CN110851292A - Method and device for intelligently preventing operation errors and computer-readable storage medium - Google Patents
Method and device for intelligently preventing operation errors and computer-readable storage medium Download PDFInfo
- Publication number
- CN110851292A CN110851292A CN201910972273.5A CN201910972273A CN110851292A CN 110851292 A CN110851292 A CN 110851292A CN 201910972273 A CN201910972273 A CN 201910972273A CN 110851292 A CN110851292 A CN 110851292A
- Authority
- CN
- China
- Prior art keywords
- data set
- solution
- operation error
- error
- error data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000002265 prevention Effects 0.000 claims abstract description 36
- 238000006243 chemical reaction Methods 0.000 claims abstract description 33
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims description 37
- 230000006870 function Effects 0.000 claims description 19
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000006073 displacement reaction Methods 0.000 description 39
- 238000012795 verification Methods 0.000 description 13
- 230000004913 activation Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 6
- 230000004048 modification Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000004973 liquid crystal related substance Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/004—Error avoidance
Abstract
The invention relates to an artificial intelligence technology, and discloses an intelligent operation error prevention method, which comprises the following steps: the method comprises the steps of obtaining an original operation error data set and a solution data set, preprocessing the original operation error data set to obtain an operation error data set, carrying out word vector conversion on the operation error data set and the solution data set to obtain a word vectorization operation error data set and a word vectorization solution data set, inputting the word vectorization operation error data set to a feature extraction model to obtain an operation feature data set, carrying out clustering operation on the operation feature data set and the word vectorization solution data set to obtain an error-prone data set, receiving operation of a user, and intelligently reminding the user according to the error-prone data set. The invention also provides a device for intelligently preventing the operation error and a computer readable storage medium. The invention can realize the function of high-efficiency intelligent operation error prevention.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a method and a device for intelligent prevention based on user operation and a computer readable storage medium.
Background
At present, a large amount of information needs to be input in various webpage or APP operation processes, if the information is not noticed slightly, errors can occur when the information is input, and for example, in the process of insuring a new energy vehicle, if the displacement is not modified, insuring failure can occur, and the start date and the end date of business insurance and forced insurance are inconsistent, insuring failure can also occur. At present, based on the problems, traversing the whole operation input information to determine whether the operation input information is consistent with a preset standard or not is mostly adopted, if the operation input information is not consistent with the preset standard, text reminding is carried out on the relevant input information which is not consistent, and a user revises the information again according to the text reminding backtracking.
Disclosure of Invention
The invention provides a method and a device for intelligently preventing operation errors and a computer readable storage medium, and mainly aims to intelligently prevent links which are easy to generate errors in user operation.
In order to achieve the above object, the present invention provides a method for intelligently preventing an operation error, including:
acquiring an original operation error data set and a solution data set;
filling missing data and rechecking operation are carried out on the original operation error data set to obtain an operation error data set;
performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set;
inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set;
clustering the operation characteristic data set and the word vectorization solution data set to obtain an error-prone data set;
and receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
Optionally, the word vector conversion comprises:
presetting a weight relationship between the operation error data set and the vectorization operation error data set, and between the solution data set and the word vectorization solution data set;
calculating a weight between the operation error data set and the solution data set based on the weight relationship, and completing the word vector conversion process according to the weight.
Alternatively,
d＝{(t1,w1),(t2,w2),……,(ti,wi),……，(tn,wn)}
wherein d is the operation error data set or the solution data set, t1、t2、……、tnFor each piece of textual information of the operation error data set or the solution data set, w, i.e. each piece of data of the operation error data set or the solution data set1、w2、……、wnThe weight corresponding to each piece of text information; and
the calculating a weight between the operational error data set and the solution data set, comprising:
wherein f is1Representing the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmIs a weighting factor.
Optionally, the clustering operation comprises:
calculating a distance between the operating characteristic dataset and the word vectorization solution dataset;
optimizing a function of the clustering center and the distance to obtain an optimal value set;
and obtaining a data set which is most prone to errors in the operation process according to the optimal value set.
Alternatively,
the distance is as follows:
wherein D is the word vectorization solution dataset, D is a total amount of data of the word vectorization solution dataset, C is the operation feature dataset, C is a total amount of data of the operation feature dataset, xi,dA word vector, x, representing data i of the word vectorization solution datasetj,cCharacteristic data representing data j of the operating characteristic data set.
