Enhanced ways to optimize data query prompts

Abstract

To provide a system capable of generating specific queries that include business knowledge without increasing a burden on a user.SOLUTION: A method includes the steps of: receiving a first query issued by a user by a processor; extracting multiple field status items associated with the first query by the processor; extracting first schema information associated with the multiple field status items by the processor; adding the multiple field status items as contextual information and the first schema information to the first query by the processor to generate a second query; generating an information search code based on the second query by the processor; and executing the information search code by the processor to take out information associated with the first query from multiple data source systems.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] FIELD OF THE DISCLOSURE The present disclosure relates generally to methods and systems for information retrieval. [Background technology]

[0002] Many businesses today are engaged in digital transformation, which aims to improve operational efficiency and add value using digital technologies. Digital transformation involves connecting different systems and sharing data between them. For example, data can be shared and exchanged by connecting business-related systems, including enterprise resource planning (ERP) systems, product lifecycle management (PLM) systems, manufacturing execution systems (MES), etc. Data from connected systems can be shared on an information sharing platform. In addition, data related to the digital transformation project itself is distributed across file servers, team collaboration tools, code sharing platforms, etc. Therefore, integrated data access becomes possible on the information sharing platform.

[0003] Various data, including but not limited to documents, program codes, numerical data, images, audio, etc., may be stored on an information sharing platform. In order for a user to find desired data from the large amount of available data on the information sharing platform, an excellent search system is required. For example, if a user wants to retrieve information from a relational database, the user uses a structured query language to perform an accurate search. If a user wants to retrieve information from documents in a file system, the user can perform a full-text search using keywords. When searching for data on an information sharing platform where information from different systems is aggregated, it is necessary to be able to search for information without being aware of differences between the systems.

[0004] Related technology discloses a method for utilizing artificial intelligence (AI) in data retrieval. Various users, including business owners, system designers, field researchers, data analysts, maintenance engineers, and robots, can easily retrieve required information by querying the AI ​​in natural language. In addition, AI has the advantage of not only searching for a single document, but also generating sentences that aggregate multiple pieces of data and presenting them to the user, or displaying a list of related documents created as search results.

[0005] However, to retrieve desired user information, an appropriate query is required. If the query is vague, irrelevant / undesired information may be retrieved instead, resulting in wasted time in processing additional queries to arrive at the desired information. On the other hand, creating a specific query requires business knowledge about the data stored in the information sharing platform, such as understanding the type of data stored, which places a burden on the user when generating the query.

[0006] In the related art, methods are disclosed for performing fact / rule generation for a given search target, but the information retrieved by these extensions only produces static results for the user and cannot keep up with current changes in real time.

[0007] In this related art, a system is disclosed that utilizes semantic search to determine similar prompts for use in retraining. Prompts can be generated and searched to identify similar prompts. Data related to the identified similar prompts can then be used for prompt tuning. While the system improves its ability to retrieve through prompt training, it cannot keep up with current changes if it cannot track direct changes in real time. Summary of the Invention [Problem to be solved by the invention]

[0008] There is a need for a system that can generate specific queries that include business knowledge without increasing the burden on users. [Means for solving the problem]

[0009] An aspect of the present disclosure involves an innovative method for performing information retrieval. The method may include: receiving, by a processor, a first query issued by a user; extracting, by the processor, a plurality of field status items associated with the first query; extracting, by the processor, first schema information associated with the plurality of field status items; adding, by the processor, the plurality of field status items and the first schema information as contextual information to the first query to generate a second query; generating, by the processor, information retrieval code based on the second query; and executing, by the processor, the information retrieval code to retrieve information associated with the first query from a plurality of data source systems.

[0010] Aspects of the present disclosure involve an innovative non-transitory computer-readable medium storing instructions for performing information retrieval, which may include receiving a first query issued by a user, extracting a plurality of field status items associated with the first query, extracting first schema information associated with the plurality of field status items, adding the plurality of field status items and the first schema information as contextual information to the first query to generate a second query, generating information retrieval code based on the second query, and executing the information retrieval code to retrieve information associated with the first query from a plurality of data source systems.

[0011] An aspect of the present disclosure involves an innovative server system for performing information retrieval, which may include: receiving, by a processor, a first query issued by a user; extracting, by the processor, a plurality of field status items associated with the first query; extracting, by the processor, first schema information associated with the plurality of field status items; adding, by the processor, the plurality of field status items and the first schema information as contextual information to the first query to generate a second query; generating, by the processor, information retrieval code based on the second query; and executing, by the processor, the information retrieval code to retrieve information associated with the first query from a plurality of data source systems.

