Qualification service customer recommendation method and system based on enterprise knowledge graph, and medium

Abstract

The application provides a qualification service customer recommendation method and system based on an enterprise knowledge graph, and a medium, and comprises the following steps: collecting and processing public service platform information data and enterprise information data to obtain a standardized information dataset; first feature data, second feature data and third feature data are respectively generated; based on comparing the first feature data and the second feature data, an enterprise customer group model based on customer group classification is obtained; and based on the customer group model and enterprise information matched in the enterprise knowledge graph based on the third feature data, a target customer is determined. The application generates screening conditions by means of the enterprise knowledge graph and the collected and processed information data, so that the target customer of the qualification service industry supplier is confirmed, and the efficiency and accuracy of the business supplier in finding the target customer are improved.

Description

Technical Field

[0001] The present invention relates to the field of data mining, and in particular to a method, system and medium for recommending qualification service customers based on an enterprise knowledge graph. Background Art

[0002] Finding and screening target customers is a scenario encountered by qualification service industry suppliers when mining target customers' business information. Currently, qualification service industry suppliers do not have similar systems to conduct accurate target customer queries. Qualification service business mainly handles construction qualifications for enterprises in the construction industry, and customer development methods are mainly divided into the following two types:

[0003] 1) Obtaining data on newly established companies and their contact information through some non-compliant and illegal channels, screening out leads of companies that may be engaged in the construction industry, and contacting them one by one to discuss whether they need to apply for construction company qualifications;

[0004] 2) Use third-party SaaS products (such as Tanji, Lixiaoyun, Qikeduo, etc.) to search for companies whose construction qualifications are about to expire, and contact them one by one to discuss whether they need to apply for an extension for their expiring qualifications;

[0005] However, the above methods of finding target customers have the following disadvantages:

[0006] (1) Unable to find clients for qualification upgrade and qualification transfer business, unable to accurately identify whether the enterprise has the need to upgrade or purchase transfer qualifications;

[0007] (2) Customer acquisition is done through manual labor, which is costly. For situations such as failed qualification applications and dynamic verification, manual labor is required to check the notices and announcements of the housing and construction departments in various regions every day, and then use other platforms to search for the company's contact information based on the information in the notices;

[0008] (3) It is unable to identify the business level of the client company and relies on manual judgment, which is time-consuming and labor-intensive. Since the information is complex and requires manual identification and judgment, it brings huge information processing costs to practitioners.

[0009] Therefore, the market is in urgent need of a customer recommendation strategy for the qualification service industry to address the shortcomings of low screening efficiency, low matching degree and insufficient accuracy when suppliers in the qualification service industry are looking for target customers. Summary of the Invention

[0010] In response to the shortcomings of the existing technology, the present invention proposes a qualification service customer recommendation method, system and medium based on enterprise knowledge graph, which improves the screening efficiency, matching degree and accuracy of qualification service industry suppliers when looking for target customers.

[0011] The technical solution of the present invention is achieved as follows:

[0012] In a first aspect, the present application discloses a qualification service customer recommendation method based on an enterprise knowledge graph, comprising the following steps:

[0013] Collecting public service platform information data and enterprise information data, performing data processing on the information data to obtain a standardized information dataset, and importing the standardized information dataset into a pre-constructed enterprise knowledge graph;

[0014] Analyzing the public service platform information data, extracting relevant qualification information, and generating first feature data containing multi-dimensional information through structured processing;

[0015] According to the first feature data, performing data processing on the enterprise knowledge graph to obtain second feature data of the same dimension as the first feature data;

[0016] Based on the comparison between the first feature data and the second feature data, an enterprise customer group model based on customer group classification is obtained, the customer group classification including: qualification new customer group, qualification extension customer group, qualification upgrade customer group, application not passed customer group, talent service customer group, qualification transfer customer group, and bankrupt enterprise customer group;

[0017] Based on the enterprise knowledge graph and the precise screening rules, the standardized information dataset is subjected to secondary data processing to generate third feature data;

[0018] Based on the customer group model and the third feature data matched with the enterprise information in the enterprise knowledge graph, a target customer is determined.

