Electronic business card recommendation method, device, equipment and computer-readable storage medium

Abstract

The present invention discloses an electronic business card recommendation method, apparatus, device, and computer-readable storage medium, relating to the field of financial technology. The method comprises: upon receiving an electronic business card recommendation request, obtaining target input data and an electronic business card to be recommended according to the electronic business card recommendation request; obtaining first enterprise data of a target enterprise and constructing an industry relationship map based on the first enterprise data; obtaining a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model; and recommending the user to be recommended based on the recommendation score of each electronic business card to be recommended. The present invention can achieve accurate electronic business card recommendations and improve the effectiveness of electronic business card recommendations.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology of financial technology (Fintech), and in particular to an electronic business card recommendation method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of computer technology, more and more technologies are being applied in the financial field. The traditional financial industry is gradually transforming into financial technology (Fintech). However, due to the security and real-time requirements of the financial industry, higher requirements are also placed on technology.

[0003] In modern business, business cards have always served as an important bridge for introducing oneself, making business partners, and expanding and maintaining personal connections. With the online evolution of social scenarios and the development of industrial Internet, corporate social networking has gradually moved from offline to online, and electronic business cards have come into being.

[0004] Existing methods for exchanging electronic business cards primarily rely on direct, near-field exchanges, passively accepting business cards from other users, or recommending them based on friendships. These methods are inefficient and inaccurate in exchanging one's own business cards, and they also fail to leverage the advantages of the industrial internet to obtain business cards of interest to identify potential partners. Therefore, achieving accurate electronic business card recommendations and improving their effectiveness are pressing challenges. Summary of the Invention

[0005] The main purpose of the present invention is to provide an electronic business card recommendation method, device, equipment and computer-readable storage medium, aiming to achieve accurate electronic business card recommendation and improve the recommendation effect of electronic business cards.

[0006] To achieve the above-mentioned object, the present invention provides an electronic business card recommendation method, which comprises:

[0007] Upon receiving an electronic business card recommendation request, acquiring target input data and the electronic business card to be recommended according to the electronic business card recommendation request;

[0008] Acquire first enterprise data of a target enterprise, and construct an industry relationship map based on the first enterprise data;

[0009] Obtaining a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model;

[0010] The user to be recommended is recommended according to the recommendation score of each electronic business card to be recommended.

[0011] Optionally, the step of obtaining first enterprise data of the target enterprise and constructing an industry relationship map based on the first enterprise data includes:

[0012] Acquire first enterprise data of a target enterprise, and extract a first target feature from the first enterprise data to obtain first feature data;

[0013] Combine the target enterprises in pairs, process the first feature data according to the first combination results, and obtain a first feature vector for each first combination;

[0014] Inputting each first feature vector into a pre-trained industry relationship classification model to obtain an industry relationship classification result of each first combination;

[0015] The industry relationship map is generated according to the industry relationship classification result.

[0016] Optionally, before the step of inputting each first feature vector into a pre-trained industry relationship classification model to obtain the industry relationship classification results of each first combination, the step further includes:

[0017] Acquire second enterprise data of the sample enterprise, and extract the first target feature from the second enterprise data to obtain second feature data;

[0018] The sample enterprises are combined in pairs, the second characteristic data are processed according to the second combination results to obtain the second characteristic vectors of each second combination, and each second combination is labeled;

[0019] Constructing a first training sample according to the second feature vectors and the labeling results of each second combination;

[0020] The preset industry relationship classification model is trained using the first training sample to obtain the pre-trained industry relationship classification model.

[0021] Optionally, before the step of obtaining the recommendation score of each electronic business card to be recommended based on the target input data, the industry relationship map and the pre-trained score prediction model, the method further includes:

[0022] Obtaining third user data, third business card data, and third behavior data of the sample user;

[0023] Obtaining an operation business card of the sample user according to the third behavior data, and obtaining operation business card data and operation user data corresponding to the operation business card;

[0024] Obtaining the degree of association between the operation business card and the sample business card of the sample user based on the industry relationship graph;

[0025] extracting the second target feature from the third user data, the third business card data, the operation business card data, and the operation user data to obtain third feature data;

[0026] Processing the third feature data, obtaining a third feature vector according to the processing result and the correlation degree, and constructing a second training sample according to the third feature vector;

[0027] The preset score prediction model is trained using the second training sample to obtain the pre-trained score prediction model.

[0028] Optionally, upon receiving the electronic business card recommendation request, the step of acquiring target input data and the electronic business card to be recommended according to the electronic business card recommendation request includes:

[0029] Upon receiving an electronic business card recommendation request, obtaining user information to be recommended according to the electronic business card recommendation request, the user information to be recommended including a first user identifier, first user data, and first business card data of the user to be recommended;

[0030] According to a preset business card list, the electronic business card to be recommended corresponding to the first user identifier is obtained, and the second user data and second business card data corresponding to the electronic business card to be recommended are obtained; wherein the target input data includes the first user data, the first business card data, the second user data and the second business card data.

[0031] Optionally, before the step of obtaining the electronic business card to be recommended corresponding to the first user identifier according to the preset business card list and obtaining the second user data and second business card data corresponding to the electronic business card to be recommended, the method further includes:

[0032] Obtaining a fourth user identifier, fourth user data, fourth business card data, and fourth behavior data of the target user;

[0033] Obtaining a first electronic business card set corresponding to each target user according to the fourth user data, the fourth business card data and a first preset algorithm;

[0034] Obtaining a second electronic business card set corresponding to each target user according to the fourth behavior data and a second preset algorithm;

[0035] Obtaining the intersection of the first electronic business card set and the second electronic business card set corresponding to each target user to obtain the electronic business card of interest to each target user;

[0036] The preset business card list is constructed based on the electronic business card of interest and the fourth user identifier.

[0037] Optionally, the step of obtaining a first electronic business card set corresponding to each target user according to the fourth user data, the fourth business card data and a first preset algorithm includes:

[0038] Obtaining a user tag of each target user according to the fourth user data and the fourth business card data;

[0039] Calculating user similarity between target users based on the user tags;

[0040] Determine similar users corresponding to each target user based on the user similarity and a preset threshold range;

[0041] A first electronic business card set of each target user is obtained according to the electronic business cards of the similar users.

[0042] Optionally, the step of obtaining a second electronic business card set corresponding to each target user according to the fourth behavior data and a second preset algorithm includes:

[0043] Obtaining historically interested business cards of each target user according to the fourth behavior data;

[0044] Counting each of the target user's historically interested business cards, and constructing a business card similarity matrix based on the statistical results;

[0045] Calculating the business card similarities between the historically interested business cards based on the business card similarity matrix, and calculating the interest value of each target user in each historically interested business card based on the business card similarities and the historically interested business cards of each target user;

[0046] A second electronic business card set corresponding to each target user is obtained according to the business card similarity and the interest value.

[0047] Optionally, the step of recommending the user to be recommended according to the recommendation score of each electronic business card to be recommended includes:

[0048] sorting the electronic business cards to be recommended according to the recommendation scores of the electronic business cards to be recommended;

[0049] The electronic business cards to be recommended are screened according to the sorting result and preset screening rules to determine a target recommended electronic business card, and the target recommended electronic business card is recommended to the user to be recommended.

[0050] In addition, to achieve the above-mentioned purpose, the present invention further provides an electronic business card recommendation device, the electronic business card recommendation device comprising:

[0051] A first acquisition module is configured to acquire target input data according to the electronic business card recommendation request upon receiving the electronic business card recommendation request;

[0052] A second acquisition module is used to acquire first enterprise data of a target enterprise and construct an industry relationship map based on the first enterprise data;

[0053] A score determination module, configured to obtain a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model;

[0054] The business card recommendation module is used to recommend the user to be recommended according to the recommendation score of each electronic business card to be recommended.

[0055] In addition, to achieve the above-mentioned purpose, the present invention also provides an electronic business card recommendation device, which includes: a memory, a processor, and an electronic business card recommendation program stored on the memory and capable of running on the processor. When the electronic business card recommendation program is executed by the processor, the steps of the electronic business card recommendation method described above are implemented.

[0056] In addition, to achieve the above purpose, the present invention also provides a computer-readable storage medium, which stores an electronic business card recommendation program. When the electronic business card recommendation program is executed by a processor, it implements the steps of the electronic business card recommendation method described above.

[0057] The present invention provides an electronic business card recommendation method, device, equipment, and computer-readable storage medium. When an electronic business card recommendation request is received, target input data and the electronic business card to be recommended are obtained according to the electronic business card recommendation request; first enterprise data of the target enterprise is obtained, and an industry relationship map is constructed based on the first enterprise data; recommendation scores of each electronic business card to be recommended are obtained according to the target input data, the industry relationship map, and a pre-trained score prediction model; and recommendations are made to the users to be recommended based on the recommendation scores of each electronic business card to be recommended. Through the above-mentioned method, the present invention combines multiple algorithms to pre-construct an industry relationship map, first obtains the target input data and the electronic business card to be recommended based on the electronic business card recommendation request, then combines the industry relationship map with the score prediction model to obtain the recommendation score of the electronic business card to be recommended, and then recommends the electronic business card based on the recommendation score. This can achieve intelligent and accurate recommendation of electronic business cards, improve the accuracy of electronic business card recommendation results and the exchange efficiency of electronic business cards, and at the same time, can also expand the company's visibility and help users discover potential business partners. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 A schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention;

[0059] Figure 2 This is a flow chart of a first embodiment of the electronic business card recommendation method of the present invention;

[0060] Figure 3 This is a flow chart of a second embodiment of the electronic business card recommendation method of the present invention;

[0061] Figure 4 This is a flow chart of a third embodiment of the electronic business card recommendation method of the present invention;

[0062] Figure 5 This is a flow chart of a fourth embodiment of the electronic business card recommendation method of the present invention;

[0063] Figure 6 This is a schematic diagram of the functional modules of the first embodiment of the electronic business card recommendation device of the present invention.

[0064] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0065] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] Reference Figure 1 , Figure 1 This is a schematic diagram of the device structure of the hardware operating environment involved in the embodiment of the present invention.

[0067] The electronic business card recommendation device in the embodiment of the present invention may be a smart phone, or may be a terminal device such as a PC (Personal Computer), a tablet computer, a portable computer, or a server.

[0068] like Figure 1 As shown, the electronic business card recommendation device may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 1003 may optionally include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed RAM memory, or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may optionally also be a storage device independent of the aforementioned processor 1001.

[0069] Those skilled in the art will understand that Figure 1The electronic business card recommendation device structure shown in the figure does not constitute a limitation on the electronic business card recommendation device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0070] like Figure 1 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an electronic business card recommendation program.

[0071] exist Figure 1 In the terminal shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client and communicate data with the client; and the processor 1001 can be used to call the electronic business card recommendation program stored in the memory 1005 and execute the various steps of the following electronic business card recommendation method.

[0072] Based on the above hardware structure, various embodiments of the electronic business card recommendation method of the present invention are proposed.

[0073] The invention provides an electronic business card recommendation method.

[0074] Reference Figure 2 , Figure 2 This is a flow chart of the first embodiment of the electronic business card recommendation method of the present invention.

[0075] In this embodiment, the electronic business card recommendation method includes:

[0076] Step S10, upon receiving an electronic business card recommendation request, obtaining target input data and an electronic business card to be recommended according to the electronic business card recommendation request;

[0077] The electronic business card recommendation method of this embodiment is implemented by an electronic business card recommendation device, which is described using a server as an example.

[0078] In this embodiment, upon receiving an electronic business card recommendation request, target input data and an electronic business card to be recommended are obtained according to the electronic business card recommendation request, wherein the target input data includes first user data, first business card data, second user data, and second business card data. The acquisition process is as follows: first, information about the user to be recommended is obtained according to the electronic business card recommendation request, wherein the information about the user to be recommended includes the first user identifier, first user data, and first business card data of the user to be recommended. Then, the electronic business card to be recommended corresponding to the first user identifier is obtained according to a preset business card list, and the second user data and second business card data corresponding to the electronic business card to be recommended are obtained. The specific acquisition process can be referred to in the fourth embodiment described below and will not be described in detail here.

[0079] Step S20: obtaining first enterprise data of the target enterprise, and constructing an industry relationship map based on the first enterprise data;

[0080] Obtain the first enterprise data of the target enterprise, and construct an industry relationship map based on the first enterprise data. Among them, the target enterprise can be the enterprise of the user who has completed registration and created an electronic business card in the electronic business card recommendation applet or electronic business card recommendation software. The types of the first enterprise data include but are not limited to: annual reports of enterprises, industry reports, satellite remote sensing data, social network data, industrial and commercial tax data, industry classification dictionaries and other data. The first target feature may include but is not limited to: the main products of the enterprise, upstream companies of the enterprise, downstream companies of the enterprise, region, enterprise scale, popularity, tax grade, annual tax amount, industry classification, etc. The first feature data is the first target feature in the first enterprise data and its corresponding value or information. The process of constructing the industry relationship map can refer to the second embodiment below and will not be repeated here.

[0081] It should be noted that the execution order of step S10 and step S20 is not particular.

