Replacement resource service recommendation method and device, equipment, medium and program product

Abstract

The invention discloses a replacement resource service recommendation method and device, equipment, a medium and a program product, and relates to the technical field of big data. The method comprises the following steps: respectively obtaining business data, log data, user production and operation data and replacement resource demand data of a target user; the user production and operation data and the replacement resource demand data are acquired based on the form of a replacement resource service questionnaire, and a target user portrait is constructed according to the acquired data; adopting a preset recommendation model to analyze the target user portrait through a machine learning algorithm, and generating a replacement resource service based on a plurality of replacement resource products in a product feature library and product features corresponding to the plurality of replacement resource products; and pushing the replacement resource service to the target user. According to the embodiment of the invention, the recommendation efficiency and accuracy of the replacement resource service of the user can be effectively improved, so that the satisfaction degree of the user on the recommended replacement resource service and the conversion rate of the replacement resource service can be fully improved.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and in particular, relates to a replacement resource service recommendation method, device, equipment, medium and program product. Background Art

[0002] In recent years, with the continuous development of the rural economy and the rapid advancement of financial technology, users' demand for replacement resources has increased. However, under the traditional replacement resource processing method, users' access to replacement resources is limited, and the accuracy of replacement resource recommendations is low, resulting in low user satisfaction with the recommended replacement resource service and a low replacement resource acceptance rate. Based on this, the industry is still in urgent need of a new user replacement resource service recommendation solution to fully improve user satisfaction with the recommended replacement resource service, so as to fully improve the replacement resource service recommendation efficiency of replacement resource products and improve the replacement resource service conversion rate. Summary of the invention

[0003] The embodiments of the present application provide a replacement resource service recommendation method, apparatus, device, medium and program product, which can effectively improve the recommendation efficiency and accuracy of replacement resource services for users, thereby fully improving the user's satisfaction with the recommended replacement resource services and the replacement resource service conversion rate.

[0004] In a first aspect, an embodiment of the present application provides a replacement resource service recommendation method, the replacement resource service recommendation method comprising:

[0005] The target user's business data, log data, user production and operation data, and replacement resource demand data are obtained respectively; the user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire;

[0006] Build a target user profile for the target user based on business data, log data, user production and operation data, and replacement resource demand data;

[0007] The preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on multiple replacement resource products in the product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service matching the target user portrait is generated;

[0008] The resource replacement service is pushed to the target user; wherein the resource replacement service includes the type of resource replacement product matched with the target user, the recommended resource replacement timing, the resource replacement amount and the repayment plan.

[0009] In some possible implementations, a target user profile of a target user is constructed based on business data, log data, user production and operation data, and replacement resource demand data, including:

[0010] When the production and operation data and replacement resource demand data of the user are obtained, the basic user profile of the target user is supplemented based on the production and operation data and replacement resource demand data to construct a target user profile of the target user in the current cycle;

[0011] Among them, the basic user portrait is pre-constructed based on the business data and log data of the target user; the data change frequency of the user's production and operation data and replacement resource demand data is higher than that of the business data and log data.

[0012] In some possible implementations, a preset recommendation model is used to analyze the target user profile through a machine learning algorithm, and based on a plurality of replacement resource products in a product feature library and the product features respectively corresponding to the plurality of replacement resource products, a replacement resource service matching the target user profile is generated, including:

[0013] Based on the recommendation model, the target user portrait is analyzed by using the K-means clustering algorithm to obtain the target credit risk group to which the target user belongs, and the decision tree is used to predict whether the target user has a demand for replacement resources, thereby obtaining the replacement resource demand prediction result;

[0014] Analyze the target user portrait based on the recommendation model to determine the target user's production cycle and income fluctuation;

[0015] Based on multiple replacement resource products stored in the product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service matching the target credit risk group, replacement resource demand forecast results, production cycle and income fluctuation is determined.

[0016] In some possible implementations, obtaining user production and operation data and replacement resource demand data of a target user includes:

[0017] Obtaining the target user's questionnaire response information to a preset resource replacement service questionnaire, wherein the preset resource replacement service questionnaire is provided with inquiry information corresponding to the user's production and operation data and the resource replacement demand data;

[0018] Based on the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted.

[0019] In some possible implementations, after obtaining the target user's questionnaire response information to the preset replacement resource service questionnaire, the replacement resource service recommendation method further includes:

[0020] Send the questionnaire response information to the target auditor so that the target auditor can verify whether the questionnaire response information is authentic;

[0021] Based on the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted, including:

[0022] When the target auditor has verified and passed the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted based on the questionnaire response information.

[0023] In some possible implementations, a target user profile of a target user is constructed based on business data, log data, user production and operation data, and replacement resource demand data, including:

[0024] Perform data cleaning, data integration and data standardization on business data, log data, user production and operation data and replacement resource demand data to obtain summary data that meets data processing standards;

[0025] Based on the aggregated data, a target user profile of the target user is constructed.

[0026] In some possible implementations, before using a preset recommendation model to analyze the target user portrait through a machine learning algorithm, the replacement resource service recommendation method further includes:

[0027] Obtain historical replacement resource services and corresponding historical user portraits;

[0028] Based on historical user portraits and historical replacement resource services, the recommendation model is trained through machine learning algorithms.

[0029] In some possible implementations, the user's production and management data includes: at least one of: the type of crops planted, the sowing time, the expected yield, and the use of agricultural machinery and equipment;

[0030] The replacement resource demand data includes at least one of a replacement resource amount, a replacement resource period, and a replacement resource purpose.

[0031] Based on the same inventive concept, in a second aspect, an embodiment of the present application provides a replacement resource service recommendation device, the replacement resource service recommendation device comprising:

[0032] The first acquisition module is used to respectively acquire the target user's business data, log data, user production and operation data, and replacement resource demand data; the user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire;

[0033] The first construction module is used to construct a target user portrait of the target user based on business data, log data, user production and operation data, and replacement resource demand data;

[0034] The first generation module is used to analyze the target user portrait through a machine learning algorithm, and generate a replacement resource service matching the target user portrait based on multiple replacement resource products in the product feature library and the product features respectively corresponding to the multiple replacement resource products;

[0035] The first push module is used to push the replacement resource service to the target user; wherein the replacement resource service includes the replacement resource product type matched by the target user, the recommended replacement resource timing, the replacement resource amount and the repayment plan.

[0036] In a third aspect, an embodiment of the present application provides a replacement resource service recommendation device, the replacement resource service recommendation device comprising:

[0037] a processor and a memory storing computer program instructions;

[0038] When the processor executes the computer program instructions, the replacement resource service recommendation method provided in any one of the above embodiments of the present application is implemented.

[0039] In a fourth aspect, an embodiment of the present application provides a computer storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, a replacement resource service recommendation method as provided in any one of the above-mentioned embodiments of the present application is implemented.

[0040] In a fifth aspect, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes a replacement resource service recommendation method as provided in any one of the above-mentioned embodiments of the present application.

[0041] The embodiments of the present application provide a replacement resource service recommendation method, device, equipment, medium and program product, which respectively obtains the business data, log data, user production and operation data and replacement resource demand data of the target user. The above-mentioned user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire. Then, based on the acquired business data, log data, user production and operation data and replacement resource demand data, a target user portrait of the target user is constructed. In this way, a preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on multiple replacement resource products in a product feature library and the product features corresponding to multiple replacement resource products, a replacement resource service matching the target user portrait is generated, and finally the replacement resource service including the replacement resource product type, the recommended replacement resource timing, the replacement resource amount and the repayment plan is pushed to the target user.

[0042] It can be seen from the above description that a replacement resource service recommendation method, device, equipment, medium and program product of the embodiment of the present application fully considers the production and operation characteristics and seasonal income of the user, and comprehensively supplements and constructs the user portrait from the multi-dimensional data source by supplementing the user's production and operation data and replacement resource demand data, thereby greatly improving the accuracy of the user portrait, which is conducive to more efficient and accurate replacement resource service mining and processing. Then, the recommendation model is used to analyze the user portrait through a machine learning algorithm to match the replacement resource products of the corresponding product features in the product feature library, so as to accurately obtain the user's replacement resource service in a targeted manner, and then push the replacement resource service to the user at the right time. The replacement resource service recommendation method, device, equipment, medium and program product of the embodiment of the present application can effectively improve the recommendation efficiency of the user's replacement resource service and improve the user's satisfaction with the recommended replacement resource service, thereby fully improving the conversion rate of the replacement resource service and the risk control ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0044] Figure 1 It is a flowchart of a replacement resource service recommendation method provided by an embodiment of the present application;

[0045] Figure 2 It is a schematic diagram of the system framework of a replacement resource service recommendation method provided by an embodiment of the present application;

[0046] Figure 3 It is a system flow diagram of a replacement resource service recommendation method provided by an embodiment of the present application;

[0047] Figure 4 It is a structural diagram of a replacement resource service recommendation device provided in an embodiment of the present application;

[0048] Figure 5 It is a structural diagram of a replacement resource service recommendation device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0050] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0051] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations.

[0052] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0053] As described in the background technology section, users' demand for replacement resources is increasing day by day. However, it is currently impossible to accurately and specifically push replacement resource services to users. Users are not satisfied with the recommended replacement resource services, resulting in a low replacement resource acceptance rate.

[0054] In view of the above, in order to provide appropriate replacement resource products and services according to the specific needs and preferences of users, the embodiments of the present application provide a replacement resource service recommendation method, device, equipment, medium and program product. It should be noted that the embodiments provided in this application are not intended to limit the scope of the disclosure of this application.

[0055] The following first introduces the replacement resource service recommendation method provided in the embodiment of the present application.

[0056] Figure 1The flowchart of the replacement resource service recommendation method provided by an embodiment of the present application is shown. The replacement resource service recommendation method is applied to an electronic device, which may include a server or a user terminal. Figure 1 As shown, the replacement resource service recommendation method includes the following steps:

[0057] S110, respectively obtaining the target user's business data, log data, user production and operation data, and replacement resource demand data; the user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire;

[0058] S120, constructing a target user profile of the target user based on the business data, log data, user production and operation data, and replacement resource demand data;

[0059] S130, using a preset recommendation model to analyze the target user profile through a machine learning algorithm, and based on a plurality of replacement resource products in a product feature library and product features corresponding to the plurality of replacement resource products, generating a replacement resource service matching the target user profile;

[0060] S140, pushing the resource replacement service to the target user; wherein the resource replacement service includes the type of replacement resource product matched by the target user, the recommended resource replacement timing, the resource replacement amount and the repayment plan.

