Data processing method, system and related device

Abstract

The invention discloses a data processing method and system and a related device, and the method comprises the steps: obtaining a structured data table, and determining a query index matched with each piece of initial field data in the structured data table; obtaining query request information, and obtaining target field data matched with the query request information from all the initial field data based on the query index; wherein associated information is matched between different target field data; and obtaining an output result by utilizing the query request information, the target field data and the associated information corresponding to the target field data. In this way, the accuracy of data processing can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a data processing method, system and related devices. Background Art

[0002] In recent years, with the rapid development of artificial intelligence technology, large-scale pre-trained models (referred to as "big models") have made significant breakthroughs in natural language processing, image recognition and other fields. Relying on massive data and powerful computing resources, big models can capture complex semantic relationships and generate high-quality content, and can be applied to data processing tasks such as text generation and language translation. However, in actual application, the accuracy of data processing is poor due to the untimely update of the data they rely on.

[0003] In view of this, how to improve the accuracy of data processing has become an urgent problem to be solved. Summary of the invention

[0004] The main technical problem solved by the present application is to provide a data processing method, system and related devices, which can improve the accuracy of data processing.

[0005] In order to solve the above technical problems, a technical solution adopted by the present application is: providing a data processing method, including: obtaining a structured data table, determining a query index matching each initial field data in the structured data table; obtaining query request information, and based on the query index, obtaining target field data matching the query request information from all the initial field data; wherein, different target field data are matched with associated information; and obtaining output results using the query request information, the target field data and the corresponding associated information.

[0006] To solve the above technical problems, another technical solution adopted by the present application is: to provide a data processing system, including: an acquisition module, used to acquire a structured data table and determine a query index matching each initial field data in the structured data table; a retrieval module, used to acquire query request information and, based on the query index, acquire target field data matching the query request information from all the initial field data; wherein different target field data are matched with associated information; a processing module, used to acquire output results using the query request information, the target field data and the corresponding associated information.

[0007] To solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, comprising: a memory and a processor coupled to each other, the memory storing program instructions, and the processor being used to execute the program instructions to implement the data processing method mentioned in the above technical solution.

[0008] In order to solve the above technical problems, another technical solution adopted in the present application is: providing a computer-readable storage medium on which program instructions are stored, and when the program instructions are executed by a processor, the data processing method mentioned in the above technical solution is implemented.

[0009] The beneficial effect of the present application is that, different from the prior art, the data processing method proposed in the present application generates a query index that matches each initial field data in a structured data table, and uses the query index to efficiently retrieve the target field data that matches the query request information, so that the output result with a high degree of fit with the query request information can be obtained based on the target field data. In addition, different target data fields are matched with related information, so that different target field data can be jointly analyzed in the process of generating output results, thereby improving the accuracy of generating output results. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work. Among them:

[0011] Figure 1 It is a flowchart of an implementation method of the data processing method of the present application;

[0012] Figure 2 yes Figure 1 Step S101 corresponds to a flow chart of another implementation method;

[0013] Figure 3 yes Figure 1 Step S102 corresponds to a flow chart of another implementation method;

[0014] Figure 4 yes Figure 3 A schematic diagram of another embodiment of the process before step S302;

[0015] Figure 5 yes Figure 3 Step S302 corresponds to a flow chart of another implementation method;

[0016] Figure 6 yes Figure 1 Step S103 corresponds to a flow chart of another implementation method;

[0017] Figure 7 It is a structural schematic diagram of an implementation method of the data processing system of the present application;

[0018] Figure 8 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0019] Fig. 9 It is a structural schematic diagram of an implementation method of a computer-readable storage medium 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, and different embodiments can be adaptively combined. 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] The data processing method proposed in this application relies on an application on a smart terminal or a smart terminal with at least integrated data processing function, wherein the smart terminal can be a smart office notebook, a mobile phone, a tablet computer, a personal computer or a wearable smart device.

[0022] See also Figure 1 , Figure 1 It is a flow chart of an implementation method of the data processing method of the present application, the method comprising:

[0023] S101: Obtain a structured data table, and determine a query index that matches each initial field data in the structured data table.

[0024] In one embodiment, a structured data table is obtained, wherein the structured data table includes a plurality of initial field data, and a corresponding query index is generated based on table information matched by the structured data table and field information matched by each initial field data.

[0025] S102: Acquire query request information, and based on the query index, acquire target field data matching the query request information from all initial field data; wherein different target field data are matched with associated information.

[0026] In one embodiment, query request information input by a user is obtained, and the data in the structured data table is searched using the query index to obtain target field data matching the query request information.

[0027] In an implementation scenario, the target field data is retrieved by using at least one of the keywords and semantic information corresponding to the query index. Also, different target field data are matched with association information, and the association information is used to associate different target field data, and to associate the structured data table where the corresponding target field data is located with other structured data tables, so that different target field data can be jointly analyzed in the subsequent data processing process.

[0028] In addition, it should be noted that the above-mentioned query request information is text, which can be inquiry information or intention information input by the user; and the query request information input by the user can be obtained through the input method of the smart terminal, or the audio input by the user can be obtained through the smart terminal and converted into query request information in text form.

[0029] S103: Obtain output results using the query request information, target field data and corresponding associated information.

[0030] In one embodiment, the query request information, the target field data and the corresponding associated information are input into the intelligent analysis model, so that the intelligent analysis model combines the input content to generate an output result that matches the query request information.

[0031] Specifically, a preset prompt template is obtained, and a task text is generated using the prompt template to prompt the intelligent analysis model to process the query request information. The task text is input into the intelligent analysis model so that the intelligent analysis model parses the task text and outputs an output result that matches the query request information.

[0032] In one implementation scenario, the intelligent analysis model is a large language model with superior data analysis capabilities. The task text is input into the intelligent analysis model so that the intelligent analysis model combines the target field data in the task text to generate an output result that matches the query request information.

[0033] In a specific application scenario, the above-mentioned large language model may include but is not limited to deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTM), and generative pre-trained Transformer models, etc., and no specific restrictions are made on the specific structure and specific deployment of the large language model. In addition, it should be noted that the specific structure and specific deployment of the intelligent analysis model mentioned in other implementations of this application can refer to this implementation.

[0034] The data processing method proposed in the present application generates a query index that matches each initial field data in a structured data table, and uses the query index to efficiently retrieve the target field data that matches the query request information, so that the output result with a high degree of fit with the query request information can be obtained based on the target field data. In addition, different target data fields are matched with related information, so that different target field data can be jointly analyzed in the process of generating output results, which improves the accuracy of generating output results.

[0035] See also Figure 2 , Figure 2 yes Figure 1 Step S101 in the flowchart corresponds to another embodiment. Specifically, the implementation process of step S101 includes:

[0036] S201: Acquire table information matched by the structured data table and field information matched by each initial field data in the structured data table.

[0037] In one implementation, the structured data table includes a plurality of initial field data, and table information matched by the structured data table and field information matched by each initial field data are acquired.

[0038] In an implementation scenario, the table information matched by the structured data table includes the table name corresponding to the structured data table, and the field information matched by the initial field data includes at least one of the field name, field type, and field constraint conditions corresponding to the initial field data. The field constraint conditions include at least one of the primary key, foreign key, and uniqueness constraint corresponding to the initial field data.

[0039] In another embodiment, in order to improve the intelligent analysis model's ability to understand the corresponding initial field data, the above field information also includes field notes matching the corresponding initial field data, and the field notes are used to describe the corresponding initial field data.

[0040] S202: Based on the structured data table, table information and field information, a query index matching each initial field data is obtained.

[0041] In one implementation, for the initial field data in the structured data table, the initial field data, the table information, and the field information are sequentially concatenated to obtain a query index that matches the initial field data.