[0082] Step S30, obtaining a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model;

[0083] Then, based on the target input data (i.e., the second user data, the second business card data, the first user data, and the first business card data), the industry relationship map, and the pre-trained score prediction model, a recommendation score for each electronic business card to be recommended is obtained. The training process of the score prediction model can be referred to in the third embodiment below and will not be described in detail here.

[0084] The specific process for obtaining the recommendation score for each electronic business card to be recommended is as follows: first, the target features from the second user data, the second business card data, the first user data, and the first business card data are extracted to obtain target feature data, where the target features include but are not limited to: gender, age, place of origin, position, company name, and company address. Simultaneously, the corresponding second industry is determined based on the second business card data, and the corresponding first industry is determined based on the first business card. The target correlation between the second industry and the first industry is obtained based on the industry relationship map. These target feature data are then processed, and the corresponding target feature vector is obtained based on the processing results and the target correlation. The specific processing method can refer to the process for obtaining the third feature vector. The target feature vector is then input into a pre-trained score prediction model to obtain the recommendation score for each electronic business card to be recommended.

[0085] Step S40: recommending the user to be recommended according to the recommendation score of each electronic business card to be recommended.

[0086] After obtaining the recommendation score of each electronic business card to be recommended, recommendations are made to the users to be recommended according to the recommendation score of each electronic business card to be recommended.

[0087] As one of the recommended methods, step S40 includes:

[0088] Step a1, sorting the electronic business cards to be recommended according to the recommendation scores of the electronic business cards to be recommended;

[0089] Step a2: screening the electronic business cards to be recommended according to the sorting result and preset screening rules, determining a target recommended electronic business card, and recommending the target recommended electronic business card to the user to be recommended.

[0090] First, the recommended electronic business cards are sorted according to their recommendation scores, for example, by descending order of score. Then, the recommended electronic business cards are filtered based on the sorting results and preset filtering rules to determine the target recommended electronic business card, and the target recommended electronic business card is recommended to the user to be recommended. The preset filtering rules are pre-set. For example, the N recommended electronic business cards with the highest recommendation scores and / or those with recommendation scores greater than a preset threshold can be filtered as the target recommended electronic business cards. When making recommendations, the target recommended electronic business cards can be sorted by recommendation score, so that users can prioritize electronic business cards that they are theoretically more interested in, thereby improving the user experience.

[0091] As another recommendation method, the recommendation order of the electronic business cards to be recommended may be determined directly according to the recommendation scores of the electronic business cards to be recommended, and then the electronic business cards to be recommended may be recommended to the users to be recommended according to the recommendation order.

[0092] An embodiment of the present invention provides an electronic business card recommendation method. When an electronic business card recommendation request is received, target input data and the electronic business card to be recommended are obtained according to the electronic business card recommendation request; first enterprise data of the target enterprise is obtained, and an industry relationship map is constructed based on the first enterprise data; a recommendation score of each electronic business card to be recommended is obtained according to the target input data, the industry relationship map, and a pre-trained score prediction model; and recommendations are made to the users to be recommended based on the recommendation scores of each electronic business card to be recommended. Through the above-mentioned method, the embodiment of the present invention combines multiple algorithms to pre-construct an industry relationship map. First, the target input data and the electronic business card to be recommended are obtained based on the electronic business card recommendation request. Then, the recommendation score of the electronic business card to be recommended is obtained by combining the industry relationship map and the score prediction model. Then, the electronic business card is recommended based on the recommendation score. This can realize intelligent and accurate recommendation of electronic business cards, improve the accuracy of electronic business card recommendation results and the exchange efficiency of electronic business cards, and at the same time, expand the company's visibility, helping users to discover potential business partners.

[0093] Furthermore, based on the above first embodiment, a second embodiment of the electronic business card recommendation method of the present invention is proposed. Figure 3 , Figure 3 This is a flow chart of the second embodiment of the electronic business card recommendation method of the present invention.

[0094] In this embodiment, step S20 includes:

[0095] Step S21, obtaining first enterprise data of a target enterprise, and extracting a first target feature from the first enterprise data to obtain first feature data;

[0096] This embodiment introduces the process of constructing an industry relationship map.

[0097] First, the first enterprise data of the target enterprise is obtained, and the first target feature in the first enterprise data is extracted to obtain the first feature data. Among them, the target enterprise can be the enterprise of the user who has completed registration and created an electronic business card in the electronic business card recommendation applet or electronic business card recommendation software. The types of the first enterprise data include but are not limited to: annual reports of enterprises, industry reports, satellite remote sensing data, social network data, industrial and commercial tax data, industry classification dictionaries and other data. The first target feature may include but is not limited to: the main products of the enterprise, upstream companies of the enterprise, downstream companies of the enterprise, region, enterprise size, popularity, tax grade, annual tax amount, industry classification, etc. The first feature data is the first target feature in the first enterprise data and its corresponding value or information. The extraction of the first target feature can be based on regular matching. For example, for the annual tax amount, the regular matching method can be used to match the industrial and commercial tax data to obtain the value corresponding to the "annual tax amount".

[0098] Step S22: Combine the target enterprises in pairs, process the first feature data according to the first combination results, and obtain a first feature vector for each first combination;

[0099] Then, the target enterprises are combined in pairs, and the first feature data is processed according to the first combination result to obtain the first feature vector of each first combination. Specifically, when processing the first feature data according to the first combination result, the feature data of some features in the first feature data are first converted according to the preset mapping relationship table. For example, for the features of enterprise scale, popularity, tax grade, and annual tax amount in the first target feature, feature values ​​(0 or 1) corresponding to different ranges of values ​​are set respectively to convert the above feature data into corresponding feature values, and then the similarity between the feature values ​​of the above features is calculated based on the preset similarity algorithm. Among them, the preset similarity algorithm includes but is not limited to Euclidean distance and cosine similarity. For example, for the feature of enterprise scale, the feature value corresponding to more than 1,000 people is set to 1; when there are less than 1,000 people, the corresponding feature value is 0. For text features, such as the main products of the enterprise, upstream companies of the enterprise, downstream companies of the enterprise, and region, the corresponding word vectors can be generated based on the Word2vec (word to vector, a related model used to generate word vectors) algorithm, and then the similarity between the above word vectors is calculated based on the preset similarity algorithm. Then, the similarities of the first target features between the two target enterprises in each first combination are combined to obtain a first feature vector.

[0100] Step S23: input each first feature vector into a pre-trained industry relationship classification model to obtain an industry relationship classification result for each first combination;

[0101] Step S24: generating the industry relationship map according to the industry relationship classification result.

[0102] After obtaining the first eigenvectors of each first combination, each first eigenvector is input into a pre-trained industry relationship classification model to obtain the industry relationship classification results of each first combination. The training process of the industry relationship classification model can refer to the following embodiment and will not be described in detail here. The industry relationship classification model can be a binary classification model or a multi-classification model. If it is a binary classification model, it outputs the classification results of whether there is a relationship between the industries corresponding to the two target enterprises and its corresponding probability value; if it is a multi-classification model, it outputs the classification results between the industries corresponding to the two target enterprises, and the probability values ​​of the three situations of the existence of upstream relationship, the existence of downstream relationship and the absence of relationship. Then, based on the industry relationship classification results, an industry relationship map is generated. The industry relationship map may include the types and probability values ​​of the relationships between industries, and the probability value is the degree of association.

[0103] Furthermore, before the above step S23, the electronic business card recommendation method further includes:

[0104] Step A, obtaining second enterprise data of a sample enterprise, and extracting a first target feature from the second enterprise data to obtain second feature data;

[0105] This embodiment introduces the training process of the industry relationship classification model.

[0106] Obtain second enterprise data of the sample enterprise and extract the first target feature from the second enterprise data to obtain second feature data. The second enterprise data may include, but is not limited to, annual reports, industry reports, satellite remote sensing data, social network data, industrial and commercial tax data, industry classification dictionaries, and the like. The second feature data is the first target feature in the second enterprise data and its corresponding value or information.

[0107] Step B: combining the sample enterprises in pairs, processing the second feature data according to the second combination results to obtain a second feature vector for each second combination, and labeling each second combination;

[0108] Step C, constructing a first training sample based on the second feature vectors and the annotation results of each second combination;

[0109] Then, the sample enterprises are combined in pairs, and the second characteristic data is processed according to the second combination result to obtain the second characteristic vector of each second combination, and each second combination is labeled; the first training sample is constructed according to the second characteristic vector of each second combination and the labeling result. Among them, the acquisition process of the second characteristic vector is consistent with the acquisition process of the first characteristic vector, and the above embodiment can be referred to. For the labeling of the combination, the corresponding labeling method is different for different types of industry relationship classification models. Specifically, if the industry relationship classification model is a two-class model, that is, it is only used to determine whether there is a correlation relationship between the two industries, then it is only necessary to determine whether the upstream or downstream company of any of the two sample enterprises is another enterprise. If the upstream or downstream company of any of the two sample enterprises is another enterprise, it is labeled as yes. If the upstream and downstream companies of any of the two sample enterprises are not the other enterprise, it is labeled as no. If the industry relationship classification model is a multi-classification model, it can be used to determine whether there is a correlation between the two industries and the specific correlation (upstream or downstream). At this time, it is only necessary to determine whether the upstream or downstream company of one of the two sample companies is the other company. If the upstream or downstream company of one of the two sample companies is the other company, it is marked as upstream or downstream accordingly. If both the upstream and downstream companies of one of the two sample companies are not the other company, it is marked as no.

[0110] Step D: training the preset industry relationship classification model using the first training sample to obtain the pre-trained industry relationship classification model.

[0111] Finally, the preset industry relationship classification model is trained using the first training sample to obtain a pre-trained industry relationship classification model. Among them, the type of the preset industry relationship classification model can be a logistic regression model, a neural network model, an XGBoost (eXtreme Gradient Boosting) model, an SVM (Support Vector Machine) model, a Bayesian model, and a CNN (Convolutional Neural Networks) model, etc. Preferably, the type of the preset industry relationship classification model can be a logistic regression model. In addition, it should be noted that the preset industry relationship classification model can be a binary classification model or a multi-classification model. The difference lies in the different labeling methods of the training samples, which have been explained in the above steps. For the specific training process of the model, reference can be made to the existing technology.

[0112] Through the above method, an industry relationship classification model is first trained to determine whether there is a correlation between industries. Then, based on the industry relationship classification model, the industry relationship classification results between industries are obtained, and then an industry relationship map is generated. The industry relationship map is applied to electronic business card recommendations, which can improve the accuracy of electronic business card recommendation results and the exchange efficiency of electronic business cards. In addition, it can also expand corporate visibility and help users discover potential business partners.

[0113] Furthermore, based on the above second embodiment, a third embodiment of the electronic business card recommendation method of the present invention is proposed. Figure 4 , Figure 4 This is a flow chart of the third embodiment of the electronic business card recommendation method of the present invention.

[0114] In this embodiment, after step S24 and before step S30, the electronic business card recommendation method further includes:

[0115] Step S50, obtaining the third user data, third business card data and third behavior data of the sample user;

[0116] This embodiment introduces the training process of the score prediction model.

[0117] First, obtain the sample user's third user data, third business card data, and third behavior data. The types of third user data may include, but are not limited to: basic user attribute data (such as gender, age, and place of origin) and user intended attribute data (including pre-selected industry tags that the user hopes to meet and industry tags derived from clustering based on the user's information browsing behavior data, such as finance and technology); third business card data refers to the data information on the sample user's electronic business card, which may include contact information, email address, position, company name, company address, etc.; third behavior data includes the sample user's operation data on the electronic business card, such as the operation object (i.e., business card identifier), number of operations, and browsing time.

[0118] Step S60, obtaining the sample user's operation card according to the third behavior data, and acquiring the operation card data and operation user data corresponding to the operation card;

[0119] The sample user's operation card is obtained based on the third behavior data, and the operation card data and operation user data corresponding to the operation card are obtained. The operation card is the operation object in the sample user's operation data on the electronic business card, the operation card data is the data information on the operation card, and the operation user data is the user data of the user corresponding to the operation card.

[0120] Step S70, obtaining the correlation between the operation business card and the sample business card of the sample user based on the industry relationship map;

[0121] Then, based on the industry relationship graph, the correlation between the operation card and the sample card of the sample user is obtained. Specifically, the company names corresponding to the operation card and the sample card are obtained, and then, based on the pre-set mapping relationship between company names and industry types, the industries corresponding to the obtained operation card and the sample card are determined. Furthermore, based on the industry relationship graph, the correlation between the industries corresponding to the operation card and the sample card is obtained.

[0122] Step S80, extracting the second target feature from the third user data, the third business card data, the operation business card data, and the operation user data to obtain third feature data;

[0123] Simultaneously, the second target feature is extracted from the third user data, third business card data, operation business card data, and operation user data to obtain third feature data. The second target feature includes, but is not limited to, gender, age, place of origin, position, company name, and company address. The third feature data is the second target feature in the third user data, third business card data, operation business card data, and operation user data, and its corresponding value or information. The process for obtaining the third feature data is similar to the process for obtaining the first feature data described above and is not further described here.

[0124] Step S90, processing the third feature data, obtaining a third feature vector according to the processing result and the correlation degree, and constructing a second training sample according to the third feature vector;

[0125] Then, the third feature data is processed, and a third feature vector is obtained based on the processing result and the correlation degree, and a second training sample is constructed based on the third feature vector. The processing process of the third feature data can refer to the processing process of the first feature data described above. The processing results obtained are the similarity between the third user data and the second target feature in the third business card data (recorded as the first similarity set), and the similarity between the third business card data and the second target feature in the operation business card data (recorded as the second similarity set). The first similarity set, the second similarity set, and the correlation degree are then combined in a preset order to obtain a third feature vector, and then the second training sample is constructed based on the three feature vectors.

[0126] Step S100: training a preset score prediction model using the second training sample to obtain the pre-trained score prediction model.

[0127] Finally, the preset score prediction model is trained using the second training sample to obtain a pre-trained score prediction model. The score prediction model may be a logistic regression model, and the specific training process may refer to the prior art.

[0128] Through the above method, a score prediction model can be constructed to facilitate the subsequent prediction of the recommendation score of the recommended business card, and then make recommendations based on the recommendation score.

[0129] Furthermore, based on the above first embodiment, a fourth embodiment of the electronic business card recommendation method of the present invention is proposed. Figure 5 , Figure 5 This is a flow chart of the fourth embodiment of the electronic business card recommendation method of the present invention.

[0130] In this embodiment, step S10 includes:

[0131] Step S11, upon receiving an electronic business card recommendation request, obtaining information of a user to be recommended according to the electronic business card recommendation request, wherein the information of the user to be recommended includes a first user identifier, first user data, and first business card data of the user to be recommended;

[0132] In this embodiment, when an electronic business card recommendation request is received, the user information to be recommended is first obtained according to the electronic business card recommendation request, wherein the user information to be recommended includes the first user identifier, first user data and first business card data of the user to be recommended.

[0133] The triggering method for the electronic business card recommendation request may be when the user selects the electronic business card recommendation option based on the electronic business card recommendation applet or electronic business card recommendation software on the user terminal; or when it is detected that the user has opened the electronic business card recommendation applet or electronic business card recommendation software. The first user identifier may be the registered account ID (number), ID number or device ID of the user to be recommended, that is, a number used to uniquely represent the identity of the user to be recommended; the types of the first user data may include but are not limited to: basic user attribute data (such as gender, age, place of origin, etc.) and user intention attribute data (including industry labels pre-selected by the user and industry labels obtained by clustering based on the user's information browsing behavior data, such as finance and technology); the first business card data is the data information on the electronic business card of the user to be recommended, and the first business card data may include contact information such as contact number, email address, position, company name, and company address.

[0134] Step S12: Obtain the electronic business card to be recommended corresponding to the first user identifier according to the preset business card list, and obtain the second user data and second business card data corresponding to the electronic business card to be recommended; wherein the target input data includes the first user data, the first business card data, the second user data and the second business card data.

[0135] Then, the electronic business card to be recommended corresponding to the first user identifier is obtained based on the preset business card list, and the second user data and second business card data corresponding to the electronic business card to be recommended are obtained. The preset business card list may consist of user identifiers and business card identifiers, and its storage format may be a key-value pair, i.e., key: user identifier, value: business card identifier. The value obtained by querying the key, i.e., querying the corresponding electronic business card identifier to be recommended based on the first user identifier of the user to be recommended, is used to obtain the second user data and second business card data corresponding to the electronic business card to be recommended. The second user data is the user data corresponding to the electronic business card to be recommended. The types of the second user data may include, but are not limited to, basic user attribute data (such as gender, age, and place of origin) and user preference attribute data (including industry tags pre-selected by the user and industry tags derived from clustering of the user's information browsing behavior data, such as finance and technology). The second business card data is the data information on the electronic business card to be recommended, and may include information such as contact number, email address, position, company name, and company address. The process of constructing the preset business card list can be referred to in the fourth embodiment below and will not be described in detail here.

[0136] The target input data includes the first user data, the first business card data, the second user data and the second business card data obtained above.

[0137] Furthermore, before the above step S12, the electronic business card recommendation method further includes:

[0138] Step E, obtaining the fourth user identifier, fourth user data, fourth business card data, and fourth behavior data of the target user;

[0139] This embodiment introduces a process of constructing a preset business card list, wherein the preset business card list is composed of user identifiers and business card identifiers, and can be used to search for electronic business cards that are of interest to each user.

[0140] First, obtain the target user's fourth user identifier, fourth user data, fourth business card data, and fourth behavior data. The target user is a user who has completed registration and created an electronic business card in the electronic business card recommendation applet or electronic business card recommendation software. The fourth user identifier can be the target user's registered account ID, ID number, or device ID, that is, a number used to uniquely represent the target user's identity; the types of fourth user data can include, but are not limited to: user basic attribute data (such as gender, age, place of origin, etc.) and user intention attribute data (including industry labels pre-selected by the user and industry labels obtained by clustering based on the user's information browsing behavior data, such as finance and technology); the fourth business card data is the data information on the target user's electronic business card, which may include contact information, email address, position, company name, company address, etc.; the fourth behavior data includes user operation data on the electronic business card, such as the operation object (i.e., business card identifier), number of operations, browsing time, etc.

[0141] Step F, obtaining a first electronic business card set corresponding to each target user according to the fourth user data, the fourth business card data and a first preset algorithm;

[0142] Then, a first electronic business card set corresponding to each target user is obtained based on the fourth user data, the fourth business card data and the first preset algorithm. Optionally, the first preset algorithm may be a content-based recommendation algorithm.

[0143] Specifically, step F includes:

[0144] Step F1, obtaining a user tag of each target user according to the fourth user data and the fourth business card data;

[0145] Step F2, calculating the user similarity between target users based on the user tags;

[0146] Step F3, determining similar users corresponding to each target user based on the user similarity and a preset threshold range;

[0147] Step F4: obtaining a first electronic business card set corresponding to each target user based on the electronic business cards of the similar users.

[0148] Specifically, the process of obtaining the first electronic business card set is as follows:

[0149] First, based on the fourth user data and the fourth business card data, a user tag is obtained for each target user. User tag types include, but are not limited to, gender, age, place of origin, intended industry, position, and company. For example, if the fourth user data indicates male, the corresponding gender tag is male.

[0150] Then, the user similarity between each target user is calculated based on the user tags. The specific user similarity calculation method includes but is not limited to: 1) counting the number of identical user tags between each target user, and then dividing it by the total number of user tags to obtain the user similarity; 2) combining the target users in pairs, calculating the similarity between each user tag between the two target users in each combination, and then calculating the weighted sum based on the similarity between each user tag and the preset tag weight coefficient as the user similarity. The similarity between two user tags can be determined based on a preset mapping table, that is, the preset mapping table is queried based on the two user tags to determine the similarity between the two. For example, the similarity can be set to 1 when the two user tags are the same, and to 0 when they are different. Of course, different similarities can also be set according to specific circumstances.

[0151] After calculating the user similarity between each target user, similar users corresponding to each target user are determined based on the user similarity and the preset threshold range. Specifically, users corresponding to user similarities within the preset threshold range can be considered similar users. For example, if the user similarities between target user A and target users B, C, and D are 0.8, 0.7, and 0.5, respectively, and the preset threshold range is above 0.6, then similar users of target user A can be determined to be B and C. Then, based on the electronic business cards of similar users, the first electronic business card set corresponding to each target user is obtained. For example, in the above example, it can be determined that the first electronic business card set corresponding to target user A includes the electronic business cards of similar users B and C.

[0152] Step G, obtaining a second electronic business card set corresponding to each target user according to the fourth behavior data and a second preset algorithm;

[0153] Based on the fourth behavior data and the second preset algorithm, a second electronic business card set corresponding to each target user is obtained. Optionally, the second preset algorithm can be an item-based collaborative filtering algorithm (Item Collaboration Filter, ItemCF), which determines the electronic business cards that the user has been interested in historically by analyzing the user's behavior data, and then recommends to the user those electronic business cards that are similar to the electronic business cards they were previously interested in.

[0154] Specifically, step G includes:

[0155] Step G1, obtaining the historically interested business cards of each target user according to the fourth behavior data;

[0156] Step G2, collecting statistics on each target user's historically interested business cards, and constructing a business card similarity matrix based on the statistical results;

[0157] Step G3, calculating the business card similarity between each historically interested business card based on the business card similarity matrix, and calculating the interest value of each target user in each historically interested business card based on the business card similarity and the historically interested business cards of each target user;

[0158] Step G4: obtaining a second electronic business card set corresponding to each target user based on the business card similarity, the interest value, and the historically interested business cards of each target user.

[0159] The process of obtaining the second electronic business card set is as follows:

[0160] First, the historical business cards of interest of each target user are obtained based on the fourth behavior data. The methods for determining the historical business cards of interest include but are not limited to: 1) determining the operation object, that is, the business card identifier, based on the fourth behavior data, and the electronic business card corresponding to the business card identifier is the historical business card of interest; 2) determining the operation object and the corresponding number of operations and browsing time based on the fourth behavior data, and then filtering out the operation objects that meet certain conditions based on the number of operations and browsing time, and then using the filtered operation objects that meet the conditions as the historical business cards of interest.

[0161] Then, statistics are collected based on the target user's historically interested cards, and a card similarity matrix is ​​constructed based on the statistical results. For example, if target user A's historically interested cards include a, b, and c, target user B's historically interested cards include b and d, and target user C's historically interested cards include a, b, and d, then the statistics show that there are two users who are interested in both a and b, one user who is interested in both a and c, one user who is interested in both a and d, one user who is interested in both b and c, and two users who are interested in both b and d. Based on these statistical results, a card similarity matrix is ​​constructed, which records the number of users who are interested in both card i and card j.

[0162] Based on the card similarity matrix, the card similarity between each historically interested card is calculated, and then the interest value of each target user in each historically interested card is calculated based on the card similarity and the historically interested cards of each target user. The card similarity between each historically interested card can be calculated using the following formula (1); the interest value of each target user in each historically interested card can be calculated using the following formula (2).

[0163]

[0164]

[0165] Among them, w ij represents the similarity between business cards i and j, N(i) represents the set of users interested in business card i, and N(j) represents the set of users interested in business card j; P uj represents the interest value of user u in business card j, N(u) represents the set of business cards that the user likes (i is a business card that the user is interested in), S(j,k) represents the set of k business cards that are most similar to business card j (j is a business card in this set), w ji represents the similarity between business card j and business card i, r ui Indicates the user u’s interest in business card i, r ui =1.

[0166] Finally, based on the business card similarities between the historical business cards of interest, the interest values ​​of the target users in the historical business cards of interest, and the historical business cards of interest of the target users, a second electronic business card set corresponding to each target user is obtained. Taking the process of obtaining the second electronic business card set corresponding to a target user as an example, the target business cards of interest corresponding to the historical business cards of interest of the target user are first obtained based on the business card similarities between the historical business cards of interest. For example, the business cards corresponding to the n values ​​(which can be specifically set) with the largest business card similarities with the historical business cards of interest can be taken as the target business cards of interest; then, based on the business card similarities between the target business cards of interest and the corresponding historical business cards of interest, and the interest values ​​of the historical business cards of interest, the target interest level of the user in the target business cards of interest is calculated, and then the target business cards corresponding to the target interest levels greater than a preset threshold are taken as the second electronic business card set corresponding to the target user.

[0167] It should be noted that the execution order of the above steps F and G is not specific.

[0168] Step H, obtaining the intersection of the first electronic business card set and the second electronic business card set corresponding to each target user, and obtaining the electronic business card of interest to each target user;

[0169] Step I: constructing the preset business card list based on the electronic business card of interest and the fourth user identifier.

[0170] After obtaining the first electronic business card set and the second electronic business card set based on different algorithms, the intersection of the first electronic business card set and the second electronic business card set corresponding to each target user is obtained to obtain the electronic business cards of interest to each target user. For example, in the above example, the first electronic business card set corresponding to target user A includes electronic business card b of user B and electronic business card c of user C. The second electronic business card set corresponding to target user A includes electronic business card b of user B and electronic business card e of user E, so the electronic business card of interest to target user A is determined to be electronic business card b. Finally, based on the electronic business cards of interest and the fourth user identifier, a preset business card list is constructed. The preset business card list consists of a user identifier and a business card identifier, and its storage format can be in the form of a key-value pair, that is, key: user identifier, value: business card identifier. When making recommendations, the value obtained based on the key query can be used, that is, the corresponding business card identifier can be obtained based on the user identifier.

[0171] Through the above method, the electronic business cards that each target user may be interested in are pre-determined, and a preset business card list is then constructed. This facilitates subsequent querying of the preset business card list to obtain the recommended electronic business card corresponding to the user to be recommended. Furthermore, by combining multiple algorithms to determine the electronic business cards that each target user may be interested in, the reliability of the preset business card list can be improved, thereby improving the accuracy of the electronic business card recommendation results.

[0172] The invention also provides an electronic business card recommendation device.

[0173] Reference Figure 6 , Figure 6 This is a schematic diagram of the functional modules of the first embodiment of the electronic business card recommendation device of the present invention.

[0174] like Figure 6 As shown, the electronic business card recommendation device includes:

[0175] A first acquisition module 10 is configured to acquire target input data according to an electronic business card recommendation request upon receiving the electronic business card recommendation request;

[0176] A second acquisition module 20 is configured to acquire first enterprise data of a target enterprise and construct an industry relationship map based on the first enterprise data;

[0177] The score determination module 30 is used to obtain the recommendation score of each electronic business card to be recommended based on the target input data, the industry relationship map and the pre-trained score prediction model;

[0178] The business card recommendation module 40 is configured to recommend the user to be recommended according to the recommendation score of each electronic business card to be recommended.

[0179] Furthermore, the second acquisition module 20 includes:

[0180] a first acquiring unit, configured to acquire first enterprise data of a target enterprise and extract a first target feature from the first enterprise data to obtain first feature data;

[0181] a first processing unit, configured to combine the target enterprises in pairs, process the first feature data according to the first combination results, and obtain a first feature vector for each first combination;

[0182] A vector input unit, configured to input each first feature vector into a pre-trained industry relationship classification model to obtain an industry relationship classification result of each first combination;

[0183] A graph generation unit is used to generate the industry relationship graph according to the industry relationship classification result.

[0184] Furthermore, the electronic business card recommendation device further includes:

[0185] A first feature extraction module is used to obtain second enterprise data of the sample enterprise and extract the first target feature in the second enterprise data to obtain second feature data;

[0186] a first processing module, configured to combine the sample enterprises in pairs, process the second feature data according to the second combination results, obtain a second feature vector for each second combination, and label each second combination;

[0187] A first sample construction module, configured to construct a first training sample according to the second feature vectors and the labeling results of each second combination;

[0188] The first training module is used to train the preset industry relationship classification model through the first training sample to obtain the pre-trained industry relationship classification model.

[0189] Furthermore, the electronic business card recommendation device further includes:

[0190] A third acquisition module, configured to acquire third user data, third business card data, and third behavior data of a sample user;

[0191] a fourth acquisition module, configured to obtain an operation card of a sample user according to the third behavior data, and obtain operation card data and operation user data corresponding to the operation card;

[0192] A fifth acquisition module, configured to acquire, based on the industry relationship graph, a degree of association between the operation business card and the sample business card of the sample user;

[0193] A second feature extraction module is used to extract the second target feature from the third user data, the third business card data, the operation business card data and the operation user data to obtain third feature data;

[0194] a second processing module, configured to process the third feature data, obtain a third feature vector according to the processing result and the correlation degree, and construct a second training sample according to the third feature vector;

[0195] The second training module is used to train the preset score prediction model through the second training sample to obtain the pre-trained score prediction model.

[0196] Furthermore, the first acquisition module 10 includes:

[0197] A second acquiring unit is configured to acquire, upon receiving an electronic business card recommendation request, information of a user to be recommended according to the electronic business card recommendation request, wherein the information of the user to be recommended includes a first user identifier, first user data, and first business card data of the user to be recommended;

[0198] The third acquisition unit is used to obtain the electronic business card to be recommended corresponding to the first user identifier according to a preset business card list, and obtain the second user data and second business card data corresponding to the electronic business card to be recommended; wherein the target input data includes the first user data, the first business card data, the second user data and the second business card data.

[0199] Furthermore, the electronic business card recommendation device further includes:

[0200] A sixth acquisition module, configured to acquire a fourth user identifier, fourth user data, fourth business card data, and fourth behavior data of the target user;

[0201] A first determining module, configured to obtain a first electronic business card set corresponding to each target user based on the fourth user data, the fourth business card data, and a first preset algorithm;

[0202] A second determining module is configured to obtain a second electronic business card set corresponding to each target user according to the fourth behavior data and a second preset algorithm;

[0203] A third determining module is configured to obtain the intersection of the first electronic business card set and the second electronic business card set corresponding to each target user, and obtain the electronic business card of interest to each target user;

[0204] The business card list building module is used to build the preset business card list based on the electronic business card of interest and the fourth user identifier.

[0205] Furthermore, the first determining module is specifically configured to:

[0206] Obtaining a user tag of each target user according to the fourth user data and the fourth business card data;

[0207] Calculating user similarity between target users based on the user tags;

[0208] Determine similar users corresponding to each target user based on the user similarity and a preset threshold range;

[0209] A first electronic business card set of each target user is obtained according to the electronic business cards of the similar users.

[0210] Furthermore, the second determining module is specifically configured to:

[0211] Obtaining historically interested business cards of each target user according to the fourth behavior data;

[0212] Counting each of the target user's historically interested business cards, and constructing a business card similarity matrix based on the statistical results;

[0213] Calculating the business card similarities between the historically interested business cards based on the business card similarity matrix, and calculating the interest value of each target user in each historically interested business card based on the business card similarities and the historically interested business cards of each target user;

[0214] A second electronic business card set corresponding to each target user is obtained according to the business card similarity and the interest value.

[0215] Furthermore, the business card recommendation module 40 is specifically configured to:

[0216] sorting the electronic business cards to be recommended according to the recommendation scores of the electronic business cards to be recommended;

[0217] The electronic business cards to be recommended are screened according to the sorting result and preset screening rules to determine a target recommended electronic business card, and the target recommended electronic business card is recommended to the user to be recommended.

[0218] The functional implementation of each module in the electronic business card recommendation device corresponds to each step in the electronic business card recommendation method embodiment, and their functions and implementation processes are not described here one by one.

[0219] The present invention also provides a computer-readable storage medium storing an electronic business card recommendation program. When the electronic business card recommendation program is executed by a processor, the steps of the electronic business card recommendation method described in any of the above embodiments are implemented.

[0220] The specific embodiments of the computer-readable storage medium of the present invention are substantially the same as the embodiments of the above-mentioned electronic business card recommendation method, and are not described in detail here.

[0221] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0222] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0223] 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.

[0224] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for recommending an electronic business card, characterized in that: The electronic business card recommendation method includes: Upon receiving an electronic business card recommendation request, acquiring target input data and the electronic business card to be recommended according to the electronic business card recommendation request; Acquire first enterprise data of a target enterprise, and construct an industry relationship map based on the first enterprise data; Obtaining a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model; Recommending users to be recommended according to the recommendation scores of the electronic business cards to be recommended; The target input data includes first user data, first business card data, second user data, and second business card data. The step of obtaining a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model includes: Extracting target features from the second user data, the second business card data, the first user data, and the first business card data in the target input data to obtain target feature data; Determine the corresponding second industry according to the second business card data, and determine the corresponding first industry according to the first business card data; Acquire a target correlation between the second industry and the first industry based on the industry relationship graph; Processing the target feature data to obtain a corresponding processing result, and obtaining a corresponding target feature vector based on the processing result and the target correlation degree; The target feature vector is input into a pre-trained score prediction model to obtain the recommendation score of each electronic business card to be recommended.

2. The electronic business card recommendation method according to claim 1, wherein: The step of obtaining the first enterprise data of the target enterprise and constructing an industry relationship map based on the first enterprise data includes: Acquire first enterprise data of a target enterprise, and extract a first target feature from the first enterprise data to obtain first feature data; Combine the target enterprises in pairs, process the first feature data according to the first combination results, and obtain a first feature vector for each first combination; Inputting each first feature vector into a pre-trained industry relationship classification model to obtain an industry relationship classification result of each first combination; The industry relationship map is generated according to the industry relationship classification result.

3. The electronic business card recommendation method according to claim 2, wherein: Before the step of inputting each first feature vector into a pre-trained industry relationship classification model to obtain the industry relationship classification results of each first combination, the method further includes: Acquire second enterprise data of the sample enterprise, and extract the first target feature from the second enterprise data to obtain second feature data; The sample enterprises are combined in pairs, the second characteristic data are processed according to the second combination results to obtain the second characteristic vectors of each second combination, and each second combination is labeled; Constructing a first training sample according to the second feature vectors and the labeling results of each second combination; The preset industry relationship classification model is trained using the first training sample to obtain the pre-trained industry relationship classification model.

4. The electronic business card recommendation method according to claim 1, wherein: Before the step of obtaining the recommendation score of each electronic business card to be recommended based on the target input data, the industry relationship map and the pre-trained score prediction model, the method further includes: Obtaining third user data, third business card data, and third behavior data of the sample user; Obtaining an operation business card of the sample user according to the third behavior data, and obtaining operation business card data and operation user data corresponding to the operation business card; Obtaining the degree of association between the operation business card and the sample business card of the sample user based on the industry relationship graph; extracting the second target feature from the third user data, the third business card data, the operation business card data, and the operation user data to obtain third feature data; Processing the third feature data, obtaining a third feature vector according to the processing result and the correlation degree, and constructing a second training sample according to the third feature vector; The preset score prediction model is trained using the second training sample to obtain the pre-trained score prediction model.

5. The electronic business card recommendation method according to claim 1, wherein: When receiving the electronic business card recommendation request, the step of obtaining target input data and the electronic business card to be recommended according to the electronic business card recommendation request includes: Upon receiving an electronic business card recommendation request, obtaining user information to be recommended according to the electronic business card recommendation request, the user information to be recommended including a first user identifier, first user data, and first business card data of the user to be recommended; According to a preset business card list, the electronic business card to be recommended corresponding to the first user identifier is obtained, and the second user data and second business card data corresponding to the electronic business card to be recommended are obtained; wherein the target input data includes the first user data, the first business card data, the second user data and the second business card data.

6. The electronic business card recommendation method according to claim 5, wherein: Before the step of obtaining the electronic business card to be recommended corresponding to the first user identifier according to the preset business card list and obtaining the second user data and second business card data corresponding to the electronic business card to be recommended, the method further includes: Obtaining a fourth user identifier, fourth user data, fourth business card data, and fourth behavior data of the target user; Obtaining a first electronic business card set corresponding to each target user according to the fourth user data, the fourth business card data and a first preset algorithm; Obtaining a second electronic business card set corresponding to each target user according to the fourth behavior data and a second preset algorithm; Obtaining the intersection of the first electronic business card set and the second electronic business card set corresponding to each target user to obtain the electronic business card of interest to each target user; The preset business card list is constructed based on the electronic business card of interest and the fourth user identifier.

7. The electronic business card recommendation method according to claim 6, wherein: The step of obtaining the first electronic business card set corresponding to each target user according to the fourth user data, the fourth business card data and the first preset algorithm includes: Obtaining a user tag of each target user according to the fourth user data and the fourth business card data; Calculating user similarity between target users based on the user tags; Determine similar users corresponding to each target user based on the user similarity and a preset threshold range; A first electronic business card set of each target user is obtained according to the electronic business cards of the similar users.

8. The electronic business card recommendation method according to claim 6, wherein: The step of obtaining the second electronic business card set corresponding to each target user according to the fourth behavior data and the second preset algorithm includes: Obtaining historically interested business cards of each target user according to the fourth behavior data; Counting each of the target user's historically interested business cards, and constructing a business card similarity matrix based on the statistical results; Calculating the business card similarities between the historically interested business cards based on the business card similarity matrix, and calculating the interest value of each target user in each historically interested business card based on the business card similarities and the historically interested business cards of each target user; A second electronic business card set corresponding to each target user is obtained according to the business card similarity and the interest value.

9. The electronic business card recommendation method according to any one of claims 1 to 8, wherein: The step of recommending the user to be recommended according to the recommendation score of each electronic business card to be recommended comprises: sorting the electronic business cards to be recommended according to the recommendation scores of the electronic business cards to be recommended; The electronic business cards to be recommended are screened according to the sorting result and preset screening rules to determine a target recommended electronic business card, and the target recommended electronic business card is recommended to the user to be recommended.

10. An electronic business card recommendation device, characterized in that: The electronic business card recommendation device comprises: A first acquisition module is configured to acquire target input data according to the electronic business card recommendation request upon receiving the electronic business card recommendation request; A second acquisition module is used to acquire first enterprise data of a target enterprise and construct an industry relationship map based on the first enterprise data; A score determination module, configured to obtain a recommendation score for each electronic business card to be recommended based on the target input data, the industry relationship map, and a pre-trained score prediction model; A business card recommendation module, configured to make recommendations to users to be recommended based on the recommendation scores of the electronic business cards to be recommended; Among them, the target input data includes first user data, first business card data, second user data and second business card data, and the score determination module is also used to: extract target features from the second user data, second business card data, first user data and first business card data in the target input data to obtain target feature data; determine the corresponding second industry based on the second business card data, and determine the corresponding first industry based on the first business card data; obtain the target correlation between the second industry and the first industry based on the industry relationship map; process the target feature data to obtain the corresponding processing result, and obtain the corresponding target feature vector based on the processing result and the target correlation; input the target feature vector into a pre-trained score prediction model to obtain the recommendation score of each electronic business card to be recommended.

11. An electronic business card recommendation device, characterized in that: The electronic business card recommendation device includes: a memory, a processor, and an electronic business card recommendation program stored in the memory and executable on the processor. When the electronic business card recommendation program is executed by the processor, the steps of the electronic business card recommendation method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores an electronic business card recommendation program, which, when executed by a processor, implements the steps of the electronic business card recommendation method according to any one of claims 1 to 9.

Images