CN117494073A - Training method, device, equipment and storage medium of dialogue recommendation model - Google Patents
Training method, device, equipment and storage medium of dialogue recommendation model Download PDFInfo
- Publication number
- CN117494073A CN117494073A CN202311384081.5A CN202311384081A CN117494073A CN 117494073 A CN117494073 A CN 117494073A CN 202311384081 A CN202311384081 A CN 202311384081A CN 117494073 A CN117494073 A CN 117494073A
- Authority
- CN
- China
- Prior art keywords
- model
- training
- dialogue
- data
- recommendation model
- 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
- 238000012549 training Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000010801 machine learning Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 238000013461 design Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims abstract description 5
- 238000013210 evaluation model Methods 0.000 claims abstract description 4
- 230000003993 interaction Effects 0.000 claims abstract description 4
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000003169 central nervous system Anatomy 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/40—Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
-
- 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
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- 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
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2178—Validation; Performance evaluation; Active pattern learning techniques based on feedback of a supervisor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Physics (AREA)
- Machine Translation (AREA)
Abstract
The invention relates to the technical field of computers, in particular to a training method, a training device, training equipment and a training storage medium of a dialogue recommendation model, which comprise the steps of collecting and cleaning data of external information based on interaction between two machine learning models; selecting an appropriate frame based on the collected and cleaned data; based on the selection of the appropriate framework, performing design architecture; preprocessing the text based on the design framework; training a model using training data and a designed architecture based on the preprocessing; evaluating performance of the model using a test dataset based on the training model; based on the evaluation model, the model is judged, and as a result, the proper framework is not selected again ideally. The training method, the device, the equipment and the storage medium of the dialogue recommendation model are improved on the related programs, the probability of confusion of program operation is reduced, the practicability of the dialogue recommendation model is improved, and the resource expense is reduced.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a training method, a training device, training equipment and a training storage medium for a dialogue recommendation model.
Background
The dialogue recommendation system is a system for recommending target information to a user through multiple rounds of dialogue. The dialogue recommendation system may process dialogue information input by a user based on the dialogue information input by the user using a dialogue recommendation model to output recommendation information. The dialogue recommendation model can be obtained after training by using dialogue recommendation corpus.
However, in the existing dialogue recommendation system, the operation logic in the system is disordered, the dialogue recommendation system can generate program errors according to the maximum probability of instruction transmission of an internal program, the correct instruction is affected to be made by the dialogue recommendation system, and the resource expense is improved.
Disclosure of Invention
The invention aims to provide a training method, a training device, training equipment and a storage medium of a dialogue recommendation model, so as to solve the problem that operation logic in a system is disordered and errors occur in a high probability in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions: training method, device, equipment and storage medium of dialogue recommendation model, comprising:
based on interaction between the two machine learning models, collecting and cleaning data of external information;
selecting an appropriate frame based on the collected and cleaned data;
based on the selection of the appropriate framework, performing design architecture;
preprocessing the text based on the design framework;
training a model using training data and a designed architecture based on the preprocessing;
evaluating performance of the model using a test dataset based on the training model;
based on the evaluation model, the model is judged, and the result is not ideal, the proper framework is reselected, and the result is ideal, so that the model is deployed.
Preferably, the two machine learning models include extracting keywords, after the extracting keywords, the two machines substitute the keywords into a database, after the substituting the keywords into the database, the two machines perform data analysis on the keywords, and after the data analysis, the two machines can accurately express ideas.
Preferably, the two machines may be replaced by users, and after the users transmit the user dialogue information to the dialogue recommendation model, the dialogue recommendation model transmits the model dialogue information to the users through internal analysis operation.
Preferably, the active guiding module is configured to obtain an active guiding corpus in a target domain based on dialogue information between two machine learning models, where the active guiding corpus includes recommended targets in the target domain;
the knowledge dialogue module is used for obtaining knowledge dialogue corpus corresponding to the recommended target based on the knowledge graph of the target field;
the data analysis module is used for collecting and cleaning data by two machines and analyzing and sorting the data;
and the training module is used for training the dialogue recommendation model of the target field by adopting the dialogue recommendation corpus of the target field.
Preferably, at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.
Preferably, computer instructions for causing the computer to perform the method according to any of claims 1-3.
Preferably a computer program which, when executed by a processor, implements the method according to any of claims 1-3.
Compared with the prior art, the invention has the beneficial effects that:
the training method, the training device, the training equipment and the training storage medium of the novel dialogue recommendation model are improved in related programs, the probability of confusion of program operation is reduced, the practicability of the dialogue recommendation model is improved, and the resource cost is reduced.
Description of the drawings:
FIG. 1 is a schematic view of a first embodiment of the present invention;
FIG. 2 is a schematic diagram of a second embodiment of the present invention;
FIG. 3 is a schematic view of a third embodiment of the present invention;
FIG. 4 is a schematic view of a fourth embodiment of the present invention;
fig. 5 is a schematic view of a fifth embodiment of the present invention.
The specific embodiment is as follows:
the following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-5, an embodiment of the present invention is provided: training method, device, equipment and storage medium of dialogue recommendation model,
comprising the following steps: based on interaction between the two machine learning models, collecting and cleaning data of external information;
selecting an appropriate frame based on the collected and cleaned data; training data is constructed using a corpus with diversity.
Based on selecting a proper framework, designing a framework; a deep learning framework of the appropriate task is selected.
Preprocessing the text based on a design architecture; a neural network architecture based on a self-attention mechanism.
Training a model using training data and the designed architecture based on the preprocessing;
evaluating performance of the model using the test dataset based on the training model; the model is trained using the training data and the designed network structure.
Based on the evaluation model, the model is judged, the appropriate framework is not ideally reselected as a result, the model is ideally deployed starting, the performance of the model is evaluated using the test dataset, the model is integrated into an application or system, and the response request is prepared and text is generated.
Further, the two machine learning models include extracting keywords, after extracting the keywords, the two machines substitute the keywords into the database, after substituting the keywords into the database, the two machines perform data analysis on the keywords, and after the data analysis, the two machines can accurately express ideas.
Further, the two machines can be replaced by users, and after the users transmit the user dialogue information to the dialogue recommendation model, the dialogue recommendation model transmits the model dialogue information to the users through internal analysis operation.
Further, the active guiding module is used for acquiring active guiding corpus in the target field based on dialogue information between the two machine learning models, wherein the active guiding corpus comprises recommended targets in the target field; the active guidance model may be obtained by fine-tuning an existing open domain dialog model.
The knowledge dialogue module is used for obtaining knowledge dialogue corpus corresponding to the recommended target based on the knowledge graph of the target field; the method can divide the dialogue recommendation process into active guidance and deep knowledge dialogue during dialogue recommendation, thereby being beneficial to improving the consistency, knowledge and interestingness of the chat process of the user and improving the efficiency of dialogue recommendation.
The data analysis module is used for collecting and cleaning data by two machines and analyzing and sorting the data;
and the training module is used for training a dialogue recommendation model of the target field by adopting dialogue recommendation corpus of the target field.
Further, at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor such that the at least one processor is capable of performing the method of any one of claims 1-3, the processor being a functional unit for interpreting and executing the instructions, which is the central nervous system of the computer, the memory unit being in fact a kind of sequential logic circuit
Further, computer instructions for causing a computer to perform the method according to any one of claims 1-3, the computer instructions being instructions and commands for directing the operation of the machine, the program being a series of instructions arranged in a certain order, the process of executing the program being the operation of the computer.
Further, a computer program which, when executed by a processor, implements a method according to any of claims 1-3, the computer program being a set of instructions which can be recognized and executed by a computer, running on an electronic computer, an informatization tool meeting certain needs of people.
Working principle: when the method is used, firstly, data are collected and cleaned by the dialogue recommendation model, keywords are extracted from external information, then the keywords are substituted into a database, data analysis is performed, a proper framework is selected according to the data in the database, a proper deep learning framework is selected, a framework is designed, the text is preprocessed, the model is trained by training data and a designed network structure, the performance of the model is evaluated by using a data set, a proper framework is reselected under an undesirable state, the model is deployed under an ideal state, and finally the idea is accurately expressed. The above is the whole working principle of the invention.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (7)
1. The training method of the dialogue recommendation model is characterized by comprising the following steps of:
based on interaction between the two machine learning models, collecting and cleaning data of external information;
selecting an appropriate frame based on the collected and cleaned data;
based on the selection of the appropriate framework, performing design architecture;
preprocessing the text based on the design framework;
training a model using training data and a designed architecture based on the preprocessing;
evaluating performance of the model using a test dataset based on the training model;
based on the evaluation model, the model is judged, and the result is not ideal, the proper framework is reselected, and the result is ideal, so that the model is deployed.
2. The method for training a conversational recommendation model according to claim 1, wherein: the two machine learning models comprise extracted keywords, after the extracted keywords, the two machines substitute the keywords into a database, after the substituted keywords are substituted into the database, the two machines perform data analysis on the keywords, and after the data analysis, the two machines can accurately express ideas.
3. The method for training a conversational recommendation model according to claim 1, wherein: the two machines can be replaced by users, and after the users transmit the user dialogue information to the dialogue recommendation model, the dialogue recommendation model transmits the model dialogue information to the users through internal analysis operation.
4. The training device of the dialogue recommendation model is characterized by comprising:
the active guiding module is used for acquiring active guiding corpus of the target field based on dialogue information between the two machine learning models, wherein the active guiding corpus comprises recommended targets of the target field;
the knowledge dialogue module is used for obtaining knowledge dialogue corpus corresponding to the recommended target based on the knowledge graph of the target field;
the data analysis module is used for collecting and cleaning data by two machines and analyzing and sorting the data;
and the training module is used for training the dialogue recommendation model of the target field by adopting the dialogue recommendation corpus of the target field.
5. Training device for conversational recommendation models, characterized in that it comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.
6. A non-transitory computer-readable storage medium storing computer instructions comprising: computer instructions for causing the computer to perform the method according to any one of claims 1-3.
7. A computer program product, comprising: a computer program which, when executed by a processor, implements the method according to any of claims 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311384081.5A CN117494073A (en) | 2023-10-24 | 2023-10-24 | Training method, device, equipment and storage medium of dialogue recommendation model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311384081.5A CN117494073A (en) | 2023-10-24 | 2023-10-24 | Training method, device, equipment and storage medium of dialogue recommendation model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117494073A true CN117494073A (en) | 2024-02-02 |
Family
ID=89680630
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311384081.5A Pending CN117494073A (en) | 2023-10-24 | 2023-10-24 | Training method, device, equipment and storage medium of dialogue recommendation model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117494073A (en) |
-
2023
- 2023-10-24 CN CN202311384081.5A patent/CN117494073A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10528878B2 (en) | Tailoring question answering system output based on user experience | |
KR102388042B1 (en) | Dialogue system and computer program therefor | |
US10599997B2 (en) | System and method for ground truth evaluation | |
Karri et al. | Deep learning techniques for implementation of chatbots | |
CN105373478B (en) | Automated testing method and system | |
KR102259390B1 (en) | System and method for ensemble question-answering | |
US9710829B1 (en) | Methods, systems, and articles of manufacture for analyzing social media with trained intelligent systems to enhance direct marketing opportunities | |
WO2022237253A1 (en) | Test case generation method, apparatus and device | |
CN111090735B (en) | Performance evaluation method of intelligent question-answering method based on knowledge graph | |
EP3862891A2 (en) | Method and apparatus for retrieving multi-turn dialogue, storage medium, and electronic device | |
CN111198935A (en) | Model processing method and device, storage medium and electronic equipment | |
CN111078546A (en) | Method for expressing page features and electronic equipment | |
CN111930912A (en) | Dialogue management method, system, device and storage medium | |
CN111092769A (en) | Web fingerprint identification method based on machine learning | |
CN109934631A (en) | Question and answer information processing method, device and computer equipment | |
Ma et al. | Scenario-based microservice retrieval using Word2Vec | |
CN117494073A (en) | Training method, device, equipment and storage medium of dialogue recommendation model | |
CN110908919A (en) | Response test system based on artificial intelligence and application thereof | |
Shapiro et al. | Visual deep learning recommender system for personal computer users | |
US12026467B2 (en) | Automated learning based executable chatbot | |
CN105491090A (en) | Network data processing method and device | |
CN111461344B (en) | Automatic generation method, system, equipment and medium for high-order features | |
CN113628077A (en) | Method for generating non-repeated examination questions, terminal and readable storage medium | |
CN117556906B (en) | Question-answer data set generation method and device, electronic equipment and storage medium | |
US20240086768A1 (en) | Learning device, inference device, non-transitory computer-readable medium, learning method, and inference method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |