CN115905711A - Intelligent recommendation method with feedback function - Google Patents
Intelligent recommendation method with feedback function Download PDFInfo
- Publication number
- CN115905711A CN115905711A CN202211691278.9A CN202211691278A CN115905711A CN 115905711 A CN115905711 A CN 115905711A CN 202211691278 A CN202211691278 A CN 202211691278A CN 115905711 A CN115905711 A CN 115905711A
- Authority
- CN
- China
- Prior art keywords
- data
- keywords
- recommendation
- degree
- feedback function
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to the field of intelligent recommendation methods, in particular to an intelligent recommendation method with a feedback function, which aims at the problems that the existing intelligent recommendation method cannot acquire the adoption degree of a client and cannot obtain the recommendation satisfaction degree, and provides the following scheme, which comprises the following steps: s1, collecting, identifying, processing and storing data, and extracting keywords; s2, classifying the extracted keywords, and calculating the proportion of each keyword; s3, sorting the keywords from high to low according to the occupied proportion; s4, matching recommended data according to the keywords, performing duplicate checking processing on the recommended data, and recommending the data after the duplicate checking is passed; s5, after data recommendation, collecting feedback data and knowing the data acceptance degree; and S6, optimizing the recommendation scheme according to the adoption degree to complete intelligent recommendation.
Description
Technical Field
The invention relates to the technical field of intelligent recommendation methods, in particular to an intelligent recommendation method with a feedback function.
Background
The artificial intelligence can be used in an intelligent recommendation method, intelligent recommendation is based on a mass data mode for intelligent recommendation service, a data set needs to be collected from a data source, a single model is adopted for carrying out operation and data result verification on the collected data set, and finally a model conclusion is obtained, and intelligent or non-intelligent recommendation and customer behavior guidance of some data are carried out.
The existing intelligent recommendation method cannot acquire the adoption degree of a client and cannot obtain the recommendation satisfaction degree, so that an intelligent recommendation method with a feedback function is provided for solving the problems.
Disclosure of Invention
The invention aims to solve the defects that the intelligent recommendation method in the prior art cannot acquire the customer acceptance and cannot obtain recommendation satisfaction, and provides the intelligent recommendation method with the feedback function.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent recommendation method with a feedback function comprises the following steps:
s1, collecting, identifying, processing and storing data, and extracting keywords;
s2, classifying the extracted keywords, and calculating the proportion of each keyword;
s3, sorting the keywords according to the occupied proportion from high to low;
s4, matching recommended data according to the keywords, performing duplicate checking processing on the recommended data, and recommending the data after the duplicate checking is passed;
s5, after data recommendation, collecting feedback data and knowing the data acceptance degree;
and S6, optimizing a recommendation scheme according to the adoption degree, and finishing intelligent recommendation.
Preferably, in S1, during data acquisition, the acquired data is subjected to preliminary processing, unnecessary repeated data is removed, and the acquired data is sorted.
Preferably, in S1, when the data is stored, the pre-stored data is matched with the data already stored in the memory, and if the matching is unsuccessful, it indicates that the data is not repeated, and the data may be stored.
Preferably, in S1, when extracting the keyword, the type of the keyword is determined, and the determined keyword is subjected to type tagging.
Preferably, in S2, the extracted keywords are classified, the total amount of the extracted keywords and the amount of each type of keywords are calculated, and the amount of a single type of keywords is divided by the total amount of the keywords, so as to obtain the occupation ratio of the type of keywords.
Preferably, in S4, recommended data is matched according to the keywords, duplicate checking is performed on the recommended data, when duplicate checking is performed, the matched recommended data is compared with historical recommended data, and when the comparison is not repeated, data recommendation is performed.
Preferably, in S5, after the data is recommended, the recommended person performs satisfaction evaluation, and the evaluation grades are: poor, general, excellent and extremely satisfactory.
Preferably, in S6, the recommended scheme is optimized according to the degree of adoption, and when the degree of adoption is always above the optimum, optimization is not required, and when the degree of adoption is below the optimum, optimization is performed.
Preferably, after the data is recommended, the recommended personnel judges the satisfaction degree and feeds back the opinions at the same time.
Preferably, the recommendation scheme is optimized according to the adoption degree and the feedback opinions.
Compared with the prior art, the invention has the beneficial effects that:
the scheme is used for collecting, identifying, processing and storing data, extracting keywords, classifying the extracted keywords, calculating the occupation proportion of each keyword, and sequencing the keywords from high to low according to the occupation proportion;
according to the scheme, recommended data are matched according to keywords, duplicate checking processing is carried out on the recommended data, the data are recommended after the duplicate checking is passed, feedback data are collected after the data are recommended, the data acceptance degree is known, and the recommendation scheme is optimized according to the acceptance degree;
the invention can collect feedback data after recommendation, know the data satisfaction degree and optimize the recommendation scheme according to the adoption degree.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Example one
An intelligent recommendation method with a feedback function comprises the following steps:
s1, collecting, identifying, processing and storing data, and extracting keywords;
s2, classifying the extracted keywords, and calculating the proportion of each keyword;
s3, sorting the keywords according to the occupied proportion from high to low;
s4, matching recommended data according to the keywords, performing duplicate checking processing on the recommended data, and recommending the data after the duplicate checking is passed;
s5, after data recommendation, collecting feedback data and knowing the data acceptance degree;
and S6, optimizing a recommendation scheme according to the adoption degree, and finishing intelligent recommendation.
In this embodiment, in S1, during data acquisition, the acquired data is subjected to preliminary processing, unnecessary repeated data is removed, and the acquired data is sorted.
In this embodiment, in S1, when data is stored, the pre-stored data is matched with the data already stored in the memory, and if the matching is unsuccessful, it indicates that the data is not repeated, and the data can be stored.
In this embodiment, in S1, when extracting a keyword, the type of the keyword is determined, and the determined keyword is subjected to type tagging.
In this embodiment, in S2, the extracted keywords are classified, the total amount of the extracted keywords and the amount of each type of keywords are calculated, and the amount of a single type of keywords is divided by the total amount of the keywords, so that the occupation ratio of the type of keywords can be obtained.
In this embodiment, in S4, recommended data is matched according to the keywords, duplicate checking is performed on the recommended data, when duplicate checking is performed, the matched recommended data is compared with historical recommended data, and when the comparison is not repeated, data recommendation is performed.
In this embodiment, in S5, after the data is recommended, the recommended person performs satisfaction evaluation, and the evaluation grades are: poor, general, excellent and extremely satisfactory.
In this embodiment, in S6, the recommendation scheme is optimized according to the adoption degree, when the adoption degree is always over excellent, optimization is not required, and when the adoption degree is lower than excellent, optimization is performed.
In the embodiment, after the data is recommended, the recommended personnel performs satisfaction evaluation and simultaneously performs opinion feedback.
In this embodiment, the recommendation scheme is optimized according to the adoption degree and the feedback opinions.
Example two
An intelligent recommendation method with a feedback function comprises the following steps:
s1, extracting keywords;
s2, classifying the extracted keywords, and calculating the proportion of each keyword;
s3, sorting the keywords from high to low according to the occupied proportion;
s4, matching the recommended data according to the keywords, performing duplicate checking processing on the recommended data, and recommending the data after the duplicate checking is passed;
s5, after data recommendation, collecting feedback data and knowing the data acceptance degree;
and S6, optimizing a recommendation scheme according to the adoption degree, and completing intelligent recommendation.
In this embodiment, in S1, when extracting a keyword, the type of the keyword is determined, and a type tag is performed on the determined keyword.
In this embodiment, in S2, the extracted keywords are classified, the total amount of the extracted keywords and the amount of each type of keywords are calculated, and the amount of a single type of keywords is divided by the total amount of the keywords, so that the occupation ratio of the type of keywords can be obtained.
In this embodiment, in S4, recommended data is matched according to the keywords, duplicate checking is performed on the recommended data, when duplicate checking is performed, the matched recommended data is compared with historical recommended data, and when the comparison is not repeated, data recommendation is performed.
In this embodiment, in S5, after the data is recommended, the recommended person performs satisfaction evaluation, and the evaluation grades are: poor, general, excellent and extremely satisfactory.
In this embodiment, in S6, the recommendation scheme is optimized according to the degree of adoption, and when the degree of adoption is always above the optimum, optimization is not required, and when the degree of adoption is below the optimum, optimization is performed.
In this embodiment, after data recommendation, the recommended person performs satisfaction evaluation and simultaneously performs opinion feedback.
In this embodiment, the recommendation scheme is optimized according to the adoption degree and the feedback opinions.
EXAMPLE III
An intelligent recommendation method with a feedback function comprises the following steps:
s1, collecting, identifying, processing and storing data, and extracting keywords;
s2, classifying the extracted keywords, and calculating the proportion of each keyword;
s3, sorting the keywords from high to low according to the occupied proportion;
s4, recommending data according to keyword matching recommendation data;
s5, after data recommendation, collecting feedback data and knowing the data acceptance degree;
and S6, optimizing a recommendation scheme according to the adoption degree, and finishing intelligent recommendation.
In this embodiment, in S1, during data acquisition, the acquired data is subjected to preliminary processing, unnecessary repeated data is removed, and the acquired data is sorted.
In this embodiment, in S1, when data is stored, the pre-stored data is matched with the data already stored in the memory, and if the matching is unsuccessful, it indicates that the data is not repeated, and the data may be stored.
In this embodiment, in S1, when extracting a keyword, the type of the keyword is determined, and the determined keyword is subjected to type tagging.
In this embodiment, in S2, the extracted keywords are classified, the total amount of the extracted keywords and the amount of each type of keywords are calculated, and the amount of a single type of keywords is divided by the total amount of the keywords, so that the occupation ratio of the type of keywords can be obtained.
In this embodiment, in S5, after the data is recommended, the recommended person performs satisfaction evaluation, and the evaluation level is: poor, general, excellent and extremely satisfactory.
In this embodiment, in S6, the recommendation scheme is optimized according to the degree of adoption, and when the degree of adoption is always above the optimum, optimization is not required, and when the degree of adoption is below the optimum, optimization is performed.
In this embodiment, after data recommendation, the recommended person performs satisfaction evaluation and simultaneously performs opinion feedback.
In this embodiment, the recommendation scheme is optimized according to the adoption degree and the feedback opinions.
Data recommendation is performed through the intelligent recommendation methods provided by the first embodiment, the second embodiment and the third embodiment, and the first embodiment is the best embodiment.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (10)
1. An intelligent recommendation method with a feedback function is characterized by comprising the following steps:
s1, collecting, identifying, processing and storing data, and extracting keywords;
s2, classifying the extracted keywords, and calculating the proportion of each keyword;
s3, sorting the keywords from high to low according to the occupied proportion;
s4, matching recommended data according to the keywords, performing duplicate checking processing on the recommended data, and recommending the data after the duplicate checking is passed;
s5, after data recommendation, collecting feedback data and knowing the data acceptance degree;
and S6, optimizing a recommendation scheme according to the adoption degree, and completing intelligent recommendation.
2. The intelligent recommendation method with the feedback function according to claim 1, wherein in S1, during data acquisition, the acquired data is subjected to preliminary processing, useless repeated data is removed, and the acquired data is sorted.
3. The intelligent recommendation method with feedback function according to claim 1, wherein in S1, when storing data, matching pre-stored data with data already stored in a memory, and if matching is unsuccessful, it indicates that data is not repeated, and thus data can be stored.
4. The intelligent recommendation method with feedback function according to claim 1, wherein in S1, when extracting the keywords, the type of the keywords is determined, and the determined keywords are labeled with the type.
5. The intelligent recommendation method with feedback function according to claim 1, wherein in S2, the extracted keywords are classified, the total amount of the extracted keywords and the amount of each type of keywords are calculated, and the occupation ratio of the type of keywords is obtained by dividing the amount of the single type of keywords by the total amount of the keywords.
6. The intelligent recommendation method with the feedback function according to claim 1, wherein in S4, recommendation data is matched according to the keywords, duplicate checking is performed on the recommendation data, when duplicate checking is performed, the matched recommendation data is compared with historical recommendation data, and when the comparison is not repeated, data recommendation is performed.
7. The intelligent recommendation method with feedback function according to claim 1, wherein in S5, after the data recommendation, the recommendation staff performs satisfaction evaluation, and the evaluation grades are: poor, general, excellent and extremely satisfactory.
8. The intelligent recommendation method with the feedback function according to claim 1, wherein in S6, the recommendation scheme is optimized according to the degree of adoption, and when the degree of adoption is always above the optimum, optimization is not required, and when the degree of adoption is below the optimum, optimization is performed.
9. The intelligent recommendation method with feedback function as claimed in claim 7, wherein after the data recommendation, the recommendation staff performs satisfaction evaluation and opinion feedback.
10. The intelligent recommendation method with feedback function as claimed in claim 8, wherein the recommendation scheme is optimized according to the adoption degree and the feedback opinion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211691278.9A CN115905711A (en) | 2022-12-28 | 2022-12-28 | Intelligent recommendation method with feedback function |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211691278.9A CN115905711A (en) | 2022-12-28 | 2022-12-28 | Intelligent recommendation method with feedback function |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115905711A true CN115905711A (en) | 2023-04-04 |
Family
ID=86496297
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211691278.9A Pending CN115905711A (en) | 2022-12-28 | 2022-12-28 | Intelligent recommendation method with feedback function |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115905711A (en) |
-
2022
- 2022-12-28 CN CN202211691278.9A patent/CN115905711A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112766550B (en) | Random forest-based power failure sensitive user prediction method, system, storage medium and computer equipment | |
CN105590146A (en) | Power plant device intelligent prediction overhaul method and power plant device intelligent prediction overhaul system based on big data | |
CN111738462B (en) | Fault first-aid repair active service early warning method for electric power metering device | |
CN110690701A (en) | Analysis method for influence factors of abnormal line loss | |
CN110046792B (en) | Zero-power user checking method based on radar chart comprehensive evaluation method | |
CN111061709A (en) | Data cleaning automation method and system for similar repeated records | |
CN115034525B (en) | Steel pipe order production period prediction monitoring system and method based on data analysis | |
CN110188984A (en) | A kind of tobacco rolls up the method for building up of anomalous mass data model between hired car | |
CN115358481A (en) | Early warning and identification method, system and device for enterprise ex-situ migration | |
CN111178690A (en) | Electricity stealing risk assessment method for electricity consumers based on wind control scoring card model | |
CN117290462B (en) | Intelligent decision system and method for large data model | |
CN117057942B (en) | Intelligent financial decision big data analysis system | |
CN110555619A (en) | Power supply capacity evaluation method based on intelligent power distribution network | |
CN114118588A (en) | Peak-facing summer power failure prediction method based on game feature extraction under clustering undersampling | |
CN106844419A (en) | A kind of skyline preference querying methods based on magnanimity Incomplete data set | |
CN116910602B (en) | Line loss analysis method and system based on relevance analysis | |
CN115905711A (en) | Intelligent recommendation method with feedback function | |
CN112100419A (en) | Single weather image identification method and system based on image retrieval | |
CN111339167A (en) | Method for analyzing influence factors of transformer area line loss rate based on K-means and principal component linear regression | |
CN114693067A (en) | Abnormal electricity utilization user identification method | |
CN112348066A (en) | Line uninterrupted power rating evaluation method based on gray clustering algorithm | |
CN114925859A (en) | Intelligent automobile maintenance transaction system based on block chain | |
CN116796040A (en) | Intelligent recommendation method based on artificial intelligence | |
CN116187775B (en) | Production working hour management system and method | |
CN116862209B (en) | New energy automobile charging facility management method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |