CN119149604B - AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium - Google Patents
AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium Download PDFInfo
- Publication number
- CN119149604B CN119149604B CN202411144788.3A CN202411144788A CN119149604B CN 119149604 B CN119149604 B CN 119149604B CN 202411144788 A CN202411144788 A CN 202411144788A CN 119149604 B CN119149604 B CN 119149604B
- Authority
- CN
- China
- Prior art keywords
- data
- database
- query
- error
- aigc
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/242—Query formulation
- G06F16/2433—Query languages
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application relates to the field of sales data statistics, in particular to a sales data statistics method, a sales data statistics system and a storage medium based on AIGC, which comprise reading wide table setting data, determining wide table data through the wide table setting data, reading query data, determining required wide table data through the query data and preset AIGC, determining SQL query sentences through the query data, AIGC and the required wide table data, determining grammar correctness of the SQL query sentences through a preset compiler and the SQL query sentences, determining semantic correctness of the SQL query sentences through AIGC and the SQL query sentences, determining result data through the SQL query sentences and the required wide table data, determining format data through AIGC and the result data, and determining output data through the format data and the result data.
Description
Technical Field
The application relates to the field of sales data statistics, in particular to a AIGC-based sales data statistics method, a AIGC-based sales data statistics system and a storage medium.
Background
Enterprises use order systems for sales management and efficiency improvement, and deposit sales data in the order systems. When enterprise staff or management layer needs to inquire and count sales data, the enterprise staff or management layer often needs to log in to a corresponding order system to find out corresponding functions, input inquiry conditions and inquire.
At present, a plurality of bins and a BI system are commonly used, data in each system are firstly extracted, the data are split into a plurality of data dimensions and stored in the plurality of bins, the data in the plurality of bins are read and called through the BI system, and statistical report generation is performed through a visual report component. However, if the user needs a new data dimension and the current number of bins does not have the data dimension, if the user does not grasp the related technology, the BI system cannot be used to perform secondary processing on the original data, so that the required data is generated, and a professional technician is required to use the BI system to develop the data, or to add the data dimension to the number of bins and then provide the data for the user. Therefore, users are required to have professional ability, whereas general enterprise staff (such as sales manager and business staff) do not have professional IT ability, and a plurality of bins need a large amount of development cost and post maintenance cost, resulting in high IT cost.
Disclosure of Invention
In order to solve the problem of user warehouse, the application provides a sales data statistics method, a sales data statistics system and a storage medium based on AIGC.
The application provides a sales data statistics method and a sales data statistics system based on AIGC, which adopt the following technical scheme:
A method of marketing data statistics based on AIGC, comprising:
Reading wide table setting data, and determining wide table data through the wide table setting data;
Reading query data, determining required wide table data through the query data and preset AIGC, and determining SQL query sentences through the query data, AIGC and the required wide table data;
determining grammar correctness of the SQL query statement through a preset compiler and the SQL query statement, and determining semantic correctness of the SQL query statement through the AIGC and the SQL query statement;
determining result data through the SQL query statement and the required wide table data;
And determining format data through AIGC and the result data, and determining output data through the format data and the result data.
By adopting the technical scheme, the design of the wide table is greatly simplified compared with the original design of a plurality of bins, secondary data processing is not required to be carried out by disassembling data dimension, workload is reduced, the relation between a data main body and dimension is not required to be designed, the complexity of a data structure and the requirement on storage space are greatly reduced, the wide table and the original data of each service system are directly mapped, a technical engineer can intuitively understand the data relation, development and operation and maintenance are simplified, the technical threshold required by a user is greatly reduced, the learning sinking cost is reduced, the user only needs to send a spoken language instruction, no system operation is required, the operation experience is greatly improved, the data statistics and formatting output is completed based on AIGC, and the random personalized data statistics requirement of the user can be met.
Optionally, after determining output data by the format data and the result data, the method includes:
And reading feedback data, and adjusting AIGC through the feedback data.
By adopting the technical scheme, after receiving the feedback data input after the output data representing the query result is received by the user, the AIGC is correspondingly trained on AIGC through the feedback data, so that the subsequent query result is more accurate, and the feedback effect is achieved.
Optionally, adjusting the AIGC by the feedback data includes:
If the read feedback data is unsatisfactory, storing the result data and the query data corresponding to the result data into a preset negative case library, after the result data is generated after the query data is read, retrieving the same query data from the negative case library, and if the result data corresponding to the retrieved query data is the result data, fine-tuning AIGC in a preset floating data range to obtain different result data.
By adopting the technical scheme, the wrong result data is recorded through the negative case library, and the output of the wrong result data is reduced by retrieving the negative case library, so that the accuracy is improved.
Optionally, adjusting the AIGC by the feedback data further includes:
the method comprises the steps of presetting correction frequency data, counting the frequency of reading query data, searching and directly outputting result data corresponding to the query data read at the time from a negative case base if the frequency of reading the query data is within the correction frequency data range, removing the result data and the query data corresponding to the result data from the negative case base if the read feedback data is satisfactory, and moving the result data and the query data corresponding to the result data to a preset error database if the read feedback data is unsatisfactory.
By adopting the technical scheme, the reproduction of the result data in the negative case library is realized through the correction frequency data, so that the probability of maliciously input feedback data of individual users interfering with AIGC training is reduced, the accuracy is improved, the misjudged result data is moved out of the negative case library, the truly problematic result data is further moved into an error database, and the probability of use reduction of users caused by reproduction of the truly problematic result data in the reproduction is also reduced.
Optionally, the preset error database includes:
The method comprises the steps of presetting error frequency data, determining database triggering data through the correction frequency data and the error frequency data, arranging a plurality of error databases in sequence, wherein each error database corresponds to one database triggering data, determining the next database triggering data through the last database triggering data and the error frequency data, reading result data from the corresponding error database when the frequency of reading the query data falls within the range of the database triggering data, if the read feedback data is satisfactory, moving the result data and the query data corresponding to the result data to the last error database, if the read feedback data is unsatisfactory, moving the result data and the query data corresponding to the result data to the next error database in the first error database, and if the read feedback data is unsatisfactory, moving the result data and the query data corresponding to the result data to the next error database.
By adopting the technical scheme, the probability that correct result data enter the error database due to multiple misjudgment is reduced, the correct result data in the error database are removed through reproduction, the accuracy is further improved, and the influence of personal initiative ideas of users on objective results is reduced.
Optionally, the default error database further includes:
When the result data corresponding to the query data in the negative case library is read and the read feedback data is unsatisfactory, determining the database trigger data through the correction frequency data and the error frequency data, searching whether the corresponding error database exists through the database trigger data, if so, moving the query data and the corresponding result data into the error database, if not, establishing the error database, giving the database trigger data to the established error database, and then moving the query data and the corresponding result data into the error database.
By adopting the technical scheme, the error database is automatically built, the workload of the user is reduced, and the technical threshold required by the user is further reduced.
Optionally, the default error database further includes:
When the result data corresponding to the query data in the error database is read and the read feedback data is unsatisfactory, determining new database trigger data through the database trigger data corresponding to the read error database and the error frequency data, searching whether the corresponding error database exists through the new database trigger data, if so, moving the query data and the corresponding result data into the next error database, if not, establishing the new error database, giving the new database trigger data into the newly established error database, and then moving the query data and the corresponding result data into the next error database.
By adopting the technical scheme, a plurality of error databases are automatically built, the probability of repeated error judgment result data is reduced, the accuracy is improved, and the probability of user experience reduction caused by reading the error data in the error databases is reduced.
The application provides a system for sales data statistics based on AIGC, which adopts the following technical scheme:
a system for AIGC-based sales data statistics, comprising:
the operation panel is used for carrying out man-machine interaction with a user, inputting the wide table setting data and the query data by the user, forming and outputting an operation signal;
The processor receives the operation signals, performs calculation processing on the signals and the data and outputs result data;
the database is used for storing data and signals and is called by the processor;
And the display module is used for receiving the result data and displaying the result data to a user for viewing.
Through adopting above-mentioned technical scheme, realize the human-computer interaction of user and treater through operating panel, carry out the storage of data and supply the treater to call and calculate through the database, output the result for the user and look over through display module, convenient and fast.
The application provides a computer readable storage medium, which adopts the following technical scheme:
A computer readable storage medium stores a computer program based on AIGC sales data statistics method that can be loaded and executed by a processor.
By adopting the technical scheme, the computer program is stored through the computer readable storage medium.
In summary, the present application includes at least one of the following beneficial technical effects:
1. The design of the wide table reduces the complexity and the space requirement of data storage and reduces the workload of data development and operation and maintenance.
2. The user only needs to send out a spoken language instruction, and no system operation is needed, so that the operation experience is greatly improved.
3. And based on AIGC, data statistics and formatting output are completed, and any personal data statistics requirement of a user can be met without any work of technicians.
Drawings
Fig. 1 is a flow chart of a sales data statistics method based on AIGC in an embodiment of the present application.
Fig. 2 is a flow chart after step S14.
Fig. 3 is a flow chart of step S5.
FIG. 4 is a block diagram of a system based on AIGC sales data statistics in accordance with an embodiment of the present application.
The reference numerals indicate 1, an operation panel, 2, a processor, 3, a database, and 4, a display module.
Detailed Description
The application is described in further detail below with reference to fig. 1-4.
The embodiment of the application discloses a sales data statistics method and system based on AIGC. Referring to fig. 1, the sales data statistics method based on AIGC includes the steps of:
S1, inputting broad table setting data by a user, reading the broad table setting data, and determining broad table data through the broad table setting data;
S11, inputting query data by a user, reading the query data, determining required wide table data through the query data and preset AIGC, and determining SQL query sentences through the query data, AIGC and the required wide table data;
S12, determining the grammar correctness of the SQL query statement through a preset compiler and the SQL query statement, and determining the semantic correctness of the SQL query statement through AIGC and the SQL query statement;
s13, determining result data through SQL query sentences and required wide table data;
s14, determining format data through AIGC and the result data, and determining output data through the format data and the result data.
For example, the user inputs the broad table setting data to set the broad table, for example, the broad table can be formulated according to each theme, all cross-system data related to the theme is stored in the broad table, for example, the broad table of the order theme comprises order detail data in a wholesale order system, customer detail information in a CRM customer relation management system, delivery detail data in a TMS logistics system and the like, at the moment, the inputted broad table setting data at least comprises three data (a, b and c), wherein a is the data of which subsystem, b is the data type, and c is the data quantity, for example (wholesale order system, ignition device and 1000);
The user inputs query data for query, for example, "i want to see sales condition in Shandong province of this year", in this embodiment, AIGC is trained and optimized for the cycle of continuously reading query data and obtaining result data, analysis is performed on the query data input by the user through AIGC, and all the corresponding wide table data (one or more) are combined with the wide table data to determine which corresponding wide table data (one or more) are needed, namely, the needed wide table data, so as to obtain SQL query sentences, then reliability query is performed on the grammar and the semantic correctness of the SQL query sentences through a compiler and AIGC, if the reliability query has a problem, the result is output to AIGC as an error generation result, so that AIGC is trained and optimized again for generating the SQL query sentences through AIGC until the reliability query is correct, then the SQL query is performed in the needed wide table data (one or more corresponding wide table data) determined before, so as to obtain the result data, and then the result data is output to the user according to the format data, for example, different shape charts, such as a corresponding bar graph, a cake graph, and the like are output to the user for viewing.
Referring to fig. 2, step S14 further includes the following steps:
S2, reading feedback data, and adjusting AIGC through the feedback data;
S21, if the read feedback data is unsatisfactory, storing the result data and query data corresponding to the result data into a preset negative case library, after the query data is read, generating the result data, retrieving the same query data from the negative case library, and if the result data corresponding to the retrieved query data is found, fine-tuning AIGC in a preset floating data range to obtain different result data.
For example, if the query data input by the user is "i want to see the sales situation in Shandong province of the present year", the result outputs a bar graph representing the sales situation in Shanxi province, the user inputs unsatisfactory feedback data, at this time, the query data is "i want to see the sales situation in Shandong province of the present year", the result data is two data of "the sales situation in Shanxi province" and is stored in the negative case base, and when the subsequent user inputs similar query data, for example, "i want to see the sales situation in Shandong province of the present year", "how the sales situation in Shandong province of the present year" and the like, the generated result data is still the "sales situation in Shanxi province", that is, the generated result data is the same as the result data in the negative case base, so that the algorithm parameters of AIGC are automatically adjusted, and if the result data is different from the result data in the negative case base, the result data is output to the user.
Referring to fig. 2, step S21 further includes the following steps:
S3, presetting correction frequency data, counting the frequency of reading query data, if the frequency of reading the query data is within the correction frequency data range, retrieving and directly outputting result data corresponding to the read query data from a negative case base, if the read feedback data is satisfactory, moving the result data and the query data corresponding to the result data from the negative case base, and if the read feedback data is unsatisfactory, moving the result data and the query data corresponding to the result data into a preset error database.
If the correction frequency data is 10000, namely after the query data are read every 10000 times, the query data input next time exist in the negative case base, the result data are read from the negative case base once, and if the query data input next time are not consistent in the negative case base, the process continues until the query data in the negative case base are consistent again;
The method comprises the steps of after 10000 times of inquiry data are input by a user, namely, the next input inquiry data are 'I want to see sales conditions in Shandong province of the present year', if the same recorded inquiry data are not retrieved from a negative case base, the result data are normally generated, if the same or similar inquiry data are retrieved from the negative case base, such as 'I want to see sales conditions in Shandong province of the present year', the corresponding result data are directly read from the negative case base, if a plurality of corresponding result data are recorded, one of the corresponding result data is randomly read, at the moment, if the feedback data input by the user are read to be satisfied, the fact that the user possibly has misjudgment before is shown, the result data and the inquiry data are moved out of the negative case base, and if the feedback data input by the user are read to be unsatisfied, the fact that the result data are indeed have problems is further confirmed, and the result data and the inquiry data are moved into an error database.
Referring to fig. 2, after step S3, the following steps are further included:
S4, presetting error frequency data, determining database triggering data through correction frequency data and error frequency data, arranging a plurality of error databases in sequence, wherein each error database corresponds to one database triggering data, determining the next database triggering data through the last database triggering data and the error frequency data, reading result data from the corresponding error database when the frequency of reading the query data falls within the range of the database triggering data, if the read feedback data is satisfactory, moving the result data and the query data corresponding to the result data to the last error database, if the read feedback data is unsatisfactory, moving the result data and the query data corresponding to the result data to the next error database, and if the read feedback data is unsatisfactory, moving the result data and the query data corresponding to the result data to the next error database.
If the error count data is 12345, the database trigger data is 10000+12345= 22345 obtained by calculating the correction count data and the error count data, in this embodiment, the addition is adopted, the error count data can be set to 2, and the calculation is performed by adopting a multiplication or secondary method with the correction count data, in this embodiment, the addition is convenient, the database trigger data represents that each 22345 times of reading the query data is adopted, the next time of reading the result data from the corresponding error database is performed, the number of error databases is a plurality of, in this embodiment, the database trigger data is 22345 to be assigned to the error count data 1, then the database trigger data of the error count data 1 is calculated to be 22345+12345= 34690, the database trigger data is assigned to the error count data 2, the database trigger data is 47035 to be assigned to the error count data 3, when the number of the error is set to be greater than the error count data of the error count data 3, and the number of the error is greater than the error count data is calculated to be avoided when the number of the error is greater than the error count data is set to be equal to the error count data 3, and the error count data is greater than the error count data is read from the error count data of the corresponding error count data of the number 4;
If the number of times of the read query data is 34690, the result data is read from the No. 2 error database when the query data is read next time, if the feedback data input by the user read at the time is satisfactory, the result data and the query data are moved from the No. 2 error database to the No. 1 error database, if the feedback data input by the user read at the time is unsatisfactory, the result data and the query data are moved from the No. 2 error database to the No. 3 error database;
If there is no error database with a later sequence, that is, the number of times of the query data is 47035, and the read feedback data is unsatisfactory, but there is no error database No. 4, the result data and the query data are not moved.
Referring to fig. 3, after step 4, the following steps are further included:
S5, when the result data corresponding to the query data in the negative case library is read and the read feedback data is unsatisfactory, determining database trigger data through correction frequency data and error frequency data, searching whether a corresponding error database exists through the database trigger data, if so, moving the query data and the corresponding result data into the error database, if not, establishing the error database, giving the database trigger data to the established error database, and then moving the query data and the corresponding result data into the error database;
S51, when the result data corresponding to the query data in the error database is read and the read feedback data is unsatisfactory, determining new database trigger data through database trigger data corresponding to the read error database and error frequency data, searching whether the corresponding error database exists through the new database trigger data, if so, moving the query data and the corresponding result data into the next error database, if not, establishing the new error database, giving the new database trigger data into the newly established error database, and moving the query data and the corresponding result data into the next error database.
For example, when the feedback data read from the negative case database is unsatisfactory, the database trigger data corresponding to the error database in which the correction frequency data and the error frequency data should be stored is 10000+12345= 22345, but when the error database does not exist, an error database can be automatically built by AIGC or other modes, the database trigger data is 22345 to the newly built error database, then the result data and the query data are moved into the error database, when the feedback data read from the error database No. 1 is unsatisfactory, the database trigger data corresponding to the error database in which the result data should be stored is 22345+12345= 34690, when the error database does not exist, an error database can be automatically built by AIGC or other modes, the database trigger data is 34690 to the newly built error database (No. 2) and then the error database is not found, and the number 3 is set to the error database No. 3, and the number 3 is not limited to the error database, and the number 3 is not found, and the number 3 is not limited to the error database.
The implementation principle of the sales data statistics method based on AIGC is that broad table data are established by inputting broad table setting data, then professional SQL query sentences are determined by means of AIGC through spoken input query data, then grammar and semantic correctness of the SQL query sentences are determined by means of a compiler and AIGC, then result data are obtained through the SQL query sentences and the broad table data, and output data are determined according to format data to a user.
Referring to fig. 4, the system based on AIGC's sales data statistics method includes an operation panel 1, a processor 2, a database 3 and a display module 4, in this embodiment, the operation panel 1 may use a device such as a key, a keyboard including a plurality of keys, or a touch screen for inputting data for human-computer interaction by a user, the display module 4 may use a device such as a digital screen, a display screen, or a touch screen for optical display, the user inputs data such as wide table setting data, query data, error number data, correction number data, and the like, signals through the operation panel 1, and forms an operation signal to output to the processor 2, the processor 2 invokes related data and signals from the database 3, and performs calculation processing on the operation signal to obtain result data, and the result data obtains output data according to format data and displays through the display module 4.
The processor 2 may include a central processing unit such as a CPU or an MPU, or a host system including hardware or software, which is built with the CPU or the MPU as a core. With the meter having the processor 2, one can freely control the meter by programming to operate as one wishes. The processor 2 may control local mass transfer, remote communication means, etc. via an internal protocol. Internal protocols refer broadly to all protocols within the same meter or within the same system that implement mutual communication or linking, including man-machine interaction protocols, software/hardware (interface) protocols, on-chip Bus (C-Bus) protocols, internal Bus (I-Bus) protocols, and the like. With the development of integrated circuit technology, some protocols belonging to external buses (E-Bus) are also attributed to internal protocols after the external buses (E-Bus) are integrated into a chip.
A computer readable storage medium stores a computer program based on AIGC sales data statistics method that can be loaded and executed by a processor.
The computer readable storage medium includes, for example, a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, etc., which can store program codes.
The above embodiments are not intended to limit the scope of the application, so that the equivalent changes of the structure, shape and principle of the application are covered by the scope of the application.
Claims (5)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411144788.3A CN119149604B (en) | 2024-08-20 | 2024-08-20 | AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411144788.3A CN119149604B (en) | 2024-08-20 | 2024-08-20 | AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119149604A CN119149604A (en) | 2024-12-17 |
| CN119149604B true CN119149604B (en) | 2025-03-14 |
Family
ID=93809124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411144788.3A Active CN119149604B (en) | 2024-08-20 | 2024-08-20 | AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119149604B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117992033A (en) * | 2024-01-31 | 2024-05-07 | 北京世纪互联宽带数据中心有限公司 | AIGC-based programming method, AIGC-based programming device, AIGC-based programming equipment and storage medium |
| CN118012901A (en) * | 2023-12-27 | 2024-05-10 | 度小满科技(北京)有限公司 | A structured query language generation method, device, equipment and readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116798254A (en) * | 2022-03-18 | 2023-09-22 | 北京百度网讯科技有限公司 | Intelligent interaction methods, devices, equipment and storage media |
| CN118093795B (en) * | 2024-04-28 | 2024-07-05 | 浪潮通用软件有限公司 | AIGC interaction analysis-oriented data preparation method, system, equipment and medium |
| CN118394912A (en) * | 2024-05-11 | 2024-07-26 | 美的网络信息服务(深圳)有限公司 | Question-answering processing method and device, electronic equipment and storage medium |
-
2024
- 2024-08-20 CN CN202411144788.3A patent/CN119149604B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118012901A (en) * | 2023-12-27 | 2024-05-10 | 度小满科技(北京)有限公司 | A structured query language generation method, device, equipment and readable storage medium |
| CN117992033A (en) * | 2024-01-31 | 2024-05-07 | 北京世纪互联宽带数据中心有限公司 | AIGC-based programming method, AIGC-based programming device, AIGC-based programming equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119149604A (en) | 2024-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108304378B (en) | Text similarity computing method, apparatus, computer equipment and storage medium | |
| WO2021073242A1 (en) | Index creation and data querying methods, apparatus and device | |
| CN109491989B (en) | Data processing method and device, electronic equipment and storage medium | |
| CN101208689B (en) | Method and apparatus for creating a language model and kana-kanji conversion | |
| US20240403344A1 (en) | Code retrieval method and apparatus based on large language model | |
| CN109710631A (en) | Auxiliary generates method, apparatus, equipment and the computer storage medium of SQL code | |
| CN111061758B (en) | Data storage method, device and storage medium | |
| US12135740B1 (en) | Generating a unified metadata graph via a retrieval-augmented generation (RAG) framework systems and methods | |
| CN119149604B (en) | AIGC-based sales data statistics method, AIGC-based sales data statistics system and storage medium | |
| CN114547117A (en) | Data processing method, device, equipment, storage medium and product | |
| US12361001B2 (en) | Accessing siloed data across disparate locations via a unified metadata graph systems and methods | |
| WO2025118788A1 (en) | Data query method and apparatus | |
| CN117609458A (en) | Graph result generation method and device based on man-machine conversation and related equipment | |
| EP3743833A1 (en) | Reducing latency and improving accuracy of work estimates utilizing natural language processing | |
| EP3822822A1 (en) | Relationship network generation method and device, electronic apparatus, and storage medium | |
| Ni et al. | ARTAR: Temporal association rule mining algorithm based on attribute reduction | |
| CN116882408B (en) | Construction method and device of transformer graph model, computer equipment and storage medium | |
| CN117951336B (en) | Enterprise-level data standard processing methods, devices, equipment and media | |
| JP6970867B1 (en) | Search device, search method, and program | |
| CN118885333A (en) | Database replication method and system for SaaS software | |
| CN118586668A (en) | Power grid operation ticket generation method, device, equipment, storage medium and program product | |
| CN118113595A (en) | Test case generation method, device, computer equipment and storage medium | |
| CN118798127A (en) | Method, device and computer equipment for generating structured query code statements | |
| CN118733046A (en) | Application code conversion method, device and computer equipment | |
| CN116975046A (en) | A data storage method, device and electronic equipment |
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 |