[0061] The embodiment of the present application provides a replacement resource service recommendation method, which obtains the target user's business data, log data, user production and operation data, and replacement resource demand data respectively. The above-mentioned user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire. Then, based on the acquired business data, log data, user production and operation data, and replacement resource demand data, a target user portrait of the target user is constructed. In this way, a preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on multiple replacement resource products in a product feature library and the product features corresponding to multiple replacement resource products, a replacement resource service matching the target user portrait is generated, and finally the replacement resource service including the replacement resource product type, the recommended replacement resource timing, the replacement resource amount, and the repayment plan is pushed to the target user.

[0062] It can be seen from the above description that a replacement resource service recommendation method of an embodiment of the present application fully considers the production and operation characteristics and seasonal income of the user, and comprehensively supplements and constructs the user portrait from a multi-dimensional data source by supplementing the user's production and operation data and replacement resource demand data, thereby greatly improving the accuracy of the user portrait, which is conducive to more efficient and accurate replacement resource service mining and processing. Then, the recommendation model is used to analyze the user portrait through a machine learning algorithm to match the replacement resource products with corresponding product features in the product feature library, so as to accurately obtain the user's replacement resource service in a targeted manner, and then push the replacement resource service to the user at the right time. The replacement resource service recommendation method of the embodiment of the present application can effectively improve the recommendation efficiency of the user's replacement resource service and the user's satisfaction with the recommended replacement resource service, thereby fully improving the conversion rate of the replacement resource service and the risk control ability.

[0063] The specific implementation of the above steps 110 to 140 is described in detail below.

[0064] In S110, during specific implementation, the target user's business data, log data, user production and operation data, and replacement resource demand data are obtained respectively; the user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire.

[0065] Among them, the users in this application can specifically refer to users who engage in production and operation of agricultural products.

[0066] The above-mentioned business data and log data may specifically include basic information of users, consumption habit data, geographic environment data, historical resource replacement data, and behavior log data, etc. The above-mentioned basic information, such as age, gender, family members, education level, etc.; consumption habit data, such as consumption frequency, consumption amount, purchased commodity categories, etc.; geographic environment data, such as farmland location, area, natural disaster risk, etc.; historical resource replacement data, such as the number of resource replacements, the amount of resource replacements, the period of resource replacements, etc.; behavior log data, such as search records, browsing records, click records, etc.

[0067] And, more specifically, the user production and operation data may include at least one of: the type of crops planted, sowing time, expected yield, and the use of agricultural machinery and equipment. The replacement resource demand data may include at least one of the replacement resource amount, replacement resource period, and replacement resource purpose.

[0068] Furthermore, considering that the above-mentioned user production and operation data and replacement resource demand data often change frequently, this application supplements them by means of an online replacement resource service survey by the user client, thereby effectively solving the current lack of information on user production and operation.

[0069] According to some embodiments of the present application, optionally, in order to more reasonably obtain the user production and operation data and the replacement resource demand data through the replacement resource service questionnaire form, the above-mentioned acquisition of the user production and operation data and the replacement resource demand data of the target user may include:

[0070] Obtaining the target user's questionnaire response information to a preset resource replacement service questionnaire, wherein the preset resource replacement service questionnaire is provided with inquiry information corresponding to the user's production and operation data and the resource replacement demand data;

[0071] Based on the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted.

[0072] In this embodiment, the inquiry information in the replacement resource service questionnaire can be set accordingly in combination with the actual information acquisition needs, so as to obtain the questionnaire response information of the preset replacement resource service questionnaire. Then, the received questionnaire response information is processed and summarized through technical means such as keyword extraction and semantic analysis, so as to accurately and effectively extract the above-mentioned user production and operation data and replacement resource demand data.

[0073] According to some embodiments of the present application, optionally, in order to further ensure the reliability and authenticity of the above-mentioned user production and operation data and replacement resource demand data, after obtaining the target user's questionnaire response information to the preset replacement resource service questionnaire, the replacement resource service recommendation method may further include:

[0074] Send the questionnaire response information to the target auditor so that the target auditor can verify whether the questionnaire response information is authentic;

[0075] Based on the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted, which may include:

[0076] When the target auditor has verified and passed the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted based on the questionnaire response information.

[0077] In specific implementation, after receiving the target user's questionnaire response information for the preset resource replacement service questionnaire, the questionnaire response information can be forwarded to the pre-agreed target reviewer. After receiving the questionnaire response information, the target reviewer can verify whether the questionnaire response information is true and accurate based on the actual understanding of the user's production and operation and experience analysis.

[0078] When the target auditor has approved the questionnaire response information, it indicates that the authenticity and accuracy of the questionnaire response information are relatively reliable. In this case, the above-mentioned user production and operation data and replacement resource demand data are extracted based on the questionnaire response information.

[0079] In this embodiment, since the authenticity and accuracy of the questionnaire response information filled in by the user have been verified, the reliability of the above-mentioned user production and operation data and replacement resource demand data can be effectively guaranteed.

[0080] In S120, during the specific implementation, a target user portrait of the target user is constructed based on the business data, log data, user production and operation data, and replacement resource demand data.

[0081] According to some embodiments of the present application, optionally, in order to more reasonably and efficiently realize the accurate construction of the target user portrait, the target user portrait of the target user constructed based on the business data, log data, user production and operation data and replacement resource demand data may include:

[0082] When the production and operation data and replacement resource demand data of the user are obtained, the basic user profile of the target user is supplemented based on the production and operation data and replacement resource demand data to construct a target user profile of the target user in the current cycle;

[0083] Among them, the basic user portrait is pre-constructed based on the business data and log data of the target user; the data change frequency of the user's production and operation data and replacement resource demand data is higher than that of the business data and log data.

[0084] In specific implementation, a basic user portrait can be established through these business data and log data. However, this basic portrait fails to fully consider the user's production and operation characteristics and seasonal income, which affects the accuracy of the user portrait and, in turn, affects the precise push of replacement resource services.

[0085] Therefore, in this embodiment, the user portrait is further supplemented and constructed by collecting the user's production and operation data and replacement resource demand data, so as to facilitate the subsequent push of more accurate replacement resource services based on the user portrait.

[0086] At the same time, this application takes into account that the above-mentioned user production and operation data and replacement resource demand data often change frequently, so it can be supplemented by the user client online replacement resource service survey, thereby effectively solving the current lack of information on user production and operation. In addition, the replacement resource service questionnaire is used to obtain user production and operation data and replacement resource demand data, and the specific information is answered by the user himself, which helps to achieve more targeted and accurate construction of user portraits.

[0087] It should be added that the business data and log data of the above-mentioned users are often relatively fixed, while the production and operation data and replacement resource demand data of the above-mentioned users often change frequently. Therefore, the data collection frequency of business data and log data can be lower than the data collection frequency of user production and operation data and replacement resource demand data.

[0088] In this way, a basic profile can be built in advance based on business data and log data, and then supplemented with the latest collected user production and operation data and replacement resource demand data to obtain the latest target user profile. This helps to greatly improve the efficiency of building a complete user profile for the target user.

[0089] According to some embodiments of the present application, optionally, considering that the above-collected data format specifications may be inconsistent and there may be duplicate or erroneous data, therefore, in order to fully realize the reasonable and accurate construction of the target user portrait, the above-mentioned target user portrait constructed based on business data, log data, user production and operation data and replacement resource demand data may include:

[0090] Perform data cleaning, data integration and data standardization on business data, log data, user production and operation data and replacement resource demand data to obtain summary data that meets data processing standards;

[0091] Based on the aggregated data, a target user profile of the target user is constructed.

[0092] In this embodiment, when cleaning the above-mentioned business data, log data, user production and operation data, and replacement resource demand data, the accuracy and consistency of the data can be ensured by removing duplicate, erroneous, and irrelevant data. In addition, for missing values ​​in the data, interpolation, mean filling, and other methods can be used to complete the data.

[0093] After the data is cleaned as described above, the multi-dimensional data is integrated again, considering that the sources of different data are often different. In the data integration process, the user's identity information can be effectively used for data matching and association, thereby ensuring the consistency and integrity of the data.

[0094] In order to achieve the standardization of the above integrated data, different types of data are standardized and converted into a unified format and unit for subsequent analysis. For example, numerical data can be normalized and mapped into a unified range. This embodiment does not strictly limit the specific implementation means of data standardization.

[0095] Finally, based on the above preprocessed data, by using data mining techniques such as cluster analysis and association rules, a target user portrait corresponding to the target user is constructed. The target user portrait includes the target user's basic information, behavioral characteristics, interest preferences, consumption habits, etc. In addition, a user portrait data structure can also be constructed to sequentially splice each feature into a high-dimensional vector for use in replacement resource service analysis.

[0096] In S130, during the specific implementation, a preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on multiple replacement resource products in a product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service matching the target user portrait is generated.

[0097] The above-mentioned product feature library can be maintained by relevant management personnel to replace resource product information, extract the features of the replacement resource products through feature extraction means, and store the results in the product feature library, thereby realizing the construction of the product feature library.

[0098] The above-mentioned preset recommendation model can be obtained by obtaining historical replacement resource services and corresponding historical user portraits before using the preset recommendation model to analyze the target user portrait through a machine learning algorithm, and then training through a machine learning algorithm based on the historical user portraits and historical replacement resource services. This embodiment does not impose strict restrictions on this.

[0099] It should be added that in order to fully improve the accuracy of the recommendation model, the above-mentioned historical resource replacement service can be a resource replacement service under the premise that the user has successfully undertaken the project.

[0100] More specifically, in order to effectively generate a replacement resource service that matches the target user profile, a preset recommendation model is used to analyze the target user profile through a machine learning algorithm, and based on multiple replacement resource products in a product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service that matches the target user profile is generated, which may include:

[0101] Based on the recommendation model, the target user portrait is analyzed by using the K-means clustering algorithm to obtain the target credit risk group to which the target user belongs, and the decision tree is used to predict whether the target user has a demand for replacement resources, thereby obtaining the replacement resource demand prediction result;

[0102] Analyze the target user portrait based on the recommendation model to determine the target user's production cycle and income fluctuation;

[0103] Based on multiple replacement resource products stored in the product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service matching the target credit risk group, replacement resource demand forecast results, production cycle and income fluctuation is determined.

[0104] In this embodiment, the recommendation model obtained by training with a machine learning algorithm analyzes the target user portrait of the target user. Specifically, the recommendation model can use the K-means clustering algorithm to divide users into credit risk groups such as "high net worth customers", "potential replacement resource customers", and "low-risk customers", and then use a decision tree to predict whether the user has a replacement resource demand. The above recommendation model can be trained based on historical data to continuously improve the accuracy of the analysis.

[0105] In addition, managers can maintain different types of replacement resource products in advance, and divide the products according to different replacement resource terms, interest rates, amounts, repayment plans and other factors to meet users' diverse replacement resource needs, and then extract features from a variety of replacement resource products and store the product features corresponding to the replacement resource products in the product feature library.

[0106] In this way, by analyzing the above target user portraits, suitable replacement resource product types can be matched from the product feature library, such as seed replacement resources, agricultural machinery and equipment replacement resources, consumer replacement resources, etc. At the same time, the target user portrait can also be used to determine the target user's production cycle and income fluctuations, and then determine the best replacement resource timing and replacement resource quota based on the production cycle and income fluctuations, and provide flexible repayment plans, such as quarterly repayments and income sharing repayments.

[0107] In S140, during specific implementation, the replacement resource service is pushed to the target user; wherein the replacement resource service includes the replacement resource product type matched by the target user, the recommended replacement resource timing, the replacement resource amount and the repayment plan.

[0108] In this embodiment, the resource replacement service may be actively pushed to the target user via SMS, email, or client message, etc. Alternatively, in order to select a suitable push timing to improve user satisfaction, the resource replacement service may be pushed to the target user when the target user consults about the resource replacement related information, which is not strictly limited in this embodiment.

[0109] It should be added that, after the above-mentioned replacement resource service is pushed to the target user, if the target user successfully accepts the above-mentioned replacement resource service to replace the corresponding resources, it means that the replacement resource service is successfully converted.

[0110] In this case, the corresponding replacement resource services of the replacement resource products and the above-mentioned target user portraits can also be used as training samples of the above-mentioned recommendation model to train, update and optimize the recommendation model, so as to continuously improve the accuracy of the recommendation model.

[0111] In order to facilitate understanding of the resource replacement service recommendation method provided in the above embodiment, the above method is described below using a specific scenario embodiment. Figure 2 It is a schematic diagram of the system framework of a replacement resource service recommendation method provided by an embodiment of the present application; Figure 3 : is a system flow diagram of a replacement resource service recommendation method provided in an embodiment of the present application. It should be noted that: Figure 2 The medium-sized farmers are the users in this application, and specifically are users who engage in production and operation of agricultural products. Figure 2 The business opportunities etc. may be equivalent to the resource replacement service in the aforementioned embodiments of the present application.

[0112] See also Figure 2 1. Business opportunity collection and display

[0113] The user client is a mobile APP (Application) provided to users, which can be used to handle card opening, payment, resource replacement and other services online. The employee client is a mobile APP provided to employees, which can review and process various application materials online. The smart terminal is a terminal device provided to partners such as village committees, which can assist users in handling transfers, payment, resource replacement (such as loans) and other services.

[0114] The above business opportunity collection sources mainly include user clients, employee clients and smart terminals. They are responsible for collecting users' basic information, production and operation data, consumption habit data, geographic location and environmental data, etc., and storing these data in the database, mainly including the following data:

[0115] The above basic information, such as age, gender, family members, education level, etc.; consumption habit data, such as consumption frequency, consumption amount, purchased goods categories, etc.; geographical environment data, such as farmland location, area, natural disaster risks, etc.; historical resource replacement data, such as the number of resource replacements, the amount of resource replacements, the period of resource replacements, etc.; behavior log data, such as search records, browsing records, click records, etc.

[0116] The basic profile of users can be established through these business data and log data, but there is a lack of user production and operation data and replacement resource demand data. Such data often changes frequently and needs to be supplemented through online questionnaires on the user client. The customer manager will review the authenticity and accuracy of the filled data on the employee client and write it into the database after the review is passed. It mainly includes the following data:

[0117] The above production and operation data mainly include: types of crops planted, sowing time, expected output, use of agricultural machinery and equipment, etc. The above replacement resource demand data mainly include: replacement resource amount, replacement resource period, replacement resource use, etc.

[0118] At the same time, user clients, employee clients and smart terminals are also channels for displaying resource exchange services (business opportunities), which are displayed through in-site messages, homepage advertisements, pop-up reminders, etc.

[0119] 2. Data processing module

[0120] Responsible for integrating and cleaning the collected data to ensure data quality and facilitate the subsequent construction of accurate user portraits. The main steps include:

[0121] 1. Data cleaning: Remove duplicate, erroneous and irrelevant data to ensure data accuracy and consistency. Handle missing values ​​and use interpolation, mean filling and other methods to complete the data.

[0122] 2. Data integration: Integrate data from different sources to establish a unified data warehouse. Use user identity information to match and associate data to ensure data consistency and integrity.

[0123] 3. Data standardization: Standardize different types of data and convert them into a unified format and unit for subsequent analysis. Normalize numerical data and map them to a unified range (such as between 0 and 1); use One-Hot encoding to convert categorical data into numerical data, for example, "rice" and "wheat" in "crop types" are encoded as [1,0] and [0,1] respectively.

[0124] 3. User portrait module

[0125] Based on the preprocessed data, we use data mining techniques such as cluster analysis and association rules to build user portraits. User portraits include basic information, behavioral characteristics, interest preferences, consumption habits, etc. Finally, we build a user portrait data structure and sequentially splice each feature into a high-dimensional vector.

[0126] Assuming that the features such as age, gender, and education level are standardized, and the crop types are One-Hot encoded, the feature vector of user A may be as follows: User_Vector_A = [0.45, 1, 0, 0.5, 0.07, 0.4, 0.9, 1, 0.1] (assuming that 0.45 is the standardized age value, 1 represents male, 0.5 is the standardized education level value, 1 represents rice, 0 represents wheat, and so on). The user portrait results will be stored in the HBase database for subsequent business opportunity analysis.

[0127] 4. Business Opportunity Analysis Module

[0128] Through machine learning algorithms, user portraits are analyzed, and K-means clustering algorithms are used to divide users into groups such as "high net worth customers", "potential replacement resource customers", and "low-risk customers". Decision tree models are used to predict whether users have replacement resource needs. Algorithm models can be trained based on historical data to continuously improve recognition accuracy.

[0129] At the same time, managers maintain different types of replacement resource products into the database. Products are divided according to different replacement resource terms, interest rates, quotas, repayment plans and other factors to meet users' diverse replacement resource needs. After the system extracts features from replacement resource products, it stores the data in the product feature library.

[0130] According to the user portrait, suitable replacement resource products are matched from the product feature library, such as seed replacement resources, agricultural machinery replacement resources, consumer replacement resources, etc. At the same time, according to the production cycle and income fluctuations, the best time and amount of replacement resources are determined, and flexible repayment plans are provided, such as quarterly repayments and income sharing repayments. In addition, the above matching results will be stored in the ElasticSearch database for subsequent business opportunity push module queries.

[0131] 5. Business Opportunity Push Module

[0132] The business opportunity push module is mainly responsible for pushing relevant recommendation data to users, mainly including the following methods.

[0133] 1. Remind users to check replacement resource information via SMS, email or client message.

[0134] 2. Push the message to the employee client, and the employee will follow up on the resource replacement service.

[0135] 3. Provide query interface to user client and smart terminal, query and display exchange resource service (business opportunity) data when user logs in or trades.

[0136] exist Figure 2 Based on the system framework diagram provided Figure 3, this scenario embodiment may specifically include the following steps:

[0137] Step 1: Collect user data required for business opportunity processing from user clients or smart terminals, mainly including business data and log data. At the same time, use business opportunity questionnaires to obtain user production and operation data and replacement resource demand data as an important supplement to user portraits.

[0138] Step 2: Integrate, clean and standardize the collected data to ensure data quality; then store the pre-processed collected data in the data warehouse.

[0139] Step 3: Obtain the preprocessed collected data from the data warehouse to construct a user profile, and store the user profile results in the data warehouse.

[0140] Step 4: The management personnel maintain the replacement resource product information. The system uses corresponding feature extraction methods to extract the product features of the replacement resource products, and stores the extracted product features corresponding to the replacement resource products into the product feature library.

[0141] Step 5: The recommendation model analyzes the user portrait through a machine learning algorithm, matches the appropriate replacement resource product features from the product feature library, generates the replacement resource service corresponding to the user, and stores the replacement resource service in the data warehouse. In addition, historical data can be obtained from the data warehouse in advance to train the recommendation model in order to continuously improve the accuracy of model analysis.

[0142] Step 6: Query the replacement resource service corresponding to the user from the data warehouse, and then push the replacement resource service to the user or employee's terminal.

[0143] It should be added that the execution order of the above steps in this embodiment is only an example. In some other possible implementations, the execution order of the above steps can also be flexibly adjusted according to actual situations and needs.

[0144] In this scenario embodiment, unlike the traditional credit assessment that only relies on financial behavior data, the present invention comprehensively assesses the user's credit risk by integrating multi-dimensional data sources such as the user's production and operation data, consumption habit data, behavior data, and geographic location data. On this basis, through in-depth analysis of user behavior data and demand data, customized replacement resource service recommendations can be provided to users.

[0145] In summary, the embodiments of the present application analyze the user's production and operation behavior, replacement resource demand, consumption habits, social records and other data to accurately identify the user's replacement resource demand, and make personalized recommendations and risk assessments, thereby improving the replacement resource conversion rate and risk control capabilities, so as to achieve more efficient and accurate replacement resource service mining and processing, and promote the development of rural financial services.

[0146] Based on the replacement resource service recommendation method provided in the above embodiment, out of the same inventive concept, the present application also provides a replacement resource service recommendation device corresponding to the above replacement resource service recommendation method. Figure 4 A detailed introduction to the replacement resource service recommendation device.

[0147] Figure 4 A schematic diagram of the structure of a replacement resource service recommendation device provided in an embodiment of the present application is shown. Figure 4 The replacement resource service recommendation device 400 shown includes:

[0148] The first acquisition module 410 is used to respectively acquire the target user's business data, log data, user production and operation data, and replacement resource demand data; the user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire;

[0149] The first construction module 420 is used to construct a target user portrait of the target user based on the business data, log data, user production and operation data, and replacement resource demand data;

[0150] The first generating module 430 is used to analyze the target user profile through a machine learning algorithm, and generate a replacement resource service matching the target user profile based on a plurality of replacement resource products in a product feature library and product features respectively corresponding to the plurality of replacement resource products;

[0151] The first push module 440 is used to push the replacement resource service to the target user; wherein the replacement resource service includes the replacement resource product type matched by the target user, the recommended replacement resource timing, the replacement resource amount and the repayment plan.

[0152] A replacement resource service recommendation device provided in an embodiment of the present application obtains the target user's business data, log data, user production and operation data, and replacement resource demand data by setting corresponding functional modules. The above-mentioned user production and operation data and replacement resource demand data are collected in the form of a replacement resource service questionnaire. Then, based on the acquired business data, log data, user production and operation data, and replacement resource demand data, a target user portrait of the target user is constructed. In this way, a preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on multiple replacement resource products in a product feature library and the product features corresponding to multiple replacement resource products, a replacement resource service matching the target user portrait is generated, and finally the replacement resource service including the replacement resource product type, the recommended replacement resource timing, the replacement resource amount, and the repayment plan is pushed to the target user.

[0153] It can be seen from the above description that a replacement resource service recommendation device of an embodiment of the present application fully considers the production and operation characteristics and seasonal income of the user, and comprehensively supplements and constructs the user portrait from multi-dimensional data sources by supplementing the user's production and operation data and replacement resource demand data, thereby greatly improving the accuracy of the user portrait, which is conducive to more efficient and accurate replacement resource service mining and processing. Then, the recommendation model is used to analyze the user portrait through a machine learning algorithm to match the replacement resource products with corresponding product features in the product feature library, so as to accurately obtain the user's replacement resource service in a targeted manner, and then push the replacement resource service to the user at the right time. The replacement resource service recommendation device of the embodiment of the present application can effectively improve the recommendation efficiency of the user's replacement resource service, thereby fully improving the conversion rate and risk control ability of the replacement resource service.

[0154] In some possible implementations, the first construction module 520 constructs a target user portrait of a target user based on business data, log data, user production and operation data, and replacement resource demand data, including:

[0155] When the production and operation data and replacement resource demand data of the user are obtained, the basic user profile of the target user is supplemented based on the production and operation data and replacement resource demand data to construct a target user profile of the target user in the current cycle;

[0156] Among them, the basic user portrait is pre-constructed based on the business data and log data of the target user; the data change frequency of the user's production and operation data and replacement resource demand data is higher than that of the business data and log data.

[0157] In some possible implementations, the first generation module 530 uses a preset recommendation model to analyze the target user profile through a machine learning algorithm, and generates a replacement resource service matching the target user profile based on multiple replacement resource products in the product feature library and the product features corresponding to the multiple replacement resource products, including:

[0158] Based on the recommendation model, the target user portrait is analyzed by using the K-means clustering algorithm to obtain the target credit risk group to which the target user belongs, and the decision tree is used to predict whether the target user has a demand for replacement resources, thereby obtaining the replacement resource demand prediction result;

[0159] Analyze the target user portrait based on the recommendation model to determine the target user's production cycle and income fluctuation;

[0160] Based on multiple replacement resource products stored in the product feature library and the product features corresponding to the multiple replacement resource products, a replacement resource service matching the target credit risk group, replacement resource demand forecast results, production cycle and income fluctuation is determined.

[0161] In some possible implementations, obtaining user production and operation data and replacement resource demand data of a target user includes:

[0162] The first acquisition submodule may be used to acquire the target user's questionnaire response information to a preset resource replacement service questionnaire, wherein the preset resource replacement service questionnaire is provided with inquiry information corresponding to the user's production and operation data and resource replacement demand data;

[0163] The first extraction submodule can be used to extract user production and operation data and replacement resource demand data based on questionnaire response information.

[0164] In some possible implementations, after obtaining the target user's questionnaire response information to the preset replacement resource service questionnaire, the replacement resource service recommendation device further includes:

[0165] The first sending module can be used to send the questionnaire answer information to the target auditor, so that the target auditor can verify whether the questionnaire answer information is true;

[0166] The first extraction submodule extracts the user's production and operation data and replacement resource demand data based on the questionnaire response information, including:

[0167] When the target auditor has verified and passed the questionnaire response information, the user's production and operation data and replacement resource demand data are extracted based on the questionnaire response information.

[0168] In some possible implementations, the first construction module 520 constructs a target user portrait of a target user based on business data, log data, user production and operation data, and replacement resource demand data, including:

[0169] The first processing submodule can be used to clean, integrate and standardize business data, log data, user production and operation data and replacement resource demand data to obtain summary data that meets the data processing standards;

[0170] The first construction submodule can be used to construct a target user portrait of the target user based on the summary data.

[0171] In some possible implementations, before using a preset recommendation model to analyze the target user portrait through a machine learning algorithm, the replacement resource service recommendation device further includes:

[0172] The second acquisition module can be used to obtain historical replacement resource services and corresponding historical user portraits;

[0173] The first training module can be used to obtain a recommendation model through machine learning algorithm training based on historical user portraits and historical replacement resource services.

[0174] In some possible implementations, the user's production and management data includes: at least one of: the type of crops planted, the sowing time, the expected yield, and the use of agricultural machinery and equipment;

[0175] The replacement resource demand data includes at least one of a replacement resource amount, a replacement resource period, and a replacement resource purpose.

[0176] Based on the replacement resource service recommendation method provided in the above embodiment, out of the same inventive concept, the present application also provides a replacement resource service recommendation device corresponding to the above replacement resource service recommendation method. Figure 5 Provide a detailed introduction to the equipment recommended for the replacement resource service.

[0177] See below Figure 5 , Figure 5 It is a structural diagram of a replacement resource service recommendation device provided in an embodiment of the present application.

[0178] The replacement resource service recommendation device may include a processor 501 and a memory 502 storing computer program instructions.

[0179] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0180] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 502 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 502 is a non-volatile solid-state memory.

[0181] The memory may include read-only memory (ROM), random access memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0182] The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the replacement resource service recommendation methods in the above embodiments.

[0183] In one example, the data replacement resource service recommendation device may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0184] The communication interface 503 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0185] Bus 510 includes hardware, software or both, and the parts of the replacement resource service recommendation device are coupled to each other. For example, but not limitation, the bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0186] The replacement resource service recommendation device executes the replacement resource service recommendation method in the embodiment of the present application, thereby realizing the replacement resource service recommendation method described in the embodiment of the present application.

[0187] In addition, in combination with the replacement resource service recommendation method in the above embodiment, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any one of the replacement resource service recommendation methods in the above embodiment is implemented.

[0188] Based on the replacement resource service recommendation method in the above embodiment, an embodiment of the present application provides a computer program product. When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the replacement resource service recommendation method provided in any one of the above embodiments of the present application.

[0189] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0190] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application-specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0191] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0192] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0193] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A replacement resource service recommendation method, characterized in that: The method comprises: Respectively obtaining target user's business data, log data, user production and operation data and replacement resource demand data; the user production and operation data and the replacement resource demand data are collected in the form of a replacement resource service questionnaire; Based on the business data, the log data, the user production and operation data and the replacement resource demand data, a target user portrait of the target user is constructed; The target user portrait is analyzed by a machine learning algorithm using a preset recommendation model, and a replacement resource service matching the target user portrait is generated based on a plurality of replacement resource products in a product feature library and the product features respectively corresponding to the plurality of replacement resource products; The replacement resource service is pushed to the target user; wherein the replacement resource service includes the replacement resource product type matched by the target user, the recommended replacement resource timing, the replacement resource amount and the repayment plan.

2. The method according to claim 1, characterized in that The constructing a target user portrait of the target user based on the business data, the log data, the user production and operation data, and the replacement resource demand data includes: When the production and operation data and the replacement resource demand data of the user are obtained, the basic user profile of the target user is supplemented based on the production and operation data and the replacement resource demand data of the user to construct a target user profile of the target user in the current period; Among them, the basic user portrait is pre-constructed based on the business data and log data of the target user; the data change frequency of the user's production and operation data and the replacement resource demand data is higher than that of the business data and the log data.

3. The method according to claim 1, characterized in that The preset recommendation model is used to analyze the target user portrait through a machine learning algorithm, and based on a plurality of replacement resource products in a product feature library and the product features respectively corresponding to the plurality of replacement resource products, a replacement resource service matching the target user portrait is generated, including: Based on the recommendation model, the target user portrait is analyzed by using a K-means clustering algorithm to obtain the target credit risk group to which the target user belongs, and a decision tree is used to predict whether the target user has a replacement resource demand, thereby obtaining a replacement resource demand prediction result; Analyze the target user portrait based on the recommendation model to determine the production cycle and income fluctuation of the target user; Based on the multiple replacement resource products stored in the product feature library and the product features respectively corresponding to the multiple replacement resource products, the replacement resource service matching the target credit risk group, the replacement resource demand forecast result, the production cycle and the income fluctuation is determined.

4. The method according to claim 1, characterized in that: Obtaining the user production and operation data and replacement resource demand data of the target user, including: Obtaining questionnaire response information of the target user to a preset resource replacement service questionnaire, wherein the preset resource replacement service questionnaire is provided with inquiry information corresponding to the user's production and operation data and the resource replacement demand data; Based on the questionnaire response information, the user production and operation data and the replacement resource demand data are extracted.

5. The method according to claim 4, characterized in that After obtaining the target user's questionnaire response information to the preset resource replacement service questionnaire, the method further includes: Sending the questionnaire response information to a target auditor so that the target auditor can verify whether the questionnaire response information is authentic; The extracting of the user production and operation data and the replacement resource demand data based on the questionnaire response information includes: When the target auditor has verified and passed the questionnaire response information, the user production and operation data and the replacement resource demand data are extracted based on the questionnaire response information.

6. The method according to claim 1, characterized in that The constructing a target user portrait of the target user based on the business data, the log data, the user production and operation data, and the replacement resource demand data includes: Performing data cleaning, data integration and data standardization processing on the business data, the log data, the user production and operation data and the replacement resource demand data to obtain summary data that meets the data processing standards; Based on the summarized data, a target user portrait of the target user is constructed.

7. The method according to claim 1, characterized in that Before analyzing the target user portrait by a machine learning algorithm using a preset recommendation model, the method further includes: Obtain historical replacement resource services and corresponding historical user portraits; Based on the historical user portraits and the historical replacement resource services, the recommendation model is obtained through machine learning algorithm training.

8. The method according to any one of claims 1 to 7, characterized in that: The user's production and operation data includes: at least one of: the type of crops planted, the sowing time, the expected yield, and the use of agricultural machinery and equipment; The replacement resource demand data includes at least one of a replacement resource amount, a replacement resource period, and a replacement resource purpose.

9. A replacement resource service recommendation device, characterized in that: The device comprises: The first acquisition module is used to respectively acquire the target user's business data, log data, user production and operation data, and replacement resource demand data; the user production and operation data and the replacement resource demand data are collected in the form of a replacement resource service questionnaire; A first construction module is used to construct a target user portrait of the target user based on the business data, the log data, the user's production and operation data, and the replacement resource demand data; A first generating module is used to analyze the target user portrait through a machine learning algorithm, and generate a replacement resource service matching the target user portrait based on a plurality of replacement resource products in a product feature library and product features respectively corresponding to the plurality of replacement resource products; The first push module is used to push the replacement resource service to the target user; wherein the replacement resource service includes the replacement resource product type matched by the target user, the recommended replacement resource timing, the replacement resource amount and the repayment plan.

10. A replacement resource service recommendation device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the replacement resource service recommendation method according to any one of claims 1 to 8 is implemented.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the replacement resource service recommendation method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the replacement resource service recommendation method according to any one of claims 1 to 8.

Images