In addition, to achieve the above object, the present invention further provides an apparatus for intelligently preventing an operation error, including a memory and a processor, where the memory stores therein a program for intelligently preventing an operation error that can be executed on the processor, and the program for intelligently preventing an operation error, when executed by the processor, implements the following steps:
acquiring an original operation error data set and a solution data set;
filling missing data and rechecking operation are carried out on the original operation error data set to obtain an operation error data set;
performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set;
inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set;
clustering the operation characteristic data set and the word vectorization solution data set to obtain an error-prone data set;
and receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
Optionally, the word vector conversion comprises:
presetting a weight relationship between the operation error data set and the vectorization operation error data set, and between the solution data set and the word vectorization solution data set;
calculating a weight between the operation error data set and the solution data set based on the weight relationship, and completing the word vector conversion process according to the weight.
Alternatively,
d＝{(t1,w1),(t2,w2),……,(ti,wi),……，(tn,wn)}
wherein d is the operation error data set or the solution data set, t1、t2、……、tnFor each piece of textual information of the operation error data set or the solution data set, w, i.e. each piece of data of the operation error data set or the solution data set1、w2、……、wnThe weight corresponding to each piece of text information; and
the calculating a weight between the operational error data set and the solution data set, comprising:
wherein f isiRepresenting the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmIs a weighting factor.
Optionally, the clustering operation comprises:
calculating a distance between the operating characteristic dataset and the word vectorization solution dataset;
optimizing a function of the clustering center and the distance to obtain an optimal value set;
and obtaining a data set which is most prone to errors in the operation process according to the optimal value set.
Furthermore, to achieve the above object, the present invention also provides a computer readable storage medium having stored thereon a program for intelligent operation error prevention, the program being executable by one or more processors to implement the steps of the method for intelligent operation error prevention as described above.
According to the invention, the original operation error data set and the solution data set are obtained and subjected to missing data and re-verification operation, so that the purity of data is ensured, and further, in order to better utilize data, the original operation error data set and the solution data set are subjected to word vector conversion and feature extraction, so that better utilization data is facilitated, and meanwhile, the operation data which is most prone to error is found out based on clustering operation, and intelligent reminding is given to a user. Therefore, the method, the device and the computer readable storage medium for intelligently preventing the operation errors can realize efficient operation error prevention.
Drawings
FIG. 1 is a flow chart illustrating a method for intelligently preventing an operation error according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an internal structure of an apparatus for intelligently preventing operation errors according to an embodiment of the present invention;
fig. 3 is a block diagram illustrating a program for operating error intelligent prevention in the apparatus for operating error intelligent prevention according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a method for intelligently preventing operation errors. Referring to fig. 1, a flow chart of a method for intelligently preventing an operation error according to an embodiment of the present invention is shown. The method may be performed by an apparatus, which may be implemented by software and/or hardware.
In this embodiment, the method for intelligently preventing operation errors includes:
s1, acquiring an original error data set and a solution data set including error operation and error reason.
Preferably, the original error data set refers to a data set which is represented in text form and has an error operation when a user operates on a platform such as a web page, an app and the like. For example, in the process of automobile application operation, as the new automobile license plate number has an urban prefix, such as YueB, if the license plate is on the local city and on the other places, the local city prefix needs to be removed, otherwise, application error operation occurs, such as license plate in Hunan area on Shenzhen area, and YueB needs to be removed; if the displacement is not modified, tax can not be paid in the process of insurance application as a new energy vehicle; if the start date and the end date of the business insurance and the forced insurance are inconsistent, the order will fail at the end of the insurance application; some insurance application types need the insurance applicant and the insured person to be the same person, if the insurance application types are not the same person, the insurance application form failure can be found after all the information is recorded, and therefore the insurance application type needs to return to a page or an app and the like for re-change.
Further, each data of the original error data set includes an error operation and an error cause. Such as when a web page, app, etc. performs an application operation, including performing the error operations resulting from filling in the insured life, filling in the license plate number, filling in the displacement, etc. The error reason refers to the reason of the error operation, for example, the error operation of filling out the insured person is because the insured person and the insured person are not the same person, the error operation of filling out the displacement is because the displacement does not meet the specified displacement interval requirement, the error operation of filling out the license plate number is because of a foreign license plate, a prefix of a local city is not removed, and the like. Therefore, the error operation and the error reason are preferably in a one-to-one correspondence relationship.
The solution data set is a data set that gives a relevant solution to the erroneous operation generated in the original operation error data set, and is generally represented by text data information. As described above, in the solution data set, it is sequentially recorded that the modification of the applicant and the insured person is the same person because of the number plate of the foreign place, and the prefix of the local city needs to be removed when the number plate is filled, and the displacement is modified again, so that the displacement is within the specified displacement interval [ a, b ], and the like.
And S2, filling missing data and re-verifying the original error data set to obtain an error data set.
In the preferred embodiment of the present invention, a small amount of the erroneous operation and the error cause may be missing from the original erroneous data, that is, one of the erroneous operation and the error cause is empty or both of them are empty, that is, a missing value exists. Preferably, when the error operation A is absent, the error reason A corresponding to the error operation A is traversed1According to the error cause A1The error operation A can be obtained, the same as the error reason B1Traversing the error cause B in the absence1Corresponding error operation B, and obtaining the error reason B according to the error operation B1And when the error operation and the error reason are both missing, directly rejecting the error operation and the error reason.
And the re-verification operation is to sequentially traverse each error operation and error reason in the original operation error data, open the corresponding application webpage or app for verification operation, if the verified error operation or error reason does not correspond to the error operation and error reason in the original operation error data, remove the original error operation or error reason of the original operation error data, and replace the original error operation or error reason with the error operation or error reason after the re-verification operation. If the error operation is filling displacement, the corresponding error reason is that the displacement does not meet the requirement of the specified displacement interval [0.8L,4L ], but when the operation is re-verified, the specified displacement interval is found to be [0.9L,4.5L ], so that corresponding modification is carried out.
Preferably, the re-verification operation may use a pre-written script based on JAVA, C + +, or other programming languages to automatically traverse the error operation and the error reason for verification operation.
And S3, performing word vector conversion on the error data set and the solution data set to respectively obtain a word-vectorization error data set and a word-vectorization solution data set.
Because the error data set and the solution data set are both text-form data sets, and the text-form data sets are not beneficial to subsequent feature extraction, the error data set and the solution data set need to be converted into vector forms, the conversion process is word vector conversion, and the conversion completed is a word vector conversion model.
Further, the converting the operation error data set and the solution data set into a word-vectorization operation error data set and a word-vectorization solution data set, respectively, includes: respectively assuming the weight relationship between the operation error data set and the vectorization operation error data set, the weight relationship between the solution data set and the word vectorization solution data set, calculating the weight between the data sets based on the weight relationship, and completing the word vector conversion process according to the weight.
Specifically, the weight relationship is:
d＝{(t1,w1),(t2,w2),……,(ti,wi),……，(tn,wn)}
wherein d is the operation error data set or the solution data set, t1、t2、……、tnFor each piece of textual information of the operation error data set or the solution data set (i.e. each piece of data of the operation error data set or the solution data set), as described above [ insured life ]][ filling in license plate number][ filling discharge volume]Etc. w1、w2、……、wnAnd weighting corresponding to each piece of text information.
Further, the weight calculation method comprises:
wherein f isiRepresenting the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmThe weighting factor is generally less than 1.
Preferably, a weight corresponding to each text message of the operation error data set or the solution data set is calculated, and the weight corresponding to each text message is used to replace each text message, so as to complete the word vector conversion to obtain a word-vectorization operation error data set and a word-vectorization solution data set.
And S4, inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set.
Preferably, the feature extraction model includes an encoding process, and an operational feature output process.
Preferably, the encoding process is based on a Bi-LSTM model, the Bi-LSTM model includes an input gate, an output gate, and a forgetting gate, and the specific decoding process is as follows:
ht＝ot⊙tanh(ct)
wherein t is data of the word vectorization operation error data set,
the unit representing the data t before the memory of the Bi-LSTM model, ctRepresenting the cells of the data t after the memory of said Bi-LSTM model, ct-1Represents the unit of the data t-1 after the memory of the Bi-LSTM model, and sigma is sigmoid function ot,it,ftRespectively representing the updated values of the input gate, the forgetting gate and the output gate, ⊙ representing the element product, tanh being an arc tangent function, W being the weight of the Bi-LSTM model, b being the bias of the Bi-LSTM model, htRepresenting a coded value, h, representing data tt-1Representing the encoded value representing data t-1.
Further, the operation characteristic output process includes: and solving the coding value based on the sigma (sigmoid function) to obtain an activation value, judging the size of the activation value and a preset threshold value, abandoning the activation value when the activation value is smaller than the preset threshold value, and outputting the activation value as an operation characteristic when the activation value is larger than the preset threshold value.
And S5, carrying out clustering operation on the operation characteristic data set and the word vectorization solution data set to obtain a data set which is most prone to error.
Preferably, the clustering operation comprises: and calculating the distance between the operation characteristic data set and the word vectorization solution data set, optimizing a function of a clustering center and the distance to obtain an optimal value set, and obtaining a data set which is most prone to error in the operation process according to the optimal value set.
The distance is
Wherein D is the word vectorization solution dataset, D is a total amount of data of the word vectorization solution dataset, C is the operation feature dataset, C is a total amount of data of the operation feature dataset, xi,dA word vector, x, representing data i of the word vectorization solution datasetj,cTo representCharacteristic data of data j of the operating characteristic data set.
The function of the cluster center and the distance is:
wherein J is a function of the cluster Center and the distance, K is the number of clusters of the clustering operation, CenterkIs the cluster center, x, corresponding to the cluster KiIs said distance, i.e. xi＝dist(xi,d,xj,c)。
Further, a function J that optimizes the cluster center and the distance obtains an optimal value, and the optimal value set includes various operation feature data that are most likely to generate operation errors and corresponding word vectorization solution data.
Preferably, the error-prone data set is solved reversely according to the optimal value set, wherein the optimal value set comprises operation characteristic data which is most prone to operation errors and corresponding word vectorization solution data, and the reverse solution comprises word vectorization, encoding and other operations corresponding to S3-S4. The most error prone data set comprises three parts of error operation, error reason and solution.
And S6, receiving the operation of the user, and carrying out intelligent prevention reminding on the operation of the user according to the most error-prone data set.
If the user writes in the automobile displacement in the insurance process, the user can traverse the error operation in the data set which is most prone to error to determine whether the automobile displacement exists, if so, the automobile displacement (error operation) is fed back to the user when the displacement does not meet the specified displacement interval requirement (error reason) and the automobile displacement needs to meet the requirement (solution) in the displacement interval [ a, b ], so that the purpose of intelligent prevention reminding is achieved.
The invention also provides a device for intelligently preventing operation errors. Referring to fig. 2, there is shown an internal structural diagram of an apparatus for intelligently preventing an operation error according to an embodiment of the present invention.
In the present embodiment, the device 1 for intelligently preventing operation errors may be a PC (personal computer), or a terminal device such as a smart phone, a tablet computer, or a portable computer, or may be a server. The apparatus 1 for intelligent prevention of operating errors comprises at least a memory 11, a processor 12, a communication bus 13, and a network interface 14.
The memory 11 includes at least one type of readable storage medium, which includes a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the apparatus 1 for intelligent protection of operational errors, for example a hard disk of the apparatus 1 for intelligent protection of operational errors. The memory 11 may in other embodiments also be an external storage device of the apparatus 1 for intelligent protection against operating errors, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which is provided on the apparatus 1 for intelligent protection against operating errors. Further, the memory 11 may also comprise both an internal memory unit and an external memory device of the apparatus 1 for intelligent prevention of operating errors. The memory 11 can be used not only for storing application software installed in the apparatus for intelligently preventing operation errors 1 and various kinds of data, such as a code of the program 01 for intelligently preventing operation errors, etc., but also for temporarily storing data that has been output or is to be output.
The processor 12 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip in some embodiments, and is used for executing program codes stored in the memory 11 or Processing data, such as executing the program 01 for intelligently preventing operation errors.
The communication bus 13 is used to realize connection communication between these components.
The network interface 14 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), typically used to establish a communication link between the apparatus 1 and other electronic devices.
Optionally, the apparatus 1 may further comprise a user interface, which may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-emitting diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the apparatus 1 for intelligent prevention of operating errors and for displaying a visual user interface.
Fig. 2 shows only the apparatus 1 for operational error intelligent prevention with the components 11-14 and the program 01 for operational error intelligent prevention, it being understood by a person skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the apparatus 1 for operational error intelligent prevention, and may comprise fewer or more components than shown in the figures, or a combination of certain components, or a different arrangement of components.
In the embodiment of the device 1 shown in fig. 2, a program 01 for intelligently preventing operation errors is stored in the memory 11; the processor 12 executes the program 01 for intelligently preventing operation errors stored in the memory 11, and implements the following steps:
the method comprises the steps of firstly, obtaining an original error data set and a solution data set which comprise error operation and error reasons.
Preferably, the original error data set refers to a data set which is represented in text form and has an error operation when a user operates on a platform such as a web page, an app and the like. For example, in the process of automobile application operation, as the new automobile license plate number has an urban prefix, such as YueB, but if the license plate is on the local city and on the other places, the local city prefix needs to be removed, otherwise the application error operation occurs, and if the license plate is on the Hunan area on Shenzhen, the YueB needs to be removed; if the displacement is not modified, tax can not be paid in the process of insurance application as a new energy vehicle; if the start date and the end date of the business insurance and the forced insurance are inconsistent, the order will fail at the end of the insurance application; some insurance application types need the insurance applicant and the insured person to be the same person, if the insurance application types are not the same person, the insurance application form failure can be found after all the information is recorded, and therefore the insurance application type needs to return to a page or an app and the like for re-change.
Further, each data of the original error data set includes an error operation and an error cause. Such as when a web page, app, etc. performs an application operation, including performing the error operations resulting from filling in the insured life, filling in the license plate number, filling in the displacement, etc. The error reason refers to the reason of the error operation, for example, the error operation of filling out the insured person is because the insured person and the insured person are not the same person, the error operation of filling out the displacement is because the displacement does not meet the specified displacement interval requirement, the error operation of filling out the license plate number is because of a foreign license plate, a prefix of a local city is not removed, and the like. Therefore, the error operation and the error reason are preferably in a one-to-one correspondence relationship.
The solution data set is a data set that gives a relevant solution to the erroneous operation generated in the original operation error data set, and is generally represented by text data information. As described above, in the solution data set, it is sequentially recorded that the modification of the applicant and the insured person is the same person because of the number plate of the foreign place, and the prefix of the local city needs to be removed when the number plate is filled, and the displacement is modified again, so that the displacement is within the specified displacement interval [ a, b ], and the like.
And step two, filling missing data and re-verifying the original operation error data set to obtain an operation error data set.
In the preferred embodiment of the present invention, a small amount of the erroneous operation and the error cause may be missing from the original operation error data, that is, one of the erroneous operation and the error cause is empty or both of them are empty, that is, a missing value exists. Preferably, when the error operation A is absent, the error reason A corresponding to the error operation A is traversed1According to the error cause A1The error operation A can be obtained, the same as the error reason B1Traversing the error cause B in the absence1Corresponding error operation B, according to which the error can be obtainedReason for error B1And when the error operation and the error reason are both missing, directly rejecting the error operation and the error reason.
And the re-verification operation is to sequentially traverse each error operation and error reason in the original operation error data, open the corresponding application webpage or app for verification operation, if the verified error operation or error reason does not correspond to the error operation and error reason in the original operation error data, remove the original error operation or error reason of the original operation error data, and replace the original error operation or error reason with the error operation or error reason after the re-verification operation. If the error operation is filling displacement, the corresponding error reason is that the displacement does not meet the requirement of the specified displacement interval [0.8L,4L ], but when the operation is re-verified, the specified displacement interval is found to be [0.9L,4.5L ], so that corresponding modification is carried out.
Preferably, the re-verification operation may use a pre-written script based on JAVA, C + +, or other programming languages to automatically traverse the error operation and the error reason for verification operation.
And thirdly, performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set.
Because the operation error data set and the solution data set are both text-form data sets, and the text-form data sets are not beneficial to subsequent feature extraction, the operation error data set and the solution data set need to be converted into vector forms, the conversion process is word vector conversion, and the conversion process is completed and is a word vector conversion model.
Further, the converting the operation error data set and the solution data set into a word-vectorization operation error data set and a word-vectorization solution data set, respectively, includes: respectively assuming the weight relationship between the operation error data set and the vectorization operation error data set, the weight relationship between the solution data set and the word vectorization solution data set, calculating the weight between the data sets based on the weight relationship, and completing the word vector conversion process according to the weight.
Specifically, the weight relationship is:
d＝{(t1,w1),(t2,w2),……,(ti,wi),……，(tn,wn)}
wherein d is the operation error data set or the solution data set, t1、t2、……、tnFor each piece of textual information of the operation error data set or the solution data set (i.e. each piece of data of the operation error data set or the solution data set), as described above [ insured life ]][ filling in license plate number][ filling discharge volume]Etc. w1、w2、……、wnAnd weighting corresponding to each piece of text information.
Further, the weight calculation method comprises:
wherein f isiRepresenting the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmThe weighting factor is generally less than 1.
Preferably, a weight corresponding to each text message of the operation error data set or the solution data set is calculated, and the weight corresponding to each text message is used to replace each text message, so as to complete the word vector conversion to obtain a word-vectorization operation error data set and a word-vectorization solution data set.
And step four, inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set.
Preferably, the feature extraction model includes an encoding process, and an operational feature output process.
Preferably, the encoding process is based on a Bi-LSTM model, the Bi-LSTM model includes an input gate, an output gate, and a forgetting gate, and the specific decoding process is as follows:
ht＝ot⊙tanh(ct)
wherein t is data of the word vectorization operation error data set,
the unit representing the data t before the memory of the Bi-LSTM model, ctRepresenting the cells of the data t after the memory of said Bi-LSTM model, ct-1Represents the unit of the data t-1 after the memory of the Bi-LSTM model, and sigma is sigmoid function ot,it,ftRespectively representing the updated values of the input gate, the forgetting gate and the output gate, ⊙ representing the element product, tanh being an arc tangent function, W being the weight of the Bi-LSTM model, b being the bias of the Bi-LSTM model, htRepresenting a coded value, h, representing data tt-1Representing the encoded value representing data t-1.
Further, the operation characteristic output process includes: and solving the coding value based on the sigma (sigmoid function) to obtain an activation value, judging the size of the activation value and a preset threshold value, abandoning the activation value when the activation value is smaller than the preset threshold value, and outputting the activation value as an operation characteristic when the activation value is larger than the preset threshold value.
And fifthly, clustering the operation characteristic data set and the word vectorization solution data set to obtain a data set which is most prone to error.
Preferably, the clustering operation comprises: and calculating the distance between the operation characteristic data set and the word vectorization solution data set, optimizing a function of a clustering center and the distance to obtain an optimal value set, and obtaining a data set which is most prone to error in the operation process according to the optimal value set.
The distance is
Wherein D is the word vectorization solution dataset, D is a total amount of data of the word vectorization solution dataset, C is the operation feature dataset, C is a total amount of data of the operation feature dataset, xi,dA word vector, x, representing data i of the word vectorization solution datasetj,cCharacteristic data representing data j of the operating characteristic data set.
The function of the cluster center and the distance is:
wherein J is a function of the cluster Center and the distance, K is the number of clusters of the clustering operation, CenterkIs the cluster center, x, corresponding to the cluster KiIs said distance, i.e. xi＝dist(xi,d,xj,c)。
Further, a function J that optimizes the cluster center and the distance obtains an optimal value, and the optimal value set includes various operation feature data that are most likely to generate operation errors and corresponding word vectorization solution data.
Preferably, the error-prone data set is solved reversely according to the optimal value set, wherein the optimal value set comprises operation characteristic data which is most prone to operation errors and corresponding word vectorization solution data, and the reverse solution comprises word vectorization, encoding and other operations corresponding to S3-S4. The most error prone data set comprises three parts of error operation, error reason and solution.
And step six, receiving the operation of the user, and carrying out intelligent prevention reminding on the operation of the user according to the data set which is most prone to error.
If the user writes in the automobile displacement in the insurance process, the user can traverse the error operation in the data set which is most prone to error to determine whether the automobile displacement exists, if so, the automobile displacement (error operation) is fed back to the user when the displacement does not meet the specified displacement interval requirement (error reason) and the automobile displacement needs to meet the requirement (solution) in the displacement interval [ a, b ], so that the purpose of intelligent prevention reminding is achieved.
Alternatively, in other embodiments, the program for operating the error intelligent prevention may be further divided into one or more modules, and the one or more modules are stored in the memory 11 and executed by one or more processors (in this embodiment, the processor 12) to implement the present invention.
For example, referring to fig. 3, a schematic diagram of program modules of the operation error intelligent prevention program in an embodiment of the operation error intelligent prevention apparatus of the present invention is shown, in this embodiment, the operation error intelligent prevention program may be divided into the data receiving and processing module 10, the word vector conversion module 20, the feature extraction and clustering module 30, and the operation intelligent prompting module 40, which are exemplarily:
the data receiving and processing module 10 is configured to: and acquiring an original operation error data set and a solution data set, and performing filling missing data and re-verification operation on the original operation error data set to obtain an operation error data set.
The word vector conversion module 20 is configured to: and performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set.
The feature extraction and clustering module 30 is configured to: and inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set, and carrying out clustering operation on the operation feature data set and the word vectorization solution data set to obtain an error-prone data set.
The operation intelligent reminding module 40 is used for: and receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
The functions or operation steps implemented by the data receiving and processing module 10, the word vector conversion module 20, the feature extraction and clustering module 30, the intelligent operation reminding module 40 and other program modules when executed are substantially the same as those of the above embodiments, and are not described herein again.
