CN117875522A - Method, device, storage medium and equipment for predicting event number - Google Patents
Method, device, storage medium and equipment for predicting event number Download PDFInfo
- Publication number
- CN117875522A CN117875522A CN202410281161.6A CN202410281161A CN117875522A CN 117875522 A CN117875522 A CN 117875522A CN 202410281161 A CN202410281161 A CN 202410281161A CN 117875522 A CN117875522 A CN 117875522A
- Authority
- CN
- China
- Prior art keywords
- occurrence
- sequence
- specific event
- event
- correlation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000003860 storage Methods 0.000 title claims description 20
- 230000004927 fusion Effects 0.000 claims description 50
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012549 training Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 11
- 238000002360 preparation method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000006872 improvement Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000005096 rolling process Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000004907 gland Anatomy 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 229920001296 polysiloxane Polymers 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000010979 ruby Substances 0.000 description 1
- 229910001750 ruby Inorganic materials 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The method utilizes the occurrence times of the specific event in history, provides a prediction method of the occurrence times of the specific event in a future period according to the correlation among the specific events of each attribute, and provides a basis for resource preparation required by related departments to process the specific event.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a method, an apparatus, a storage medium, and a device for predicting an event number.
Background
In the work of the related departments, there are often specific events which are out of the work plan but must be processed, and the processing of the specific events affects the normal work progress of the related departments because the specific events are out of the normal work flow of the related departments. At the same time, unplanned processing of a particular event also affects the ability of the relevant departments to process the particular event.
Thus, the invention provides a method, a device, a storage medium and equipment for predicting the number of events.
Disclosure of Invention
The present disclosure provides a method and apparatus for predicting the number of events, so as to partially solve the above-mentioned problems in the prior art.
The technical scheme adopted in the specification is as follows:
the present specification provides a method of event number prediction, comprising:
acquiring a specific event which occurs historically;
obtaining each occurrence frequency sequence of the specific event according to the occurrence frequency of the specific event, the occurrence time of the specific event and the attribute of the specific event;
determining the correlation between the occurrence sequences;
according to the correlation, fusing the occurrence frequency sequences to obtain a fused sequence;
the fusion sequence is input into a pre-trained predictive model to predict the number of occurrences of the particular event within a future period of time from the predictive model.
Optionally, the attribute of the specific event specifically includes: the region in which the specific event occurs and/or the type of the specific event.
Optionally, according to the occurrence times of the specific event, the occurrence times of the specific event and the attribute of the specific event, obtaining the occurrence times sequence of the specific event specifically includes:
for each specific event of the attribute, determining the occurrence sequence of the specific event of the attribute according to the occurrence times of the specific event of the attribute and the occurrence times of the specific event of the attribute.
Optionally, according to the correlation, fusing the occurrence frequency sequences to obtain a fused sequence, which specifically includes:
and combining the occurrence frequency sequences to obtain a fusion sequence, wherein the position distance of each occurrence frequency sequence with higher correlation in the fusion sequence is closer.
Optionally, fusing the occurrence frequency sequences to obtain a fused sequence, which specifically includes:
for each occurrence sequence, obtaining a correlation score of the occurrence sequence according to the sum of correlation values of the occurrence sequences and all occurrence sequences except the occurrence sequence;
and combining the occurrence frequency sequences into a fusion sequence according to the correlation scores, wherein the correlation scores of the occurrence frequency sequences which are closer to the edge position in the fusion sequence are lower.
Optionally, pre-training the prediction model specifically includes:
determining standard occurrence times and sample events, wherein the standard occurrence times are the occurrence times of specific events in a specified time period, and the sample events are the specific events occurring in each time period before the specified time period;
obtaining sample sequences of the occurrence times of the sample events according to the occurrence times of the sample events, the occurrence times of the sample events and the attributes of the sample events;
determining sample correlation between sample sequences of occurrence times;
fusing the sample sequences of the occurrence times according to the sample correlation to obtain a fused sample sequence;
inputting the fusion sample sequence into a prediction model to obtain the predicted occurrence times of specific events in a specified period;
the predictive model is trained with the aim of minimizing the difference between the number of occurrences of a particular event within the predicted specified period of time and the number of occurrences of the criterion.
Optionally, the method further comprises:
acquiring each description text corresponding to each occurrence of a specific event;
inputting each description text into a semantic analysis model, and carrying out cluster analysis on each description text to obtain a plurality of types of labels;
a number of types of the particular event are determined from the type tag.
The present specification provides an event number prediction apparatus including:
the acquisition module acquires specific events occurring historically;
the extraction module is used for obtaining each occurrence frequency sequence of the specific event according to the occurrence frequency of the specific event, the occurrence time of the specific event and the attribute of the specific event;
the computing module is used for determining the correlation among the occurrence frequency sequences;
the fusion module fuses the occurrence frequency sequences according to the correlation to obtain a fusion sequence;
a prediction module inputs the fusion sequence into a pre-trained prediction model to predict the number of occurrences of the particular event within a future period of time from the prediction model.
The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the above-described event number prediction method.
The present specification provides an apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing a method of event number prediction as described above when executing the program.
The above-mentioned at least one technical scheme that this specification adopted can reach following beneficial effect:
in the method for predicting the number of events provided in the present specification, a specific event occurring in history is obtained, according to the occurrence times of the specific event, the occurrence time of the specific event and the attribute of the specific event, each occurrence time sequence of the specific event is obtained, the correlation between each occurrence time sequence is determined, each occurrence time sequence is fused according to the correlation, a fusion sequence is obtained, and the fusion sequence is input into a pre-trained prediction model, so that the occurrence times of the specific event in a future period are predicted through the prediction model.
According to the method, the historical occurrence times of the specific events are utilized, and according to the correlation among the specific events of all the attributes, a prediction method of the occurrence times of the specific events in a future period is provided, so that a basis is provided for resource preparation required by related departments to process the specific events.
Drawings
The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. In the drawings:
FIG. 1 is a flow chart of a method of event number prediction in the present specification;
FIG. 2 is a schematic structural diagram of the fusion sequence in the present specification;
FIG. 3 is a schematic diagram of an event number prediction apparatus provided in the present specification;
fig. 4 is a schematic view of the electronic device corresponding to fig. 1 provided in the present specification.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present application based on the embodiments herein.
The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for predicting the number of events in the present specification, where the method for predicting the number of events specifically includes the following steps:
s100: a particular event that has historically occurred is obtained.
For the related departments, the work content is often determined by the top-to-bottom internal arrangement, that is, the planned workload is adapted to the working capacity of the personnel, but the related departments also have interfaces with the external personnel, through which the related departments also receive specific events which need to be processed inside the related departments and are not in the planned workload, so that the processing speed of the specific events and the working progress of the related departments are influenced. After the specific event is obtained, the related departments may count the occurrence of the specific event, where the occurrence may include the occurrence number of the specific event, the occurrence time of each occurrence of the specific event, and the attribute of each occurrence of the specific event, so that when the method provided in the present specification is applied, the occurrence of the specific event that occurs historically may be obtained through statistical records. The method provided by the specification can be applied to an event quantity prediction system, wherein the event quantity prediction system can comprise a pre-trained prediction model, and the event quantity prediction system can be connected with or comprise a specific event statistics system, so that a statistical record of a specific event can be obtained when the event quantity prediction is carried out.
In one or more embodiments of the present description, the particular event may be, in particular, a contradictory dispute event that the relevant department accepts the process.
S102: and obtaining each occurrence frequency sequence of the specific event according to the occurrence frequency of the specific event, the occurrence time of the specific event and the attribute of the specific event.
According to the occurrence condition of the specific event which occurs historically, the occurrence times of the specific event, the occurrence time of the specific event and the attribute of the specific event can be determined, specifically, a user can preset a time period and a time period length, so that the time period preset by the user can be divided into various time periods according to the time period preset by the user, the number of the specific event which occurs in each time period can be determined according to the occurrence time of the specific event each time period, the specific event is classified according to the attribute of the specific event, and finally various occurrence times sequences representing the occurrence times of various specific events in various time periods of the preset period are obtained. Specifically, when the preset time is one week and the time period is one day, the method provided by the specification is applied to predict the occurrence times of the specific events on 1 month and 8 days, the specific event occurrence time sequence 1-2-2-1-3-1-4 aiming at the A attribute is represented, wherein the specific event of the A attribute on 1 month and 1 day occurs 1 time, the specific event of the A attribute on 1 month and 2 days occurs 2 times, … … times and the specific event of the A attribute on 1 month and 7 days occurs 4 times.
In one or more embodiments of the present specification, the attribute of the specific event specifically includes: the region in which the specific event occurs and/or the type of the specific event.
That is, a particular event may be classified into different attributes according to the region in which the particular event occurs and/or the type of the particular event. For example, when the attribute of the specific event specifically includes an area where the specific event occurs and a type of the specific event, the specific event may be classified into attributes of A, B, C … …, etc., the specific event of the a attribute may represent a first type of the specific event occurring in the a area, and the specific event of the B attribute may represent a second type of the specific event … … occurring in the a area.
In one or more embodiments of the present disclosure, the manner of acquiring the type of the specific event may be to acquire each description text corresponding to each occurrence of the specific event, input each description text into a semantic analysis model, perform cluster analysis on each description text to obtain a plurality of type tags, and determine a plurality of types of the specific event according to the type tags.
When the related departments count the specific events, the statistical records of the statistics can also comprise descriptive texts corresponding to the specific events which occur each time, the descriptive texts describe information such as the event of the specific events which occur each time, and therefore the types of a plurality of specific events can be obtained through semantic analysis clustering by utilizing the descriptive texts corresponding to the specific events which occur each time. Thus, when predicting the number of occurrences of a specific event in a future period using the method provided in the present specification, the type of the specific event per occurrence can be determined through descriptive text. Of course, the mode of acquiring the specific event type may be that the related departments directly record the type of the specific event which occurs each time when counting the occurrence of the specific event.
In one or more embodiments of the present specification, for each attribute specific event, a sequence of occurrence times of the attribute specific event is determined according to the occurrence times of the attribute specific event and the respective occurrence times of the attribute specific event.
That is, when the statistics of the specific event is performed, the attribute of the specific event can be determined, so that the sequence of occurrence times corresponding to the specific event of each attribute can be determined without classifying after the specific event is acquired, and the sequence of occurrence times corresponding to the specific event of all the attributes is used as the final sequence of occurrence times of the specific event.
S104: a correlation between the sequences of occurrence times is determined.
After each occurrence sequence is obtained, because each occurrence sequence is obtained according to the preset time period and the time period length, that is, the sequence length of each occurrence sequence is identical, and the sequence and the interval in each occurrence sequence have the same meaning, the correlation between each occurrence sequence can be obtained by using the correlation algorithm of the time sequence. Specifically, for any two different occurrence sequences in the occurrence sequence population, correlation between the two sequences needs to be obtained. Then, according to the correlation of the time series, the correlation between the occurrence sequences of the two attributes corresponds to A, B, that is, the probability that the occurrence of the specific event representing the a attribute causes the occurrence of the event of the B attribute, or vice versa. The correlation algorithm of the time sequence may include a time-series delay correlation algorithm, a gland cause and effect detection algorithm, and other common time-series correlation algorithms, when the correlation is calculated according to the two algorithms, the correlation of the attribute a to the attribute B is different from the correlation of the attribute B to the attribute a, that is, the probability that the specific event of the attribute a causes the event of the attribute B is distinguished from the probability that the specific event of the attribute B causes the specific event of the attribute a when the two algorithms are applied, and the specific application of the correlation algorithm is not limited herein.
S106: and according to the correlation, fusing the occurrence frequency sequences to obtain a fused sequence.
Since the method provided in the present specification predicts the occurrence times of the specific events in the future period by using the occurrence times of the specific events in the history, the correlation between the specific events of each attribute is first determined in the prediction process, that is, the occurrence probability of the specific event of the attribute a causes the occurrence of the specific event of the attribute B, and then the occurrence of the specific event of each attribute in the future is predicted by using the occurrence of the specific event of each attribute in the history. In step S102, the occurrence sequences of the specific events are obtained, and in order to obtain the predicted occurrence of the specific event in the future period through one prediction, the occurrence sequences need to be fused to obtain a fused sequence. The fusion sequence is used for predicting the occurrence times of specific events in future time periods in subsequent steps, and in order to facilitate the extraction of the relationship of the specific events with different attributes in the fusion sequence (namely, the occurrence probability of the specific events with the attribute A and the specific events with the attribute B in the previous step) by the prediction model in the subsequent steps, the fusion of the occurrence times sequences needs to be carried out according to the correlation among the occurrence times sequences of the specific events with the attributes.
In one or more embodiments of the present description, the fusion sequence may be a high-dimensional matrix with attributes of a particular event and time periods as respective dimensions.
In one or more embodiments of the present disclosure, the sequences of occurrence times are combined to obtain a fusion sequence, and the sequences of occurrence times with higher correlation are positioned closer together in the fusion sequence.
S108: the fusion sequence is input into a pre-trained predictive model to predict the number of occurrences of the particular event within a future period of time from the predictive model.
After the fusion sequence is obtained, the fusion sequence can be input into a pre-trained prediction model, so that the prediction model can directly output the predicted occurrence times of specific events of each attribute in a future period. Specifically, the prediction model may include a cross attention layer, a convolution layer and a full connection output layer, wherein the cross attention layer is used for establishing an association relation between the occurrence frequency sequences of specific events of all attributes in the fusion sequence, the convolution layer is used for extracting association characteristics, and the full connection output layer is used for obtaining the predicted occurrence frequency of the specific events of all the attributes in a future period.
In one or more embodiments of the present disclosure, the number of occurrences of a specific event in a future period and a plurality of periods after the future period may be further predicted, specifically, the number of occurrences of the specific event in the predicted future period may be obtained first by using the number of occurrences of the specific event historically, then the number of occurrences of the specific event historically and the number of occurrences of the specific event in the predicted future period may be combined, the number of occurrences of the specific event in the period after the future period may be predicted by using the combined number of occurrences sequence and the prediction model, and when the number of occurrences of the specific event in the subsequent period needs to be predicted continuously, the result of the prediction may be combined with the number of occurrences sequence for the prediction continuously, and the combined number of occurrences sequence may be used for the prediction.
For example, when the preset time is one week and the time period is one day, and the method provided by the specification is applied to predict the occurrence times of the specific events on 1 month 8 day and 1 month 9 day, the occurrence times sequence of each occurrence time can be obtained according to the occurrence times of the specific events on 1 month 1-7 day, the occurrence times of the specific events on 1 month 8 day can be further predicted, and then the occurrence times of the specific events on 1 month 9 day can be predicted according to the occurrence times of the specific events on 1 month 2-8 day, so as to obtain the occurrence times of the specific events on 1 month 9 day.
The method for predicting the number of events shown in fig. 1 utilizes the historical occurrence times of specific events, and according to the correlation among specific events of all attributes, provides a method for predicting the occurrence times of specific events in a future period, and provides a basis for resource preparation required by related departments for processing the specific events.
In step S106 shown in fig. 1, for each occurrence sequence, a correlation score of the occurrence sequence is obtained from the sum of correlation values of the occurrence sequences and all occurrence sequences except the occurrence sequence, and the occurrence sequences are combined into a fusion sequence according to the correlation score, wherein the correlation score of the occurrence sequence closer to the edge position in the fusion sequence is lower.
Specifically, the method of combining the occurrence sequences into the fusion sequence may be that the correlation score of the occurrence sequences is obtained by the above-described method, and the occurrence sequences are sorted in the attribute dimension according to the correlation score. Taking the attribute of the specific event as an example, in a fusion sequence shown in fig. 2, the two attributes and a time period are taken as three dimensions of the fusion sequence, the fusion sequence is a three-dimensional matrix, each occurrence frequency sequence naturally forms the dimension of the time period, in the two dimensions of the area where the specific event occurs and the type of the specific event, according to the correlation score of each occurrence frequency sequence, the occurrence frequency sequence with the highest correlation score is arranged in the central position of the area where the event occurs and the type of the specific event, and according to the position in the three-dimensional matrix corresponding to the high-low correlation score, each occurrence frequency sequence is arranged from the center to the edge, and the obtained three-dimensional matrix is the fusion sequence.
Because the convolution kernel used by the convolution layer in the prediction model has limited receptive field, the occurrence frequency sequences are combined into the fusion sequence in the mode, the positions of the occurrence frequency sequences with strong correlation in the fusion sequence are closer, so that the prediction model can more directly utilize the characteristic information among the occurrence frequency sequences with strong correlation when the feature of the fusion sequence is extracted by the convolution layer, and finally, the accuracy of the occurrence frequency prediction of a specific event in a future period is improved.
In one or more embodiments of the present disclosure, a predictive model may be trained in advance by determining a standard occurrence number and a sample event, where the standard occurrence number is a occurrence number of a specific event in a specified period, the sample event is a specific event occurring in each period before the specified period, obtaining a sample sequence of each occurrence number of the sample event according to the occurrence number of the sample event, each occurrence time of the sample event, and an attribute of the sample event, determining a sample correlation between sample sequences of each occurrence number, fusing sample sequences of each occurrence number according to the sample correlation, obtaining a fused sample sequence, inputting the fused sample sequence into the predictive model, obtaining a predicted occurrence number of the specific event in the specified period, and training the predictive model with a goal of minimizing a difference between the predicted occurrence number of the specific event in the specified period and the standard occurrence number.
Namely, selecting a specified period, taking the occurrence times of the specific events of the attributes in the specified period as labels, obtaining a fused sample sequence by utilizing the occurrence times sequence of the specific events of the attributes in the past periods of the specified period, inputting the fused sample sequence into a prediction model to obtain the predicted occurrence times of the specific events of the attributes in the specified period, and training the prediction model according to the difference between the occurrence times of the specific events of the attributes in the predicted specified period and the labels.
The process of training the model can also be implemented using a rolling prediction method. The rolling prediction is to take a prediction result as an input of a model, repeatedly call the model to predict a result of the next moment, and solve the problem of the reduction of accuracy and reliability of the prediction model caused by the rolling prediction by a plan sampling (Scheduled sampling) method, wherein the plan sampling is to set a probability p, predict each step by the probability p by the input of the last step, and predict according to the prompt of real data by the probabilities 1-p.
In one or more embodiments of the present description, the methods provided herein may also be applied while maintaining updates to the predictive model, and specific methods of updating the predictive model may be implemented by means of parametric cure, knowledge distillation, and incremental learning to adapt the predictive model to changes in social environments.
The above method for predicting the number of events provided for one or more embodiments of the present disclosure further provides a corresponding device for predicting the number of events based on the same concept, as shown in fig. 3.
Fig. 3 is a schematic diagram of an event counting device provided in the present specification, specifically including:
an acquisition module 300 that acquires a specific event that has historically occurred;
the extraction module 302 obtains each occurrence sequence of the specific event according to the occurrence times of the specific event, the occurrence time of the specific event and the attribute of the specific event;
a calculation module 304 that determines a correlation between the sequences of occurrence times;
the fusion module 306 fuses the occurrence times according to the correlation to obtain a fusion sequence;
a prediction module 308 inputs the fusion sequence into a pre-trained prediction model to predict the number of occurrences of the particular event within a future period of time from the prediction model.
Optionally, the attribute of the specific event specifically includes: the region in which the specific event occurs and/or the type of the specific event.
Optionally, the extracting module 302 is specifically configured to: for each specific event of the attribute, determining the occurrence sequence of the specific event of the attribute according to the occurrence times of the specific event of the attribute and the occurrence times of the specific event of the attribute.
Optionally, the fusion module 306 is specifically configured to: and combining the occurrence frequency sequences to obtain a fusion sequence, wherein the position distance of each occurrence frequency sequence with higher correlation in the fusion sequence is closer.
Optionally, the fusion module 306 is specifically configured to: and aiming at each occurrence sequence, obtaining a correlation score of the occurrence sequence according to the sum of correlation values of the occurrence sequences and all occurrence sequences except the occurrence sequence, combining the occurrence sequences into a fusion sequence according to the correlation score, wherein the correlation score of the occurrence sequence which is closer to the edge position in the fusion sequence is lower.
Optionally, the prediction module 308 is further configured to: determining standard occurrence times and sample events, wherein the standard occurrence times are occurrence times of specific events in a specified time period, the sample events are specific events occurring in time periods before the specified time period, obtaining sample sequences of the occurrence times of the sample events according to the occurrence times of the sample events, the occurrence times of the sample events and the attributes of the sample events, determining sample correlation among the sample sequences of the occurrence times, fusing the sample sequences of the occurrence times according to the sample correlation, obtaining a fused sample sequence, inputting the fused sample sequence into a prediction model, obtaining the occurrence times of the specific events in the predicted specified time period, and training the prediction model with the aim of minimizing the difference between the occurrence times of the specific events in the predicted specified time period and the standard occurrence times.
Optionally, the extracting module 302 is further configured to: and acquiring each description text corresponding to each occurrence of the specific event, inputting each description text into a semantic analysis model, carrying out cluster analysis on each description text to obtain a plurality of types of labels, and determining a plurality of types of the specific event according to the types of labels.
The present specification also provides a computer readable storage medium storing a computer program operable to perform the method of event number prediction provided in fig. 1 above.
The present specification also provides a schematic structural diagram of the electronic device shown in fig. 4. At the hardware level, the event number prediction device includes a processor, an internal bus, a network interface, a memory, and a nonvolatile memory, as described in fig. 4, and may include hardware required by other services. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs to implement the method of event number prediction described above with respect to fig. 1. Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.
In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.
The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.
The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.
The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of event number prediction, the method comprising:
acquiring a specific event which occurs historically;
obtaining each occurrence frequency sequence of the specific event according to the occurrence frequency of the specific event, the occurrence time of the specific event and the attribute of the specific event;
determining the correlation between the occurrence sequences;
according to the correlation, fusing the occurrence frequency sequences to obtain a fused sequence;
the fusion sequence is input into a pre-trained predictive model to predict the number of occurrences of the particular event within a future period of time from the predictive model.
2. The method of claim 1, wherein the attributes of the specific event specifically comprise: the region in which the specific event occurs and/or the type of the specific event.
3. The method according to claim 1, wherein obtaining the sequence of occurrence times of the specific event according to the occurrence times of the specific event, the occurrence times of the specific event and the attribute of the specific event specifically comprises:
for each specific event of the attribute, determining the occurrence sequence of the specific event of the attribute according to the occurrence times of the specific event of the attribute and the occurrence times of the specific event of the attribute.
4. The method according to claim 1, wherein the step of fusing the sequences of occurrence times based on the correlation to obtain a fused sequence specifically comprises:
and combining the occurrence frequency sequences to obtain a fusion sequence, wherein the position distance of each occurrence frequency sequence with higher correlation in the fusion sequence is closer.
5. The method of claim 1, wherein the sequence of occurrence times is fused to obtain a fused sequence, and the method specifically comprises:
for each occurrence sequence, obtaining a correlation score of the occurrence sequence according to the sum of correlation values of the occurrence sequences and all occurrence sequences except the occurrence sequence;
and combining the occurrence frequency sequences into a fusion sequence according to the correlation scores, wherein the correlation scores of the occurrence frequency sequences which are closer to the edge position in the fusion sequence are lower.
6. The method of claim 1, wherein pre-training the predictive model specifically comprises:
determining standard occurrence times and sample events, wherein the standard occurrence times are the occurrence times of specific events in a specified time period, and the sample events are the specific events occurring in each time period before the specified time period;
obtaining sample sequences of the occurrence times of the sample events according to the occurrence times of the sample events, the occurrence times of the sample events and the attributes of the sample events;
determining sample correlation between sample sequences of occurrence times;
fusing the sample sequences of the occurrence times according to the sample correlation to obtain a fused sample sequence;
inputting the fusion sample sequence into a prediction model to obtain the predicted occurrence times of specific events in a specified period;
the predictive model is trained with the aim of minimizing the difference between the number of occurrences of a particular event within the predicted specified period of time and the number of occurrences of the criterion.
7. The method of claim 2, wherein the method further comprises:
acquiring each description text corresponding to each occurrence of a specific event;
inputting each description text into a semantic analysis model, and carrying out cluster analysis on each description text to obtain a plurality of types of labels;
a number of types of the particular event are determined from the type tag.
8. An event number prediction apparatus, comprising:
the acquisition module acquires specific events occurring historically;
the extraction module is used for obtaining each occurrence frequency sequence of the specific event according to the occurrence frequency of the specific event, the occurrence time of the specific event and the attribute of the specific event;
the computing module is used for determining the correlation among the occurrence frequency sequences;
the fusion module fuses the occurrence frequency sequences according to the correlation to obtain a fusion sequence;
a prediction module inputs the fusion sequence into a pre-trained prediction model to predict the number of occurrences of the particular event within a future period of time from the prediction model.
9. A computer readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-7.
10. An apparatus comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of the preceding claims 1-7 when the program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281161.6A CN117875522A (en) | 2024-03-12 | 2024-03-12 | Method, device, storage medium and equipment for predicting event number |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410281161.6A CN117875522A (en) | 2024-03-12 | 2024-03-12 | Method, device, storage medium and equipment for predicting event number |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117875522A true CN117875522A (en) | 2024-04-12 |
Family
ID=90595365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410281161.6A Pending CN117875522A (en) | 2024-03-12 | 2024-03-12 | Method, device, storage medium and equipment for predicting event number |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117875522A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| CN111914569A (en) * | 2020-08-10 | 2020-11-10 | 哈尔滨安天科技集团股份有限公司 | Prediction method and device based on fusion map, electronic equipment and storage medium |
| CN113672823A (en) * | 2021-08-09 | 2021-11-19 | 北京三快在线科技有限公司 | User native place prediction method and device |
| CN114559951A (en) * | 2022-03-16 | 2022-05-31 | 北京三快在线科技有限公司 | Obstacle trajectory prediction method, obstacle trajectory prediction device, storage medium, and electronic device |
| CN116450814A (en) * | 2022-01-04 | 2023-07-18 | 腾讯科技（深圳）有限公司 | Event processing method, device, equipment and medium based on event processing model |
| US20230259959A1 (en) * | 2021-08-09 | 2023-08-17 | Tencent Technology (Shenzhen) Company Limited | Multi-target prediction method and apparatus, device, storage medium and program product |