[0012] An aspect of the present disclosure involves an innovative system for performing information retrieval, which may include means for receiving a first query issued by a user, means for extracting a plurality of field status items associated with the first query, means for extracting first schema information associated with the plurality of field status items, means for adding the plurality of field status items and the first schema information as contextual information to the first query to generate a second query, generating information retrieval code based on the second query, and means for executing the information retrieval code to retrieve information associated with the first query from a plurality of data source systems.

[0013] A general architecture embodying various features of the present disclosure is described below with reference to the drawings. The drawings and related description are provided to illustrate example embodiments of the present disclosure and are not intended to limit the scope of the disclosure. Throughout the drawings, reference numbers are also used again to indicate correspondence between referenced elements. [Brief explanation of the drawings]

[0014] [Figure 1]FIG. 1 illustrates an exemplary information retrieval query generation system 100, according to one exemplary implementation. [Figure 2] FIG. 2 illustrates an example assembly plant information system 200 that implements the information retrieval query generation system 100 of FIG. 1, according to one exemplary implementation. [Figure 3] FIG. 3 illustrates an exemplary query generation process flow 300, according to one exemplary implementation. [Figure 4] FIG. 1 illustrates an exemplary field status table 104, according to one exemplary implementation. [Figure 5] FIG. 5 illustrates an exemplary field status item 500 extracted by the status adding unit 110, according to one exemplary implementation. [Figure 6] FIG. 1 illustrates an exemplary schema table 105, according to one exemplary implementation. [Figure 7] FIG. 7 illustrates exemplary schema information 700 extracted by schema addition unit 111, according to one exemplary implementation. [Figure 8] FIG. 8 illustrates an exemplary field status item 800 extracted by the status adding unit 110, related to a second use case, according to an exemplary implementation. [Figure 9] FIG. 9 illustrates exemplary schema information 900 extracted by the schema adding unit 111 as applied in a second use case, according to one exemplary implementation. [Figure 10] FIG. 1 illustrates an exemplary computing environment having an exemplary computer device suitable for use in some exemplary implementations. DETAILED DESCRIPTION OF THE INVENTION

[0015] The following detailed description provides details of the figures and exemplary embodiments of the present application. Reference numbers and descriptions of elements that are duplicated between figures are omitted for clarity. Terms used throughout the description are provided by way of example and are not intended to be limiting. For example, use of the term "automatic" can include fully automatic or semi-automatic implementations, including user or administrator control over certain aspects of the implementation, depending on the desired implementation of one skilled in the art practicing the embodiments of the present application. Selection can be performed by a user via a user interface or other input means, or can be implemented via a desired algorithm. The exemplary implementations as described herein can be used either alone or in combination, and the functionality of the exemplary implementations can be implemented via any means according to the desired implementation.

[0016] Exemplary embodiments relate to methods and systems for performing query generation that takes business knowledge into account while reducing the burden of query entry on users. The exemplary embodiments extract information a user is searching for without increasing the burden on the user by adding contextual information to the user's query according to the current situation. This contextual information may include, but is not limited to, information associated with the user's organization and task, the time and location at which the query was entered, scheduled tasks and actual tasks performed in the field, the method of communication with data sources, the type of data stored, etc.

[0017] The first use case involves a query input involving a worker performing assembly work in an assembly plant. Figure 1 illustrates an exemplary information retrieval query generation system 100, according to one exemplary implementation. The information retrieval query generation system 100 may include components such as, but not limited to, a context adding unit 101, a field status table creating unit 102, a schema table creating unit 103, a field status table 104, a schema table 105, a history table creating unit 106, a query history table 107, a history adding unit 108, and an execution code generating unit 109.

[0018] The context adding unit 101 analyzes a query entered / entered by a user and extracts field context items and associated schema information based on the query. The context adding unit 101 further adds the field context items and schema information as context information to the query to generate a second query. As shown in FIG. 1 , the context adding unit 101 may include components such as a context adding unit 110 and a schema adding unit 111. The context adding unit 110 performs extraction of field context information / items related to the query entered by the user from the field context table 104, and the schema adding unit 111 performs extraction of schema information related to the extracted field context items from the schema table 105.

[0019] The field status table 104 contains shop floor status information for an assembly plant and is generated and updated by the field status table creation unit 102. In some example implementations, the shop floor status information may include information related to business resources, product lifecycle, manufacturing execution, etc. The field status table 104 is described in more detail below with reference to FIG. 2.

[0020] The schema table 105 contains information necessary to obtain the worksite status information of the field status table 104, and is generated and updated by the schema table creation unit 103. The schema table 105 may include information such as, but is not limited to, data format, database address, authentication information, table name, data type, directory name, etc. The schema table 105 will be described in more detail below with reference to FIG. 2.

