CN110633840A - Data processing method, device and storage medium - Google Patents
Data processing method, device and storage medium Download PDFInfo
- Publication number
- CN110633840A CN110633840A CN201910729574.5A CN201910729574A CN110633840A CN 110633840 A CN110633840 A CN 110633840A CN 201910729574 A CN201910729574 A CN 201910729574A CN 110633840 A CN110633840 A CN 110633840A
- Authority
- CN
- China
- Prior art keywords
- data
- processing
- processing result
- target
- adjustment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 344
- 238000000034 method Methods 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 description 70
- 239000002994 raw material Substances 0.000 description 20
- 230000008569 process Effects 0.000 description 18
- 230000004048 modification Effects 0.000 description 15
- 238000012986 modification Methods 0.000 description 15
- 238000012549 training Methods 0.000 description 14
- 238000007405 data analysis Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000013468 resource allocation Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 235000004789 Rosa xanthina Nutrition 0.000 description 2
- 241000109329 Rosa xanthina Species 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007477 logistic regression Methods 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 1
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 230000000153 supplemental effect Effects 0.000 description 1
- 210000002268 wool Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Medical Informatics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a data processing method, a data processing device and a storage medium; the data processing method comprises the following steps: acquiring data to be processed; the data to be processed comprises historical data and target data; processing the data to be processed to obtain a processing result, and determining a processing mode based on the processing result; the processing mode comprises one of a first processing mode and a second processing mode; the first processing mode is to determine the amount of resources required for reaching the processing result; and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
Description
Technical Field
The present invention relates to the field of data analysis and prediction, and in particular, to a data processing method, apparatus, and storage medium.
Background
In recent years, under the new era background of rapid development of big data and artificial intelligence technology, it has become a trend to dig useful information hidden in the big data from the mass data through machine learning, and to analyze and predict behaviors by using a specific algorithm. By applying big data analysis and algorithm technology, long-term information can be accurately identified and predicted, and a data basis is provided for a large number of application scenes.
However, the data based on the current behavior analysis and prediction are historical static data, and cannot be used for processing different requirements of users in different application scenarios in a targeted manner.
Disclosure of Invention
In view of this, embodiments of the present invention are expected to provide a data processing method, an apparatus, and a storage medium, which can meet different processing requirements, perform data analysis based on actual needs, and provide a processing result.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
the embodiment of the invention provides a data processing method, which comprises the following steps:
acquiring data to be processed; the data to be processed comprises historical data and target data;
processing the data to be processed to obtain a processing result, and determining a processing mode based on the processing result;
the processing mode comprises one of a first processing mode and a second processing mode;
the first processing mode is to determine the amount of resources required for reaching the processing result;
and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
In the foregoing solution, the processing the data to be processed to obtain a processing result, and determining a first processing manner based on the processing result includes:
constructing a first processing model based on historical data of at least one time period, and obtaining a first processing result according to the first processing model;
based on the first processing result, an amount of resources required to achieve the first processing result is determined.
In the foregoing scheme, the processing the data to be processed to obtain a processing result, and determining a second processing manner based on the processing result includes:
acquiring a target time node corresponding to the target data;
determining, based on the target time node, a required time to reach the target time node;
decomposing the required time to obtain at least one sub-time, and determining a second sub-processing result corresponding to each sub-time in the at least one sub-time;
and comparing the second sub-processing result with the current resource amount, judging whether the adjustment is needed, determining that the adjustment is needed, and generating adjustment information.
In the above solution, the determining that adjustment is required and generating adjustment information includes:
acquiring historical data of at least one time period before a target time node corresponding to the target data, constructing a second processing model based on the historical data of at least one time period before the target time node, and obtaining a second processing result corresponding to the target time node based on the second processing model;
determining an adjustment factor based on the second processing result, the target data, and the required time to reach the target time node;
based on the adjustment factor, adjustment information is generated.
In the above scheme, the acquiring data to be processed includes:
judging whether a preset time node is reached or not, and judging whether at least one of operation instructions sent by a terminal side is received or not;
and determining at least one of the preset time node and the operation instruction sent by the receiving terminal side, and acquiring the data to be processed.
In the foregoing solution, after determining the processing manner based on the processing result, the method further includes:
receiving adjustment data;
and processing the data to be processed based on the adjustment data to obtain a new processing result.
An embodiment of the present invention further provides a data processing apparatus, where the apparatus includes: an acquisition unit and a processing unit; wherein,
the acquisition unit is used for acquiring data to be processed; the data to be processed comprises historical data and target data;
the processing unit is used for processing the data to be processed to obtain a processing result and determining a processing mode based on the processing result;
the processing mode comprises one of a first processing mode and a second processing mode;
the first processing mode is to determine the amount of resources required for reaching the processing result;
and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements any of the steps of the above-mentioned method.
An embodiment of the present invention further provides a data processing apparatus, including: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform any of the steps of the above method when executing the computer program.
According to the data processing method, the data processing device and the storage medium provided by the embodiment of the invention, the acquired historical data and the acquired target data can be processed to obtain the corresponding processing result, the corresponding processing mode is determined based on the processing result, and then the processing is executed according to the corresponding processing mode. Therefore, corresponding processing can be executed according to different requirements of different users in different application scenes, and the processing can be executed by setting different processing modes, so that decisions can be provided for the users, particularly the management layer, and the user experience is greatly improved.