[0019] Preferably, the information data is network public information obtained through a crawler technology, and the network public information includes construction engineering enterprise information published by a construction market supervision public service platform, relevant information of employees, construction project information, bidding information, enterprise yellow page information, enterprise business information, and enterprise public recruitment information.

[0020] Preferably, the data processing includes data analysis, data standardization, data mapping, core field extraction, and multi-dimensional processing.

[0021] Preferably, the relevant qualification information includes qualification type information, qualification level information, qualification standard information, qualification requirement information, qualification demand information, qualification application information, and qualification data information.

[0022] Preferably, the first feature data is qualification condition recognition feature data generated based on the public service platform information, and the first feature data is used as a screening condition for identifying whether an enterprise meets the qualification standard requirements.

[0023] Preferably, the second feature data is enterprise qualification feature data generated based on the enterprise knowledge graph, and the second feature data is used as basic information data for comparison with the first feature data.

[0024] Preferably, the accurate screening rule is a multi-dimensional screening condition established by enterprise information, qualification information, registered personnel information and project performance information, and the screening condition includes: construction industry, item demand, enterprise type, establishment time, registered region, available qualification type, to-be-extended qualification type, to-be-extended qualification quantity, qualification expiration time, upgraded qualification type, certificate issuance date, registered capital, rejected qualification type, rejection time, rejection times, qualification application category, recruitment talent type, recruitment publication time, safety permit information and contact information.

[0025] Preferably, the third feature data is enterprise information data and public platform information data in the standardized information data set as screening conditions, and the second feature data is used as a screening condition for screening target customer enterprises in the enterprise customer group.

[0026] Preferably, the application failure customer group is determined whether an enterprise applies for a qualification through an announcement file published in the public service platform information, and the announcement file is subjected to data cleaning and data mapping, industry standard business terms and file information are extracted, application failure customer group enterprise related information is generated, the related information is used for screening enterprises, and the related information includes: enterprise list, qualification type, business type and examination result.

[0027] Preferably, the item demand is obtained by processing the public service platform information data, enterprise information data and enterprise qualification information data to obtain enterprise big data samples, and based on the enterprise big data samples and a big data prediction algorithm, the probability of enterprise demand for different qualifications is predicted.

[0028] In a second aspect, the present application provides a qualification service customer recommendation system based on an enterprise knowledge graph, which is used to execute the qualification service customer recommendation method based on the enterprise knowledge graph.

[0029] A data collection and processing module is configured to collect public service platform information data and enterprise information data, process the information data, obtain a standardized information data set, and import the standardized information data set into a pre-constructed enterprise knowledge graph.

[0030] A first feature data generation module is configured to analyze the public service platform information data, extract related qualification information, and generate first feature data containing multi-dimensional information through structured processing.

[0031] A second feature data generation module is used to process the enterprise knowledge graph based on the first feature data to obtain second feature data of the same dimension as the first feature data;

[0032] a customer group model generation module, which obtains an enterprise customer group model based on customer group classification based on the comparison of the first feature data and the second feature data, wherein the customer group classification includes: a new qualification customer group, a qualification extension customer group, a qualification upgrade customer group, an application failure customer group, a talent service customer group, a qualification transfer customer group, and a bankrupt enterprise customer group;

[0033] A third feature data generation module is used to perform secondary data processing on the standardized information data set based on the enterprise knowledge graph and precise screening rules to generate third feature data;

[0034] The target customer determination module determines the target customer based on the customer group model and the enterprise information matched by the third feature data in the enterprise knowledge graph.

[0035] In a third aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor executes the method as described in any one of the first aspects.

[0036] Compared with the existing technology, the method, system and medium for recommending qualification service customers based on enterprise knowledge graph of the present invention have the following advantages:

[0037] (1) Through the collected public platform information, the content of the announcement documents, policy documents and project documents related to the qualifications is analyzed to generate characteristic data for identifying corporate customer groups. By comparing and matching corporate information, the companies corresponding to the qualification service business are identified, and customer groups are identified and classified. Business providers can directly find and screen target customers within the target customer group through customer group classification, thereby improving query efficiency.

[0038] (2) By generating multi-dimensional screening conditions and combining them with the business needs of companies within the customer base, we can accurately screen and query suitable target companies and specific customers, thereby improving efficiency and increasing accuracy.

