CN114610723B - Data processing method and system based on artificial intelligence and cloud platform - Google Patents
Data processing method and system based on artificial intelligence and cloud platform Download PDFInfo
- Publication number
- CN114610723B CN114610723B CN202210317954.XA CN202210317954A CN114610723B CN 114610723 B CN114610723 B CN 114610723B CN 202210317954 A CN202210317954 A CN 202210317954A CN 114610723 B CN114610723 B CN 114610723B
- Authority
- CN
- China
- Prior art keywords
- vector
- standard
- report data
- return call
- simulated return
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/22—Indexing; Data structures therefor; Storage structures
- G06F16/2282—Tablespace storage structures; Management thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/183—Tabulation, i.e. one-dimensional positioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Abstract
According to the data processing method, the system and the cloud platform based on the artificial intelligence, the error permission vector of the first simulated return call business report data and the report character area relation of the first simulated return call business report data and the second simulated return call business report data are obtained, the second simulated return call business report data is built behind the first simulated return call business report data, the built standard training model of the first simulated return call business report data is generated according to the report character area relation of the first simulated return call business report data and the second simulated return call business report data and the error permission vector of the first simulated return call business report data, when the second simulated return call business report data is the burst return call business report data, the generation efficiency of the second simulated return call business report data on the first simulated return call business report data can be simulated, the integrity of a report generation result is improved, and the high efficiency of data processing is realized.
Description
Technical Field
The application relates to the technical field of data generation, in particular to a data processing method and system based on artificial intelligence and a cloud platform.
Background
Artificial Intelligence (Artificial Intelligence), the definition of Artificial Intelligence can be divided into two parts, namely "Artificial" and "intelligent". "Manual" is well understood and is not controversial. Sometimes we will consider what is available to man and what is manufactured, or whether the level of intelligence of the person himself is so high that artificial intelligence can be created, etc.
In the conventional technology, the recording and inputting process is finished through reports by related technicians on a construction site, so that not only is a large amount of manpower consumed, but also huge time is required. This causes a problem of resource waste.
The relevant data are collected through artificial intelligence, and the generation of a report is completed, so that the efficiency is improved, and the cost can be effectively reduced. However, in the process of generating reports by artificial intelligence, related data are disturbed.
Disclosure of Invention
In view of this, the present application provides a data processing method, system and cloud platform based on artificial intelligence.
In a first aspect, a method for data processing based on artificial intelligence is provided, the method comprising:
calculating first simulated return call service report data according to the established standard training model;
when the current building mode of second simulated return call service report data and the first simulated return call service report data meets a target mode, acquiring an error permission vector of the first simulated return call service report data and a report character area relation of the first simulated return call service report data and the second simulated return call service report data, building the second simulated return call service report data behind the first simulated return call service report data, and using the error permission vector to represent an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data;
and generating the built standard training model according to the report text area relation and the error permission vector.
Further, the generating the built standard training model according to the report text area relationship and the error permission vector includes:
acquiring a correction permission range vector of the first simulated return call service report data, wherein the correction permission range vector is used for representing an execution correction permission range of the first simulated return call service report data;
determining a generation training thread of the built standard training model according to the report text area relation;
and generating the built standard training model according to the corrected allowable range vector and the error allowable vector based on the generated training thread.
Further, the step of building a standard training model includes building a table matching standard, and the step of determining a generation training thread of the built standard training model according to the report text area relationship includes:
when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining the generation training thread of the built standard training model as descending the built table pairing standard;
wherein the generating of the built standard training model according to the modified allowable range vector and the error allowable vector comprises:
acquiring the set-up form pairing standard currently configured by the first simulated return call service report data;
obtaining a first generation table content vector according to the corrected permission range vector;
obtaining a second generated table content vector according to the error permission vector;
and updating the content vector of the first generated table by using the content vector of the second generated table, and decreasing the pairing standard of the constructed table according to the updated content vector of the first generated table.
Further, the step of building a standard training model includes building a standard configuration preset model, and the step of determining a generation training thread of the built standard training model according to the report text area relationship includes:
when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining a generation training thread of the built standard training model to incrementally build the standard configuration preset model;
wherein the generating of the built standard training model according to the modified allowable range vector and the error allowable vector comprises:
acquiring the set-up standard configuration preset model of the current configuration of the first simulated callback service report data;
obtaining a third generation table content vector according to the corrected permission range vector;
obtaining a fourth generated table content vector according to the error permission vector;
updating the third generated table content vector by using the fourth generated table content vector, and increasing the standard configuration preset model according to the updated third generated table content vector in an incremental manner;
the method for generating the standard training model comprises the following steps of establishing a table matching standard, determining a generation training thread of the established standard training model according to the report text area relationship, and comprising the following steps of:
and when the first simulated return call service report data and the second simulated return call service report data are constructed to belong to the same table attribute description, determining a generation training thread of the constructed standard training model as the incremental constructed table matching standard.
Further, the generating the built standard training model according to the corrected allowable range vector and the error allowable vector includes:
acquiring the set-up form pairing standard currently configured by the first simulated return call service report data;
obtaining a fifth generated table content vector according to the corrected allowable range vector;
obtaining a sixth generated table content vector according to the error permission vector;
and updating the fifth generated table content vector by using the sixth generated table content vector, and increasing the set-up table pairing standard according to the updated fifth generated table content vector.
Further, the building of the first simulated return call service report data and the second simulated return call service report data in a simulated table range, the simulated table range being configured with a first table attribute description and a second table attribute description which are similar to each other, the built standard training model including a first line standard configuration preset model and a second line standard configuration preset model, the determining of the generation training thread of the built standard training model according to the report text area relationship includes:
when the first simulated return call service report data and the second simulated return call service report data are both established in the first table attribute description, determining that a generation training thread of the established standard training model is to decrease the first row-column standard configuration preset model and the second row-column standard configuration preset model, wherein the first row-column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a historical table attribute in the second table attribute description, and the second row-column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a current table attribute in the second table attribute description.
Further, the generating the built standard training model according to the modified allowable range vector and the error allowable vector includes:
acquiring the first row standard configuration preset model and the second row standard configuration preset model currently configured by the first simulated return call service report data;
obtaining a seventh generated table content vector according to the corrected allowable range vector and obtaining an eighth generated table content vector according to the error allowable vector;
and updating the seventh generated table content vector by using the eighth generated table content vector, and decrementing the first row standard configuration preset model and the second row standard configuration preset model according to the updated seventh generated table content vector.
Further, the generating the built standard training model according to the modified allowable range vector and the error allowable vector further includes:
configuring a preset model and a preset model based on a first row standard and a second row standard after decreasing, and obtaining a set-up form pairing standard currently configured by the first simulated return call service report data when the first simulated return call service report data is not successfully described from the first form attribute description row to the second form attribute description in a candidate standard vector;
increasing the set-up table pairing standard incrementally according to the corrected allowable range vector and the error allowable vector;
wherein, the method further comprises:
acquiring a candidate standard vector of current configuration;
and generating the candidate standard vector according to the corrected allowable range vector.
In a second aspect, there is provided an artificial intelligence based data processing system comprising a processor and a memory in communication with each other, the processor being configured to read a computer program from the memory and execute the computer program to implement the above method.
In a third aspect, a cloud platform, comprising: a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the above-described method.
According to the data processing method, the system and the cloud platform based on artificial intelligence, first simulated return call business report data are calculated according to a set standard training model, in response to the fact that the current set-up mode of second simulated return call business report data and the first simulated return call business report data meets a target mode, an error permission vector of the first simulated return call business report data and a report character regional relation of the first simulated return call business report data and the second simulated return call business report data are obtained, the second simulated return call business report data are set up behind the first simulated return call business report data, the error permission vector is used for representing an error permission quantization range of the first simulated return call business report data to the second simulated return call business report data, the set-up standard training model is generated according to the report character regional relation and the error permission vector, the error permission vector is introduced into the embodiment of the invention, and the set-up standard training model is generated according to the report character regional relation of the first simulated return call business report data and the set-up standard training model, and the error permission vector of the set-up standard report data can be generated when the simulated return call business report data is simulated return call business report data, and the report data simulation efficiency of the report data is improved by the set-up standard report data.
Drawings
To more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 is a flowchart of a data processing method based on artificial intelligence according to an embodiment of the present disclosure.
Fig. 2 is a block diagram of an artificial intelligence based data processing apparatus according to an embodiment of the present disclosure.
FIG. 3 is a block diagram of an artificial intelligence based data processing system according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions of the present application, the following detailed descriptions are provided with accompanying drawings and specific embodiments, and it should be understood that the specific features in the embodiments and examples of the present application are detailed descriptions of the technical solutions of the present application, and are not limitations of the technical solutions of the present application, and in a case of no conflict, the technical features in the embodiments and examples of the present application may be combined with each other.
Referring to fig. 1, a data processing method based on artificial intelligence is shown, which may include the technical solutions described in the following steps 100 to 300.
And step 100, calculating the first simulated return call service report data according to the established standard training model.