Drawings
Fig. 1 is a first schematic flow chart illustrating an implementation of a data processing method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart illustrating a process executed based on a second processing manner in a data processing method according to an embodiment of the present invention;
fig. 3 is a schematic flow chart illustrating an implementation of a data processing method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a specific hardware structure of a data processing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the data processing method provided by the embodiment of the present invention can be applied to an intelligent center, and the intelligent center has a calculation and storage function module, and can be used for data learning, analysis and prediction.
In order to implement data analysis and prediction, an embodiment of the present invention provides a data processing method, as shown in fig. 1, the method includes:
102, processing the data to be processed to obtain a processing result, and determining a processing mode based on the processing result; the processing mode comprises one of a first processing mode and a second processing mode; the first processing mode is to determine the amount of resources required for reaching the processing result; and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
It should be noted that the historical data is already existing data; the target data is a target value which is expected to be realized at a target time node by any user needing data processing, namely the target data comprises the target time node and the target value. The historical data and the target data can be data in corresponding application scenes. For example, in the production field, the historical data and the target data can be purchasing data, data required in production and the like.
The amount of resources required to achieve the processing result refers to the amount of resources that need to be prepared/configured to achieve the processing result. For example, the target value to be achieved for the yield of a certain product is set according to the current production level, the purchase of raw materials, the equipment of production line personnel, and the like.
In addition, since analysis processing that needs to be performed differs in different application scenarios, it is necessary to determine a processing method according to a processing result.
Here, when the same-type demand prediction is required, the resource allocation can be realized by acquiring the historical data and predicting future data based on the historical data. For example, production data of 8 months may be predicted from production data of 1-7 months in history, and corresponding procurement amounts and staffing configurations may be determined based on the obtained predicted production data. When future planning is required, target data may be input first, the amount of resources required to reach the target data is determined based on the target data, and then compared with the current resource configuration, and if the target data cannot be realized by the current resource configuration, the current resource configuration needs to be adjusted. For example, assuming that the production amount of 8 months should be 800 pieces according to the historical schedule, when the user expects that the production amount of 8 months reaches 1600 pieces, that is, the production amount of 8 months reaches 1600 pieces as the target data, in order to achieve the target, the resource allocation needs to be adjusted.
It should be noted that, when future planning is required, if the amount of resources required to reach the target data is determined and compared with the current resource configuration, and it is found that the target data cannot be realized no matter what adjustment is made on the current resource configuration, the target data needs to be adjusted, that is, new target data needs to be determined and acquired again. The failure to achieve the target data no matter how the current resource configuration is adjusted may be the failure to adjust due to various conditions such as insufficient funds, insufficient materials, and the like.
Here, in step 101, the acquiring of the data to be processed may include: judging whether a preset time node is reached or not, and judging whether at least one of operation instructions sent by a terminal side is received or not; and determining at least one of the preset time node and the operation instruction sent by the receiving terminal side, and acquiring the data to be processed.
It should be noted that the setting of the preset time node may be realized by setting a timer in the intelligent middleboard, and the preset time node is set according to needs. The determining that the preset time node is reached refers to data analysis and prediction triggered by the time node, and specifically may be: and setting time nodes in the intelligent central station, and automatically executing to-be-processed data acquisition after the corresponding time nodes are reached.
The time node can be set at the end of a month, at the end of a quarter, at the end of a year and the like, or can be any time node. Therefore, the data to be processed is triggered and acquired at the end of each month, at the end of each quarter, at the end of each year and the like, so that corresponding processing is realized.
Here, the automatically performing the acquisition of the history data in the data to be processed after the corresponding time node is reached may be that the history data of the corresponding time period is set first, and when the corresponding time node is reached, the history data of the time period is automatically acquired. For example, the corresponding time period of the historical data may be set to 5 months, that is, to predict future data, data of the previous 5 months of the current time may be selected as the historical data.
The automatically acquiring the target data in the data to be processed may be performed by taking a preset multiple of the currently predicted data as the target data after the corresponding time node is reached, and automatically acquiring the preset multiple of the currently predicted data as the target data when the corresponding time node is reached. For example, if the current predicted production amount should be 400 pieces, 4 times the target data is set as the target data, that is, the target data is 1600 pieces of production amount.
The operation instruction sent by the receiving terminal side refers to data analysis prediction started by user behavior, and a user can input or select target data and historical data of a certain time period to further perform analysis. For example, a user inputs target data or selects historical data of a certain time period on an input interface of a terminal, and after the input is finished, the terminal receives the target data and the historical data of the certain time period and sends the target data and the historical data of the certain time period to a server side, so that the server acquires the target data and the historical data of the certain time period. Here, the intelligent middlebox is the server side.
The operation instruction sent by the receiving terminal side may also be: the terminal receives the target data and the historical data of a period of time to execute processing after the target data and the historical data of the period of time are input or selected by a user on an input interface of the terminal, namely the processing is directly executed by a processor on the terminal side.
For better understanding of the embodiment of the present invention, the server acquires the target data and the historical data of a period of time, and then performs the processing.
In step 102, the processing results include a first type of processing result and a second type of processing result.
Here, the first type processing result is a processing result of historical data, taking production data as an example, and may be a predicted production capacity, and thus in step 102, the data to be processed is processed, and the obtained processing result is the processing result of the historical data in the data to be processed, so as to obtain the first type processing result; the first type of treatment results are predicted production volumes; the corresponding first processing mode is the amount of resources required to achieve the throughput.
