Multi-customer linkage information recommendation method, electronic device, storage medium and program

Abstract

The embodiment of the invention discloses a multi-customer linkage information recommendation method, electronic equipment, a storage medium and a program, and relates to the field of big data and financial science and technology. The method comprises the following steps: acquiring attribute associated data and project fund associated data of a target customer; generating a target customer portrait of the target customer according to the attribute associated data and the project fund associated data of the target customer; classifying the target clients according to the target client portraits of the target clients, and determining a client list to which the target clients belong; and recommending target matching information to each customer included in the customer list in a linkage manner according to the type of the customer list. According to the technical scheme provided by the embodiment of the invention, the customer list to which the target customer belongs can be accurately positioned, so that the linkage information recommendation accuracy is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of big data and financial technology, and in particular to a multi-client interaction information recommendation method, electronic device, storage medium and program. BACKGROUND

[0002] With the vigorous development of digitization and the Internet, information recommendation has become a key means for enterprises to deeply interact with customers, optimize user experience and improve business value.

[0003] In the prior art, a customer group classification method is usually used to classify customers, determine the customer group category to which the customer belongs, and then make targeted information recommendation to the customer based on the customer group category to which the customer belongs. The more accurate the customer group classification is, the higher the matching rate of information recommendation is.

[0004] However, in the existing customer information recommendation method, when classifying the customer group, the problem of insufficient data is often encountered, which affects the accurate division of the customer category, and thus the accuracy of information recommendation is greatly reduced. SUMMARY

[0005] Embodiments of the present application provide a multi-client interaction information recommendation method, device, electronic device, storage medium and program, which can improve the accuracy of customer classification and thus improve the accuracy of interaction information recommendation.

[0006] According to an aspect of the present application, a multi-client interaction information recommendation method is provided, comprising:

[0007] obtaining attribute association data and project fund association data of a target customer;

[0008] generating a target customer portrait of the target customer according to the attribute association data and the project fund association data of the target customer;

[0009] classifying the target customer according to the target customer portrait of the target customer, and determining a customer list to which the target customer belongs;

[0010] According to the type of the customer list, each customer in the customer list is recommended target matching information.

[0011] According to another aspect of the present application, a multi-client interaction information recommendation device is provided, comprising:

[0012] a data acquisition module configured to obtain attribute association data and project fund association data of a target customer;

[0013] a target customer portrait generation module configured to generate a target customer portrait of the target customer according to the attribute association data and the project fund association data of the target customer;

[0014] The customer list determination module is used to classify the target customers according to the target customer profile of the target customers and determine the customer list to which the target customers belong;

[0015] The target matching information recommendation module is used to recommend target matching information to each customer included in the customer list based on the type of the customer list.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the multi-customer linkage information recommendation method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the multi-client linkage information recommendation method described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the multi-customer linkage information recommendation method described in any embodiment of the present invention.

[0022] This invention, in its embodiments, acquires attribute-related data and project funding-related data of target customers, and generates target customer profiles based on these data. Furthermore, it categorizes target customers according to their profiles, determines the customer list to which each target customer belongs, and then recommends matching information to each customer in the customer list based on the type of the customer list. This solution introduces project funding-related data for customer classification, enabling more accurate customer categorization and improving the accuracy of customer classification. It solves the problem of inaccurate customer group classification caused by insufficient data in existing information recommendation methods, thereby improving the accuracy of linked information recommendations.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a multi-customer collaborative information recommendation method provided in Embodiment 1 of the present invention;

[0026] Figure 2 This is a flowchart of a multi-customer collaborative information recommendation method provided in Embodiment 2 of the present invention;

[0027] Figure 3 This is a schematic diagram of a multi-customer interactive information recommendation device provided in Embodiment 3 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," and "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1This is a flowchart of a multi-customer linkage information recommendation method provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where matching information is recommended to customers based on customer attribute association data and project funding association data. This method can be executed by a multi-customer linkage information recommendation device, which can be implemented in software and / or hardware, and is generally integrated into an electronic device. This electronic device can be a terminal device or a server device, as long as it can execute the multi-customer linkage information recommendation method. The present invention does not limit the specific type of electronic device. Correspondingly, as... Figure 1 As shown, the method includes the following operations:

[0033] S110. Obtain the attribute-related data and project funding-related data of the target customers.

[0034] The target customer can be any customer for whom information recommendations are needed. It should be noted that the target customer can be an individual, a company, or other organization; this embodiment of the invention does not limit the specific type of target customer. Attribute-related data can be data reflecting different attributes of the target customer. For example, attribute-related data can include, but is not limited to, the target customer's basic personal information and transaction data. Basic personal information can include, but is not limited to, the target customer's name, gender, age, and occupation; transaction data can include, but is not limited to, transaction name, transaction amount, and transaction time. Project funding-related data can be data reflecting the relationship between projects and funding. Project funding-related data can be publicly available project information obtained from official websites or other professional data platforms, or it can be project funding-related data obtained through comprehensive analysis of project plans and project progress data. This embodiment of the invention does not limit the type and content of project funding involved in the project funding-related data.

[0035] Multi-customer collaborative information recommendation, also known as collaborative information recommendation, refers to recommending consistent information to all customers on the same customer list. In this embodiment of the invention, to perform collaborative information recommendation for multiple customers, the customers can first be accurately categorized. During the customer categorization process, attribute association data of the target customers can be obtained as reference data for customer classification. This attribute association data can comprehensively describe the characteristics and needs of the target customers, thereby enabling more accurate information recommendations.

[0036] Additionally, publicly available project information can be obtained from relevant official websites and other platforms, or a comprehensive analysis of project plans and progress data can be conducted. This information includes abundant project funding-related data. By analyzing this data, a better understanding of the target client's role in the project, their funding needs, and other project-related information can be gained, thereby providing more precise information recommendations to the target client.

[0037] S120. Generate a target customer profile of the target customer based on the attribute association data and project funding association data of the target customer.

[0038] Among them, the target customer profile can be a comprehensive model built on multi-dimensional data to fully describe the characteristics, behavioral patterns, preferences and needs of the target customer.

[0039] Correspondingly, after obtaining the attribute association data and project funding association data of the target customers, the attribute association data and project funding association data of the target customers can be analyzed to explore various characteristics of the target customers, thereby generating customer profiles of the target customers based on these characteristics.

[0040] Optionally, before generating a target customer profile based on the target customer's attribute association data and project funding association data, the obtained target customer's attribute association data and project funding association data can be cleaned and preprocessed, such as including but not limited to filling missing values, removing duplicate data, and standardizing data formats.

[0041] S130. Classify the target customers according to the target customer profile and determine the customer list to which the target customers belong.

[0042] The customer list can be a list of a specific customer group.

[0043] Accordingly, after generating a target customer profile, the target customer can be categorized based on the characteristics of that profile, thus determining the customer list to which the target customer belongs. It should be noted that a target customer's profile may have multiple characteristics, conforming to the classification criteria of multiple customer groups. Therefore, a target customer may belong to different customer lists. Customers within the same customer list share similar characteristics, allowing for the recommendation of the same information to customers within the same list, thereby improving the accuracy and efficiency of information recommendation.

[0044] In a specific example, the customer list may include the agricultural subsidy scenario, customer A's personal information, funding amount, application time, payer's name, summary, and project progress. It should be noted that customer A's personal information in the customer list can be anonymized.

[0045] S140. Based on the type of the customer list, recommend target matching information to each customer included in the customer list.

[0046] The customer list can be categorized based on different classification criteria or application scenarios. For example, the customer list type may include, but is not limited to, individual customer lists and enterprise customer lists; this embodiment of the invention does not limit the specific classification of customer list types. Target matching information can be information that matches the characteristics of customers in the target customer list.

[0047] Accordingly, after determining the target customer's customer list, the type of customer list can be determined based on the characteristics of each customer in the list. Furthermore, based on the type of customer list, targeted matching information can be recommended to each customer in the target customer list, ensuring that the recommended information matches the type of customer list, thereby improving the accuracy and effectiveness of information recommendation. In a specific example, customers participating in the same officially funded research project can be grouped into the same customer list. By analyzing the attribute correlation data of the target customers and the project funding correlation data, it can be found that the project is stagnant due to technical difficulties. Therefore, relevant technical resources, industry trends, and potential partners can be recommended to each customer in this customer list.

[0048] This invention, in its embodiments, acquires attribute-related data and project funding-related data of target customers, and generates target customer profiles based on these data. Furthermore, it categorizes target customers according to their profiles, determines the customer list to which each target customer belongs, and then recommends matching information to each customer in the customer list based on the type of the customer list. This solution introduces project funding-related data for customer classification, enabling more accurate customer categorization and improving the accuracy of customer classification. It solves the problem of inaccurate customer group classification caused by insufficient data in existing information recommendation methods, thereby improving the accuracy of linked information recommendations.

[0049] Example 2

[0050] Figure 2 This is a flowchart of a multi-customer linkage information recommendation method provided in Embodiment 2 of the present invention. This embodiment is based on the above embodiment and is further specified. In this embodiment, several specific optional implementation methods are given for generating a target customer profile based on the attribute association data and project funding association data of the target customer. Correspondingly, such as Figure 2 As shown, the method in this embodiment may include:

[0051] S210. Obtain the attribute-related data and project funding-related data of the target customers.

[0052] S220. Determine the scenario classification label of the target customer based on the attribute association data of the target customer.

[0053] Among them, scene classification labels can be feature identifiers that describe different scenes.

[0054] In this embodiment of the invention, after obtaining the attribute association data of the target customer, the target customer's scenario classification tags can be determined by analyzing the attribute association data.

[0055] In an optional embodiment of the present invention, determining the scenario classification label of the target customer based on the attribute association data of the target customer may include: determining the scenario classification result of information recommendation based on the attribute association data of the target customer using artificial intelligence; and determining the category customer label of the target customer based on the attribute association data of the target customer and the scenario classification result.

[0056] For example, artificial intelligence methods may include, but are not limited to, machine learning models such as random forests, support vector machines, or neural networks. Scene classification results can be used to classify target customers based on attribute-related data.

[0057] In this embodiment of the invention, during the process of determining the scenario classification label of a target customer based on the target customer's attribute association data, the target customer's attribute association data can first be input into a trained machine learning model to classify the scenarios to which the target customer belongs, and the output of the machine learning model is used as the scenario classification result. After obtaining the scenario classification result, the target customer's category label can be determined based on the target customer's attribute association data and the scenario classification result. The above method uses artificial intelligence to classify the scenarios to which the target customer belongs, which can improve the accuracy of scenario classification and avoid the subjectivity and errors caused by manual classification. At the same time, the artificial intelligence method can dynamically adjust the classification result based on the latest data and trends.

[0058] In a specific example, assuming the target customer's attribute-related data is customer transaction data, then the customer transaction data may include, but is not limited to, transaction name, transaction amount, and transaction time. This embodiment of the invention does not limit the specific data types included in the customer transaction data. First, the customer transaction data can be input into a trained machine learning model to classify the scenario to which the target customer belongs. For example, if the customer transaction data matches keywords such as points or local customs, the scenario classification result of the customer transaction data can be points; if the customer transaction data matches keywords such as pension, insurance, salary, wages, bonus, medical care, medical expenses, annuity, social security, work injury, housing provident fund, employee withdrawal, assessment, allowance, on-the-job, performance, year-end bonus, or remuneration, the scenario classification result of the customer transaction data is salary; if the customer transaction data matches keywords such as subsidy, allowance, pension, mutual aid, support, preferential treatment, security fund, or development fund, the scenario classification result of the customer transaction data can be relief subsidy; if the customer transaction data matches keywords such as resettlement, resettlement, housing voucher, relocation, demolition, expropriation, acquisition, building number, disposal, repurchase, or land occupation... If the customer transaction data contains keywords such as "demolition fee," then the scenario classification result can be demolition compensation. If the customer transaction data contains keywords such as "engineering," "national highway," "project," "expressway," "avenue," "transportation," "construction," "road," "industrial park," "rent," "land use," "investment," "earthwork," "new construction," "site," "flower and tree payment," "comprehensive management," "afforestation," "subway," "renovation," "seedling cultivation," "industrial development," "agricultural materials," "remediation," "straw utilization," "toilet," "municipal," "greening," "sewage," "safety," "design services," "garbage," "technical services," "design fee," "infrastructure," "isolation," "cleaning," "housing payment," "pig fattening," "maintenance fee," "environment," "prevention," "protection," "land reclamation," "atmosphere," "land use," "monitoring equipment," "management," "cold chain," "patrol," or "infrastructure," then the scenario classification result can be project engineering payment. Furthermore, the scenario classification tag corresponding to the target customer can be determined based on the classification result and attribute association data of the customer transaction data. For example, the scenario classification tag may include, but is not limited to, information such as customer type, transaction scenario, and transaction amount. The customer type may include, but is not limited to, institutional customers, corporate customers, and individual customers. This embodiment of the invention does not limit the specific content included in the scenario classification tag. If customer A's scenario classification result is project engineering payment, and customer A is a project manager of a large enterprise, then customer A's scenario classification tag can be enterprise customer.

[0059] Optionally, before determining the scenario classification label of the target customer based on the attribute association data of the target customer, the method further includes: obtaining attribute association sample data of each customer; using the attribute association sample data of each customer as training sample data for a machine learning model, and training a machine learning model based on the machine learning model training sample data.

[0060] S230. Analyze the project funding association data of the target customer to obtain the project-related customer attribute association data.

[0061] The project-related customer attribute data can be project data related to customer attributes. For example, the project-related customer attribute data may include, but is not limited to, project name, total amount of funds, disbursement batches, disbursement progress, and application conditions. This embodiment of the invention does not limit the data types included in the project-related customer attribute data.

[0062] Specifically, the acquired project funding data can be parsed to extract information related to customer attributes, and this information can be used as project-related customer attribute data.

[0063] S240. Match the project-related customer attribute association data with the target customer attribute association data to obtain the project matching result.

[0064] The project matching result can be the matching result between the project-related customer attribute data and the target customer attribute data. For example, the project matching result can be a successful match or a failed match.

[0065] Accordingly, after obtaining the project-related customer attribute association data and the target customer attribute association data, the two data can be matched to obtain a matching score. Further, the project matching result can be determined based on the matching score. For example, if the matching score exceeds a preset threshold, the project-related customer attribute association data and the target customer attribute association data are considered successfully matched; if the matching score does not exceed the preset threshold, the matching is considered unsuccessful. Simultaneously, information on unsuccessful matches can be recorded and manually reviewed.

[0066] Optionally, before matching the project-related customer attribute association data with the target customer attribute association data, data preprocessing can be performed on both sets of data. Specifically, text cleaning can be performed on the project-related customer attribute association data and the target customer attribute association data, including but not limited to removing stop words, special characters, and standardizing the data format. Natural language processing techniques can also be used to extract keywords from the project-related customer attribute association data and the target customer attribute association data. Furthermore, feature engineering can be performed on the project-related customer attribute association data and the target customer attribute association data. For example, TF-IDF (Term Frequency-Inverse Document Frequency) or Word2Vec methods can be used to convert the preprocessed target customer attribute association data into feature vectors; information such as project name, total amount of funds, and disbursement batches in the project-related customer attribute association data can be encoded to form structured features.

[0067] In an optional embodiment of the present invention, the step of matching the project-related customer attribute association data with the target customer attribute association data to obtain a project matching result may include: calculating the text similarity and data information matching degree between the target customer attribute association data and the project-related customer attribute association data; wherein, the project-related customer attribute association data includes: project name, total amount of funds, disbursement batches, disbursement progress, and application conditions; determining a comprehensive matching score based on the text similarity and the data information matching degree; and outputting the project matching result based on the comprehensive matching score.

[0068] Text similarity refers to the similarity between the text of attribute-related data of target customers and attribute-related data of project-related customers. Data matching degree refers to the degree of matching between the attribute-related data of target customers and attribute-related data of project-related customers. The comprehensive matching score is a score obtained by comprehensively analyzing text similarity and data matching degree.

[0069] In this embodiment of the invention, during the process of matching project-related customer attribute data with target customer attribute data to obtain project matching results, the textual similarity between the project-related customer attribute data and the target customer attribute data can first be calculated using methods such as cosine similarity, Jaccard similarity, or BM25 (Best Matching 25). Further, the numerical information matching degree between the project-related customer attribute data and the target customer attribute data can be calculated to obtain the numerical information matching degree. After calculating the textual similarity and data information matching degree of the project-related customer attribute data and the target customer attribute data, a comprehensive matching score can be calculated by combining the textual similarity and numerical information matching degree, thereby determining the project matching result based on the comprehensive matching score. For example, a weighted summation or machine learning model can be used to calculate the comprehensive matching score.

[0070] The above solution calculates the text similarity and data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer to obtain the project matching result, thereby improving the accuracy of the matching between the attribute association data of the target customer and the attribute association data of the project-related customer, thus enabling the accurate positioning of the customer list to which the customer belongs.

[0071] In an optional embodiment of the present invention, the attribute association data of the target customer may include transaction name, transaction amount, and transaction time; the target matching information may include financial product information; the calculation of the text similarity and data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer may include: calculating a first text similarity between the transaction name of the attribute association data of the target customer and the project name of the attribute association data of the project-related customer; calculating a first data information matching degree between the transaction amount of the attribute association data of the target customer and the total amount of funds of the attribute association data of the project-related customer; calculating a second data information matching degree between the transaction time of the attribute association data of the target customer and the issuance batch of the attribute association data of the project-related customer; and determining the data information matching degree based on the first text similarity, the first data information matching degree, and the second data information matching degree.

[0072] Specifically, the first text similarity can be the textual similarity between the transaction name in the target customer's attribute-related data and the project name in the project-related customer's attribute-related data. The first data information matching degree can be the numerical information matching degree between the transaction amount in the target customer's attribute-related data and the total amount of funds in the project-related customer's attribute-related data. The second data information matching degree can be the numerical information matching degree between the transaction time in the target customer's attribute-related data and the issuance batch in the project-related customer's attribute-related data.

[0073] In a multi-customer information recommendation scenario involving financial product information, the attribute-related data of the target customer can include transaction name, transaction amount, and transaction time, while the target matching information can be financial product information. Accordingly, in this scenario, a target customer profile can be generated based on the target customer's transaction-related attribute data and the project funding data of the financial projects the target customer may have applied for. The target customers can then be categorized, and financial product information can be recommended to them based on this categorization.

[0074] Therefore, in information recommendation scenarios involving multiple customers in financial product information, when calculating the text similarity and data information matching degree between the attribute-related data of the target customer and the attribute-related data of the project-related customer, the text similarity between the transaction name of the attribute-related data of the target customer and the project name of the attribute-related data of the project-related customer can be calculated, and the result is used as the first text similarity. Alternatively, the numerical information matching degree between the transaction amount of the attribute-related data of the target customer and the total amount of funds of the attribute-related data of the project-related customer can be calculated, and the result is used as the first data information matching degree. Furthermore, the numerical information matching degree between the transaction time of the attribute-related data of the target customer and the issuance batch of the attribute-related data of the project-related customer can be calculated, and the result is used as the second data information matching degree. After calculating the first text similarity, the first data information matching degree, and the second data information matching degree, a weighted sum can be performed on the first text similarity, the first data information matching degree, and the second data information matching degree, and the weighted sum is used as the data information matching degree. For example, the weights of the first text similarity, the first data information matching degree, and the second data information matching degree can all be 1 / 3. This embodiment of the invention does not limit the specific values ​​of the weights of the first text similarity, the first data information matching degree, and the second data information matching degree. The above solution calculates the text similarity and data matching degree between the target customer's attribute association data and the project's related customer attribute association data, given that the target customer's attribute association data includes transaction name, transaction amount, and transaction time. This allows the solution to push matching financial product information to the target customer.

[0075] In a specific example, target customer A is the legal representative of a company. Its attribute-related data includes transaction name, transaction amount, and transaction time. Project-related customer attribute-related data includes project name, total amount of funds, and disbursement batches. Therefore, the project-related customer attribute-related data of target customer A can be matched with the attribute-related data. Based on the matching results, if the disbursement time for projects undertaken by target customer A's company is delayed, then information on financial products such as corporate loans can be pushed to target customer A.

[0076] In an optional embodiment of the present invention, the attribute association data of the target customer may include professional title, number of scientific research achievements, and research field; the target matching information may include scientific research project application information; the calculation of the text similarity and data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer may include: calculating a second text similarity between the research field of the attribute association data of the target customer and the project name of the attribute association data of the project-related customer; calculating a third data information matching degree between the professional title of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; calculating a fourth data information matching degree between the number of scientific research achievements of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; and determining the data information matching degree based on the second text similarity, the third data information matching degree, and the fourth data information matching degree.

[0077] The second text similarity can be the text similarity between the research field of the target customer's attribute-related data and the project name of the project-related customer's attribute-related data. The third data information matching degree can be the numerical information matching degree between the professional title of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data. The fourth data information matching degree can be the numerical information matching degree between the number of scientific research achievements of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data.

[0078] In a multi-customer information recommendation scenario involving research project application information, the attribute-related data of target customers can include professional title, number of research achievements, and research field, while the target matching information can be research project application information. Accordingly, in this scenario, a target customer profile can be generated based on the target customer's professional attribute-related data and the project funding-related data of the research projects the target customer may apply for. The target customers can then be categorized, and research project information can be recommended to them based on this categorization.

[0079] Therefore, in a multi-customer information recommendation scenario involving research project application information, when calculating the text similarity and data information matching degree between the attribute-related data of the target customer and the attribute-related data of the project-related customer, the text similarity between the research field of the target customer's attribute-related data and the project name of the project-related customer's attribute-related data can be calculated, and the result can be used as the second text similarity. The numerical information matching degree between the professional title of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data can also be calculated, and the result can be used as the third data information matching degree. Furthermore, the numerical information matching degree between the number of research achievements of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data can be calculated, and the result can be used as the fourth data information matching degree. After obtaining the second, third, and fourth data information matching degrees, a weighted sum can be performed on these three scores, and the weighted sum can be used as the data information matching degree. For example, the weights of the second text similarity, the third data information matching degree, and the fourth data information matching degree can all be 1 / 3. This embodiment of the invention does not limit the specific values ​​of the weights of the second text similarity, the third data information matching degree, and the fourth data information matching degree. When the attribute-related data of the target customer includes professional title, number of research achievements, and research field, the above scheme calculates the text similarity and data information matching degree between the attribute-related data of the target customer and the attribute-related data of the project-related customer, thereby enabling the push of matching research project application information to the target customer.

[0080] In a specific example, target customer B is a scientific and technical personnel working at a university. Target customer B's attribute-related data includes their professional title, number of research achievements, and research field. Project-related customer attribute-related data includes the project name and application requirements. Therefore, the project-related customer attribute-related data can be matched with the attribute-related data. Analysis of the project matching results shows that target customer B's professional title, number of research achievements, and research field meet the application requirements for National Natural Science Foundation of China (NSFC) project X. Therefore, information such as the NSFC project application process and policy interpretations can be sent to target customer B.

[0081] In an optional embodiment of the present invention, the attribute association data of the target customer may include enterprise type, enterprise revenue information, enterprise size information, and the number of enterprise intellectual property rights; the target matching information may include technology industry project information; the calculation of the numerical information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer may include: calculating a third text similarity between the enterprise type of the attribute association data of the target customer and the project name of the attribute association data of the project-related customer; calculating a fifth data information matching degree between the enterprise revenue information of the attribute association data of the target customer and the total amount of funds of the attribute association data of the project-related customer; calculating a sixth data information matching degree between the enterprise size information of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; calculating a seventh data information matching degree between the number of enterprise intellectual property rights of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; and determining the data information matching degree based on the third text similarity, the fifth data information matching degree, the sixth data information matching degree, and the seventh data information matching degree.

[0082] The third text similarity can be the text similarity between the enterprise type in the target customer's attribute-related data and the project name in the project-related customer attribute-related data. The fifth data information matching degree can be the numerical information matching degree between the enterprise revenue information in the target customer's attribute-related data and the total funds in the project-related customer attribute-related data. The sixth data information matching degree can be the numerical information matching degree between the enterprise size information in the target customer's attribute-related data and the application conditions in the project-related customer attribute-related data. The seventh data information matching degree can be the numerical information matching degree between the number of enterprise intellectual property rights in the target customer's attribute-related data and the application conditions in the project-related customer attribute-related data.

[0083] In a multi-customer information recommendation scenario for technology industry project information, the attribute-related data of target customers can include enterprise type, enterprise revenue information, enterprise size information, and the number of intellectual property rights of the enterprise. The target matching information can be technology industry project information. Accordingly, in this scenario, a target customer profile can be generated based on the attribute-related data of the target customer in terms of enterprise operation and the project funding-related data of the technology industry projects that the target customer may apply for. The target customers can then be categorized, and technology industry project information can be recommended to them based on the categorization results.

[0084] Therefore, in the information recommendation scenario involving multiple customers in the technology industry, when calculating the text similarity and data information matching degree between the attribute-related data of the target customer and the attribute-related data of the project-related customer, the text similarity between the enterprise type of the attribute-related data of the target customer and the project name of the attribute-related data of the project-related customer can be calculated, and the result is used as the third text similarity; the numerical information matching degree between the enterprise revenue information of the attribute-related data of the target customer and the total amount of funds of the attribute-related data of the project-related customer can be calculated, and the result is used as the fifth data information matching degree; the numerical information matching degree between the enterprise size information of the attribute-related data of the target customer and the application conditions of the attribute-related data of the project-related customer can be calculated, and the result is used as the sixth data information matching degree; the numerical information matching degree between the number of enterprise intellectual property rights of the attribute-related data of the target customer and the application conditions of the attribute-related data of the project-related customer can be calculated, and the result is used as the seventh data information matching degree. After calculating the third text similarity, fifth data information matching degree, sixth data information matching degree, and seventh data information matching degree, a weighted sum can be performed on these scores, and the result is taken as the data information matching degree. For example, the weights of the third text similarity, fifth data information matching degree, sixth data information matching degree, and seventh data information matching degree can all be 1 / 4. This embodiment of the invention does not limit the specific values ​​of the weights for these weights. The above scheme, when the target customer's attribute-related data includes enterprise type, enterprise revenue information, enterprise size information, and the number of enterprise intellectual property rights, calculates the text similarity and data information matching degree between the target customer's attribute-related data and the project-related customer's attribute-related data, thereby enabling the push of matching technology industry project information to the target customer.

[0085] In a specific example, the target customer is Company C. Its associated attribute data includes company type, revenue information, size information, and number of intellectual property rights. The project-related customer attribute data includes project name, total funding amount, and application requirements. Therefore, Company C's project-related customer attribute data can be matched with its associated attribute data. Analysis of the matching results shows that Company C's company type, revenue information, size information, and number of intellectual property rights meet the criteria for high-tech enterprise certification. Therefore, information such as the high-tech enterprise application process and the preferential policies available to high-tech enterprises can be pushed to Company C.

[0086] S250. Generate a target customer profile for the target customer based on the project matching results and the scenario classification tags of the target customer.

[0087] Specifically, after obtaining the project matching results, if the matching is successful, the associated customer attribute data can be added to the target customer profile, enabling a more comprehensive portrayal of the target customer's business capabilities and professional background. Simultaneously, scenario-based category tags can be added to the target customer profile, allowing for more accurate information recommendations to be provided in different scenarios. Furthermore, combining the attribute data of the target customer can create a complete target customer profile.

[0088] S260. Classify the target customers according to the target customer profile and determine the customer list to which the target customers belong.

[0089] S270. Based on the type of the customer list, recommend target matching information to each customer included in the customer list.

[0090] This invention acquires customer attribute association data and project funding association data of target customers, and determines the scenario classification tags of target customers based on the target customer attribute association data. Simultaneously, it parses the target customer's project funding association data to obtain project-related customer attribute association data. Further, it matches the project-related customer attribute association data with the target customer's attribute association data to obtain project matching results, thereby generating a target customer profile based on the project matching results and the target customer's scenario classification tags. Further, it classifies target customers based on their target customer profiles, determines the customer list to which each target customer belongs, and then recommends targeted matching information to each customer in the customer list based on the type of the customer list. This solution introduces project funding association data for customer classification, enabling more accurate customer classification and improving the accuracy of customer classification. It solves the problem of inaccurate customer group classification caused by insufficient data in existing information recommendation methods, thereby improving the accuracy of linked information recommendations.

[0091] In the technical solution disclosed herein, the information collected (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0092] It should be noted that, in this embodiment of the invention, a corresponding operation entry can be provided to the user, allowing the user to choose to agree to or reject the automated decision result; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0093] It should be noted that any arrangement or combination of the technical features in the above embodiments also falls within the protection scope of this invention.

[0094] Example 3

[0095] Figure 3 This is a schematic diagram of a multi-customer interactive information recommendation device provided in Embodiment 3 of the present invention, as shown below. Figure 3 As shown, the device includes: a data acquisition module 310, a target customer profile generation module 320, a customer list determination module 330, and a target matching information recommendation module 330, wherein:

[0096] The data acquisition module 310 is used to acquire attribute-related data and project funding-related data of the target customer.

[0097] The target customer profile generation module 320 is used to generate a target customer profile of the target customer based on the attribute association data and project funding association data of the target customer.

[0098] The customer list determination module 330 is used to classify the target customers according to the target customer profile of the target customers and determine the customer list to which the target customers belong.

[0099] The target matching information recommendation module 340 is used to recommend target matching information to each customer included in the customer list based on the type of the customer list.

[0100] This invention, in its embodiments, acquires attribute-related data and project funding-related data of target customers, and generates target customer profiles based on these data. Furthermore, it categorizes target customers according to their profiles, determines the customer list to which each target customer belongs, and then recommends matching information to each customer in the customer list based on the type of the customer list. This solution introduces project funding-related data for customer classification, enabling more accurate customer categorization and improving the accuracy of customer classification. It solves the problem of inaccurate customer group classification caused by insufficient data in existing information recommendation methods, thereby improving the accuracy of linked information recommendations.

[0101] Optionally, the target customer profile generation module 320 is specifically used for: determining the scenario classification label of the target customer based on the attribute association data of the target customer; parsing the project funding association data of the target customer to obtain project-related customer attribute association data; matching the project-related customer attribute association data with the attribute association data of the target customer to obtain a project matching result; and generating a target customer profile of the target customer based on the project matching result and the scenario classification label of the target customer.

[0102] Optionally, the target customer profile generation module 320 is further configured to: determine the scenario classification result of information recommendation based on the attribute association data of the target customer using artificial intelligence; and determine the category customer tag of the target customer based on the attribute association data of the target customer and the scenario classification result.

[0103] Optionally, the target customer profile generation module 320 is further configured to: calculate the text similarity and data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer; wherein, the attribute association data of the project-related customer includes: project name, total amount of funds, disbursement batches, disbursement progress and application conditions; determine a comprehensive matching score based on the text similarity and the data information matching degree; and output the project matching result based on the comprehensive matching score.

[0104] Optionally, the target customer's attribute association data includes transaction name, transaction amount, and transaction time; the target matching information includes financial product information; the target customer profile generation module 320 is further configured to: calculate a first text similarity between the transaction name of the target customer's attribute association data and the project name of the project-related customer's attribute association data; calculate a first data information matching degree between the transaction amount of the target customer's attribute association data and the total amount of funds of the project-related customer's attribute association data; calculate a second data information matching degree between the transaction time of the target customer's attribute association data and the issuance batch of the project-related customer's attribute association data; and determine the data information matching degree based on the first text similarity, the first data information matching degree, and the second data information matching degree.

[0105] Optionally, the attribute association data of the target customer includes professional title, number of scientific research achievements, and research field; the target matching information includes scientific research project application information; the target customer profile generation module 320 is further used to: calculate a second text similarity between the research field of the attribute association data of the target customer and the project name of the attribute association data of the project-related customer; calculate a third data information matching degree between the professional title of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; calculate a fourth data information matching degree between the number of scientific research achievements of the attribute association data of the target customer and the application conditions of the attribute association data of the project-related customer; and determine the data information matching degree based on the second text similarity, the third data information matching degree, and the fourth data information matching degree.

[0106] Optionally, the target customer attribute association data includes enterprise type, enterprise revenue information, enterprise size information, and the number of enterprise intellectual property rights; the target matching information includes technology industry project information; the target customer profile generation module 320 is further configured to: calculate a third text similarity between the enterprise type of the target customer attribute association data and the project name of the project-related customer attribute association data; calculate a fifth data information matching degree between the enterprise revenue information of the target customer attribute association data and the total amount of funds of the project-related customer attribute association data; calculate a sixth data information matching degree between the enterprise size information of the target customer attribute association data and the application conditions of the project-related customer attribute association data; calculate a seventh data information matching degree between the number of enterprise intellectual property rights of the target customer attribute association data and the application conditions of the project-related customer attribute association data; and determine the data information matching degree based on the third text similarity, the fifth data information matching degree, the sixth data information matching degree, and the seventh data information matching degree.

[0107] The aforementioned multi-customer collaborative information recommendation device can execute the multi-customer collaborative information recommendation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method. Technical details not described in detail in this embodiment can be found in the multi-customer collaborative information recommendation method provided in any embodiment of the present invention.

[0108] Since the multi-customer linkage information recommendation device described above is an apparatus capable of executing the multi-customer linkage information recommendation method in the embodiments of the present invention, those skilled in the art can understand the specific implementation methods and various variations of the multi-customer linkage information recommendation device in this embodiment based on the multi-customer linkage information recommendation method described in the embodiments of the present invention. Therefore, how the multi-customer linkage information recommendation device implements the multi-customer linkage information recommendation method in the embodiments of the present invention will not be described in detail here. Any apparatus used by those skilled in the art to implement the multi-customer linkage information recommendation method in the embodiments of the present invention falls within the scope of protection of this application.

[0109] Example 4

[0110] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0111] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0112] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0113] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as multi-client interactive information recommendation methods.

[0114] In some embodiments, the multi-client interactive information recommendation method can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the multi-client interactive information recommendation method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the multi-client interactive information recommendation method by any other suitable means (e.g., by means of firmware).

[0115] Optionally, the multi-customer linkage information recommendation method may include: acquiring attribute association data and project funding association data of target customers; generating a target customer profile of the target customer based on the attribute association data and project funding association data of the target customer; classifying the target customer based on the target customer profile of the target customer to determine the customer list to which the target customer belongs; and recommending target matching information to each customer included in the customer list according to the type of the customer list.

[0116] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0118] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0119] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0120] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0121] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0122] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0123] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A multi-customer collaborative information recommendation method, characterized in that, include: Obtain attribute-related data and project funding-related data of target customers; A target customer profile is generated based on the attribute association data and project funding association data of the target customer. Based on the target customer profile, the target customers are categorized to determine the customer list to which the target customers belong; Based on the type of the customer list, target matching information is recommended to each customer included in the customer list.

2. The method according to claim 1, characterized in that, The step of generating a target customer profile based on the target customer's attribute association data and project funding association data includes: Determine the scenario classification tags of the target customers based on the attribute association data of the target customers; The project funding data of the target customers is parsed to obtain the project-related customer attribute data. The project-related customer attribute data is matched with the target customer attribute data to obtain the project matching result; A target customer profile is generated based on the project matching results and the scenario classification tags of the target customer.

3. The method according to claim 2, characterized in that, The step of determining the scenario classification tag of the target customer based on the attribute association data of the target customer includes: The scenario classification results for information recommendation are determined based on the attribute association data of the target customer using artificial intelligence. The target customer's category label is determined based on the attribute association data of the target customer and the scenario classification results.

4. The method according to claim 2, characterized in that, The step of matching the project-related customer attribute association data with the target customer attribute association data to obtain the project matching result includes: Calculate the text similarity and data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer; wherein, the attribute association data of the project-related customer includes: project name, total amount of funds, disbursement batches, disbursement progress and application conditions; A comprehensive matching score is determined based on the text similarity and the data information matching degree. The project matching result is output based on the comprehensive matching score.

5. The method according to claim 4, characterized in that, The target customer's attribute association data includes transaction name, transaction amount, and transaction time; the target matching information includes financial product information; the calculation of the data information matching degree between the target customer's attribute association data and the project-related customer attribute association data includes: Calculate the first text similarity between the transaction name in the attribute-related data of the target customer and the project name in the attribute-related data of the project-related customer; Calculate the first data information matching degree between the transaction amount of the target customer's attribute-related data and the total funds of the project-related customer's attribute-related data; Calculate the second data information matching degree between the transaction time of the target customer's attribute-related data and the distribution batch of the project-related customer attribute-related data; The data information matching degree is determined based on the first text similarity, the first data information matching degree, and the second data information matching degree.

6. The method according to claim 4, characterized in that, The attribute association data of the target customer includes professional title, number of scientific research achievements, and research field; the target matching information includes scientific research project application information; the calculation of the data information matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer includes: Calculate the second text similarity between the research field of the target customer's attribute-related data and the project name of the project-related customer's attribute-related data; Calculate the third data information matching degree between the professional title of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data; Calculate the fourth data information matching degree between the number of scientific research achievements of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data; The data information matching degree is determined based on the second text similarity, the third data information matching degree, and the fourth data information matching degree.

7. The method according to claim 4, characterized in that, The attribute association data of the target customers includes enterprise type, enterprise revenue information, enterprise size information, and the number of enterprise intellectual property rights; the target matching information includes information on technology industry projects. The calculation of the numerical matching degree between the attribute association data of the target customer and the attribute association data of the project-related customer includes: Calculate the third text similarity between the enterprise type of the attribute-related data of the target customer and the project name of the attribute-related data of the project-related customer; Calculate the fifth data information matching degree between the enterprise revenue information of the target customer's attribute-related data and the total funds of the project-related customer's attribute-related data; Calculate the sixth data information matching degree between the enterprise size information of the target customer's attribute-related data and the application conditions of the project-related customer's attribute-related data; Calculate the seventh data information matching degree between the number of enterprise intellectual property rights in the attribute-related data of the target customer and the application conditions in the attribute-related data of the project-related customer; The data information matching degree is determined based on the third text similarity, the fifth data information matching degree, the sixth data information matching degree, and the seventh data information matching degree.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that is executed by the at least one processor, such that the at least one processor can perform the multi-client interactive information recommendation method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the information recommendation method for multi-client interaction as described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, wherein, When the computer program / instruction is executed by the processor, it implements the multi-customer linkage information recommendation method as described in any one of claims 1-7.

Images