CN117216243A - Visual component interaction method and system based on template knowledge base in retail industry - Google Patents
Visual component interaction method and system based on template knowledge base in retail industry Download PDFInfo
- Publication number
- CN117216243A CN117216243A CN202311255028.5A CN202311255028A CN117216243A CN 117216243 A CN117216243 A CN 117216243A CN 202311255028 A CN202311255028 A CN 202311255028A CN 117216243 A CN117216243 A CN 117216243A
- Authority
- CN
- China
- Prior art keywords
- knowledge base
- chart
- user
- module
- template
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000003993 interaction Effects 0.000 title claims abstract description 25
- 230000000007 visual effect Effects 0.000 title claims abstract description 24
- 239000003795 chemical substances by application Substances 0.000 claims description 50
- 238000012790 confirmation Methods 0.000 claims description 26
- 230000011218 segmentation Effects 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 239000012634 fragment Substances 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 239000013589 supplement Substances 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 33
- 230000008569 process Effects 0.000 abstract description 12
- 238000000605 extraction Methods 0.000 abstract description 4
- 230000002452 interceptive effect Effects 0.000 abstract description 3
- 230000008859 change Effects 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
Abstract
The application relates to a visual component interaction method and a visual component interaction system based on a template knowledge base in retail industry, which utilize a large language knowledge base model to meet user demands, automatically perform demand understanding and key index extraction matching, and analyze charts through the industry knowledge base. The user only describes the analysis scene or the target through natural language, and the system can give out more analysis visual angle suggestions and complete analysis report templates when automatically generating the chart result, so that the system has the characteristics of more intelligence and automation, and helps the user to discover hidden information and rules in the data more quickly. At the same time, the user can also use the interactive control or natural language to change the corresponding chart so as to quickly search the data. In the process of generating new demands on business parties, a data analyst can generate examples in the form of system session on the spot, so that subsequent ambiguity is avoided, the rework rate is reduced to below 10%, and the overall business analysis efficiency of an enterprise is improved.
Description
Technical Field
The application relates to the technical field of retail industry, in particular to a construction method of a template knowledge base of retail industry, the template knowledge base of retail industry, a visual component interaction method and system based on the template knowledge base of retail industry and electronic equipment.
Background
The data analysis and exploration system can be used for business data analysis and provides analysis report forms of business data for merchants, so that the merchants can analyze business behaviors and customer behaviors conveniently and adjust business.
In the traditional business data analysis and use process, the effective temporary demand response and exploration analysis functions are also lacking. This is because conventional business data analysis tools only provide data processing and graphic functions, and specific analysis ideas still rely on the manual experience of an analyst for design construction, so the process takes about 50% -60% of the working time of a data analyst, including additional demands for demand communication, text confirmation, billboard fabrication, conclusion synchronization and initiation, or possibly rework, and rework generated under the demands may often take more than 80% of the processing demands. Thus, the analysis process is longer in period, and the "invalid work" generated during the analysis process gradually reduces the overall project efficiency.
Disclosure of Invention
In order to solve the problems, the application provides a construction method of a template knowledge base in retail industry, the template knowledge base in retail industry, a visual component interaction method and system based on the template knowledge base in retail industry and electronic equipment.
In one aspect of the present application, a method for constructing a template knowledge base in retail industry is provided, comprising the following steps:
collecting an original knowledge record of the service;
extracting the text from the original knowledge record, and segmenting the extracted text by a word segmentation device;
word Embedding-Embedding is carried out on the segmented words of the segmented content, and vectors of the vectorized representation of the segmented words are obtained;
and storing the vector and the corresponding original knowledge record in a vector database in a key-value form to obtain a template knowledge base of retail industry.
In another aspect, the application provides a retail industry template knowledge base, which is obtained by adopting the construction method of the retail industry template knowledge base.
On the other hand, the application also provides a visual component interaction method based on the template knowledge base of the retail industry, which comprises the following steps:
collecting business consultation problems input by a user and sending the business consultation problems to an agent module;
the agent module is used for disconnecting the problem, extracting key word segments from the problem, and matching the extracted key word segments with fields in a preset data set;
after the matching is successful, service index searching is initiated to a service knowledge base, and knowledge corresponding to the problem is returned to the proxy module after the service knowledge base searching;
the agent module integrates the problems and the corresponding knowledge, and sends the integrated problems and the corresponding knowledge to the generation module, and the generation module obtains parameters of the generated chart;
the generation module generates the parameters according to the integrated problems and the corresponding knowledge, returns the parameters to the proxy module, generates a chart corresponding to the problems according to the parameters by the proxy module, and sends the chart to a user for confirmation;
after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
As an optional embodiment of the present application, optionally, when matching the extracted keyword with a field in the preset dataset, further includes:
if the keyword is not matched with the field in the preset data set, the matching result is fed back to the user, and the user is reminded of not supporting the business consultation problem input by the user.
As an optional embodiment of the present application, optionally, before the agent module sends the chart to the user for confirmation, the method further includes:
the agent module sends the integrated problems and the corresponding knowledge to the template knowledge base;
in the template knowledge base, similar scene retrieval is carried out to obtain corresponding similar scenes, and the obtained similar scenes are returned to the proxy module;
and the agent module supplements the example information in the chart according to the similar scene, and sends the chart to a user for secondary confirmation after supplementing.
As an optional embodiment of the present application, optionally, after the user performs the secondary confirmation, the method further includes:
the agent module integrates the chart examples of the secondary confirmation of the user, sends the integrated chart examples to the generation module, and acquires parameters of the regenerated chart from the generation module;
and the generation module regenerates the parameters according to the integrated chart examples, returns the parameters to the proxy module, regenerates the chart corresponding to the problem according to the parameters by the proxy module, and sends the chart to a user for secondary confirmation.
As an optional embodiment of the present application, optionally, after the user performs the secondary confirmation, the method further includes:
and the agent module stores the chart secondarily confirmed by the user in the template knowledge base in a word segmentation vectorization mode, and returns the chart to the front end for display.
In another aspect of the present application, a system for implementing the visual component interaction method based on the retail industry template knowledge base is also provided, including:
the agent module is used for collecting business consultation problems input by a user, disconnecting the problems, extracting key word fragments from the problems, and matching the extracted key word fragments with fields in a preset data set; after successful matching, initiating a service index search to a service knowledge base;
the service knowledge base is used for searching service indexes, and after searching, the knowledge corresponding to the problem is returned to the proxy module;
the agent module is also used for integrating the problems and the corresponding knowledge, and sending the integrated problems and the corresponding knowledge to the generation module, and acquiring parameters of the generated chart from the generation module;
the generation module is used for generating the parameters according to the integrated problems and the corresponding knowledge and returning the parameters to the agent module;
the agent module is also used for generating a chart corresponding to the problem according to the parameters and sending the chart to a user for confirmation; after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
In another aspect, the present application further provides an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the visual component interaction method based on the retail industry template knowledge base when executing the executable instructions.
The application has the technical effects that:
according to the application, the knowledge base corpus of retail industry is combined, the large language knowledge base model is utilized to meet the user demands, the demand understanding and the key index extraction matching are automatically carried out, and the analysis chart result generation and the related data insight suggestion are carried out through the industry knowledge base.
The user can describe the analysis scene or target only through natural language, and the system can give out more analysis visual angle suggestions and complete analysis report templates while automatically generating the chart result. Compared with the traditional commercial data analysis tool (only providing data processing and chart functions, and the specific analysis thought still depends on the manual experience of an analyst to design and build), the system has the characteristics of more intelligence and automation, and helps users to discover hidden information and rules in data more quickly. At the same time, the user can also use the interactive control or natural language to change the corresponding chart so as to quickly search the data.
By using the scheme, a new demand process can be generated on the business side, a data analyst can generate examples in the form of a system session on the spot, subsequent ambiguity is avoided, and the rework rate is reduced to below 10%. Even, the service personnel can quickly generate the chart to be analyzed through the session by themselves, so that the whole analysis link is quickened. The need for trivial disposability can also be solved by session form during meeting or talking without additional time exploration, and the need for repeated wheel making can be avoided if the historical existing analysis scene can be quickly searched.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features and aspects of the application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram of an implementation flow of a method for constructing a template knowledge base for the retail industry of the present application;
FIG. 2 illustrates a timing diagram for a visual component interaction method based on a retail industry template knowledge base of the present application;
fig. 3 shows a schematic application diagram of the electronic device of the application.
Detailed Description
Various exemplary embodiments, features and aspects of the application will be described in detail below with reference to the drawings. In the drawings, like reference numbers indicate identical or functionally similar elements. Although various aspects of the embodiments are illustrated in the accompanying drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
In addition, numerous specific details are set forth in the following description in order to provide a better illustration of the application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, well known means, elements and circuits have not been described in detail so as not to obscure the present application.
Example 1
As shown in fig. 1, in one aspect of the present application, a method for constructing a template knowledge base in retail industry is provided, including the following steps:
collecting an original knowledge record of the service;
extracting the text from the original knowledge record, and segmenting the extracted text by a word segmentation device;
word Embedding-Embedding is carried out on the segmented words of the segmented content, and vectors of the vectorized representation of the segmented words are obtained;
and storing the vector and the corresponding original knowledge record in a vector database in a key-value form to obtain a template knowledge base of retail industry.
The scheme combines the knowledge base corpus of retail industry to generate a large language knowledge base model.
And then, the large language knowledge base model is utilized to meet the demands of users, the demands are automatically understood, the key indexes are extracted and matched, and analysis chart result generation and related data insight suggestion are carried out through the industry knowledge base.
The industry general knowledge is extracted to form a business template knowledge base (see for details the template knowledge base in fig. 2, which only stores the business data set and the business index search).
Retail industry analysis templates are summarized by precipitation, while a wide variety of analysis charts and reports are created by business personnel in the BI platform. These charts, reports and templates reflect business person understanding and analysis ideas of the enterprise data and are stored in the system in the form of metadata. Metadata refers to some basic information of the chart, such as: chart names, chart references fields, business field meanings and calculation modes, etc.
And constructing a business template knowledge base, namely vectorizing and storing metadata.
The method specifically comprises the following steps:
step 1: collecting platform metadata and remote solution general metadata (original business knowledge records containing questions and answers between customers and merchants), wherein the data mainly comprise business index names, index calculation logic descriptions and index calculation examples;
step 2: extracting the text of the metadata, and performing word segmentation and slicing through a word segmentation device (token), so that the original text knowledge can be split into a plurality of relatively independent knowledge points with certain length and relation;
step 3: the segmented content is subjected to word Embedding (Embedding) to obtain vectorized representation, so that similarity searching can be performed when a user performs similar scene analysis, and meanwhile, a BM25 algorithm is also used in searching, which is an algorithm for evaluating the relevance of search words and documents and can be understood as keyword searching, because besides similarity matching, the service indexes of some cores also need to be precisely matched;
step 4: the vectors and the original knowledge after the Embedding are stored in a vector database in a key-value form.
When the service personnel make analysis decisions, the service template knowledge base is automatically matched with corresponding service background knowledge from the vector database through the requirement description system to generate a corresponding chart report, and a similar analysis chart is matched with the template knowledge base to serve as search recommendation, so that decision landing is quickened.
Example 2
In another aspect of the present application, a template knowledge base in retail industry is provided, which is obtained by using the method for constructing a template knowledge base in retail industry in embodiment 1.
See the description of example 1 for details.
Example 3
Based on the principle of embodiment 1, as shown in fig. 2, in another aspect of the present application, a visual component interaction method based on a template knowledge base of retail industry is further provided, which includes the following steps:
collecting business consultation problems input by a user and sending the business consultation problems to an agent module;
the agent module is used for disconnecting the problem, extracting key word segments from the problem, and matching the extracted key word segments with fields in a preset data set;
after the matching is successful, service index searching is initiated to a service knowledge base, and knowledge corresponding to the problem is returned to the proxy module after the service knowledge base searching;
the agent module integrates the problems and the corresponding knowledge, and sends the integrated problems and the corresponding knowledge to the generation module, and the generation module obtains parameters of the generated chart;
the generation module generates the parameters according to the integrated problems and the corresponding knowledge, returns the parameters to the proxy module, generates a chart corresponding to the problems according to the parameters by the proxy module, and sends the chart to a user for confirmation;
after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
As shown in fig. 2, the system mainly includes a preprocessing layer, a chart generation layer, and a chart retrieval layer.
When a user inputs related demands through natural language, firstly, a preprocessing layer is used for carrying out demand disassembly and key index extraction matching, then related business knowledge is called in a platform business template knowledge base, and then problems and knowledge are integrated. The second step is to enter a chart generation layer, schedule a platform private domain calculation engine and quickly generate a data chart required by the user, and the step can respond to the requirement of the user on front-end interaction timely and accurately. And meanwhile, the third step is to match the similarity of the related analysis scenes in the template knowledge base through a chart retrieval layer and concurrent tasks, so as to recommend more analysis view charts and reports, and achieve the purpose of active exploration.
And in the preprocessing layer link. Assume that when the user front-end inputs a question: "what are the new and old guests in each channel monthly in this year? "the problem enters into the agent module, keyword extraction is carried out by the agent: "channel", "new guest", "old guest". The agent matches the extracted segmentation words with the fields in the data set, if the data fields do not have the fields of 'new guest' and 'old guest', the agent initiates a query to the business template knowledge base module to acquire the definition thereof, and then enters into a 'chart generation layer' link.
In the chart generation layer link. When the business template knowledge base is matched, the agent module integrates the problems and the knowledge, the integrated content is integrally sent to the generation module for generating chart parameters, the generated parameters are secondarily confirmed through the agent, the JSON format of the generated parameters is uniformly corrected, and the result is transmitted back to the front end, so that a related chart aiming at the user problem is displayed. If the user carries out confirmation feedback at the front end, the generated chart is vectorized through a knowledge base generation path and stored in a template knowledge base for subsequent session inquiry.
As an optional embodiment of the present application, optionally, when matching the extracted keyword with a field in the preset dataset, further includes:
if the keyword is not matched with the field in the preset data set, the matching result is fed back to the user, and the user is reminded of not supporting the business consultation problem input by the user.
If all the key words are not matched, the front end is directly fed back to not support the problem, which means that the problem asked by the user is irrelevant to the data set of the current working area, and the step is mainly to establish connection with the user in the early stage of interaction and fast pull-through cognition.
Entering a chart retrieval layer link.
As an optional embodiment of the present application, optionally, before the agent module sends the chart to the user for confirmation, the method further includes:
the agent module sends the integrated problems and the corresponding knowledge to the template knowledge base;
in the template knowledge base, similar scene retrieval is carried out to obtain corresponding similar scenes, and the obtained similar scenes are returned to the proxy module;
and the agent module supplements the example information in the chart according to the similar scene, and sends the chart to a user for secondary confirmation after supplementing.
After the agent module integrates the problems and the knowledge, concurrent tasks transmit the integrated contents to a template knowledge base for searching to obtain a similar analysis scene, and then the similar analysis scene is returned to the agent module for supplementing the chart example information and then transmitted to the front end for selection by a user.
As an optional embodiment of the present application, optionally, after the user performs the secondary confirmation, the method further includes:
the agent module integrates the chart examples of the secondary confirmation of the user, sends the integrated chart examples to the generation module, and acquires parameters of the regenerated chart from the generation module;
and the generation module regenerates the parameters according to the integrated chart examples, returns the parameters to the proxy module, regenerates the chart corresponding to the problem according to the parameters by the proxy module, and sends the chart to a user for secondary confirmation.
The above-mentioned mode of reprocessing parameters and regenerating a graph can be referred to as the above-mentioned graph generating process.
As an optional embodiment of the present application, optionally, after the user performs the secondary confirmation, the method further includes:
and the agent module stores the chart secondarily confirmed by the user in the template knowledge base in a word segmentation vectorization mode, and returns the chart to the front end for display.
If the user selects some chart examples, the method enters a generating module to generate relevant parameters, and the method is similar to a chart generating process, and finally the generated content is returned to the front end again for result display.
The system interaction is developed in a natural language dialogue form, so that the system can store dialogue states without worrying about disappearance of historical dialogue records due to exit or page refreshing, and can continue to develop data exploration at any time following the last analysis thought. In addition, in the subsequent interactive dialogue between the customer user and the merchant, if the previous analysis result is to be reproduced in the analysis process, the previous analysis chart can be dispatched again through a one-key backtracking function.
Therefore, by using the scheme, a new demand process can be generated on the business side, a data analyst can generate examples in the form of a system session on the spot, subsequent ambiguity is avoided, and the rework rate is reduced to below 10%. Even, the service personnel can quickly generate the chart to be analyzed through the session by themselves, so that the whole analysis link is quickened. The need for trivial disposability can also be solved by session form during meeting or talking without additional time exploration, and the need for repeated wheel making can be avoided if the historical existing analysis scene can be quickly searched.
It should be apparent to those skilled in the art that implementing all or part of the above-described embodiments may be accomplished by computer programs to instruct related hardware, and the programs may be stored in a computer readable storage medium, which when executed may include the processes of the embodiments of the controls described above. It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiments may be accomplished by computer programs to instruct related hardware, and the programs may be stored in a computer readable storage medium, which when executed may include the processes of the embodiments of the controls described above. The storage medium may be a magnetic disk, an optical disc, a Read-only memory (ROM), a random access memory (RandomAccessMemory, RAM), a flash memory (flash memory), a hard disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
Example 4
Based on the implementation principle of embodiment 1, in another aspect, the application further provides a system for implementing the visual component interaction method based on the retail industry template knowledge base, which comprises the following steps:
the agent module is used for collecting business consultation problems input by a user, disconnecting the problems, extracting key word fragments from the problems, and matching the extracted key word fragments with fields in a preset data set; after successful matching, initiating a service index search to a service knowledge base;
the service knowledge base is used for searching service indexes, and after searching, the knowledge corresponding to the problem is returned to the proxy module;
the agent module is also used for integrating the problems and the corresponding knowledge, and sending the integrated problems and the corresponding knowledge to the generation module, and acquiring parameters of the generated chart from the generation module;
the generation module is used for generating the parameters according to the integrated problems and the corresponding knowledge and returning the parameters to the agent module;
the agent module is also used for generating a chart corresponding to the problem according to the parameters and sending the chart to a user for confirmation; after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
The functions and interactions of the above modules are described in detail in embodiment 3.
The modules or steps of the application described above may be implemented in a general-purpose computing system, they may be centralized in a single computing system, or distributed across a network of computing systems, where they may alternatively be implemented in program code executable by a computing system, where they may be stored in a memory system and executed by a computing system, where they may be separately fabricated into individual integrated circuit modules, or where multiple modules or steps within them may be fabricated into a single integrated circuit module. Thus, the present application is not limited to any specific combination of hardware and software.
Example 5
As shown in fig. 3, in still another aspect, the present application further provides an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the visual component interaction method based on the retail industry template knowledge base when executing the executable instructions.
The electronic device of the embodiment of the application comprises a processor and a memory for storing instructions executable by the processor. Wherein the processor is configured to implement any of the aforementioned visual component interaction methods based on a retail industry template knowledge base when executing the executable instructions.
Here, it should be noted that the number of processors may be one or more. Meanwhile, in the electronic device according to the embodiment of the application, an input system and an output system may be further included. The processor, the memory, the input system, and the output system may be connected by a bus, or may be connected by other means, which is not specifically limited herein.
The memory is a computer-readable storage medium that can be used to store software programs, computer-executable programs, and various modules, such as: the embodiment of the application discloses a program or a module corresponding to a visual component interaction method based on a template knowledge base in retail industry. The processor executes various functional applications and data processing of the electronic device by running software programs or modules stored in the memory.
The input system may be used to receive an input digital or signal. Wherein the signal may be a key signal generated in connection with user settings of the device/terminal/server and function control. The output system may include a display device such as a display screen.
The foregoing description of embodiments of the application has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (9)
1. The construction method of the template knowledge base in the retail industry is characterized by comprising the following steps:
collecting an original knowledge record of the service;
extracting the text from the original knowledge record, and segmenting the extracted text by a word segmentation device;
word Embedding-Embedding is carried out on the segmented words of the segmented content, and vectors of the vectorized representation of the segmented words are obtained;
and storing the vector and the corresponding original knowledge record in a vector database in a key-value form to obtain a template knowledge base of retail industry.
2. A retail industry template knowledge base obtained by the method of constructing a retail industry template knowledge base of claim 1.
3. The visual component interaction method based on the retail industry template knowledge base is characterized by comprising the following steps of:
collecting business consultation problems input by a user and sending the business consultation problems to an agent module;
the agent module is used for disconnecting the problem, extracting key word segments from the problem, and matching the extracted key word segments with fields in a preset data set;
after the matching is successful, service index searching is initiated to a service knowledge base, and knowledge corresponding to the problem is returned to the proxy module after the service knowledge base searching;
the agent module integrates the problems and the corresponding knowledge, and sends the integrated problems and the corresponding knowledge to the generation module, and the generation module obtains parameters of the generated chart;
the generation module generates the parameters according to the integrated problems and the corresponding knowledge, returns the parameters to the proxy module, generates a chart corresponding to the problems according to the parameters by the proxy module, and sends the chart to a user for confirmation;
after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
4. A visual component interaction method based on a retail industry template knowledge base as recited in claim 3, further comprising, when matching the extracted keyword with a field in a preset dataset:
if the keyword is not matched with the field in the preset data set, the matching result is fed back to the user, and the user is reminded of not supporting the business consultation problem input by the user.
5. The visual component interaction method based on a retail industry template knowledge base of claim 3, further comprising, before the agent module sends the chart to a user for confirmation:
the agent module sends the integrated problems and the corresponding knowledge to the template knowledge base;
in the template knowledge base, similar scene retrieval is carried out to obtain corresponding similar scenes, and the obtained similar scenes are returned to the proxy module;
and the agent module supplements the example information in the chart according to the similar scene, and sends the chart to a user for secondary confirmation after supplementing.
6. The visual component interaction method based on a retail industry template knowledge base of claim 5, further comprising, after the secondary confirmation by the user:
the agent module integrates the chart examples of the secondary confirmation of the user, sends the integrated chart examples to the generation module, and acquires parameters of the regenerated chart from the generation module;
and the generation module regenerates the parameters according to the integrated chart examples, returns the parameters to the proxy module, regenerates the chart corresponding to the problem according to the parameters by the proxy module, and sends the chart to a user for secondary confirmation.
7. The visual component interaction method based on a retail industry template knowledge base of claim 6, further comprising, after the secondary confirmation by the user:
and the agent module stores the chart secondarily confirmed by the user in the template knowledge base in a word segmentation vectorization mode, and returns the chart to the front end for display.
8. A system for implementing the visual component interaction method based on a retail industry template knowledge base of any of claims 3-7, comprising:
the agent module is used for collecting business consultation problems input by a user, disconnecting the problems, extracting key word fragments from the problems, and matching the extracted key word fragments with fields in a preset data set; after successful matching, initiating a service index search to a service knowledge base;
the service knowledge base is used for searching service indexes, and after searching, the knowledge corresponding to the problem is returned to the proxy module;
the agent module is also used for integrating the problems and the corresponding knowledge, and sending the integrated problems and the corresponding knowledge to the generation module, and acquiring parameters of the generated chart from the generation module;
the generation module is used for generating the parameters according to the integrated problems and the corresponding knowledge and returning the parameters to the agent module;
the agent module is also used for generating a chart corresponding to the problem according to the parameters and sending the chart to a user for confirmation; after the user confirms, the agent module stores the chart in the template knowledge base in a word segmentation vectorization mode for subsequent session inquiry.
9. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the visual component interaction method of any one of claims 3-7 based on a retail industry template knowledge base when executing the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311255028.5A CN117216243A (en) | 2023-09-27 | 2023-09-27 | Visual component interaction method and system based on template knowledge base in retail industry |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311255028.5A CN117216243A (en) | 2023-09-27 | 2023-09-27 | Visual component interaction method and system based on template knowledge base in retail industry |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117216243A true CN117216243A (en) | 2023-12-12 |
Family
ID=89035196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311255028.5A Pending CN117216243A (en) | 2023-09-27 | 2023-09-27 | Visual component interaction method and system based on template knowledge base in retail industry |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216243A (en) |
-
2023
- 2023-09-27 CN CN202311255028.5A patent/CN117216243A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20180129976A1 (en) | Machine learning data analysis system and method | |
| US11741384B2 (en) | Adaptable systems and methods for discovering intent from enterprise data | |
| CN110727761B (en) | Object information acquisition method and device and electronic equipment | |
| CN110807566A (en) | Artificial intelligence model evaluation method, device, equipment and storage medium | |
| US11907659B2 (en) | Item recall method and system, electronic device and readable storage medium | |
| WO2022197669A1 (en) | End-to-end machine learning pipelines for data integration and analytics | |
| Abdul‐Rahman et al. | Constructive visual analytics for text similarity detection | |
| WO2019060520A1 (en) | Method, apparatus, and computer-readable media for customer interaction semantic annotation and analytics | |
| KR102117287B1 (en) | Method and apparatus of dialog scenario database constructing for dialog system | |
| WO2016113648A1 (en) | Database statistical histogram forecasting | |
| CN112949973A (en) | AI-combined robot process automation RPA process generation method | |
| CN113362045A (en) | Conference schedule generation method and device, electronic equipment and readable storage medium | |
| Groher et al. | Leveraging AI-based decision support for opportunity analysis | |
| CN117216243A (en) | Visual component interaction method and system based on template knowledge base in retail industry | |
| CN110062112A (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN115686447A (en) | Intelligent recommendation method for application creation, and creation method, device and system for application | |
| CN114428881A (en) | Method and device for pushing media asset video, storage medium and electronic equipment | |
| WO2021071428A1 (en) | System and method for innovation, creativity, and learning as a service | |
| US20240037344A1 (en) | Generating conversational ai response suggestions | |
| CN117473457B (en) | Big data mining method and system based on digital service | |
| CN112182358B (en) | Method and system for creating multimedia push plan | |
| US11170045B2 (en) | Method and system for interactive search indexing | |
| CN116863922A (en) | Method, device, development platform and storage medium for speech transcription | |
| CN117272048A (en) | Data set processing method and device based on machine learning platform | |
| KR20240053911A (en) | Method and system for AI collaboration service based on source code automatic generation system |
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 |