Method for acquiring price of financial product and application
By obtaining and analyzing the user's financial product price questioning information and its context, and using natural language processing technology to generate financial product price estimate reference solutions, it solves the problem that existing chatbots cannot provide accurate information, and improves user experience and transaction stickiness.
Patent Information
- Application Number
- CN202411095839.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-29
AI Technical Summary
The existing chatbots in the financial field lack self-growth ability and personalized service capabilities, and are unable to provide accurate financial product price information, resulting in poor user experience and low transaction stickiness.
By obtaining user's questioning information on the price of financial products and its context information, disassembly and analyze it to provide an estimated reference solution for financial product prices, using natural language processing and artificial intelligence technology to understand user needs, extract anchor information and display logical relationships To generate a price answer.
It improves users' transaction stickiness in the financial field, provides accurate and personalized reference solutions for financial product price estimates, and enhances user experience and service quality.
Smart Images

Figure CN119048136A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and application for obtaining prices of financial products. Background Art
[0002] In the financial field, with the continuous advancement of technology and the changing needs of users, chatbots have become an important part of financial services. Chatbots use artificial intelligence and natural language processing technology to provide users with convenient financial services and personalized investment advice.
[0003] At present, financial institutions are paying more and more attention to improving user experience, reducing costs, and enhancing service capabilities. As an intelligent customer service solution, chatbots have the advantages of 24 / 7 online, quick response, and personalized services. Technically, chatbots in the financial field need to have a high degree of semantic understanding ability and be able to accurately understand users' questions, instructions, and needs. This involves the use of natural language processing (NLP) and machine learning (ML) technologies, including semantic analysis, entity recognition, intent recognition, etc. Through these technologies, chatbots can achieve natural communication with users, thereby improving user experience.
[0004] The existing chatbots used in the financial field have the characteristics of pre-set answers and lack of self-growth capabilities. Therefore, the information provided in response often fails to satisfy users, thus wasting their patience and time and leading to customer loss.
[0005] For example, chatbots in the financial field lack the operational authority to call financial knowledge graphs or professional knowledge bases, so they are unable to provide accurate information when answering user questions. However, if the operational authority is released, there will be concerns about data attacks and leakage. In addition, since the chatbot is not based on personalized information such as the user's historical transaction data and investment preferences, it is difficult to build a personalized model and recommendation system based on machine learning technology to provide users with customized investment advice and services. Therefore, chatbots need to improve service quality in terms of enhancing user stickiness and usage satisfaction.
[0006] Based on this, the present application provides a method and application for obtaining the prices of financial products, focusing on the user's question information regarding the prices of financial products, and providing a corresponding price reference plan that reflects the current prices of financial products, thereby answering users' questions about the prices of financial products, which is a technical problem that needs to be solved urgently. Summary of the invention
[0007] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a method and application for obtaining the prices of financial products. The present invention can focus on the user's question information on the price of financial products and provide an estimated reference solution that reflects the price of financial products, thereby answering the user's questions related to the price of financial products and improving the user's transaction stickiness in the financial field.
[0008] In order to solve the existing technical problems, the present invention provides the following technical solutions:
[0009] A method for obtaining a price of a financial product, comprising:
[0010] Obtaining at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information;
[0011] After disassembling the aforementioned question information and the aforementioned context information, at least one price answer information is provided through analysis; the price answer information can reflect at least one estimated reference solution for the price of at least one financial product.
[0012] Furthermore, the financial products include stocks, bonds, currencies, foreign exchange, funds, insurance products, loans, credit instruments and / or securitized products;
[0013] The inquiry information includes inquiry information related to investment objectives, investment preferences, market trends, market forecasts, investment risks, investment returns, investment strategies and / or investment advice;
[0014] The context information includes previous question information, previous price answer information, user personal information, current conversation situation, network environment information, user emotions, user tone, external knowledge and / or external events related to the current topic.
[0015] Further, the disassembly comprises the steps of:
[0016] Extracting anchor information from the question information and context information of the question information; the anchor information is extracted from the question information and context information of the question information to facilitate subsequent provision of decision information for predicting the price of financial products;
[0017] According to the aforementioned question information and the context information of the question information, the information hierarchy of the anchor information is obtained, and the first-level anchor information, the second-level anchor information, ..., the N-1-level anchor information, and the N-level anchor information are set from high to low levels, and N is an integer greater than or equal to 1; wherein the second-level anchor information is the subordinate anchor information of the first-level anchor information, and so on, the N-level anchor information is the subordinate anchor information of the N-1-level anchor; there is at least one anchor information in each level.
[0018] Further, the analysis comprises the steps of:
[0019] Understanding the aforementioned question information and context information of the aforementioned question information based on natural language technology;
[0020] Anchor point information having a logical relationship is extracted from the question information and the context information of the question information; the logical relationship includes a causal relationship and / or a time sequence relationship between the anchor point information.
[0021] Furthermore, corresponding to the information hierarchy of the above anchor information, the logical relationship between the anchor information at different levels is displayed;
[0022] After displaying the logical relationship between the anchor point information at different levels, the information answer information predicting the price of the financial product is displayed accordingly based on the logical relationship between the anchor point information at different levels.
[0023] Furthermore, the price answer information provides at least one estimated reference solution for the price of at least one financial product based on a combination of the aforementioned anchor point information at different levels.
[0024] Furthermore, when it is determined that the information stored in the preset prediction library cannot form price answer information suitable for the aforementioned question information, suitable price answer information is provided by issuing a cross-database query or transferring the answer to a professional.
[0025] A device for obtaining the price of a financial product, comprising the structure:
[0026] A price questioning unit, used to obtain at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information;
[0027] The price providing unit is used to analyze the aforementioned question information and the aforementioned context information and provide at least one price answer information through analysis; the price answer information can reflect at least one estimated reference solution for the price of at least one financial product.
[0028] A system for obtaining prices of financial products, comprising:
[0029] A network node, configured to send and receive at least one question message and price answer message regarding at least one financial product price;
[0030] An information answering module is used to provide corresponding price answering information according to the aforementioned question information;
[0031] A system server, wherein the system server connects the network node and the information answering module;
[0032] The system server is configured to: obtain at least one question information from at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information; after disassembling the aforementioned question information and the aforementioned context information, provide at least one price answer information through analysis; the price answer information can reflect at least one estimated reference solution for the price of at least one financial product.
[0033] A computer-readable storage medium stores a computer program, wherein the computer program, when executed by a processor, implements the implementation steps of any of the above methods.
[0034] Based on the above advantages and positive effects, the advantages of the present invention are: focusing on users' questions about the prices of financial products, providing corresponding estimated reference solutions that reflect the prices of financial products, thereby answering users' questions about the prices of financial products and improving users' transaction stickiness in the financial field. BRIEF DESCRIPTION OF THE DRAWINGS
[0035] Figure 1 A flowchart provided for an embodiment of the present invention.
[0036] Figure 2 A schematic diagram of the structure of a device provided in an embodiment of the present invention.
[0037] Figure 3 A schematic diagram of the structure of a system provided in an embodiment of the present invention.
[0038] Description of reference numerals:
[0039] Device 200, price questioning unit 201, price providing unit 202;
[0040] System 300 , network node 301 , information answering module 302 , system server 303 . DETAILED DESCRIPTION
[0041] The following is a further detailed description of a method and application for obtaining the price of financial products disclosed in the present invention in conjunction with the accompanying drawings and specific embodiments. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated, and they can be combined with each other to achieve better technical effects. In the drawings of the following embodiments, the same reference numerals appearing in each drawing represent the same features or components, which can be applied to different embodiments. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.
[0042] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the invention. Any modification of the structure, change of the proportion relationship or adjustment of the size should fall within the scope of the technical content disclosed by the invention without affecting the effects and purposes that can be achieved by the invention. The scope of the preferred embodiments of the present invention includes other implementations, in which the functions can be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by those skilled in the art of the technical field to which the embodiments of the present invention belong.
[0043] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and devices should be considered part of the authorization specification. In all examples shown and discussed herein, any specific values should be interpreted as merely exemplary and not as limiting. Therefore, other examples of the exemplary embodiments may have different values.
[0044] Example
[0045] The technical solution involved in this embodiment is centered around the price prediction of financial products, which refer to various financial products and tools available for sale or investment in the financial market, which have specific financial attributes and functions and can be used to meet the various financial needs of investors, borrowers and other market participants.
[0046] The financial products include various types of products and instruments, including but not limited to stocks, bonds, currencies, foreign exchange, funds, insurance products, loans, credit instruments and / or securitized products.
[0047] The stock is a security that represents ownership of a company. The holder is the shareholder and has the right to share in the company's profits and make decisions.
[0048] The bond represents a security in which the debtor promises to the creditor (i.e., the investor) to pay interest at an agreed time and to repay the principal at maturity. Bonds are often used to raise funds and provide a fixed-income investment opportunity.
[0049] The currency and foreign exchange mentioned include legal tender, foreign currency, foreign exchange derivatives, etc., which are used for payment and settlement transactions and for foreign exchange investment.
[0050] The fund is a pool of funds managed by an investment manager that invests in a variety of financial product categories, such as stocks, bonds, commodities, etc., with the aim of achieving specific investment objectives.
[0051] The insurance products mentioned above are contracts that provide insurance protection and risk management services, including life insurance, property insurance, health insurance, etc.
[0052] The loans and credit instruments include bank loans, credit cards, mortgages, etc., which are used for borrowing and financing.
[0053] The securitization products package products into securities, such as mortgage-backed securities, product-backed securities, etc.
[0054] As the types and characteristics of financial products vary, when predicting the prices of corresponding financial products, it is necessary to combine the unique financial attributes and functions of the above-mentioned financial products to achieve appropriate prediction results.
[0055] See also Figure 1 FIG. 1 is a flow chart of the present invention. The implementation step S100 of the method is as follows:
[0056] S101, obtaining at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information.
[0057] The question information includes inquiry information related to investment objectives, investment preferences, market trends, market forecasts, investment risks, investment returns, investment strategies and / or investment advice.
[0058] Specifically, the question information depends on the specific needs and background of the user. As an example but not a limitation, the user's question information regarding the price of at least one financial product is as follows:
[0059] Taking investment goals and investment preferences as an example, the question information may be "I would like to know what is the price (yield to maturity) of a specific bond for long-term investment?", "I would like to invest in some low-risk bonds. Can you recommend some bonds with higher yield to maturity?", or "I am more interested in high-risk and high-return investments. Do you have any suggestions?"
[0060] Taking market trends and market forecasts as an example, the question information may be "Do you have any predictions about the yield trend of the bond market in the next few quarters?", "I would like to know the recent situation of the bond market. How do you think the bond yields will change in the next few months?", or "I heard that the central bank plans to raise interest rates. What impact will this have on the bond market?"
[0061] Taking investment risk and investment return as an example, the question information may be "I am a little worried about the risks of investing in bonds. Can you tell me the relationship between yield and risk?", "I am considering investing in a lower-rated bond. What kind of returns and risks do you think this will bring?", or "I want to understand the returns and volatility of investing in different types of bonds in order to better balance risks and returns."
[0062] Taking investment strategies and investment advice as an example, the question information may be "How should I allocate funds to different types of bonds to achieve the best returns?", "Do you have any suggestions on optimizing returns using a bond portfolio?", or "I would like to learn some strategies for long-term bond investments to cope with market uncertainty and volatility."
[0063] The context information includes but is not limited to previous question information, previous price answer information, user personal information, current conversation situation, network environment information, user emotions, user tone, external knowledge and / or external events related to the current topic.
[0064] The previous question information and the previous price answer information are respectively the question information and the price answer information before the user asked the question information. In this embodiment, it is preferred to provide the previous question information about the user's intention and the current topic as the selected context information.
[0065] The user personal information refers to the user's personal data, preferences, historical behaviors and other information. The user personal information can help the chatbot to develop personalized answers to provide more relevant communication content.
[0066] The current dialogue context may be information such as context, topic transition, etc. in the dialogue between the chat robot and the user. Determination of the current dialogue context helps to understand the user's current intentions and needs.
[0067] The network environment information is used to describe the network environment where the user is located, such as time, location, and the network environment where the network equipment is located.
[0068] The user's emotion and tone of voice can affect the user's questioning method and demand expression.
[0069] External knowledge and external events related to the current topic can help the chatbot provide more comprehensive price answer information around the current topic.
[0070] By comprehensively considering the above contextual information, it is possible to more intelligently understand the user's question information based on natural language processing technology in artificial intelligence technology, and provide price answer information that meets the user's needs.
[0071] S102, after disassembling the aforementioned question information and the aforementioned context information, provide at least one price answer information through analysis.
[0072] The price solution information can reflect at least one estimated reference solution for the price of at least one financial product.
[0073] The estimated financial plan includes but is not limited to the description of the type of financial product, data source, selection, verification, risk assessment and result display of the price analysis model of the financial product.
[0074] In this embodiment, considering that the question information provided by the user may contain multiple pieces of information to be answered, it is necessary to disassemble the question information to determine the fields and contents that require professional answers to the question information. The process of disassembling the question information particularly involves breaking down complex questions or statements presented in the question information into smaller and more specific parts for better understanding and answering.
[0075] In this embodiment, artificial intelligence technology is preferably used to disassemble the question information and sort out the price answer information accordingly. Specifically, the disassembly includes step S110:
[0076] S111, extracting anchor point information from the question information and context information of the question information.
[0077] The anchor point information is extracted from the question information and the context information of the question information to facilitate the subsequent provision of decision information for predicting the price of financial products.
[0078] The anchor information may be a keyword in the question information. If the user's question information is about the asset price of a certain stock, then the stock name, industry, market conditions and other information may be keywords. For example, the user's question information is "I am interested in investing in FAANG stocks in the technology industry. What is the expected price in the next year?" At this time, the question information contains anchor information such as stock code, company name and industry information.
[0079] The anchor information may also be important data in the price answer information. The price answer information may include important data such as past stock prices, market indices, and average industry returns. For example, the price answer information includes key data such as the average annual return of FAANG stocks and the average industry growth rate over the past five years. These important data can be used as anchor information to establish a prediction model.
[0080] The anchor information may also be associated data in the context information. When there is previous question information and previous price answer information, the associated data may be extracted as anchor information based on these historical information. For example, in a previous conversation, the user mentioned their interest in the technology industry and their investment history in certain FAANG stocks, which may make previous investment preferences, transaction records and other information helpful in predicting financial returns.
[0081] In addition, the anchor information can also be related financial knowledge and financial indicators. According to the professional knowledge and common indicators in the financial field, the corresponding indicators can be extracted from the question information and the price answer information as anchor information. For example, indicators such as price-earnings ratio, price-to-book ratio, and profit growth rate may have an important impact on predicting financial returns.
[0082] Based on this, keywords, important data, related data, domain knowledge and other contents are extracted from the question information and its context information as anchor information, which can establish a prediction model or provide investment advice for predicting the price of financial products, and facilitate the subsequent provision of price answer information for predicting the price of financial products.
[0083] Specifically, the analysis includes step S120:
[0084] S121, understanding the question information and context information of the question information based on natural language technology.
[0085] The understanding refers to using natural language processing technology in artificial intelligence technology to understand the text of the question information and its following information, so as to identify key information and sentence structure, which can be achieved through part-of-speech tagging, entity recognition, grammatical analysis and other technologies.
[0086] It is worth noting that the understanding particularly includes the understanding of ambiguous contents in the question information and the understanding of long-tail question information.
[0087] Considering that ambiguity often exists in natural language, the same word or phrase may have multiple different meanings. Therefore, in the process of deconstruction, it is necessary to correctly understand the ambiguous content to ensure that the question information given by the user is correctly understood.
[0088] In the financial field, due to the complex market mechanism, the use of professional terms and the large amount of data involved, it is easy to generate ambiguous content. By way of example and not limitation, there are at least the following situations:
[0089] In one case, financial terms usually have specific meanings, but different people or different contexts may interpret or use these terms differently, resulting in ambiguous content. For example, price can refer to the price rate of different financial products such as stock prices, bond yields, and annualized returns of funds, but there is ambiguity as to whether the rate of return specifically refers to compound interest or single rate of return. In this case, the rate of return is ambiguous content.
[0090] Second, the interpretation of financial data may vary from person to person, and the same set of data may be given different interpretations or meanings as ambiguous content. For example, a company's profit growth of 10% may be good news for investors, but for analysts, they may need to further consider factors such as the sustainability of growth and cost structure.
[0091] Third, financial markets are often affected by market sentiment, which may lead to unstable interpretation of question information. For example, the same piece of news may be interpreted as positive news when market sentiment is good, but as negative news when market sentiment is bad.
[0092] In the fourth case, in financial analysis, using different methods or models may lead to different conclusions, thus causing the existence of ambiguous content. For example, for the valuation of the same stock, different target prices may be obtained based on different financial models.
[0093] Fifth, financial news or media reports may contain ambiguous content that is erroneous, exaggerated or inaccurate, leading to misunderstandings or wrong decisions among investors.
[0094] In the sixth case, sometimes the content provided by financial information is not enough to support a clear conclusion or decision. For example, a financial statement may lack certain key information, causing analysts to have doubts about the company's financial situation.
[0095] As for the understanding of long-tail question information, it is considered that some of the question information provided by users may have long sentences or paragraphs, which may contain a lot of information. Dealing with these long-tail questions may cause information overload, so effective information filtering is required to extract anchor information.
[0096] S122, extracting anchor point information having a logical relationship from the question information and the context information of the question information.
[0097] The logical relationship is specifically reflected in the existence of a logical reasoning or inference relationship between the question information and the price answer information. For example, according to the specific question embodied in the question information, the corresponding price answer information may provide a series of logically related information or suggestions. Then, according to the logical relationship between the question information and the price answer information, further reasoning and analysis are performed to formulate a decision-making strategy for predicting the price of financial products.
[0098] The logical relationship includes reflecting the causal relationship and / or time sequence relationship between the anchor point information.
[0099] Among them, the causal relationship is specifically reflected in that: specific questions in the question information may cause the price answer information to provide relevant data or suggestions, thereby affecting the forecast results of the financial product prices; and the data or information provided in the price answer information may directly affect the subsequent forecast results of the financial product prices because it provides important reference information about the prices.
[0100] The temporal order relationship is specifically reflected in the temporal order relationship between the question information and the price answer information. Considering the temporal order relationship between the question information and the price answer information can better understand the dynamics of the financial market and future prices. For example, the user may ask questions based on the past performance of the financial market, and the chatbot will provide corresponding suggestions based on the latest market trends.
[0101] S112, according to the aforementioned question information and the context information of the question information, the information hierarchy of the anchor information is obtained, and the anchor information is respectively set as first-level anchor information, second-level anchor information, ..., N-1-level anchor information, and N-level anchor information according to the information hierarchy from high to low, where N is an integer greater than or equal to 1.
[0102] Among them, the second-level anchor point information is the subordinate anchor point information of the first-level anchor point information, and so on, the N-level anchor point information is the subordinate anchor point information of the N-1-level anchor point; there is at least one anchor point information in each level.
[0103] As one of the preferred implementations of this embodiment, the process of obtaining the information hierarchy of the anchor information according to the aforementioned question information and its context information is, as an example but not a limitation, assuming that for financial investment, the user gives a question information: "I am interested in investing in FAANG stocks in the technology industry. How will the stock price be in the next year?" The corresponding price answer information is "The price of FAANG stocks in the next year may be affected by many factors, including the overall trend of the technology industry, the performance of FAANG companies, the global economic environment, etc. At present, the technology industry continues to innovate and accelerates digital transformation, which has a positive impact on the business development of FAANG companies. However, there are also some uncertain factors, such as the global trade situation and changes in regulatory policies, which may affect returns. Therefore, investors should consider various factors comprehensively when considering investing in FAANG stocks and carefully assess risks." In addition, the context information of the question information and price answer information is "The user is an investor who is interested in FAANG (Facebook, Apple, Amazon, Netflix and Google) stocks in the technology industry and wants to know the price trends in the next year. The question may be asked in an investment discussion or research, and may be part of a recent market dynamics or personal investment decision. The user may have learned some basic information about FAANG companies and the technology industry, but still wants to get more professional insights and forecasts."
[0104] Based on this, by analyzing the aforementioned question information and its context information, it can be determined that the question information provides first-level anchor point information to seventh-level anchor point information.
[0105] Among them, the first-level anchor information is the theme and purpose. The theme is financial investment, and the purpose is to predict the price of FAANG stocks in the next year.
[0106] Under the primary anchor information, the secondary anchor information is the problem and solution. The problem is the predicted price of FAANG stocks in the next year, and the solution is to analyze factors such as technology industry trends, FAANG company performance, and market prospects.
[0107] The third-level anchor information, namely key factors and data, is derived from the second-level anchor information. Among them, the key factors are the financial status of FAANG companies, the development trend of the technology industry, the global market situation, etc. The data are the financial statements of FAANG companies, the market share of the technology industry, global economic data, etc.
[0108] Next, we sorted out the fourth-level anchor information, namely financial indicators and market data, based on the third-level anchor information. The financial indicators include the revenue growth rate, profit margin, price-earnings ratio, etc. of FAANG companies, and the market data includes the overall growth rate of the technology industry, the performance of competitors, and the global market index.
[0109] Next, the fifth level of anchor information is derived from the fourth level of anchor information, namely specific company and industry analysis. The specific companies are Apple, Amazon, Facebook and FAANG companies, and the industry analysis aims to analyze the hot spots, innovation trends, market competition patterns, etc. of the technology industry.
[0110] Corresponding to the fifth level of anchor information, the sixth level of anchor information is mined, namely market comments and expert opinions. Among them, market comments can be analysts' predictions and suggestions on the future performance of FAANG stocks, and expert opinions are financial experts' analysis and views on the technology industry and FAANG companies.
[0111] Finally, based on the six-level anchor information, the seven-level anchor information is obtained, namely investment strategy and risk assessment. Among them, the investment strategy is to formulate an investment portfolio, choose investment timing and other suggestions, and the risk assessment is used to evaluate the risks and uncertainties faced by investing in the technology industry and FAANG stocks.
[0112] Since each level of anchor information generated helps to build a deeper and more comprehensive understanding of the question information, this operation helps to understand the user's topic and purpose, as well as the key factors and data that need to be considered, and ultimately derive decision-making information such as investment strategy and risk assessment.
[0113] Through the above steps, the question information and its context information can be broken down into smaller and more specific components, which helps to understand the question more accurately and provides a basis for the subsequent generation of adaptive price answer information.
[0114] It is also worth mentioning that, corresponding to the information hierarchy of the above-mentioned anchor point information, the logical relationship between the anchor point information at different levels is displayed. Furthermore, after displaying the logical relationship between the anchor point information at different levels, the information answer information for predicting the price of financial products is displayed accordingly based on the logical relationship between the anchor point information at different levels.
[0115] Still taking the sequential generation of the first-level anchor information to the seventh-level anchor information in the above embodiment as an example, in this information hierarchy, anchor information at different levels are interrelated to form an information system. Each level of information provides different levels of understanding of the problem, starting from the overall theme and purpose, and gradually refining to specific analysis and suggestions. Among them, the logical relationship is reflected in each level of anchor information. The high-level anchor information provides the background and framework for the low-level anchor information, and guides the direction of analysis and decision-making. At the same time, the low-level information provides specific data and detail support for the high-level, forming a complete information chain with each other.
[0116] Specifically, when the first-level anchor information reflects the theme and purpose, all other levels of anchor information depend on the first-level anchor information because the theme and purpose determine the scope and direction of the entire information.
[0117] When the secondary anchor information reflects problems and solutions, it solves the problems raised in the primary anchor information and provides a framework for subsequent analysis, which reflects the causal relationship between the primary anchor information and the secondary anchor information.
[0118] When the tertiary anchor information reflects key factors and data, it reflects that the key factors and data depend on problems and solutions because they provide the necessary information and data support for solving the problems, which reflects that there is a causal relationship between the secondary anchor information and the tertiary anchor information.
[0119] When the fourth-level anchor information reflects financial indicators and market data, it reflects that the financial indicators and market data depend on key factors and data, which makes the financial and market information more specific and provides a basis for further analysis, which reflects the existence of a causal relationship between the third-level anchor information and the fourth-level anchor information.
[0120] When the five-level anchor information reflects the analysis of specific companies and industries, it reflects that the analysis of specific companies and industries depends on financial indicators and market data. It further refines the financial and market data, analyzes the specific conditions of companies and industries, and reflects the causal relationship and time sequence relationship between the fourth-level anchor information and the fifth-level anchor information.
[0121] When the sixth-level anchor information reflects market comments and expert opinions, it reflects that market comments and expert opinions rely on specific company and industry analysis, and provide insights and forecasts from professionals, which are guiding for analysis and decision-making. It reflects that there is a causal relationship between the fifth-level anchor information and the sixth-level anchor information.
[0122] When the seventh-level anchor information reflects investment strategies and risk assessments, specific investment strategies and risk assessments are formulated based on expert advice and market analysis, which reflects the causal relationship between the sixth-level anchor information and the seventh-level anchor information.
[0123] Based on this, it can be determined that by understanding the logical relationship between anchor information at different levels, the price answer information can be better matched to ensure the coherence and completeness of the price answer information, thereby effectively solving the user's question information and providing targeted suggestions.
[0124] Preferably, the price solution information provides at least one estimated reference solution for the price of at least one financial product based on a combination of the aforementioned anchor point information at different levels.
[0125] The price answer information can be provided in combination with the most appropriate information screened from a preset corpus. Specifically, based on the combination of anchor point information at different levels, at least one estimated reference solution of at least one financial product price in the preset corpus is matched as the price answer information.
[0126] Based on this, this embodiment uses natural language technology in artificial intelligence technology to analyze the question information and the context information of the question information to obtain the information level of the anchor information, thereby combining the anchor information of different levels and matching the price answer information accordingly, so that the user can obtain at least one estimated reference solution for the price of at least one financial product. This method can improve the accuracy and completeness of the price answer information.
[0127] However, in some cases, the information in the preset prediction library may not be able to provide price answer information suitable for specific financial products. For example, factors such as delayed data updates, incomplete data coverage, inapplicability of preset analysis models, low data quality in the corpus, and the occurrence of emerging events may result in the information answer information not being fully adapted.
[0128] To this end, when it is determined that the information stored in the preset prediction library cannot constitute price answer information suitable for the aforementioned question information, it is preferred to provide suitable price answer information by issuing a cross-database query or transferring the answer to a professional.
[0129] Among them, the cross-database query method can aggregate the information of the currently used corpus with the information in other databases, thereby providing a data basis for this embodiment to display the information answer information of the predicted financial product prices according to the logical relationship between the anchor point information at different levels.
[0130] In addition, by aggregating data from different dimensions to obtain accurate price answer information that is suitable for the aforementioned question information, it is possible to better maintain user stickiness and assist users with consulting matters during transactions.
[0131] For other technical features, please refer to the previous embodiments and will not be described in detail here.
[0132] In addition, see Figure 2 As shown, the present invention also provides an embodiment, providing a device 200 for obtaining the price of a financial product, including a structure:
[0133] The price questioning unit 201 is used to obtain at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information.
[0134] The price providing unit 202 is used to analyze the aforementioned question information and the aforementioned context information and provide at least one price answer information through analysis; the price answer information can reflect at least one estimated reference solution for the price of at least one financial product.
[0135] For other technical features, please refer to the previous embodiments and will not be repeated here.
[0136] In addition, see Figure 3 As shown, the present invention also provides an embodiment, providing a system 300 for obtaining the price of a financial product, including:
[0137] The network node 301 is used to send and receive at least one question information and price answer information regarding at least one financial product price.
[0138] The information answering module 302 is used to provide corresponding price answering information according to the aforementioned question information.
[0139] The system server 303 is connected to the network node 301 and the information response module 302 .
[0140] The system server 303 is configured to: obtain at least one question information from at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information; after disassembling the aforementioned question information and the aforementioned context information, provide at least one price answer information through analysis; the price answer information can reflect at least one estimated reference solution for the price of at least one financial product.
[0141] For other technical features, please refer to the previous embodiments and will not be repeated here.
[0142] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a program stored thereon for use in the aforementioned system for obtaining the price of a financial product. When the program is executed by a processor, the steps of any of the aforementioned methods for obtaining the price of a financial product can be implemented.
[0143] For other technical features, please refer to the previous embodiments and will not be repeated here.
[0144] In the above description, within the scope of the target protection of the present disclosure, the components can be selectively and operatively combined in any number. In addition, terms such as "including", "comprising" and "having" should be interpreted as inclusive or open by default, rather than exclusive or closed, unless they are explicitly defined to the contrary. All technical, scientific or other terms have the meaning understood by those skilled in the art unless they are defined to the contrary. Common terms found in dictionaries should not be interpreted too idealistically or too impractically in the context of relevant technical documents, unless the present disclosure explicitly defines them as such.
[0145] Although the exemplary aspects of the present disclosure have been described for illustrative purposes, those skilled in the art should appreciate that the above description is only a description of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention. The scope of the preferred embodiments of the present invention includes other implementations in which functions may not be performed in the order in which they appear or are discussed. Any changes or modifications made by those skilled in the art based on the above disclosure are within the scope of the claims.
Claims
1. A method for obtaining the price of a financial product, characterized in that: include: Obtaining at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information; After disassembling the aforementioned question information and the aforementioned context information, provide at least one price answer information through analysis; The price solution information can reflect at least one estimated reference solution for the price of at least one financial product.
2. The method according to claim 1, characterized in that The financial products include stocks, bonds, currencies, foreign exchange, funds, insurance products, loans, credit instruments and / or securitized products; The inquiry information includes inquiry information related to investment objectives, investment preferences, market trends, market forecasts, investment risks, investment returns, investment strategies and / or investment advice; The context information includes previous question information, previous price answer information, user personal information, current conversation situation, network environment information, user emotions, user tone, external knowledge and / or external events related to the current topic.
3. The method according to claim 1, characterized in that The decomposition comprises the steps of: extracting anchor information from the question information and the context information of the question information; the anchor information is extracted from the question information and the context information of the question information to facilitate the subsequent provision of decision information for predicting the price of financial products; According to the aforementioned question information and the context information of the question information, the information hierarchy of the anchor information is obtained, and the first-level anchor information, the second-level anchor information, ..., the N-1-level anchor information, and the N-level anchor information are set from high to low levels, and N is an integer greater than or equal to 1; wherein the second-level anchor information is the subordinate anchor information of the first-level anchor information, and so on, the N-level anchor information is the subordinate anchor information of the N-1-level anchor; there is at least one anchor information in each level.
4. The method according to claim 3, characterized in that The analysis includes the steps of: understanding the aforementioned question information and context information of the aforementioned question information based on natural language technology; Anchor point information having a logical relationship is extracted from the question information and the context information of the question information; the logical relationship includes a causal relationship and / or a time sequence relationship between the anchor point information.
5. The method according to claim 4, characterized in that Corresponding to the information hierarchy of the above anchor information, the logical relationship between anchor information at different levels is displayed; After displaying the logical relationship between the anchor point information at different levels, the information answer information predicting the price of the financial product is displayed accordingly based on the logical relationship between the anchor point information at different levels.
6. The method according to claim 5, characterized in that The price answer information provides at least one estimated reference solution for the price of at least one financial product based on a combination of the aforementioned anchor point information at different levels.
7. The method according to claim 6, characterized in that When it is determined that the information stored in the preset prediction library cannot form price answer information suitable for the aforementioned question information, suitable price answer information is provided by issuing a cross-database query or transferring the answer to a professional.
8. A device for obtaining the price of a financial product according to the method according to any one of claims 1 to 7, characterized in that: Includes structure: A price questioning unit, used to obtain at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the aforementioned question information; A price providing unit, configured to analyze the question information and the context information and provide at least one price answer information; The price solution information can reflect at least one estimated reference solution for the price of at least one financial product.
9. A system for obtaining the price of a financial product according to the method of any one of claims 1 to 7, characterized in that include: A network node, configured to send and receive at least one question message and price answer message regarding at least one financial product price; An information answering module, used to provide corresponding price answering information according to the aforementioned question information; a system server, wherein the system server is connected to the network node and the information answering module; The system server is configured to: obtain at least one question information of at least one user regarding the price of at least one financial product, and at least one context information of the question information; after disassembling the question information and the context information, provide at least one price answer information through analysis; The price solution information can reflect at least one estimated reference solution for the price of at least one financial product.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps described in any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Contextual information-based intelligent robot cloud computing method
CN107493353A
Financial product screening method and system, terminal equipment and storage medium
CN117557381A
Financial product recommendation method and device based on artificial intelligence, and electronic equipment
CN118154272A
Dynamic adaptation question answering system and method based on hierarchical structure and retrieval enhancement
CN118193714A
Intelligent investment analysis method and system based on user portrait technology
CN118350943A
