CN118037318B - AI purchasing business analysis device and method based on supply chain management - Google Patents
AI purchasing business analysis device and method based on supply chain management Download PDFInfo
- Publication number
- CN118037318B CN118037318B CN202410437138.1A CN202410437138A CN118037318B CN 118037318 B CN118037318 B CN 118037318B CN 202410437138 A CN202410437138 A CN 202410437138A CN 118037318 B CN118037318 B CN 118037318B
- Authority
- CN
- China
- Prior art keywords
- analysis
- data
- text
- corpus
- purchase
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 182
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013068 supply chain management Methods 0.000 title claims abstract description 26
- 239000000463 material Substances 0.000 claims description 21
- 230000008520 organization Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000003058 natural language processing Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 26
- 238000007405 data analysis Methods 0.000 description 8
- 238000010276 construction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000012925 reference material Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012384 transportation and delivery Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/604—Tools and structures for managing or administering access control systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
- G06F40/295—Named entity recognition
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioethics (AREA)
- Evolutionary Biology (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Automation & Control Theory (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides an AI purchasing business analysis device and method based on supply chain management, and relates to the technical field of artificial intelligence. According to the application, a corresponding purchasing analysis big database is generated based on purchasing business original data, after the demand text information of a user is acquired, entities, relations or events carried in the demand text information are understood to generate corresponding demand characteristics, then a preset template is selected according to the demand characteristics, corresponding analysis corpus is matched, and corresponding target index data is called from the purchasing analysis big database, so that an analysis text composed of the preset template, the analysis corpus and the target index data is generated. Thus, the problems of inaccuracy, low efficiency and high cost of the traditional purchasing analysis can be improved.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an AI purchasing business analysis device and method based on supply chain management.
Background
The supply chain is the process of creating and delivering value by taking enterprise core products or services as carriers, and the process from the production of the products or services to the delivery of consumers is completed by the cooperation of various enterprises such as suppliers, manufacturers, distributors and the like in different stages and in different forms.
With the rapid development of economy and information technology, and the popularization of AI (ARTIFICIAL INTELLIGENCE ) technology in various industries, the conventional business model is greatly impacted. In the case of modern business models, competition among enterprises is competition of a supply chain, more and more enterprises realize full-flow management of supply chain management through a digital platform, meanwhile, as continuous operation of the digital platform generates a large amount of business data, an enterprise purchase analysis summary based on real-time data of the platform is often required regularly or irregularly for an enterprise business decision maker to guide operation decisions of the enterprises. Then a summary of on-demand, timely, accurate, comprehensive and quantitative purchasing analysis directly affects the decision-making efficiency and effect of the enterprise.
At present, the enterprise purchase data analysis summary in the field of supply chains still depends on manual arrangement, the statistical report of a conventional digital platform can provide an auxiliary means, but a great deal of manpower and time cost are required to be consumed, and the problems of report data errors, untimely report data, incomplete summary, incomplete analysis, inconsistent analysis summary and the like can occur, so that how to automatically generate an accurate, comprehensive, quantized and standardized purchase data analysis summary according to the requirements of users becomes a problem to be solved in the field of supply chains.
Disclosure of Invention
Accordingly, an objective of the embodiments of the present application is to provide an AI purchasing business analysis device and method based on supply chain management, which can solve the problems of inaccuracy, low efficiency and high cost of the conventional purchasing analysis.
In order to achieve the technical purpose, the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides an AI procurement services analysis apparatus based on supply chain management, the apparatus including:
the first acquisition module is used for acquiring the raw data of the purchasing business;
The first generation module is used for generating index data corresponding to the purchasing business original data according to the purchasing business original data, and taking the purchasing business original data and the index data as a purchasing analysis big database;
the second acquisition module is used for acquiring the text information of the user's demands;
The identification module is used for identifying the entity, the relation or the event carried in the demand text information so as to generate corresponding demand characteristics according to the entity, the relation or the event carried in the demand text information;
The second generation module is used for selecting a preset template corresponding to the demand characteristics according to the demand characteristics and matching analysis corpus corresponding to the demand characteristics from a preset purchase analysis corpus;
And the third generation module is used for calling target index data corresponding to the analysis corpus from the purchase analysis big database so as to generate an analysis text formed by the preset template, the analysis corpus and the target index data.
With reference to the first aspect, in some optional embodiments, the apparatus further includes a preprocessor, where the preprocessor is configured to preprocess the raw purchase service data, so as to perform data cleaning on the raw purchase service data, and obtain preprocessed data;
The first generation module is further configured to generate, according to the preprocessed data, the index data corresponding to the preprocessed data, and use the preprocessed data and the index data as the purchase analysis big database.