[0021] The query history table 107 stores information related to queries that have been executed in the past, and is generated and updated by the history table creation unit 106. The query history table 107 may include information such as, but not limited to, the date and time of the executed query, the user input query, the revised query with added context information from the field status table 104 and the schema table 105, the information search execution code, etc. The query history table 107 will be described in more detail below with reference to FIG. 2.

[0022] The history adding unit 108 searches the query history table 107 to extract past queries similar to the second query generated by the context adding unit 101. Past query information related to the extracted past queries is then added to the second query by the history adding unit 108. The execution code generating unit 109 generates an information retrieval execution code based on the second query. The information retrieval execution code is executed to retrieve information as needed by the user from various data sources based on the input query.

[0023] 2 illustrates an example assembly plant information system 200 that implements the information retrieval query generation system 100 of FIG. 1, according to one example implementation. In some example implementations, the assembly plant information system 200 may include components such as, but not limited to, the information retrieval query generation system 100, a data source system 201, etc.

[0024] The data source system 201 may include systems such as, but not limited to, an enterprise resource planning (ERP) system 203, a product lifecycle management (PLM) system 204, a manufacturing execution system (MES) 205, an autonomous mobile robot (AMR) 206, and a monitoring sensor / camera / device 207. In some exemplary implementations, the data source system 201 may include collaboration platforms / systems 208-210, such as messaging applications, program code revision control systems, internet site pages, and document libraries. The data source system 201 further includes a data infrastructure platform 220 that provides a common access method and data flow control to achieve collaboration among various data sources in the data source system 201. When the information retrieval execution code generated by the execution code generation unit 109 is executed, information (e.g., data, tables, files, etc.) and / or programs can be retrieved from various data sources through the data infrastructure platform 220.

[0025] The ERP system 203 stores business resource information, including, but not limited to, worker information, order information, and work order information. Worker information includes employee / worker name, job title, job, employee / worker work period, etc. Order information includes customer, delivery date, product name, quantity, inventory information, etc. Work order information includes the recorded plan for the product, the number of units of the product to be produced per day, week, or month.

[0026] The PLM system 204 stores product lifecycle information, including but not limited to product specification information, product production method information, etc. Product specification information includes product detailed design drawings, a list of parts required for assembly, etc. Product production method information includes assembly manuals, inspection manuals, etc.

[0027] The MES 205 stores manufacturing execution information, including detailed work plan information, which includes a plan for what and how many units should be produced in a given time unit, the workers / employees involved in tasks such as assembly and inspection, and the locations where assembly and inspection should be performed. The detailed work plan information may be dynamically changed based on conditions at the work site. The MES 205 also stores work execution status information, including the completion time of each product's manufacturing or inspection process, the name of the worker responsible, the work execution location, and the like. Using the detailed work plan information, the status of the work execution information may be dynamically changed according to local conditions. In some exemplary implementations, the work execution status information may be entered by workers using input devices such as, but not limited to, laptops, kiosks, tablets, mobile devices, devices using radio frequency identification tags, devices using two-dimensional codes, devices using camera images, or audio from microphones installed in the factory.

[0028] 3 shows an exemplary query generation process flow 300 according to one exemplary implementation. The process begins in step S301 when a user issues and inputs a query, which is received by the information retrieval query generation system 100. For example, a user named Clara inputs the query "View the manual" in cell A on July 10, 2023 at 8:50 AM. In step S302, the field status table creation unit 102 performs an update of the field status table 104.

[0029] 4 illustrates an exemplary field status table 104, according to one exemplary implementation. As shown in FIG. 4, the field status table 104 may include information such as, but not limited to, worker information 401, order information 402, work order information 403, and manufacturing execution information 404. The information stored in the field status table 104 is obtained from various data sources, such as an ERP system, a PLM system, an MES, etc. In some exemplary implementations, the information stored in the field status table 104 may be saved in a format other than a table, such as comma-separated values ​​(CSV), extensible markup language (XML), or JavaScript object notation (JSON).

[0030] Worker information 401 may include fields such as name, job title, job duties, and work duration. Order information 402 may include fields such as client name / identifier, delivery due date, product name / identifier, order quantity, and inventory. Work order information 403 may include fields such as date, product name / identifier, and quantity produced. Manufacturing execution information 404 may include fields such as shift start time, shift end time, worker name / identifier, product and quantity, and location.