[0039] (3) Through the pre-built enterprise knowledge graph, all qualification-related information related to the enterprise can be queried to ensure that the query and screening results meet business needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0041] Figure 1 A flowchart of a qualification service customer recommendation method based on an enterprise knowledge graph according to the present application;

[0042] Figure 2 A schematic diagram of a qualification service customer recommendation system based on an enterprise knowledge graph according to the present application. DETAILED DESCRIPTION

[0043] In order to more clearly illustrate the above-mentioned purposes, features and advantages of the embodiments of the present disclosure, the embodiments of the present disclosure will be further described in detail below in combination with the drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0044] In the following description, many specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure, but the embodiments of the present disclosure can also be implemented in other ways different from those described herein, therefore, the protection scope of the embodiments of the present disclosure is not limited by the specific embodiments disclosed below.

[0045] Embodiment 1

[0046] As shown in the drawings, the qualification service customer recommendation method based on an enterprise knowledge graph according to the embodiments of the present application comprises the following steps: Figure 1

[0047] S101: Collecting public service platform information data and enterprise information data, processing the information data to obtain a standardized information data set, and importing the standardized information data set into a pre-constructed enterprise knowledge graph;

[0048] S102: Analyzing the public service platform information data, extracting relevant qualification information, and generating first feature data containing multi-dimensional information through structured processing;

[0049] S103: According to the first feature data, processing the enterprise knowledge graph to obtain second feature data of the same dimension as the first feature data;

[0050] ​S104: Obtain an enterprise customer group model based on customer group classification based on the comparison of the first feature data and the second feature data, the customer group classification including: new qualification customer group, qualification extension customer group, qualification upgrade customer group, application not passed customer group, talent service customer group, qualification transfer customer group, and bankrupt enterprise customer group;

[0051] S105: Based on the enterprise knowledge graph and the accurate screening rule, the standardized information data set is processed again to generate third feature data;

[0052] S106: Determine the target customer based on the customer group model and the third feature data matched in the enterprise knowledge graph.

[0053] In this embodiment, the information data is network public information obtained by crawler technology, and the network public information includes: construction market supervision public service platform published construction engineering enterprise information, employee related information, construction project information, bidding information, enterprise yellow page information, enterprise business information and enterprise public recruitment information.

[0054] In this embodiment, the data processing includes: data analysis, data standardization, data mapping, core field extraction and multi-dimensional processing.

[0055] In this embodiment, the related qualification information includes qualification type information, qualification level information, qualification standard information, qualification requirement information, qualification demand information, qualification application information and qualification data information.

[0056] In this embodiment, the first feature data is qualification condition identification feature data generated based on the public service platform information, and the first feature data is used as a screening condition for identifying whether the enterprise meets the qualification standard requirement.

[0057] In this embodiment, the second feature data is enterprise qualification feature data generated based on the enterprise knowledge graph, and the second feature data is used as the basis information data for comparing the first feature data.

[0058] In this embodiment, the accurate screening rule is a multi-dimensional screening condition established by enterprise information, qualification information, registered personnel information and project performance information, and the screening condition includes: construction industry, item demand, enterprise type, establishment time, registered area, available qualification type, to be extended qualification type, to be extended qualification quantity, qualification expiration time, upgrade qualification type, certificate date, registered capital, rejected qualification type, rejection time, rejection times, qualification application category, recruitment talent type, recruitment release time, Anxu information, contact information.

[0059] In the embodiment, the third feature data is enterprise information data and public platform information data in the standardized information data set as a screening condition, and the second feature data is used as a screening condition for screening target customer enterprises in the enterprise customer group.

[0060] In the embodiment, the application failed customer group judges whether an enterprise applies for qualification through the announcement file published in the public service platform information, and then performs data cleaning and data mapping on the announcement file, extracts industry standard business terms and file information, generates application failed customer group enterprise related information, and the related information is used for screening enterprises.

[0061] In the embodiment, the additional requirement is obtained by processing the public service platform information data, enterprise information data and enterprise qualification information data to obtain enterprise big data samples, and based on the enterprise big data samples and big data prediction algorithm, the probability of enterprise demand for different qualifications is predicted.

[0062] The qualification service customer recommendation method based on the enterprise knowledge graph has the following advantages:

[0063] (1) By collecting public platform information, the content of the qualification related announcement file, the policy file and the project file is analyzed to obtain feature data for identifying enterprise customer groups, and the corresponding enterprises of the qualification service business are identified through enterprise information comparison and matching, and the customer groups are identified and classified. Business suppliers can directly find and screen target customers in the target customer group through customer group classification, improving the query efficiency.

[0064] (2) By generating multi-dimensional screening conditions, the business demand of the enterprises in the customer group is combined to accurately screen and query suitable target enterprises and specific customers, improving the efficiency while increasing the accuracy.

[0065] (3) Through the pre-constructed enterprise knowledge graph, all qualification related information associated with the enterprise can be queried to ensure that the query and screening results meet the business demand.

[0066] Embodiment 2

[0067] The application provides a qualification service customer recommendation system based on an enterprise knowledge graph, which is used for executing the qualification service customer recommendation method based on the enterprise knowledge graph in the embodiment 1, and the system comprises:

[0068] The data collection and processing module collects information data from the public service platform and enterprise information data, processes the information data to obtain a standardized information data set, and imports it into the pre-built enterprise knowledge graph;

[0069] A first feature data generation module is used to analyze the public service platform information data, extract relevant qualification information, and generate first feature data containing multi-dimensional information through structured processing;

[0070] A second feature data generation module is used to process the enterprise knowledge graph based on the first feature data to obtain second feature data of the same dimension as the first feature data;

[0071] a customer group model generation module, which obtains an enterprise customer group model based on customer group classification based on the comparison of the first feature data and the second feature data, wherein the customer group classification includes: a new qualification customer group, a qualification extension customer group, a qualification upgrade customer group, an application failure customer group, a talent service customer group, a qualification transfer customer group, and a bankrupt enterprise customer group;

[0072] A third feature data generation module is used to perform secondary data processing on the standardized information data set based on the enterprise knowledge graph and precise screening rules to generate third feature data;

[0073] The target customer determination module determines the target customer based on the customer group model and the enterprise information matched by the third feature data in the enterprise knowledge graph.

[0074] Example 3

[0075] This embodiment provides a computer-readable storage medium having computer instructions stored thereon. When executed by a processor, the computer instructions cause the processor to perform the method disclosed in Embodiment 1. Specifically, a system or device equipped with a storage medium can be provided. The storage medium stores software program code that implements the functions of any of the above embodiments, and a computer (or CPU or MPU) of the system or device can be configured to read and execute the program code stored in the storage medium.

[0076] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0077] The storage medium for providing the program code includes a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as a CD-ROM, a CD-R, a CD-RW, a DVD-ROM, a DVD-RAM, a DVD-RW, a DVD+RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0078] Further, it should be understood that not only the program code read by the computer is executed, but also the operating system and the like operating on the computer are caused to perform part or all of the actual operation based on the instructions of the program code, thereby realizing the functions of any one of the above-described embodiments.

[0079] Further, it should be understood that the program code read by the storage medium is written into the memory provided in the expansion board inserted into the computer or the memory provided in the expansion unit connected to the computer, and then part or all of the actual operation is performed based on the instructions of the program code by the CPU and the like installed on the expansion board or the expansion unit, thereby realizing the functions of any one of the above-described embodiments.

[0080] It should be noted that not all the steps and modules in the above-described flowcharts and system block diagrams are necessary, and some steps or modules can be omitted according to actual needs. The execution order of the steps is not fixed and can be adjusted according to needs. The system structure described in the above-described embodiments can be a physical structure or a logical structure, that is, some modules can be implemented by the same physical entity, or some modules can be implemented by multiple physical entities, or some modules can be implemented by some components in multiple independent devices.

