Financial data efficient retrieval method and financial data processing system

Abstract

The invention relates to the technical field of data processing, in particular to a financial data efficient retrieval method and a financial data processing system. The method comprises the following steps: firstly, analyzing a fuzzy retrieval behavior of a retriever in financial data to obtain an actual expected retrieval community of the retriever for the financial data, and then respectively obtaining information validity of different financial data in the expected retrieval community; according to multiple times of fuzzy retrieval behaviors, different financial data in an expected retrieval community are subjected to information validity increment acquisition, then according to the validity of the financial data and the validity increment, a final expected value of the financial data is acquired, and finally, the final expected value of the financial data is acquired. And displaying a retrieval result to the retriever according to the financial data obtained by the retriever in the last retrieval behavior under one retrieval purpose and the final expected value corresponding to each piece of financial data. According to the method, more accurate financial data meeting the expectation of a searcher can be provided for the searcher.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an efficient financial data retrieval method and a financial data processing system. Background Art

[0002] In the operation and management of modern enterprises, financial data is not only the basis for internal audits, report preparation and tax declarations, but also an important source of information for external investors, some institutions and other stakeholders to assess the health of the enterprise and the value of investment. Financial data covers all aspects of the enterprise, including income, expenditure, assets, liabilities, cash flow, etc., involving almost every aspect of the enterprise's operation. Therefore, accurate and efficient financial data processing is particularly important. Due to the large amount of enterprise financial data, complex content, and continuous updates as the business of the enterprise changes, how to quickly extract valuable information from the huge amount of financial data has become a problem that needs to be solved urgently.

[0003] The existing financial data retrieval method generally requires the searcher to set corresponding keyword restrictions and then use a full-text search engine to perform a global search of the financial database. This search method can provide relatively effective search results when the keyword input is very accurate, but it is common that the search keywords are mostly fuzzy words, and the global search method is an independent search process, that is, each search is not related in the search algorithm. This type of search usually returns a large number of documents, or even completely unrelated results. This search process is very inefficient, causing inconvenience to the staff in searching and consulting financial data. Summary of the invention

[0004] In order to solve the technical problem of inefficient financial data retrieval process in the prior art, the purpose of the present invention is to provide an efficient financial data retrieval method and a financial data processing system. The technical solutions adopted are as follows: In a first aspect, a method for efficiently retrieving financial data is provided, the method comprising: Step S1: Collect financial data, create indexes, and build a financial database; Step S2: obtaining the validity of the financial data according to the browsing behavior of the searcher for a financial data in each search behavior under a search purpose; Step S3: Obtain the validity increment of the financial data according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple search behaviors under a search purpose of the searcher; Step S4: obtaining a final expected value of the financial data according to the validity and validity increment of the financial data; Step S5: Display the search results to the searcher based on the financial data obtained from the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

[0005] Furthermore, the step S1 specifically includes: Collect financial data, clear or correct incomplete or inaccurate financial data, and standardize financial data; Create an index for each piece of financial data, and build a financial database based on the indexed financial data.

[0006] Furthermore, after step S1 and before step S2, the method further includes: According to the searcher's operation behavior on the first keyword search result, obtain the searcher's satisfaction with the first search result; According to the searcher's satisfaction with the first search result, the possibility of the searcher conducting a second search is obtained; If the possibility that the searcher conducts a second search is greater than or equal to the preset possibility threshold, then continue with step S2-step S5; if the possibility that the searcher conducts a second search is less than the preset possibility threshold, then there is no need to continue with step S2-step S5.

[0007] Furthermore, the method of obtaining the searcher's satisfaction with the first search result based on the searcher's operational behavior on the first keyword search result is specifically as follows: obtaining the searcher's satisfaction with the first search result based on the time interval between the searcher's first keyword search and the second keyword search, the semantic similarity of the keywords in the first keyword search and the second keyword search, the average time the searcher spends viewing the financial data in the first search result, the total number of reference operations on the financial data in the first search result, and the total number of financial data in the first search result that the searcher browsed.

[0008] Furthermore, the time interval between the searcher's first keyword search and the second keyword search, the average time the searcher spends viewing the financial data in the first search results, and the total number of reference operations on the financial data in the first search results are all positively correlated with the searcher's satisfaction with the first search results; the semantic similarity of the keywords in the first keyword search and the second keyword search, and the total number of financial data browsed by the searcher in the first search results are all negatively correlated with the searcher's satisfaction with the first search results.

[0009] Furthermore, after step S1 and before step S2, it also includes: constructing a network graph based on the financial data extracted from the searcher's search keywords, taking each financial data as a node, facilitating the graph algorithm and the connectivity and density between nodes, and dividing relevant communities as the searcher's expected search communities for this search.

[0010] Furthermore, in step S2, based on the browsing behavior of a financial data in each search behavior under a search purpose by the searcher, obtaining the validity of the financial data specifically includes: a search behavior under a search purpose by the searcher forms a search expectation community for the search, the searcher browses the financial data under the search expectation community, when a financial data is browsed, the validity of the financial data is obtained based on the browsing time of the financial data and the average time of other financial data browsed by the searcher, and when a financial data is not browsed, the validity of the financial data is obtained based on the inverse of the total number of all the financial data that have not been browsed.

[0011] Furthermore, in step S3, the number of times a financial data appears in multiple search results in multiple search behaviors for one search purpose and the similarity of the search keywords each time they appear are positively correlated with the increase in the effectiveness of the financial data, and the number of times a financial data is browsed in multiple search behaviors for one search purpose is negatively correlated with the increase in the effectiveness of the financial data.

[0012] Furthermore, in step S5, based on the financial data obtained by the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data, the search result display to the searcher specifically includes: The final expected values ​​corresponding to all the financial data in the search expectation community obtained by the searcher in the last search are screened, and the financial data with a value less than a preset expected value threshold is screened out; The remaining financial data are sorted in descending order according to the final expected values ​​corresponding to the financial data, and the sorted remaining financial data are the display order of the relevant financial data corresponding to this search; The search results are displayed in sequence according to the display order of the relevant financial data corresponding to this search.

[0013] In another aspect, the present invention provides a financial data processing system, the system comprising: Financial database acquisition module, used to collect financial data, create indexes, and build a financial database; The validity acquisition module is used to acquire the validity of the financial data according to the browsing behavior of the financial data in each search behavior under a search purpose by the searcher; The validity increment acquisition module is used to obtain the validity increment of the financial data according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple search behaviors under a search purpose of the searcher; A final expected value acquisition module, used to acquire the final expected value of the financial data according to the validity and validity increment of the financial data; The display result acquisition module is used to display the search results to the searcher based on the financial data obtained from the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

[0014] The present invention has the following beneficial effects: utilizing a dynamic incremental retrieval algorithm of reinforcement learning, by analyzing the searcher's fuzzy retrieval behavior in financial data, the searcher's actual expected retrieval community for financial data is obtained, and then the information validity of different financial data in the expected retrieval community is obtained respectively, and dynamic learning adjustment of the information validity of different financial data in the expected retrieval community is performed based on multiple fuzzy retrieval behaviors, thereby more accurately realizing local joint learning incremental retrieval of financial data when the searcher uses fuzzy financial data retrieval, and providing the searcher with more accurate financial data that meets the searcher's expectations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 A flow chart of an efficient financial data retrieval method provided by an embodiment of the present invention.

[0017] Figure 2 A block diagram of a financial data processing system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, characteristics and effects of a financial data efficient retrieval method and a financial data processing system proposed according to the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. Unless otherwise defined, all technical and scientific terms used in this article have the same meaning as those commonly understood by technicians in the technical field of the present invention.

[0019] The scenario targeted by the present invention is: generally, when calling financial data, it is necessary to search the data in the financial database. However, due to the large amount of data and complex content, how to obtain accurate demand information from the financial data often requires extremely accurate search formulas to assist. However, when searching for financial data, general personnel usually enter keywords for fuzzy search multiple times, resulting in the query usually returning a large number of documents, or even completely irrelevant results, which makes the overall search process appear very inefficient. And because each search behavior of the conventional search method is usually an independent search behavior, the search keywords can only be adjusted manually according to the results of each fuzzy search, and then approach the final search expected key words. This independent search behavior cannot effectively learn the behaviors of multiple fuzzy searches together to adjust the search results.

[0020] The specific scheme of an efficient financial data retrieval method and a financial data processing system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0021] First, see Figure 1 , which shows a flow chart of an efficient financial data retrieval method provided by an embodiment of the present invention, the method comprising the following steps: Step S1: Collect financial data, create indexes, and build a financial database.

[0022] Among them, step S1 specifically includes: collecting financial data, clearing or correcting incomplete and inaccurate financial data, and standardizing the financial data; indexing each piece of financial data, and building a financial database based on the indexed financial data.

[0023] More specifically, first, the required financial data is collected by using the enterprise's internal ERP (Enterprise Resource Planning) system, external financial reports, third-party API (Application Programming Interface), etc., and the collected financial data is cleaned to ensure the integrity and accuracy of the data; then, the financial data is standardized, including the unit unification of relevant parameters in the financial data, the time format unification in the financial data, etc.; finally, an index is established for each piece of financial data, and a database is established for the indexed financial data. At this point, the construction of the financial database is completed.

[0024] When searching for financial data in a financial data database, there are generally two types of results based on the information feedback from the search: the first type of result is that the search result is the accurate result required by the searchee, in which case the searchee can obtain valid financial information and the search ends; the second type of result is that the search result is an inaccurate result, in which case the searchee cannot obtain the required valid financial information and a secondary search is required.

[0025] Generally speaking, the first type of search results mentioned above are for accurate searches. This search mode requires the searcher to have a thorough understanding of all the financial information in the financial database. However, since there is a large amount of financial data in the financial database, this type of search behavior is generally impossible except for special or professional personnel. Under normal circumstances, most financial data searches belong to the second type of search. In fact, when the searcher cannot obtain valid financial data information in the financial database, the search behavior of searching again is a supplement and further limitation to the previous search behavior, that is, the searcher's actual search expectations can be further obtained by analyzing the searcher's search behavior, so as to obtain the actual financial data information required by the searcher.

[0026] When performing data retrieval, the above two results will appear, and the actual behaviors of the search personnel for the two different results are different. Therefore, this embodiment obtains the searcher's satisfaction with the first search result by analyzing the searcher's search behavior and the searcher's use of the search results, so as to further obtain whether the current search belongs to the first category of search results or the second category of search results. When the search behavior belongs to the second search result, the searcher's actual search expectations are obtained by further analyzing the connectivity of the qualifiers in the search process, so as to make efficient recommendations on the search results.

[0027] Specifically, first, based on the searcher's operational behavior on the first keyword search result, the searcher's satisfaction with the first search result is obtained; then, based on the searcher's satisfaction with the first search result, the possibility of the searcher conducting a second search is obtained; if the possibility of the searcher conducting a second search is less than a preset possibility threshold (the preset possibility threshold can be 0.75), it is considered that the first search result belongs to the first category of search results, and under the search purpose of this searcher, the searcher has obtained the accurate results required by the searcher through the first search, and this search ends; if the possibility of the searcher conducting a second search is greater than or equal to the preset possibility threshold, it is considered that the first search result belongs to the second category of search results, and it is necessary to further analyze the connectivity of the qualifiers in the search process of the searcher to achieve the acquisition of the searcher's actual search expectations.

[0028] Among them, based on the searcher's operational behavior on the first keyword search result, the searcher's satisfaction with the first search result is obtained specifically as follows: based on the time interval between the searcher's first keyword search and the second keyword search, the semantic similarity of the keywords in the first keyword search and the second keyword search, the average time the searcher spends viewing the financial data browsed in the first search result, the total number of reference operations on the financial data in the first search result, and the total number of financial data browsed by the searcher in the first search result, the searcher's satisfaction with the first search result is obtained.

[0029] More specifically, when analyzing the searcher's satisfaction with the first search result, for the accurate information retrieved, the searcher generally has obvious clicks or references to financial data (transmission, downloading, etc.), while for the inaccurate information retrieved, the searcher generally has inconspicuous clicks or browses multiple information in a short time, and there is no clear click or reference to financial data. Therefore, according to this logic, the searcher's behavioral information on the first search result is quantified. Furthermore, when the searcher performs the first financial data search by entering the search keyword, if the search result is accurate, there is no need to perform a second search, so the time interval between the two adjacent searches is long, and there is a certain gap in the semantics of the keywords of the two searches; however, if the search result is inaccurate, it is often necessary to perform a second or multiple searches, so there is a short interval between the current search and the second search, and the semantic similarity of the keywords is high.

