A method for financial scenario search ranking integrating category features, a device, and a medium

HK40137259APending Publication Date: 2026-09-11WIND INFORMATION(HK) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
HK42026125166
Authority / Receiving Office
HK · HK
Patent Type
Applications
Current Assignee / Owner
Filing Date
2026-06-23
Publication Date
2026-09-11

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

The first aspect of the technical scheme of the invention is to disclose a financial scene searching and sorting method fusing category features. The second aspect of the technical scheme of the invention is to disclose an electronic device. The third aspect of the technical scheme of the invention is to disclose a computer readable storage medium. A traditional keyword retrieval method is difficult to meet the requirement of a user for the financial information acquisition accuracy, and compared with the prior art, the method based on document category prediction can greatly improve the information accuracy, effectively reduce the burden of screening invalid information by the user and improve the information acquisition efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

(54) Invention Title: Financial Scene Search Ranking Method, Device, and Medium Integrating Category Features (57) Abstract: The first aspect of this invention discloses a financial scene search ranking method integrating category features. The second aspect of this invention discloses an electronic device. The third aspect of this invention discloses a computer-readable storage medium. Traditional keyword retrieval methods are difficult to meet users' requirements for the accuracy of financial information acquisition. In contrast, the document category prediction method proposed in this invention can significantly improve the accuracy of information, effectively reduce the burden on users to filter invalid information, and improve the efficiency of information acquisition. (19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number CN 121597912 A (43) Application Publication Date 2026.03.03 (21) Application Number 202511797361.8 (22) Application Date 2025.12.02 (71) Applicant Wind Information Software (Shanghai) Co., Ltd. Address Building C, No. 888, Huanhu West Second Road, Lingang New Area, Pudong New Area, Shanghai 200120, China (Shanghai) Pilot Free Trade Zone (72) Inventors Peng Long, Chu Jiawen, Cai Changkun (74) Patent Agency Shanghai Shenhui Patent Agency Co., Ltd. 31001 Patent Attorney Weng Ruoying (51) Int.CI. G06F / 6 / 9535 (2019.01) G06F f6 / 9536 (2019.01) G06F / 6 / 9538 (2019.01) G06F / 8 / 24 / (2023.01) Claims 1 page, Description 5 pages, Drawings 1 page, ATM I output 11 pages, M 7 CN 121597912 A Claims 1 / 1 page 1. A method for ranking financial scenario searches by integrating category features, characterized by the following steps: Step 1: Identify the document category information associated with the user's question and obtain the relevance between the current user's question and each document category; Step 2: Based on the relevance prediction results output in Step 1, filter out candidate document category groups with high relevance from all document categories according to a pre-set relevance threshold; Step 3: Based on the candidate document category groups obtained in Step 2, construct the recall quantity of different document categories in the candidate document category groups; Step 4: Based on the recall quantity of different document categories constructed in Step 3, construct the recall conditions for document search AH and perform document recall; Step 5: Based on the candidate document categories and relevance in the candidate document category groups obtained in Step 2, use pre-set auxiliary features to perform regularized weighted scoring on the documents recalled through Step 4, rank the recalled documents based on the weighted scoring results, and return the number of documents requested by the front end.2. A financial scenario search ranking method integrating category features as described in claim 1, characterized in that step 1 includes the following steps: Step 101, training a BERT text multi-classification model to identify the relevance between user questions and document categories based on classification data annotated by human experts; Step 102, during online inference, using the trained BERT classification model to predict the relevance between user questions and documents of different categories. 3. A financial scenario search ranking method integrating category features as described in claim 2, characterized in that, in step 101, when annotating the classification data by human experts: if the user question explicitly mentions the document type required; if the user question does not explicitly mention the document type required, then annotate according to which documents the relevant answer might appear in. 4. A financial scenario search ranking method integrating category features as described in claim 1, characterized in that step 3 includes the following steps: Step 301, obtaining the recall ratio of different document categories after standardization based on the relevance values ​​of different document categories; Step 302, calculating the recall quantity of different document categories based on the recall ratio of different document categories and the preset total recall quantity. 5. A financial scenario search and ranking method integrating category features as described in claim 1, characterized in that, in step 5, when performing rule-based weighted scoring, the relevance scores of different document categories are used as relevance weight factors, and weighted scoring is performed on the document relevance calculated with other features, as shown in the following formula: score(q, doc) = score(doc type) * score(text match, time,…), where <q is the user question, doc is the recalled document, score^(doc type) is the document category relevance, text match is the text relevance, tfme is the document timeliness score, and score(text match, time,…) is the joint score of text relevance and timeliness weighted factors. 6. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors execute software to implement the financial scenario search and ranking method according to claim 1. 7. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the financial scenario search and ranking method according to claim 1.2 CN 121597912 A Specification 1 / 5 pages Financial Scene Search Ranking Method, Device and Media Integrating Category Features Technical Field

[0001] This invention relates to a method, device and media for effectively searching financial documents in a financial scene by utilizing available document category features, and ranking the documents that best meet user needs to the top position. Background Art

[0002] With the rapid development of the Internet and the exponential growth of various data, users face a massive amount of information resources. How to efficiently and accurately obtain the required information has become a major challenge. As an important technology to solve this challenge, search engines have become an indispensable core tool in modern society. In the financial field, efficient acquisition and accurate analysis of information are crucial for decision-making, and search engines play a vital role in this context. For example: 1) Financial professionals need to obtain the latest prices and trends of financial products such as stocks, bonds, and foreign exchange in real time. Search engines need to provide relevant data quickly and accurately to help users make immediate decisions; 2) When making investment decisions, investors often need to consult various research reports and market analysis articles. Search engines need to accurately match relevant content and provide in-depth analysis support; 3) Investment research personnel monitor specific keywords or events through search engines to promptly discover potential market risks, such as policy changes and industry crises, to help users take countermeasures in advance; 4) The financial industry is greatly affected by policies. Users need to keep abreast of the latest laws, regulations, and policy developments. Search engines need to quickly provide relevant interpretations and analyses.

[0003] Therefore, financial users have a particularly strong demand for search engines. Optimizing the application of search engines in the financial field has extremely high practical value and market prospects.

[0004] Unlike general web pages, financial documents have more specialized classification information. For example, research reports can be divided into industry research reports, company research reports, strategy research reports, etc.; announcements can be divided into financial reports, announcements of major events, investor relations announcements, etc.; and news covers multiple subcategories such as market dynamics, policy interpretations, and company news. In addition, financial documents often contain some additional attribute information, such as the author of the research report, the institution that issued the research report, the publisher of the announcement, etc. Users' needs often explicitly or implicitly include their needs for document categories. However, when processing these highly specialized financial documents, existing general search algorithms often do not consider the detailed category needs of users in financial scenarios, which may lead to overly broad and untargeted search results that cannot effectively meet the actual needs of users. Most vertical search engines often only use keyword matching or text similarity to retrieve relevant documents, and document category information needs to be filtered by users by clicking different tabs, resulting in low user search efficiency.

[0005] The technical problem to be solved by the present invention is that search ranking algorithms based on keyword search or text similarity matching are difficult to capture users' needs for professional information such as document categories in financial scenarios. Although the tab menu filtering method can help users narrow down the search scope to a certain extent, it is cumbersome and lacks flexibility. Users need to manually select multiple tabs to filter layer by layer, which not only increases the user's operational burden, but may also lead to missed or false detections due to insufficient refinement of option settings or users' lack of understanding of the options.

[0006] To solve the above-mentioned technical problems, the first aspect of the technical solution of the present invention discloses a financial scenario search ranking method that integrates category features (CN 121597912 A specification page 2 / 5), characterized by including the following steps: Step 1: Identify the document category information associated with the user question and obtain the relevance between the current user question and each document category; Step 2: Based on the relevance prediction results output in Step 1, filter out candidate document category groups with high relevance from all document categories according to a pre-set relevance threshold; Step 3: Based on the candidate document category groups obtained in Step 2, construct the recall quantity of different document categories in the candidate document category groups; Step 4: Based on the recall quantity of different document categories constructed in Step 3, construct the recall conditions of the document search API and perform document recall; Step 5: Based on the candidate document categories and relevance in the candidate document category groups obtained in Step 2, use the preset features to perform rule-based weighted scoring on the documents recalled through Step 4, sort the recalled documents based on the weighted scoring results, and return the number of documents requested by the front end.

[0007] Preferably, step 1 includes the following steps: Step 101: Train a BERT text multi-classification model to identify the relevance between user questions and document categories based on classification data annotated by human experts; Step 102: During online inference, use the trained BERT classification model to predict the relevance between user questions and documents of different categories.

[0008] Preferably, in step 101, when annotating the classification data by human experts: if the user question explicitly mentions the document type of the requirement; if the user question does not explicitly mention the document type of the requirement, then annotate according to which documents the relevant answer may appear in.

[0009] Preferably, step 3 includes the following steps: Step 301: Obtain the recall ratio of different document categories after standardization based on the relevance values ​​of different document categories; Step 302: Calculate the recall quantity of different document categories based on the recall ratio of different document categories and the preset total recall quantity.

[0010] Preferably, in step 5, when performing rule-based weighted scoring, the relevance scores of different document categories are used as relevance weight factors, and weighted scoring is performed on the document relevance calculated with other features, as shown in the following formula: score (q, doc) — score(doc type) * score (text match, time,...)

[0011] Wherein, <7 is the user question, q is the recalled document, score(doctype) is the document category relevance, text match is the text relevance, time is the document timeliness score, and score(text match, time,...) is the joint score of text relevance and timeliness weighted factors. tool2] The second aspect of the technical solution of the present invention discloses an electronic device, including: one or more processors; a storage device for storing one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors execute software to implement the financial scenario search and ranking method based on the above-mentioned fused category features.

[0013] The third aspect of the technical solution of the present invention discloses a computer-readable storage medium storing executable instructions, which, when executed by a processor, cause the processor to execute a search and sorting method for financial scenarios based on the aforementioned fusion category features.

[0014] Traditional keyword retrieval methods are difficult to meet users' requirements for the accuracy of financial information acquisition. In contrast, the document category prediction method proposed in this invention can significantly improve the accuracy of information, effectively reduce the burden on users to filter invalid information, and improve the efficiency of information acquisition. Specifically, it has the following beneficial effects: 1) The BERT text classification model based on the pre-training-fine-tuning paradigm has been widely used in various intelligent systems, and its accuracy and adaptability have been widely verified; 2) By analyzing the correlation between user questions and different document categories, irrelevant documents can be effectively filtered, increasing the probability of hitting the correct document; 3) By weighted scoring and sorting by document category, the most relevant documents can be effectively obtained, increasing the probability of hitting the first page. Brief Description of the Drawings

[0015] Figure 1 is a flowchart of the method disclosed in this invention. Detailed Description of Embodiments

[0016] Various aspects and features of the present invention are described herein with reference to the accompanying drawings.

[0017] It should be understood that various modifications can be made to the embodiments described herein. Therefore, the foregoing description should not be considered as limiting, but merely as an example of embodiments. Other modifications within the scope and spirit of this disclosure will be apparent to those skilled in the art.

[0018] The accompanying drawings, which are included in and constitute a part of this specification, illustrate embodiments of the invention and, together with the general description of the invention given above and the detailed description of the embodiments given below, serve to explain the principles of the invention.

[0019] These and other features of the invention will become apparent from the following description of preferred forms of embodiments given as non-limiting examples, with reference to the accompanying drawings.

[0020] It should also be understood that although the invention has been described with reference to some specific examples, many other equivalent forms of the invention can be definitively implemented by those skilled in the art, having the features as claimed and therefore falling within the scope of protection defined herein.

[0021] The above and other aspects, features, and advantages of the invention will become more apparent when taken in conjunction with the accompanying drawings, in view of the following detailed description.

[0022] Specific embodiments of the invention are described thereafter with reference to the accompanying drawings; however, it should be understood that the claimed embodiments are merely examples of the invention, which may be implemented in various ways. Well-known and / or repeated functions and structures are not described in detail to avoid unnecessary or redundant details that would obscure this disclosure. Therefore, the specific structural and functional details applied in this invention are not intended to be limiting, but are merely intended as the basis and representative basis of the claims to teach those skilled in the art to use this disclosure in various ways with substantially any suitable detailed structure.

[0023] The phrases “in one embodiment,” “in another embodiment,” “in yet another embodiment,” or “in other embodiments” may be used in this specification, all of which may refer to one or more of the same or different embodiments according to this disclosure.

[0024] In order to solve the problem of the professionalism of search in the current financial scenario, the present invention proposes an automated technical solution that considers the user’s detailed needs for document categories and attributes, which can greatly improve the efficiency and accuracy of document retrieval in the financial scenario. 5 CN 121597912 A Specification 4 / 5 pages

[0025] Referring to Figure 1, the first aspect of the embodiment of the present invention discloses a financial scenario search ranking method that integrates category features, including the following steps: Step 1: Identify the document category information associated with the user’s question and obtain the relevance between the current user’s question and each document category.

[0026] In an embodiment of the present invention, a preferred implementation is that step 1 further includes the following steps: Step 101: Train a BERT text multi-classification model that identifies the relevance between user questions and document categories based on classification data annotated by human experts.

[0027] In another preferred embodiment of the present invention, when manually annotating the classified data by experts: if the user's question explicitly mentions the document type of the need, such as research reports, announcements, news, etc., the category is labeled as the mentioned document type; if the user's question does not explicitly mention the document type of the need, then the category is labeled according to which documents the relevant answer may appear in.

[0028] Step 102: During online inference, the trained BERT classification model is used to predict the relevance between the user's question and documents of different categories. In a preferred embodiment of the present invention, the BERT classification model outputs 0-1 to represent the relevance, for example, 1 can be used to represent relevance, and 0 is used to represent no relevance.

[0029] Step 2: Based on the relevance prediction results output in Step 1, according to the pre-set relevance threshold, candidate document category groups with high relevance are selected from all document categories.

[0030] In a preferred embodiment of the present invention, step 2 specifically involves: predicting the relevance between different document categories and the current user's question using the BERT classification model in step 1. The obtained result can be represented as [(category 1, relevance 1), (category 2, relevance 2), ...]. Based on a preset relevance threshold, filtering out document categories with low relevance yields a candidate document category group.

[0031] Step 3: Based on the candidate document category group obtained in step 2, constructing the recall count for different document categories within the candidate document category group.

[0032] In a preferred embodiment of the present invention, step 3 further includes the following steps: Step 301: Standardizing the relevance values ​​of different document categories to obtain the recall ratio for different document categories; Step 302: Calculating the recall count for different document categories based on the recall ratio for different document categories and a preset total recall count.

[0033] Step 4: Based on the recall count for different document categories constructed in step 3, constructing the recall conditions for the document search API and performing document recall. [E0034] In this embodiment of the invention, a preferred implementation is that, when recalling documents, the backend retrieval API is called for different document categories to recall documents.

[0035] Step 5: Based on the candidate document categories and relevance in the candidate document category group obtained in Step 2, other features, including text similarity and timeliness, are used to perform rule-based weighted scoring on the documents recalled through Step 4. Based on the weighted scoring results, the recalled documents are sorted, and the number of documents requested by the front end is returned.

[0036] In an embodiment of the present invention, a preferred implementation is that, when performing rule-based weighted scoring, the relevance scores of different document categories are used as relevance weight factors, and weighted scores are calculated with document relevance obtained from other features, as shown in the following formula: score (q, doc) = score (doc type) ♦ score (text match, time,...)

[0037] Where, <7 is the user question, doc is the recalled document, score(,doc type) is the document category relevance, text match is the text relevance, time is the document timeliness score, and score(text match, time,...) is the joint score of text relevance and timeliness weighted factors.

[0038] A second aspect of the present invention is to provide an electronic device, including at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the above-mentioned financial scenario search and ranking method when executing the computer program in the memory.

[0039] In some embodiments, the processor executing the computer program may be a processing device that includes one or more general-purpose processing devices, such as a microprocessor, a central processing unit (CPU), a graphics processing unit (GPU), etc. More specifically, the processor may be a complex instruction set computing (CISC) microprocessor, a reduced instruction set computing (RISC) microprocessor, a very long instruction word (VLIW) microprocessor, a processor that runs other instruction sets, or a processor that runs a combination of instruction sets. The processor may also be one or more special-purpose processing devices, such as application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), system-on-a-chip (SoCs), etc.

[0040] The memory may be a read-only memory (ROM), random access memory (RAM), phase-change random access memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), electrically erasable programmable read-only memory (EEPROM), other types of random access memory (RAM), flash drives or other forms of flash memory, cache, registers, static memory, optical disc read-only memory (CD-ROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape cassette or other magnetic storage devices, or any other possible non-transitory medium used to store information or instructions that can be accessed by a computer device.

[0041] A third aspect of the present invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described financial scenario search and ranking method.

[0042] The computer-readable storage medium of the embodiments of the present invention may be any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. In the embodiments of the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device, for example, the aforementioned memory.

[0043] The computer program of the embodiments of the present invention may be organized into one or more computer-executable components or modules. Any number and combination of such components or modules may be used to implement aspects of this disclosure. For example, aspects of this disclosure are not limited to the specific computer-executable instructions or specific components or modules shown in the drawings and described herein. Other embodiments may include different computer-executable instructions or components having more or fewer functions than those shown and described herein.

[0044] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in this invention is not limited to technical solutions formed by specific combinations of the above-mentioned technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-mentioned technical features or their equivalent features without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this invention. 7 CN 121597912 A Specification Figure 1 / 1 page Figure 1 8 Title of Invention: A Method for Financial Scenario Search Ranking Integrating Category Features, a Device, and a Medium Title of Invention: A Method for Financial Scenario Search Ranking Integrating Category Features, a Device, and a Medium Chinese Abstract The first aspect of the technical solution of this invention discloses a method for searching and ranking financial scenarios based on category features. The second aspect of the technical solution of this invention discloses an electronic device. The third aspect of the technical solution of this invention discloses a computer-readable storage medium. Traditional key search methods are insufficient to meet users' requirements for the accuracy of financial information acquisition. In contrast, the document category prediction method proposed in this invention can significantly improve the accuracy of information, effectively reduce the burden on users to filter out invalid information, and improve the efficiency of information acquisition.English Abstract A first aspect of the technical solution of the present invention discloses a financial scenario search ranking method integrating category features. A second aspect of the technical solution of the present invention discloses an electronic device. A third aspect of the technical solution of the present invention discloses a computer-readable storage medium. Traditional keyword retrieval methods have difficulty meeting users' requirements for accuracy in obtaining financial information. In comparison, the method based on document category prediction proposed by the present invention can greatly improve information precision, effectively reduce the users' burden of filtering invalid information, and improve information acquisition efficiency. Abstract.

Claims

1. A search and ranking method for financial scenarios that integrates category features, characterized in that, Includes the following steps: Step 1: Identify the document category information associated with the user's question and obtain the relevance between the current user's question and each document category; Step 2: Based on the relevance prediction results output in Step 1, filter out candidate document category groups with high relevance from all document categories according to the pre-set relevance threshold; Step 3: Based on the candidate document category groups obtained in Step 2, construct the recall quantity of different document categories in the candidate document category groups; Step 4: Based on the recall quantity of different document categories constructed in Step 3, construct the recall conditions for the document search API and perform document recall; Step 5: Based on the candidate document categories and relevance in the candidate document category groups obtained in Step 2, use the pre-set auxiliary features to perform rule-based weighted scoring on the documents recalled through Step 4, sort the recalled documents based on the weighted scoring results, and return the number of documents requested by the front end.

2. The financial scenario search and ranking method integrating category features as described in claim 1, characterized in that, Step 1 includes the following steps: Step 101, train a BERT text multi-classification model to identify the relevance between user questions and document categories based on classification data annotated by human experts; Step 102, during online inference, use the trained BERT classification model to predict the relevance between user questions and documents of different categories.

3. The financial scenario search and ranking method integrating category features as described in claim 2, characterized in that, In step 101, when performing manual expert annotation on the categorized data: if the user's question explicitly mentions the document type required; if the user's question does not explicitly mention the document type required, then the annotation is performed based on which documents the relevant answer might appear in.

4. The financial scenario search and ranking method integrating category features as described in claim 1, characterized in that, Step 3 includes the following steps: Step 301, standardize the relevance values ​​of different document categories to obtain the recall ratio of different document categories; Step 302, calculate the recall quantity of different document categories based on the recall ratio of different document categories and the preset total recall quantity.

5. The financial scenario search and ranking method integrating category features as described in claim 1, characterized in that, In step 5, when performing rule-based weighted scoring, the relevance scores for different document categories are used as relevance weighting factors, and weighted together with the document relevance calculated from other features, as shown in the following formula: In the formula, For users to ask questions, To recall the documents, For document category relevance, For text relevance, Rate the timeliness of the document. A combined score is given based on factors such as text relevance and timeliness.

6. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute software to implement the financial scenario search and ranking method according to claim 1.

7. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the financial scenario search and ranking method according to claim 1.