The second type of processing result is a processing result of the target data, and when the target data is a future target production amount, the data to be processed is processed in step 102, and the obtained processing result is the target data in the data to be processed, so that the second type of processing result is obtained; the second type of processing result is the amount of resources needed to reach the target data; the corresponding second processing mode is to compare the resource amount required for reaching the target data with the current resource amount, judge whether to need adjustment, determine that adjustment is needed, and generate adjustment information.
Here, the processing the data to be processed in step 102 to obtain a processing result, and determining a first processing manner based on the processing result includes:
step 201, constructing a processing model based on historical data of at least one time period, and obtaining a first processing result according to the processing model;
step 202, determining an amount of resources required to reach the first processing result based on the first processing result.
Here, the first processing result in step 201 belongs to the first type of processing result. In step 201, constructing the first processing model based on the historical data of the at least one time period may be training the historical data of the at least one time period as training data, and obtaining the first processing model based on the training data. After the first processing model is obtained, the current input data may be processed based on the first processing model to obtain a first processing result.
It should be noted that the training data is a training sample, and the training sample may represent one or more items (features) reflecting the performance or properties of an event or object in some aspect. In supervised learning, each training sample also has a respective label that corresponds to a known outcome for the predicted objective. The prediction result may be various predicted values for the target demand information, such as a classification result (discrete value), a regression result (continuous value), and the like.
It should be noted that the training samples for training out the processing model may be data records stored in a database or a data warehouse or acquired online; the training sample can also be obtained after data splicing, characteristic engineering and other processing is carried out on the data records.
It should be further noted that the first processing model may be constructed by a machine learning algorithm using historical data as training data. Here, the Machine learning algorithm may be Logistic Regression (Logistic Regression), Support Vector Machine (SVM), and some neural network/deep learning algorithms.
It should be noted that, in the process of constructing the first processing model in step 201, at least a part of features of the historical data may be extracted as training data to construct the processing model; the at least one part of the features are features which play a main prediction role in the features of the historical data. Here, the features that play a major role can be screened out from the features of the historical data in various ways; for example, features that are weighted more heavily in a linear prediction model.
It should be further noted that, under different application scenarios and different requirements, the establishment of the first processing model is different, and the current input data is also different.
When the requirement is only to implement a linear prediction of a ring ratio or a homonymy, the process of constructing the first processing model in step 201 may be to construct the first processing model by using a part of data in the historical data of at least one time period as an input and another part of data as an output, and process the historical data of a preset time before the time corresponding to the current requirement based on the first processing model to obtain a first processing result.
Here, the historical data of the preset time before the time corresponding to the current demand is the current input data, and the historical data of the preset time before the time corresponding to the current demand is the related recent data of the current demand. For example, assuming that production data of 8 months needs to be predicted from production data of 1-7 months in history, and resource allocation is further implemented, production data of 1 month may be input, production data of 2 months may be output, production data of 2 months may be input, production data of 3 months may be output, and so on, and production data of 8 months may be predicted when production data of 7 months is input. Here, the production data of 7 months is history data of a preset time before the time (8 months) corresponding to the current demand. The preset time can be set according to the requirement, and can be the previous time or the previous two times. When what kind of results need to be obtained, corresponding parameters are selected during the training of the processing model. Here, the specific training process of the model is not described in detail herein.
When the demand is to realize prediction based on the influence parameters, the historical data includes historical influence parameters and historical demand information, and the process of constructing the first processing model in step 201 may be to construct the first processing model based on the historical influence parameters and the historical demand information, and process the current influence parameters based on the first processing model to obtain a processing result.
Here, the current influence parameter is the current input data; the influence parameters are parameters influencing the demand information, and the historical influence parameters are past influence parameters relative to the current influence parameters; the historical demand information is past demand information, and is also relative to the current demand information. For example, the parameters that have an influence on the 8-month throughput are the amount of resources such as material, labor, and the like. When the production capacity of 8 months is predicted according to the historical production data of 1-7 months, and further resource allocation is realized, a processing model can be built based on the resource capacity of 1-7 months and the production capacity of 1-7 months, and the current resource capacity is processed through the processing model, so that the production capacity of 8 months is obtained.
Here, since the result obtained according to the linear prediction may be different from the data obtained by the current resource amount prediction, the two may be compared, and the resource amount may be reconfigured.
It should be noted that, for the first processing mode of step 102, the above proportional linear prediction mode is adopted to determine the amount of resources required to achieve the processing result. In this way, the processing of the historical data to obtain the first type of processing result may be to construct a first processing model by using a part of data in the historical data of at least one time period as input and another part of data as output, and process the historical data of a preset time before the time corresponding to the current demand based on the first processing model to obtain the first processing result. Taking the predicted production capacity of 8 months as an example, the first result is the predicted production capacity of 8 months.
It should be noted that, the processing of the target data to obtain the second type of processing result may be, for example, to construct a processing model related to resource amount prediction by taking the production amount per month in history as input and the resource amount required per month in history as output, and to process the target data based on the processing model related to resource amount prediction to obtain the required resource amount corresponding to the target data, that is, the second type of processing result.
Fig. 2 is a schematic flow chart of executing processing based on a second processing manner in the data processing method according to the embodiment of the present invention, and as shown in fig. 2, the processing of the data to be processed in step 102 to obtain a processing result, and determining the second processing manner based on the processing result includes:
step 303, decomposing the required time to obtain at least one sub-time, and determining a second sub-processing result corresponding to each sub-time in the at least one sub-time;
and 304, comparing the second sub-processing result with the current resource amount, judging whether the adjustment is needed, determining that the adjustment is needed, and generating adjustment information.
It should be noted that the second sub-processing result belongs to a second type of processing result, that is, the required resource amount obtained by processing the target data corresponding to each sub-time.
In practical application, the data to be processed received by the intelligent middlebox may be target data, and prediction can be performed in stages by splitting and taking the target data as guidance so as to meet the condition that a node reaches a target value at a target time.
Here, the acquisition of the target time node in step 301 will be explained: since the target data includes the target time node and the target value, the target time node corresponding to the target data may be obtained based on the target data in the data to be processed. For example, if the target data is that the production volume reaches 1600 in 8 months, then the end of 8 months is the target time node and the production volume reaches 1600 is the target value.
It should be noted that, in the step 302, the time required to reach the target time node is determined based on the target time node, and may be determined based on the current time node and the target time node by acquiring the current time node. For example, currently 5 months, when the production amount of the target data is 8 months reaches 1600 pieces, the time required for reaching the target time node is 4 months, here, since the production amount is 1600 pieces requiring 8 months, 8 months is also the data to be processed.
After the time required for reaching the target time node is obtained, the required time needs to be decomposed to obtain at least one sub-time, and a processing result corresponding to each sub-time in the at least one sub-time, namely a second sub-processing result, is determined. As described above, the required time is divided into 4 sub-times by dividing the required time into 4 months, and the second sub-processing result corresponding to each of the 4 sub-times is determined.
Here, since the target time node is required to reach the target value, it is required to ensure that each sub-time before reaching the target time node reaches the corresponding sub-target value, so that the target time node reaches the target value. As described above, assuming that currently 5 months, the production volume of 8 months is the target data, and reaches 1600, if the production volume of 8 months should be 800 according to the historical schedule, when the user expects the production volume of 8 months to reach 1600, then 5 months, 6 months, and 7 months all need to be adjusted to ensure the production volume of 8 months reaches 1600.
Here, the determination of the adjustment information (the second processing sub-result corresponding to each sub-time) may be: acquiring historical data of at least one time period before a target time node corresponding to the target data, constructing a second processing model based on the historical data of at least one time period before the target time node, and obtaining a second processing result corresponding to the target time node based on the second processing model; determining an adjustment factor based on the second processing result, the target data, and the required time to reach the target time node; based on the adjustment factor, adjustment information is generated.
The adjustment factor may be a numerical value, and the second processing result may be a prediction result obtained according to the history progress as described above, that is, a result obtained based on the history data, and belongs to the first type of processing result. For example, assuming that the current time is 5 months, according to the historical schedule, the production amount of 5 months is 500, and the production amount of 8 months should be 800, where 800 production amounts are the second processing result corresponding to the target time node of 8 months.
Here, determining an adjustment factor based on the second processing result, the target data, and the required time to reach the target time node means: the adjustment factor is determined based on the second processing result, the target value in the target data, and the time required to reach the target time node, and specifically, the adjustment factor may be determined by determining a difference between the target value in the target data and the second processing result, and dividing the difference by the time required to reach the target time node. For example, assuming that the current time is 5 months, the production amount of 8 months according to the historical schedule should be 800 pieces, when the user aims at producing 1600 pieces in 8 months, the difference between the target value 1600 pieces and the second processing result 800 pieces is determined to be 800 pieces, and the adjustment factor is determined to be 200 by dividing 800 pieces by 4 months.
After the adjustment factor is obtained, the adjustment information may be generated based on the adjustment factor. The generating the adjustment information based on the adjustment factor may be: and determining the required resource amount based on the adjusting factor, and generating adjusting information according to the determined required resource amount. Here, the determination of the required resource amount based on the adjustment factor may be implemented by the above-constructed processing model related to resource amount prediction, that is, the adjustment factor is processed by the processing model related to resource amount prediction to obtain the required resource amount corresponding to the adjustment factor. The generating of the adjustment information according to the determined required resource amount may be increasing the required resource amount corresponding to the adjustment factor on the basis of the original resource amount corresponding to each sub-time.
As an example, the amount of 5 shares predicted from the historical data is 500, and in order to achieve a yield of 8 months of 1600, the yield of 5 months needs to be adjusted, and if the adjustment factor is 200, the required resource amount corresponding to the adjustment factor of 200 is obtained through a processing model related to resource amount prediction, and if the required resource amount corresponding to the adjustment factor of 200 is increased by 2 persons and 200KG of raw materials, the generated adjustment information is increased by 2 persons and 200KG of raw materials on the basis of the original resource amount required by 5 months.
In step 304, the current resource amount is the current configuration amount. Taking production data as an example, the current resource amount may be the current production line number, the production line personnel number, the raw material number, and the like. And comparing the second sub-processing with the current resource amount, if the current resource amount is different from the second sub-processing, determining that the adjustment is needed, and giving adjustment information.