The set-up standard training model is used for determining a target standard vector of a currently set-up form vector of the first simulated return call service report data, the currently set-up form vector of the first simulated return call service report data is updated according to the set-up standard training model, the currently set-up form vector of the first simulated return call service report data is used for representing a current set-up state of the first simulated return call service report data, for example, the currently set-up form vector may include the current set-up speed, the current content recognition accuracy or the current column-column mode, correspondingly, the set-up standard training model may include the set-up form pairing standard, the set-up standard configuration preset model or the column-column standard configuration preset model, the set-up standard training model is a global form vector, the standard vector is assigned to the corresponding simulated return call service report data before simulation begins, the simulated return call service report data is simulated and set up according to the set-up standard training model configured by the set-up standard training model in the whole simulation process, and the set-up standard training models set-up report data of different simulated return call service report data may be different. The first simulated return call service report data is simulated and constructed according to a constructed standard training model corresponding to the first simulated return call service report data, namely the target return call service report data required to be calculated in the embodiment of the invention, and can be one of simulated return call service report data in different conditions.
200, when the current building mode of the second simulated return call service report data and the first simulated return call service report data meets a target mode, obtaining an error permission vector of the first simulated return call service report data and a report character area relation of the first simulated return call service report data and the second simulated return call service report data, wherein the second simulated return call service report data is built behind the first simulated return call service report data, and the error permission vector is used for representing an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data.
In the scenario provided by the embodiment of the present invention, the second simulated return service report data is built behind the first simulated return service report data.
Based on this, the embodiment of the present invention introduces an error permission vector, where the error permission vector is used to represent an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data, the error permission vector may be any floating value between 0 and 1, the error permission vector may assign a standard vector to the corresponding simulated return call service report data before the simulation starts, and the error permission vectors of different simulated return call service report data may be different, so that a reaction of different executors to the burst return call service report data in a real situation may be simulated, for example, some executors may actively avoid the burst return call service report data in error, some executors may decide again according to the burst return call service report data and their own manner, or even some executors may not execute any action of avoiding the error. In a possible implementation manner, the larger the error permission vector is, the higher the error permission quantization range of the first simulated return traffic reporting data to the second simulated return traffic reporting data is represented, that is, when the second simulated return traffic reporting data is close to each other, the first simulated return traffic reporting data is more prone to execute the relevant error avoiding action. Of course, it may also be configured that the larger the error permission vector is, the lower the error permission quantization range of the first simulated return service report data to the second simulated return service report data is represented, and depending on the actual simulation requirement, the embodiment of the present invention takes the example that the larger the error permission vector is, the higher the error permission quantization range of the first simulated return service report data to the second simulated return service report data is.
The report text area relationship between the first simulated return call service report data and the second simulated return call service report data refers to a position relationship between a currently-built form attribute description of the first simulated return call service report data and a currently-built form attribute description of the second simulated return call service report data, for example, the first simulated return call service report data and the second simulated return call service report data may be built in the same form attribute description, or the first simulated return call service report data and the second simulated return call service report data are respectively built in form attribute descriptions around each form.
And 300, generating the built standard training model according to the report text area relation and the error permission vector.
And after determining the generation training thread of the built standard training model, generating the built standard training model according to the correction permission range vector and the error permission vector based on the corresponding generation training thread. The established standard training model is generated by introducing the correction allowable range vector and combining the correction allowable range vector and the error allowable vector, so that the reasonability of the established standard training model can be improved.
It can be understood that, when the technical solutions described in steps 100 to 300 are executed, first simulated return call service report data is calculated according to a built standard training model, in response to that a current building manner of second simulated return call service report data and the first simulated return call service report data satisfies a target manner, an error permission vector of the first simulated return call service report data and a report text area relationship of the first simulated return call service report data and the second simulated return call service report data are obtained, the second simulated return call service report data is built behind the first simulated return call service report data, the error permission vector is used for representing an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data, the built standard training model is generated according to the report text area relationship and the error permission vector, in the embodiment of the present invention, an error permission vector is introduced, and a first simulated return call service report data simulation result of the first simulated return call service report data is generated according to an error permission quantization range of the first simulated return call service report text area relationship of the first simulated return call service report data and the error permission vector of the first simulated return call service report data, thereby realizing that an error of the simulated return call service report data is generated in a simulated return call simulation result of the simulated return call service report data.
In an alternative embodiment, the inventor finds that, when the report text area relationship and the error permission vector are used, there is a problem that the correction permission range vector is inaccurate, so that it is difficult to accurately generate the constructed standard training model, and in order to improve the above technical problem, the step of generating the constructed standard training model according to the report text area relationship and the error permission vector described in step 100 may specifically include the technical solutions described in the following step q1 to step q 3.
And q1, acquiring a correction permission range vector of the first simulated return call service report data, wherein the correction permission range vector is used for representing an execution correction permission range of the first simulated return call service report data.
And step q2, determining a generation training thread of the built standard training model according to the report text area relation.
And q3, generating the built standard training model according to the correction allowable range vector and the error allowable vector based on the generated training thread.
It can be understood that, when the technical scheme described in the above step q1 to step q3 is executed, the problem that the correction permission range vector is inaccurate is solved according to the report text area relationship and the error permission vector, so that the built standard training model can be accurately generated.
In an alternative embodiment, the inventor finds that the constructed standard training model includes a constructed table pairing standard, and when the generation training thread of the constructed standard training model is determined according to the report literal domain relationship, there is a problem that table attribute description around each table is unreliable, so that it is difficult to reliably generate the training thread.
Step q21, when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining the generation training thread of the built standard training model as descending the built table pairing standard.
It can be understood that, when the technical solution described in the above step q21 is executed, the built standard training model includes a built table pairing standard, and when the generation training thread of the built standard training model is determined according to the report text area relationship, the problem that the table attribute description around each table is unreliable is improved, so that the training thread can be reliably generated.
In an alternative embodiment, the inventor finds that, when building a table pairing standard according to the corrected allowable range vector and the error allowable vector, there is a problem that the standard training model built is not accurate, so that it is difficult to accurately generate the standard training model built, and in order to improve the above technical problem, the step of generating the standard training model built according to the corrected allowable range vector and the error allowable vector described in step q3 may specifically include the technical solutions described in the following step q31 to step q 34.
And q31, acquiring the set-up form pairing standard currently configured by the first simulated return call service report data.
And q32, obtaining a first generation table content vector according to the corrected permission range vector.
And q33, obtaining a second generated table content vector according to the error permission vector.
And q34, updating the first generated table content vector by using the second generated table content vector, and decreasing the constructed table pairing standard according to the updated first generated table content vector.
It can be understood that, when the technical scheme described in the above step q31 to step q34 is executed, the problem that the constructed table pairing standard is inaccurate is solved according to the correction permission range vector and the error permission vector, so that the constructed standard training model can be accurately generated.
In an alternative embodiment, the inventor finds that the constructed standard training model includes a constructed standard configuration preset model, and when the table attribute description around each table is inaccurate according to the report literal region relationship, it is difficult to accurately determine a generation training thread of the constructed standard training model, in order to improve the above technical problem, the constructed standard training model described in step q2 includes a constructed standard configuration preset model, and the step of determining the generation training thread of the constructed standard training model according to the report literal region relationship may specifically include the technical scheme described in the following step w 1.
And w1, when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining a generation training thread of the built standard training model to incrementally build the standard configuration preset model.
It can be understood that, when the technical scheme described in the step w1 is executed, the established standard training model includes establishing a standard configuration preset model, and when the table attribute description around each table is inaccurate according to the report text region relationship, the problem of inaccurate description of the table attribute around each table is solved, so that the generation training thread of the established standard training model can be accurately determined.
In an alternative embodiment, the inventor finds that, when building a standard configuration preset model according to the corrected allowable range vector and the error allowable vector, there is a problem that it is inaccurate, so that it is difficult to accurately generate the built standard training model, and in order to improve the above technical problem, the step of generating the built standard training model according to the corrected allowable range vector and the error allowable vector described in step q3 may specifically include the technical problems described in the following steps e1 to e 4.
Step e1, obtaining the standard configuration preset model currently configured by the first analog return call business report data.
And e2, obtaining a third generation table content vector according to the corrected allowable range vector.
And e3, obtaining a fourth generated table content vector according to the error permission vector.
And e4, updating the third generated table content vector by using the fourth generated table content vector, and incrementally building the standard configuration preset model according to the updated third generated table content vector.
It can be understood that, when the technical problems described in the above steps e1 to e4 are performed, the problem that the set-up standard configuration preset model is inaccurate is solved according to the correction permission range vector and the error permission vector, so that the set-up standard training model can be accurately generated.
In an alternative embodiment, the inventor finds that the constructed standard training model includes a constructed table pairing standard, and when the standard training model is based on the report literal region relationship, the table attribute description is inaccurate, so that it is difficult to accurately determine a generation training thread of the constructed standard training model.
And r1, when the first simulated return call service report data and the second simulated return call service report data are constructed and belong to the same table attribute description, determining a generation training thread of the constructed standard training model as the incremental constructed table pairing standard.
It can be understood that when the technical scheme described in the step r1 is executed, the set standard training model includes a set table pairing standard, and when the report text area relationship is obtained, the problem of inaccurate table attribute description is solved, so that a generation training thread of the set standard training model can be accurately determined.
In an alternative embodiment, the inventor finds that, when the table pairing standard is built according to the corrected allowable range vector and the error allowable vector, the problem that the built standard training model is not accurately generated exists, and in order to improve the technical problem, the step of generating the built standard training model according to the corrected allowable range vector and the error allowable vector, which is described in step r1, may specifically include the technical solutions described in the following steps r11 to r 14.
And r11, acquiring the set-up form pairing standard currently configured by the first simulated return call service report data.
And r12, obtaining a fifth generated table content vector according to the corrected allowable range vector.
And step r13, obtaining a sixth generated table content vector according to the error permission vector.
And r14, updating the fifth generated table content vector by using the sixth generated table content vector, and increasing the constructed table pairing standard according to the updated fifth generated table content vector.
It can be understood that, when the technical solutions described in the above steps r11 to r14 are executed, the problem that the set-up table pairing standard is inaccurate is solved according to the correction permission range vector and the error permission vector, so that the set-up standard training model can be accurately generated.
In an alternative embodiment, the inventor finds that, a first simulated return call service report data and a second simulated return call service report data are built in a simulated table range, a first table attribute description and a second table attribute description which are similar are configured in the simulated table range, the built standard training model includes a first row standard configuration preset model and a second row standard configuration preset model, when determining a training thread for generating the built standard training model according to the report character area relationship, the first table attribute description is inaccurate, so that it is difficult to accurately generate the training thread, in order to improve the above technical problem, the first simulated return call service report data and the second simulated return call service report data described in step q2 are built in the simulated table range, the first table attribute description and the second table attribute description which are configured in the simulated table range, the built standard training model includes a first row standard configuration preset model and a second row standard configuration preset model, the training thread for generating the built standard training model is determined according to the report character area relationship, and the step t1 may specifically include the technical scheme described in the following step 1.
Step t1, when the first simulated return call service report data and the second simulated return call service report data are both established in the first table attribute description, determining that a generation training thread of the established standard training model is to decrement the first row and column standard configuration preset model and the second row and column standard configuration preset model, wherein the first row and column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a historical table attribute in the second table attribute description, and the second row and column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a current table attribute in the second table attribute description.
It can be understood that, when the technical scheme described in the step t1 is executed, the first simulated return call service report data and the second simulated return call service report data are built in a simulated table range, the simulated table range is configured with a first table attribute description and a second table attribute description which are close to each other, the built standard training model includes a first row standard configuration preset model and a second row standard configuration preset model, and when the training thread generation of the built standard training model is determined according to the report character area relationship, the problem of inaccurate description of the first table attribute is improved, so that the training thread can be accurately generated.
In an alternative embodiment, the inventor finds that, when the modified allowable range vector and the error allowable vector are used, the modified allowable range vector is inaccurate, so that it is difficult to accurately generate the constructed standard training model, and in order to improve the above technical problem, the step of generating the constructed standard training model according to the modified allowable range vector and the error allowable vector described in step q3, specifically the technical scheme described in the following step y1 to step y4, is provided.
Step y1, obtaining the first row standard configuration preset model and the second row standard configuration preset model currently configured by the first simulated return call service report data.
And y2, obtaining a seventh generated table content vector according to the corrected allowable range vector.
And y3, obtaining an eighth generated table content vector according to the error permission vector.
And y4, updating the seventh generated table content vector by using the eighth generated table content vector, and decreasing the first row standard configuration preset model and the second row standard configuration preset model according to the updated seventh generated table content vector.
It can be understood that, when the technical solutions described in the above steps y1 to y4 are executed, the problem that the correction allowable range vector is not accurate is solved according to the correction allowable range vector and the error allowable vector, so that the built standard training model can be accurately generated.
Based on the above basis, the constructed standard training model is generated according to the corrected allowable range vector and the error allowable vector, and the technical scheme described in the following steps a1 and a2 can also be included.
Step a1, configuring a preset model based on a first row standard and a second row standard after decreasing, and obtaining a set-up table pairing standard currently configured by the first simulated return call service report data when the first simulated return call service report data is not successfully described from the first table attribute description row to the second table attribute description in a candidate standard vector.
Step a2, increasing the set-up table pairing standard progressively according to the correction permission range vector and the error permission vector.
It can be understood that, when the technical solutions described in the above steps a1 and a2 are executed, the set-up form matching standard currently configured by the first simulated return call service report data is obtained through accurate obtaining, so that the accuracy of the set-up form matching standard is improved.
Based on the above basis, the following technical solutions described in step s1 and step s2 may also be included.
And step s1, obtaining a candidate standard vector of the current configuration.
And step s2, generating the candidate standard vector according to the corrected allowable range vector.
It can be understood that, when the technical solutions described in the above steps s1 and s2 are executed, the accuracy of generating the candidate standard vector is improved by correcting the allowable range vector.
On the basis, please refer to fig. 2 in combination, there is provided an artificial intelligence based data processing apparatus 200, applied to a data processing terminal, the apparatus comprising:
the data building module 210 is used for calculating first simulated callback service report data according to a built standard training model;
a data obtaining module 220, configured to obtain an error permission vector of the first simulated return call service report data and a report text area relationship between the first simulated return call service report data and the second simulated return call service report data when a current building manner of the second simulated return call service report data and the first simulated return call service report data satisfies a target manner, where the second simulated return call service report data is built behind the first simulated return call service report data, and the error permission vector is used to represent an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data;
and the model generating module 230 is configured to generate the built standard training model according to the report text area relationship and the error permission vector.
On the basis of the above, please refer to fig. 3, which shows an artificial intelligence based data processing system 300, comprising a processor 310 and a memory 320, which are communicated with each other, wherein the processor 310 is configured to read a computer program from the memory 320 and execute the computer program to implement the above method.
On the basis of the above, there is also provided a computer-readable storage medium on which a computer program is stored, which when executed implements the above-described method.
In summary, based on the above-mentioned scheme, first simulated return call service report data is calculated according to a built standard training model, in response to that a current building manner of second simulated return call service report data and the first simulated return call service report data satisfies a target manner, an error permission vector of the first simulated return call service report data and a report text area relationship of the first simulated return call service report data and the second simulated return call service report data are obtained, the second simulated return call service report data is built behind the first simulated return call service report data, the error permission vector is used for representing an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data, and the built standard training model is generated according to the report text area relationship and the error permission vector.
It should be appreciated that the system and its modules shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, for example such code provided on a carrier medium such as a diskette, CD-or DVD-ROM, programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be considered merely illustrative and not restrictive of the broad application. Various modifications, improvements and adaptations to the present application may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present application and thus fall within the spirit and scope of the exemplary embodiments of the present application.
Also, this application uses specific language to describe embodiments of the application. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the present application is included in at least one embodiment of the present application. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics may be combined as suitable in one or more embodiments of the application.
Moreover, those skilled in the art will appreciate that aspects of the present application may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereon. Accordingly, various aspects of the present application may be embodied entirely in hardware, entirely in software (including firmware, resident software, micro-code, etc.) or in a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present application may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of the present application may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C + +, C #, VB.NET, python, and the like, a conventional programming language such as C, visual Basic, fortran 2003, perl, COBOL 2002, PHP, ABAP, a dynamic programming language such as Python, ruby, and Groovy, or other programming languages, and the like. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While certain presently contemplated useful embodiments of the invention have been discussed in the foregoing disclosure by way of various examples, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of the disclosure. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features are required than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the numbers allow for adaptive variation. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application history document is inconsistent or conflicting with the present application as to the extent of the present claims, which are now or later appended to this application. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present application. Other variations are also possible within the scope of the present application. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the present application can be viewed as being consistent with the teachings of the present application. Accordingly, the embodiments of the present application are not limited to only those embodiments explicitly described and depicted herein.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (9)
1. A method of artificial intelligence based data processing, the method comprising:
calculating first simulated return call service report data according to the established standard training model;
when the current building mode of second simulated return call service report data and the first simulated return call service report data meets a target mode, acquiring an error permission vector of the first simulated return call service report data and a report character area relation of the first simulated return call service report data and the second simulated return call service report data, building the second simulated return call service report data behind the first simulated return call service report data, and using the error permission vector to represent an error permission quantization range of the first simulated return call service report data to the second simulated return call service report data;
generating the set standard training model according to the report character area relation and the error permission vector; the generating of the built standard training model according to the report text area relationship and the error permission vector comprises the following steps:
acquiring a correction permission range vector of the first simulated return call service report data, wherein the correction permission range vector is used for representing an execution correction permission range of the first simulated return call service report data;
determining a generation training thread of the built standard training model according to the report text area relation;
and generating the built standard training model according to the corrected allowable range vector and the error allowable vector based on the generated training thread.
2. The artificial intelligence based data processing method according to claim 1, wherein the constructed standard training model includes constructed table pairing standards, and the determining of the generation training thread of the constructed standard training model according to the report literal domain relationship includes:
when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining the generation training thread of the built standard training model as the descending built table pairing standard;
wherein the generating the built standard training model according to the modified allowable range vector and the error allowable vector comprises:
acquiring the set-up form pairing standard currently configured by the first simulated return call service report data;
obtaining a first generation table content vector according to the corrected permission range vector;
obtaining a second generated table content vector according to the error permission vector;
and updating the content vector of the first generated table by using the content vector of the second generated table, and decreasing the pairing standard of the constructed table according to the updated content vector of the first generated table.
3. The artificial intelligence-based data processing method according to claim 1, wherein the building of the standard training model comprises building of a standard configuration preset model, and the determining of the generation training thread of the built standard training model according to the report literal region relationship comprises:
when the first simulated return call service report data and the second simulated return call service report data are respectively built on the table attribute description around each table, determining a generation training thread of the built standard training model to incrementally build the standard configuration preset model;
wherein the generating the built standard training model according to the modified allowable range vector and the error allowable vector comprises:
acquiring the set-up standard configuration preset model of the current configuration of the first simulated callback service report data;
obtaining a third generation table content vector according to the corrected permission range vector;
obtaining a fourth generated table content vector according to the error permission vector;
updating the third generated table content vector by using the fourth generated table content vector, and increasing the construction standard configuration preset model incrementally according to the updated third generated table content vector;
the method for generating the standard training model comprises the following steps of establishing a table matching standard, determining a generation training thread of the established standard training model according to the report text area relationship, and comprising the following steps of:
and when the first simulated return call service report data and the second simulated return call service report data are constructed to belong to the same form attribute description, determining a generation training thread of the constructed standard training model as the incremental constructed form pairing standard.
4. The artificial intelligence based data processing method of claim 3, wherein the generating the constructed standard training model from the modified allowable range vector and the error allowable vector comprises:
acquiring the set-up form pairing standard currently configured by the first simulated return call service report data;
obtaining a fifth generated table content vector according to the corrected allowable range vector;
obtaining a sixth generated table content vector according to the error permission vector;
and updating the fifth generated table content vector by using the sixth generated table content vector, and increasing the set-up table pairing standard according to the updated fifth generated table content vector.
5. The artificial intelligence-based data processing method according to claim 1, wherein the first simulated return call business report data and the second simulated return call business report data are built in a simulated table range, the simulated table range is configured with a first table attribute description and a second table attribute description which are close to each other, the built standard training model includes a first line standard configuration preset model and a second line standard configuration preset model, and the determining of the generation training thread of the built standard training model according to the report text area relationship includes:
when the first simulated return call service report data and the second simulated return call service report data are both established in the first table attribute description, determining that a generation training thread of the established standard training model is to decrease the first row-column standard configuration preset model and the second row-column standard configuration preset model, wherein the first row-column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a historical table attribute in the second table attribute description, and the second row-column standard configuration preset model is an associated standard vector between the first simulated return call service report data and a current table attribute in the second table attribute description.
6. The artificial intelligence based data processing method of claim 5, wherein the generating the built standard training model from the modified allowable range vector and the error allowable vector comprises:
acquiring the first row standard configuration preset model and the second row standard configuration preset model currently configured by the first simulated return call service report data;
obtaining a seventh generated table content vector according to the corrected allowable range vector;
obtaining an eighth generated table content vector according to the error permission vector;
and updating the seventh generated table content vector by using the eighth generated table content vector, and decrementing the first row standard configuration preset model and the second row standard configuration preset model according to the updated seventh generated table content vector.
7. The artificial intelligence based data processing method according to claim 5 or 6, wherein the generating the constructed standard training model from the modified allowable range vector and the error allowable vector further comprises:
configuring a preset model based on the first row standard and a second row standard after the descending, and obtaining a set-up table pairing standard currently configured by the first simulated return call service report data when the first simulated return call service report data is not successfully described from the first table attribute description row to the second table attribute description in the candidate standard vector;
increasing the set-up table pairing standard incrementally according to the corrected allowable range vector and the error allowable vector;
wherein, the method further comprises:
acquiring a candidate standard vector of current configuration;
and generating the candidate standard vector according to the corrected allowable range vector.
8. An artificial intelligence based data processing system comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method of any of claims 1-7.
9. A cloud platform, comprising:
a memory for storing a computer program;
a processor coupled to the memory for executing the computer program stored by the memory to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317954.XA CN114610723B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210317954.XA CN114610723B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114610723A CN114610723A (en) | 2022-06-10 |
| CN114610723B true CN114610723B (en) | 2022-10-14 |
Family
ID=81867108
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210317954.XA Active CN114610723B (en) | 2022-03-29 | 2022-03-29 | Data processing method and system based on artificial intelligence and cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114610723B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779603A (en) * | 2016-12-19 | 2017-05-31 | 深圳市跨境翼电子商务股份有限公司 | A kind of declaration system and declaration information processing method |
| WO2021164425A1 (en) * | 2020-02-19 | 2021-08-26 | 京东方科技集团股份有限公司 | Method and device for data processing, electronic device, and storage medium |
| CN113722324A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Report generation method and device based on artificial intelligence, electronic equipment and medium |
| CN114138741A (en) * | 2021-11-11 | 2022-03-04 | 北京银盾泰安网络科技有限公司 | Historical data analysis platform |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6018731A (en) * | 1998-12-22 | 2000-01-25 | Ac Properties B.V. | System, method and article of manufacture for a goal based system utilizing a spreadsheet and table based architecture |
| CN111708801A (en) * | 2020-05-29 | 2020-09-25 | 北京金山云网络技术有限公司 | Report generation method and device and electronic equipment |
-
2022
- 2022-03-29 CN CN202210317954.XA patent/CN114610723B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106779603A (en) * | 2016-12-19 | 2017-05-31 | 深圳市跨境翼电子商务股份有限公司 | A kind of declaration system and declaration information processing method |
| WO2021164425A1 (en) * | 2020-02-19 | 2021-08-26 | 京东方科技集团股份有限公司 | Method and device for data processing, electronic device, and storage medium |
| CN113722324A (en) * | 2021-08-30 | 2021-11-30 | 平安国际智慧城市科技股份有限公司 | Report generation method and device based on artificial intelligence, electronic equipment and medium |
| CN114138741A (en) * | 2021-11-11 | 2022-03-04 | 北京银盾泰安网络科技有限公司 | Historical data analysis platform |
Non-Patent Citations (1)
| Title |
|---|
| 智能算法在电信业务用户体验感知分析中的应用;周天圆;《中国优秀硕士学位论文全文数据库》;20110915;第I138-295页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114610723A (en) | 2022-06-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114625741A (en) | Data processing method and system based on artificial intelligence and cloud platform | |
| CN111552370B (en) | Vibration signal calibration method, storage medium and electronic device | |
| CN114610723B (en) | Data processing method and system based on artificial intelligence and cloud platform | |
| EP4174713A1 (en) | Method and system for three-dimensional modeling | |
| CN111340245A (en) | Model training method and system | |
| CN113485203A (en) | Method and system for intelligently controlling network resource sharing | |
| CN112799658B (en) | Model training method, model training platform, electronic device, and storage medium | |
| CN114417076A (en) | Production line intelligent early warning method and system based on artificial intelligence | |
| CN113605980A (en) | Intelligent mine safety early warning method and system based on Internet of things | |
| CN113626594A (en) | Operation and maintenance knowledge base establishing method and system based on multiple intelligent agents | |
| CN113626538A (en) | Medical information intelligent classification method and system based on big data | |
| CN113610129A (en) | Multi-source heterogeneous information fusion method and system | |
| CN115345194A (en) | Signal processing method and system based on mixed tree algorithm | |
| CN111814949B (en) | Data labeling method and device and electronic equipment | |
| CN113298636B (en) | Risk control method, device and system based on simulation resource application | |
| CN113610127A (en) | Genetic crossing algorithm-based image feature fusion method and system | |
| CN113613288A (en) | Intelligent data distribution method and system based on 5G | |
| CN113590951A (en) | Perception data processing method and system | |
| CN115292301A (en) | Task data abnormity monitoring and processing method and system based on artificial intelligence | |
| CN115079881A (en) | Virtual reality-based picture correction method and system | |
| CN114169437A (en) | Intelligent key data attribute fusion method and system | |
| CN115374107A (en) | Power load analysis method and system based on big data | |
| CN113627490A (en) | Operation and maintenance multi-mode decision method and system based on multi-core heterogeneous processor | |
| CN114611478A (en) | Information processing method and system based on artificial intelligence and cloud platform | |
| CN113610133A (en) | Laser data and visual data fusion method and system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220916 Address after: Room 501, No. 1, Floor 1-5, Building 3-13, Phase III, Optics Valley Core Center, No. 303, Optics Valley Avenue, Fozuling Street, Donghu New Technology Development Zone, Wuhan City, Hubei Province 430000 Applicant after: ChinaSoft digital intelligence information technology (Wuhan) Co.,Ltd. Address before: No. 289, Chuanjin Road North Station New Village, Panlong District, Kunming, Yunnan 650000 Applicant before: Li Rui |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |