Financing demand matching method and device, equipment and storage medium

Abstract

The invention relates to the field of finance, and discloses a financing demand matching method and device, equipment and a storage medium. The method comprises the following steps: acquiring call voice, and analyzing the call voice to obtain a voice text; according to the voice text, through a trained financing demand model, judging a financing demand type of the user; according to a preset financing product library and financing demand types, carrying out financing demand type matching; and matching a corresponding financing product according to a financing demand type matching result, and pushing the financing product to the user. According to the embodiment of the invention, the credit status and market potential of the user can be comprehensively evaluated, and the most suitable financing product can be accurately matched.

Description

Technical Field

[0001] The present invention relates to the financial field, and in particular to a financing demand matching method, device, equipment and storage medium. Background Art

[0002] In the modern financial market, financing products are an important tool for enterprises and individuals to obtain funds. Various types of financing products have emerged to meet the needs of investors with different needs and risk preferences. Financing products can be classified according to different standards, such as corporate loans and natural person loans by customer type, short-term loans, medium-term loans and long-term loans by term, working capital loans, fixed asset loans, mergers and acquisitions loans, personal business loans and personal consumption loans by purpose, etc.

[0003] However, most financial financing products on the market are recommended by relevant personnel, most of whom do not have professional financing skills. In addition, financing products are constantly updated and customers' financing needs are constantly changing, resulting in the inability to accurately match the most suitable financing products for enterprises or individuals. Summary of the invention

[0004] The main purpose of the present invention is to solve the technical problem of how to improve the accuracy of financing product matching.

[0005] A first aspect of the present invention provides a financing demand matching method, the financing demand matching method comprising:

[0006] Acquire call voice, and analyze the call voice to obtain voice text, wherein the call voice is the user's answer voice regarding the financing access;

[0007] According to the voice text, the financing demand type of the user is determined by using a trained financing demand model;

[0008] According to a preset financing product library and the financing demand type, matching of financing demand types is performed, wherein the financing product library is obtained by dividing according to the classification in the financing demand model;

[0009] According to the result of matching the financing demand type, the corresponding financing product is matched and pushed to the user.

[0010] Optionally, in a first implementation of the first aspect of the present invention, before judging the type of financing demand of the user according to the voice text by using a trained financing demand model, the method further includes:

[0011] Acquiring financing demand data, and classifying financing demands according to the financing demand data;

[0012] Building a corpus for each financing demand classification, wherein the corpus includes multiple types of data;

[0013] According to each financing demand classification and the corresponding corpus, the initial financing demand model is trained to obtain a trained financing demand model.

[0014] Optionally, in a second implementation of the first aspect of the present invention, after training the initial financing demand model according to each financing demand classification and the corresponding corpus to obtain the trained financing demand model, the method further includes:

[0015] Evaluate the trained financing demand model, and use precision and recall rate indicators to measure the performance of the financing demand model;

[0016] Determining whether to iteratively update the financing demand model according to the precision and recall rate indicators;

[0017] If so, the corpus is supplemented, and the financing demand model is trained again based on the supplemented corpus until the precision and recall rate indicators reach preset thresholds.

[0018] Optionally, in a third implementation of the first aspect of the present invention, matching the financing demand type according to the preset financing product library and the financing demand type includes:

[0019] Extracting key features of financing products and the financing demand types in a preset financing product library;

[0020] Based on the key features, the similarity between the financing product and the financing demand type is compared by a feature matching algorithm;

[0021] Based on the similarity, it is determined whether there is a financing product in the financing product library that matches the financing demand type.

[0022] Optionally, in a fourth implementation of the first aspect of the present invention, matching corresponding financing products according to the result of matching the financing demand type, and pushing the financing products to the user includes:

[0023] If there is a financing product in the financing product library that matches the financing demand type, push the matching financing product to the user;

[0024] If there is no financing product in the financing product library that matches the financing demand type, a message indicating that the matching has failed is pushed to the user.

[0025] Optionally, in a fifth implementation of the first aspect of the present invention, the acquiring the call voice and analyzing the call voice to obtain the voice text includes:

[0026] Acquire call voice and extract sound features from the call voice;

[0027] Inputting the sound features into a trained speech recognition model to generate corresponding speech text;

[0028] The voice text is corrected and analyzed to obtain the user's financing sentiment tendency.

[0029] Optionally, in a sixth implementation of the first aspect of the present invention, after acquiring the call voice and analyzing the call voice to obtain the voice text, the method further includes:

[0030] The voice text is encrypted through data encryption technology, and the sensitive data in the voice text is desensitized to prevent the user's sensitive information from being exposed.

[0031] The second aspect of the present invention provides a financing demand matching device, comprising: a memory and at least one processor, wherein instructions are stored in the memory, and the memory and the at least one processor are interconnected via lines; the at least one processor calls the instructions in the memory so that the financing demand matching device executes the above-mentioned financing demand matching method.

[0032] A third aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned financing demand matching method.

[0033] In an embodiment of the present invention, a call voice is obtained, and the call voice is analyzed to obtain a voice text, wherein the call voice is the user's answer voice regarding a financing visit; based on the voice text, the user's financing demand type is determined through a trained financing demand model; the financing demand type is matched according to a preset financing product library and the financing demand type, and the financing product library is obtained by dividing according to the classification in the financing demand model; according to the result of the financing demand type matching, the corresponding financing product is matched, and the financing product is pushed to the user. In the present invention, the user's financing demand type is determined through a trained financing demand model, and the corresponding financing product is matched according to the financing demand type, which can comprehensively evaluate the user's credit status and market potential, accurately match the most suitable financing product, thereby improving the success rate of financing applications and reducing the risk of financing failure due to information asymmetry or improper selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of an embodiment of a financing demand matching method in an embodiment of the present invention;

[0035] Figure 2 It is a schematic diagram showing the main classification structure of the financing demand model in the embodiment of the present invention;

[0036] Figure 3 A schematic diagram of an embodiment of a financing demand matching device in an embodiment of the present invention;

[0037] Figure 4 It is a schematic diagram of an embodiment of a financing demand matching device in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] Embodiments of the present invention provide a financing demand matching method, apparatus, device and storage medium.

[0039] The embodiments disclosed in the present invention will be described in more detail below with reference to the accompanying drawings. Although certain embodiments disclosed in the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present invention. It should be understood that the drawings and embodiments disclosed in the present invention are only for exemplary purposes and are not intended to limit the scope of protection disclosed in the present invention.

[0040] In the description of the embodiments disclosed in the present invention, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0041] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 , an embodiment of the financing demand matching method in the embodiment of the present invention includes:

[0042] S100, acquiring call voice, and analyzing the call voice to obtain voice text.

[0043] In this embodiment, a customer service or robot customer service conducts a telephone financing visit to the demand, records the user's answer voice about the financing visit, obtains the call voice, and then converts the call voice into voice text through voice recognition technology. Before converting to voice text, the call voice needs to be pre-processed for denoising. Optionally, denoising technologies such as Wiener filter and spectrum reduction can be combined for denoising, which can effectively reduce echo and noise, thereby improving the accuracy of ASR (automatic speech recognition). Wiener filter and spectrum reduction are simple and low-computation methods that can effectively suppress the attenuation of voice signals caused by noise and channel pollution, and restore the original signal to improve the performance of voice recognition.

[0044] S200, judging the user's financing demand type based on the voice text and the trained financing demand model.

[0045] In this embodiment, the financing demand model is first trained. The trained model can be used to analyze the user's voice text in real time and identify the type of financing demand. For example, the model can identify whether the user needs short-term working capital, long-term investment or other types of financing. The financing demand model includes multiple categories, such as financing type, loan amount, repayment period, etc. Figure 2 As shown, the user's financing demand type can be obtained by analyzing the classification in the financing demand model. In addition, after speech recognition, the correct punctuation marks can be automatically inserted into the text through punctuation prediction technology, thereby improving the readability and standardization of the text and making the generated speech text more natural and easy to understand.

[0046] S300: Matching the financing demand type according to the preset financing product library and financing demand type.

[0047] In this embodiment, a financing product library is first established, and the financing products in the financing product library are divided according to the classification in the financing demand model. Then, the financing demand type is matched with the products in the financing product library one by one. For example, if the financing demand type is identified as long-term investment, then the financing product corresponding to the long-term investment is matched in the financing product library.

[0048] S400, matching corresponding financing products according to the financing demand type matching result, and pushing the financing products to the user.

[0049] In this embodiment, according to the result of matching the financing demand type, the corresponding financing product is selected and recommended to the user. In addition, the user's satisfaction with the recommended financing product can also be evaluated to determine the accuracy of the financing demand model. Specifically, various indicators related to user satisfaction are first collected, such as user behavior data, user feedback, etc., and then the specific meaning and calculation method of each indicator are defined, and the collected indicators are classified into different user satisfaction dimensions, such as the correct proportion of product recommendations, response speed, etc., and then different weights are assigned according to the importance of each indicator, and the user satisfaction score is calculated comprehensively. Among them, the indicator data can be collected through qualitative research and quantitative research, wherein qualitative research is to collect users' subjective feelings and opinions through interviews, questionnaires, etc.; quantitative research is to collect users' objective behavior data through data analysis tools, such as user purchase rate, etc.

[0050] In an optional implementation of the first aspect of the present invention, before determining the type of financing demand of the user through the trained financing demand model according to the voice text, the method further includes:

[0051] Financing demand data is obtained, and financing demands are classified according to the financing demand data; a corpus is built for each financing demand classification, and the corpus includes multiple types of data; an initial financing demand model is trained according to each financing demand classification and the corresponding corpus to obtain a trained financing demand model.

[0052] In this embodiment, the financing demand is classified according to the financing demand data, wherein the classification includes financing type, loan amount, repayment period, etc.; the financing demand data can be obtained by crawling tools. Then, a corpus is built for each financing demand classification. The corpus is the basic resource for training the model. The corpus can collect corpus in the financial field in a targeted manner to ensure the performance of the model in a specific task. The introduction of special corpus in the financial field through the corpus can help the large model better understand the terms, expressions and knowledge in the financial field, thereby improving the model's ability in industry analysis and other aspects. The corpus contains annotated data (financing professional terms, financing emotional tendencies, relationships between people and property, etc.), keyword data, dialogue data, audio data, etc., wherein the collection and analysis of keyword data can be carried out through a variety of methods, including data collection, data processing, data analysis, etc.; the collection and annotation of dialogue data can be carried out through dialogue data collection and annotation strategies, and the annotation of dialogue data usually includes dialogue intention, entity, etc.; the annotation of audio data can also be carried out through a variety of tools, such as audio-annotator. After the corpus is built, the corpus is used to train the initial financing demand model.

[0053] In an optional implementation of the first aspect of the present invention, after the initial financing demand model is trained according to each financing demand classification and the corresponding corpus to obtain the trained financing demand model, the method further includes:

[0054] Evaluate the trained financing demand model and use the precision and recall indicators to measure the performance of the financing demand model; based on the precision and recall indicators, determine whether to iteratively update the financing demand model; if so, supplement the corpus and train the financing demand model again based on the supplemented corpus until the precision and recall indicators reach the preset thresholds.

[0055] In this embodiment, during training, overfitting can be prevented by adjusting the learning rate, modifying the network structure, or using regularization techniques to optimize model parameters. The trained financing demand model is evaluated, and the performance of the model is measured using indicators such as precision and recall, where precision measures the proportion of samples predicted by the model to be positive and actually positive, and recall measures the proportion of samples that are actually positive and correctly predicted by the model to be positive. According to the precision and recall indicators, decide whether it is necessary to iteratively update the model. If an update is required, collect more data to classify and supplement the corpus, and train the financing demand model again until the precision and recall indicators reach the preset threshold. In addition, after the financing demand model reaches a certain stability and accuracy, model compression can be considered, such as weight quantization, model weight sparseness, model channel pruning, etc., to improve the efficiency of the model.

[0056] In an optional implementation of the first aspect of the present invention, matching the financing demand type according to the preset financing product library and the financing demand type includes:

[0057] Extract key features of financing products and financing demand types in the preset financing product library; compare the similarity between financing products and financing demand types based on the key features through feature matching algorithm; and determine whether there are financing products in the financing product library that match the financing demand type based on the similarity.

[0058] In this embodiment, the key features of the financing products and financing demand types in the preset financing product library are extracted, such as amount, term, interest rate preference, credit rating, etc., and then the feature matching algorithm is used to compare the similarity between the financing demand type and the financing product. This can be achieved by calculating the similarity score between the two, for example, using methods such as cosine similarity or Euclidean distance. Risk assessment can also be considered in the matching process. Through the risk rating system, the matching results are risk screened to ensure that the recommended products meet the customer's credit qualifications and risk tolerance. Finally, the matching results are submitted to the client, and are displayed to the customer one by one through the calculation method of pre-order traversal for the customer to choose. This process ensures that the customer can intuitively see all eligible financing products and choose according to their needs.

[0059] In an optional implementation of the first aspect of the present invention, matching corresponding financing products according to the result of financing demand type matching, and pushing the financing products to the user includes:

[0060] If there is a financing product in the financing product library that matches the financing demand type, the matching financing product will be pushed to the user; if there is no financing product in the financing product library that matches the financing demand type, a message indicating that the matching has failed will be pushed to the user.

[0061] In this embodiment, if there is a financing product in the financing product library that matches the financing demand type, the matching financing product is pushed to the user. If there is no financing product in the financing product library that matches the financing demand type, a message of matching failure is pushed to the user, and the user manually performs matching. If the manual matching fails, it means that the user's demand expression is insufficient.

[0062] In an optional implementation of the first aspect of the present invention, acquiring a call voice, analyzing the call voice, and obtaining a voice text includes:

[0063] Acquire call audio and extract sound features from the call audio; input the sound features into the trained speech recognition model to generate corresponding speech text; correct and analyze the speech text to obtain the user's financing sentiment tendency.

[0064] In this embodiment, first, the sound signal in the call voice is converted into an electronic signal for processing and analysis. The collected sound signal is preprocessed, including noise reduction, etc., to improve the voice quality. Then, the sound features, such as spectral features, time domain features, etc., are extracted from the voice signal through feature extraction technology. The automatic speech recognition model is trained using an existing voice data set. Common models include acoustic models and language models based on neural networks, such as RNN, CNN, Transformer, etc. These models can recognize and understand human voice content by learning a large amount of voice data. The extracted features are input into the trained voice recognition model, and the model will generate the corresponding voice text output. This process usually includes a decoding step to convert the acoustic features into a vocabulary sequence in the language model. Since the generated voice text may contain some errors or incoherent parts, post-processing is required, such as spelling correction, grammar correction, etc., and the user's financing sentiment tendency is analyzed through the voice text to determine whether the user has a tendency to purchase financing products.

[0065] In an optional implementation of the first aspect of the present invention, after acquiring the call voice and analyzing the call voice to obtain the voice text, the method further includes:

[0066] Through data encryption technology, the voice text is encrypted and the sensitive data in the voice text is desensitized to prevent the user's sensitive information from being exposed.

[0067] In this embodiment, data encryption technology is used during transmission and storage to ensure the confidentiality and integrity of voice text data. Optionally, the data encryption technology can use a symmetric cryptographic system, such as an encryption method based on a chaotic logistic algorithm, or an encryption scheme based on a chaotic switching system. Before encryption, sensitive field information in the voice text, such as the patient's name, ID number, telephone number, etc., is identified, and the sensitive fields are desensitized. Technical means such as replacement, filtering, encryption, masking or deletion can be used. After desensitization, ensure that the data format and attributes remain unchanged, and maintain its identifiability and availability.

[0068] See also Figure 3 The second aspect of the present invention provides a financing demand matching device, the financing demand matching device comprising:

[0069] The voice analysis module 10 is used to obtain the call voice and analyze the call voice to obtain the voice text, where the call voice is the user's answer voice regarding the financing access;

[0070] The type determination module 20 is used to determine the type of financing demand of the user according to the voice text and the trained financing demand model;

[0071] The type matching module 30 is used to match the financing demand type according to the preset financing product library and the financing demand type. The financing product library is obtained by dividing according to the classification in the financing demand model;

[0072] The product matching module 40 is used to match corresponding financing products according to the results of financing demand type matching, and push the financing products to users.

[0073] In an optional implementation of the second aspect of the present invention, the financing demand matching device further includes:

[0074] The model training module is used to obtain financing demand data and classify financing demands according to the financing demand data; build a corpus for each financing demand classification, and the corpus includes multiple types of data; according to each financing demand classification and the corresponding corpus, train the initial financing demand model to obtain the trained financing demand model.

[0075] In an optional implementation of the second aspect of the present invention, the financing demand matching device further includes:

[0076] The model evaluation module is used to evaluate the trained financing demand model and use the precision and recall rate indicators to measure the performance of the financing demand model; based on the precision and recall rate indicators, it is determined whether to iteratively update the financing demand model; if so, the corpus is supplemented and the financing demand model is trained again based on the supplemented corpus until the precision and recall rate indicators reach the preset thresholds.

[0077] In an optional implementation of the second aspect of the present invention, the type matching module 30 is also used to extract key features of financing products and financing demand types in a preset financing product library; based on the key features, the similarity between the financing products and the financing demand types is compared through a feature matching algorithm; based on the similarity, it is determined whether there is a financing product in the financing product library that matches the financing demand type.

[0078] In an optional implementation of the second aspect of the present invention, the product matching module 40 is also used to push the matching financing product to the user if there is a financing product in the financing product library that matches the financing demand type; if there is no financing product in the financing product library that matches the financing demand type, push a matching failure message to the user.

[0079] In an optional implementation of the second aspect of the present invention, the speech analysis module 10 is also used to obtain call speech and extract sound features in the call speech; input the sound features into the trained speech recognition model to generate corresponding speech text; correct and analyze the speech text to obtain the user's financing sentiment tendency.

[0080] In an optional implementation of the second aspect of the present invention, the financing demand matching device further includes:

[0081] The encryption and desensitization module is used to encrypt voice text through data encryption technology, and desensitize sensitive data in the voice text to prevent the user's sensitive information from being exposed.

[0082] Figure 4 is a schematic diagram of the structure of a financing demand matching device provided by an embodiment of the present invention. The financing demand matching device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 may be temporary storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the financing demand matching device 500. Furthermore, the processor 510 may be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the financing demand matching device 500.

[0083] The financing demand matching device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 4 The structure of the financing demand matching device shown does not constitute a limitation on the financing demand matching device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0084] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the financing demand matching method.

[0085] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in the specific order shown or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.

[0087] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A financing demand matching method, characterized in that: The financing demand matching method includes: Acquire call voice, and analyze the call voice to obtain voice text, wherein the call voice is the user's answer voice regarding the financing access; According to the voice text, the financing demand type of the user is determined by using a trained financing demand model; According to a preset financing product library and the financing demand type, matching of financing demand types is performed, wherein the financing product library is obtained by dividing according to the classification in the financing demand model; According to the result of matching the financing demand type, the corresponding financing product is matched and pushed to the user.

2. The financing demand matching method according to claim 1, characterized in that: Before judging the type of financing demand of the user through the trained financing demand model according to the voice text, the method further includes: Acquiring financing demand data, and classifying financing demands according to the financing demand data; Building a corpus for each financing demand classification, wherein the corpus includes multiple types of data; According to each financing demand classification and the corresponding corpus, the initial financing demand model is trained to obtain a trained financing demand model.

3. The financing demand matching method according to claim 2, characterized in that: After training the initial financing demand model according to each financing demand classification and the corresponding corpus to obtain the trained financing demand model, the method further includes: Evaluate the trained financing demand model, and use precision and recall rate indicators to measure the performance of the financing demand model; Determining whether to iteratively update the financing demand model according to the precision and recall rate indicators; If so, the corpus is supplemented, and the financing demand model is trained again based on the supplemented corpus until the precision and recall rate indicators reach preset thresholds.

4. The financing demand matching method according to claim 1, characterized in that: The matching of the financing demand type according to the preset financing product library and the financing demand type includes: Extracting key features of financing products and the financing demand types in a preset financing product library; Based on the key features, the similarity between the financing product and the financing demand type is compared by a feature matching algorithm; Based on the similarity, it is determined whether there is a financing product in the financing product library that matches the financing demand type.

5. The financing demand matching method according to claim 1, characterized in that: The matching of the corresponding financing products according to the result of the financing demand type matching and pushing the financing products to the user includes: If there is a financing product in the financing product library that matches the financing demand type, push the matching financing product to the user; If there is no financing product in the financing product library that matches the financing demand type, a message indicating that the matching has failed is pushed to the user.

6. The financing demand matching method according to claim 1, characterized in that: The acquiring of the call voice and analyzing the call voice to obtain the voice text includes: Acquire call voice and extract sound features from the call voice; Inputting the sound features into a trained speech recognition model to generate corresponding speech text; The voice text is corrected and analyzed to obtain the user's financing sentiment tendency.

7. The financing demand matching method according to claim 1, characterized in that: After acquiring the call voice and analyzing the call voice to obtain the voice text, the method further includes: The voice text is encrypted through data encryption technology, and the sensitive data in the voice text is desensitized to prevent the user's sensitive information from being exposed.

8. A financing demand matching device, characterized in that: The financing demand matching device comprises: A voice analysis module, used to obtain a call voice and analyze the call voice to obtain a voice text, wherein the call voice is a user's answer voice regarding a financing access; A type judgment module, used to judge the type of financing demand of the user according to the voice text through a trained financing demand model; A type matching module, used to match the financing demand type according to a preset financing product library and the financing demand type, wherein the financing product library is obtained by dividing according to the classification in the financing demand model; The product matching module is used to match the corresponding financing products according to the results of the financing demand type matching, and push the financing products to the user.

9. A financing demand matching device, characterized in that: The financing demand matching device comprises: a memory and at least one processor, the memory stores instructions, and the memory and the at least one processor are interconnected via a line; The at least one processor calls the instructions in the memory to enable the financing demand matching device to execute the financing demand matching method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the financing demand matching method according to any one of claims 1 to 7 is implemented.

Images