It should be noted that, in practical applications, there are various purposes related to data processing, and there may be adjustments at any time. In this case, accurate prediction meeting actual requirements cannot be realized only based on static input data, and data needs to be adjusted, that is, modified.
As such, after determining the processing manner based on the processing result, the method further includes: receiving adjustment information; and processing the data to be processed based on the adjustment information to generate a new processing result.
Here, the adjustment data includes: modified data, supplemental data, etc.
For some application scenarios, some specific characteristics need to be considered, and these specific characteristics cause the data performance of consecutive months to be greatly different; such as seasonal characteristics, social characteristics, etc. Based on this, it is possible to acquire a specific feature, and correct the processing result based on the specific feature to acquire a more accurate processing result.
Here, the specific feature is modification data. In this way, the above processing the data to be processed based on the adjustment information to generate a new processing result may be: modifying the processing result based on the modification data to obtain a new processing result; and the new processing result is obtained after data modification.
Taking the production data as an example, because the sales of the roses are greatly different from other times in the hours of the valentine's day and the seven suns, the production data of the roses before the valentine's day and the seven suns needs to be corrected. Similarly, there are also some fixed social activities that affect some products, such as the effect of the afternoon festival on rice dumplings and the effect of the mid-autumn festival on moon cakes.
It should be noted that the modification data may be modification of target data, history increase amount, required time, and unit parameter of raw material. In the production data, the unit parameter of the raw material is the unit price of the raw material. For example, the time required to reach the target value according to the current trend is calculated according to the current resource amount and the target value input by the user; if the linear predicted speed increase is increased by x%, data which need to be adjusted every month can be obtained; here, the x% is the modification data of the speed increase. As another example, the time scale is changed, the required time is changed from 12 months to 10 months, from quarterly to monthly, and the like. For example, the production in the next year is predicted, and if the increase of the price of the raw material is 2% obtained from the historical data, the intelligent central station can automatically predict the purchase cost and the like corresponding to the increase, and if the increase of the price of the raw material is modified to be 3% or the price of the raw material is directly modified, the data which needs to be adjusted every month can be obtained.
Here, the data that needs to be adjusted per month may be obtained based on the acquired modification data, that is, acquiring modification data (speed increase x%, amplitude increase 2%, 12 month change to 10 months, etc.), determining current relevant data based on the historical data, determining target modification data based on the modification data and the current relevant data, and determining the amount of adjustment needed per time period according to the target modification data.
The related data refers to data related to demand information, taking production data as an example, and the related data comprises data such as speed increase, time, raw material cost and the like.
It should be noted that, when the price of a certain raw material rises too much, that is, the modification data is too large, the purchase amount of the raw material can be reduced by setting a threshold value, the modification data is determined again, and then the data to be adjusted every month is determined by the determined modification data.
Further, since there may be a case where the database or the data warehouse is not full of data, if the data is determined to be a default, the data needs to be supplemented. Here, the data category corresponding to each kind of demand information may be set in advance, and whether the acquired data to be processed is complete may be determined based on the set data category. The method specifically comprises the following steps: dividing pre-acquired data into at least one item of data, the at least one item of data comprising: essential class data, auxiliary class data; the essential class data refers to data necessary for completing prediction, and the auxiliary class data refers to data which has an influence on a prediction result and is additionally added to achieve more accurate prediction. Judging whether the acquired data has the necessary data and the auxiliary data, if so, considering the data to be complete, and if one or all of the necessary data and the auxiliary data is missing, considering the data to be incomplete.
As an example, predicting production volume of 8 months, the data to be acquired includes: raw material quantity, production line personnel quantity, production line personnel gender, production line personnel's production efficiency etc. These data are classified into 2 types: essential class data, auxiliary class data; the raw material quantity, the production line personnel quantity and the production line quantity belong to necessary data; production line personnel's production efficiency belongs to supplementary class data. When the collected data includes data such as the number of raw materials, the number of production line personnel, the number of production lines, the sex of the production line personnel and the production efficiency of the production line personnel, the data is considered to be complete, and if only partial data exists or none exists, the data is considered to be incomplete.
It should be further noted that, processing the data to be processed may also implement combined recommendation. For example, first relevant data of historical data for production realized by a woolen material which is an unprocessed original material can be obtained; and second related data for realizing production through ready-made raw materials in the historical data can be acquired, and a new processing result is generated by combining the first related data and the second related data.
Here, the wool is cheap but needs further processing, and the ready-made raw materials are expensive but can save time and processing cost, so that the two can be combined in proportion to obtain a production scheme which is cost-saving and relatively cheap.
The new combination generated by combining the first correlation data and the second correlation data may be: and setting a combination factor, and processing the first related data and the second related data based on the combination factor to generate a new processing result. The combination factor may be randomly generated, or may be set by a user based on needs, and the combination factor sent by the receiving terminal is processed, for example, the combination factor may be set to 0.5, that is, half of each of the raw material and the ready-made raw material is used to realize production.
According to the data processing method provided by the embodiment of the invention, the acquired data to be processed is processed to obtain the corresponding first processing result and second processing result, the corresponding processing mode is determined based on the first processing result and the second processing result, and then the processing is executed according to the corresponding processing mode. Therefore, corresponding processing can be executed according to different requirements of different users, decisions are provided for the users, particularly the management layer, through processing of information with different requirements, and user experience is greatly improved.
An embodiment of the present invention provides a data processing method, and fig. 3 is a schematic diagram illustrating an implementation flow of the data processing method provided in the embodiment of the present invention, as shown in fig. 3, the method mainly includes the following steps:
It should be noted that the setting of the time node may be realized by setting a timer in the intelligent middle station, and if the time node is set, whether the preset time node is reached currently is determined, and after the corresponding time node is reached, the acquisition of the to-be-processed data is automatically executed.
It should be noted that, here, the current time of the intelligent central station is obtained, and the current time is compared with the preset time node to determine whether the preset time node is reached. For example, the preset time node is every hour: 11:00, 12:00, 13:00 …, assuming the current time of acquisition is 12:30, the preset time node is not considered to have been reached.
It should be noted that the data to be processed includes historical data and target data; the target data comprises a target time node and a target value.
The process proceeds to step 405 after the acquisition of the data to be processed is completed.
It should be noted that the data category corresponding to each type of demand information may be preset, and whether the acquired data to be processed is complete is determined based on the set data category. The method specifically comprises the following steps: dividing pre-acquired data into at least one item of data, the at least one item of data comprising: essential class data, auxiliary class data; the necessary class data refers to data which is necessary to complete prediction, and the auxiliary class data refers to data which is additionally added and has influence on a prediction result in order to realize more accurate prediction; judging whether the acquired data has the necessary data and the auxiliary data, if so, considering the data to be complete, and if one or all of the necessary data and the auxiliary data is missing, considering the data to be incomplete.
And 406, processing the data to be processed to obtain a processing result, determining a processing mode based on the processing result, and returning a final processing result.
It should be noted that, after the final processing result is returned, the current flow is ended.
It should be further noted that the processing results include a first type of processing result and a second type of processing result.
The method comprises the steps that a first processing model can be constructed based on historical data of at least one time period, and a first processing result is obtained according to the first processing model; based on the first processing result, an amount of resources required to achieve the first processing result is determined.
A target time node corresponding to the target data can be obtained; determining, based on the target time node, a required time to reach the target time node; decomposing the required time to obtain at least one sub-time, and determining a second sub-processing result corresponding to each sub-time in the at least one sub-time; and comparing the second sub-processing result with the current resource amount, judging whether the adjustment is needed, determining that the adjustment is needed, and generating adjustment information.
It should be noted that the alarm command may include a default data category, i.e., a specific missing data is notified. The alarm instruction can be in the forms of an alarm bullet frame, an alarm short message and the like.
In addition, since there may be a case where data is not complete in the database or the data warehouse, if data is determined to be default, data needs to be supplemented.
In practical application, relevant information corresponding to the demand information can be searched through a network, and the searched relevant information is stored in a database or a data warehouse of the intelligent central station. The related information includes information associated with the demand information.
It should be noted that the demand information may be used as a search parameter to perform a search on the network. Here, the search may be performed by a search engine on the server side, and the search engine may be any search engine such as hundredths, google, and the like. After the search result related to the demand information is displayed on the search engine of the intelligent middle station, the obtained search result is added to a database or a data warehouse, and the update of the information related to the demand information is realized.
In practical applications, there may be any adjustment to determine the time required to complete the process and the cost required to complete the process. In this case, accurate prediction meeting actual requirements cannot be realized only based on static input data, and data needs to be adjusted, that is, modified. New processing may be performed based on the modification data transmitted from the terminal side.
And step 410, processing the data to be processed based on the modified data, generating a new processing result, and ending the process.
According to the data processing method provided by the embodiment of the invention, the acquired historical data and the acquired target data are processed to obtain the corresponding first processing result and second processing result, the corresponding processing mode is determined based on the first processing result and the second processing result, and then the processing is executed according to the corresponding processing mode. Therefore, corresponding processing can be executed according to different requirements of different users, decisions are provided for the users, particularly the management layer, through processing of different kinds of information, and user experience is greatly improved.
Based on the same inventive concept of the above embodiments, an embodiment of the present invention provides a data processing apparatus, and fig. 4 is a schematic structural diagram of a data processing apparatus 500 according to an embodiment of the present invention, as shown in fig. 4, the data processing apparatus 500 includes: an acquisition unit 501 and a processing unit 502; wherein,
the acquiring unit 501 is configured to acquire data to be processed; the data to be processed comprises historical data and target data;
the processing unit 502 is configured to process the data to be processed to obtain a processing result, and determine a processing mode based on the processing result; the processing mode comprises at least one of a first processing mode and a second processing mode;
the first processing mode is to determine the amount of resources required for reaching the processing result;
and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
It should be noted that the processing unit 502 further includes: a first processing unit 5021 and a second processing unit 5022; wherein,
the first processing unit 5021 is configured to construct a first processing model based on historical data of at least one time period, and obtain a first processing result according to the first processing model; based on the first processing result, an amount of resources required to achieve the first processing result is determined.
The second processing unit 5022 is configured to obtain a target time node corresponding to the target data; determining, based on the target time node, a required time to reach the target time node; decomposing the required time to obtain at least one sub-time, and determining a second sub-processing result corresponding to each sub-time in the at least one sub-time; and comparing the second sub-processing result with the current resource amount, judging whether the adjustment is needed, determining that the adjustment is needed, and generating adjustment information.
