Target enterprise recommendation method and device, computer device and storage medium

Abstract

Embodiments of the application disclose a target enterprise recommendation method and device, computer equipment and a storage medium. The method comprises: obtaining target attribute information of a target requester; then, according to the target attribute information, matching the target requester with a plurality of candidate enterprises in an enterprise database to obtain initial access scores of the candidate enterprises for the target requester; further, clustering the target requester and a first sample requester to determine a plurality of second sample requesters of the same type as the target requester; then, according to the initial access scores and a sample access score set, determining target access scores of the target requester relative to the candidate enterprises; finally, determining a target enterprise from the candidate enterprises according to the target access scores. The scheme recommends a target enterprise for a user, the user can apply for a business by referring to the recommended target enterprise, thereby improving the success rate of the user's business application.

Description

Technical Field

[0001] This application relates to the field of financial technology, and in particular to a method, apparatus, computer equipment, and storage medium for recommending a target enterprise. Background Technology

[0002] With the rapid development of the internet and mobile internet, various financial and related businesses have accelerated their informatization efforts, gradually shifting from traditional offline service models to online platforms, especially in the vertical sub-sector of supply chain finance.

[0003] In traditional supply chain finance, especially for small and medium-sized enterprises (SMEs), there are very few channels for them to obtain financing. Due to the uncertainty of the eligibility of enterprises (such as funding parties), the requester (such as an SME needing financing) usually needs to submit materials to multiple enterprises, and then the business personnel of each enterprise will manually judge whether they meet the enterprise's eligibility rules. The requester submits applications blindly, resulting in a low success rate of business applications. Summary of the Invention

[0004] This application provides a method, apparatus, computer device, and storage medium for recommending target enterprises, which can improve the success rate of user business applications.

[0005] In a first aspect, embodiments of this application provide a method for recommending target enterprises, which includes:

[0006] Obtain the target attribute information of the target requester;

[0007] Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester.

[0008] Based on the target attribute information and the sample attribute information corresponding to each first sample requester, clustering is performed on the target requester and the first sample requester to determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters. The first sample requesters are sample requesters in the sample database.

[0009] Based on the initial admission score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined, and the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise.

[0010] The target company is determined from the candidate companies based on the target score.

[0011] Secondly, embodiments of this application also provide a target enterprise recommendation device, which includes:

[0012] The acquisition unit is used to acquire the target attribute information of the target requester.

[0013] The processing unit is used to match the target requester with multiple candidate companies in the enterprise database according to the target attribute information, and obtain the initial admission score of each candidate company for the target requester.

[0014] The processing unit is further configured to perform clustering processing on the target requester and the first sample requester according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determine a number of second sample requesters of the same type as the target requester from the multiple first sample requesters, wherein the first sample requesters are sample requesters in the sample database.

[0015] The processing unit is further configured to determine the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, wherein the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise.

[0016] The processing unit is also configured to determine the target company from the candidate companies based on the target standard input score.

[0017] In some embodiments, the target attribute information includes multiple target sub-attribute information. When the processing unit performs the step of matching the target requester with multiple candidate enterprises in the enterprise database based on the target attribute information to obtain the initial admission score for the target requester from each candidate enterprise, it is specifically used for:

[0018] The target sub-attribute information is compared with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester;

[0019] The initial admission score is determined based on the comparison results.

[0020] In some embodiments, when the processing unit performs the step of clustering the target requester and the first sample requesters according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determining a plurality of second sample requesters of the same type as the target requester from a plurality of first sample requesters, the specific configuration is as follows:

[0021] Based on the K-Means clustering algorithm, each user to be clustered is clustered according to the target attribute information and the sample attribute information to obtain multiple clusters. The users to be clustered include the target requester and each first sample requester.

[0022] The first sample requester in the target cluster is determined as the second sample requester, and the target cluster is a cluster that contains the target requester among a plurality of clusters.

[0023] In some embodiments, when the processing unit performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, it is specifically used for:

[0024] Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined.

[0025] Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined.

[0026] In some embodiments, when the processing unit performs the step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set, it is specifically used for:

[0027] The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is:

[0028]

[0029] Where sim(i,j) is the similarity score between i and j, i is the target requester, j is one of the requesters in the second sample, and P ij R is a candidate company shared by both the target requester and the second sample requester. i,c R is the initial admission score for target requester i among candidate enterprise c. j,c This is the initial admission score for the second sample requester j among candidate company c. This represents the average admission score of all candidate companies corresponding to the target requester i. P represents the average admission score of all candidate companies corresponding to the second sample requester j. i For the candidate enterprise corresponding to the target requester i, P j The candidate company corresponding to the second sample requester j.

[0030] In some embodiments, when the processing unit performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the similarity score and the sample admission score set, it is specifically used for:

[0031] The target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is:

[0032]

[0033] in, For target user i relative to candidate enterprise Item n The target admission score is given by , where j is one of the requesters in the second sample request, U is the second sample requester, and sim(i,j) is the similarity score between i and j.

[0034] In some embodiments, before the processing unit performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, the method further includes:

[0035] The second sample requester is adjusted, and the adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

[0036] Thirdly, embodiments of this application also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0037] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, the computer program including program instructions that, when executed by a processor, can implement the above-described method.

[0038] This application provides a method, apparatus, computer device, and storage medium for recommending target enterprises. The method includes: acquiring target attribute information of a target requester; then, matching the target requester with multiple candidate enterprises in an enterprise database based on the target attribute information to obtain an initial admission score for each candidate enterprise relative to the target requester; further, clustering the target requester and the first sample requesters based on the target attribute information and sample attribute information corresponding to each first sample requester to determine multiple second sample requesters of the same type as the target requester from among the multiple first sample requesters, wherein the first sample requesters are sample requesters in a sample database; then, determining a target admission score for the target requester relative to each candidate enterprise based on the initial admission score and a sample admission score set, wherein the sample admission score set includes the sample admission scores of each second sample requester for its corresponding candidate enterprise; and finally, determining a target enterprise from the candidate enterprises based on the target admission score. This solution can identify sample requesters with similar attributes to the target requester based on the target attribute information and the sample attribute information. Then, based on the sample admission scores of each candidate enterprise corresponding to each sample requester with similar attributes and the initial admission score of the target requester, the target enterprise is determined. Users can refer to the recommended target enterprises when applying for business, thereby improving the success rate of users' business applications. Attached Figure Description

[0039] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a schematic diagram illustrating an application scenario of the target enterprise recommendation method provided in the embodiments of this application;

[0041] Figure 2 A flowchart illustrating the method for recommending a target enterprise as provided in the embodiments of this application;

[0042] Figure 3 A schematic diagram of a sub-process of the method for recommending a target enterprise provided in the embodiments of this application;

[0043] Figure 4 A schematic diagram of a sub-process of the method for recommending a target enterprise provided in the embodiments of this application;

[0044] Figure 5 This is a schematic diagram of the clustering method provided in the embodiments of this application;

[0045] Figure 6 A schematic diagram of a sub-process of the method for recommending a target enterprise provided in the embodiments of this application;

[0046] Figure 7 A flowchart illustrating a method for recommending a target enterprise as provided in another embodiment of this application;

[0047] Figure 8 A schematic block diagram of a recommended device for a target enterprise provided in the embodiments of this application;

[0048] Figure 9 A schematic block diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0050] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0051] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0052] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0053] This application provides a method, apparatus, computer device, and storage medium for recommending a target enterprise.

[0054] The entity executing the recommendation method for the target enterprise can be the recommendation device for the target enterprise provided in the embodiments of this application, or a computer device that integrates the recommendation device for the target enterprise. The recommendation device for the target enterprise can be implemented in hardware or software. The computer device can be a terminal or a server. The terminal can be a smartphone, tablet computer, handheld computer, or laptop computer, etc.

[0055] The applicant found that, in general, most legitimate companies have very similar admission rules for requesters who need to submit business applications. For users with similar attributes, the admission level of the same requester can be mutually referenced. That is, if two requesters with similar attributes submit business applications to the same company, the company's admission level scores for the two companies will also be similar.

[0056] Therefore, this application uses sample requesters with similar attributes to the requester as an admission reference to determine which companies have a higher degree of admission.

[0057] In this embodiment of the application, the sample requester is a requester with accurate access scores for multiple enterprises. The accurate access score can be the access score recorded by the sample requester when it actually applies for business with an enterprise, or it can be a sample formulated by each enterprise for multiple sample requesters with different attributes. The formulated sample includes sample requesters with different attributes and the access scores of each sample requester relative to each enterprise.

