Intelligent data query method and device, equipment, medium and product

Abstract

The invention discloses an intelligent data query method and device, equipment, a medium and a product, and relates to the technical field of data processing.The method comprises the steps that an original query request language and a target industry are determined from data query requirement information input by a user; acquiring a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on original data of the target industry; determining target data dimension information matched with the original query request language from the data model library; retrieving the original query request language by using the target data dimension information to obtain keyword information; determining a target data model matched with the keyword information from the data model library; and obtaining the data query result from the original data by using the target data model. The data query method and device can improve the comprehensiveness of the queried data.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data intelligent query method, device, equipment, medium and product. Background Art

[0002] In today's era of rapid development of information technology, data has become the core resource driving the development of all industries. As enterprises, organizations and research institutions continue to generate and accumulate massive amounts of data during their operations, how to accurately find the required data from the massive amount of data has become an urgent problem to be solved.

[0003] Traditional data query methods usually retrieve data from a database that is consistent with the keywords entered by the user. However, in practice, it is found that this data query method can only query data that is consistent with the keywords entered by the user, the data obtained by the query is relatively small, and other data related to the keywords entered by the user cannot be queried. It can be seen that the data obtained by the traditional data query method is not comprehensive enough. Summary of the invention

[0004] The purpose of this application is to provide a data intelligent query method, device, equipment, medium and product, which can improve the comprehensiveness of the data obtained by the query.

[0005] To achieve the above objectives, this application provides the following solutions: In a first aspect, the present application provides a data intelligent query method, comprising: Determine the original query request language and the target industry from the data query requirement information input by the user; Acquire a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on the original data of the target industry; Determine target data dimension information matching the original query request language from the data model library; Using the target data dimension information to search the original query request language to obtain keyword information; Determine a target data model matching the keyword information from the data model library; The target data model is used to obtain data query results from the original data.

[0006] Optionally, determining target data dimension information matching the original query request language from the data model library specifically includes: Acquire multiple initial data dimension information from the data model library; Determine the dimension vector of each initial data dimension information; Determining a language vector of the original query request language; Using the language vector and each dimension vector, calculate the first cosine similarity between the original query request language and each initial data dimension information; The initial data dimension information whose first cosine similarity is greater than a first preset similarity threshold is determined as the target data dimension information.

[0007] Optionally, the using the target data dimension information to search the original query request language to obtain keyword information specifically includes: Splitting the original query request language into a plurality of original query request words; Perform part-of-speech tagging on each original query request word to obtain a target part-of-speech for each original query request word; Based on the target part of speech of each original query request vocabulary, the original query request vocabulary is filtered for stop words to obtain a target query request vocabulary; wherein the target query request vocabulary does not include an original query request vocabulary whose target part of speech is a stop word; Acquire a target keyword matching the target data dimension information from the target query request vocabulary; The target keyword is converted into a preset data format to obtain keyword information.

[0008] Optionally, determining a target data model matching the keyword information from the data model library specifically includes: Performing vectorization processing on each data model in the data model library to obtain a data vector for each data model; Performing vectorization processing on the keyword information to obtain a query vector; Using the query vector and each data vector, calculating the second cosine similarity between the keyword information and each data model; The data model whose second cosine similarity is greater than the second preset similarity threshold is determined as the target data model.

[0009] Optionally, the data intelligent query method further includes: Processing the data query result to obtain a data chart corresponding to the data query result; Rendering the data chart to obtain visualized data; The data query results, the data charts and the visualized data are used to perform data analysis to obtain analysis results for the target industry.

[0010] Optionally, the data model library corresponding to the target industry is established in the following manner: Obtaining original data of the target industry; wherein the original data at least includes user data, industry organization data, and industry-related comparative data; Using the original data to construct multiple data models; wherein the data models include data dimension information of the original data and a path from the data dimension information to the original data; Multiple data models are combined to obtain a data model library.

[0011] In a second aspect, the present application provides a data intelligent query device, comprising: A first determining unit, used to determine the original query request language and the target industry from the data query requirement information input by the user; A first acquisition unit is used to acquire a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on the original data of the target industry; A second determining unit, configured to determine target data dimension information matching the original query request language from the data model library; A retrieval unit, configured to use the target data dimension information to search the original query request language to obtain keyword information; A third determining unit, configured to determine a target data model matching the keyword information from the data model library; The second acquisition unit is used to acquire a data query result from the original data using the target data model.

[0012] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of any one of the above-mentioned intelligent data query methods.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the above-mentioned intelligent data query methods.

[0014] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned data intelligent query methods.

[0015] In a sixth aspect, the present application provides a chip, comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run a program or instructions. When the processor executes the program or instructions, the steps of any one of the above-mentioned data intelligent query methods are implemented.

[0016] According to the specific embodiments provided in this application, this application discloses the following technical effects: The present application provides a data intelligent query method, device, equipment, medium and product. Through a pre-built industry-related data model library, the original data of the data query can be expanded; in addition, the data model library can be matched with the original query request language to determine the target data dimension information that matches the original query request language, and then the original query request language can be retrieved through the obtained target data dimension information to obtain keyword information that better matches the data model library. By using the keyword information, a more accurate and comprehensive target data model can be determined from the database model; the data query results can be obtained from the original data through the target data model, thereby improving the comprehensiveness of the data obtained by the query. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 This is a flow chart of a data intelligent query method in one embodiment of the present application; Figure 2 A schematic diagram of the functional modules of a data intelligent query device provided in one embodiment of the present application.

[0019] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.

[0022] In an exemplary embodiment, Figure 1As shown, a data intelligent query method is provided, which is executed by a computer device, specifically, it can be executed by a computer device such as a terminal or a server alone, or it can be executed by a terminal and a server together. In the embodiment of the present application, the following steps 101 to 106 are included. Among them: Step 101: determine the original query request language and target industry from the data query requirement information input by the user.

[0023] In an embodiment of the present application, an AI robot may initiate an intelligent chat dialog box, in which the user may input the data requirements (i.e., data query requirement information) that he or she wants to query. The input method may be text or voice, and the questions may be more life-related or industry-specific.

[0024] When the data query request information input by the user is in the text format, the typos in the data query request information in the text format can be corrected, that is, the typos in the data query request information in the text format can be corrected to the correct words; and then the modified data query request information in the text format can be determined as the original query request language; When the data query request information input by the user is in voice format, the data query request information in voice format can be converted into data query request information in text format through voice recognition technology, and then the data query request information in text format can be determined as the original query request language.

[0025] In an embodiment of the present application, the data query requirement information input by the user may include industry information of the data that the user needs to obtain. Therefore, semantic analysis can be performed on the data query requirement information input by the user to determine the target industry of the data that the user wants to query from the data query requirement information.

[0026] Step 102: Acquire a pre-established data model library corresponding to the target industry.

[0027] In an embodiment of the present application, the data model library is constructed based on the original data of the target industry.

[0028] As an optional implementation, the method of establishing the data model library corresponding to the target industry includes: Obtaining original data of the target industry; wherein the original data at least includes user data, industry organization data, and industry-related comparative data; Using the original data to construct multiple data models; wherein the data models include data dimension information of the original data and a path from the data dimension information to the original data; Multiple data models are combined to obtain a data model library.

[0029] Among them, the implementation of this implementation method ensures that the basic data of the data model library is rich and comprehensive by comprehensively acquiring the original data of the target industry, including user data, industry organization data, and industry-related comparative data, providing solid data support for subsequent data analysis and decision-making.

[0030] Secondly, multiple data models are built using these raw data. Each data model contains the data dimension information of the raw data and the path pointing to the raw data. This design not only enables the data model to flexibly reflect different aspects and dimensions of the data, but also ensures a close connection between the data model and the raw data, facilitating subsequent data retrieval and analysis.

[0031] Finally, multiple data models are combined to form a data model library, which realizes centralized management and efficient use of data. As a whole, the data model library can better support complex data query and analysis tasks and improve the efficiency and accuracy of data processing. At the same time, the establishment of the data model library also provides powerful tools and methods for industry research, market forecasting, etc., which helps enterprises grasp market trends and make scientific strategic decisions.

[0032] For example, take the data of the financial banking industry as an example: User data may be user transaction data: including transaction amount, number of transactions, transaction type, etc.; Industry institution data can be summarized for institutions: including total transaction volume, total deposits, total loans, number of merchants, assessment indicators, etc. Industry-related comparative data: year-on-year, month-on-month, net increase, interest rate, interest payment rate, etc.; There can be multiple data models built.

[0033] For example, the deposit-loan spread model is a model built based on the difference between deposit interest rates and loan interest rates.

[0034] The data model mainly contains special indicator information. Taking the financial banking industry as an example, it includes information on all banking institutions in the province, mapping relationship information of data display indicators, transaction data, etc.

[0035] Taking institutional information as an example, it includes institutional ID, institutional name, institutional hierarchical relationships, institutional location, institutional level, etc.

[0036] Step 103: Determine target data dimension information matching the original query request language from the data model library.

[0037] As an optional implementation manner, the method of determining the target data dimension information matching the original query request language from the data model library in step 103 may include: Acquire multiple initial data dimension information from the data model library; Determine the dimension vector of each initial data dimension information; Determining a language vector of the original query request language; Using the language vector and each dimension vector, calculate the first cosine similarity between the original query request language and each initial data dimension information; The initial data dimension information whose first cosine similarity is greater than a first preset similarity threshold is determined as the target data dimension information.

[0038] Among them, the implementation of this implementation method can efficiently and accurately determine the target data dimension information that matches the original query request language from the data model library. By obtaining multiple initial data dimension information and determining the dimension vector for it, and determining the language vector of the original query request language at the same time, the similarity between the original query request and each initial data dimension information can be quantified by calculating the first cosine similarity between the vectors. Setting the first preset similarity threshold as a screening condition can automatically filter out those initial data dimension information that do not match the original query request language or have low similarity, thereby accurately locking the target data dimension information. This method not only improves the accuracy and efficiency of data dimension matching, but also reduces manual intervention, making the data processing process more intelligent and automated.

[0039] In an embodiment of the present application, the initial data dimension information may represent the attributes of the corresponding original data in the data model library.

[0040] In the embodiment of the present application, the closer the first cosine similarity is to 1, the more similar the language vector is to the dimension vector; the closer the first cosine similarity is to -1, the greater the difference between the language vector and the dimension vector. Therefore, a first preset similarity threshold can be predetermined. If the first cosine similarity is greater than the first preset similarity threshold, it can be considered that the original query request language corresponding to the first cosine similarity is relatively similar to the initial data dimension information.

[0041] Step 104: Use the target data dimension information to search the original query request language to obtain keyword information.

[0042] As an optional implementation, step 104 uses the target data dimension information to search the original query request language, and the method of obtaining keyword information may include: Splitting the original query request language into a plurality of original query request words; Perform part-of-speech tagging on each original query request word to obtain a target part-of-speech for each original query request word; Filter out stop words from the original query request vocabulary based on the target part of speech of each original query request vocabulary, and obtain the target query request vocabulary; wherein, the target query request vocabulary does not include the original query request vocabulary whose target part of speech is a stop word. Obtain target keywords that match the target data dimension information from the target query request vocabulary. Convert the target keywords into a preset data format to obtain keyword information.

[0043] Among them, by implementing this implementation method, by subdividing the original query request language into multiple words and performing part-of-speech tagging on them, the system can more accurately understand the function and importance of each word in the query. Subsequently, through the stop word filtering step, words that do not contribute substantially to the retrieval results, such as prepositions and conjunctions, are effectively removed, thereby reducing noise and making the retrieval process more focused and efficient. In addition, based on the matching of the target data dimension information, the system can intelligently screen out keywords that are highly relevant to the target query, and these keywords are directly related to the core intention of the user's query. Finally, converting the target keywords into a preset data format not only facilitates subsequent data processing and analysis, but also ensures the standardization and consistency of the keyword information. The combined effect of these steps makes the entire retrieval process more intelligent and accurate, greatly improving the efficiency and accuracy of information retrieval.

[0044] In the embodiments of the present application, stop words are a class of words defined in advance to reduce the indexing volume, improve the search efficiency, or remove words that contribute little to the text meaning. These words are usually the most common words in the language but contribute the least to the text meaning, such as Chinese words like "的", "了", "在", "是", etc., and English words like "the", "is", "at", "of", etc.

[0045] For example, the obtained keyword information can be a date, a location, a data type, a data range, etc.

[0046] Step 105, determine a target data model that matches the keyword information from the data model library.

[0047] As an optional implementation method, the method for step 105 to determine a target data model that matches the keyword information from the data model library may include: Perform vectorization processing on each data model in the data model library to obtain data vectors of each data model; Perform vectorization processing on the keyword information to obtain a query vector; Use the query vector and each data vector to calculate the second cosine similarity between the keyword information and each data model; The data model whose second cosine similarity is greater than the second preset similarity threshold is determined as the target data model.

[0048] Among them, by implementing this implementation method, by vectorizing each data model and keyword information in the data model library, the system can convert complex data structures and query requirements into computable numerical vectors, which makes subsequent similarity calculations possible. Using the second cosine similarity as a metric, the system can quantify the similarity between keyword information and each data model, so as to accurately capture the data model that best matches the query requirements. By setting a second preset similarity threshold, the system can automatically screen out data models that are highly relevant to keyword information, exclude those data models that do not meet the query requirements or have low relevance, and further improve the accuracy and efficiency of matching. This vectorized data model matching method not only simplifies the matching process, but also significantly improves the level of intelligence in data processing, providing strong support for complex data query and analysis tasks.

[0049] In an embodiment of the present application, methods such as TF-IDF, word embedding, or sentence embedding can be used to vectorize the data model and keyword information.

[0050] In the embodiment of the present application, the first cosine similarity and the second cosine similarity may be the same or different.

[0051] Step 106: Use the target data model to obtain data query results from the original data.

[0052] In an embodiment of the present application, a uniform resource locator (URL) of the data query result can be generated and output to the user, so that the user can view the data query result anytime and anywhere according to the URL, and can also share the data query result with others conveniently and quickly, thereby improving the efficiency of data sharing.

[0053] As an optional implementation, after step 106, the following steps may also be performed: Processing the data query result to obtain a data chart corresponding to the data query result; Rendering the data chart to obtain visualized data; The data query results, the data charts and the visualized data are used to perform data analysis to obtain analysis results for the target industry.

[0054] Among them, by implementing this implementation method, through further processing of the data query results, the system can generate corresponding data charts, which not only makes the data more intuitive and easy to understand, but also helps to reveal the relationship and trends between the data. Subsequently, the data charts are rendered to obtain visualized data. This process allows the data to be presented in a graphical manner, greatly improving the readability and attractiveness of the data. Finally, by combining the data query results, data charts, and visualized data for comprehensive data analysis, the system can deeply explore the inherent laws and potential value of the target industry and provide strong data support for decision-making. This comprehensive data analysis and visualization display method not only improves the depth and breadth of data analysis, but also makes the analysis results more intuitive and easy to interpret, providing valuable insights for industry research and business development.

[0055] In an embodiment of the present application, the data chart is rendered, and the obtained visualization data may be a bar chart, a line chart, a pie chart, etc.

[0056] For example, for the financial industry, data query results, data charts, and visualized data can be used to analyze market data, transaction data, customer data, etc. The analysis results can help financial institutions conduct risk assessment, investment decisions, customer management, etc. For the medical and health industry, data query results, data charts, and visualized data can be used to analyze patients' medical records, imaging data, genetic data, etc. The analysis results can help doctors diagnose diseases, formulate treatment plans, and manage health, etc. The final analysis results will be displayed after the chart information in the previous step.

[0057] By implementing the above steps 101 to 106, the original data of the data query can be expanded through the pre-built industry-related data model library; in addition, the data model library can be matched with the original query request language to determine the target data dimension information that matches the original query request language, and then in turn, the original query request language is retrieved through the obtained target data dimension information to obtain keyword information that is more matched with the data model library. By using the keyword information, a more accurate and comprehensive target data model can be determined from the database model; the data query results can be obtained from the original data through the target data model, so that the comprehensiveness of the data obtained by the query can be improved. In addition, the present application can also better support complex data query and analysis tasks and improve the efficiency and accuracy of data processing. In addition, the present application can also efficiently and accurately determine the target data dimension information that matches the original query request language from the data model library. In addition, the present application can also intelligently screen out keyword information that is highly relevant to the target query. In addition, the present application can also improve the accuracy and efficiency of the target data model matching. In addition, the present application can also deeply explore the inherent laws and potential value of the target industry and provide strong data support for decision-making.

[0058] The present application also provides an application scenario, which applies the above-mentioned data intelligent query method. Specifically: The data intelligent query method provided by this embodiment can be applied in the scenario of querying key data in the industry. By obtaining the request language that the user inputs to be queried, the data that matches the request language that needs to be queried is searched from the pre-built data model library of the relevant industry. The data intelligent query method provided by this embodiment belongs to the link of searching for data that matches the request language that needs to be queried from the pre-built data model library of the relevant industry in the content processing of the video.

[0059] Based on the same inventive concept, the embodiment of the present application also provides a data intelligent query device for implementing the data intelligent query method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more data intelligent query device embodiments provided below can refer to the limitations on the data intelligent query method above, and will not be repeated here.

[0060] In an exemplary embodiment, Figure 2 As shown, a data intelligent query device is provided, comprising: The first determining unit 201 is used to determine the original query request language and the target industry from the data query requirement information input by the user; A first acquisition unit 202 is used to acquire a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on the original data of the target industry; A second determining unit 203 is used to determine target data dimension information matching the original query request language from the data model library; A retrieval unit 204 is used to retrieve the original query request language using the target data dimension information to obtain keyword information; A third determining unit 205 is used to determine a target data model matching the keyword information from the data model library; The second acquisition unit 206 is configured to acquire a data query result from the original data using the target data model.

[0061] As an optional implementation manner, the second determining unit 203 determines the target data dimension information matching the original query request language from the data model library in the following manner: Acquire multiple initial data dimension information from the data model library; Determine the dimension vector of each initial data dimension information; Determining a language vector of the original query request language; Using the language vector and each dimension vector, calculate the first cosine similarity between the original query request language and each initial data dimension information; The initial data dimension information whose first cosine similarity is greater than a first preset similarity threshold is determined as the target data dimension information.

[0062] Among them, the implementation of this implementation method can efficiently and accurately determine the target data dimension information that matches the original query request language from the data model library. By obtaining multiple initial data dimension information and determining the dimension vector for it, and determining the language vector of the original query request language at the same time, the similarity between the original query request and each initial data dimension information can be quantified by calculating the first cosine similarity between the vectors. Setting the first preset similarity threshold as a screening condition can automatically filter out those initial data dimension information that do not match the original query request language or have low similarity, thereby accurately locking the target data dimension information. This method not only improves the accuracy and efficiency of data dimension matching, but also reduces manual intervention, making the data processing process more intelligent and automated.

[0063] As an optional implementation, the retrieval unit 204 uses the target data dimension information to retrieve the original query request language, and the method of obtaining the keyword information may be: Splitting the original query request language into a plurality of original query request words; Perform part-of-speech tagging on each original query request word to obtain a target part-of-speech for each original query request word; Based on the target part of speech of each original query request vocabulary, the original query request vocabulary is filtered for stop words to obtain a target query request vocabulary; wherein the target query request vocabulary does not include an original query request vocabulary whose target part of speech is a stop word; Acquire a target keyword matching the target data dimension information from the target query request vocabulary; The target keyword is converted into a preset data format to obtain keyword information.

[0064] Among them, by implementing this implementation method, by subdividing the original query request language into multiple words and tagging them with parts of speech, the system can more accurately understand the function and importance of each word in the query. Subsequently, through the stop word filtering step, words that do not contribute substantially to the retrieval results, such as prepositions, conjunctions, etc., are effectively removed, thereby reducing noise and making the retrieval process more focused and efficient. In addition, based on the matching of target data dimension information, the system can intelligently screen out keywords that are highly relevant to the target query, and these keywords are directly related to the core intent of the user's query. Finally, the target keywords are converted into a preset data format, which not only facilitates subsequent data processing and analysis, but also ensures the standardization and consistency of keyword information. This series of steps work together to make the entire retrieval process more intelligent and precise, greatly improving the efficiency and accuracy of information retrieval.

[0065] As an optional implementation manner, the third determining unit 205 determines the target data model matching the keyword information from the data model library in the following manner: Performing vectorization processing on each data model in the data model library to obtain a data vector for each data model; Performing vectorization processing on the keyword information to obtain a query vector; Using the query vector and each data vector, calculating the second cosine similarity between the keyword information and each data model; The data model whose second cosine similarity is greater than the second preset similarity threshold is determined as the target data model.

[0066] Among them, by implementing this implementation method, by vectorizing each data model and keyword information in the data model library, the system can convert complex data structures and query requirements into computable numerical vectors, which makes subsequent similarity calculations possible. Using the second cosine similarity as a metric, the system can quantify the similarity between keyword information and each data model, so as to accurately capture the data model that best matches the query requirements. By setting a second preset similarity threshold, the system can automatically screen out data models that are highly relevant to keyword information, exclude those data models that do not meet the query requirements or have low relevance, and further improve the accuracy and efficiency of matching. This vectorized data model matching method not only simplifies the matching process, but also significantly improves the level of intelligence in data processing, providing strong support for complex data query and analysis tasks.

[0067] As an optional implementation manner, the second obtaining unit 206 may also be used for: Processing the data query result to obtain a data chart corresponding to the data query result; Rendering the data chart to obtain visualized data; The data query results, the data charts and the visualized data are used to perform data analysis to obtain analysis results for the target industry.

[0068] Among them, by implementing this implementation method, through further processing of the data query results, the system can generate corresponding data charts, which not only makes the data more intuitive and easy to understand, but also helps to reveal the relationship and trends between the data. Subsequently, the data charts are rendered to obtain visualized data. This process allows the data to be presented in a graphical manner, greatly improving the readability and attractiveness of the data. Finally, by combining the data query results, data charts, and visualized data for comprehensive data analysis, the system can deeply explore the inherent laws and potential value of the target industry and provide strong data support for decision-making. This comprehensive data analysis and visualization display method not only improves the depth and breadth of data analysis, but also makes the analysis results more intuitive and easy to interpret, providing valuable insights for industry research and business development.

[0069] As an optional implementation, the data model library corresponding to the target industry may be established in the following manner: Obtaining original data of the target industry; wherein the original data at least includes user data, industry organization data, and industry-related comparative data; Using the original data to construct multiple data models; wherein the data models include data dimension information of the original data and a path from the data dimension information to the original data; Multiple data models are combined to obtain a data model library.

[0070] Among them, implementing this embodiment, By fully acquiring the original data of the target industry, including user data, industry organization data, and industry-related comparative data, we ensure that the basic data of the data model library is rich and comprehensive, providing solid data support for subsequent data analysis and decision-making.

[0071] Secondly, multiple data models are built using these raw data. Each data model contains the data dimension information of the raw data and the path pointing to the raw data. This design not only enables the data model to flexibly reflect different aspects and dimensions of the data, but also ensures a close connection between the data model and the raw data, facilitating subsequent data retrieval and analysis.

[0072] Finally, multiple data models are combined to form a data model library, which realizes centralized management and efficient use of data. As a whole, the data model library can better support complex data query and analysis tasks and improve the efficiency and accuracy of data processing. At the same time, the establishment of the data model library also provides powerful tools and methods for industry research, market forecasting, etc., which helps enterprises grasp market trends and make scientific strategic decisions.

[0073] By implementing the above implementation mode, the original data of data query can be expanded through the pre-built industry-related data model library; in addition, the data model library can be matched with the original query request language to determine the target data dimension information that matches the original query request language, and then in turn, the original query request language is retrieved through the obtained target data dimension information to obtain keyword information that better matches the data model library. By using the keyword information, a more accurate and comprehensive target data model can be determined from the database model; the data query results can be obtained from the original data through the target data model, thereby improving the comprehensiveness of the data obtained by the query. In addition, the present application can also better support complex data query and analysis tasks and improve the efficiency and accuracy of data processing. In addition, the present application can also efficiently and accurately determine the target data dimension information that matches the original query request language from the data model library. In addition, the present application can also intelligently screen out keyword information that is highly relevant to the target query. In addition, the present application can also improve the accuracy and efficiency of the target data model matching. In addition, the present application can also deeply explore the inherent laws and potential value of the target industry and provide strong data support for decision-making.

[0074] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data intelligent query data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a data intelligent query method is implemented.

[0075] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0076] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0077] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0078] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0079] In an exemplary embodiment, a chip is provided, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the steps in the above-mentioned method embodiments and achieve the same technical effects. To avoid repetition, they are not described here.

[0080] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0081] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0082] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0083] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0084] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A data intelligent query method, characterized in that: The data intelligent query method comprises: Determine the original query request language and the target industry from the data query requirement information input by the user; Acquire a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on the original data of the target industry; Determine target data dimension information matching the original query request language from the data model library; Using the target data dimension information to search the original query request language to obtain keyword information; Determine a target data model matching the keyword information from the data model library; The target data model is used to obtain data query results from the original data.

2. The data intelligent query method according to claim 1, characterized in that: The determining, from the data model library, target data dimension information matching the original query request language specifically includes: Acquire multiple initial data dimension information from the data model library; Determine the dimension vector of each initial data dimension information; Determining a language vector of the original query request language; Using the language vector and each dimension vector, calculate the first cosine similarity between the original query request language and each initial data dimension information; The initial data dimension information whose first cosine similarity is greater than a first preset similarity threshold is determined as the target data dimension information.

3. The data intelligent query method according to claim 1, characterized in that: The using the target data dimension information to search the original query request language to obtain keyword information specifically includes: Splitting the original query request language into a plurality of original query request words; Perform part-of-speech tagging on each original query request word to obtain a target part-of-speech for each original query request word; Based on the target part of speech of each original query request vocabulary, the original query request vocabulary is filtered for stop words to obtain a target query request vocabulary; wherein the target query request vocabulary does not include an original query request vocabulary whose target part of speech is a stop word; Acquire a target keyword matching the target data dimension information from the target query request vocabulary; The target keyword is converted into a preset data format to obtain keyword information.

4. The data intelligent query method according to claim 1, characterized in that: The determining of the target data model matching the keyword information from the data model library specifically includes: Performing vectorization processing on each data model in the data model library to obtain a data vector for each data model; Performing vectorization processing on the keyword information to obtain a query vector; Using the query vector and each data vector, calculating the second cosine similarity between the keyword information and each data model; The data model whose second cosine similarity is greater than the second preset similarity threshold is determined as the target data model.

5. The data intelligent query method according to any one of claims 1 to 4, characterized in that: The data intelligent query method also includes: Processing the data query result to obtain a data chart corresponding to the data query result; Rendering the data chart to obtain visualized data; The data query results, the data charts and the visualized data are used to perform data analysis to obtain analysis results for the target industry.

6. The data intelligent query method according to claim 1, characterized in that: The method of establishing the data model library corresponding to the target industry includes: Obtaining original data of the target industry; wherein the original data at least includes user data, industry organization data, and industry-related comparative data; Using the original data to construct multiple data models; wherein the data models include data dimension information of the original data and a path from the data dimension information to the original data; Multiple data models are combined to obtain a data model library.

7. A data intelligent query device, characterized in that: The data intelligent query device comprises: A first determining unit, used to determine the original query request language and the target industry from the data query requirement information input by the user; A first acquisition unit is used to acquire a pre-established data model library corresponding to the target industry; wherein the data model library is constructed based on the original data of the target industry; A second determining unit, configured to determine target data dimension information matching the original query request language from the data model library; A retrieval unit, configured to use the target data dimension information to search the original query request language to obtain keyword information; A third determining unit, configured to determine a target data model matching the keyword information from the data model library; The second acquisition unit is used to acquire a data query result from the original data using the target data model.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the data intelligent query method described in any one of claims 1 to 6.

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

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

Images