Furthermore, an embodiment of the present invention provides a computer-readable storage medium, on which a program for intelligent operation error prevention is stored, where the program for intelligent operation error prevention is executable by one or more processors to implement the following operations:
and acquiring an original operation error data set and a solution data set, and performing filling missing data and re-verification operation on the original operation error data set to obtain an operation error data set.
And performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set.
And inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set, and carrying out clustering operation on the operation feature data set and the word vectorization solution data set to obtain an error-prone data set.
And receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
It should be noted that the above-mentioned numbers of the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments. And the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A method of intelligently preventing operational errors, the method comprising:
acquiring an original operation error data set and a solution data set;
filling missing data and rechecking operation are carried out on the original operation error data set to obtain an operation error data set;
performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set;
inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set;
clustering the operation characteristic data set and the word vectorization solution data set to obtain an error-prone data set;
and receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
2. The method of intelligent prevention of operational errors of claim 1 wherein the word vector conversion comprises:
presetting a weight relationship between the operation error data set and the vectorization operation error data set, and between the solution data set and the word vectorization solution data set;
calculating a weight between the operation error data set and the solution data set based on the weight relationship, and completing the word vector conversion process according to the weight.
3. The method of operational error intelligent prevention of claim 2, wherein the weight relationship comprises:
d＝{(t1，w1)，(t2，w2)，......，(ti，wi)，......，(tn，wn)}
wherein d is the operation error data set or the solution data set, t1、t2、......、tnFor each piece of textual information of the operation error data set or the solution data set, w, i.e. each piece of data of the operation error data set or the solution data set1、w2、......、wnThe weight corresponding to each piece of text information; and
the calculating a weight between the operational error data set and the solution data set, comprising:
wherein f isiRepresenting the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmIs a weighting factor.
4. The method of operational operation error intelligent prevention of claim 1, wherein the clustering operation comprises:
calculating a distance between the operating characteristic dataset and the word vectorization solution dataset;
optimizing a function of the clustering center and the distance to obtain an optimal value set;
and obtaining a data set which is most prone to errors in the operation process according to the optimal value set.
5. The method of intelligent prevention of operational errors of claim 4, wherein the distance is:
wherein D is the word vectorization solution dataset, D is a total amount of data of the word vectorization solution dataset, C is the operation feature dataset, C is a total amount of data of the operation feature dataset, xi，dA word vector, x, representing data i of the word vectorization solution datasetj，cCharacteristic data representing data j of the operating characteristic data set.
6. An apparatus for intelligent operation error prevention, the apparatus comprising a memory and a processor, the memory having stored thereon a program for intelligent operation error prevention executable on the processor, the program for intelligent operation error prevention when executed by the processor implementing the steps of:
acquiring an original operation error data set and a solution data set;
filling missing data and rechecking operation are carried out on the original operation error data set to obtain an operation error data set;
performing word vector conversion on the operation error data set and the solution data set to respectively obtain a word vectorization operation error data set and a word vectorization solution data set;
inputting the word vectorization operation error data set into a feature extraction model to obtain an operation feature data set;
clustering the operation characteristic data set and the word vectorization solution data set to obtain an error-prone data set;
and receiving the operation of the user, and intelligently preventing and reminding the operation of the user according to the error-prone data set.
7. The apparatus for intelligent prevention of operational errors as defined in claim 6, wherein the word vector conversion comprises:
presetting a weight relationship between the operation error data set and the vectorization operation error data set, and between the solution data set and the word vectorization solution data set;
calculating a weight between the operation error data set and the solution data set based on the weight relationship, and completing the word vector conversion process according to the weight.
8. The apparatus for intelligent prevention of operational errors as set forth in claim 7, wherein the weight relationship comprises:
d＝{(t1，w1)，(t2，w2)，......，(ti，wi)，......，(tn，wn)}
wherein d is the operation error data set or the resolverSet of case data, t1、t2、......、tnFor each piece of textual information of the operation error data set or the solution data set, w, i.e. each piece of data of the operation error data set or the solution data set1、w2、......、wnThe weight corresponding to each piece of text information; and
the calculating a weight between the operational error data set and the solution data set, comprising:
wherein f isiRepresenting the number of times the text information appears in the operation error data set or the solution data set, N being the total number of data of the operation error data set or the solution data set, NjRepresenting a total number, N, of text messages in the operation error data set or the solution data setiRepresenting the number of occurrences of a text message i in said operation error data set or said solution data set, FmIs a weighting factor.
9. The apparatus for intelligent prevention of operational errors as recited in claim 6, wherein the clustering operation comprises:
calculating a distance between the operating characteristic dataset and the word vectorization solution dataset;
optimizing a function of the clustering center and the distance to obtain an optimal value set;
and obtaining a data set which is most prone to errors in the operation process according to the optimal value set.
10. A computer-readable storage medium, having stored thereon a program for intelligent prevention of operating errors, the program being executable by one or more processors to perform the steps of the method for intelligent prevention of operating errors as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972273.5A CN110851292B (en) | 2019-10-12 | 2019-10-12 | Method, apparatus and computer readable storage medium for intelligent prevention of operation errors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910972273.5A CN110851292B (en) | 2019-10-12 | 2019-10-12 | Method, apparatus and computer readable storage medium for intelligent prevention of operation errors |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110851292A true CN110851292A (en) | 2020-02-28 |
| CN110851292B CN110851292B (en) | 2024-04-02 |
Family
ID=69596258
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910972273.5A Active CN110851292B (en) | 2019-10-12 | 2019-10-12 | Method, apparatus and computer readable storage medium for intelligent prevention of operation errors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110851292B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107111625A (en) * | 2014-09-26 | 2017-08-29 | 甲骨文国际公司 | Realize the method and system of the efficient classification and exploration of data |
| CN109583904A (en) * | 2018-11-30 | 2019-04-05 | 深圳市腾讯计算机系统有限公司 | Training method, impaired operation detection method and the device of abnormal operation detection model |
| US10361802B1 (en) * | 1999-02-01 | 2019-07-23 | Blanding Hovenweep, Llc | Adaptive pattern recognition based control system and method |
-
2019
- 2019-10-12 CN CN201910972273.5A patent/CN110851292B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10361802B1 (en) * | 1999-02-01 | 2019-07-23 | Blanding Hovenweep, Llc | Adaptive pattern recognition based control system and method |
| CN107111625A (en) * | 2014-09-26 | 2017-08-29 | 甲骨文国际公司 | Realize the method and system of the efficient classification and exploration of data |
| CN109583904A (en) * | 2018-11-30 | 2019-04-05 | 深圳市腾讯计算机系统有限公司 | Training method, impaired operation detection method and the device of abnormal operation detection model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110851292B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107145940A (en) | The recurrent neural networks model of compression | |
| CN111414353A (en) | Intelligent missing data filling method and device and computer readable storage medium | |
| WO2020248366A1 (en) | Text intention intelligent classification method and device, and computer-readable storage medium | |
| WO2020253043A1 (en) | Intelligent text classification method and apparatus, and computer-readable storage medium | |
| CN114822812A (en) | Character dialogue simulation method, device, equipment and storage medium | |
| CN107247767B (en) | Method and device for importing formatted data file into database | |
| WO2023040742A1 (en) | Text data processing method, neural network training method, and related devices | |
| CN107943788B (en) | Enterprise abbreviation generation method and device and storage medium | |
| CN112507663A (en) | Text-based judgment question generation method and device, electronic equipment and storage medium | |
| CN113947095A (en) | Multilingual text translation method and device, computer equipment and storage medium | |
| CN112509554A (en) | Speech synthesis method, speech synthesis device, electronic equipment and storage medium | |
| CN104679493A (en) | Improved method for process event handling mechanism | |
| CN110851292A (en) | Method and device for intelligently preventing operation errors and computer-readable storage medium | |
| CN114238656A (en) | Reinforced learning-based affair atlas completion method and related equipment thereof | |
| CN111259318A (en) | Intelligent data optimization method and device and computer readable storage medium | |
| US20230273826A1 (en) | Neural network scheduling method and apparatus, computer device, and readable storage medium | |
| CN114781359A (en) | Text error correction method and device, computer equipment and storage medium | |
| CN111241066A (en) | Automatic operation and maintenance method and device for platform database and computer readable storage medium | |
| CN114625340B (en) | Commercial software research and development method, device, equipment and medium based on demand analysis | |
| CN112084105A (en) | Log file monitoring and early warning method, device, equipment and storage medium | |
| CN113656690B (en) | Product recommendation method and device, electronic equipment and readable storage medium | |
| CN111857715B (en) | H5-based linked pull-down component selection method, device, equipment and storage medium | |
| CN113641714A (en) | Medical data correction method, device, computer equipment and storage medium | |
| CN111026746B (en) | Method, device, computer equipment and storage medium for calling multi-channel data | |
| CN110647566B (en) | Intelligent importing method and device of template table and computer readable storage medium |
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 |