CN117370426B - Report data generation method, system and storage medium based on artificial intelligence - Google Patents
Report data generation method, system and storage medium based on artificial intelligence Download PDFInfo
- Publication number
- CN117370426B CN117370426B CN202311641706.1A CN202311641706A CN117370426B CN 117370426 B CN117370426 B CN 117370426B CN 202311641706 A CN202311641706 A CN 202311641706A CN 117370426 B CN117370426 B CN 117370426B
- Authority
- CN
- China
- Prior art keywords
- information
- data
- query
- dimension
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 23
- 230000002452 interceptive effect Effects 0.000 claims abstract description 30
- 238000000605 extraction Methods 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 29
- 230000000007 visual effect Effects 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 abstract description 16
- 238000012549 training Methods 0.000 abstract description 7
- 238000007405 data analysis Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/248—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a report data generation method, a report data generation system and a storage medium based on artificial intelligence, which relate to the field of artificial intelligence, and the method comprises the following steps: acquiring demand input information from an interactive terminal; invoking a pre-trained target feature extraction model according to the demand input information to acquire context information and prompt information corresponding to the demand input information; generating data query scheme information, wherein the data query scheme information comprises query dimension information and query index information; and calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal. According to the method, a manual report development scheme can be changed into collection and adjustment of training data, a user is required to actively find a report for use according to the automatic generation of the problem, a report interface is generated, and development cost and user learning and use cost are reduced.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a report data generation method, system and storage medium based on artificial intelligence.
Background
In an ERP (Enterprise Resource Planning ) system, an enterprise can realize the following benefits through the ERP system:
1. process integration and optimization: ERP integrates each department and business process of enterprise for information flows more smoothly between different departments, has avoided information island and repeated work. Meanwhile, through an automatic and standardized process, the operation efficiency of enterprises can be optimized, and the productivity is improved.
2. Data centralization and real-time performance: the ERP system stores the data of each business field of the enterprise in a unified database, and ensures that all related parties use the same piece of accurate and real-time data. This may help the management layer make more accurate, more informed decisions.
3. Information sharing and collaboration: the ERP system can connect related stakeholders inside and outside the enterprise to realize information sharing and cooperative work. Suppliers, customers, and partners may interact with the enterprise through the system to facilitate closer partnerships.
4. Data analysis and decision support: the ERP system provides various reports and data analysis tools to help the enterprise management layer to comprehensively monitor and analyze the business. This enables the management layer to make accurate decisions based on the data and respond quickly to market changes.
In terms of data analysis and decision support of the traditional ERP, a large number of analysis reports with various purposes need to be developed for users. The traditional ERP report is factory preset by a developer with a plurality of data analysis schemes, and a user can only inquire and analyze data by using the existing functions, but can also modify dimensions and indexes in a limited range.
Therefore, in the prior art, a large number of reports need to be developed, users need to learn the use of various reports before using the reports, the reports cannot be rapidly and flexibly subjected to custom analysis according to the intention of the users, and the development and use cost is high.
Disclosure of Invention
Based on the above, it is necessary to provide a report data generating method, system and storage medium based on artificial intelligence, aiming at the problem that the existing ERP system cannot be rapidly and flexibly subjected to user-defined analysis according to user intention and has high development and use costs.
A report data generation method based on artificial intelligence comprises the following steps:
acquiring demand input information from an interactive terminal;
according to the requirement input information, invoking a pre-trained target feature extraction model to acquire context information and prompt information corresponding to the requirement input information;
generating data query scheme information based on the demand input information, the context information corresponding to the demand input information and the prompt information, wherein the data query scheme information comprises query dimension information and query index information;
and calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal.
In one preferred embodiment, the obtaining the requirement input information from the interactive terminal includes:
and acquiring the required input information from a visual dialog of the interactive terminal.
In one preferred embodiment, the invoking the pre-trained target feature extraction model according to the requirement input information to obtain the context information and the prompt information corresponding to the requirement input information includes:
obtaining a target field, target problem data and historical dialogue data according to the requirement input information;
performing data splicing on the target field, the target problem data and the historical dialogue data to obtain a problem attention vector;
and calling the pre-trained target sign extraction model based on the problem attention vector to obtain context information and prompt information about the problem attention vector.
In one preferred embodiment, the data stitching is performed on the target field, the target problem data, and the historical dialogue data to obtain a problem attention vector, including:
importing the target field, the target question data and the historical dialogue data into a pre-trained question selector;
obtaining at least two candidate question sequences regarding the target field, target question data, and historical dialog data based on the question selector;
receiving a candidate question selection instruction to determine one of the candidate questions about the candidate question;
the problem interest vector corresponding to the candidate problem is obtained based on the candidate problem.
In one preferred embodiment, the displaying the dimension result information and the index result information on the interactive terminal includes:
and the dimension result information and the index result information are displayed on the interactive terminal in a visual dialogue report form.
In one preferred embodiment, the generating data query scheme information based on the requirement input information, the context information corresponding to the requirement input information, and the prompt information, where the data query scheme information includes query dimension information and query index information includes:
when the data query scheme comprises a plurality of query dimension information and query index information, grouping the plurality of query dimension information and query index information, and identifying each group of query dimension information and query index information.
In one preferred embodiment, the data query schema information is in JSON format.
In one preferred embodiment, the data query scheme information is in JSON format, including:
judging the format of the query scheme information, and if the format of the query scheme information is JSON format, continuing to execute;
if the format of the query scheme information is not the JSON format, the required input information is continuously acquired from the interactive terminal.
According to the method disclosed by the embodiment of the invention, the manual report development scheme can be changed into the collection and adjustment of training data, the report which is required to be actively found by the user is automatically generated according to the problem which is required to be used by the user, the problem is directly set up, the report interface is generated, the query scheme can be automatically adjusted according to the requirement of the user, and the development cost and the cost of learning and using of the user are reduced.
An artificial intelligence report data based generation system comprising:
the dialog box input module is used for acquiring the required input information from the interactive terminal;
the information extraction module is used for calling a pre-trained target feature extraction model according to the requirement input information to acquire context information and prompt information corresponding to the requirement input information;
the query scheme generation module is used for generating data query scheme information based on the requirement input information, the context information corresponding to the requirement input information and the prompt information, wherein the data query scheme information comprises query dimension information and query index information;
and the data information analysis module is used for calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal.
The system disclosed by the embodiment of the invention can change the manual report development scheme into the collection and adjustment of training data, automatically generate the report which is required to be actively found by a user according to the problem which is required to be used by the user, directly put forward the problem, generate a report interface, automatically adjust the query scheme according to the requirement of the user, and reduce the development cost and the cost of learning and use of the user.
A computer readable storage medium having a computer program stored thereon, which when executed by a processor, performs the steps of a report data generation method based on artificial intelligence as described above.
According to the method disclosed by the embodiment of the invention, the manual report development scheme can be changed into the collection and adjustment of training data by executing the method, the report use which is required to be actively found by a user is automatically generated according to the problem which is required to be used by the user, the problem is directly set up, a report interface is generated, the query scheme can be automatically adjusted according to the requirement of the user, and the development cost and the cost of user learning and use are reduced.
Drawings
FIG. 1 is a flowchart of a report data generation method based on artificial intelligence in a first preferred embodiment of the present invention;
FIG. 2 is a block diagram of an artificial intelligence report data based generation system in accordance with a second preferred embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that when an element is referred to as being "disposed on" another element, it can be directly on the other element or intervening elements may also be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. The terms "vertical," "horizontal," "left," "right," and the like are used herein for illustrative purposes only and are not meant to be the only embodiment.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
As shown in fig. 1, in a first preferred embodiment of the present invention, a report data generating method based on artificial intelligence is disclosed, which mainly includes:
s10: and acquiring the required input information from the interactive terminal.
In this step, the requirement input information is obtained from the visual dialog of the interactive terminal.
In this embodiment, the operator can input the required input information by opening the intelligent assistant.
S20: and according to the requirement input information, invoking a pre-trained target feature extraction model to acquire context information and prompt information corresponding to the requirement input information.
S21: obtaining a target field, target problem data and historical dialogue data according to the requirement input information;
s22: performing data splicing on the target field, the target problem data and the historical dialogue data to obtain a problem attention vector;
s221: importing the target field, the target question data and the historical dialogue data into a pre-trained question selector;
s222: obtaining at least two candidate question sequences regarding the target field, target question data, and historical dialog data based on the question selector;
s223: receiving a candidate question selection instruction to determine one of the candidate questions about the candidate question;
s224: the problem interest vector corresponding to the candidate problem is obtained based on the candidate problem.
S23: and calling the pre-trained target sign extraction model based on the problem attention vector to obtain context information and prompt information about the problem attention vector.
S30: generating data query scheme information based on the demand input information, the context information corresponding to the demand input information and the prompt information, wherein the data query scheme information comprises query dimension information and query index information;
when the data query scheme comprises a plurality of query dimension information and query index information, grouping the plurality of query dimension information and query index information, and identifying each group of query dimension information and query index information.
The data query scheme information is in a JSON format. JSON (JavaScript Object Notation, JS object profile) is a lightweight data exchange format. It stores and presents data in a text format that is completely independent of the programming language based on a subset of ECMAScript (European Computer Manufacturers Association, js specification by the european computer institute). The compact and clear hierarchical structure makes JSON an ideal data exchange language. Is easy to read and write by people, is easy to analyze and generate by machines, and effectively improves the network transmission efficiency.
Vector databases are databases that are dedicated to storing and querying vectors, the vectors stored being from vectorization of text, speech, images, video, etc. Vector databases can handle more unstructured data (such as images and audio) than traditional databases. In machine learning and deep learning, data is typically represented in vector form.
Specifically, the data query scheme information is in JSON format, including:
judging the format of the query scheme information, and if the format of the query scheme information is JSON format, continuing to execute;
if the format of the query scheme information is not the JSON format, the required input information is continuously acquired from the interactive terminal.
The scheme is characterized in that the index and the dimension are divided into a plurality of sections, each section contains a model name and a scheme description, each section is marked with a serial number, such as 1/2,2/2 and the like, and later prompt words can require that the schemes with the same dimension need to be combined and returned.
In this embodiment, this step invokes the target feature extraction model, extracts the context according to the context extraction rule, invokes the large model interface with the context and the prompt word plus the user question, and generates the query schema JSON.
S40: and calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal.
And the dimension result information and the index result information are displayed on the interactive terminal in a visual dialogue report form.
And calling a data query service according to the dimension and index definition in the JSON, generating SQL corresponding to the query scheme by the query service, calling a database service to execute SQL and returning a data array, and returning the dimension and index column definition in the data and scheme to the front-end generation interface.
Generating a markdown table according to the data returned by the query service and the column definition, and generating an HTML page according to the markdown to display the query data result.
According to the method disclosed by the embodiment of the invention, the manual report development scheme can be changed into the collection and adjustment of training data, the report which is required to be actively found by the user is automatically generated according to the problem which is required to be used by the user, the problem is directly set up, the report interface is generated, the query scheme can be automatically adjusted according to the requirement of the user, and the development cost and the cost of learning and using of the user are reduced.
As shown in fig. 2, a second preferred embodiment of the present invention discloses an artificial intelligence report data based generation system 100, the system 100 comprising: dialog input module 110, information extraction module 120, query plan generation module 130, data information analysis module 140
The dialog box input module 110 is configured to obtain the required input information from the interactive terminal;
the dialog input module 110 may obtain the requirement input information from the visual dialog of the interactive terminal. The operator can input the above-mentioned demand input information by opening the intelligent assistant.
The information extraction module 120 is configured to invoke a pre-trained target feature extraction model according to the requirement input information to obtain context information and prompt information corresponding to the requirement input information;
the information extraction module 120 includes an extraction unit, a splicing unit, and a calling unit.
The extraction unit obtains a target field, target problem data and historical dialogue data according to the requirement input information;
the splicing unit performs data splicing on the target field, the target problem data and the historical dialogue data to obtain a problem attention vector;
specifically, the splicing unit imports the target field, the target question data and the historical dialogue data to a pre-trained question selector; obtaining at least two candidate question sequences regarding the target field, target question data, and historical dialog data based on the question selector; receiving a candidate question selection instruction to determine one of the candidate questions about the candidate question; the problem interest vector corresponding to the candidate problem is obtained based on the candidate problem.
And the calling unit calls the pre-trained target sign extraction model based on the problem attention vector to obtain context information and prompt information about the problem attention vector.
The query scheme generating module 130 is configured to generate data query scheme information based on the requirement input information, context information corresponding to the requirement input information, and prompt information, where the data query scheme information includes query dimension information and query index information;
the above-mentioned query scheme generation module 130 groups the plurality of query dimension information and query index information and identifies each group of query dimension information and query index information when the data query scheme includes the plurality of query dimension information and query index information.
The data query scheme information is in a JSON format. JSON (JavaScript Object Notation, JS object profile) is a lightweight data exchange format. It stores and presents data in a text format that is completely independent of the programming language based on a subset of ECMAScript (European Computer Manufacturers Association, js specification by the european computer institute). The compact and clear hierarchical structure makes JSON an ideal data exchange language. Is easy to read and write by people, is easy to analyze and generate by machines, and effectively improves the network transmission efficiency.
Vector databases are databases that are dedicated to storing and querying vectors, the vectors stored being from vectorization of text, speech, images, video, etc. Vector databases can handle more unstructured data (such as images and audio) than traditional databases. In machine learning and deep learning, data is typically represented in vector form.
Specifically, the data query scheme information is in JSON format, including:
judging the format of the query scheme information, and if the format of the query scheme information is JSON format, continuing to execute;
if the format of the query scheme information is not the JSON format, the required input information is continuously acquired from the interactive terminal.
The scheme is characterized in that the index and the dimension are divided into a plurality of sections, each section contains a model name and a scheme description, each section is marked with a serial number, such as 1/2,2/2 and the like, and later prompt words can require that the schemes with the same dimension need to be combined and returned.
In this embodiment, this step invokes the target feature extraction model, extracts the context according to the context extraction rule, invokes the large model interface with the context and the prompt word plus the user question, and generates the query schema JSON.
The data information analysis module 140 is configured to invoke a data query database based on the query dimension information and the query index information, so as to obtain corresponding dimension result information and index result information, and display the dimension result information and the index result information on the interactive terminal.
And the dimension result information and the index result information are displayed on the interactive terminal in a visual dialogue report form.
And calling a data query service according to the dimension and index definition in the JSON, generating SQL corresponding to the query scheme by the query service, calling a database service to execute SQL and returning a data array, and returning the dimension and index column definition in the data and scheme to the front-end generation interface.
Generating a markdown table according to the data returned by the query service and the column definition, and generating an HTML page according to the markdown to display the query data result.
The system disclosed by the embodiment of the invention can change the manual report development scheme into the collection and adjustment of training data, automatically generate the report which is required to be actively found by a user according to the problem which is required to be used by the user, directly put forward the problem, generate a report interface, automatically adjust the query scheme according to the requirement of the user, and reduce the development cost and the cost of learning and use of the user.
In another preferred embodiment of the present invention, a computer readable storage medium is disclosed, on which a computer program is stored, which when executed by a processor, implements the steps of a report data generation method based on artificial intelligence described above.
According to the method disclosed by the embodiment of the invention, the manual report development scheme can be changed into the collection and adjustment of training data by executing the method, the report use which is required to be actively found by a user is automatically generated according to the problem which is required to be used by the user, the problem is directly set up, a report interface is generated, the query scheme can be automatically adjusted according to the requirement of the user, and the development cost and the cost of user learning and use are reduced.
It should be noted that the computer storage media described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer storage medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.
In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.
The computer storage medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.
The computer storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to:
the technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the invention, which are described in detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
Claims (8)
1. The report data generation method based on the artificial intelligence is characterized by comprising the following steps of:
acquiring demand input information from an interactive terminal;
obtaining a target field, target problem data and historical dialogue data according to the requirement input information;
importing the target field, the target question data and the historical dialogue data into a pre-trained question selector;
obtaining at least two candidate question sequences regarding the target field, target question data, and historical dialog data based on the question selector;
receiving a candidate question selection instruction to determine one of the candidate questions about the candidate question;
obtaining a problem attention vector corresponding to the candidate problem based on the candidate problem;
invoking the pre-trained target sign extraction model based on the problem interest vector to obtain context information and prompt information about the problem interest vector;
generating data query scheme information based on the demand input information, the context information corresponding to the demand input information and the prompt information, wherein the data query scheme information comprises query dimension information and query index information;
and calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal.
2. The method for generating report data based on artificial intelligence according to claim 1, wherein the step of obtaining the required input information from the interactive terminal comprises the steps of:
and acquiring the required input information from a visual dialog of the interactive terminal.
3. The method for generating report data based on artificial intelligence according to claim 2, wherein the step of displaying the dimension result information and the index result information on the interactive terminal comprises the steps of:
and the dimension result information and the index result information are displayed on the interactive terminal in a visual dialogue report form.
4. The method for generating report data based on artificial intelligence according to claim 1, wherein generating data query plan information based on the demand input information, context information corresponding to the demand input information, and prompt information, the data query plan information including query dimension information and query index information comprises:
when the data query scheme information comprises a plurality of query dimension information and query index information, grouping the plurality of query dimension information and query index information, and identifying each group of query dimension information and query index information.
5. The report data generation method based on artificial intelligence according to claim 1, wherein the data query scheme information is in JSON format.
6. The method for generating report data based on artificial intelligence according to claim 5, wherein the data query scheme information is in JSON format, comprising:
judging the format of the data query scheme information, and if the format of the data query scheme information is JSON format, continuing to execute;
if the format of the data query scheme information is not the JSON format, the required input information is continuously acquired from the interactive terminal.
7. An artificial intelligence report data based generation system, comprising:
the dialog box input module is used for acquiring the required input information from the interactive terminal;
the information extraction module is used for obtaining a target field, target problem data and historical dialogue data according to the requirement input information; importing the target field, the target question data and the historical dialogue data into a pre-trained question selector; obtaining at least two candidate question sequences regarding the target field, target question data, and historical dialog data based on the question selector; receiving a candidate question selection instruction to determine one of the candidate questions about the candidate question; obtaining a problem attention vector corresponding to the candidate problem based on the candidate problem; invoking the pre-trained target sign extraction model based on the problem interest vector to obtain context information and prompt information about the problem interest vector;
the query scheme generation module is used for generating data query scheme information based on the requirement input information, the context information corresponding to the requirement input information and the prompt information, wherein the data query scheme information comprises query dimension information and query index information;
and the data information analysis module is used for calling a data query database based on the query dimension information and the query index information to acquire corresponding dimension result information and index result information, and displaying the dimension result information and the index result information on the interactive terminal.
8. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of a report data generation method based on artificial intelligence according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311641706.1A CN117370426B (en) | 2023-12-04 | 2023-12-04 | Report data generation method, system and storage medium based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311641706.1A CN117370426B (en) | 2023-12-04 | 2023-12-04 | Report data generation method, system and storage medium based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117370426A CN117370426A (en) | 2024-01-09 |
| CN117370426B true CN117370426B (en) | 2024-03-26 |
Family
ID=89389555
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311641706.1A Active CN117370426B (en) | 2023-12-04 | 2023-12-04 | Report data generation method, system and storage medium based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117370426B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148440A (en) * | 2019-03-29 | 2019-08-20 | 北京汉博信息技术有限公司 | A kind of medical information querying method |
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN111125145A (en) * | 2019-11-26 | 2020-05-08 | 复旦大学 | Automatic system for acquiring database information through natural language |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200117740A1 (en) * | 2018-10-10 | 2020-04-16 | Bouquet.ai | Data analytics platform with interactive natural language query interface |
-
2023
- 2023-12-04 CN CN202311641706.1A patent/CN117370426B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148440A (en) * | 2019-03-29 | 2019-08-20 | 北京汉博信息技术有限公司 | A kind of medical information querying method |
| CN110188163A (en) * | 2019-04-13 | 2019-08-30 | 上海策友信息科技有限公司 | Data intelligence processing system based on natural language |
| CN111125145A (en) * | 2019-11-26 | 2020-05-08 | 复旦大学 | Automatic system for acquiring database information through natural language |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117370426A (en) | 2024-01-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7877367B2 (en) | Computer method and apparatus for graphical inquiry specification with progressive summary | |
| US20190080370A1 (en) | Dynamic Scripts for Tele-Agents | |
| US11106683B2 (en) | System architecture for interactive query processing | |
| CN111414457A (en) | Intelligent question-answering method, device, equipment and storage medium based on federal learning | |
| WO2020215914A1 (en) | Information processing method, information processing device, and information processing system | |
| US20100179951A1 (en) | Systems and methods for mapping enterprise data | |
| US20150293947A1 (en) | Validating relationships between entities in a data model | |
| CN116737129B (en) | Supply chain control tower generation type large language model and construction method thereof | |
| US11461317B2 (en) | Method, apparatus, system, device, and storage medium for answering knowledge questions | |
| EP3905066A1 (en) | Intent recognition optimization processing method, apparatus, device, storage medium and computer program product | |
| CN110807044A (en) | Model dimension management method based on artificial intelligence technology | |
| CN112766936A (en) | Intelligent customer service processing method and system | |
| CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
| US20210319372A1 (en) | Ontologically-driven business model system and method | |
| CN117370426B (en) | Report data generation method, system and storage medium based on artificial intelligence | |
| AU2019300545A1 (en) | Machine intelligence for research and analytics (MIRA) system and method | |
| Jiao* et al. | Coordinating product and process variety for mass customized order fulfilment | |
| Rupnik et al. | Decision support system to support decision processes with data mining | |
| CN106021624B (en) | A kind of ETL model generating method and device | |
| Favela | Capture and dissemination of specialized knowledge in network organizations | |
| CN112000864A (en) | Intelligent matching and pushing system for policies | |
| CN109933672A (en) | Handle method, apparatus, electronic equipment and the computer readable storage medium of inquiry | |
| US20130089850A1 (en) | Method and Tool to Assess the Vitality of Technical Communities of Practice | |
| Das et al. | Customer Relationship Management in a Data-Driven World: Leveraging Data Mining Tools | |
| US20220075835A1 (en) | Feature recommendation based on user-generated content |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |