CN117725310A - Solution recommendation method based on matrix factorization and machine learning - Google Patents
Solution recommendation method based on matrix factorization and machine learning Download PDFInfo
- Publication number
- CN117725310A CN117725310A CN202311706969.6A CN202311706969A CN117725310A CN 117725310 A CN117725310 A CN 117725310A CN 202311706969 A CN202311706969 A CN 202311706969A CN 117725310 A CN117725310 A CN 117725310A
- Authority
- CN
- China
- Prior art keywords
- solution
- machine learning
- user
- matrix factorization
- recommendation
- 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
- 238000010801 machine learning Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 64
- 239000011159 matrix material Substances 0.000 title claims abstract description 57
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 abstract description 7
- 239000003550 marker Substances 0.000 abstract description 2
- 230000003287 optical effect Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Abstract
The application discloses a solution recommendation method based on matrix factorization and machine learning, which comprises the following steps: s1, initializing an MLContext object; s2, loading solution information of each user, and generating a training data set; s3, converting the user ID and the solution ID into a digital key type Feature column, and adding the digital key type Feature column into a new data set column; adding a matrix factorization training algorithm to the new dataset columns; converting a training dataset based on data of the specified algorithm marker features as a machine learning model; s4, predicting a plurality of inputs of training data set data based on a machine learning model, and training the machine learning model; s5, generating a prediction engine based on the trained machine learning model, and predicting the single data instance based on the prediction engine. The invention adopts the matrix factorization training and machine learning methods, and can realize the function of recommending personalized solutions to users according to the user information and the actual operation records of the users in the solution database.
Description
Technical Field
The present application relates to the field of machine learning technologies, and in particular, to a solution recommendation method, apparatus, and storage medium based on matrix factorization and machine learning.
Background
When the manufacturing and assembling system works, the solutions of different staff to the same alarm can be different when facing the equipment alarm, and the system can recommend a plurality of solutions which are most likely to be adopted by the staff from all the solutions for selection so as to avoid the situation that the problem cannot be quickly solved when a new staff goes on duty.
However, existing recommendation systems are relatively single in function, most users interact with only a few solutions, which makes it difficult to capture the user's preferences, and recommendation systems tend to be over-specialized, i.e. to recommend to the user only similar solutions to their previous selections, ignoring the possible diversity, and failing to truly personalize the solutions that the recommended user is most likely to select.
Disclosure of Invention
In order to meet at least one defect or improvement requirement of the prior art, the invention provides a solution recommending method based on matrix factorization and machine learning, and the function of recommending personalized solutions to users can be realized according to user information and user actual operation records in a solution database by adopting the matrix factorization training and machine learning method.
To achieve the above object, according to a first aspect of the present invention, there is provided a solution recommendation method based on matrix factorization and machine learning, the method comprising the steps of:
s1, initializing an MLContext object;
s2, loading solution information of each user from a solution database, and generating a set of user IDs, solution IDs and solution scores, namely a training data set;
s3, converting each user ID and each solution ID into a digital key type Feature column based on a MapValueToKey method, and adding the digital key type Feature column into a new data set column; adding a matrix factorization training algorithm to the new data set column to generate data of a designated algorithm marking characteristic; converting a training dataset based on the data of the specified algorithm marker feature as a machine learning model;
s4, predicting a plurality of inputs of the training data set data based on the machine learning model to obtain a prediction set, comparing the prediction set with actual Lables to obtain indexes of the execution condition of the machine learning model, and training the machine learning model based on the indexes;
s5, generating a prediction engine based on the trained model, predicting a single data instance based on the prediction engine, and determining a recommended solution list based on a prediction result.
Further, the solution recommending method based on matrix factorization and machine learning, wherein the solution list recommended based on the prediction result is determined, further comprises:
generating a prediction recommendation parameter for the prediction result, and determining a list of recommended solutions based on the recommendation parameter.
Further, the solution recommendation method based on matrix factorization and machine learning, before step S1, collects system information, including:
acquiring user information, equipment alarm information and a solution, and acquiring a default score of the solution; wherein, a device alarm message can be associated with a plurality of solutions, and the entered solutions are visible to all users.
Further, in the solution recommending method based on matrix factorization and machine learning, after system information is input, communication parameters of a programmable logic controller are configured in a configuration database, the programmable logic controller monitors equipment alarm, and an equipment alarm information collector reads equipment alarm information from the programmable logic controller in real time;
after the equipment alarm information collector reads the equipment alarm information from the programmable logic controller, the equipment alarm information collector calls webapi of the solution recommendation system to push the equipment alarm information to the server;
the solution recommendation system reads all solutions of the device alarm information from the solution database.
Further, the solution recommending method based on matrix factorization and machine learning, wherein the user information comprises user ID, user name and user authority;
the solution information includes a solution ID, a solution name, solution content, an attachment address, and a score.
Further, the solution recommending method based on matrix factorization and machine learning includes starting time, recovery time, equipment name, alarm classification, alarm variable address in the programmable logic controller, alarm content, alarm position, level, position code, operator and solution ID.
Further, in the solution recommendation method based on matrix factorization and machine learning, after the user selects a certain recommended solution, recommendation degree parameter evaluation is performed on the solution again based on the solution selected by the user.
Further, according to the solution recommendation method based on matrix factorization and machine learning, after a new user enters the system, the solution recommendation system trains a model by using the latest data, and the recommendation degree parameter evaluation of the new user solution is obtained.
According to a second aspect of the present invention there is also provided a solution recommendation device based on matrix factorization and machine learning comprising at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of any of the methods described above.
According to a third aspect of the present invention there is also provided a storage medium storing a computer program executable by an access authentication device, the computer program, when run on the access authentication device, causing the access authentication device to perform the steps of any one of the methods described above.
In general, the above technical solutions conceived by the present invention, compared with the prior art, enable the following beneficial effects to be obtained:
(1) According to the solution recommending method based on matrix factorization and machine learning, provided by the invention, the function of recommending personalized solutions to users can be realized according to the user information and the actual operation records of the users in the solution database by adopting the matrix factorization training and machine learning method.
(2) By adopting the solution recommendation method based on matrix factorization and machine learning, which is provided by the invention, the equipment alarm collector reads the alarm information from the programmable logic controller in real time, the alarm information can be acquired and the solution can be pushed at the first time when equipment fault alarm occurs, the reaction speed is high, and a user can process equipment faults based on the solution in time. .
(3) By adopting the solution recommending method based on matrix factorization and machine learning, which is provided by the invention, after a new user enters the system, the solution recommending system trains the model by using the latest data to obtain the score of the solution of the new user, so that the condition of the latest user can be adapted, and the condition that no historical data is cold-started when a fault occurs is avoided.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a solution recommendation method based on matrix factorization and machine learning according to an embodiment of the present application.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention. In addition, the technical features of the embodiments of the present invention described below may be combined with each other as long as they do not collide with each other.
The terms first, second, third and the like in the description and in the claims of the application and in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a particular sequential or chronological order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
The application relates to a solution recommendation system, which comprises a programmable logic controller, a configuration database, a solution recommendation system, an equipment alarm information collector, a server and an upper computer. The programmable logic controller is used for collecting equipment alarm information; the configuration database is used for storing communication parameters of the programmable logic controller; the solution database is used for maintaining system information, including user information, equipment alarm information and solution information; the solution recommendation system is used for pushing a solution to a specific user according to the equipment alarm information pushed by the equipment alarm information collector; the equipment alarm information collector is used for collecting equipment alarm information in the programmable logic controller and pushing the equipment alarm information to the solution recommendation system; the server is used for installing a solution database and a solution recommendation system; the upper computer is used for installing a configuration database and an equipment alarm information collector.
Fig. 1 is a solution recommendation method based on matrix factorization and machine learning, provided by the present application, comprising the following steps:
s1, initializing an MLContext object.
Specifically, the solution recommendation method based on matrix factorization and machine learning is mainly implemented under an ML.NET framework, and the ML.NET framework is used for training, building and publishing a machine learning model. The MLContext is the starting point of the ML.NET operation, is used for creating and using an ML.NET model, and can load and convert data after the MLContext is added, so as to select the optimal algorithm and training model for the machine learning task. After training, the accuracy of the model can be tested, and the model can be saved and used for prediction. After initializing the MLContext object, an ML context can be created, which can be used for data preparation, feature engineering, training, prediction, and model evaluation.
S2 loads per-user solution information from the solution database for generating a set of user IDs, solution IDs and solution scores, i.e. a training dataset.
Specifically, each user's solution information is loaded from a solution database for generating a set of user IDs, solution IDs, and solution scores, i.e., a training dataset. Where the dataset is the starting point for building a machine learning model, the dataset is essentially an M x N matrix, where M represents the columns (features) and N represents the rows (samples).
S3, converting each user ID and each solution ID into a digital key type Feature column based on a MapValueToKey method, and adding the digital key type Feature column into a new data set column; adding a matrix factorization training algorithm to the new data set column to generate data of the marking characteristics of the designated algorithm; the training dataset is transformed based on the data specifying algorithmic signature as a machine learning model.
Specifically, the mapvalue Key method may convert a string value Type into a Key Type, and encode a tag value. In machine learning, features are used to describe an attribute or index of a particular aspect in a dataset, a Feature may be a column or a variable in the dataset, typically used to train a model to predict a target variable or perform other tasks.
Each user ID and each solution ID are converted into a digital key type Feature column based on the mapvalue key method, that is, original data is converted into Feature-labeled data, and the Feature-labeled data is added as a new data set column. Matrix factorization training (Matrix Factorization Trainer) algorithms are added to the new dataset columns, algorithm parameters are set, the algorithm parameters are stored in options, and data specifying algorithm marking characteristics are generated. The matrix factorization training algorithm is a recommendation training algorithm that means that joining user 1 has the same perspective on a problem as user 2, then user 1 is more likely to have the same perspective on another problem as user 2.
The training dataset is transformed based on the data specifying algorithmic signature as a machine learning model. The matrix factorization training method for setting parameters can convert the data of the marking characteristics into a machine learning model, and can call the corresponding part of the ML.NET framework to realize the functions. The machine model is usually a quantitative model. Machine learning model building algorithms can be divided into three categories: the specific modeling method used for supervised learning, unsupervised learning and reinforcement learning depends on the actual situation.
S4, predicting a plurality of inputs of the training data set data based on the machine learning model to obtain a prediction set, comparing the prediction set with actual Lables to obtain indexes of the execution condition of the machine learning model, and training the machine learning model based on the indexes.
In particular, a prediction set is obtained by predicting a plurality of inputs of training dataset data based on a machine learning model, wherein the inputs may be operation log data of a user, i.e. the prediction set predicts possible results of a user selection solution by means of the model. The resulting prediction set is compared to actual Lables, where Labels are the target or output variables in the data set, which model predicted, categorized or analyzed values. The labels are reference answers or target results used in training the machine learning model. And comparing the predicted result with the target result to obtain an index of the execution condition of the machine learning model, wherein the evaluation method can call a corresponding part in the ML.NET framework to realize, can evaluate the execution condition of the machine learning model, obtain the index of the execution condition of the machine learning model, and adjust and train the machine learning model based on the index.
S5, generating a prediction engine based on the trained machine learning model, predicting a single data instance based on the prediction engine, and determining a recommended solution list based on a prediction result.
Specifically, a prediction engine may be generated based on the ml.net framework based on the trained machine learning model, and a single data instance is predicted based on the prediction engine, wherein the single data instance is an operation record of the user, and a recommended solution list is determined based on the prediction result.
According to the solution recommending method based on matrix factorization and machine learning, provided by the invention, the function of recommending personalized solutions to users can be realized according to the user information and the actual operation records of the users in the solution database by adopting the matrix factorization training and machine learning method.
Optionally, the solution recommending method based on matrix factorization and machine learning provided by the application specifically includes that a recommended solution list is determined based on a prediction result:
generating a predicted recommendation parameter for the predicted result, and determining a list of recommended solutions based on the predicted recommendation parameter.
Specifically, the prediction engine may generate a prediction recommendation parameter for the prediction result, and may determine the solution list by the prediction recommendation parameter. The recommendation parameters can be selected according to actual needs, and the solutions can be ordered in a list based on the recommendation parameters. In one embodiment, the recommendation parameter may be a predictive score based on the likelihood that the user selected the solution, e.g., the higher the predictive score the greater the likelihood that the user will take the solution, the solutions may be ranked in order of predictive score from high to low, facilitating the user's selection of the appropriate solution.
According to the solution recommending method based on matrix factorization and machine learning, through determining the list of recommended solutions based on the prediction recommendation degree parameter, a user can select a proper solution more quickly, and the fault solving efficiency is improved.
Optionally, the solution recommendation method based on matrix factorization and machine learning provided in the present application collects system information before step S1, including:
acquiring user information, equipment alarm information and a solution, and acquiring a default score of the solution; wherein, a device alarm message can be associated with a plurality of solutions, and the entered solutions are visible to all users.
Specifically, user information can be input into the solution recommendation system, alarm information of the assembly manufacturing system can be input into the solution recommendation system, corresponding solutions can be added to the alarm information, multiple solutions can be added to one alarm information, namely, different users can input own solutions to the same alarm information respectively, and the input solutions are visible to all users.
According to the solution recommending method based on matrix factorization and machine learning, through collecting system information, alarm information and a solution can be added to a solution recommending system for subsequent machine learning model construction and training.
Optionally, in the solution recommendation method based on matrix factorization and machine learning provided by the application, after system information is input, communication parameters of a programmable logic controller are configured in a configuration database, the programmable logic controller monitors equipment alarm, and an equipment alarm information collector reads equipment alarm information from the programmable logic controller in real time.
Specifically, after system information is recorded, communication parameters of a Programmable Logic Controller (PLC) are configured in a configuration database, so that the PLC can communicate with other parts in the system, the PLC can monitor equipment alarm, the equipment alarm information collector reads the equipment alarm information from the PLC in real time, namely, when equipment fails and alarms, the PLC monitors the equipment alarm and communicates with the equipment alarm information collector, and the equipment alarm information collector can read the monitored alarm information in the PLC.
After the equipment alarm information collector reads the equipment alarm information from the programmable logic controller, the equipment alarm information collector calls webapi of the solution recommendation system to push the equipment alarm information to the server.
The solution recommendation system reads all solutions of the device alarm information from the solution database.
Specifically, after the device alarm information collector reads the device alarm information from the programmable logic controller, the device alarm information collector calls webapi of the solution recommendation system to push the device alarm information to the server, wherein the webapi is a new framework for constructing the HTTP service. The webapi of the solution recommendation system is internally provided with a singalR, and all front-end web interfaces subscribe to the singalR, namely when the server receives alarm information, all logged-in users can receive alarm prompts. The solution recommendation system reads all solutions of the device alarm information from the solution database.
According to the solution recommending method based on matrix factorization and machine learning, the equipment alarm collector reads the alarm information from the programmable logic controller in real time, the alarm information can be acquired and the solution can be pushed in the first time when equipment fault alarm occurs, the response speed is high, and a user can process equipment faults based on the solution in time.
Optionally, the solution recommendation method based on matrix factorization and machine learning provided by the application, wherein the user information comprises a user ID, a user name and a user authority;
the solution information includes a solution ID, a solution name, solution content, an attachment address, and a score.
The solution recommending method based on matrix factorization and machine learning can be used for generating and training a machine learning model in the subsequent steps by setting user information and solution information.
Optionally, the solution recommending method based on matrix factorization and machine learning provided by the application, wherein the equipment alarm information comprises a start time, a recovery time, an equipment name, an alarm classification, an alarm variable address, alarm content, an alarm position, a level, a position code, an operator and a solution ID in the programmable logic controller.
According to the solution recommendation method based on matrix factorization and machine learning, the alarm information can be clearer through setting the equipment alarm information.
Optionally, the solution recommendation method based on matrix factorization and machine learning provided by the application re-scores solutions based on the solutions selected by the user after the user selects a certain recommended solution.
Specifically, after the user selects a recommended solution, the user and the solution selected by the user may be added to the training data set, to adjust the machine learning model to adapt to the new data, and the recommendation parameter evaluation may be performed again on the solution to update the scoring system to adapt to the new environment.
According to the solution recommendation method based on matrix factorization and machine learning, recommendation degree parameter evaluation is conducted on the solutions based on the solutions selected by the user after the user selects a certain solution, and the machine learning model recommendation strategy can be updated to adapt to the updated environment.
Optionally, the solution recommendation method based on matrix factorization and machine learning provided by the application trains the model by using the latest data after a new user enters the system, and obtains the recommendation degree parameter evaluation of the new user solution.
According to the solution recommendation method based on matrix factorization and machine learning, after a new user enters the system, the solution recommendation system trains a model by using the latest data, and obtains the recommendation degree parameter evaluation of the new user solution, so that the situation of the latest user can be adapted, and the situation that no historical data is cold-started when a fault occurs is avoided.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the above method. The computer readable storage medium may include, among other things, any type of disk including floppy disks, optical disks, DVDs, CD-ROMs, micro-drives, and magneto-optical disks, ROM, RAM, EPROM, EEPROM, DRAM, VRAM, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of media or device suitable for storing instructions and/or data.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random-access Memory (Random Access Memory, RAM), magnetic or optical disk, and the like.
The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Embodiments of the present disclosure will be readily apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any adaptations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
It will be readily appreciated by those skilled in the art that the foregoing description is merely a preferred embodiment of the invention and is not intended to limit the invention, but any modifications, equivalents, improvements or alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (10)
1. A solution recommendation method based on matrix factorization and machine learning, comprising the steps of:
s1, initializing an MLContext object;
s2, loading solution information of each user from a solution database, and generating a set of user IDs, solution IDs and solution scores, namely a training data set;
s3, converting each user ID and each solution ID into a digital key type Feature column based on a MapValueToKey method, and adding the digital key type Feature column into a new data set column; adding a matrix factorization training algorithm to the new data set column to generate data of a designated algorithm marking characteristic; converting the training data set based on the data of the specified algorithm signature feature as a machine learning model;
s4, predicting a plurality of inputs of the training data set data based on the machine learning model to obtain a prediction set, comparing the prediction set with actual Lables to obtain indexes of the execution condition of the machine learning model, and training the machine learning model based on the indexes;
s5, generating a prediction engine based on the trained machine learning model, predicting a single data instance based on the prediction engine, and determining a recommended solution list based on a prediction result.
2. The solution recommendation method based on matrix factorization and machine learning according to claim 1, wherein the determining a recommended solution list based on a prediction result specifically comprises:
generating a recommendation degree parameter for the prediction result, and determining a recommended solution list based on the recommendation degree parameter.
3. The solution recommendation method based on matrix factorization and machine learning according to claim 1, wherein collecting system information before step S1 comprises:
acquiring user information, equipment alarm information and a solution, and acquiring a default score of the solution; wherein, a device alarm message can be associated with a plurality of solutions, and the entered solutions are visible to all users.
4. The solution recommending method based on matrix factorization and machine learning according to claim 3, wherein after inputting system information, the communication parameters of the programmable logic controller are configured in the configuration database, the programmable logic controller monitors equipment alarm, and the equipment alarm information collector reads equipment alarm information from the programmable logic controller in real time;
after the equipment alarm information collector reads the equipment alarm information from the programmable logic controller, the equipment alarm information collector calls webapi of the solution recommendation system to push the equipment alarm information to the server;
the solution recommendation system reads all solutions of the device alarm information from the solution database.
5. The solution recommendation method based on matrix factorization and machine learning according to claim 4, wherein the user information includes a user ID, a user name, and a user right;
the solution information includes a solution ID, a solution name, solution content, an attachment address, and a score.
6. The solution recommendation method based on matrix factorization and machine learning of claim 4, wherein the device alarm information comprises a start time, a resume time, a device name, an alarm classification, an alarm variable address in a programmable logic controller, alarm content, an alarm location, a level, a location code, an operator, and a solution ID.
7. The solution recommendation method based on matrix factorization and machine learning according to claim 1, wherein after a user selects a recommended solution, the solution is re-evaluated for recommendation parameters based on the user selected solution.
8. The solution recommendation method based on matrix factorization and machine learning of claim 1, wherein the solution recommendation system trains the model with up-to-date data after a new user enters the system, obtaining a recommendation level parameter evaluation for the new user.
9. A solution recommendation device based on matrix factorization and machine learning, characterized by comprising at least one processing unit and at least one storage unit, wherein the storage unit stores a computer program which, when executed by the processing unit, causes the processing unit to perform the steps of the method of any of claims 1-8.
10. A storage medium storing a computer program executable by an access authentication device, the computer program, when run on the access authentication device, causing the access authentication device to perform the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311706969.6A CN117725310A (en) | 2023-12-12 | 2023-12-12 | Solution recommendation method based on matrix factorization and machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311706969.6A CN117725310A (en) | 2023-12-12 | 2023-12-12 | Solution recommendation method based on matrix factorization and machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117725310A true CN117725310A (en) | 2024-03-19 |
Family
ID=90199173
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311706969.6A Pending CN117725310A (en) | 2023-12-12 | 2023-12-12 | Solution recommendation method based on matrix factorization and machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117725310A (en) |
-
2023
- 2023-12-12 CN CN202311706969.6A patent/CN117725310A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bendakir et al. | Using association rules for course recommendation | |
| US10460617B2 (en) | Testing system | |
| JP2019533242A (en) | System and method for predicting fraud in automobile warranty | |
| CN103733194A (en) | Dynamically organizing cloud computing resources to facilitate discovery | |
| JP2019185422A (en) | Failure prediction method, failure prediction device, and failure prediction program | |
| CN113010389A (en) | Training method, fault prediction method, related device and equipment | |
| JP2018147407A (en) | Factor estimation device, factor estimation system, and factor estimation method | |
| CN111563156A (en) | Intelligent knowledge point diagnosis method and device, electronic equipment and storage medium | |
| CN111080417A (en) | Processing method for improving booking smoothness rate, model training method and system | |
| Rupnik et al. | Integrating data mining and decision support through data mining based decision support system | |
| KR100736033B1 (en) | Apparatus and method for growing automatically up business process | |
| CN117725310A (en) | Solution recommendation method based on matrix factorization and machine learning | |
| Özpeynirci et al. | An interactive approach for inverse multiple criteria sorting problem | |
| CN115147020B (en) | Decoration data processing method, device, equipment and storage medium | |
| CN112365302B (en) | Product recommendation network training method, device, equipment and medium | |
| CN113377640B (en) | Method, medium, device and computing equipment for explaining model under business scene | |
| US20220198367A1 (en) | Expert matching through workload intelligence | |
| EP4049213A1 (en) | Account prediction using machine learning | |
| Elsaid et al. | Automatic framework for requirement analysis phase | |
| US20080300934A1 (en) | System and method for evolutionary learning of best-of-breed business processes | |
| JP2021170244A (en) | Learning model construction system and method of the same | |
| CN112163167A (en) | Intelligent decision-making method, system, equipment and medium based on big data platform | |
| CN113238770B (en) | Product platform updating method and device, electronic equipment and storage medium | |
| Pinheiro et al. | A bi‐objective procedure to deliver actionable knowledge in sport services | |
| CN111861404B (en) | Data processing method and device based on intelligent machine and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |