Method and device for evaluating credibility of digital business card, electronic equipment and storage medium

Abstract

The invention relates to a method and device for evaluating the credibility of a digital business card, electronic equipment and a storage medium. The method for evaluating the credibility of the digital business card comprises the following steps of: S1, evaluating basic information of a user identity, and initiating a query of whether the identity is a white list, a black list and a grey list to a third-party data provider comprising a basic operator according to a mobile phone number so as to obtain basic evaluation information of the identity of a registered user of the digital business card; s2, business card element information evaluation: in a digital business card creation / editing link, evaluating the credibility of the business card element information based on a collaborative filtering algorithm; s3, business card distribution weight evaluation: when the digital business cards are exchanged, analyzing forwarding times and credibility of business card forwarders; and S4, calculating the credibility of the digital business card, and carrying out weighted calculation to obtain the credibility C of the digital business card based on the evaluation results of the three parts. The method for evaluating the credibility of the identity information of the digital business card is a new method capable of dynamically calculating the credibility of the identity information.

Description

Technical Field

[0001] The present invention relates to the fields of communication network technology and digital security, and in particular to a method, device, electronic device and storage medium for evaluating the credibility of a digital business card. Background Art

[0002] Digital business cards, also known as electronic business cards, are used to display and exchange user identity information over the internet during communications. Digital business cards typically include name, address, phone number, company, and position. Digital business cards, aligning with green and low-carbon initiatives, are rapidly replacing paper business cards and gaining widespread adoption. Major domestic telecom operators have launched digital business card services.

[0003] Digital business cards can be edited and published by registered users, making it extremely convenient for users to publish and exchange digital business cards. However, these user-generated business cards also pose potential security risks, such as the spread of false identity information. Examples include fraudulent use of someone else's name, forged identity information, and the illegal use of someone else's phone number to disrupt their daily lives. How can we dynamically assess the credibility of user-defined identity information on massive amounts of digital business cards? Ensuring that recipients of digital business cards receive timely credibility information and, therefore, receive necessary early warnings to prevent the spread of false and fraudulent information online is a pressing issue in the digital business card industry.

[0004] Currently, existing methods for assessing the credibility of identity information can be roughly divided into two categories. One involves comparing business card information with pre-recorded identity information. For example, Chinese Patent No. cn114826613, "Blockchain-Based Identity Information Query Method, Device, Equipment, and Storage Medium," utilizes a decentralized blockchain-based identity information query method to compare business card information with identity certificates stored in blockchain mining nodes, ultimately obtaining an identity certificate from the blockchain. This method essentially statically compares the identity information to be evaluated with pre-recorded identity information (stored in the blockchain). Given the vast number of user-defined digital business cards, pre-creating identity certificates for each individual for comparison is obviously costly and difficult to implement. Another major category involves designing a verification system that manually verifies and verifies business card information. For example, Chinese Patent No. cn111310144, "Electronic Business Card Authentication Method, Device, Computer Equipment, and Storage Medium," primarily addresses the authentication relationship between so-called "personal accounts" and "legal entity business cards." Essentially, this involves manually reviewing and judging the business cards created by individual users who submit review requests through a company's "legal person" (i.e., the "administrator" of their organization). This ensures that individual users cannot impersonate the "legal person's" corporate information. This is an evaluation method based entirely on manual judgment, addressing the issue of authenticating the relationship between a company and its employees. This method, based on the company's existing knowledge of its employees' identities, can accurately address this aspect of identity assessment. However, due to its manual nature and the need to maintain a correspondence between companies and employees, it is clearly unrealistic for digital business cards intended for universal service to assign an administrator to each company ("legal person"), making widespread adoption difficult.

[0005] In summary, current methods for assessing the credibility of digital business cards are generally based on comparing and verifying reserved information (whether manual or non-manual), which is not suitable for large-scale digital business card applications. Therefore, there is an urgent need to develop a new, efficient, and low-cost method that can automatically and dynamically assess the credibility of digital business card identity information. Summary of the Invention

[0006] The technical problem to be solved by the present invention is how to prevent the information security risk of spreading false information through digital business cards. A new method that does not rely on the comparison of reserved identity information and does not require human intervention is used to dynamically evaluate the credibility of digital business card identity information.

[0007] In order to solve the above technical problems, according to one aspect of the present invention, a method for evaluating the credibility of a digital business card is provided. The digital business card contains identity information. The method for evaluating the credibility of a digital business card includes the following steps: S1, user identity basic information evaluation. Before creating a digital business card, the user first registers. At this time, the mobile phone number is first verified to confirm that the user is actually using the registered mobile phone number; the mobile phone number is verified, and a query is initiated to a third-party data provider including the basic operator based on the mobile phone number to determine whether it is on the white list, black list, or gray list, thereby obtaining basic evaluation information of the registered user identity of the digital business card, performing user identity basic information evaluation, and calculating the user identity basic information score F0, wherein the white list is a list of users whose identity information is determined to be authentic and reliable, the black list is a list of users who are determined to be fraudulent calls or false identity information, and the gray list is a list of users who are determined to be suspected of harassment or List of fraudulent users; S2. Business card element information evaluation. During the digital business card creation / editing phase, the credibility of the business card element information is evaluated based on the collaborative filtering algorithm. The similarity of the elements between the business cards is first calculated, and then the credibility of the business card to be evaluated is predicted by analyzing the business cards with similar elements, and the business card element evaluation score F1 is calculated. The elements of the digital business card include: name, mobile phone number, email, company, address, position, WeChat, or one or more of them; S3. Business card distribution weight evaluation. When digital business cards are exchanged, the credibility of the business card to be evaluated is predicted based on the analysis of the number of forwarding times and credibility of the business card forwarder, and the business card distribution weight evaluation score F2 is calculated; S4. Calculation of digital business card credibility. Each time the digital business card is displayed, the digital business card credibility C based on the evaluation results of the above three parts is calculated in real time by weighted calculation, and the prompt to the digital business card recipient is output and completed.

[0008] According to an embodiment of the present invention, in step S1, the user identity basic information score is F0, and the calculation formula can be:

[0009]

[0010] Among them, when the user name and phone number of the digital business card registered user are verified to be authentic and valid by the whitelist, the evaluation score is 100; when the user name and phone number fail to pass the verification and are identified as a fraudulent call by the blacklist, the evaluation score is 0; when the user's mobile phone number hits the gray list, the risk level is scored in a stepped manner according to formula (1).

[0011] According to an embodiment of the present invention, in step S2, the elements of the digital business card including classification, company, address, and position are selected for modeling. Step S2 may include the following steps: S21, pre-processing the company and address names, cutting off the head and tail of the company name and address, and removing the common words therein; S22, classifying the industry of the company elements, segmenting the company name, matching the industry information according to the keywords in the company name, and corresponding to the industry classification; S23, constructing a word vector, after segmenting the company name, address, and position, constructing a four-dimensional word vector, the four-dimensional word vector includes: industry classification, company Company name segmentation 1, company name segmentation 2…, address segmentation 1, address segmentation 2…, position segmentation 1, position segmentation 2…; S24, training model, through the word2vec model of the Gensim package in Python, input data training model on each individual dimension of "company name, address, position", and obtain the segmentation similarity on each dimension; S25, calculate similarity, for two four-dimensional word vectors belonging to two digital business cards, the similarity can be compared on each dimension, and the overall similarity can be obtained by weighted average method, and the similarity of each dimension is set as R i , then the formula for the overall similarity R is:

[0012]

[0013] S26. Calculate the business card element evaluation score. Apply collaborative filtering to find the top 100 evaluated business cards that are most similar to the current digital business card to be evaluated. Obtain the business card element evaluation score of the current digital business card to be evaluated by taking the weighted average of the business card element evaluation scores of each business card in this result set. The business card element evaluation score F1 can be:

[0014]

[0015] Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R i In the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

[0016] According to an embodiment of the present invention, in step S3, the calculation formula of F2 can be:

[0017]

[0018] Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count iIndicates the number of times the i-th user forwarded the digital business card among the n users who forwarded the digital business card of the user.

[0019] According to an embodiment of the present invention, in step S4, the initial score F0 of the user dimension is defined to account for 30%, the review score F1 of the business card dimension is defined to account for 40%, and the weighted score F2 based on business card distribution is defined to account for 30%. The credibility of the digital business card is:

[0020] C=F0*0.3+F1*0.4+F2*0.3 (5)

[0021] According to a second aspect of the present invention, there is provided an apparatus for evaluating the credibility of a digital business card, comprising:

[0022] User identity basic information evaluation module, before creating a digital business card, the user must first register, at this time the mobile phone number is first verified to confirm that the user is actually using the registered mobile phone number; the user identity basic information evaluation module is used to verify the mobile phone number, and based on the mobile phone number, initiate a query to the third-party data provider including the basic operator to determine whether it is on the white list, black list, or gray list, so as to obtain the basic evaluation information of the registered user identity of the digital business card, perform the user identity basic information evaluation, and calculate the user identity basic information score F2, where the white list is a list of users whose identity information is recognized to be authentic and reliable, the black list is a list of users who are recognized to be fraudulent calls or false identity information, and the gray list is a list of users who are recognized to be suspected of harassment or fraud; business card element information evaluation module, the business card element information evaluation module is used to create a digital business card / Editing stage, the credibility of the business card element information is evaluated based on the collaborative filtering algorithm. The similarity of the elements between the business cards is first calculated, and then the credibility of the business card to be evaluated is predicted by analyzing the business cards with similar elements, and the business card element evaluation score F1 is calculated. Among them, the elements of the digital business card include: name, mobile phone number, email, company, address, position, WeChat, or one or more; business card distribution weight evaluation module, when digital business cards are exchanged, the business card distribution weight evaluation module analyzes the number of forwarding times and credibility of the business card forwarder, and predicts the credibility of the business card to be evaluated based on this, and calculates the business card distribution weight evaluation score F2; digital business card credibility calculation module, used to calculate the digital business card credibility C based on the above three evaluation results in real time when the digital business card is displayed, and output and complete the prompt to the digital business card recipient.

[0023] According to an embodiment of the present invention, the business card element information evaluation module includes: a company and address name preprocessing unit, which is used to cut off the company name and address and remove the common words therein; a company element industry classification unit, which is used to segment the company name and match the industry information according to the keywords in the company name to correspond to the industry classification; a word vector construction unit, which is used to segment the company name, address, and position, and then construct a four-dimensional word vector including: industry classification, company name segmentation, address segmentation, and position segmentation; a training model unit, which uses the word2vec model of the Gensim package in Python to input data for training and modeling on each individual dimension of "company name, address, and position" to obtain the segmentation similarity on each dimension; a similarity calculation unit, which is used to compare the similarity of two four-dimensional word vectors belonging to two digital business cards on each dimension, and obtain the overall similarity by the weighted average method, wherein the similarity of each dimension is R i , the formula for the overall similarity R can be:

[0024]

[0025] Calculate the business card element evaluation score unit and apply the collaborative filtering strategy to find the top 100 evaluated business cards that are most similar to the current digital business card to be evaluated. The business card element evaluation score of the current digital business card to be evaluated is obtained by taking the weighted average of the business card element evaluation scores of each business card in this result set. The business card element evaluation score F1 can be:

[0026]

[0027] Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R i In the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

[0028] According to an embodiment of the present invention, the calculation formula for F2 performed by the business card distribution weight evaluation module may be:

[0029]

[0030] Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count i Indicates the number of times the i-th user forwarded the digital business card among the n users who forwarded the digital business card of the user.

[0031] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory, a processor, and a program for evaluating the credibility of a digital business card stored in the memory and executable on the processor, wherein the program for evaluating the credibility of a digital business card implements the steps of the above-mentioned method for evaluating the credibility of a digital business card when executed by the processor.

[0032] According to a fourth aspect of the present invention, a computer storage medium is provided, wherein a program for evaluating the credibility of a digital business card is stored on the computer storage medium, and when the program for evaluating the credibility of a digital business card is executed by a processor, the steps of the above-mentioned method for evaluating the credibility of a digital business card are implemented.

[0033] Compared with the prior art, the technical solution provided by the embodiments of the present invention can achieve at least the following beneficial effects:

[0034] The present invention's method for assessing the credibility of digital business card identity information employs a dynamic approach that relies neither on pre-recorded identity information nor on manual review and judgment. By applying targeted credit assessment methods at three key points in the digital business card lifecycle, this new approach dynamically calculates the credibility of identity information.

[0035] The method for evaluating the credibility of digital business card identity information of the present invention adopts a static single evaluation feature that is different from the traditional method. This method is a dynamic multiple evaluation, which triggers dynamic evaluations when the business card is created, edited, and exchanged. Specifically, when a digital business card user registers, the basic identity information of the business card owner is verified on the basis of three lists: black, white, and gray, and a "user identity basic information evaluation" is performed; when a digital business card is created / edited, the collaborative filtering concept is applied to perform a "business card element information evaluation" on the main business card content elements in four dimensions; when digital business cards are exchanged, a "business card distribution weight evaluation" is performed on the distribution relationship of the business cards. Then, the "digital business card credibility" is calculated by weighting the above evaluation points. The advantage of this method is that it does not require human intervention, greatly reduces the cost of identity credibility evaluation, and is suitable for dynamically evaluating the credibility of identity information of massive digital business cards. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings of the embodiments will be briefly introduced below. Obviously, the drawings in the following description only relate to some embodiments of the present invention, but are not intended to limit the present invention.

[0037] Figure 1 FIG. 1 is a flow chart illustrating a method for evaluating the credibility of a digital business card according to an embodiment of the present invention.

[0038] Figure 2 FIG. 1 is a schematic diagram illustrating a process of evaluating business card distribution weights according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in the present patent application specification and claims do not denote any order, quantity, or importance, but are merely used to distinguish different components. Similarly, terms such as "a" or "an" do not denote a limitation of quantity, but rather denote the presence of at least one.

[0041] Figure 1 FIG. 1 is a flow chart illustrating a method for evaluating the credibility of a digital business card according to an embodiment of the present invention.

[0042] Digital business cards contain identity information such as Figure 1 As shown, the method for evaluating the credibility of a digital business card includes the following steps:

[0043] S1. Evaluation of basic user identity information. Before creating a digital business card, the user must first register. At this time, the mobile phone number is first verified to confirm that the user is actually using the registered mobile phone number. The mobile phone number is verified, and a query is initiated to the third-party data provider including the basic operator to determine whether the mobile phone number is on the whitelist, blacklist, or graylist, so as to obtain the basic evaluation information of the registered user identity of the digital business card, perform the basic user identity information evaluation, and calculate the basic user identity information score F0.

[0044] Among them, the whitelist is a list of users whose identity information is confirmed to be authentic and reliable, the blacklist is a list of users who are confirmed to be scam calls or false identity information, and the graylist is a list of users who are confirmed to be suspected of harassment or fraud.

[0045] S2. Business card element information evaluation. During the digital business card creation / editing phase, the credibility of the business card element information is evaluated based on the collaborative filtering algorithm. The similarity between the elements between the business cards is first calculated, and then the credibility of the business card to be evaluated is predicted by analyzing the business cards with similar elements. The business card element evaluation score F1 is calculated. The elements of a digital business card include one or more of: name, mobile phone number, email address, company, address, position, and WeChat.

[0046] S3. Business card distribution weight evaluation. When digital business cards are exchanged, the number of forwarding times and credibility of the business card forwarder are analyzed to predict the credibility of the business card to be evaluated and calculate the business card distribution weight evaluation score F2.

[0047] S4. Calculation of the credibility of the digital business card. Each time the digital business card is displayed, the credibility C of the digital business card based on the above three evaluation results is calculated in real time by weighted calculation, and output and complete the prompt to the digital business card recipient.

[0048] The present invention's method for assessing the credibility of digital business card identity information employs a dynamic approach that relies neither on pre-recorded identity information nor on manual review and judgment. By applying targeted credit assessment methods at three key points in the digital business card lifecycle, this new approach dynamically calculates the credibility of identity information.

[0049] According to one or some embodiments of the present invention, in step S1, the user identity basic information score is F0, and the calculation formula is:

[0050]

[0051] Among them, when the user name and phone number of the digital business card registered user are verified to be true and valid through whitelist review, the evaluation score is 100.

[0052] If the user's name and phone number fail verification and are blacklisted and identified as a fraudulent call, the evaluation score is 0.

[0053] When a user's mobile phone number hits the gray list, it will be scored in a stepped manner according to the risk level of formula (1).

[0054] According to one or some embodiments of the present invention, in step S2, elements of the digital business card including category, company, address, and position are selected for modeling. Step S2 includes the following steps:

[0055] S21. Preprocessing of company and address names: remove common words such as "China" representing the country and "XX Lane XX No." on the address sign.

[0056] S22. Classify the company's industry elements, segment the company name, match the industry information based on the keywords in the company name, and correspond to the industry classification. This can be matched to the base table of industry classification; the industry base table is shown in the following table:

[0057]

[0058]

[0059] The industry base table includes 26 major industry categories. The values ​​in the table are the correlation coefficients between two industries that intersect horizontally and vertically. -1 indicates a perfect negative correlation, and 1 indicates a perfect positive correlation. The larger the value, the higher the correlation. The industry base table is derived from external basic data.

[0060] The industry classification matching process is shown in the following industry classification matching table: (split the word according to the user name and find the keyword matching industry category)

[0061]

[0062] S23. Build word vectors. After segmenting the company name, address, and position, build a four-dimensional word vector. The four-dimensional word vector includes: (

[0064] Industry Classification,

[0065] (Company name participle 1, Company name participle 2…),

[0066] (address participle 1, address participle 2…),

[0067] (Position participle 1, Position participle 2…) )

[0069] S24. Training the model: Using the word2vec model of the Gensim package in Python, input data for each individual dimension of "company name, address, and position" for training and modeling, and obtain the word segmentation similarity in each dimension.

[0070] "Industry Classification" obtains the correlation coefficient based on the industry classification matching table.

[0071] The value range of word segmentation similarity and industry classification is [-1, 1], where -1 indicates a complete negative correlation and 1 indicates a complete positive correlation.

[0072] S25. Calculate the similarity. For the two four-dimensional word vectors belonging to the two digital business cards, the similarity can be compared in each dimension, and the overall similarity can be obtained by weighted average. Let the similarity of each dimension be R i , then the formula for the overall similarity R is:

[0073]

[0074] S26. Calculate the business card element evaluation score, apply the collaborative filtering strategy, find the top 100 evaluated business cards that are most similar to the current digital business card to be evaluated, and obtain the business card element evaluation score of the current digital business card to be evaluated by taking the weighted average of the business card element evaluation scores of each business card in this result set.

[0075] Business card element evaluation score F1 is:

[0076]

[0077] Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R i In the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

[0078] Figure 2 FIG. 1 is a schematic diagram illustrating a process of evaluating business card distribution weights according to an embodiment of the present invention.

[0079] like Figure 2 As shown in the figure, A, B, and C represent three different user nodes, that is, three business card users who have created different numbers of digital business cards. The Count value represents the number of times each user node has made outbound calls to other user nodes, that is, the number of times a business card has been forwarded. For example, Count(AB) represents the number of times user A has forwarded user B's business card, and Count(BA) represents the number of times user B has forwarded user A's business card.

[0080] Assume that the “business card distribution weight evaluation score” of a digital business card of user A is F2. The credibility of other user nodes that forward this business card is C i , when the user node has multiple business cards, take the average credibility of all the user's business cards; Count i represents the number of times the i-th user forwarded A's business card among the n users who forwarded A's business card. Then in step S3, the calculation formula of F2 is:

[0081]

[0082] Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count i represents the number of times the i-th user forwarded the user's digital business card among the n users who forwarded the business card. This formula indicates that to calculate the card distribution weight evaluation score for a digital business card of user A, the credibility scores of all other users who forwarded the card are taken and weighted by the number of forwarding times.

[0083] According to one or some embodiments of the present invention, in step S4, the initial score F0 of the user dimension is defined as 30%, the review score F1 of the business card dimension is defined as 40%, and the weighted score F2 based on business card distribution is defined as 30%. The credibility of the digital business card is:

[0084] C=F0*0.3+F1*0.4+F2*0.3 (5)

[0085] The method for evaluating the credibility of digital business card identity information of the present invention adopts a static single evaluation feature that is different from the traditional method. This method is a dynamic multiple evaluation, which triggers dynamic evaluations when the business card is created, edited, and exchanged. Specifically, when a digital business card user registers, the basic identity information of the business card owner is verified on the basis of three lists: black, white, and gray, and a "user identity basic information evaluation" is performed; when a digital business card is created / edited, the collaborative filtering concept is applied to perform a "business card element information evaluation" on the main business card content elements in four dimensions; when digital business cards are exchanged, a "business card distribution weight evaluation" is performed on the distribution relationship of the business cards. Then, the "digital business card credibility" is calculated by weighting the above evaluation points. The advantage of this method is that it does not require human intervention, greatly reduces the cost of identity credibility evaluation, and is suitable for dynamically evaluating the credibility of identity information of massive digital business cards.

[0086] According to a second aspect of the present invention, a device for evaluating the credibility of a digital business card is provided, comprising: a user identity basic information evaluation module, a business card element information evaluation module, a business card distribution weight evaluation module, and a digital business card credibility calculation module.

[0087] Before creating a digital business card, the user must first register. At this time, the mobile phone number is first verified to confirm that the user is actually using the registered mobile phone number; the user identity basic information evaluation module is used to verify the mobile phone number and initiate a query to the third-party data provider including the basic operator based on the mobile phone number to determine whether it is on the whitelist, blacklist, or graylist, thereby obtaining the basic evaluation information of the registered user identity of the digital business card, performing the user identity basic information evaluation, and calculating the user identity basic information score F0.

[0088] Among them, the whitelist is a list of users whose identity information is confirmed to be authentic and reliable, the blacklist is a list of users who are confirmed to be scam calls or false identity information, and the graylist is a list of users who are confirmed to be suspected of harassment or fraud.

[0089] The business card element information evaluation module is used to evaluate the credibility of business card element information based on the collaborative filtering algorithm during the creation / editing of digital business cards. It first calculates the similarity of elements between business cards, and then predicts the credibility of the business card to be evaluated by analyzing business cards with similar elements, and calculates the business card element evaluation score F1. The elements of a digital business card include: name, mobile phone number, email address, company, address, position, WeChat, or one or more of them.

[0090] When digital business cards are exchanged, the business card distribution weight evaluation module analyzes the forwarding times and credibility of the business card forwarder, and accordingly predicts the credibility of the business card to be evaluated, and calculates the business card distribution weight evaluation score F2.

[0091] The digital business card credibility calculation module is used to calculate the digital business card credibility C based on the above three evaluation results in real time each time the digital business card is displayed, and output and complete the prompt to the digital business card recipient.

[0092] According to one or some embodiments of the present invention, the business card element information evaluation module includes: a company address name preprocessing unit, a company element industry classification unit, a word vector construction unit, a model training unit, a similarity calculation unit and a business card element evaluation calculation unit.

[0093] The company address name preprocessing unit is used to cut off the beginning and end of the company name and address and remove common words therein.

[0094] The company element industry classification unit is used to segment the company name, match industry information based on the keywords in the company name, and correspond to the industry classification.

[0095] The word vector construction unit is used to segment the company name, address, and position, and then construct a four-dimensional word vector including industry classification, company name segmentation, address segmentation, and position segmentation.

[0096] The training model unit uses the word2vec model of the Gensim package in Python to input data training modeling on each individual dimension of "company name, address, and position" to obtain the word segmentation similarity on each dimension.

[0097] The similarity calculation unit is used to compare the similarity of the two four-dimensional word vectors belonging to the two digital business cards in each dimension, and the overall similarity is obtained by weighted average method, where the similarity of each dimension is R i , the formula for the overall similarity R is:

[0098]

[0099] Calculate the business card element evaluation score unit, apply the collaborative filtering strategy, find the top 100 evaluated business cards that are most similar to the current digital business card to be evaluated, and obtain the business card element evaluation score of the current digital business card to be evaluated by taking the weighted average of the business card element evaluation scores of each business card in this result set.

[0100] Business card element evaluation score F1 is:

[0101]

[0102] Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R iIn the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

[0103] According to one or some embodiments of the present invention, the calculation formula for F2 performed by the business card distribution weight evaluation module is:

[0104]

[0105] Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count i Indicates the number of times the i-th user forwarded the digital business card among the n users who forwarded the digital business card of the user.

[0106] According to one or some embodiments of the present invention, for example, user A registers and uses a digital business card. In the "User Identity Basic Information Evaluation", his phone number hits the whitelist, and the value of F0 calculated by formula (1) is 100.

[0107] User A creates a digital business card. The business card information includes:

[0108] Company Name: ** Company

[0109] Address: No. **, ** Road, ** District, ** City

[0110] Position: Technical Manager

[0111] Constructing a four-dimensional word vector:

[0112] ((communication,

[0113] (Telecom, Co., Ltd., Shanghai Branch),

[0114] (Shanghai, Pudong New Area, Yanggao South Road),

[0115] (Technical Department, Manager)

[0116] Through model calculation, the average evaluation score of the top 100 most similar business cards is taken, that is, according to formula (3) in "Business Card Element Information Evaluation", F1 = 87.37.

[0117] On a certain day, user A's digital business card was accessed 5 times by user B (credibility 70) and 3 times by user C (credibility 92). Therefore, the "business card distribution weight evaluation" of user A on that day is calculated according to formula (4): F2 = (70*5+92*3) / (5+3) = 78.25.

[0118] On that day, the credibility of the digital business card of user A was calculated according to formula (5): C = F0*0.3+F1*0.4+F2*0.3 = 88.42.

[0119] The present invention's method for dynamically assessing the credibility of digital business card identity information initially uses a "basic user identity information assessment" to determine a user review score (F0). During the creation of a digital business card, a "business card element information assessment" is used to determine a review score (F1). During the distribution of a digital business card, a "business card distribution weight assessment" is used to determine a review score (F2). These three scores are combined to form the "digital business card credibility" (C), with F0 accounting for 30%, F1 for 70%, and F2 for 30%.

[0120] The method of "basic user identity information evaluation" in the digital business card of the present invention verifies the authenticity of the user identity through the mobile phone number and evaluates the credibility of the user identity through the "white list", "black list" and "grey list".

[0121] The method of "business card element information evaluation" in the digital business card of the present invention uses the "company name, address, and position" in the digital business card as data elements for modeling, extracts industry classifications, constructs word vectors, and trains the model. The similarity of business cards is compared through the model, and the evaluation scores of the top 100 reviewed users who are most similar to the "user to be reviewed" are weighted averaged as their score.

[0122] The method of "business card distribution weight evaluation" in the digital business card of the present invention constructs a directed graph of user forwarding business cards, takes the credibility scores of all other users who forwarded the business card, and takes a weighted average of the forwarding times as the score.

[0123] The business card elements are modeled in four dimensions, and the collaborative filtering method is used to calculate other similar digital business cards, and the "business card element evaluation score" is obtained after weighted calculation; the business card distribution relationship is calculated, and the credibility of the business card forwarder and the number of forwarding times are weighted to obtain the "business card distribution weight evaluation score"; a calculation formula for the "digital business card credibility" based on the "basic information evaluation score", "business card element evaluation score" and "business card distribution weight evaluation score" is given.

[0124] According to another aspect of the present invention, a device for evaluating the credibility of a digital business card is provided, comprising: a memory, a processor, and a program for evaluating the credibility of a digital business card stored in the memory and executable on the processor, wherein the program for evaluating the credibility of a digital business card implements the steps of the above-mentioned method for evaluating the credibility of a digital business card when executed by the processor.

[0125] According to the present invention, a computer storage medium is also provided.

[0126] The computer storage medium stores a program for evaluating the credibility of a digital business card. When the program for evaluating the credibility of a digital business card is executed by the processor, the steps of the above-mentioned method for evaluating the credibility of a digital business card are implemented.

[0127] The method implemented when the program for evaluating the credibility of a digital business card running on the processor is executed can refer to the various embodiments of the method for evaluating the credibility of a digital business card of the present invention, and will not be described in detail here.

[0128] The present invention also provides a computer program product.

[0129] The computer program product of the present invention includes a program for evaluating the credibility of a digital business card. When the program for evaluating the credibility of a digital business card is executed by a processor, the steps of the method for evaluating the credibility of a digital business card as described above are implemented.

[0130] The method implemented when the program for evaluating the credibility of a digital business card running on the processor is executed can refer to the various embodiments of the method for evaluating the credibility of a digital business card of the present invention, and will not be described in detail here.

[0131] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0132] The above description is merely an exemplary embodiment of the present invention and is not intended to limit the scope of protection of the present invention. The scope of protection of the present invention is determined by the appended claims.

Claims

1. A method for evaluating the credibility of a digital business card, wherein the digital business card contains identity information, the method comprising the following steps: S1. User identity basic information assessment. Before creating a digital business card, the user first registers. At this time, the mobile phone number is first verified to confirm that the user is actually using the registered mobile phone number. Verify the mobile phone number and initiate a query to the third-party data provider including the basic operator to determine whether it is on the whitelist, blacklist or greylist based on the mobile phone number, thereby obtaining the basic evaluation information of the registered user identity of the digital business card, evaluating the basic information of the user identity, and calculating the basic information score F0 of the user identity. in, The whitelist is a list of users whose identity information is confirmed to be authentic, the blacklist is a list of users who are confirmed to be scam calls or false identity information, and the graylist is a list of users who are confirmed to be suspected of harassment or fraud; S2, business card element information evaluation, in the digital business card creation / editing stage, the credibility of the business card element information is evaluated based on the collaborative filtering algorithm, firstly the similarity of the elements between the business cards is calculated, then the credibility of the business card to be evaluated is predicted by analyzing the business cards with similar elements, and the business card element evaluation score F1 is calculated, where the elements of the digital business card include: one or more of the name, mobile phone number, email address, company, address, position, and WeChat; S3, business card distribution weight evaluation, when digital business cards are exchanged, by analyzing the forwarding times and credibility of the business card forwarder, the credibility of the business card to be evaluated is predicted, and the business card distribution weight evaluation score F2 is calculated; S4. Calculation of the credibility of the digital business card. The credibility C of the digital business card based on the above three evaluation results is calculated in real time and outputted to complete the prompt to the digital business card recipient each time the digital business card is displayed.

2. The method for evaluating the credibility of a digital business card as claimed in claim 1, wherein: In step S1, the user identity basic information score is F0, and the calculation formula is: Among them, if the user name and phone number of the digital business card registered user are verified to be authentic and valid by the whitelist, the evaluation score is 100; If the user's name and phone number fail to pass the verification and are blacklisted as a fraudulent call, the evaluation score is 0; When a user's mobile phone number hits the grey list, it will be scored in a stepped manner according to the risk level of formula (1).

3. The method for evaluating the credibility of a digital business card as claimed in claim 1, wherein: In step S2, the elements of the digital business card including category, company, address, and position are selected for modeling, including the following steps: S21, preprocessing of company and address names, cutting off the beginning and the end of company names and addresses, and removing common words; S22. Classify the company's elements by industry, segment the company's name, match the industry information according to the keywords in the company's name, and correspond to the industry classification; S23, construct word vectors, after segmenting the company name, address, and position, construct a four-dimensional word vector, the four-dimensional word vector includes: Industry classification, Company name participle 1, Company name participle 2…, Address participle 1, address participle 2..., Position participle 1, Position participle 2… S24. Training the model: using the word2vec model of the Gensim package in Python, input data for training and modeling on each individual dimension of "company name, address, and position" to obtain the word segmentation similarity on each dimension; S25. Calculate the similarity. For two four-dimensional word vectors belonging to two digital business cards, the similarity can be compared in each dimension, and the overall similarity can be obtained by weighted average method. Let the similarity of each dimension be R i , then the formula for the overall similarity R is: S26, calculating the business card element evaluation score, applying the collaborative filtering strategy, finding the first 100 evaluated business cards that are most similar to the current digital business card to be evaluated, and obtaining the business card element evaluation score of the current digital business card to be evaluated by weighted average of the business card element evaluation scores of each business card in the result set. Business card element evaluation score F1 is: Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R i In the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

4. The method for evaluating the credibility of a digital business card as claimed in claim 1, wherein: In step S3, the calculation formula of F2 is: Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count i Indicates the number of times the i-th user among the n users who forwarded the digital business card of the user forwarded the digital business card.

5. The method for evaluating the credibility of a digital business card as claimed in claim 1, wherein: In step S4, it is defined that the initial score F0 of the user dimension accounts for 30%, the review score F1 of the business card dimension accounts for 40%, and the weight score F2 based on business card distribution accounts for 30%. Then the credibility of the digital business card is: C=F0*0.3+F1*0.4+F2*0.3 (5).

6. A device for evaluating the credibility of a digital business card, comprising: The user identity basic information evaluation module is used to verify the mobile phone number before creating a digital business card. The user first registers and verifies the mobile phone number to confirm that the user actually uses the registered mobile phone number. The user identity basic information evaluation module is used to verify the mobile phone number and to query the third-party data provider including the basic operator whether the mobile phone number is on the white list, black list or grey list, thereby obtaining the basic evaluation information of the registered user identity of the digital business card, evaluating the user identity basic information and calculating the user identity basic information score F0. The whitelist is a list of users whose identity information is confirmed to be authentic, the blacklist is a list of users whose calls are confirmed to be fraudulent or whose identity information is false, and the greylist is a list of users who are confirmed to be suspected of harassment or fraud. A business card element information evaluation module is used to evaluate the credibility of business card element information based on a collaborative filtering algorithm during the creation / editing of a digital business card. The similarity between elements between business cards is first calculated, and then the credibility of the business card to be evaluated is predicted by analyzing business cards with similar elements, and a business card element evaluation score F1 is calculated. The elements of a digital business card include one or more of: name, mobile phone number, email address, company, address, position, and WeChat. A business card distribution weight evaluation module, when digital business cards are exchanged, the business card distribution weight evaluation module predicts the credibility of the business card to be evaluated by analyzing the forwarding times and credibility of the business card forwarder, and calculates the business card distribution weight evaluation score F2; The digital business card credibility calculation module is used to calculate the digital business card credibility C based on the above three evaluation results in real time every time the digital business card is displayed, and output and complete the prompt to the digital business card recipient.

7. The method for evaluating the credibility of a digital business card as claimed in claim 6, wherein: The business card element information evaluation module includes: The company and address name preprocessing unit is used to remove the beginning and end of the company name and address and remove common words; The company element industry classification unit is used to segment the company name, match the industry information according to the keywords in the company name, and correspond to the industry classification; Construct a word vector unit to segment the company name, address, and position, and then construct a four-dimensional word vector including industry classification, company name segmentation, address segmentation, and position segmentation; The training model unit uses the word2vec model of the Gensim package in Python to input data for training and modeling on each individual dimension of "company name, address, and position" to obtain the word segmentation similarity on each dimension; The similarity calculation unit is used to compare the similarity of two four-dimensional word vectors belonging to two digital business cards in each dimension, and obtain the overall similarity by weighted average method, where the similarity of each dimension is R i , the formula for the overall similarity R is: Calculate the business card element evaluation unit, apply the collaborative filtering strategy, find the top 100 evaluated business cards that are most similar to the current digital business card to be evaluated, and obtain the business card element evaluation score of the current digital business card to be evaluated by taking the weighted average of the business card element evaluation scores of each business card in this result set. Business card element evaluation score F1 is: Among them, G i is the business card element evaluation score of the first 100 business cards that are most similar to the digital business card to be evaluated, and the similarity between them is R i In the initial state, when there is no similar business card to the digital business card to be evaluated, set F1 = F0.

8. The method for evaluating the credibility of a digital business card as claimed in claim 6, wherein: The calculation formula of F2 performed by the business card distribution weight evaluation module is: Among them, the credibility of other user nodes forwarding the digital business card is C i , when the user node has multiple business cards, C i Take the average credibility of all business cards of the user; Count i Indicates the number of times the i-th user among the n users who forwarded the digital business card of the user forwarded the digital business card.

9. An electronic device, comprising: A memory, a processor, and a program for evaluating the credibility of a digital business card stored in the memory and executable on the processor, wherein the program for evaluating the credibility of a digital business card, when executed by the processor, implements the steps of the method for evaluating the credibility of a digital business card as claimed in any one of claims 1 to 5.

10. A computer storage medium, wherein: The computer storage medium stores a program for evaluating the credibility of a digital business card. When the program for evaluating the credibility of a digital business card is executed by a processor, the steps of the method for evaluating the credibility of a digital business card as claimed in any one of claims 1 to 5 are implemented.

Images