[0031] Referring back to FIG. 3 , in step S303, the context adding unit 110 extracts field context items related to the input query in real time. As shown in FIG. 4 , because the query was issued by a user named Clara, information related to Clara is extracted from the worker information 401. For the order information 402, complete information is extracted because the information cannot be narrowed based on the input query. For the work order information 403, because the query was issued on July 10, 2023, work order information related to the date July 10, 2023 is extracted. For the manufacturing execution information 404, because the query was issued by Clara, manufacturing execution information related to the work performed by Clara is extracted. FIG. 5 shows an exemplary field context item 500 extracted by the context adding unit 110 according to an exemplary embodiment. A trained artificial intelligence (AI) model may be used when extracting field context items. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some example implementations, the AI ​​model is a large-scale multimodal language model that operates with different types of input data, such as text, images, audio, video, etc.

[0032] In step S304, the schema table creation unit 103 updates the schema table 105. Figure 6 shows an exemplary schema table 105 according to one exemplary embodiment. The schema table 105 includes information such as, but not limited to, a table list 601, a file list 602, and an application program interface (API) list 603. The table list 601 contains schema information related to data recorded in table form among data to be processed by the information retrieval query generation system 100. In particular, the table list 601 may include information such as, but not limited to, authentication information, the structure of the table, the recorded data, an overview of how to access the database, etc.

[0033] The file list 602 contains schema information associated with data recorded in file format that is to be processed by the information retrieval query generation system 100. In particular, the file list 602 may include information such as, but not limited to, file names, a summary of the recorded files, authentication information, paths, and other file access methods.

[0034] The API list 603 contains schema information related to data that may be accessed by an application programming interface (API) among the data processed by the information retrieval query generation system 100. In particular, the API list 603 may include information such as, but not limited to, the name, a summary of the data to be accessed, authentication information, paths, and other data access methods.

[0035] In some example implementations, schema information about data recorded in table and file formats may also be included in API list 603. The information contained in schema table 105 may be recorded in table format, CSV, XML, JSON, or other formats. If the information recorded in schema table 105 is not current and is inappropriate for query generation, schema table 105 is updated with real-time information.

[0036] The process then continues to step S305, where the schema adding unit 111 extracts, in real time, schema information related to the field context item extracted during step S303. FIG. 7 shows exemplary schema information 700 extracted by the schema adding unit 111 according to an exemplary implementation. A trained artificial intelligence (AI) model may be used in extracting the schema information. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary implementations, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, and video.

[0037] In step S306, the context adding unit 101 adds the extracted field context items and the extracted schema information to the input query as context information to generate a second query. In step S307, a determination is made as to whether a previous query should be referenced. In some exemplary embodiments, the decision as to whether to reference a previous query is made by a user. In some exemplary embodiments, an operator of the information retrieval query generation system 100 may set a default value in advance, or the decision may be made by viewing the content of the second query generated in step S306. If the answer is "no" in step S307, the process continues to step S310, which is described in detail below.

[0038] If the answer is “yes” in step S307, the process continues to step S308, where the history adding unit 108 searches the query history table 107 to extract queries similar to the second query generated in step S306. In some exemplary implementations, a trained artificial intelligence (AI) model may be used in extracting past queries. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary implementations, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, video, etc. In step S309, the history adding unit 108 identifies past query information related to the past query extracted in step S308 and adds it to the second query, and the process proceeds to step S310. In the first use case, previous query information related to an assembly work instruction is identified and added to a second query.

[0039] In step S310, the execution code generation unit 109 generates information retrieval execution code based on the second query generated in step S306 or S309. An artificial intelligence (AI) model may be used in generating the information retrieval code. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary embodiments, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, and video. The field context information extracted in step S303 indicates that a user is searching for an assembly manual for the "Flex CF70." The schema information extracted in step S305 indicates that the manual is stored in the path "cf70 / assembly / manual / 01 / " and can be accessed by issuing the API base path (using the HTTPS protocol) "dip.com / api / v2.0 / file / cd70 / ". Then, through the use of the AI ​​model, the execution code generation unit 109 generates the information retrieval code "GET: dip.com / api / v2.0 / file / cd70 / assembly / manual / 01 / manufacturing_plan_R4.pdf".

[0040] In step S311, the generated information retrieval code is executed to retrieve the information sought by the user from various data sources. Finally, in step S312, the history table creation unit 106 updates the query history table 107 with the input query, the query input time, the second query in step S306 or S309, and the information retrieval code associated with the past query.

[0041] A second use case is described below and involves a query input involving a worker performing process control tasks in an assembly plant. The process flow 300 in Figure 3 is used to explain the query generation process for the second use case below.

[0042] The process begins in step S301 where a query is issued / input by a user. In the second use case, a user, i.e., an employee named Daniel who works at an assembly plant, issues the query "I want to know the downtime" in cell A on July 10, 2023 at 1:00 PM. In step S302, the field status table creation unit 102 updates the field status table 104.

[0043] In step S303, the status adding unit 110 extracts, in real time, field status items related to the query issued in step S301. Because the query was issued by a user named Daniel, information related to Daniel is extracted from the worker information 401. For the order information 402, complete information is extracted because the information cannot be narrowed based on the input query. For the work order information 403, because the query was issued on July 10, 2023, work order information related to the date July 10, 2023 is extracted. For the manufacturing execution information 404, because there are no items directly related to Daniel, who issued the query, all manufacturing execution information is extracted.

[0044] 8 illustrates an exemplary field situation item 800 extracted by the situation addition unit 110, related to a second use case, according to one exemplary implementation. An artificial intelligence (AI) model may be used in extracting the field situation item. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary implementations, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, video, etc.

[0045] In step S304, the schema table creation unit 103 updates the schema table 105. Similar to FIGS. 6 and 7, the schema table 105 includes information such as, but not limited to, a table list 801, a file list 802, and an application program interface (API) list 803. The process then proceeds to step S305, where the schema addition unit 111 extracts, in real time, schema information related to the field status items extracted in step S303. FIG. 9 shows exemplary schema information 900 extracted by the schema addition unit 111 as applied in the second use case according to an exemplary embodiment. An artificial intelligence (AI) model may be used in extracting the schema information. Such an AI model may be a rule-based decision-making algorithm that utilizes at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary implementations, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, and video.

[0046] In step S306, the context adding unit 101 adds the extracted field context items and the extracted schema information to the input query as context information to generate a second query. In step S307, a determination is made as to whether a previous query should be referenced. In some exemplary embodiments, the decision as to whether to reference a previous query is made by a user. In some exemplary embodiments, an operator of the information retrieval query generation system 100 may set default values ​​in advance, or the decision may be made by viewing the content of the second query generated in step S306. If the answer is "no" in step S307, the process continues to step S310.

[0047] If the answer is “yes” in step S307, the process continues to step S308, where the history adding unit 108 searches the query history table 107 to extract queries similar to the second query generated in step S306. In some exemplary implementations, an artificial intelligence (AI) model may be used in extracting past queries. Such an AI model may be a rule-based decision-making algorithm utilizing at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary implementations, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, video, etc. In step S309, the history adding unit 108 identifies past query information related to the past query extracted in step S308 and adds it to the second query, and the process proceeds to step S310. In a second use case, past query information related to downtime is identified and added to a second query.

[0048] In step S310, the execution code generation unit 109 generates information retrieval execution code based on the second query generated in step S306 or S309. In some exemplary embodiments, an artificial intelligence (AI) model may be used in generating the information retrieval code. Such an AI model may be a rule-based decision-making algorithm that utilizes at least one of a recurrent neural network (RNN), a deep recurrent neural network (DRNN), a Q-learning network (QN), a deep Q-learning network (DQN), etc. The RNN may include a long short-term memory (LSTM), etc. In some exemplary embodiments, the AI ​​model is a large-scale multimodal language model that operates using different types of input data, such as text, images, audio, and video. The field context information extracted in step S303 indicates that a user is searching for information about downtime for cell A. The schema information extracted in step S305 indicates that the data is stored in “cell_a” in the “assembly” database and that tables in “cell_a” can be accessed by the dashboard API.

[0049] In step S311, the generated information retrieval code is executed to retrieve the information sought by the user from various data sources. Through the use of the AI ​​model, the execution code generation unit 109 can generate information retrieval code such as "OPEN web browser: dip.com / api / v2.0 / dashboard / query?query=up&start=2023-07-10T07:00:00.000Z &place=cell_a," which is executable to access raw data such as "psql-d assembly-c "SELECT * FROM cell_a WHERE execute_date >'2023-07-10T07:00:00.000Z." Finally, in step S312, the history table creation unit 106 updates the query history table 107 with the input query, the query input time, the second query of step S306 or S309, and the information retrieval code associated with the past query.

[0050] The above exemplary implementation may have various benefits and advantages. For example, by including current information through the use of field status table 104 and schema table 105, search results that track changes in the user's (employees working for a company / assembly plant) status in real time may be returned to the user. A user may obtain desired information through the input of a simple query. Queries with the same input text may return different responses based on the user's status.

[0051] 10 illustrates an exemplary computing environment having an exemplary computing device suitable for use in some exemplary implementations. The computing device 1005 in the computing environment 1000 can include one or more processing units, cores, or processors 1010, memory 1015 (e.g., RAM, ROM, and / or the like), internal storage 1020 (e.g., magnetic, optical, solid-state storage, and / or organic), and / or IO interface 1025, any of which can be coupled over a communication mechanism or bus 1030 for communicating information or can be incorporated into the computing device 1005. The IO interface 1025 can be further configured to receive images from a camera or provide images to a projector or display, depending on the desired implementation.

[0052] The computing device 1005 may be communicatively coupled to an input / user interface 1035 and an output device / interface 1040. Either or both of the input / user interface 1035 and the output device / interface 1040 may be a wired or wireless interface and may be detachable. The input / user interface 1035 may include any device, component, sensor, or interface, physical or virtual, that can be used to provide input (e.g., buttons, touchscreen interface, keyboard, pointing / cursor control, microphone, camera, Braille, motion sensor, accelerometer, optical reader, and / or the like). The output device / interface 1040 may include a display, television, monitor, printer, speaker, Braille, or the like. In some exemplary implementations, the input / user interface 1035 and the output device / interface 1040 may be incorporated with or physically coupled to the computing device 1005. In other implementations, other computing devices may function as or provide the functionality of input / user interface 1035 and output device / interface 1040 for computing device 1005 .

[0053] Examples of computing devices 1005 may include, but are not limited to, highly mobile devices (e.g., smartphones, devices mounted on vehicles and other machines, devices carried by people or animals, and the like), mobile devices (e.g., tablets, notebooks, laptops, personal computers, portable televisions, radios, and the like), and devices not designed for mobility (e.g., desktop computers, other computers, information kiosks, televisions with one or more processors embedded and / or televisions with one or more processors coupled thereto, radios, and the like).

[0054] Computing device 1005 may be communicatively coupled (e.g., via IO interface 1025) to external storage 1045 and network 1050 for communication with any number of networked components, devices, and systems, including one or more computing devices of the same or different configurations. Computing device 1005 or any connected computing device may function as, provide services to, or be referred to as a server, client, thin server, general-purpose machine, special-purpose machine, or otherwise.

[0055] IO interface 1025 may include, but is not limited to, wired and / or wireless interfaces using any communication or IO protocol or convention (e.g., Ethernet, 802.11x, Universal System Bus, WiMax, modem, cellular network protocols, and the like) for communicating information to and / or from at least all connected components, devices, and networks in computing environment 1000. Network 1050 may be any network or combination of networks (e.g., the Internet, a local area network, a wide area network, a telephone network, a cellular network, a satellite network, and the like).

[0056] The computing device 1005 may use and / or communicate using computer-usable or computer-readable media, including transitory and non-transitory media. Transitory media include transmission media (e.g., metallic cables, fiber optics), signals, carrier waves, and the like. Non-transitory media include magnetic media (e.g., disks and tape), optical media (e.g., CD-ROM, digital video disks, Blu-ray disks), solid-state media (e.g., RAM, ROM, flash memory, solid-state storage), and other non-volatile storage or memory.

[0057] The computing device 1005 can be used to implement techniques, methods, applications, processes, or computer-executable instructions in some exemplary computing environments. The computer-executable instructions can be retrieved from transitory media and stored on and retrieved from non-transitory media. The executable instructions can be from one or more of any programming, scripting, and machine language (e.g., C, C++, C#, Java, Visual Basic, Python, Perl, JavaScript, etc.).

[0058] The processor 1010 can run under any operating system (OS) (not shown) in a native or virtual environment. One or more applications can be deployed, including a logic unit 1060, an application programming interface (API) unit 1065, an input unit 1070, an output unit 1075, and an inter-unit communication mechanism 1095 for different units to communicate with each other, with the OS, and with other applications (not shown). The above-mentioned units and elements can vary in design, function, configuration, or implementation and are not limited to the above description. The processor 1010 can have the form of a hardware processor, such as a central processing unit (CPU), or can be a combination of hardware and software units.

[0059] In some exemplary implementations, when information or instructions for execution are received by API unit 1065, it may be communicated to one or more other units (e.g., logic unit 1060, input unit 1070, output unit 1075). In some examples, logic unit 1060 may be configured to control the flow of information between units and, in some exemplary implementations described above, direct the services provided by API unit 1065, input unit 1070, and output unit 1075. For example, the flow of one or more processes or implementations may be controlled by logic unit 1060 alone or in conjunction with API unit 1065. Input unit 1070 may be configured to obtain inputs for the calculations described in the exemplary implementations, and output unit 1075 may be configured to provide outputs based on the calculations described in the exemplary implementations.

[0060] The processor 1010 may be configured to receive a first query issued by a user, as shown in FIG. 2. The processor 1010 may also be configured to extract a plurality of field status items associated with the first query, as shown in FIG. 2. The processor 1010 may also be configured to extract first schema information associated with the plurality of field status items, as shown in FIG. 2. The processor 1010 may also be configured to add the plurality of field status items and the first schema information as context information to the first query to generate a second query, as shown in FIG. 2. By including current information (the field status items and the first schema information) as context information, this ensures that search results that track changes in the user's (employees working for the company / assembly plant) status in real time can be returned to the user. The processor 1010 may also be configured to generate information retrieval code based on the second query, as shown in FIG. 2. The processor 1010 may also be configured to execute the information retrieval code to retrieve information related to the first query from a plurality of data source systems, as shown in FIG. 2. A user can obtain desired information through inputting a simple query. Queries with the same input text can return different responses based on the user's context (e.g., from extracted field status items).

[0061] The processor 1010 may also be configured to determine a reference to a past query, as shown in FIG. 2. The processor 1010 may also be configured to perform query extraction to extract at least one past query that is similar to the second query, as shown in FIG. 2. The processor 1010 may also be configured to identify past query information related to the at least one past query, as shown in FIG. 2. The processor 1010 may also be configured to add the past query information to the second query, as shown in FIG. 2. The processor 1010 may also be further configured to store the first query, the second query, and the information retrieval code as past queries, as shown in FIG. 2.

[0062] Some portions of the detailed description are presented in terms of algorithms and symbolic representations of operations within a computer. These algorithmic descriptions and symbolic representations are the means used by those skilled in the data processing arts to convey the substance of their innovations to others skilled in the art. An algorithm is a series of defined steps leading to a desired end state or result. In exemplary implementations, the performed steps require physical manipulations of tangible quantities to achieve a tangible result.

[0063] Unless otherwise specified, and as will be apparent from the description, throughout this specification, descriptions utilizing words such as "processing," "calculating," "computing," "determining," "displaying," or the like, are understood to include the actions and processes of a computer system or other information processing device that manipulates and converts data represented as physical (electronic) quantities in the registers and memory of the computer system into other data similarly represented as physical quantities in the memory or registers of the computer system or other information storage, transmission, or display devices.

[0064] Exemplary embodiments may further relate to apparatuses for performing the operations herein. This apparatus may be specially constructed for the desired purposes, or may include one or more general-purpose computers selectively activated or reconfigured by one or more computer programs. Such computer programs may be stored on a computer-readable medium, such as a computer-readable storage medium or a computer-readable signal medium. Computer-readable storage media may include tangible media, such as, but not limited to, optical disks, magnetic disks, read-only memory, random-access memory, solid-state devices and drives, or any other type of tangible or non-transitory medium suitable for storing electronic information. Computer-readable signal media may include media such as carrier waves. The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. A computer program may include a pure software implementation containing instructions for performing the operations of a desired embodiment.

[0065] Various general-purpose systems may be used with the programs and modules according to the examples herein, or it may prove convenient to construct specialized apparatus to perform the desired method steps. Moreover, the example embodiments are not described with reference to any particular programming language. It will be understood that a variety of programming languages ​​may be used to implement the teachings of the example embodiments as described herein. Instructions in the programming language may be executed by one or more processing devices, such as, for example, a central processing unit (CPU), a processor, or a controller.

[0066] As is known in the art, the operations described above may be performed by hardware, software, or some combination of software and hardware. Various aspects of the exemplary embodiments may be implemented using circuits and logic devices (hardware), while other aspects may be implemented using instructions stored on a machine-readable medium (software) that, when executed by a processor, cause the processor to perform methods that implement the present application. Furthermore, some exemplary embodiments of the present application may be implemented solely in hardware, while other exemplary embodiments may be implemented solely in software. Furthermore, the various functions described may be performed in a single unit or may be distributed across multiple components in any number of ways. When implemented by software, the methods may be executed by a processor, such as a general-purpose computer, based on instructions stored on a computer-readable medium. If desired, the instructions may be stored on the medium in compressed and / or encrypted format.

[0067] Additionally, other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the teachings herein. Various aspects and / or components of the described exemplary embodiments may be used singly or in any combination. It is intended that the specification and exemplary embodiments be considered exemplary only, with the true scope and spirit of the present application being indicated by the following claims. [Explanation of symbols]

[0068] 100 Information Retrieval Query Generation System 101 Context Addition Unit 102 Field Status Table Creation Unit 103 Schema Table Creation Unit 104 Field Status Table 105 Schema Tables 106 History Table Creation Unit 107 Query History Table 108 History Addition Unit 109 Execution Code Generation Unit 201 Data Source System 1005 Computer Devices 1010 processor 1015 memory 1020 Internal Storage 1025 IO interface 1035 Input / User Interface 1040 Output Device / Interface 1045 External Storage 1050 Network 1060 logical units 1065 API units 1070 input unit 1075 output unit

Claims

1. A method for generating a search query for information retrieval, comprising: receiving, by a processor, a first query issued by a user; extracting, by the processor, a plurality of field status items associated with the first query; extracting, by the processor, first schema information associated with the plurality of field status items; adding, by the processor, the plurality of field status items and the first schema information as context information to the first query to generate a second query; generating, by the processor, an information retrieval code based on the second query; executing, by the processor, the information retrieval code to retrieve information associated with the first query from a plurality of data source systems; the first schema information is derived from second schema information, the second schema information relating to data stored across the multiple data source systems; the second schema information includes schema information of a data table associated with the data, schema information of a data file associated with the data, and schema information of an application program interface that accesses the data; method.

2. A method for generating a search query for information retrieval, comprising: receiving, by a processor, a first query issued by a user; extracting, by the processor, a plurality of field status items associated with the first query; extracting, by the processor, first schema information associated with the plurality of field status items; adding, by the processor, the plurality of field status items and the first schema information as context information to the first query to generate a second query; generating, by the processor, an information retrieval code based on the second query; executing, by the processor, the information retrieval code to retrieve information associated with the first query from a plurality of data source systems; determining, by the processor, to reference a previous query; performing, by the processor, query extraction to extract at least one previous query that is similar to the second query; identifying, by the processor, past query information associated with the at least one past query; adding, by the processor, the previous query information to the second query; further comprising: method.

3. The method of claim 2 , further comprising storing, by the processor, the first query, the second query, and the information retrieval code as past queries.

4. The plurality of field status items are extracted from field status information, the field status information includes employee information, order information, work order information, and manufacturing execution information; 3. The method according to claim 1 or 2.

5. the employee information, the order information, the work order information, and the manufacturing execution information are associated with a company; the user is an employee of the company, and employee information of the user is extracted from the field status information as part of the plurality of field status items; The method of claim 4.

6. The method of claim 1 or 2, wherein the plurality of data source systems includes an enterprise resource planning (ERP) system, a product lifecycle management (PLM) system, and a manufacturing execution system (MES).

7. The method of claim 1 or 2, wherein the extraction of the plurality of field status items and the extraction of the first schema information are performed in real time.

8. The method of claim 1 or 2, wherein the extraction of the plurality of field status items, the extraction of the first schema information, and the generation of the information retrieval code are performed using a trained artificial intelligence model.

9. 1. A search query generation system for information retrieval, comprising: Multiple data source systems, a processor in communication with the plurality of data source systems, the processor comprising: receiving a first query issued by a user; extracting a plurality of field status items associated with the first query; extracting first schema information associated with the plurality of field status items; adding the plurality of field status items and the first schema information as context information to the first query to generate a second query; generating an information retrieval code based on the second query; executing the information retrieval code to retrieve information associated with the first query from the plurality of data source systems; the first schema information is derived from second schema information, the second schema information relating to data stored across the multiple data source systems; the second schema information includes schema information of a data table associated with the data, schema information of a data file associated with the data, and schema information of an application program interface that accesses the data; system.

10. A search query generation system for information retrieval, comprising: Multiple data source systems, a processor in communication with the plurality of data source systems, the processor comprising: receiving a first query issued by a user; extracting a plurality of field status items associated with the first query; extracting first schema information associated with the plurality of field status items; adding the plurality of field status items and the first schema information as context information to the first query to generate a second query; generating an information retrieval code based on the second query; executing the information retrieval code to retrieve information associated with the first query from the plurality of data source systems; the processor: determining to refer to a previous query; performing query extraction to extract at least one past query that is similar to the second query; identifying past query information associated with the at least one past query; and adding the past query information to the second query. system.

11. the processor: The system of claim 10 , further configured to store the first query, the second query, and the information retrieval code as past queries.

12. the plurality of field status items are extracted from field status information; the field status information includes employee information, order information, work order information, and manufacturing execution information; 11. A system according to claim 9 or 10.

13. the employee information, the order information, the work order information, and the manufacturing execution information are associated with a company; the user is an employee of the company, and employee information of the user is extracted from the field status information as part of the plurality of field status items; The system of claim 12.

14. The system of claim 9 or 10, wherein the plurality of data source systems includes an enterprise resource planning (ERP) system, a product lifecycle management (PLM) system, and a manufacturing execution system (MES).

15. The system of claim 9 or 10, wherein the extraction of the plurality of field status items and the extraction of the first schema information are performed in real time.

16. 11. The system of claim 9 or 10, wherein the extraction of the plurality of field status items, the extraction of the first schema information, and the generation of the information retrieval code are performed using a trained artificial intelligence model.

Images