With reference to the first aspect, in some optional embodiments, the identification module is further configured to:
Extracting an entity, a relation or an event carried in unstructured text in the demand text information through a preset natural language processing strategy;
For the entities contained in the unstructured text, identifying entity information in the unstructured text through a preset named entity identification strategy;
For the relation contained in the unstructured text, identifying the mapping relation among different entities in the unstructured text through a preset pattern matching strategy;
and for the event contained in the unstructured text, identifying event information in the unstructured text through a preset event identification strategy, wherein the event information comprises at least one of trigger words, participating entities and event types.
With reference to the first aspect, in some optional embodiments, the apparatus further includes a construction module, where the construction module is configured to obtain corpus materials in a purchase analysis scene, and construct a purchase analysis corpus based on the corpus materials;
and labeling the corpus materials in the purchase analysis corpus, and taking the purchase analysis corpus formed by the labeled corpus materials as the preset purchase analysis corpus.
With reference to the first aspect, in some optional embodiments, the apparatus further includes:
the identity authentication module is used for carrying out identity authentication on the current user to obtain an identity authentication result;
And the access control module is used for determining the calling range of the third generating module when the third generating module calls the target index data corresponding to the analysis corpus from the purchase analysis big database according to the identity authentication result.
With reference to the first aspect, in some optional embodiments, the purchase analysis big database includes at least one of project data, project order data, supplier data, purchase data, contract data, organization data.
With reference to the first aspect, in some optional embodiments, the entity information includes at least one of a time, a provider, an organization, and a purchase.
In a second aspect, an embodiment of the present application further provides an AI procurement business analysis method based on supply chain management, which is applied to the above-mentioned apparatus, where the apparatus includes a first acquisition module, a first generation module, a second acquisition module, an identification module, a second generation module, and a third generation module;
the method comprises the following steps:
Acquiring raw data of purchase service through the first acquisition module;
Generating index data corresponding to the purchasing business original data through the first generation module according to the purchasing business original data, and taking the purchasing business original data and the index data as a purchasing analysis big database;
acquiring the demand text information of the user through the second acquisition module;
Identifying an entity, a relation or an event carried in the demand text information through the identification module so as to generate a corresponding demand feature according to the entity, the relation or the event carried in the demand text information;
Selecting a preset template corresponding to the demand characteristics through the second generation module according to the demand characteristics, and matching analysis corpus corresponding to the demand characteristics from a preset purchase analysis corpus;
And calling target index data corresponding to the analysis corpus from the purchase analysis big database through the third generation module so as to generate an analysis text formed by the preset template, the analysis corpus and the target index data.
In a third aspect, an embodiment of the present application further provides an electronic device, where the electronic device includes a processor and a memory coupled to each other, where the memory stores a computer program, and when the computer program is executed by the processor, causes the electronic device to perform the method described above.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to perform the above-described method.
The invention adopting the technical scheme has the following advantages:
according to the technical scheme provided by the application, a corresponding purchasing analysis big database is generated based on purchasing business original data, after the demand text information of a user is acquired, entities, relations or events carried in the demand text information are understood to generate corresponding demand characteristics, then a preset template is selected according to the demand characteristics, corresponding analysis corpus is matched, and corresponding target index data is called from the purchasing analysis big database, so that an analysis text composed of the preset template, the analysis corpus and the target index data is generated. Therefore, the corresponding corpus and data can be called from each preset large database according to the demand text of the user, and the analysis text is generated in real time, so that the method has the characteristics of objective data, high efficiency and convenience in operation, and the problems of inaccuracy, low efficiency and high cost in traditional purchasing analysis are solved.
Drawings
The application may be further illustrated by means of non-limiting examples given in the accompanying drawings. It is to be understood that the following drawings illustrate only certain embodiments of the application and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may admit to other equally relevant drawings without inventive effort.
Fig. 1 is a block diagram of an electronic device according to an embodiment of the present application.
Fig. 2 is a block diagram of an AI procurement services analysis apparatus based on supply chain management according to an embodiment of the application.
Fig. 3 is a flowchart of an AI purchasing business analysis method based on supply chain management according to an embodiment of the present application.
Icon: 100-an electronic device; a 101-processor; 102-memory; 200-AI purchasing business analysis device based on supply chain management; 210-a first acquisition module; 220-a first generation module; 230-a second acquisition module; 240-an identification module; 250-a second generation module; 260-a third generation module.
Detailed Description
The present application will be described in detail below with reference to the drawings and the specific embodiments, wherein like or similar parts are designated by the same reference numerals throughout the drawings or the description, and implementations not shown or described in the drawings are in a form well known to those of ordinary skill in the art. In the description of the present application, the terms "first," "second," and the like are used merely to distinguish between descriptions and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, an embodiment of the present application provides an electronic device 100, where the electronic device 100 may be a personal computer, a notebook computer, a palm computer, a cloud server, etc., and the electronic device 100 may include a processor 101 and a memory 102. The processor 101 includes a supply chain management-based AI procurement services analysis apparatus 200 described below, and the memory 102 stores a computer program that, when executed by the processor 101, enables the electronic device 100 to perform corresponding steps in a supply chain management-based AI procurement services analysis method described below.
In an alternative embodiment, the supply chain management-based AI procurement services analysis apparatus 200 may also be independent of the processor 101.
Referring to fig. 2, the present application further provides an AI-procurement-service analysis apparatus 200 based on supply chain management, where the AI-procurement-service analysis apparatus 200 based on supply chain management includes at least one software functional module that may be stored in the memory 102 in the form of software or Firmware (Firmware) or cured in an Operating System (OS) of the electronic device 100. The processor 101 is configured to execute executable modules stored in the memory 102, such as software function modules and computer programs included in the AI-procurement-service analysis apparatus 200 based on supply chain management.
The AI purchasing business analysis device 200 based on supply chain management includes a first obtaining module 210, a first generating module 220, a second obtaining module 230, an identifying module 240, a second generating module 250, and a third generating module 260, and each module may have the following functions:
a first obtaining module 210, configured to obtain raw data of a purchase service;
The first generation module 220 is configured to generate, according to the purchase service original data, index data corresponding to the purchase service original data, and use the purchase service original data and the index data as a purchase analysis big database;
a second obtaining module 230, configured to obtain text information of a user's requirement;
the identifying module 240 is configured to identify an entity, a relationship, or an event carried in the required text information, so as to generate a corresponding required feature according to the entity, the relationship, or the event carried in the required text information;
The second generating module 250 is configured to select a preset template corresponding to the demand feature according to the demand feature, and match an analysis corpus corresponding to the demand feature from a preset purchase analysis corpus;
and a third generating module 260, configured to call target index data corresponding to the analysis corpus from the purchase analysis big database, so as to generate an analysis text composed of the preset template, the analysis corpus and the target index data.
In this embodiment, the raw data of the purchasing service may refer to historical purchasing data of the enterprise cut to the current moment, including but not limited to, structured data, files, images, and the like, which have real-time performance and are updated in real time according to the purchasing service of the enterprise.
In this embodiment, the raw data of the purchase service may be data related to the purchase service, which is obtained by calling the API interface written in JAVA language from the data sources such as the supply chain digitizing platform, ERP, CRM, OA, etc. by the user at a preset frequency, so as to realize the timing update of the data.
In this embodiment, the purchase analysis big database includes at least one of item data, item order data, provider data, purchase data, contract data, and organization data.
In this embodiment, the index data may be data obtained directly from the raw data of the purchasing service, for example, the total amount of the purchasing project of a certain enterprise in 2023, and the result obtained by such simple accumulation calculation may be obtained directly from the raw data of the purchasing service, or the index data may also be the result obtained by performing calculation and accumulation based on a preset algorithm rule according to the raw data of the purchasing service, for example, the cost reduction data of a certain enterprise in 2023 needs to be calculated by combining with various factors such as the historical cost of the enterprise in the past year, the actual cost of the year, the purchasing budget of the enterprise and the like carried in the raw data of the purchasing service, and the specific calculation process is formulated according to the enterprise regulation, the industry regulation and the like, which is not described herein. Therefore, a purchasing analysis large database is formed by purchasing business original data and index data, the corresponding analysis text is generated by combining analysis corpus conveniently, the content displayed in the analysis text is provided with data support, and the user can feel more visual about the relevant information of purchasing the plate of the enterprise.
Thus, the AI purchasing business analysis system based on supply chain management provided by the application is called as the data content forming the analysis text by the purchasing business original data, the data carried in the purchasing analysis big database and the like. Raw data of purchasing business generated in the operation of the supply chain digital platform acts on an analysis text under the condition of no human factor interference, so that the generation of the analysis text is based on the real data obtained immediately, the tedious processes of data information screening and false-and-true removal are omitted, and a user can conveniently and quickly decide according to the analysis text. Meanwhile, purchasing data analysis is performed from multiple dimensions of projects, orders, suppliers, purchasing products, contracts, organization and the like, and accuracy and feasibility of analysis texts are improved.
In this embodiment, the user inputs the requirement text carrying the requirement of the user through the designated popup window, search bar, etc., and the electronic device 100 obtains the requirement text information carried in the requirement text, and identifies the entity, relationship or event carried in the requirement text information through the identification module 240, so as to generate the corresponding requirement feature.
For unstructured text in the required text information, extracting an entity, a relation or an event carried in the unstructured text through a preset natural language processing strategy;
For the entities contained in the unstructured text, identifying entity information in the unstructured text through a preset named entity identification strategy;
For the relation contained in the unstructured text, identifying the mapping relation among different entities in the unstructured text through a preset pattern matching strategy;
and for the event contained in the unstructured text, identifying event information in the unstructured text through a preset event identification strategy, wherein the event information comprises at least one of trigger words, participating entities and event types.
In this embodiment, for an entity included in a structured text in the demand text information, a BiLSTM +crf model may be used for identifying the entity, so as to implement efficient identification of entity information.
In this embodiment, the entity information may include at least one of time, provider, organization, and purchase.
In practical application, the generation of the existing analysis text is based on the insertion of text data by a preset template, and has the characteristics of clear structure, strict logic and high accuracy, but has the defects of single form and no distinction; secondly, the analysis text is generated based on a deep learning mode, and the method has the characteristic of high flexibility, but also has the defect of low content accuracy. Therefore, the embodiment of the application provides an analysis text generation mode combining a template and deep learning, specifically, the generation of an initial analysis text can be realized by combining an AI application development framework based on langchain with a universal large model base, constructing a controllable preset purchase analysis corpus and then performing large model NIP natural language processing and a deep learning algorithm.
In this embodiment, the apparatus further includes a construction module, where the construction module is configured to obtain corpus materials in a purchase analysis scene, and construct a purchase analysis corpus based on the corpus materials;
and labeling the corpus materials in the purchase analysis corpus, and taking the purchase analysis corpus formed by the labeled corpus materials as the preset purchase analysis corpus.
The construction of the preset purchase analysis corpus can firstly collect corpus materials in a purchase analysis scene, establish the purchase analysis corpus, then label the collected corpus materials, and control the scope and quality of the corpus materials in a corpus scene screening and periodical spot check mode for the labeled corpus materials so as to improve the accuracy of analysis texts. Thus, a preset purchase analysis corpus is constructed through corpus materials, and a basis is provided for generating an initial analysis text.
In practical application, the initial analysis text can be a full-scale purchase analysis of enterprises within a period of time, and is displayed in a report form, wherein the content comprises purchase item data analysis, cost reduction data analysis, supplier data analysis, order data analysis, problems existing in purchase work, suggestions given for the problems and the like; or purchasing analysis of a certain level, such as supplier data analysis; or may be an analysis at a specific point, such as the item with the highest annual transaction amount. According to different requirements of users, the displayed purchase analysis content is different.
After the initial analysis text is generated, index data (i.e., target index data) required by the initial analysis text can be called from the purchase analysis big database, and the index data is inserted into the initial analysis text to obtain a final analysis text. In practical applications, the output of the analysis text may be AIGC (ARTIFICIAL INTELLIGENCE GENERATED Content, generated artificial intelligence) technology, and the analysis text may be output in a data stream form (which may be understood as instant response) according to the requirement of the user.
It can be understood that, due to the diversity of the analysis text, the target index data may be index data corresponding to the analysis corpus, or may be an operation result obtained after the operation of a preset rule of the index data corresponding to the analysis corpus, where the preset rule may be a data operation rule freely formulated by a user (e.g., an enterprise, a personal user, etc.). Such as annual profit = annual sales-annual costs, annual sales = daily sales totals, and so forth.
Therefore, after receiving the demand text input by the user, the AI purchasing business analysis system based on supply chain management provided by the application automatically analyzes the demand text through the AI framework according to the user instruction to obtain the demand characteristics, calls the corresponding corpus and index data by the demand characteristics, combines with the preset template to form the analysis text, realizes the high-efficiency processing flow of instant answering, and has the advantages of high efficiency and low cost as long as the user only needs to completely express the user demand through the demand text.
As an alternative embodiment, the apparatus further comprises:
the identity authentication module is used for carrying out identity authentication on the current user to obtain an identity authentication result;
and the access control module is configured to determine, according to the identity authentication result, a calling range of the third generating module 260 when the third generating module 260 calls target index data corresponding to the analysis corpus from the purchase analysis big database.
Therefore, when a user invokes target index data from the purchase analysis big database, the access rights of users with different positions to the confidential data are controlled through the dual mechanism of identity authentication and rights control, and information leakage is prevented.
As an optional implementation manner, the device further comprises a preprocessor, wherein the preprocessor is used for preprocessing the raw data of the purchasing service so as to perform data cleaning on the raw data of the purchasing service to obtain preprocessed data;
The first generating module 220 is further configured to generate, according to the preprocessed data, the index data corresponding to the preprocessed data, and use the preprocessed data and the index data as the purchase analysis big database.
In this embodiment, since the first obtained raw data of the purchase service generally includes data noise, the raw data of the purchase service is subjected to data cleaning by using a language program or script programmed by JAVA, so as to implement repeated data removal, missing value processing, data format conversion, and the like of the raw data of the purchase service.
Referring to fig. 3, the present application further provides an AI purchasing service analysis method based on supply chain management, which can be applied to the above-mentioned apparatus, where the apparatus includes a first obtaining module 210, a first generating module 220, a second obtaining module 230, an identifying module 240, a second generating module 250, and a third generating module 260. The AI purchasing business analysis method based on supply chain management can comprise the following steps:
step 110, acquiring raw data of the purchase service through the first acquisition module 210;
Step 120, according to the raw data of the purchase service, generating index data corresponding to the raw data of the purchase service by the first generating module 220, and using the raw data of the purchase service and the index data as a purchase analysis big database;
step 130, obtaining the text information of the user's requirement through the second obtaining module 230;
Step 140, identifying, by the identification module 240, an entity, a relationship or an event carried in the required text information, so as to generate a corresponding required feature according to the entity, the relationship or the event carried in the required text information;
Step 150, selecting a preset template corresponding to the demand feature through the second generating module 250 according to the demand feature, and matching the analysis corpus corresponding to the demand feature from a preset purchase analysis corpus;
step 160, calling, by the third generating module 260, target index data corresponding to the analysis corpus from the purchase analysis big database to generate an analysis text composed of the preset template, the analysis corpus and the target index data.
As an alternative embodiment, the apparatus further comprises a preprocessor, and the method further comprises:
preprocessing the purchasing business original data through the preprocessor to perform data cleaning on the purchasing business original data to obtain preprocessed data;
Step 120 comprises: and generating the index data corresponding to the preprocessed data according to the preprocessed data, and taking the preprocessed data and the index data as the purchase analysis big database.
As an alternative embodiment, step 140 includes:
Extracting an entity, a relation or an event carried in unstructured text in the demand text information through a preset natural language processing strategy;
For the entities contained in the unstructured text, identifying entity information in the unstructured text through a preset named entity identification strategy;
For the relation contained in the unstructured text, identifying the mapping relation among different entities in the unstructured text through a preset pattern matching strategy;
and for the event contained in the unstructured text, identifying event information in the unstructured text through a preset event identification strategy, wherein the event information comprises at least one of trigger words, participating entities and event types.
As an alternative embodiment, the apparatus further comprises a building block, the method further comprising:
Acquiring corpus materials in a purchase analysis scene, and constructing a purchase analysis corpus by using the construction module based on the corpus materials;
And marking the corpus materials in the purchase analysis corpus by the construction module, so that the purchase analysis corpus formed by the marked corpus materials is used as the preset purchase analysis corpus.
As an optional implementation manner, the apparatus further includes an identity authentication module and an access control module, and the method further includes:
Carrying out identity authentication on the current user through the identity authentication module to obtain an identity authentication result;
And according to the identity authentication result, when the access control module determines that the third generation module 260 calls the target index data corresponding to the analysis corpus from the purchase analysis big database, the third generation module 260 calls the calling range.
As an alternative embodiment, the purchase analysis big database includes at least one of project data, project order data, supplier data, purchase data, contract data, organization data.
As an alternative embodiment, the entity information includes at least one of time, provider, organization, and purchase.
For ease of understanding, please refer to fig. 3 again, the following describes, based on fig. 3, a manner of obtaining a demand feature by identifying demand text information of a user, invoking analysis corpus and target index data based on the demand feature, and generating analysis text in combination with a preset template, as follows:
Firstly, periodically using an API and an interface written in JAVA language to connect a data source (such as a supply chain digital platform, ERP, CRM, OA and other systems) based on a timing task, and acquiring raw data of purchasing business;
Then using JAVA programming program or script to clean the purchasing service original data according to preset rules, removing repeated data in the purchasing service original data, processing missing values, and converting the format of data with inconsistent standards or names in the purchasing service original data;
after data are cleaned, generating index data from cleaned purchasing business original data according to a preset algorithm rule, and forming a purchasing analysis big database by the purchasing business original data and the index data together, wherein the purchasing analysis big database comprises purchasing project data, project order data, supplier data, purchasing product data, contract data and organization data;
Then obtaining the text information of the demands input by the user, and extracting unstructured text as structured information such as entities, relations, events and the like by adopting a natural language processing technology (e.g. BiLSTM +CRF model);
And, identifying the named entities (such as time, provider, organization, purchase, etc.) in the text by using the entity information in the structured information through named entity identification technology; the relation information in the structured information is identified by a mode matching mode, and the mapping relation between different entities in the text is identified; identifying events in the required text information by means of part-of-speech tagging, syntactic analysis, semantic role tagging and the like, wherein the events comprise event trigger words, participating entities, event types and the like; and finally generating the demand characteristics.
After the demand characteristics are determined, a preset template (generally, the template comprises a title, a beginning language, a chapter title, chapter contents, an ending language, reference materials and the like) is selected, analysis corpus corresponding to the demand characteristics is matched from a pre-constructed purchase analysis corpus, and the analysis corpus is inserted into a corresponding part of the preset template to obtain an initial analysis text.
And then, calling target index data from the purchasing analysis big database according to the keywords in the analysis corpus, and inserting the target index data into the corresponding positions of the analysis corpus. In the process, identity authentication needs to be carried out on a current user when the purchasing analysis big database is accessed, different users correspond to different identity authentication results, different data access rights are opened for the users according to the identity authentication results, and the callable data range of the users when the purchasing analysis big database calls target index data is limited;
After the initial analysis text and the target index data are determined, the analysis text carrying the target index data is finally output in a data stream mode by adopting AIGC technology.
Therefore, the artificial intelligence and big data technology is applied to the field of supply chains, an accurate, flexible, comprehensive and real purchasing analysis text can be automatically and efficiently generated, the working efficiency and satisfaction of users are improved, and further the management efficiency of an enterprise supply chain and the decision effect of an enterprise decision maker are improved.
In this embodiment, the processor 101 may be an integrated circuit chip with signal processing capability. The processor 101 may be a general-purpose processor. For example, the processor 101 may be a central Processing unit (Central Processing Unit, CPU), digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic, discrete hardware components, or may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the application.
The memory 102 may be, but is not limited to, random access memory, read only memory, programmable read only memory, erasable programmable read only memory, electrically erasable programmable read only memory, and the like.
It is understood that the electronic device 100 shown in fig. 1 is only a schematic structural diagram, and that the electronic device 100 may also include more components than those shown in fig. 1. The components shown in fig. 1 may be implemented in hardware, software, or a combination thereof.
It should be noted that, for convenience and brevity of description, specific working processes of the electronic device 100 described above may refer to corresponding processes of each step in the foregoing method, and will not be described in detail herein.
The embodiment of the application also provides a computer readable storage medium. The computer-readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to execute the AI purchasing business analysis method based on supply chain management as described in the above embodiment.
From the foregoing description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented in hardware, or by means of software plus a necessary general hardware platform, and based on this understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disc, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
In summary, the embodiment of the application provides an AI purchasing business analysis device and method based on supply chain management. According to the technical scheme, a corresponding purchasing analysis big database is generated based on purchasing business original data, after the demand text information of a user is obtained, entities, relations or events carried in the demand text information are understood to generate corresponding demand features, then a preset template is selected according to the demand features, corresponding analysis corpus is matched, corresponding target index data is called from the purchasing analysis big database, and therefore analysis text composed of the preset template, the analysis corpus and the target index data is generated. Thus, the problems of inaccuracy, low efficiency and high cost of the traditional purchasing analysis can be improved.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus, system and method may be implemented in other manners as well. The above-described apparatus, system, and method embodiments are merely illustrative, for example, flow charts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. In addition, functional modules in the embodiments of the present application may be integrated together to form a single part, or each module may exist alone, or two or more modules may be integrated to form a single part.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and variations will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (9)
1. An AI procurement services analysis apparatus based on supply chain management, the apparatus comprising:
the first acquisition module is used for acquiring the raw data of the purchasing business;
The first generation module is used for generating index data corresponding to the purchasing business original data according to the purchasing business original data, and taking the purchasing business original data and the index data as a purchasing analysis big database;
the second acquisition module is used for acquiring the text information of the user's demands;
The identification module is used for identifying the entity, the relation or the event carried in the demand text information so as to generate corresponding demand characteristics according to the entity, the relation or the event carried in the demand text information;
The second generation module is used for selecting a preset template corresponding to the demand characteristics according to the demand characteristics and matching analysis corpus corresponding to the demand characteristics from a preset purchase analysis corpus;
The third generation module is used for calling target index data corresponding to the analysis corpus from the purchase analysis big database to generate an analysis text formed by the preset template, the analysis corpus and the target index data;
wherein, the identification module is further used for:
Extracting an entity, a relation or an event carried in unstructured text in the demand text information through a preset natural language processing strategy;
For the entities contained in the unstructured text, identifying entity information in the unstructured text through a preset named entity identification strategy;
For the relation contained in the unstructured text, identifying the mapping relation among different entities in the unstructured text through a preset pattern matching strategy;
for the event contained in the unstructured text, identifying event information in the unstructured text through a preset event identification strategy, wherein the event information comprises at least one of trigger words, participating entities and event types;
wherein, for the entity contained in the structured text in the demand text information, the identification of the entity adopts BiLSTM +CRF model.
2. The apparatus of claim 1, further comprising a preprocessor for preprocessing the purchase service raw data to perform data cleaning on the purchase service raw data to obtain preprocessed data;
The first generation module is further configured to generate, according to the preprocessed data, the index data corresponding to the preprocessed data, and use the preprocessed data and the index data as the purchase analysis big database.
3. The apparatus of claim 1, further comprising a building module configured to obtain corpus material in a purchase analysis scenario and build a purchase analysis corpus based on the corpus material;
and labeling the corpus materials in the purchase analysis corpus, and taking the purchase analysis corpus formed by the labeled corpus materials as the preset purchase analysis corpus.
4. The apparatus of claim 1, wherein the apparatus further comprises:
the identity authentication module is used for carrying out identity authentication on the current user to obtain an identity authentication result;
And the access control module is used for determining the calling range of the third generating module when the third generating module calls the target index data corresponding to the analysis corpus from the purchase analysis big database according to the identity authentication result.
5. The apparatus of claim 1, wherein the purchase analysis big database comprises at least one of project data, project order data, vendor data, purchase data, contract data, organization data.
6. The apparatus of claim 1, wherein the entity information comprises at least one of time, vendor, organization, purchase.
7. The AI purchasing business analysis method based on supply chain management, which is characterized by being applied to the device according to any one of claims 1-6, wherein the device comprises a first acquisition module, a first generation module, a second acquisition module, an identification module, a second generation module and a third generation module;
the method comprises the following steps:
Acquiring raw data of purchase service through the first acquisition module;
Generating index data corresponding to the purchasing business original data through the first generation module according to the purchasing business original data, and taking the purchasing business original data and the index data as a purchasing analysis big database;
acquiring the demand text information of the user through the second acquisition module;
Identifying an entity, a relation or an event carried in the demand text information through the identification module so as to generate a corresponding demand feature according to the entity, the relation or the event carried in the demand text information;
the second generation module is used for selecting a preset template corresponding to the demand characteristics according to the demand characteristics and matching analysis corpus corresponding to the demand characteristics from a preset purchase analysis corpus;
invoking target index data corresponding to the analysis corpus from the purchase analysis big database through the third generation module to generate an analysis text composed of the preset template, the analysis corpus and the target index data;
The identifying, by the identifying module, an entity, a relationship or an event carried in the required text information includes:
Extracting an entity, a relation or an event carried in unstructured text in the demand text information through a preset natural language processing strategy;
For the entities contained in the unstructured text, identifying entity information in the unstructured text through a preset named entity identification strategy;
For the relation contained in the unstructured text, identifying the mapping relation among different entities in the unstructured text through a preset pattern matching strategy;
for the event contained in the unstructured text, identifying event information in the unstructured text through a preset event identification strategy, wherein the event information comprises at least one of trigger words, participating entities and event types;
wherein, for the entity contained in the structured text in the demand text information, the identification of the entity adopts BiLSTM +CRF model.
8. An electronic device comprising a processor and a memory coupled to each other, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform the method of claim 7.
9. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the method of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410437138.1A CN118037318B (en) | 2024-04-12 | 2024-04-12 | AI purchasing business analysis device and method based on supply chain management |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410437138.1A CN118037318B (en) | 2024-04-12 | 2024-04-12 | AI purchasing business analysis device and method based on supply chain management |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118037318A CN118037318A (en) | 2024-05-14 |
| CN118037318B true CN118037318B (en) | 2024-06-28 |
Family
ID=90995255
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410437138.1A Active CN118037318B (en) | 2024-04-12 | 2024-04-12 | AI purchasing business analysis device and method based on supply chain management |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118037318B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222305A (en) * | 2019-12-17 | 2020-06-02 | 共道网络科技有限公司 | Information structuring method and device |
| CN117473971A (en) * | 2023-10-18 | 2024-01-30 | 郑州信源信息技术股份有限公司 | Automatic generation method and system for bidding documents based on purchasing text library |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886647A (en) * | 2019-01-29 | 2019-06-14 | 广东华伦招标有限公司 | Procurement business managing functional module method, apparatus, equipment and storage medium |
| CN115659938B (en) * | 2022-11-03 | 2023-11-21 | 江苏中博通信有限公司 | Purchasing document writing auxiliary system based on intelligent supply chain |
| CN116629262A (en) * | 2023-05-06 | 2023-08-22 | 鹏城实验室 | Text entity recognition method, device, equipment and storage medium |
-
2024
- 2024-04-12 CN CN202410437138.1A patent/CN118037318B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111222305A (en) * | 2019-12-17 | 2020-06-02 | 共道网络科技有限公司 | Information structuring method and device |
| CN117473971A (en) * | 2023-10-18 | 2024-01-30 | 郑州信源信息技术股份有限公司 | Automatic generation method and system for bidding documents based on purchasing text library |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118037318A (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kirchmer et al. | Value-Driven Robotic Process Automation (RPA) A Process-Led Approach to Fast Results at Minimal Risk | |
| US10839404B2 (en) | Intelligent, interactive, and self-learning robotic process automation system | |
| US8340995B2 (en) | Method and system of using artifacts to identify elements of a component business model | |
| US11367008B2 (en) | Artificial intelligence techniques for improving efficiency | |
| US11941714B2 (en) | Analysis of intellectual-property data in relation to products and services | |
| CN112732897A (en) | Document processing method and device, electronic equipment and storage medium | |
| US10922633B2 (en) | Utilizing econometric and machine learning models to maximize total returns for an entity | |
| CN113868507A (en) | Bidding information acquisition method and device combining RPA and AI and electronic equipment | |
| US20140143750A1 (en) | Structured Enterprise Software Knowledgebase Utilities, And Methods Of Use Thereof | |
| CN116701662A (en) | Knowledge graph-based supply chain data management method, device, equipment and medium | |
| CN115423578A (en) | Bidding method and system based on micro-service containerization cloud platform | |
| CN115292473A (en) | Extended selective recommendation and deployment in low code schemes | |
| CN118037318B (en) | AI purchasing business analysis device and method based on supply chain management | |
| CN115907875B (en) | Price interval manufacturing method and device, electronic equipment and medium | |
| US20140149186A1 (en) | Method and system of using artifacts to identify elements of a component business model | |
| Pourshahid et al. | Requirements for a modeling language to specify and match business process improvement patterns | |
| US20200342302A1 (en) | Cognitive forecasting | |
| Chung et al. | A case study: using UML to develop a knowledge-based system for supporting business systems in a small financial institute | |
| US11507728B2 (en) | Click to document | |
| CN116959018B (en) | OCR-based intelligent checking method, system and equipment | |
| Nayak et al. | Benefits of Robotic Process Automation (RPA): Today and Tomorrow of the Manufacturing Industries | |
| Schönsleben | ERP and SCM Software | |
| Ritchi et al. | Driving Factors of Cloud Accounting Implementation in Small and Medium Enterprises (SMEs): Evidence from Indonesia | |
| Stamenković | The Role of ERP Solutions in Managing Corporations From the Accounting Perspective | |
| H Alharbi et al. | Exploring the Impact of Shifting ERP Systems to the Cloud |
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 | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 1-036, 1st Floor, Building 1, No. 88 Nongda South Road, Haidian District, Beijing, 100193 Patentee after: Beijing Longdao Network Technology Co.,Ltd. Country or region after: China Address before: Room 402-2, 4th floor, building 3, yard 81, Zizhuyuan Road, Haidian District, Beijing 100089 Patentee before: Beijing Longdao Network Technology Co.,Ltd. Country or region before: China |