It should be noted that the determining that adjustment is required and generating adjustment information includes: acquiring historical data of at least one time period before a target time node corresponding to the target data, constructing a second processing model based on the historical data of at least one time period before the target time node, and obtaining a second processing result corresponding to the target time node based on the second processing model; determining an adjustment factor based on the second processing result, the target data, and the required time to reach the target time node; generating the adjustment information based on the adjustment factor.
It should be noted that the acquiring unit 501 further includes: the determination unit 5011, the determination unit 5012; wherein,
the judging unit 5011 is configured to judge whether a preset time node is reached, and judge whether at least one of operation instructions sent by a terminal side is received;
the determining unit 5012 is configured to determine at least one of a time node reaching a preset time and an operation instruction sent by a receiving terminal side, and acquire data to be processed.
The data processing apparatus 500 further includes an adjusting unit 503, where the adjusting unit 503 is configured to receive adjustment information after determining a processing manner based on the processing result; and processing the data to be processed based on the adjustment information to obtain a new processing result.
It should be noted that, because the principle of the data processing apparatus 500 for solving the problem is similar to the data processing method, the specific implementation process and the implementation principle of the server 500 can refer to the foregoing method and implementation process, and repeated details are not repeated.
The data processing device provided by the embodiment of the invention obtains the corresponding first processing result and second processing result by processing the acquired data to be processed, determines the corresponding processing mode based on the first processing result and the second processing result, and further executes the processing according to the corresponding processing mode. Therefore, corresponding processing can be executed according to different requirements of different users, decisions are provided for the users, particularly the management layer, through processing of different kinds of information, and user experience is greatly improved.
The components in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware or a form of a software functional module.
Based on the understanding that the technical solution of the embodiments of the present invention essentially or a part of the technical solution contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, and include several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Accordingly, embodiments of the present invention provide a computer storage medium storing a computer program that, when executed by at least one processor, performs the steps of the above-described embodiments.
Referring to fig. 5, a specific hardware structure of a data processing apparatus 600 provided in an embodiment of the present invention is shown, including: a network interface 601, a memory 602, and a processor 603; the various components are coupled together by a bus system 604. It is understood that the bus system 604 is used to enable communications among the components. The bus system 604 includes a power bus, a control bus, and a status signal bus in addition to a data bus. For clarity of illustration, however, the various buses are labeled as bus system 604 in fig. 5.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The methods disclosed in the several method embodiments provided in the present application may be combined arbitrarily without conflict to obtain new method embodiments.
Features disclosed in several of the product embodiments provided in the present application may be combined in any combination to yield new product embodiments without conflict.
The features disclosed in the several method or apparatus embodiments provided in the present application may be combined arbitrarily, without conflict, to arrive at new method embodiments or apparatus embodiments.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (9)
1. A method of data processing, the method comprising:
acquiring data to be processed; the data to be processed comprises historical data and target data;
processing the data to be processed to obtain a processing result, and determining a processing mode based on the processing result;
the processing mode comprises one of a first processing mode and a second processing mode;
the first processing mode is to determine the amount of resources required for reaching the processing result;
and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
2. The method according to claim 1, wherein the processing the data to be processed to obtain a processing result, and determining a first processing manner based on the processing result comprises:
constructing a first processing model based on historical data of at least one time period, and obtaining a first processing result according to the first processing model;
based on the first processing result, an amount of resources required to achieve the first processing result is determined.
3. The method according to claim 1, wherein the processing the data to be processed to obtain a processing result, and determining a second processing manner based on the processing result comprises:
acquiring a target time node corresponding to the target data;
determining, based on the target time node, a required time to reach the target time node;
decomposing the required time to obtain at least one sub-time, and determining a second sub-processing result corresponding to each sub-time in the at least one sub-time;
and comparing the second sub-processing result with the current resource amount, judging whether the adjustment is needed, determining that the adjustment is needed, and generating adjustment information.
4. The method of claim 3, wherein determining that an adjustment is required, generating adjustment information, comprises:
acquiring historical data of at least one time period before a target time node corresponding to the target data, constructing a second processing model based on the historical data of at least one time period before the target time node, and obtaining a second processing result corresponding to the target time node based on the second processing model;
determining an adjustment factor based on the second processing result, the target data, and the required time to reach the target time node;
based on the adjustment factor, adjustment information is generated.
5. The method of claim 1, wherein the obtaining the data to be processed comprises:
judging whether a preset time node is reached or not, and judging whether at least one of operation instructions sent by a terminal side is received or not;
and determining at least one of the preset time node and the operation instruction sent by the receiving terminal side, and acquiring the data to be processed.
6. The method of claim 1, wherein after determining a processing mode based on the processing result, the method further comprises:
receiving adjustment data;
and processing the data to be processed based on the adjustment data to obtain a new processing result.
7. A data processing apparatus, characterized in that the apparatus comprises: an acquisition unit and a processing unit; wherein,
the acquisition unit is used for acquiring data to be processed; the data to be processed comprises historical data and target data;
the processing unit is used for processing the data to be processed to obtain a processing result and determining a processing mode based on the processing result;
the processing mode comprises one of a first processing mode and a second processing mode;
the first processing mode is to determine the amount of resources required for reaching the processing result;
and the second processing mode is to compare the processing result with the current resource amount, judge whether the adjustment is needed, determine that the adjustment is needed and generate adjustment information.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
9. A data processing apparatus, comprising: a processor and a memory for storing a computer program operable on the processor, wherein the processor is operable to perform the steps of the method of any of claims 1 to 6 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910729574.5A CN110633840A (en) | 2019-08-08 | 2019-08-08 | Data processing method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910729574.5A CN110633840A (en) | 2019-08-08 | 2019-08-08 | Data processing method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110633840A true CN110633840A (en) | 2019-12-31 |
Family
ID=68969305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910729574.5A Pending CN110633840A (en) | 2019-08-08 | 2019-08-08 | Data processing method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110633840A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798261A (en) * | 2020-03-24 | 2020-10-20 | 北京沃东天骏信息技术有限公司 | Information updating method and device |
| CN113449242A (en) * | 2020-03-27 | 2021-09-28 | 北京京东振世信息技术有限公司 | Method, device and equipment for processing logistics freight volume data and storage medium |
| CN114693009A (en) * | 2020-12-25 | 2022-07-01 | 苏州国双软件有限公司 | Data processing method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120297251A1 (en) * | 2011-05-17 | 2012-11-22 | International Business Machines Corporation | Method and computer program product for system tuning based on performance measurements and historical problem data and system thereof |
| CN105139157A (en) * | 2015-10-08 | 2015-12-09 | 武汉誉德节能数据服务有限公司 | Enterprise management method and system based on energy data |
| CN105897616A (en) * | 2016-05-17 | 2016-08-24 | 腾讯科技（深圳）有限公司 | Resource allocation method and server |
| CN107918811A (en) * | 2017-11-30 | 2018-04-17 | 国网天津市电力公司 | A kind of energy internet construction method for improving efficiency of energy utilization |
-
2019
- 2019-08-08 CN CN201910729574.5A patent/CN110633840A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120297251A1 (en) * | 2011-05-17 | 2012-11-22 | International Business Machines Corporation | Method and computer program product for system tuning based on performance measurements and historical problem data and system thereof |
| CN105139157A (en) * | 2015-10-08 | 2015-12-09 | 武汉誉德节能数据服务有限公司 | Enterprise management method and system based on energy data |
| CN105897616A (en) * | 2016-05-17 | 2016-08-24 | 腾讯科技（深圳）有限公司 | Resource allocation method and server |
| CN107918811A (en) * | 2017-11-30 | 2018-04-17 | 国网天津市电力公司 | A kind of energy internet construction method for improving efficiency of energy utilization |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111798261A (en) * | 2020-03-24 | 2020-10-20 | 北京沃东天骏信息技术有限公司 | Information updating method and device |
| CN113449242A (en) * | 2020-03-27 | 2021-09-28 | 北京京东振世信息技术有限公司 | Method, device and equipment for processing logistics freight volume data and storage medium |
| CN113449242B (en) * | 2020-03-27 | 2023-09-26 | 北京京东振世信息技术有限公司 | Logistics bill data processing method, device, equipment and storage medium |
| CN114693009A (en) * | 2020-12-25 | 2022-07-01 | 苏州国双软件有限公司 | Data processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10740773B2 (en) | Systems and methods of utilizing multiple forecast models in forecasting customer demands for products at retail facilities | |
| CN105872629A (en) | Content recommendation method, apparatus and system | |
| CN110633840A (en) | Data processing method, device and storage medium | |
| Chibani et al. | Dynamic optimisation for highly agile supply chains in e-procurement context | |
| CA3097449A1 (en) | Method and system for model auto-selection using an ensemble of machine learning models | |
| CN110610382A (en) | Vehicle sales prediction method, apparatus, computer device, and storage medium | |
| Paul et al. | Development of a production inventory model with uncertainty and reliability considerations | |
| EP4283511A1 (en) | Information processing method and device, server and user equipment | |
| CN113723692A (en) | Data processing method, apparatus, device, medium, and program product | |
| Wang et al. | An estimation of distribution algorithm for hybrid flow shop scheduling under stochastic processing times | |
| Aghamohammadi-Bosjin et al. | Agile two-stage lot-sizing and scheduling problem with reliability, customer satisfaction and behaviour under uncertainty: a hybrid metaheuristic algorithm | |
| Mokhtari | A joint internal production and external supplier order lot size optimization under defective manufacturing and rework | |
| CN114692859A (en) | Data processing method and device, computing equipment and test simplification equipment | |
| Otay et al. | An integrated fuzzy approach for classifying slow-moving items | |
| JP6631263B2 (en) | Agent based demand forecasting system and method | |
| Waris et al. | Smart innovation management in product life cycle | |
| CN110543973A (en) | data prediction method, data prediction result adjusting method, device and equipment | |
| CN113065911A (en) | Recommendation information generation method and device, storage medium and electronic equipment | |
| CN113313562B (en) | Product data processing method and device, computer equipment and storage medium | |
| CN110941771A (en) | Commodity parallel dynamic pushing method in e-commerce platform | |
| US11803464B2 (en) | System for automatic identification and selection of optimization metrics and accompanying models in experimentation platforms | |
| CN108345941B (en) | Parameter adjusting method and device | |
| CN108629062A (en) | Methods, devices and systems for optimization of fixing a price | |
| Oliveira et al. | Deep Learning for Short-term Instant Energy Consumption Forecasting in the Manufacturing Sector | |
| CN113220986A (en) | Information recommendation method and device, electronic equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191231 |