Product detail interpretation method and device, equipment and storage medium

Abstract

The invention relates to the technical field of financial science and technology, in particular to a product detail interpretation method and device, equipment and a storage medium, and the method comprises the steps: obtaining financial product detail information; processing the financial product detail information based on a natural language model adopting a product comparison prompt word to obtain a specific index; determining a target index based on the specificity index and a business preset index; and processing the target index based on a natural language model for interpreting the packaged cue word to obtain a product detail interpretation result. According to the method, the manpower consumption and the operation cost of financial product detail interpretation are reduced, and the timeliness, the accuracy and the objectivity of financial product detail interpretation are improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method, device, equipment and storage medium for interpreting product details. Background Art

[0002] Banks often launch some financial products, such as fund products, in their online products. However, since the product information and product data displayed on the product details page of financial products are highly professional, it is difficult for ordinary users to understand the product information and product data. Therefore, it is necessary to interpret the product details.

[0003] At present, common ways to interpret financial products include: (1) internal professionals analyze product details one by one, judge product features based on their own experience, and then give users certain purchase recommendations; (2) external industry experts interpret product details and give purchase recommendations; (3) analyze historical product data, determine product-related features through data statistics, and give purchase recommendations; (4) analyze product details through trained artificial intelligence algorithms, manually improve the interpretation language based on the analysis results, and then present it to customers.

[0004] However, the above four methods of interpreting the details of financial products all require human intervention, and require the participation of multiple roles such as expert judgment, data analysis, and product operation. The manpower consumption and operating costs of interpreting the details of a financial product are relatively high. In addition, experts or product operators need to use appropriate words to explain the interpretation results during the interpretation of the financial product details, which may take several days to complete the interpretation of the product details, resulting in poor timeliness of the interpretation of the financial product details. On the other hand, multiple links in the interpretation of financial product details currently require human participation, but human subjective judgment can easily cause certain deviations in the interpretation of the financial product details, resulting in poor accuracy and objectivity in the interpretation of the financial product details. Summary of the invention

[0005] In order to reduce the manpower consumption and operating costs of interpreting financial product details and improve the timeliness, accuracy and objectivity of interpreting financial product details, the present application provides a product details interpretation method, device, equipment and storage medium.

[0006] In a first aspect, the present application provides a method for interpreting product details, comprising:

[0007] Get detailed information about financial products;

[0008] Processing the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index;

[0009] Determine the target indicator based on the specific indicator and the business preset indicator;

[0010] The target indicator is processed based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0011] Through the above implementation, the process of processing the financial product details information and outputting the product details interpretation results mainly relies on the natural language model, without the participation of experts or product operators, and realizes the automatic processing of the output product details interpretation results, thereby reducing the manpower consumption and operating costs of the financial product details interpretation and improving the timeliness of the financial product details interpretation. In addition, since there is no need for human participation in the process of outputting the product details interpretation results, the accuracy and objectivity of the financial product details interpretation can be effectively improved.

[0012] Preferably, a product details interpretation method provided by the present application further includes:

[0013] Reviewing the interpretation result of the product details based on a preset detection tool to obtain a review interpretation result;

[0014] The review and interpretation results are displayed to the user.

[0015] Through the above implementation, by reviewing the interpretation results of product details, it is convenient to further improve the accuracy of the interpretation results of product details.

[0016] Preferably, the obtaining of detailed information of financial products includes:

[0017] In response to the instruction to obtain product interpretation, a screenshot of the financial product details page is taken to obtain the financial product details information.

[0018] Through the above implementation, the financial product details information is obtained in the form of screenshots, which makes it easier to obtain the financial product details information in the form of pictures, and further facilitates the subsequent natural language model to process the financial product details information in the form of pictures.

[0019] Preferably, the obtaining of detailed information of financial products includes:

[0020] In response to obtaining the product interpretation instruction, the financial product detail page is processed based on a preset OCR tool to obtain the financial product detail information.

[0021] Through the above implementation, the financial product details information is obtained by means of OCR recognition, thereby facilitating the acquisition of the financial product details information in text form, and further facilitating the subsequent natural language model to process the financial product details information in text form.

[0022] Preferably, the processing of the financial product details information based on a natural language model using product comparison prompt words to obtain specific indicators includes:

[0023] Processing the financial product details information based on a natural language model using product comparison prompt words to determine details information of products of the same type;

[0024] The specificity index is obtained by comparing the financial product details information with the details information of the same type of products based on a natural language model using product comparison prompt words.

[0025] Through the above implementation, the natural language model can identify specific indicators through product comparison prompt words, thereby facilitating understanding of the special advantages of this financial product compared with other financial products.

[0026] Preferably, the determining of the target indicator based on the specific indicator and the business preset indicator includes:

[0027] Comparing the specific index with the business preset index to obtain the index deviation;

[0028] In response to the indicator deviation being greater than a preset deviation threshold, the business preset indicator is used as the target indicator; otherwise, the specific indicator and / or the business preset indicator is used as the target indicator.

[0029] Through the above implementation, it is convenient to select the best indicator from the heterogeneous indicators and the business preset indicators, so as to subsequently improve the accuracy of the output product details interpretation results.

[0030] In a second aspect, the present application provides a device for interpreting product details, including:

[0031] Information acquisition module, used to obtain detailed information of financial products;

[0032] An index calculation module, used for processing the financial product details information based on a natural language model using product comparison prompt words to obtain specific indexes;

[0033] An indicator determination module, used to determine a target indicator based on the specific indicator and the business preset indicator;

[0034] The interpretation output module is used to process the target indicator based on a natural language model that uses the interpretation package prompt words to obtain a product details interpretation result.

[0035] Through the above implementation, the process of processing the financial product details information and outputting the product details interpretation results mainly relies on the natural language model, without the participation of experts or product operators, and realizes the automatic processing of the output product details interpretation results, thereby reducing the manpower consumption and operating costs of the financial product details interpretation and improving the timeliness of the financial product details interpretation. In addition, since there is no need for human participation in the process of outputting the product details interpretation results, the accuracy and objectivity of the financial product details interpretation can be effectively improved.

[0036] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0038] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0039] The above-mentioned product details interpretation method, device, equipment and storage medium obtain financial product details information; process the financial product details information based on a natural language model using product comparison prompt words to obtain specific indicators; determine target indicators based on the specific indicators and business preset indicators; and obtain product details interpretation results by processing the target indicators based on a natural language model using interpretation package prompt words. Through the above implementation, the process of processing the financial product details information and outputting the product details interpretation results mainly relies on the natural language model, without the participation of experts or product operators, and realizes the automatic processing of outputting the product details interpretation results, thereby reducing the manpower consumption and operating costs of the financial product details interpretation and improving the timeliness of the financial product details interpretation. In addition, since there is no need for human participation in the process of outputting the product details interpretation results, the accuracy and objectivity of the financial product details interpretation can be effectively improved.

[0040] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A flowchart of a method for interpreting product details provided in an embodiment of the present application;

[0043] Figure 2This is a flow chart of another method for interpreting product details provided in an embodiment of the present application;

[0044] Figure 3 A schematic diagram of the structure of a device for interpreting product details provided in an embodiment of the present application;

[0045] Figure 4 It is a structural schematic diagram of another device for interpreting product details provided in an embodiment of the present application;

[0046] Figure 5 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0047] Figure 6 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present disclosure more clear, the present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not used to limit the present disclosure.

[0049] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0050] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.

[0051] Embodiment 1

[0052] Figure 1 A flowchart of a method for interpreting product details provided in Example 1 of this application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0053] S110. Obtain detailed information of financial products.

[0054] Among them, the bank financial product system provides users with a variety of optional financial products. Exemplarily, the financial product can be a fund product. The user can enter the financial product details page of the corresponding financial product by clicking. The financial product details page displays the financial product details information of the corresponding financial product. Among them, the financial product details information specifically includes product information and product data in this embodiment, and is not specifically limited in other embodiments; the bank financial product system is provided with a "Product Interpretation" button on the page of the financial product details page. If the user clicks the button, the bank financial product system begins to interpret the product information and product data of the corresponding financial product on the product details page for the user, so that the user can fully understand the financial product; if the customer clicks the above-mentioned "Product Interpretation" button, the bank financial product system first obtains the financial product details information corresponding to the financial product.

[0055] Specifically, in response to the customer clicking the "Product Interpretation" button, the bank's financial product system first obtains the product information and product data corresponding to the financial product, thereby obtaining the financial product details information of the financial product.

[0056] S120: Process the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0057] Among them, the product comparison prompt words are prompt words that are pre-set and input into the natural language model. For example, the product comparison prompt words are "You are now a senior investment industry expert. Please analyze the relevant data of the product, compare with similar products, identify specific indicators and tell me the significantly different features of the current product." In other embodiments, there is no specific limitation; the product comparison prompt words are used to control the natural language model to output corresponding specific indicators according to the financial product details information; the natural language model in this embodiment is a generative model based on a large-scale corpus, which can generate, understand and reason about human natural language in an end-to-end manner. The natural language model uses a probability model to generate data, and regards data generation as a process of extracting samples from a prior distribution and generating new data; in other embodiments, the specific model type used by the natural language model is not limited; the specific indicator is the advantage indicator of the financial product corresponding to the financial product details information processed by the natural language model relative to the same type of products; for example, a specific indicator output by the natural language model is "the 7-day return has increased significantly."

[0058] Specifically, artificially set product comparison prompt words are input into the natural language model in advance, and then the obtained financial product details information is input into the natural language model using the product comparison prompt words for processing, and the natural language model outputs the corresponding specificity index.

[0059] S130: Determine a target indicator based on the specific indicator and the business preset indicator.

[0060] Among them, the business preset indicators are business indicators preset artificially to meet business needs; in order to meet specific business needs, after obtaining the above-mentioned specific indicators, it is also necessary to determine the indicators that can better meet the specific business needs from the specific indicators and the business preset indicators, and use the determined indicators as the target indicators.

[0061] Specifically, an indicator that can meet specific business needs is determined from specific indicators and business preset indicators, and the indicator is used as the target indicator.

[0062] S140, processing the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0063] Among them, the interpretation package prompt words are prompt words that are pre-set and input into the natural language model. Exemplarily, the interpretation package prompt words are "You are a senior investment industry expert. Please write a product interpretation for this product in 100 words or less, focusing on the specific indicators of the product's 7-day annualized return that are significantly increased." In other embodiments, there is no specific limitation; the interpretation package prompt words are used to control the natural language model to output the corresponding product details interpretation results according to the target indicators; the product details interpretation results are the text content obtained by encapsulating the product details interpretation content through the words and writing requirements corresponding to the interpretation package prompt words, and the product details interpretation results can provide users with a full understanding of the product information and product data of the corresponding financial products.

[0064] Specifically, the interpretation package prompt words are input into the natural language model in advance, and then the target indicators obtained in the above steps are input into the natural language model using the interpretation package prompt words for processing, and the natural language model outputs the product details interpretation result corresponding to the target indicators.

[0065] It should be noted that the present embodiment obtains the detailed information of financial products; processes the detailed information of financial products based on a natural language model using product comparison prompt words to obtain specific indicators; determines target indicators based on the specific indicators and business preset indicators; and processes the target indicators based on a natural language model using interpretation package prompt words to obtain the interpretation results of product details. Through the above implementation, the process of processing the detailed information of financial products and outputting the interpretation results of product details mainly relies on the natural language model, without the participation of experts or product operators, and realizes the automatic processing of outputting the interpretation results of product details, thereby reducing the manpower consumption and operating costs of the interpretation of financial product details and improving the timeliness of the interpretation of financial product details. In addition, since there is no need for human participation in the process of outputting the interpretation results of product details, the accuracy and objectivity of the interpretation of financial product details can be effectively improved, and a better product details interpretation experience can be provided to users.

[0066] Embodiment 2

[0067] Figure 2 A flowchart of a method for interpreting product details provided in Example 2 of this application, see Figure 2 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0068] S210: Obtain detailed information of financial products.

[0069] S220: Process the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0070] S230: Determine a target indicator based on the specific indicator and the business preset indicator.

[0071] S240: Process the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0072] S250: review the product details interpretation result based on a preset detection tool to obtain a review interpretation result.

[0073] Among them, the product details interpretation results output by the natural language model in the above steps are, after all, the preliminary interpretation results directly output by the machine, and there is still a risk of problems, for example, the product details interpretation results contain sensitive words and / or phishing content; the detection tool is a preset tool in the bank's financial product system, which is used to detect whether the product details interpretation results contain sensitive words and / or phishing content, and when sensitive words and / or phishing content are detected, eliminate the sensitive words and / or phishing content contained in the product details interpretation results; in this way, it is convenient to prevent the product details interpretation results displayed to users from containing sensitive words and improve the safety of users when understanding the details of financial products; the review is that the preset detection tool detects whether the product details interpretation results contain sensitive words and / or phishing content, and eliminates the sensitive words and / or phishing content when sensitive words and / or phishing content appear; the review interpretation result is that the preset detection tool reviews the product details interpretation results and outputs the interpretation results that do not contain sensitive words and / or phishing content.

[0074] Specifically, the obtained product details interpretation results are input into a preset testing tool for review, and the testing tool outputs the reviewed interpretation results.

[0075] S260: Display the review and interpretation result to the user.

[0076] Among them, the banking financial product system can display the review and interpretation results to users in the form of pop-up windows and / or separate pages.

[0077] Specifically, after the bank financial product system obtains the review and interpretation results, it further displays the review and interpretation results to the user in the form of a pop-up window and / or a separate page.

[0078] Embodiment 3

[0079] A method for interpreting product details provided in the third embodiment of the present application is to refine the "obtaining detailed information of financial products" in the first embodiment; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0080] S310: In response to the instruction to obtain product interpretation, a screenshot of the financial product details page is taken to obtain the financial product details information.

[0081] Among them, after the user clicks the "Product Interpretation" button, the bank's financial product system will obtain the corresponding product interpretation instructions. After the bank's financial product system obtains the product interpretation instructions, it means that the user wants to know the detailed interpretation of the corresponding financial product. At this time, the bank's financial product system can take a screenshot of the financial product details page of the financial product, thereby obtaining product information and product data in the form of pictures, that is, obtaining financial product details information in the form of pictures; the subsequent natural language model can further process the financial product details information in the form of pictures.

[0082] Specifically, in response to obtaining the product interpretation instruction, the bank financial product system immediately takes a screenshot of the financial product details page, thereby obtaining the financial product details information in the form of a picture.

[0083] S320: Process the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0084] S330: Determine a target indicator based on the specific indicator and the business preset indicator.

[0085] S340: Process the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0086] Embodiment 4

[0087] A method for interpreting product details provided in the fourth embodiment of the present application is to refine the "obtaining detailed information of financial products" in the first embodiment; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0088] S410: In response to the instruction to obtain product interpretation, the financial product detail page is processed based on a preset OCR tool to obtain financial product detail information.

[0089] Among them, after the user clicks the "Product Interpretation" button, the bank's financial product system will obtain the corresponding product interpretation instructions. After the bank's financial product system obtains the product interpretation instructions, it means that the user wants to know the detailed interpretation of the corresponding financial product. At this time, the bank's financial product system can use its preset OCR tool to perform text recognition on the financial product details page corresponding to the financial product, thereby obtaining the product information and product data in text form on the financial product details page, that is, obtaining the financial product details information in text form; the subsequent natural language model can further process the financial product details information in text form.

[0090] Specifically, in response to obtaining the product interpretation instruction, the bank financial product system immediately uses its preset OCR tool to perform text recognition on the financial product details page corresponding to the financial product, thereby obtaining the financial product details information in the form of pictures.

[0091] S420: Process the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0092] S430: Determine a target indicator based on the specific indicator and the business preset indicator.

[0093] S440: Process the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0094] Embodiment 5

[0095] A method for interpreting product details provided in Example 5 of the present application is a refinement of "processing the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index" in Example 1; it should be noted that for the parts not described in detail in this embodiment, reference may be made to the descriptions of other embodiments, and the method includes:

[0096] S510: Obtain detailed information of financial products.

[0097] S521. Process the financial product details information based on a natural language model using product comparison prompt words to determine details information of products of the same type.

[0098] Among them, the same type of product details information is the product information and product data of other financial products of the same type as the financial product corresponding to the financial product details information; the natural language model using product comparison prompt words can determine the product information and product data of one or more other financial products of the same type as the financial product corresponding to the financial product details information based on the financial product details information input therein, thereby obtaining the same type of product details information.

[0099] Specifically, the financial product details information is input into a natural language model using product comparison prompt words for processing, and the natural language model obtains the details information of products of the same type.

[0100] S522: Compare the financial product details information with the same type of product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0101] Among them, after obtaining the detailed information of products of the same type, the natural language model using product comparison prompt words will further compare the input financial product detailed information with the detailed information of products of the same type, so as to determine the advantage index of the financial product detailed information over the detailed information of products of the same type, that is, the specificity index.

[0102] Specifically, a natural language model of product comparison prompt words is used to further compare the input financial product details information with the details information of similar products, so as to obtain a specificity index.

[0103] S530: Determine a target indicator based on the specific indicator and the business preset indicator.

[0104] S540: Process the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0105] Embodiment 6

[0106] A method for interpreting product details provided in Example 6 of the present application is to refine the "determining the target indicator based on the specific indicator and the business preset indicator" in Example 1; it should be noted that for the part not described in detail in this embodiment, reference can be made to the description of other embodiments, and the method includes:

[0107] S610: Obtain detailed information of financial products.

[0108] S620: Process the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index.

[0109] S631. Compare the specific index with the business preset index to obtain an index deviation.

[0110] Among them, indicator deviation is used to characterize the degree of difference between specific indicators and business preset indicators; the banking financial product system can compare the degree of difference between the specific indicators output by the natural language model and the business preset indicators, and record the degree of difference as indicator deviation.

[0111] Specifically, the banking financial product system compares the degree of difference between the specific indicators output by the natural language model and the business preset indicators to obtain the indicator deviation.

[0112] S632: In response to the indicator deviation being greater than a preset deviation threshold, the business preset indicator is used as the target indicator; otherwise, the specific indicator and / or the business preset indicator is used as the target indicator.

[0113] Among them, the deviation threshold is used to compare with the indicator deviation, so as to determine whether there is a large degree of difference between the specific indicator and the business preset indicator; if the indicator deviation is greater than the preset deviation threshold, it means that there is a large degree of difference between the corresponding specific indicator and the business preset indicator, which means that the specific indicator cannot meet the business needs; otherwise, it means that both the specific indicator and the business preset indicator can meet the business needs.

[0114] Specifically, determine whether the indicator deviation is greater than a preset deviation threshold. If so, use the business preset indicator as the target indicator; otherwise, use the specific indicator and / or the business preset indicator as the target indicator.

[0115] S640: Process the target indicator based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

[0116] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0117] Embodiment 7

[0118] Based on the same inventive concept, this embodiment also provides a product details interpretation device for implementing the product details interpretation method involved in the above embodiment 1. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations of one or more product details interpretation device embodiments provided below can refer to the limitations of the product details interpretation method above, and will not be repeated here.

[0119] In this embodiment, Figure 3 As shown, a device for interpreting product details is provided, comprising:

[0120] Information acquisition module, used to obtain detailed information of financial products;

[0121] An index calculation module, used for processing the financial product details information based on a natural language model using product comparison prompt words to obtain specific indexes;

[0122] An indicator determination module, used to determine a target indicator based on the specific indicator and the business preset indicator;

[0123] The interpretation output module is used to process the target indicator based on a natural language model that uses the interpretation package prompt words to obtain a product details interpretation result.

[0124] Each module in the above-mentioned product details interpretation device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0125] It should be noted that this embodiment obtains financial product details information; processes the financial product details information based on a natural language model using product comparison prompt words to obtain specific indicators; determines target indicators based on the specific indicators and business preset indicators; and processes the target indicators based on a natural language model using interpretation package prompt words to obtain product details interpretation results. Through the above implementation, the process of processing the financial product details information and outputting the product details interpretation results mainly relies on the natural language model, without the participation of experts or product operators, and realizes the automatic processing of outputting the product details interpretation results, thereby reducing the manpower consumption and operating costs of the financial product details interpretation and improving the timeliness of the financial product details interpretation. In addition, since there is no need for human participation in the process of outputting the product details interpretation results, the accuracy and objectivity of the financial product details interpretation can be effectively improved.

[0126] Embodiment 8

[0127] Based on the same inventive concept, this embodiment also provides a product details interpretation device for implementing the product details interpretation method involved in the above embodiment 2. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more product details interpretation device embodiments provided below can refer to the limitations of the product details interpretation method above, and will not be repeated here.

[0128] In this embodiment, Figure 4 As shown, a device for interpreting product details is provided, comprising:

[0129] Information acquisition module, used to obtain detailed information of financial products;

[0130] An index calculation module, used for processing the financial product details information based on a natural language model using product comparison prompt words to obtain specific indexes;

[0131] An indicator determination module, used to determine a target indicator based on the specific indicator and the business preset indicator;

[0132] An interpretation output module, used to process the target indicator based on a natural language model using an interpretation package prompt word to obtain a product details interpretation result;

[0133] A result review module, used to review the product details interpretation result based on a preset detection tool to obtain a review interpretation result;

[0134] The result display module is used to display the review and interpretation results to the user.

[0135] In one embodiment, in terms of obtaining detailed information of financial products, the information acquisition module is specifically used to:

[0136] In response to the instruction to obtain product interpretation, a screenshot of the financial product details page is taken to obtain the financial product details information.

[0137] In one embodiment, in terms of obtaining detailed information of financial products, the information acquisition module is specifically used to:

[0138] In response to obtaining the product interpretation instruction, the financial product detail page is processed based on a preset OCR tool to obtain the financial product detail information.

[0139] In one embodiment, in terms of obtaining specific indicators by processing the financial product details information based on a natural language model using product comparison prompt words, the indicator calculation module is specifically used to:

[0140] Processing the financial product details information based on a natural language model using product comparison prompt words to determine details information of products of the same type;

[0141] The specificity index is obtained by comparing the financial product details information with the details information of the same type of products based on a natural language model using product comparison prompt words.

[0142] In one embodiment, in determining the target indicator based on the specific indicator and the business preset indicator, the indicator determination module is specifically used to:

[0143] Comparing the specific index with the business preset index to obtain the index deviation;

[0144] In response to the indicator deviation being greater than a preset deviation threshold, the business preset indicator is used as the target indicator; otherwise, the specific indicator and / or the business preset indicator is used as the target indicator.

[0145] Each module in the above-mentioned product details interpretation device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0146] Embodiment 9

[0147] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for interpreting product details is implemented.

[0148] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] Embodiment 10

[0150] In this embodiment, a computer readable storage medium is provided. Figure 6 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0151] Embodiment 11

[0152] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0153] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present disclosure may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0155] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A method for interpreting product details, characterized in that: include: Get detailed information about financial products; Processing the financial product details information based on a natural language model using product comparison prompt words to obtain a specificity index; Determine the target indicator based on the specific indicator and the business preset indicator; The target indicator is processed based on a natural language model that interprets the packaged prompt words to obtain a product details interpretation result.

2. The method according to claim 1, characterized in that Also includes: Reviewing the interpretation result of the product details based on a preset detection tool to obtain a review interpretation result; The review and interpretation results are displayed to the user.

3. The method according to claim 1, characterized in that The obtaining of financial product details information includes: In response to the instruction to obtain product interpretation, a screenshot of the financial product details page is taken to obtain the financial product details information.

4. The method according to claim 1, characterized in that: The obtaining of financial product details information includes: In response to obtaining the product interpretation instruction, the financial product detail page is processed based on a preset OCR tool to obtain the financial product detail information.

5. The method according to claim 1, characterized in that The specificity index obtained by processing the financial product details information based on the natural language model using product comparison prompt words includes: Processing the financial product details information based on a natural language model using product comparison prompt words to determine details information of products of the same type; The specificity index is obtained by comparing the financial product details information with the details information of the same type of products based on a natural language model using product comparison prompt words.

6. The method according to claim 1, characterized in that The determining of the target indicator based on the specific indicator and the business preset indicator includes: Comparing the specific index with the business preset index to obtain the index deviation; In response to the indicator deviation being greater than a preset deviation threshold, the business preset indicator is used as the target indicator; otherwise, the specific indicator and / or the business preset indicator is used as the target indicator.

7. A device for interpreting product details, characterized in that: The device comprises: Information acquisition module, used to obtain detailed information of financial products; An index calculation module, used for processing the financial product details information based on a natural language model using product comparison prompt words to obtain specific indicators; An indicator determination module, used to determine a target indicator based on the specific indicator and the business preset indicator; The interpretation output module is used to process the target indicator based on a natural language model that uses the interpretation package prompt words to obtain a product details interpretation result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images