[0081] The above-described only is the preferred embodiment of the present application, and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for recommending qualified service customers based on enterprise knowledge graph, characterized in that: The steps include: Collect public service platform information data and enterprise information data, process the information data to obtain a standardized information data set, and import it into the pre-built enterprise knowledge graph; Analyze the public service platform information data, extract relevant qualification information, and generate first feature data containing multi-dimensional information through structured processing; Processing the enterprise knowledge graph based on the first feature data to obtain second feature data of the same dimension as the first feature data; Based on the comparison of the first feature data and the second feature data, a corporate customer group model based on customer group classification is obtained, wherein the customer group classification includes: new qualification customer group, qualification extension customer group, qualification upgrade customer group, application failure customer group, talent service customer group, qualification transfer customer group, and bankrupt enterprise customer group; Performing secondary data processing on the standardized information data set based on the enterprise knowledge graph and precise screening rules to generate third feature data; Target customers are determined based on the customer group model and the enterprise information matched by the third feature data in the enterprise knowledge graph.

2. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The information data is public information on the Internet obtained through crawler technology, and the public information on the Internet includes: construction project enterprise information, employee-related information, construction project information, bidding information, enterprise yellow pages information, enterprise industrial and commercial information and enterprise public recruitment information released by the construction market supervision public service platform.

3. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The data processing includes: data analysis, data standardization, data mapping, core field extraction and multi-dimensional processing.

4. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The relevant qualification information includes qualification type information, qualification level information, qualification standard information, qualification requirement information, qualification demand information, qualification application information and qualification data information.

5. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The first characteristic data is qualification condition identification characteristic data generated based on the public service platform information, and the first characteristic data is used as a screening condition for identifying whether an enterprise meets the qualification standard requirements.

6. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The second feature data is enterprise qualification feature data generated based on the enterprise knowledge graph, and the second feature data is used as basic information data for comparing the first feature data.

7. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The precise screening rules are multi-dimensional screening conditions established through enterprise information, qualification information, registered personnel information and project performance information. The screening conditions include: construction industry, additional item requirements, enterprise type, establishment time, registration area, available qualification type, qualification type to be extended, number of qualifications to be extended, qualification expiration time, upgraded qualification type, issuance date, registered capital, rejected qualification type, rejection time, number of rejections, qualification application category, recruitment talent type, recruitment release time, safety permit information, and contact information.

8. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 1, characterized in that: The third characteristic data is the enterprise information data and public platform information data used as screening conditions in the standardized information data set, and the second characteristic data is used as a screening condition for screening target customer enterprises in the enterprise customer group.

9. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 7, characterized in that: The group of customers who applied but were not approved determines whether the enterprise has applied for qualifications through the announcement documents published in the public service platform information, and then performs data cleaning and data mapping on the announcement documents, extracts industry standard business terms and file information, and generates relevant information about the enterprises in the group of customers who applied but were not approved. The relevant information is used to screen enterprises, and the relevant information includes: enterprise list, qualification type, business type and review results.

10. The method for recommending qualification service customers based on enterprise knowledge graph according to claim 7, characterized in that: The additional demand is obtained by processing the public service platform information data, enterprise information data and enterprise qualification information data to obtain enterprise big data samples. Based on the enterprise big data samples and big data prediction algorithms, the probability of the enterprise's demand for different qualifications is predicted and calculated.

11. A qualification service customer recommendation system based on enterprise knowledge graph, characterized in that: A system for executing the method for recommending qualification service customers based on an enterprise knowledge graph according to any one of claims 1 to 10, the system comprising: The data collection and processing module collects information data from the public service platform and enterprise information data, processes the information data to obtain a standardized information data set, and imports it into the pre-built enterprise knowledge graph; A first feature data generation module is used to analyze the public service platform information data, extract relevant qualification information, and generate first feature data containing multi-dimensional information through structured processing; A second feature data generation module is used to process the enterprise knowledge graph based on the first feature data to obtain second feature data of the same dimension as the first feature data; a customer group model generation module, which obtains an enterprise customer group model based on customer group classification based on the comparison of the first feature data and the second feature data, wherein the customer group classification includes: a new qualification customer group, a qualification extension customer group, a qualification upgrade customer group, an application failure customer group, a talent service customer group, a qualification transfer customer group, and a bankrupt enterprise customer group; A third feature data generation module is used to perform secondary data processing on the standardized information data set based on the enterprise knowledge graph and precise screening rules to generate third feature data; The target customer determination module determines the target customer based on the customer group model and the enterprise information matched by the third feature data in the enterprise knowledge graph.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which, when executed by a processor, enable the processor to perform the method according to any one of claims 1 to 10.

Images