrics: repurchase rate, renewal rate, retention rate, and number of recommendations for the target product;

[0145] The user profile includes at least one of the following metrics: user information, browsing conversion rate, access time information, access address information, and access frequency.

[0146] Specifically, the aforementioned user contribution can be the user's contribution to the data product during use, including comments made after using the data and the number of times the user recommends the purchased data to other customers. Specific indicators include recommendation rate, etc.

[0147] The aforementioned user loyalty refers to a user's willingness to continue using data services during data circulation and transaction processes, and to pay for or provide positive feedback. Specific indicators include repurchase rate, renewal rate, referral value, and user retention rate. Specifically, repurchase rate refers to the act of purchasing data products again after already having ordered and used them; renewal rate refers to the act of renewing the subscription for data products that have already been purchased but have not yet been used up; referral value refers to the number of times a purchased data product is recommended to other customers; and user retention rate refers to the continued use of data products over a potentially long period (daily, weekly, monthly) after purchase.

[0148] The aforementioned user profile can be a description of a user's basic attributes and behavioral characteristics during data flow. Specific indicators include user registration information, browsing behavior, usage habits, and transaction records. Specifically, user registration information indicates whether the user's entity is a government agency, public institution, or industry client; browsing behavior is the ratio of browsing frequency to order quantity; transaction records are the ratio of browsing frequency to transaction frequency; and usage habits include the data requester's frequent access times, frequently accessed Internet Protocol (IP) addresses, and access frequency.

[0149] It should be noted that since the transaction records, usage frequency, registration information, etc. of the above users are not in the same dimension, they need to be quantified before they can be calculated. This application does not specify the specific quantification method.

[0150] In this implementation, since the above-mentioned indicators are generated in real time by users participating in the data flow process, by dynamically collecting and processing the above-mentioned specific indicators, it is possible to evaluate the credibility of entities in real time, adapt to the ever-changing data environment in the Internet of Things, and thus further improve the accuracy of evaluating the credibility of entities.

[0151] See Figure 3 , Figure 3 This is a schematic diagram of the structure of a credibility assessment device provided in an embodiment of this application, as shown below. Figure 3As shown, the credibility assessment device 300 includes:

[0152] The acquisition module 301 is used to acquire a set of evaluation indicators for users using the target product. The set of evaluation indicators includes at least two sub-indicator sets from user participation, user contribution, user loyalty, and user profile. The user participation indicates the activity level of the user in using the target product, the user contribution indicates the positive impact of the user on the target product, and the user loyalty indicates the degree of dependence of the user on the target product.

[0153] The construction module 302 is used to construct a target judgment matrix of the evaluation index set and the preset evaluation level set. The preset evaluation level set includes multiple credibility levels. The target judgment matrix is ​​used to characterize the correlation between the multiple credibility levels and each sub-index set in the evaluation index set.

[0154] The determination module 303 is used to determine the user's target credibility level based on the target judgment matrix and the weights of each sub-indicator set in the evaluation index set.

[0155] Optionally, the determining module 303 includes:

[0156] The calculation unit is used to perform a dot product operation on the first weight vector corresponding to each sub-index set in the evaluation index set and the target judgment matrix to obtain the user's rating vector, wherein the elements in the first weight vector are the weights of each sub-index set in the evaluation index set.

[0157] The determining unit is used to determine the credibility level corresponding to the target element in the rating vector as the target credibility level of the user, wherein the target element is the element with the largest value in the rating vector.

[0158] Optionally, the construction module 302 includes:

[0159] The construction unit is used to construct a first judgment matrix between the first evaluation sub-indicator set and the preset evaluation level set based on the first preset correlation function corresponding to the first evaluation sub-indicator set, and to obtain the first judgment matrix corresponding to each sub-indicator set in the evaluation index set, wherein the first evaluation sub-indicator set is any sub-indicator set in the evaluation index set.

[0160] The merging unit is used to merge the first judgment matrices corresponding to each sub-indicator set in the evaluation index set to obtain the target judgment matrix.

[0161] Optionally, the first evaluation sub-index set includes at least one index, and the construction unit is specifically used for:

[0162] Based on the first preset correlation function, the target correlation between the multiple credibility levels and the at least one indicator is determined;

[0163] Based on the target correlation, a second judgment matrix is ​​constructed between the first evaluation sub-index set and the preset evaluation level set;

[0164] Based on the second judgment matrix and the second weight vector corresponding to the first evaluation sub-index set, a first judgment matrix is ​​determined, wherein the elements in the second weight vector are the weights of each index in the first evaluation sub-index set.

[0165] Optionally, the user engagement includes at least one of the following metrics: user usage time, access frequency, number of shares, and number of comments on the target product;

[0166] The user contribution rate includes the user's recommendation rate for the target product;

[0167] The user loyalty includes at least one of the following metrics: repurchase rate, renewal rate, retention rate, and number of recommendations for the target product;

[0168] The user profile includes at least one of the following metrics: user information, browsing conversion rate, access time information, access address information, and access frequency.

[0169] It should be noted that the credibility assessment device provided in this application embodiment is a device capable of executing the above-described credibility assessment method. Therefore, all implementation methods in the above-described credibility assessment method embodiments are applicable to this device and can achieve the same or similar beneficial effects. To avoid repetition, this embodiment will not elaborate further.

[0170] For details, see Figure 4 As shown in the figure, this application embodiment also provides an electronic device, including a bus interface, a processor 400, and a memory 420.

[0171] Processor 400 is used for:

[0172] Obtain a set of evaluation metrics for user use of the target product. The set of evaluation metrics includes at least two sub-metric sets from user engagement, user contribution, user loyalty, and user profile. The user engagement represents the activity level of the user in using the target product, the user contribution represents the positive impact of the user on the target product, and the user loyalty represents the degree of dependence of the user on the target product.

[0173] Construct a target judgment matrix between the set of evaluation indicators and the preset set of evaluation levels. The preset set of evaluation levels includes multiple credibility levels. The target judgment matrix is ​​used to characterize the correlation between the multiple credibility levels and each sub-indicator set in the set of evaluation indicators.

[0174] The user's target credibility level is determined based on the target judgment matrix and the weights of each sub-indicator set in the evaluation index set.

[0175] exist Figure 4 In this context, a bus architecture (represented by a bus) is used. The bus can include any number of interconnected buses and bridges, linking various circuits including one or more processors represented by processor 400 and memory 420 represented by memory 420. The bus can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. A bus interface provides an interface between the bus and the transceiver. The transceiver can be a single element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices over a transmission medium. Data processed by processor 400 is transmitted over a wireless medium via an antenna, which further receives data and transmits it back to processor 400.

[0176] Processor 400 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management, and other control functions. Memory 420 can be used to store data used by processor 4000 during operation.

[0177] Optionally, the processor 400 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD).

[0178] Optionally, the processor 400 is specifically used for:

[0179] The user's rating vector is obtained by performing a dot product operation on the first weight vector corresponding to each sub-index set in the evaluation index set and the target judgment matrix, wherein the elements in the first weight vector are the weights of each sub-index set in the evaluation index set.

[0180] The credibility level corresponding to the target element in the rating vector is determined as the user's target credibility level, wherein the target element is the element with the largest value in the rating vector.

[0181] Optionally, the processor 400 is specifically used for:

[0182] Based on the first preset correlation function corresponding to the first evaluation sub-index set, a first judgment matrix between the first evaluation sub-index set and the preset evaluation level set is constructed to obtain the first judgment matrix corresponding to each sub-index set in the evaluation index set. The first evaluation sub-index set is any sub-index set in the evaluation index set.

[0183] The target judgment matrix is ​​obtained by merging the first judgment matrices corresponding to each sub-indicator set in the evaluation index set.

[0184] Optionally, the first evaluation sub-index set includes at least one index, and the processor 405 is specifically used for:

[0185] Based on the first preset correlation function, the target correlation between the multiple credibility levels and the at least one indicator is determined;

[0186] Based on the target correlation, a second judgment matrix is ​​constructed between the first evaluation sub-index set and the preset evaluation level set;

[0187] Based on the second judgment matrix and the second weight vector corresponding to the first evaluation sub-index set, a first judgment matrix is ​​determined, wherein the elements in the second weight vector are the weights of each index in the first evaluation sub-index set.

[0188] Optionally, the user engagement includes at least one of the following metrics: user usage time, access frequency, number of shares, and number of comments on the target product;

[0189] The user contribution rate includes the user's recommendation rate for the target product;

[0190] The user loyalty includes at least one of the following metrics: repurchase rate, renewal rate, retention rate, and number of recommendations for the target product;

[0191] The user profile includes at least one of the following metrics: user information, browsing conversion rate, access time information, access address information, and access frequency.

[0192] It should be noted that the electronic device provided in this application embodiment is a device capable of executing the above-described credibility assessment method. Therefore, all implementation methods in the above-described credibility assessment method embodiments are applicable to this electronic device and can achieve the same or similar beneficial effects. To avoid repetition, this embodiment will not elaborate further.

[0193] This invention also provides an electronic device, including: a processor, a memory, and a program stored in the memory and executable on the processor. When the program is executed by the processor, it implements the various processes of the above-described credibility assessment method embodiments and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0194] This application also provides a computer-readable storage medium storing a computer program. When executed by a processor, this computer program implements the various processes of the above-described credibility assessment method embodiments and achieves the same technical effects. To avoid repetition, it will not be described again here. The computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0195] This application also provides a computer program product, including computer instructions. When executed by a processor, the computer instructions implement the various processes of the above-described credibility assessment method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0196] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0197] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0198] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A credibility assessment method, characterized in that, include: Obtain a set of evaluation metrics for user use of the target product. The set of evaluation metrics includes at least two sub-metric sets from user engagement, user contribution, user loyalty, and user profile. The user engagement represents the activity level of the user in using the target product, the user contribution represents the positive impact of the user on the target product, and the user loyalty represents the degree of dependence of the user on the target product. Construct a target judgment matrix between the set of evaluation indicators and the preset set of evaluation levels. The preset set of evaluation levels includes multiple credibility levels. The target judgment matrix is ​​used to characterize the correlation between the multiple credibility levels and each sub-indicator set in the set of evaluation indicators. The user's target credibility level is determined based on the target judgment matrix and the weights of each sub-indicator set in the evaluation index set.

2. The method according to claim 1, characterized in that, Determining the user's target credibility level based on the weights of each sub-indicator set in the target judgment matrix and the evaluation index set includes: The user's rating vector is obtained by performing a dot product operation on the first weight vector corresponding to each sub-index set in the evaluation index set and the target judgment matrix, wherein the elements in the first weight vector are the weights of each sub-index set in the evaluation index set. The credibility level corresponding to the target element in the rating vector is determined as the user's target credibility level, wherein the target element is the element with the largest value in the rating vector.

3. The method according to claim 1, characterized in that, The construction of the target judgment matrix of the evaluation index set and the preset evaluation level set includes: Based on the first preset correlation function corresponding to the first evaluation sub-index set, a first judgment matrix between the first evaluation sub-index set and the preset evaluation level set is constructed to obtain the first judgment matrix corresponding to each sub-index set in the evaluation index set. The first evaluation sub-index set is any sub-index set in the evaluation index set. The target judgment matrix is ​​obtained by merging the first judgment matrices corresponding to each sub-indicator set in the evaluation index set.

4. The method according to claim 3, characterized in that, The first evaluation sub-index set includes at least one index. The step of constructing a first judgment matrix between the first evaluation sub-index set and the preset evaluation level set based on a first preset correlation function corresponding to the first evaluation sub-index set includes: Based on the first preset correlation function, the target correlation between the multiple credibility levels and the at least one indicator is determined; Based on the target correlation, a second judgment matrix is ​​constructed between the first evaluation sub-index set and the preset evaluation level set; Based on the second judgment matrix and the second weight vector corresponding to the first evaluation sub-index set, a first judgment matrix is ​​determined, wherein the elements in the second weight vector are the weights of each index in the first evaluation sub-index set.

5. The method according to any one of claims 1-4, characterized in that, The user engagement includes at least one of the following metrics: user usage time, access frequency, number of shares, and number of comments on the target product; The user contribution rate includes the user's recommendation rate for the target product; The user loyalty includes at least one of the following metrics: repurchase rate, renewal rate, retention rate, and number of recommendations for the target product; The user profile includes at least one of the following metrics: user information, browsing conversion rate, access time information, access address information, and access frequency.

6. A credibility assessment device, characterized in that, include: The acquisition module is used to acquire a set of evaluation indicators for users using the target product. The set of evaluation indicators includes at least two sub-indicator sets from user participation, user contribution, user loyalty, and user profile. The user participation indicates the activity level of the user in using the target product, the user contribution indicates the positive impact of the user on the target product, and the user loyalty indicates the degree of dependence of the user on the target product. A construction module is used to construct a target judgment matrix for the set of evaluation indicators and a preset set of evaluation levels. The preset set of evaluation levels includes multiple credibility levels. The target judgment matrix is ​​used to characterize the correlation between the multiple credibility levels and each sub-indicator set in the set of evaluation indicators. The determination module is used to determine the user's target credibility level based on the target judgment matrix and the weights of each sub-indicator set in the evaluation index set.

7. An electronic device, characterized in that, Includes a processor, the processor being used for: Obtain a set of evaluation metrics for user use of the target product. The set of evaluation metrics includes at least two sub-metric sets from user engagement, user contribution, user loyalty, and user profile. The user engagement represents the activity level of the user in using the target product, the user contribution represents the positive impact of the user on the target product, and the user loyalty represents the degree of dependence of the user on the target product. Construct a target judgment matrix between the set of evaluation indicators and the preset set of evaluation levels. The preset set of evaluation levels includes multiple credibility levels. The target judgment matrix is ​​used to characterize the correlation between the multiple credibility levels and each sub-indicator set in the set of evaluation indicators. The user's target credibility level is determined based on the target judgment matrix and the weights of each sub-indicator set in the evaluation index set.

8. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the credibility assessment method as described in any one of claims 1 to 5.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the credibility assessment method as described in any one of claims 1 to 5.

10. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the credibility assessment method as described in any one of claims 1 to 5.

Images