[0042] The above scheme obtains a query index by splicing the initial field data, table information and corresponding field information, which provides a basis for the subsequent retrieval of target field data. In addition, by combining different types of information, the amount of information in the query index is increased, which helps to improve the accuracy of the target field data retrieval.

[0043] See also Figure 3 , Figure 3 yes Figure 1 Step S102 in the flowchart corresponds to another embodiment. Specifically, the implementation process of step S102 includes:

[0044] S301: Acquire extraction information corresponding to a query index; wherein the extraction information includes at least one of a keyword corresponding to the query index and a first semantic vector.

[0045] In one implementation, keyword extraction is performed on the query index to extract at least one corresponding first keyword.

[0046] Specifically, the query index is segmented, and the first keyword corresponding to the query index is determined through part-of-speech analysis. For example, after the query index is segmented, nouns, numerals, verbs, etc. therein are used as the first keyword.

[0047] And, semantic feature extraction is performed on the query index to obtain a corresponding first semantic vector.

[0048] Specifically, by obtaining a trained semantic model and inputting the query index into the semantic model, a corresponding first semantic vector is obtained. The specific model structure of the above semantic model can refer to the BERT (Bidirectional Encoder Representations from Transformers) model, and the process of extracting semantic features using the semantic model can refer to the existing semantic extraction process, which will not be elaborated in detail here.

[0049] S302: Acquire target field data based on the extraction information and the query request information.

[0050] In one implementation, when the extracted information includes a keyword corresponding to the query index, a plurality of first candidate field data are obtained from all the initial field data based on the keyword.

[0051] Specifically, at least one second keyword corresponding to the query request information is obtained. For each query index corresponding to the initial field data, the corresponding first keyword is matched with the second keyword, and the initial field data corresponding to the query index that meets the preset matching condition is used as the first candidate field data. Among them, the above-mentioned second keyword is obtained by performing keyword extraction on the query request information. The specific extraction process can refer to the above-mentioned corresponding implementation method and will not be elaborated in detail here. In addition, the same first keyword and second keyword are used as matching keywords, and the above-mentioned preset matching condition can be determined based on the number of matching keywords; for example, for any initial field data, when the number of corresponding matching keywords is greater than the quantity threshold, the initial field data is used as the first candidate field data.

[0052] And, when the extracted information includes a first semantic vector corresponding to the query index, a second semantic vector corresponding to the query request information is obtained, and the semantic similarity between the second semantic vector and each first semantic vector is determined. Based on the semantic similarity, multiple second candidate field data are obtained from all the initial field data.

[0053] Specifically, the semantic similarities between the second semantic vector and each first semantic vector are obtained, and the obtained semantic similarities are sorted in descending order to obtain a reference sequence. The initial field data corresponding to the first number of semantic similarities in the reference sequence is used as the second candidate field data.

[0054] It should be noted that, in order to improve processing efficiency, the above-mentioned process of obtaining the first candidate field data and the process of obtaining the second candidate field data can be executed simultaneously. Alternatively, in order to save processing memory consumption, the process of obtaining the first candidate field data can be executed first, and then the process of obtaining the second candidate field data can be executed; or, the process of obtaining the second candidate field data can be executed first, and then the process of obtaining the first candidate field data can be executed.

[0055] Further, based on the first candidate field data and the second candidate field data, the target field data is acquired.

[0056] Specifically, the acquired first candidate field data and the acquired second candidate field data are both used as target field data.

[0057] In another embodiment, the extraction information corresponding to the query index may also include only keywords or the first semantic vector. When the extraction information includes the first keyword, the first candidate field data is determined according to the first keyword corresponding to each initial field data and the second keyword corresponding to the query request information. The specific implementation process may refer to the above corresponding embodiment. The first candidate field data is used as the target field data.

[0058] Alternatively, when the extracted information includes the first semantic vector, the second candidate field data is determined according to the first semantic vector corresponding to each initial field data and the second semantic vector corresponding to the query request information, and the specific implementation process can refer to the above corresponding implementation method. The second candidate field data is used as the target field data.

[0059] In another embodiment, after the first candidate field data and the second candidate field data are obtained, the first candidate field data and the second candidate field data are displayed on a corresponding display interface, and each first candidate field data and each second candidate field data are respectively set with a corresponding reference weight. In response to obtaining a selection instruction triggered by a user on a portion of the first candidate field data and the second candidate field data in the display interface, the reference weight of the first candidate field data or the second candidate field data corresponding to the selection instruction is updated to increase the corresponding reference weight.

[0060] Furthermore, the first candidate field data and the second candidate field data are sorted according to the reference weights, and at least some of the first candidate field data and the second candidate field data with higher reference weights are selected from all the first candidate field data and the second candidate field data according to the sorting order to serve as the target field data. For example, according to the sorting order of all the first candidate field data and the second candidate field data, the ten candidate field data with the highest reference weights are selected as the target field data.

[0061] In a specific application scenario, the user can circle the first candidate field or the second candidate field in the display interface to trigger the selection instruction. Alternatively, in response to obtaining that the user clicks the first candidate field or the second candidate field in the display interface, a focus button is displayed at the corresponding position. In response to obtaining that the user clicks the above-mentioned focus button, the selection instruction for the corresponding first candidate field or the second candidate field is triggered.

[0062] The above scheme uses at least one retrieval method to determine the target field data related to the query request information from all the initial field data, so as to provide a reference basis for the generation of subsequent output results, thereby improving the accuracy of the output result generation.

[0063] See also Figure 4 , Figure 4 yes Figure 3Schematic diagram of another implementation process before step S302. Specifically, before acquiring the target field data based on the first candidate field data and the second candidate field data, it also includes:

[0064] S401: Obtain preset search prompt information; wherein the search prompt information is related to at least one of user portrait information, supplementary information input by the user, and historical query request information.

[0065] In one embodiment, the search prompt information is determined based on at least one of the user's portrait information, the supplementary information input by the user, and the historical query request information.

[0066] In one implementation scenario, the user's portrait information, the supplementary information input by the user, and the historical query request information are obtained, and information related to the query request information currently input by the user is extracted from the portrait information, the supplementary information, and the historical query request information as retrieval prompt information. Among them, the user's portrait information is obtained by summarizing the information input by the user and the user's usage information, the supplementary information is the supplementary text input by the user on the smart terminal to further supplement the query request information, and the historical query request information is the query request information input by the user within the target time period.

[0067] S402: Acquire third candidate field data from all initial field data based on the search prompt information and the query request information.

[0068] In one implementation, the search prompt information and the query request information are combined to obtain third candidate field data related to the query request information from all initial field data.

[0069] In a specific application scenario, based on the user's portrait information, it is determined that the user is a mathematics teacher. Then, when the query request information input by the user is related to the field of education, "mathematics" is used as the search prompt information, and based on the search prompt information, the initial field data related to "mathematics" in the structured data table is used as the third candidate field data.

[0070] The above scheme improves the flexibility of searching for data in a structured data table by using the search prompt information to retrieve the third candidate field data.

[0071] See also Figure 5 , Figure 5 yes Figure 3 Step S302 corresponds to a flowchart of another implementation. Specifically, the process of obtaining target field data includes:

[0072] S501: taking the first candidate field data, the second candidate field data and the third candidate field data as reference field data, and displaying at least part of the reference field data to the user.

[0073] In one embodiment, after the first candidate field data, the second candidate field data and the third candidate field data are acquired through the above-mentioned corresponding embodiments, the first candidate field data, the second candidate field data and the third candidate field data are used as reference field data, and at least part of the reference field data is displayed to the user through the display interface of the smart terminal.

[0074] S502: In response to obtaining a selected instruction triggered by a user, updating a reference weight of reference field data matched by the selected instruction.

[0075] In one embodiment, in response to obtaining a selection instruction triggered by a user on reference field data in the display interface, the reference weight of the reference field data corresponding to the selection instruction is updated to increase the corresponding reference weight. The manner in which the user triggers the selection instruction can refer to the above corresponding embodiment, and will not be elaborated in detail here.

[0076] Furthermore, the reference field data are sorted according to the reference weights, and at least some of the reference field data with higher reference weights are selected from all the reference field data according to the sorting order to serve as the target field data.

[0077] S503: Acquire target field data based on the reference field data and the matched reference weight.

[0078] In one embodiment, the reference field data are sorted according to the reference weights, and at least some of the reference field data with higher reference weights are selected from all the reference field data according to the sorting order to serve as the target field data.

[0079] See also Figure 6 , Figure 6 yes Figure 1 Step S103 in the flowchart corresponds to another embodiment. Specifically, the implementation process of step S103 includes:

[0080] S601: Acquire a pre-built reference knowledge base, and acquire parsing information matching the target field data from the reference knowledge base.

[0081] In one embodiment, a pre-built reference knowledge base is obtained. For the target field data obtained through the above corresponding embodiments, knowledge matching each target field data is retrieved from the reference knowledge base as corresponding parsing information.

[0082] In another embodiment, candidate knowledge bases related to multiple different fields are pre-built, and after the query request information is obtained, a reference knowledge base related to the query request information is selected from the multiple candidate knowledge bases.

[0083] Specifically, the query request information is analyzed using the trained semantic analysis model to determine the relevance between the query request information and various fields, and the candidate knowledge base corresponding to the field with the maximum relevance is used as the reference knowledge base.

[0084] S602: Input the query request information, the parsing information, the target field data and the corresponding associated information into the intelligent analysis model, and use the intelligent analysis model to output an output result that matches the query request information.

[0085] In one embodiment, the query request information, the parsing information, the target field data and their corresponding associated information are input into the intelligent analysis model, so that the intelligent analysis model analyzes the input content and outputs an output result that matches the query request information.

[0086] Specifically, a predetermined prompt template is obtained, and the query request, parsing information, target field data and their corresponding associated information are input into the corresponding positions in the prompt template to obtain the task text. The task text is input into the intelligent analysis model so that the intelligent analysis model analyzes the task text and outputs the corresponding output result.

[0087] The above solution introduces a reference knowledge base to interpret the target field data in combination with the knowledge in the reference knowledge base, thereby improving the understanding ability of the intelligent analysis model, helping to optimize the effect of generating output results, and improving user experience.

[0088] In yet another embodiment, Figure 1 After step S102, the following further includes: detecting the associated information corresponding to all target field data.

[0089] Specifically, to ensure the integrity of the target field data, according to the relationship diagram between different structured data tables, the associated information corresponding to the target field cluster is detected to determine whether all target field data covers all required connection conditions, so that the complete target field data can be determined from the corresponding structured data table according to the connection conditions. If so, it is determined that the preset execution condition is met; otherwise, it is not met.

[0090] Further, in response to the associated information corresponding to all target field data satisfying the preset execution condition, the step of using the query request information, the target field data and the associated information corresponding thereto to obtain the output result is executed, and the specific implementation process can refer to the above corresponding implementation mode. In response to the associated information corresponding to all target field data not satisfying the preset execution condition, an early warning message is generated to indicate that an error occurs in the process of returning the target field data.

[0091] See also Figure 7 , Figure 71 is a schematic diagram of the structure of an embodiment of the data processing system of the present application. Specifically, the data processing system includes an acquisition module 10, a retrieval module 20 and a processing module 30 coupled to each other.

[0092] Specifically, the acquisition module 10 is used to acquire a structured data table and determine a query index that matches each initial field data in the structured data table.

[0093] The retrieval module 20 is used to obtain the query request information, and based on the query index, obtain the target field data matching the query request information from all the initial field data; wherein, there is associated information matching between different target field data.

[0094] The processing module 30 is used to obtain output results using query request information, target field data and corresponding associated information.

[0095] In one embodiment, the acquisition module 10 acquires a structured data table and determines a query index that matches each initial field data in the structured data table, including: acquiring table information that matches the structured data table and field information that matches each initial field data in the structured data table; based on the structured data table, the table information and the field information, acquiring a query index that matches each initial field data.

[0096] In one embodiment, the retrieval module 20 obtains target field data matching the query request information from all initial field data based on the query index, including: obtaining extraction information corresponding to the query index; wherein the extraction information includes at least one of the keywords and the first semantic vector corresponding to the query index; and obtaining the target field data based on the extraction information and the query request information.

[0097] In one embodiment, the extracted information includes keywords and a first semantic vector, and the retrieval module 20 obtains the target field data based on the extracted information and the query request information, including: based on the keywords, obtaining multiple first candidate field data from all the initial field data; and, obtaining the second semantic vector corresponding to the query request information, and determining the semantic similarity between the second semantic vector and each first semantic vector; based on the semantic similarity, obtaining multiple second candidate field data from all the initial field data; based on the first candidate field data and the second candidate field data, obtaining the target field data.

[0098] In one embodiment, based on the first candidate field data and the second candidate field data, before obtaining the target field data, the retrieval module 20 is also used to obtain preset retrieval prompt information; wherein the retrieval prompt information is related to at least one of the user portrait information, the supplementary information input by the user, and the historical query request information; based on the retrieval prompt information and the query request information, the third candidate field data is obtained from all the initial field data.

[0099] In one embodiment, the retrieval module 20 obtains target field data based on the first candidate field data and the second candidate field data, including: using the first candidate field data, the second candidate field data and the third candidate field data as reference field data, and displaying at least part of the reference field data to the user; in response to obtaining a selected instruction triggered by the user, updating the reference weight of the reference field data matched by the selected instruction; and obtaining the target field data based on the reference field data and the matching reference weight.

[0100] In one embodiment, please continue to refer to Figure 7 The data processing system proposed in the present application further includes a verification module 40 coupled to the retrieval module 20. After acquiring the target field data matching the query request information from all the initial field data based on the query index, the verification module 40 is used to detect the associated information corresponding to all the target field data; in response to the associated information corresponding to all the target fields satisfying the preset execution conditions, the step of obtaining the output result by using the query request information, the target field data and the associated information corresponding to the target fields is executed.

[0101] In one embodiment, the processing module 30 uses query request information, target field data and corresponding associated information to obtain output results, including: obtaining a pre-built reference knowledge base, and obtaining parsing information that matches the target field data from the reference knowledge base; inputting the query request information, parsing information, target field data and corresponding associated information into an intelligent analysis model, and using the intelligent analysis model to output output results that match the query request information.

[0102] See also Figure 8 , Figure 8: It is a structural diagram of an embodiment of an electronic device of the present application. The electronic device includes: a memory 50 and a processor 60 coupled to each other. The memory 50 stores program instructions, and the processor 60 is used to execute the program instructions to implement the method mentioned in any of the above embodiments. Specifically, the electronic device includes but is not limited to: a desktop computer, a laptop computer, a tablet computer, a server, etc., which are not limited here. In addition, the processor 60 can also be called a CPU (Center Processing Unit). The processor 60 may be an integrated circuit chip with signal processing capabilities. The processor 60 can also be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field-programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. In addition, the processor 60 can be implemented by an integrated circuit chip.

[0103] See also Fig. 9 , Fig. 9 It is a structural diagram of an embodiment of a computer-readable storage medium of the present application. The computer-readable storage medium 70 stores program instructions 80 that can be executed by a processor. When the program instructions 80 are executed by the processor, the method mentioned in any of the above embodiments is implemented.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation described above is only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0106] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each implementation method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0108] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A data processing method, characterized in that: include: Obtaining a structured data table, and determining a query index matching each initial field data in the structured data table; Acquire query request information, and based on the query index, acquire target field data matching the query request information from all the initial field data; wherein different target field data are matched with associated information; The output result is obtained by using the query request information, the target field data and the corresponding associated information.

2. The data processing method according to claim 1, characterized in that: The step of obtaining a structured data table and determining a query index matching each initial field data in the structured data table includes: Acquire table information matched by the structured data table and field information matched by each of the initial field data in the structured data table; Based on the structured data table, the table information and the field information, the query index matching each of the initial field data is obtained.

3. The data processing method according to claim 1, characterized in that: The acquiring, based on the query index, target field data matching the query request information from all the initial field data includes: Acquire extraction information corresponding to the query index; wherein the extraction information includes at least one of a keyword and a first semantic vector corresponding to the query index; The target field data is acquired based on the extraction information and the query request information.

4. The data processing method according to claim 3, characterized in that: The extraction information includes the keyword and the first semantic vector, and acquiring the target field data based on the extraction information and the query request information includes: Based on the keyword, obtaining a plurality of first candidate field data from all the initial field data; and, Acquire a second semantic vector corresponding to the query request information, and determine a semantic similarity between the second semantic vector and each of the first semantic vectors; Based on the semantic similarity, obtaining a plurality of second candidate field data from all the initial field data; The target field data is acquired based on the first candidate field data and the second candidate field data.

5. The data processing method according to claim 4, characterized in that: Before acquiring the target field data based on the first candidate field data and the second candidate field data, the method includes: Obtaining preset search prompt information; wherein the search prompt information is related to at least one of user portrait information, supplementary information input by the user, and historical query request information; Based on the search prompt information and the query request information, third candidate field data is acquired from all the initial field data.

6. The data processing method according to claim 5, characterized in that: The acquiring the target field data based on the first candidate field data and the second candidate field data includes: using the first candidate field data, the second candidate field data and the third candidate field data as reference field data, and displaying at least part of the reference field data to a user; In response to obtaining a selected instruction triggered by a user, updating a reference weight of reference field data matched by the selected instruction; The target field data is acquired based on the reference field data and the matched reference weight.

7. The data processing method according to claim 1, characterized in that: After acquiring the target field data matching the query request information from all the initial field data based on the query index, the method further comprises: Detecting the associated information corresponding to all the target field data; In response to the association information corresponding to all the target fields satisfying a preset execution condition, the step of using the query request information, the target field data and the corresponding association information to obtain an output result is performed.

8. The data processing method according to claim 1, characterized in that: The obtaining of output results by using the query request information, the target field data and the corresponding associated information includes: Obtaining a pre-built reference knowledge base, and obtaining parsing information matching the target field data from the reference knowledge base; The query request information, the parsing information, the target field data and the corresponding associated information are input into an intelligent analysis model, and the intelligent analysis model is used to output the output result that matches the query request information.

9. A data processing system, characterized in that: include: An acquisition module, used to acquire a structured data table and determine a query index matching each initial field data in the structured data table; A retrieval module, used to obtain query request information, and based on the query index, obtain target field data matching the query request information from all the initial field data; wherein different target field data are matched with associated information; The processing module is used to obtain output results by using the query request information, the target field data and the corresponding associated information.

10. An electronic device, characterized in that: include: A memory and a processor coupled to each other, wherein the memory stores program instructions, and the processor is used to execute the program instructions to implement the data processing method according to any one of claims 1 to 8.

11. A computer-readable storage medium having program instructions stored thereon, characterized in that: When the program instructions are executed by a processor, the data processing method according to any one of claims 1 to 8 is implemented.

Images