[0058] When a sample requester has both a real admission score and a sample admission score for a certain enterprise, the real admission score shall be used.

[0059] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating an application scenario of the target enterprise recommendation method provided in this application embodiment. The target enterprise recommendation method is applied to... Figure 1 In the computer device 10, the computer device 10 acquires the target attribute information of the target requester; then, based on the target attribute information, it matches the target requester with multiple candidate enterprises in the enterprise database to obtain the initial admission score of each candidate enterprise for the target requester; furthermore, based on the target attribute information and the sample attribute information corresponding to each first sample requester, it performs clustering processing on the target requester and the first sample requesters to determine multiple second sample requesters of the same type as the target requester from the multiple first sample requesters, wherein the first sample requesters are sample requesters in the sample database; then, based on the initial admission score and the sample admission score set, it determines the target admission score of the target requester relative to each candidate enterprise, wherein the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise; finally, it determines the target enterprise from the candidate enterprises based on the target admission score.

[0060] In this embodiment, the method for recommending target companies provided in this application is described in detail, taking the requesting company as the funding party (such as a financial institution) and the requested business as a financing business.

[0061] It should be noted that the enterprise in this application embodiment can be a funding party or other types of enterprises, which is not limited here. The business requested by the requesting party can be financing business or other businesses, which is not limited here.

[0062] Method Example 1:

[0063] Figure 2 This is a flowchart illustrating the recommendation method for the target enterprise provided in the embodiments of this application. For example... Figure 2 As shown, the method includes the following steps S110-S150.

[0064] S110. Obtain the target attribute information of the target requester.

[0065] In this embodiment, the target requester is the party that needs to apply for financing, which can be a small or medium-sized enterprise.

[0066] The target requester can be a new user conducting financing business for the first time, or a historical user who has applied for financing from some funding providers.

[0067] S120. Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester.

[0068] This example illustrates the situation using a candidate company as the candidate funder.

[0069] In some embodiments, the enterprise database is the enterprise database corresponding to supply chain finance business.

[0070] In some embodiments, the target attribute information includes multiple target sub-attribute information. It should be noted that the target sub-attribute information may include basic information of the requester, historical financing information, and trade background information. Furthermore, the target sub-attribute information may also include other information about the target requester; however, this is not specifically limited here. This embodiment uses the example of target attribute information including basic information of the requester, historical financing information, and trade background information for illustration. Please refer to [link to relevant documentation]. Figure 3 Step S120 includes:

[0071] S1201. Compare the target sub-attribute information with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester.

[0072] Specifically, each funding party sets preliminary access rules to preliminarily assess the access level of the requester. In this embodiment, the basic information, historical financing information, and trade background information of the target requester need to be compared with the basic information access conditions, historical financing access conditions, and trade background access conditions in the preliminary access rules to obtain the comparison results for each type of information.

[0073] The comparison result reflects the degree of fit between the target attribute information and the preliminary admission rules of each candidate funder. The higher the degree of fit, the higher the degree of admission. In some embodiments, the degree of fit is the degree of admission.

[0074] S1202. Determine the initial admission score based on the comparison results.

[0075] For example, in the comparison results, the access level corresponding to the requester's basic information is 80%, the access level corresponding to historical financing information is 50%, and the access level corresponding to trade background information is 60%.

[0076] At this point, an initial admission score can be determined based on the preset weights of each piece of information. The specific values ​​of these weights are not limited here; in some embodiments, the scoring formula is as follows:

[0077] R i,c =β1*A+β2*B+β3*C;(1)

[0078] Among them, R i,c Let β1 be the initial admission score of the target requester i among the candidate funders c, β2 be the weight corresponding to the requester's basic information, β3 be the weight corresponding to the historical financing information, and A be the degree of admission corresponding to the requester's basic information, B be the degree of admission corresponding to the historical financing information, and C be the degree of admission corresponding to the trade background information in the comparison results.

[0079] In some embodiments, users can select financing preferences before initiating a business transaction. In this case, the candidate funders in this application are those that correspond to the financing preferences, eliminating the need for admission assessment of candidate funders that do not correspond to the financing preferences, thereby reducing computational load.

[0080] S130. Based on the target attribute information and the sample attribute information corresponding to each first sample requester, perform clustering processing on the target requester and the first sample requesters, and determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters.

[0081] The first sample requester is a sample requester in the sample database, which can be a database stored in the target company's recommendation device.

[0082] Specifically, please refer to Figure 4 In some embodiments, step S130 includes:

[0083] S1301. Based on the K-Means clustering algorithm, cluster each user to be clustered according to the target attribute information and the sample attribute information to obtain multiple clusters.

[0084] The users to be clustered include the target requester and each of the first sample requesters.

[0085] The purpose of this embodiment is to obtain sample requesters with attributes similar to the target requester.

[0086] Specifically, please refer to Figure 5 This step includes:

[0087] 1) Obtain target attribute information and sample attribute information.

[0088] 2) Define k = n as the cardinality for clustering, where n can be 5 or other numbers, which is not limited here.

[0089] 4) Randomly select n cluster centers, calculate the distance from each user to be clustered to the cluster center using the Euclidean distance formula, and assign the user to the cluster with the closest distance.

[0090] 5) Calculate the new cluster centers.

[0091] 6) Determine if the cluster centers have converged. If they have, proceed to step 7). If they have not converged, return to step 4.

[0092] 7) Output n clusters.

[0093] S1302. The first sample requester in the target cluster is determined as the second sample requester.

[0094] The target cluster is a cluster that contains the target requester among multiple clusters. Then, the sample requester that is in the same cluster as the target requester is determined as the second sample requester. Thus, sample requesters with similar attributes to the target requester are obtained.

[0095] It should be noted that the execution order of steps S120 and S130 is not limited in this embodiment of the application, that is, steps S120 and S130 can be executed simultaneously, and step S120 can be executed after step S130.

[0096] S140. Based on the initial admission score and the sample admission score set, determine the target admission score of the target requester relative to each candidate enterprise.

[0097] The sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate funder.

[0098] In some embodiments, please refer to Figure 6 Step S140 includes:

[0099] S1401. Based on the initial admission score and the sample admission score set, determine the similarity score between the target requester and each second sample requester.

[0100] In some embodiments, the similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is:

[0101]

[0102] Where sim(i,j) is the similarity score between i and j, i is the target requester, j is one of the requesters in the second sample, and P ij R is a candidate funder for both the target requester and the second sample requester. i,c R is the initial admission score for target requester i among candidate funders c. j,c This is the initial admission score for the second sample requester j among the candidate funders c. This represents the average admission score of all candidate funders corresponding to target requester i. P represents the average admission score of all candidate funders corresponding to the second sample requester j. i For the candidate funder corresponding to the target requester i, P j This is the candidate funder corresponding to the second sample requester j.

[0103] S1402. Based on the similarity score and the sample admission score set, determine the target admission score of the target requester relative to each candidate enterprise.

[0104] More specifically, the target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is:

[0105]

[0106] in, For target user i relative to candidate funder Item n The target admission score is given by , where j is one of the requesters in the second sample request, U is the second sample requester, and sim(i,j) is the similarity score between i and j.

[0107] S150. Determine the target company from the candidate companies based on the target standard admission score.

[0108] In some embodiments, the target admission scores corresponding to each candidate funder are sorted in descending order, and then the candidate funders corresponding to each M target admission score are determined as the target funders. The value of M can be 5 or other values, which can be set by the user and are not limited here.

[0109] In summary, this solution can identify sample requesters with similar attributes based on the target requester's target attribute information and sample attribute information. Then, based on the sample admission scores of each candidate company corresponding to each sample requester with similar attributes and the initial admission score of the target requester, the target company is determined. The target requester can refer to the recommended target company when making business applications, thereby improving the success rate of user business applications, such as increasing the success rate of financing applications to funding providers.

[0110] Method Example 2:

[0111] Figure 7 This is a flowchart illustrating a method for recommending target companies according to another embodiment of this application. Compared to method embodiment one, this embodiment adds a step of adjusting the second sample requester before determining the target admission score of the target requester relative to each candidate company based on the similarity score and the sample admission score set. Specifically, as follows... Figure 7 As shown, the method for recommending the target enterprise in this embodiment includes steps S210-S270.

[0112] S210. Obtain the target attribute information of the target requester.

[0113] S220. Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester.

[0114] S230. Based on the target attribute information and the sample attribute information corresponding to each first sample requester, perform clustering processing on the target requester and the first sample requesters, and determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters.

[0115] The first sample requester is a sample requester in the sample database.

[0116] Steps S210-S230 are similar to steps S110-S130 in the previous embodiment, and will not be described again here.

[0117] S240. Based on the initial admission score and the sample admission score set, determine the similarity score between the target requester and each second sample requester.

[0118] This step is similar to step S1401 in the previous embodiment, and will not be described in detail here.

[0119] S250. Adjust the second sample requester. The adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

[0120] In some embodiments, after obtaining the similarity score between the target requester and each second sample requester according to formula (2), this embodiment selects the T second sample requesters with the highest similarity scores from multiple second sample requesters as adjusted second sample requesters. Subsequent calculations will be performed based on these adjusted second sample requesters as second sample requesters. The value of T can be 10 or other values, which are not limited here.

[0121] As can be seen, this step can reduce the number of second sample requesters participating in the target standard entry scoring, thereby reducing the amount of computation and avoiding interference from other sample requesters with low similarity, thus improving the accuracy of the target standard entry scoring.

[0122] S260. Based on the similarity score and the sample admission score set, determine the target admission score of the target requester relative to each candidate enterprise.

[0123] The method for calculating the target admission score of each candidate enterprise in this step is similar to step S140 in the above embodiment, and will not be repeated here.

[0124] In this embodiment, the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise. It should be noted that, unlike the method embodiment one, the second sample requester in this step of this embodiment is the adjusted second sample requester.

[0125] S270. Determine the target company from the candidate companies based on the target standard admission score.

[0126] This step is similar to step S150 in the above embodiment, and will not be described again here.

[0127] Figure 8 This is a schematic block diagram of a recommendation device for a target enterprise provided in an embodiment of this application. For example... Figure 8As shown, corresponding to the above-described method for recommending target companies, this application also provides a device for recommending target companies. This device includes a unit for executing the aforementioned method for recommending target companies, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal. Specifically, please refer to... Figure 8 The recommendation device 800 for the target enterprise includes an acquisition unit 801 and a processing unit 802.

[0128] Acquisition unit 801 is used to acquire target attribute information of the target requester;

[0129] The processing unit 802 is used to match the target requester with multiple candidate enterprises in the enterprise database according to the target attribute information, and obtain the initial admission score of each candidate enterprise for the target requester.

[0130] The processing unit 802 is further configured to perform clustering processing on the target requester and the first sample requester according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determine a number of second sample requesters of the same type as the target requester from the multiple first sample requesters, wherein the first sample requester is a sample requester in the sample database.

[0131] The processing unit 802 is further configured to determine the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, wherein the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise.

[0132] The processing unit 802 is further configured to determine the target enterprise from the candidate enterprises based on the target standard input score.

[0133] In some embodiments, the target attribute information includes multiple target sub-attribute information. When the processing unit 802 performs the step of matching the target requester with multiple candidate enterprises in the enterprise database based on the target attribute information to obtain the initial admission score for the target requester from each candidate enterprise, it is specifically used for:

[0134] The target sub-attribute information is compared with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester;

[0135] The initial admission score is determined based on the comparison results.

[0136] In some embodiments, when the processing unit 802 performs the step of clustering the target requester and the first sample requesters according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determining a plurality of second sample requesters of the same type as the target requester from a plurality of first sample requesters, it is specifically used for:

[0137] Based on the K-Means clustering algorithm, each user to be clustered is clustered according to the target attribute information and the sample attribute information to obtain multiple clusters. The users to be clustered include the target requester and each first sample requester.

[0138] The first sample requester in the target cluster is determined as the second sample requester, and the target cluster is a cluster that contains the target requester among a plurality of clusters.

[0139] In some embodiments, when the processing unit 802 performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, it is specifically used for:

[0140] Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined.

[0141] Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined.

[0142] In some embodiments, when the processing unit 802 performs the step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set, it is specifically used for:

[0143] The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is:

[0144]

[0145] Where sim(i,j) is the similarity score between i and j, i is the target requester, j is one of the requesters in the second sample, and P ij R is a candidate company shared by both the target requester and the second sample requester. i,c R is the initial admission score for target requester i among candidate enterprise c. j,c This is the initial admission score for the second sample requester j among candidate company c. This represents the average admission score of all candidate companies corresponding to the target requester i. P represents the average admission score of all candidate companies corresponding to the second sample requester j. i For the candidate enterprise corresponding to the target requester i, P j The candidate company corresponding to the second sample requester j.

[0146] In some embodiments, when the processing unit 802 performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the similarity score and the sample admission score set, it is specifically used for:

[0147] The target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is:

[0148]

[0149] in, For target user i relative to candidate enterprise Item n The target admission score is given by , where j is one of the requesters in the second sample request, U is the second sample requester, and sim(i,j) is the similarity score between i and j.

[0150] In some embodiments, before the processing unit 802 performs the step of determining the target access score of the target requester relative to each candidate enterprise based on the initial access score and the sample access score set, the method further includes:

[0151] The second sample requester is adjusted, and the adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

[0152] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the recommended device and each unit of the aforementioned target enterprise can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0153] The aforementioned device for recommending target enterprises can be implemented as a computer program, which can, for example... Figure 9 It runs on the computer device shown.

[0154] Please see Figure 9 , Figure 9This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 900 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.

[0155] See Figure 9 The computer device 900 includes a processor 902, a memory, and a network interface 905 connected via a system bus 901. The memory may include a non-volatile storage medium 903 and internal memory 904.

[0156] The non-volatile storage medium 903 may store an operating system 9031 and a computer program 9032. The computer program 9032 includes program instructions that, when executed, cause the processor 902 to perform a recommended method for a target enterprise.

[0157] The processor 902 provides computing and control capabilities to support the operation of the entire computer device 900.

[0158] The internal memory 904 provides an environment for the execution of the computer program 9032 in the non-volatile storage medium 903. When the computer program 9032 is executed by the processor 902, the processor 902 can execute a recommended method of the target enterprise.

[0159] This network interface 905 is used for network communication with other devices. Those skilled in the art will understand that... Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 900 to which the present application is applied. The specific computer device 900 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0160] The processor 902 is used to run a computer program 9032 stored in the memory to perform the following steps:

[0161] Obtain the target attribute information of the target requester;

[0162] Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester.

[0163] Based on the target attribute information and the sample attribute information corresponding to each first sample requester, clustering is performed on the target requester and the first sample requester to determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters. The first sample requesters are sample requesters in the sample database.

[0164] Based on the initial admission score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined, and the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise.

[0165] The target company is determined from the candidate companies based on the target score.

[0166] In some embodiments, the target attribute information includes multiple target sub-attribute information. When implementing the step of matching the target requester with multiple candidate enterprises in the enterprise database based on the target attribute information to obtain the initial admission score of each candidate enterprise for the target requester, the processor 902 specifically implements the following steps:

[0167] The target sub-attribute information is compared with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester;

[0168] The initial admission score is determined based on the comparison results.

[0169] In some embodiments, when the processor 902 performs the step of clustering the target requester and the first sample requesters according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determining a plurality of second sample requesters of the same type as the target requester from a plurality of first sample requesters, the specific implementation is as follows:

[0170] Based on the K-Means clustering algorithm, each user to be clustered is clustered according to the target attribute information and the sample attribute information to obtain multiple clusters. The users to be clustered include the target requester and each first sample requester.

[0171] The first sample requester in the target cluster is determined as the second sample requester, and the target cluster is a cluster that contains the target requester among a plurality of clusters.

[0172] In some embodiments, when implementing the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, the processor 902 specifically implements the following steps:

[0173] Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined.

[0174] Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined.

[0175] In some embodiments, when implementing the step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set, the processor 902 specifically implements the following steps:

[0176] The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is:

[0177]

[0178] Where sim(i,j) is the similarity score between i and j, i is the target requester, j is one of the requesters in the second sample, and P ij R is a candidate company shared by both the target requester and the second sample requester. i,c R is the initial admission score for target requester i among candidate enterprise c. j,c This is the initial admission score for the second sample requester j among candidate company c. This represents the average admission score of all candidate companies corresponding to the target requester i. P represents the average admission score of all candidate companies corresponding to the second sample requester j. i For the candidate enterprise corresponding to the target requester i, P j The candidate company corresponding to the second sample requester j.

[0179] In some embodiments, when implementing the step of determining the target admission score of the target requester relative to each candidate enterprise based on the similarity score and the sample admission score set, the processor 902 specifically implements the following steps:

[0180] The target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is:

[0181]

[0182] in, For target user i relative to candidate enterprise Item nThe target admission score is given by , where j is one of the requesters in the second sample request, U is the second sample requester, and sim(i,j) is the similarity score between i and j.

[0183] In some embodiments, before implementing the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, the processor 902 further implements the following steps:

[0184] The second sample requester is adjusted, and the adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

[0185] It should be understood that in the embodiments of this application, the processor 902 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0186] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0187] Therefore, this application also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions. When executed by a processor, the program instructions cause the processor to perform the following steps:

[0188] Obtain the target attribute information of the target requester;

[0189] Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester.

[0190] Based on the target attribute information and the sample attribute information corresponding to each first sample requester, clustering is performed on the target requester and the first sample requester to determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters. The first sample requesters are sample requesters in the sample database.

[0191] Based on the initial admission score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined, and the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise.

[0192] The target company is determined from the candidate companies based on the target score.

[0193] In some embodiments, the target attribute information includes multiple target sub-attribute information. When the processor executes the program instructions to implement the step of matching the target requester with multiple candidate enterprises in the enterprise database based on the target attribute information to obtain the initial admission score of each candidate enterprise for the target requester, the specific implementation is as follows:

[0194] The target sub-attribute information is compared with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester;

[0195] The initial admission score is determined based on the comparison results.

[0196] In some embodiments, when the processor executes the program instructions to implement the step of clustering the target requester and the first sample requesters according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determining a plurality of second sample requesters of the same type as the target requester from a plurality of first sample requesters, the specific implementation is as follows:

[0197] Based on the K-Means clustering algorithm, each user to be clustered is clustered according to the target attribute information and the sample attribute information to obtain multiple clusters. The users to be clustered include the target requester and each first sample requester.

[0198] The first sample requester in the target cluster is determined as the second sample requester, and the target cluster is a cluster that contains the target requester among a plurality of clusters.

[0199] In some embodiments, when the processor executes the program instructions to implement the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, it specifically implements the following steps:

[0200] Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined.

[0201] Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined.

[0202] In some embodiments, when the processor executes the program instructions to implement the step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set, it specifically implements the following steps:

[0203] The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is:

[0204]

[0205] Where sim(i,j) is the similarity score between i and j, i is the target requester, j is one of the requesters in the second sample, and P ij R is a candidate company shared by both the target requester and the second sample requester. i,c R is the initial admission score for target requester i among candidate enterprise c. j,c This is the initial admission score for the second sample requester j among candidate company c. This represents the average admission score of all candidate companies corresponding to the target requester i. P represents the average admission score of all candidate companies corresponding to the second sample requester j. i For the candidate enterprise corresponding to the target requester i, P j The candidate company corresponding to the second sample requester j.

[0206] In some embodiments, when the processor executes the program instructions to implement the step of determining the target admission score of the target requester relative to each candidate enterprise based on the similarity score and the sample admission score set, it specifically implements the following steps:

[0207] The target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is:

[0208]

[0209] in, For target user i relative to candidate enterprise Item n The target admission score is given by , where j is one of the requesters in the second sample request, U is the second sample requester, and sim(i,j) is the similarity score between i and j.

[0210] In some embodiments, before executing the program instructions to implement the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, the processor further implements the following steps:

[0211] The second sample requester is adjusted, and the adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

[0212] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0213] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0214] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0215] The steps in the methods of this application embodiment can be adjusted, merged, or deleted according to actual needs. The units in the apparatus of this application embodiment can be merged, divided, or deleted according to actual needs. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0216] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0217] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for recommending target companies, characterized in that, include: Obtain the target attribute information of the target requester, which is the party that needs to apply for financing. The target attribute information includes the requester's basic information, historical financing information, and trade background information. Based on the target attribute information, the target requester is matched with multiple candidate companies in the enterprise database to obtain the initial admission score of each candidate company for the target requester, and the candidate companies are candidate funders; Based on the target attribute information and the sample attribute information corresponding to each first sample requester, clustering is performed on the target requester and the first sample requester to determine multiple second sample requesters of the same type as the target requester from multiple first sample requesters. The first sample requesters are sample requesters in the sample database. Based on the initial admission score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined, and the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise. The target company is determined from the candidate companies based on the target standard admission score; The step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set includes: Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined. Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined; The step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set includes: The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is: ； in, for and Similarity score, For the target requester, As one of the requesters in the second sample, The candidate companies are shared by both the target requester and the second sample requester. For the target requester In candidate companies The initial admission score in the process, For the second sample requester In candidate companies The initial admission score in the process, Indicates the target requester The average admission score of all candidate companies. Indicates the second sample requester The average admission score of all candidate companies. For the target requester Corresponding candidate companies, For the second sample requester Corresponding candidate companies.

2. The method according to claim 1, characterized in that, The target attribute information includes multiple target sub-attribute information. The step of matching the target requester with multiple candidate companies in the enterprise database based on the target attribute information to obtain an initial admission score for the target requester from each candidate company includes: The target sub-attribute information is compared with the preliminary admission rules of each candidate enterprise to obtain the comparison results of each candidate enterprise for the target requester; The initial admission score is determined based on the comparison results.

3. The method according to claim 1, characterized in that, The step of clustering the target requester and the first sample requesters based on the target attribute information and the sample attribute information corresponding to each first sample requester, and determining multiple second sample requesters of the same type as the target requester from the multiple first sample requesters, includes: Based on the K-Means clustering algorithm, each user to be clustered is clustered according to the target attribute information and the sample attribute information to obtain multiple clusters. The users to be clustered include the target requester and each first sample requester. The first sample requester in the target cluster is determined as the second sample requester, and the target cluster is a cluster containing the target requester among multiple clusters.

4. The method according to claim 1, characterized in that, Determining the target admission score of the target requester relative to each candidate company based on the similarity score and the sample admission score set includes: The target admission score is determined according to a preset target admission scoring formula, wherein the target admission scoring formula is: ； in, For target users Compared to candidate companies Target access score, U is one of the requesters in the second sample request. for and Similarity score.

5. The method according to any one of claims 4, characterized in that, Before determining the target admission score of the target requester relative to each candidate enterprise based on the similarity score and the sample admission score set, the method further includes: The second sample requester is adjusted, and the adjusted second sample requester is the first preset number of sample requesters with higher similarity scores among the second sample requesters.

6. A device for recommending target enterprises, characterized in that, include: The acquisition unit is used to acquire the target attribute information of the target requester, which is the party that needs to apply for financing. The target attribute information includes the requester's basic information, historical financing information and trade background information. The processing unit is configured to match the target requester with multiple candidate companies in the enterprise database based on the target attribute information, and obtain an initial admission score for the target requester from each candidate company, wherein the candidate companies are candidate funders; The processing unit is further configured to perform clustering processing on the target requester and the first sample requester according to the target attribute information and the sample attribute information corresponding to each first sample requester, and determine a number of second sample requesters of the same type as the target requester from the multiple first sample requesters, wherein the first sample requesters are sample requesters in the sample database. The processing unit is further configured to determine the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, wherein the sample admission score set includes the sample admission scores of each second sample requester for the corresponding candidate enterprise. The processing unit is further configured to determine the target enterprise from the candidate enterprises based on the target standard input score; When the processing unit performs the step of determining the target admission score of the target requester relative to each candidate enterprise based on the initial admission score and the sample admission score set, it is specifically used for: Based on the initial admission score and the sample admission score set, the similarity score between the target requester and each second sample requester is determined. Based on the similarity score and the sample admission score set, the target admission score of the target requester relative to each candidate enterprise is determined; When the processing unit performs the step of determining the similarity score between the target requester and each second sample requester based on the initial admission score and the sample admission score set, it is specifically used for: The similarity score between the target requester and each of the second sample requesters is determined according to a preset first similarity scoring formula, wherein the first similarity scoring formula is: ； in, for and Similarity score, For the target requester, As one of the requesters in the second sample, The candidate companies are shared by both the target requester and the second sample requester. For the target requester In candidate companies The initial admission score in the process, For the second sample requester In candidate companies The initial admission score in the process, Indicates the target requester The average admission score of all candidate companies. Indicates the second sample requester The average admission score of all candidate companies. For the target requester Corresponding candidate companies, For the second sample requester Corresponding candidate companies.

7. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which includes program instructions that, when executed by a processor, can implement the method as described in any one of claims 1-5.

Images