[0030] In this embodiment, the mathematical calculation formula for the searcher's satisfaction with the first search result is constructed as follows: In the formula, Indicates the time when the searcher first searched for keywords; Indicates the time of the searcher's second keyword search; Indicates the semantic similarity between the first keyword search and the second keyword search. ; Indicates that for the first search result The average time it takes to view financial data; Indicates that for all the first search results The total number of citation operations for the search results; Indicates the total number of all information browsed by the searcher in the first search result. ; Indicates the searcher's satisfaction with the first search results.

[0031] In the mathematical calculation formula for the searcher's satisfaction with the first search result constructed above, Indicates that the searcher browses The average time to browse multiple financial data. The shorter the average time, the shorter the searcher browses multiple financial data in a shorter time, which means that the searcher is less satisfied with the first search result. Indicates that the searcher in the first search result has of the search results The proportion of reference operations in financial data; in order to avoid the denominator being 0, The denominator in is ,get , which is positively correlated with the searcher's satisfaction with the first search results; It indicates the time interval between the first keyword search and the second keyword search of the searcher. If the time interval is longer, it means that the search results are accurate and there is no need to conduct a second search. Positively correlated with the searcher's satisfaction with the first search results; the semantic similarity of the keywords in the first keyword search and the second keyword search , if there is a certain gap between the semantics of the keywords in the two searches, that is, The larger the value is, the less satisfied the searcher is with the first search result. It is negatively correlated with the searcher’s satisfaction with the first search result. As a benchmark value for the searcher's satisfaction with the first search results, The weight used as the searcher's satisfaction with the first search results.

[0032] Therefore, the time interval between the searcher's first keyword search and the second keyword search, the average time the searcher spends viewing the financial data in the first search results, and the total number of reference operations on the financial data in the first search results are all positively correlated with the searcher's satisfaction with the first search results; the semantic similarity of the keywords in the first keyword search and the second keyword search, and the total number of financial data browsed by the searcher in the first search results are all negatively correlated with the searcher's satisfaction with the first search results.

[0033] It should be noted that the semantic similarity between the keywords in the first keyword search and the second keyword search can be obtained by using an existing semantic analysis algorithm, for example, NLP (Natural Language Processing).

[0034] After obtaining the searcher's satisfaction with the first search result, it is necessary to determine the possibility that the first search result belongs to the second type of search result. In this embodiment, the mathematical calculation formula for the possibility that the first search result belongs to the second type of search result is constructed as follows: In the formula, Indicates the searcher's satisfaction with the first search results; represents a natural constant; Indicates the possibility that the first search result belongs to the second category of search results.

[0035] In the above-constructed mathematical calculation formula for the possibility that the first search result belongs to the second category of search results, the higher the searcher's satisfaction with the first search result, the lower the possibility of conducting a second search; the lower the searcher's satisfaction with the first search result, the higher the possibility of conducting a second search.

[0036] Preset likelihood threshold , according to the empirical value, take ,when When , it is considered that the first search result belongs to the first category of search results. Under the search purpose of this searcher, the searcher has obtained the accurate results needed by the searcher through the first search, and this search ends; when , then it is considered that the first search result belongs to the second category of search results, and a second or even multiple searches are needed to achieve the actual search expectations of the searcher.

[0037] In addition to determining that the searcher needs to conduct a second search, for the searcher's first search result and each subsequent search result, it is necessary to determine the searcher's desired search community by utilizing the searcher's search behavior, and then obtain the validity and validity increment of the financial data for different financial data in the desired search community through non-initial search behavior.

[0038] In this embodiment, a network graph is constructed based on the financial data extracted from the searcher's search keywords, and each financial data is used as a node, which is beneficial to the graph algorithm and the connectivity and density between nodes, and the relevant communities are divided as the searcher's expected search communities for this search.

[0039] Specifically, taking the first search as an example, first, the keywords entered by the searcher during the first search are semantically analyzed using natural language processing (NLP) technology; then, financial data containing the keywords are extracted from the financial database, and a network graph is constructed based on these financial data. Each financial data is taken as a node, and the semantic similarity between each financial data and the keyword is taken as the node distance. The graph algorithm is used to automatically divide the relevant communities based on the connectivity and density between the nodes; finally, the automatically divided community is used as the expected search community for the searcher's first search.

[0040] After determining that the searcher needs to conduct a second search and the desired search community of the first search is obtained through the searcher's first search, it is necessary to further obtain the information validity of different financial data in the desired search community, and dynamically learn and adjust the information validity of different financial data in the desired search community based on multiple fuzzy search behaviors. Therefore, this embodiment further sets the following steps.

[0041] Step S2: Acquire the validity of the financial data according to the browsing behavior of the financial data in each search behavior under a search purpose by the searcher.

[0042] Among them, in step S2, according to the browsing behavior of a financial data in each search behavior under a search purpose of the searcher, obtaining the validity of the financial data specifically includes: a search behavior under a search purpose of the searcher forms a search expectation community for the search, the searcher browses the financial data in the search expectation community, when a financial data is browsed, the validity of the financial data is obtained according to the browsing time of the financial data and the average time of other financial data browsed by the searcher, and when a financial data has not been browsed, the validity of the financial data is obtained according to the inverse of the total number of all the financial data that have not been browsed.

[0043] More specifically, first, when the first search behavior occurs, according to the normal financial data retrieval process, there will be financial data results of the expected search community related to the keywords in the first search behavior displayed. However, not all financial data in the expected community are what the searcher expects, so it is necessary to obtain the information validity of the financial data in each expected community. The specific acquisition logic is: through the searcher's explicit and implicit behaviors, the information validity of each financial data is obtained.

[0044] The explicit behaviors of the searcher are divided into two categories: explicit affirmation and explicit rejection. Explicit affirmation means that the searcher obtains accurate information, which is not applicable to the second type of search results. Therefore, this embodiment mainly analyzes explicit rejection behaviors. Explicit rejection behaviors refer to that the searcher only has simple browsing behaviors for certain financial data in the expected community (the shorter the browsing time, the lower the validity of the financial data), and has no other reference operations. Then, these financial data are non-valid information for the searcher, so the validity of the information is low. In the case of non-explicit behaviors, after the search behavior occurs, there are searchers who have no behavior on certain financial data in the expected community, that is, no browsing or reference, that is, the searcher has no corresponding information acquisition for these financial data, and is in a vague cognitive state for these information. Compared with the explicitly rejected financial data, these financial data have higher validity.

[0045] In this embodiment, the mathematical calculation formula for constructing the validity of the searcher for each financial data in the desired community is as follows: In the formula, Indicates the searcher's expectation for the first The browsing time of financial data; Represents the searcher's expectation for all Average browsing time of financial data; Indicates that the searcher has The total number of financial data that have not been browsed among the financial data. Since searchers generally have financial data that have not been browsed, we define ; Indicates the searcher's expectation for the first The validity of financial data.

[0046] In the above constructed mathematical formula for calculating the effectiveness of the searcher for each financial data in the desired community, Indicates that when the nth financial data is browsed by the searcher, the searcher's first The browsing time of financial data is related to the searcher's browsing time of all The ratio of the average browsing time of the financial data is taken as the The validity of financial data, where The role of is to prevent the denominator from being 0; Indicates that when the nth financial data has not been browsed by the searcher, all the unbrowsed financial data will be equalized (the searcher will have equal rights for all The reciprocal of the total number of financial data that have not been browsed among the financial data) is taken as the validity of the nth financial data.

[0047] It should be noted that the above-mentioned behavior of the nth financial data being browsed by the searcher and not being browsed is a relative behavior, so and There is always one item that is 0. The searcher is looking for the first The validity of financial data Just take the one that is not 0.

[0048] Based on the above method, the validity of each financial data in the searcher's desired community can be obtained according to the searcher's browsing behavior of each financial data in each search behavior under a search purpose. In addition to analyzing the validity of each financial data in the searcher's desired community, the associated features under the searcher's multiple search behaviors should be further considered to determine the final search result display. Therefore, this embodiment further sets the following steps.

[0049] Step S3: Obtain the validity increment of the financial data according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple search behaviors under the same search purpose of the searcher.

[0050] Since the current search behavior is a search behavior that supplements the first search behavior, and a corresponding search expectation community is generated after each keyword search, and the current search behavior is a supplement to the first search behavior, the same financial data will exist in different search expectation communities. In addition, each time the search results are displayed, the searcher's data behavior in different search expectation communities determines the validity of the information in the current community. Specifically, in a search behavior, the searcher simply consults a certain financial data in the search expectation community and does not refer to the financial data. Even if the financial data is displayed in multiple search results, it does not have high information validity for the searcher. However, if there are financial data that the searcher does not consult each time the search results are displayed, the more times these financial data appear in the search expectation community of multiple search results, and the stronger the correlation with the search keywords, the greater the possibility that these financial data are the search results expected by the searcher.

[0051] In this embodiment, the mathematical calculation formula for constructing the validity increment of financial data obtained in multiple search behaviors under a search purpose is as follows: In the formula, Indicates Financial data in all Total number of occurrences in searches, where ; Indicates Financial data in all Results in search results The total number of times the searcher browsed the search results; Indicates the appearance of All financial data The similarity of the keywords in the search. Indicates The first search process The effectiveness increment corresponding to each financial data.

[0052] In the above-constructed mathematical formula for calculating the incremental effectiveness of financial data obtained in multiple search behaviors under a search purpose, since the current search behavior is a search behavior that supplements the first search behavior, the first search behavior is The first search process Each financial data must be obtained in multiple retrieval behaviors under a retrieval purpose. Financial data in all Results in search results The total number of times it was browsed by the searcher With The first search process The increment of effectiveness corresponding to each financial data is negatively correlated. If the number of times the searcher browses is small, then the The greater the increment of information validity of financial data, the greater the denominator in the above formula. is to avoid the denominator being 0; Financial data in all Total number of occurrences in searches With The first search process The effectiveness increment corresponding to the financial data is positively correlated. Financial data in all The more times it appears in the search, the more The greater the increment of information validity of financial data, the greater the increment of information validity of financial data. Financial data in all Total number of occurrences in all searches Percentage of searches , and also with The first search process The corresponding effectiveness increment of each financial data is positively correlated. The higher the proportion, the The effectiveness increment corresponding to the financial data; further, the All financial data Similarity of the searched keywords Also with the The first search process The effectiveness increment corresponding to each financial data is positively correlated. All financial data The higher the similarity of the keywords in the next search, the The greater the increment in the information validity of the financial data.

[0053] Therefore, the number of times a financial data appears in multiple search results in multiple search behaviors for the same search purpose and the similarity of the search keywords each time they appear are positively correlated with the increase in the effectiveness of the financial data, and the number of times a financial data is browsed in multiple search behaviors for the same search purpose is negatively correlated with the increase in the effectiveness of the financial data.

[0054] Step S4: Obtain the final expected value of the financial data according to the validity and validity increment of the financial data.

[0055] Specifically, by utilizing the validity of the financial data in the desired community and the incremental validity of the financial data after multiple retrieval actions, the final expected value of the searcher for the financial data is further obtained.

[0056] In this embodiment, the mathematical calculation formula for constructing the final expected value of financial data is as follows: In the formula, Indicates the searcher's expectation for the first the validity of financial data; Indicates The first search process The effectiveness increment corresponding to each financial data; Indicates The final expected value of a financial data.

[0057] In the mathematical calculation formula for the final expected value of the financial data constructed above, the searcher calculates the expected value of the first The validity of financial data , No. The first search process The effectiveness increment corresponding to each financial data Both The final expected value of financial data Positive correlation, the greater the validity of the financial data, the greater the increment of the validity of the financial data, and the greater the final expected value of the financial data.

[0058] Step S5: Display the search results to the searcher based on the financial data obtained from the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

[0059] Among them, step S5 specifically includes: screening the final expected values ​​corresponding to all financial data in the search expectation community obtained by the searcher in the last search, and screening out financial data that is less than the preset expected value threshold; sorting the remaining financial data in descending order from large to small according to the final expected values ​​corresponding to these financial data, and the remaining financial data after sorting is the display order of the relevant financial data corresponding to this search; and displaying the search results in sequence according to the display order of the relevant financial data corresponding to this search.

[0060] More specifically, first, all the information in the retrieval expected community is screened according to the final expected value corresponding to each information, and the information with a final expected value that is too low is removed. The specific screening method is the threshold judgment method. For the final expected value in the retrieval expected community that is less than or equal to the preset expected value threshold, Financial data is considered irrelevant to this search and will not be displayed. The financial data is considered as the relevant data for this search, and the subsequent results are displayed; then, all the relevant data corresponding to this search are sorted in descending order according to the final expected value, and the sequence number of the sorted expected value is the display order of the relevant data corresponding to this search. Finally, the search results are displayed in sequence according to the display order of the relevant data corresponding to this search.

[0061] In the second aspect, this embodiment provides a financial data processing system, see Figure 2 , which shows a block diagram of a financial data processing system provided by an embodiment of the present invention, the system comprising: The financial database acquisition module 101 is used to collect financial data, create indexes, and construct a financial database; The validity acquisition module 102 is used to acquire the validity of the financial data according to the browsing behavior of the financial data in each search behavior under a search purpose by the searcher; The validity increment acquisition module 103 is used to acquire the validity increment of the financial data according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple search behaviors under a search purpose of the searcher; A final expected value acquisition module 104, used to acquire the final expected value of the financial data according to the validity and validity increment of the financial data; The display result acquisition module 105 is used to display the search results to the searcher based on the financial data obtained by the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

[0062] Furthermore, in the validity acquisition module 102 of the system, based on the browsing behavior of a financial data in each search behavior under a search purpose, the validity of the financial data is obtained, specifically including: a search behavior under a search purpose of the searcher forms a search expectation community for the search, the searcher browses the financial data in the search expectation community, when a financial data is browsed, the validity of the financial data is obtained based on the browsing time of the financial data and the average time of other financial data browsed by the searcher, and when a financial data has not been browsed, the validity of the financial data is obtained based on the inverse of the total number of all the financial data that have not been browsed.

[0063] The present embodiment provides an efficient financial data retrieval method and a financial data processing system. First, financial data is collected, indexes are established, and a financial database is constructed. Then, the validity of the financial data is obtained based on the browsing behavior of the financial data in each retrieval behavior under a retrieval purpose of the searcher. The validity increment of the financial data is obtained based on the number of times a financial data appears in multiple retrieval results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple retrieval behaviors under a retrieval purpose of the searcher. The final expected value of the financial data is obtained based on the validity and validity increment of the financial data. Finally, the search results are displayed to the searcher based on the financial data obtained by the last retrieval behavior under a retrieval purpose of the searcher and the final expected value corresponding to each financial data. The present embodiment can provide the searcher with more accurate financial data that meets the searcher's expectations.

[0064] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0065] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An efficient financial data retrieval method, characterized in that: The method comprises: Step S1: Collect financial data, create indexes, and build a financial database; Step S2: obtaining the validity of the financial data according to the browsing behavior of the financial data in each search behavior under a search purpose by the searcher; Step S3: according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keyword each time it appears in multiple search behaviors under one search purpose of the searcher, the validity increment of the financial data is obtained; wherein, the method for obtaining the validity increment is as follows: the number of times a financial data appears in multiple search results and the similarity of the search keyword each time it appears in multiple search behaviors under one search purpose of the searcher are positively correlated with the validity increment of the financial data, and the number of times a financial data is browsed in multiple search behaviors under one search purpose of the searcher is negatively correlated with the validity increment of the financial data; Step S4: obtaining a final expected value of the financial data according to the validity and validity increment of the financial data; Step S5: Display the search results to the searcher based on the financial data obtained from the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

2. The method for efficient retrieval of financial data according to claim 1, characterized in that: The step S1 specifically includes: Collect financial data, clear or correct incomplete or inaccurate financial data, and standardize financial data; Create an index for each piece of financial data, and build a financial database based on the indexed financial data.

3. The method for efficient retrieval of financial data according to claim 1, characterized in that: After step S1 and before step S2, the method further includes: According to the searcher's operation behavior on the first keyword search result, obtain the searcher's satisfaction with the first search result; According to the searcher's satisfaction with the first search result, the possibility of the searcher conducting a second search is obtained; If the possibility that the searcher conducts a second search is greater than or equal to the preset possibility threshold, then continue with step S2-step S5; if the possibility that the searcher conducts a second search is less than the preset possibility threshold, then there is no need to continue with step S2-step S5.

4. The method for efficient retrieval of financial data according to claim 3, characterized in that: The method of obtaining the searcher's satisfaction with the first search result based on the searcher's operational behavior on the first keyword search result is specifically as follows: obtaining the searcher's satisfaction with the first search result based on the time interval between the searcher's first keyword search and the second keyword search, the semantic similarity of the keywords in the first keyword search and the second keyword search, the average time the searcher spends viewing the financial data in the first search result, the total number of reference operations on the financial data in the first search result, and the total number of financial data in the first search result that the searcher browsed.

5. The method for efficient retrieval of financial data according to claim 4, characterized in that: The time interval between the searcher's first keyword search and the second keyword search, the average time the searcher spends viewing the financial data in the first search results, and the total number of reference operations on the financial data in the first search results are all positively correlated with the searcher's satisfaction with the first search results; the semantic similarity of the keywords in the first keyword search and the second keyword search, and the total number of financial data browsed by the searcher in the first search results are all negatively correlated with the searcher's satisfaction with the first search results.

6. The method for efficient retrieval of financial data according to claim 1, characterized in that: After step S1 and before step S2, it also includes: constructing a network graph based on the financial data extracted from the searcher's search keywords, taking each financial data as a node, facilitating the graph algorithm and the connectivity and density between nodes, and dividing relevant communities as the searcher's expected search communities for this search.

7. The method for efficient retrieval of financial data according to claim 6, characterized in that: In step S2, based on the browsing behavior of a financial data in each search behavior under a search purpose by the searcher, the validity of the financial data is obtained, specifically including: a search behavior under a search purpose by the searcher forms a search expectation community for the search, the searcher browses the financial data under the search expectation community, when a financial data is browsed, the validity of the financial data is obtained based on the browsing time of the financial data and the average time of other financial data browsed by the searcher, and when a financial data is not browsed, the validity of the financial data is obtained based on the inverse of the total number of all the financial data that have not been browsed.

8. The method for efficient retrieval of financial data according to claim 6, characterized in that: In step S5, based on the financial data obtained by the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data, the search result display to the searcher specifically includes: The final expected values ​​corresponding to all the financial data in the search expectation community obtained by the searcher in the last search are screened, and the financial data with a value less than a preset expected value threshold is screened out; The remaining financial data are sorted in descending order according to the final expected values ​​corresponding to the financial data, and the sorted remaining financial data are the display order of the relevant financial data corresponding to this search; The search results are displayed in sequence according to the display order of the relevant financial data corresponding to this search.

9. A financial data processing system, characterized in that: The system comprises: Financial database acquisition module, used to collect financial data, create indexes, and build a financial database; The validity acquisition module is used to acquire the validity of the financial data according to the browsing behavior of the financial data in each search behavior under a search purpose by the searcher; The validity increment acquisition module is used to acquire the validity increment of the financial data according to the number of times a financial data appears in multiple search results, the number of times it is browsed, and the similarity of the search keywords each time it appears in multiple search behaviors under one search purpose of the searcher; wherein, the method for acquiring the validity increment is as follows: the number of times a financial data appears in multiple search results and the similarity of the search keywords each time it appears in multiple search behaviors under one search purpose of the searcher are positively correlated with the validity increment of the financial data, and the number of times a financial data is browsed in multiple search behaviors under one search purpose of the searcher is negatively correlated with the validity increment of the financial data; A final expected value acquisition module, used to acquire the final expected value of the financial data according to the validity and validity increment of the financial data; The display result acquisition module is used to display the search results to the searcher based on the financial data obtained from the last search behavior under a search purpose of the searcher and the final expected value corresponding to each financial data.

Images