| CN116701880A (en) * | 2023-07-18 | 2023-09-05 | 宏景科技股份有限公司 | Time sequence data prediction method, system, equipment and medium |
| CN116822995A (en) * | 2023-07-07 | 2023-09-29 | 京东科技信息技术有限公司 | Event occurrence number prediction method and device |
| CN117012380A (en) * | 2022-09-20 | 2023-11-07 | 腾讯科技（深圳）有限公司 | Event estimation method, device, equipment, storage medium and program product |
| CN117390585A (en) * | 2023-12-12 | 2024-01-12 | 之江实验室 | Time sequence data prediction method and model training method based on three-dimensional full-connection fusion |
-
2024
- 2024-03-12 CN CN202410281161.6A patent/CN117875522A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019174395A1 (en) * | 2018-03-13 | 2019-09-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for information recommendation, and device |
| CN111914569A (en) * | 2020-08-10 | 2020-11-10 | 哈尔滨安天科技集团股份有限公司 | Prediction method and device based on fusion map, electronic equipment and storage medium |
| CN113672823A (en) * | 2021-08-09 | 2021-11-19 | 北京三快在线科技有限公司 | User native place prediction method and device |
| US20230259959A1 (en) * | 2021-08-09 | 2023-08-17 | Tencent Technology (Shenzhen) Company Limited | Multi-target prediction method and apparatus, device, storage medium and program product |
| CN116450814A (en) * | 2022-01-04 | 2023-07-18 | 腾讯科技（深圳）有限公司 | Event processing method, device, equipment and medium based on event processing model |
| CN114559951A (en) * | 2022-03-16 | 2022-05-31 | 北京三快在线科技有限公司 | Obstacle trajectory prediction method, obstacle trajectory prediction device, storage medium, and electronic device |
| CN117012380A (en) * | 2022-09-20 | 2023-11-07 | 腾讯科技（深圳）有限公司 | Event estimation method, device, equipment, storage medium and program product |
| CN116822995A (en) * | 2023-07-07 | 2023-09-29 | 京东科技信息技术有限公司 | Event occurrence number prediction method and device |
| CN116701880A (en) * | 2023-07-18 | 2023-09-05 | 宏景科技股份有限公司 | Time sequence data prediction method, system, equipment and medium |
| CN117390585A (en) * | 2023-12-12 | 2024-01-12 | 之江实验室 | Time sequence data prediction method and model training method based on three-dimensional full-connection fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110245047B (en) | Time sequence abnormality detection method, device and equipment | |
| CN110163417B (en) | Traffic prediction method, device and equipment | |
| CN110457578B (en) | Customer service demand identification method and device | |
| CN112417093B (en) | Model training method and device | |
| CN113641896A (en) | Model training and recommendation probability prediction method and device | |
| CN115618964B (en) | Model training method and device, storage medium and electronic equipment | |
| CN110909775A (en) | Data processing method and device and electronic equipment | |
| CN110516915B (en) | Service node training and evaluating method and device and electronic equipment | |
| CN116757278B (en) | Training method and device of prediction model, storage medium and electronic equipment | |
| CN116186330B (en) | Video deduplication method and device based on multi-mode learning | |
| CN117875522A (en) | Method, device, storage medium and equipment for predicting event number | |
| CN111242195B (en) | Model, insurance wind control model training method and device and electronic equipment | |
| CN110163259B (en) | Method, system and equipment for generating sample data | |
| CN111461352B (en) | Model training method, service node identification device and electronic equipment | |
| CN117520627B (en) | Project retrieval data processing method and device | |
| CN115862675B (en) | Emotion recognition method, device, equipment and storage medium | |
| CN117494068B (en) | Network public opinion analysis method and device combining deep learning and causal inference | |
| CN117216327B (en) | Data analysis system based on visual data relationship | |
| CN116578877B (en) | Method and device for model training and risk identification of secondary optimization marking | |
| CN117593003A (en) | Model training method and device, storage medium and electronic equipment | |
| CN116776114A (en) | Risk detection method and device, storage medium and electronic equipment | |
| CN116822606A (en) | Training method, device, equipment and storage medium of anomaly detection model | |
| CN116595969A (en) | Text generation method and device, storage medium and electronic equipment | |
| CN117951527A (en) | Model training method, entity identification device and electronic equipment | |
| CN117195871A (en) | Model training method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |