CN117875737A

CN117875737A - Resource prediction method, apparatus, device, storage medium, and program product

Info

Publication number: CN117875737A
Application number: CN202311795878.4A
Authority: CN
Inventors: 骆想波; 徐辰; 刘鸿俊; 黄千双
Original assignee: China Southern Power Grid Digital Platform Technology Guangdong Co ltd
Current assignee: China Southern Power Grid Digital Platform Technology Guangdong Co ltd
Priority date: 2023-12-25
Filing date: 2023-12-25
Publication date: 2024-04-12

Abstract

The present application relates to a resource prediction method, apparatus, device, storage medium, and program product. The method comprises the following steps: acquiring historical service execution information of a target service, wherein the historical service execution information is used for indicating a historical progress state of the target service; according to the historical service execution information, predicting the progress state of the target service in a future target statistical period to obtain prediction execution information; and determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service. By adopting the method, the accuracy of resource prediction can be improved.

Description

Resource prediction method, apparatus, device, storage medium, and program product

Technical Field

The present invention relates to the field of big data technologies, and in particular, to a resource prediction method, apparatus, device, storage medium, and program product.

Background

In the actual business development process of the power grid company, business resource prediction is a key business activity, and aims to evaluate potential returns and risks of internal business of the company. Business resource prediction refers to the process of estimating and analyzing the expected resources of the business inside the company by using various methods and tools, and the company can better know the feasibility of the business through resource prediction, so as to make a key decision.

In the related art, resource prediction of a service often depends on a planning manager, and the planning manager makes a prediction scheme and predicts the service resource condition in a future period of time.

However, the above-described technique has a problem in that resource prediction is inaccurate.

Disclosure of Invention

In view of the foregoing, it is desirable to provide a resource prediction method, apparatus, device, storage medium, and program product that can improve the accuracy of resource prediction.

In a first aspect, the present application provides a resource prediction method, including:

acquiring historical service execution information of a target service, wherein the historical service execution information is used for indicating a historical progress state of the target service;

predicting the progress state of the target business in a future target statistical period according to the historical business execution information to obtain prediction execution information;

and determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service.

In one embodiment, the predicting the progress status of the target service in the future target statistics period according to the historical service execution information to obtain the predicted execution information includes:

Acquiring a service type of a target service, wherein the service type is used for indicating whether the duration between the initial service execution time and the current time of the target service exceeds the duration of a statistical period;

and determining a target prediction algorithm according to the service type, and predicting the progress state of the target service in the target statistical period by utilizing the historical service execution information according to the target prediction algorithm to obtain prediction execution information.

In one embodiment, the determining a target prediction algorithm according to the service type, and predicting, according to the target prediction algorithm, a progress state of the target service in a target statistics period by using historical service execution information to obtain prediction execution information includes:

if the service type is the first type, acquiring the service characteristics of the target service, and determining candidate services similar to the target service from a service database according to the service characteristics, wherein the candidate service is the service which has been executed, and the first type is the time length between the initial service execution time and the current time of the target service, wherein the time length does not exceed the time length of the statistical period;

determining the progress state of the target service in the current statistical period according to the progress state of the candidate service in the first statistical period and the historical service execution information of the target service, wherein the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service;

And determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress state of the candidate service in the second statistical period, so as to obtain prediction execution information, wherein the second statistical period is a statistical period corresponding to the target statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service.

In one embodiment, determining candidate services similar to the target service from the service database according to the service characteristics includes:

determining key business characteristics from the business characteristics;

screening at least one initial service consistent with the key service characteristics from the service database according to the key service characteristics;

acquiring service characteristics of each initial service, calculating the similarity between the service characteristics of each initial service and the service characteristics of the target service, and obtaining a similarity value corresponding to each initial service;

and obtaining the similarity value with the highest corresponding value in the similarity values, and taking the initial service corresponding to the similarity value with the highest value as a candidate service.

If the service type is the second type, determining the progress state of the target service in a plurality of historical statistic periods according to the historical service execution information, wherein the second type is the time length of the time length between the initial service execution time and the current time of the target service exceeding the statistic period;

determining the progress state of the target business in the current statistical period by utilizing a genetic algorithm and the progress states in a plurality of historical statistical periods;

and determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress states of the target service in a plurality of historical statistical periods to obtain prediction execution information.

In one embodiment, determining the predicted resource consumption information of the target service in the target statistics period according to the predicted execution information and the historical resource consumption information corresponding to the target service includes:

acquiring total resources pre-configured for a target service;

and calculating to obtain a first resource value according to the resource value corresponding to the total resource and the forecast execution information, and subtracting the historical resource consumption value indicated by the historical resource consumption information to obtain forecast resource consumption information.

In a second aspect, the present application further provides a resource prediction apparatus, where the apparatus includes:

The acquisition module is used for acquiring historical service execution information of the target service, wherein the historical service execution information is used for indicating a historical progress state of the target service;

the prediction module is used for predicting the progress state of the target business in a future target statistical period according to the historical business execution information to obtain prediction execution information;

and the determining module is used for determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service.

In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:

In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:

In a fifth aspect, the present application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:

According to the resource prediction method, the device, the equipment, the storage medium and the program product, the historical service execution information of the target service is obtained, the historical service execution information is used for indicating the historical progress state of the target service, the progress state of the target service in a future target statistical period is predicted according to the historical service execution information, the predicted execution information is obtained, and the predicted resource consumption information of the target service in the target statistical period is determined according to the predicted execution information and the historical resource consumption information corresponding to the target service. According to the method, the historical business execution information of the target business is obtained, the progress state of the target business in a future target statistical period is predicted according to the historical business execution information to obtain the predicted execution information, the historical business execution information of the target business can be fully utilized, accurate business execution information is provided for the progress state prediction processing of the target business, the prediction accuracy of the predicted execution information of the target business can be effectively improved, the predicted resource consumption information of the target business in the target statistical period is determined according to the predicted execution information and the historical resource consumption information corresponding to the target business, the accurate historical resource consumption information can be provided for the determination of the predicted resource consumption information through the historical resource consumption information, and the accuracy of the predicted execution information is higher.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the embodiments or the related technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to the drawings without inventive effort for a person having ordinary skill in the art.

FIG. 1 is an internal block diagram of a computer device in one embodiment;

FIG. 2 is a flow diagram of a method of resource prediction in one embodiment;

FIG. 3 is a schematic diagram of a target service in another embodiment;

FIG. 4 is a flowchart of a resource prediction method according to another embodiment;

FIG. 5 is a flowchart of a resource prediction method according to another embodiment;

FIG. 6 is a schematic diagram of basic information of a target service in another embodiment;

FIG. 7 is a flowchart of a resource prediction method according to another embodiment;

FIG. 8 is a flow chart of a method of resource prediction in another embodiment;

FIG. 9 is a schematic diagram of an alternative rule selection in another embodiment;

FIG. 10 is a diagram showing predicted outcome in another embodiment;

FIG. 11 is a block diagram of a resource prediction device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

However, the above-described technique has a problem in that resource prediction is inaccurate. Accordingly, embodiments of the present application provide a resource prediction method, apparatus, device, storage medium, and program product, which can solve the above technical problems.

The resource prediction method provided by the embodiment of the invention can be applied to computer equipment, wherein the computer equipment can be a terminal or a server, and the internal structure diagram of the computer equipment can be shown in fig. 1 by taking the terminal as an example. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a resource prediction method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.

It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a resource prediction method is provided, and this embodiment relates to a specific process of determining predicted resource consumption information of a target service, as shown in fig. 2, and taking application of the method to the computer device in fig. 1 as an example, the method may include the following steps:

s202, historical service execution information of the target service is obtained, wherein the historical service execution information is used for indicating a historical progress state of the target service.

The target service refers to a service or an item related to company construction, which may be a service or an item being executed, or may be a service or an item to be executed, as shown in fig. 3, and fig. 3 shows a plurality of items of a certain department, and each item may be used as a target service. The historical business execution information is the execution progress of the target business, and is used for indicating the historical progress state of the target business, wherein the historical progress state can refer to the execution progress of the business or the project.

In addition, the target service may be stored in the database, when the target service is stored in the database, the service name and the service code of the target service may be stored correspondingly, the history service execution information corresponding to the target service is also stored correspondingly in the database, and may be stored as a field in the database, and the history service execution information may be stored in a certain period or in a certain time node, which is not limited in this embodiment.

Optionally, the computer device may query the database for the target service, and obtain the historical service execution information of the target service according to the service name or service code of the target service.

S204, according to the historical service execution information, the progress state of the target service in a future target statistical period is predicted, and the predicted execution information is obtained.

The future target statistics period may be one year, two years, or other periods, which are not limited in this embodiment. In addition, the progress status in the future target statistics period refers to the progress status that the target business may execute or complete in a future period of time. The prediction processing refers to performing prediction processing on a progress state to obtain prediction execution information, where the prediction execution information is execution progress information possible in the future, or completion progress information.

Optionally, the progress state of the target service in the future target statistical period is predicted according to the historical service execution information, and the progress state of the target service in the future target statistical period is predicted according to the historical service execution information by adopting time ordering analysis, linear regression, decision tree and the like to obtain the predicted execution information.

S206, determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service.

The historical resource consumption information corresponding to the target service is a resource value which is consumed by the target service in the process of proceeding, the historical resource consumption information can be stored in a database together with the historical service execution information and is stored as a field in the database corresponding to the target service, the storage period of the historical resource consumption information can be the same as that of the historical service execution information, and the historical service execution information and the historical resource consumption information of the target service are stored in the same time node or time period.

Optionally, after the predicted execution information of the target service is obtained, a progress state of the target service in the target statistics period may be obtained, and the historical resource consumption information of the target service in a past period is correspondingly obtained, and by using intelligent optimization calculation, the predicted resource consumption information of the target service in the target statistics period is calculated by optimizing resource allocation and budget allocation, where the predicted resource consumption information is a resource value of the target service predicted to be consumed in the target statistics period, and may provide a company with a resource value that may be required to be consumed when the target service is executed in the target statistics period. The predicted resource consumption information may be presented through a display interface of the computer device.

In the resource prediction method, the historical service execution information of the target service is obtained, the historical service execution information is used for indicating the historical progress state of the target service, the progress state of the target service in a future target statistical period is predicted according to the historical service execution information, the predicted execution information is obtained, and then the predicted resource consumption information of the target service in the target statistical period is determined according to the predicted execution information and the historical resource consumption information corresponding to the target service. According to the method, the historical business execution information of the target business is obtained, the progress state of the target business in a future target statistical period is predicted according to the historical business execution information to obtain the predicted execution information, the historical business execution information of the target business can be fully utilized, accurate business execution information is provided for the progress state prediction processing of the target business, the prediction accuracy of the predicted execution information of the target business can be effectively improved, the predicted resource consumption information of the target business in the target statistical period is determined according to the predicted execution information and the historical resource consumption information corresponding to the target business, the accurate historical resource consumption information can be provided for the determination of the predicted resource consumption information through the historical resource consumption information, and the accuracy of the predicted execution information is higher.

The above-described embodiment refers to a case where the progress state of the target service in the future target statistical period can be predicted based on the history service execution information to obtain the predicted execution information, and the following embodiment describes an embodiment of how the predicted execution information is obtained specifically.

In another embodiment, another resource prediction method is provided, and based on the above embodiment, as shown in fig. 4, the step S204 may include the following steps:

s302, acquiring a service type of a target service, wherein the service type is used for indicating whether the duration between the initial service execution time and the current time of the target service exceeds the duration of a statistical period.

The service type of the target service is used for classifying and identifying the target service, the service type of the target service can be classified according to the execution time of the target service, and the service type is used for indicating whether the time length between the initial service execution time and the current time of the target service exceeds the time length of the statistical period. The initial service execution time of the target service is the time of service development or formal production, the time can be specific to the day, the current time is the time corresponding to the time when the service type of the target service is acquired, the time can be specific to the day, the duration between the initial service execution time and the current time of the target service can be the number of days between the date corresponding to the current time and the date corresponding to the initial service execution time. Correspondingly, the time unit of the statistical period needs to be consistent with the duration unit between the initial service execution time and the current time of the target service.

Optionally, the initial service execution time of the target service is stored in a database corresponding to the target service, and is stored in the database as a field in the database, the computer device obtains the initial service execution time of the target service according to the service name or service code of the target service, then calculates the time length between the initial service execution time and the current time, compares the calculated time length with the time length of the statistical period to obtain a comparison result, wherein the comparison result is that the time length between the initial service execution time and the current time is the time length which does not exceed the statistical period, or the time length between the initial service execution time and the current time is the time length which exceeds the statistical period, and the two comparison results correspond to the two service types, so that the service type of the target service can be obtained.

S304, determining a target prediction algorithm according to the service type, and predicting the progress state of the target service in the target statistical period by utilizing the historical service execution information according to the target prediction algorithm to obtain prediction execution information.

Optionally, the target prediction algorithm is configured to predict a progress state of the target service according to the service type, where different service types correspond to different prediction algorithms, and inputs corresponding to the different prediction algorithms are different, but outputs are all progress states of the target service in a target statistics period, and the prediction algorithm may be a predefined calculation algorithm, or may be a prediction model, or may also be other algorithms or models, and this embodiment is not limited specifically.

After the service type is determined, a target prediction algorithm is determined from different prediction algorithms according to the service type, and the progress state of the target service in a target statistical period is predicted by using historical service execution information by using the target prediction algorithm to obtain prediction execution information.

In this embodiment, a service type of a target service is obtained, where the service type is used to indicate whether a duration between an initial service execution time and a current time of the target service exceeds a duration of a statistical period, then a target prediction algorithm is determined according to the service type, and according to the target prediction algorithm, a progress state of the target service in the target statistical period is predicted by using historical service execution information, so as to obtain prediction execution information. By acquiring the service type of the target service and determining the target prediction algorithm according to the service type, the proper target prediction algorithm can be determined according to different service types, so that the progress state prediction processing of the target service in the target statistical period is more accurate, and the accuracy of the prediction execution information corresponding to the target service is improved.

The above embodiments refer to determining a target prediction algorithm according to a service type, and predicting a progress state of a target service in a target statistics period according to the target prediction algorithm by using historical service execution information to obtain prediction execution information, and the following embodiments describe a possible implementation manner of determining the target prediction algorithm according to the service type and predicting to obtain the prediction execution information.

In another embodiment, as shown in fig. 5, the step S304 may include the following steps:

s402, if the service type is the first type, acquiring the service characteristics of the target service, and determining candidate services similar to the target service from a service database according to the service characteristics, wherein the candidate service is the service which has been executed, and the first type is the time length between the initial service execution time and the current time of the target service, and the time length of the time length does not exceed the statistical period.

The first type is the duration that the duration between the initial service execution time and the current time of the target service does not exceed the duration of the statistical period, and the first type corresponds to the new service. In addition, the service characteristics of the target service refer to characteristics for describing information of the target service, the service characteristics may be a service name, a service code, a department where the service is located, and the like of the target service, and the service characteristics may be fields corresponding to the target service in the database.

Alternatively, the service database refers to a database storing the target service and other initial services, and may be a database storing all services of the whole department or the whole company. For the target service with the service type of the first type, the service database lacks initial service identical to the target service, candidate service similar to the target service is determined from the service database according to the service characteristics, as an alternative embodiment, key service characteristics are determined from the service characteristics, and at least one initial service consistent with the key service characteristics is screened from the service database according to the key service characteristics; acquiring service characteristics of each initial service, calculating the similarity between the service characteristics of each initial service and the service characteristics of the target service, and obtaining a similarity value corresponding to each initial service; and obtaining the similarity value with the highest corresponding value in the similarity values, and taking the initial service corresponding to the similarity value with the highest value as a candidate service.

The key service features are used to determine services having the same or similar key service features in the service database, and the key service features may be service names, service codes, or a combination of the service names and the service codes, which is not limited in this embodiment.

Alternatively, the key service feature may be determined from the service features, by extracting a keyword in the service name, and using one or more keywords as the key service feature, or may also directly use the service code as the service key feature, or may also use a combination of a code in a specific position in the service code and a keyword in the service name in any form, as the service key feature, which is not specifically limited in this embodiment.

After the key business characteristics are acquired, at least one initial business consistent with the key business characteristics is screened from a business database according to the key business characteristics, inquiry is carried out in business data according to the key business characteristics, and inquiry sentences are called to inquire from the database to acquire at least one initial business matched with the key business characteristics. And then, respectively acquiring service characteristics of each initial service in the acquired plurality of initial services, namely acquiring service names or service codes of the initial services, and calculating the similarity of the service characteristics of each initial service and the service characteristics of the target service, wherein optionally, the plurality of characteristics in the service characteristics can be respectively subjected to similarity calculation, the service characteristics can be expressed as word vectors, cosine similarity among the corresponding word vectors is calculated, and the cosine similarity among the plurality of word vectors is taken as a similarity value between each initial service and the target service characteristics, so that the similarity value corresponding to each initial service is obtained. And obtaining the similarity value with the largest value from the similarity values, and taking the initial service corresponding to the similarity value with the largest value as a candidate service.

S404, determining the progress state of the target service in the current statistical period according to the progress state of the candidate service in the first statistical period and the historical service execution information of the target service, wherein the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service.

The current statistical period is a duration from the current time to the starting time of the target statistical period, the current statistical period is less than one year, and the first statistical period is a statistical period corresponding to the duration of the current statistical period in the historical multiple statistical periods. The candidate service is an executed service, the execution period may be multiple periods, and when the candidate service stores the progress state in the database, the candidate service may be stored in a month or other units, so that the candidate service correspondingly stores the progress state of multiple statistical periods in the database. The progress state of the candidate service in the first statistical period may be obtained first, that is, the duration corresponding to the first statistical period, and according to the date corresponding to the current statistical period, the first statistical period with the same date (only including month/day) and duration as the current statistical period is obtained in the database, and further the progress state corresponding to the candidate service in the first statistical period may be obtained, where the first statistical period may be multiple, and each first statistical period may correspond to one progress state.

Optionally, according to the progress state of the candidate service in the first statistic period and the historical service execution information of the target service, determining the progress state of the target service in the current statistic period, counting the progress states in the first statistic periods, calculating the progress increment value of the starting time and the ending time of the first statistic period, subtracting the progress state of the starting time from the progress state of the ending time to obtain the progress increment value, and taking the average of the progress increment values in the first statistic periods to obtain the average progress increment value. And then, summing the corresponding progress state in the historical service execution information of the target service with the average progress increment value to obtain the progress state of the target service in the current statistical period. Optionally, after the progress status of the current statistical period is obtained, the service name, the service code, the historical service execution information and the progress status of the current statistical period of the target service are displayed on a visual interface of the computer device, as shown in fig. 6, the basic information of the target service is shown in fig. 6, and the basic information includes the service name, the service code, the historical service execution information and the progress status of the target service in the current statistical period.

S406, determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress state of the candidate service in the second statistical period, and obtaining the predicted execution information, wherein the second statistical period is a statistical period corresponding to the target statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service.

Optionally, the progress state of the candidate service in the second statistical period may be obtained, according to the date corresponding to the start time and the end time of the target statistical period and the duration of the target statistical period, the second statistical period corresponding to the date and the time length may be obtained, the progress state corresponding to the start time is subtracted from the progress state corresponding to the end time of the second statistical period to obtain a progress increase value in the second statistical period, similarly, the second statistical period may be multiple, the multiple second statistical periods correspond to the multiple progress increase values, the multiple progress increase values are averaged to obtain an average progress increase value in the second statistical period, the progress increase value identical to the duration of the second statistical period is determined according to the progress state and the historical service execution information of the current statistical period, the current progress increase value is recorded as the current progress increase value, the current progress increase value and the average progress increase value are weighted and averaged to obtain the progress increase value in the target statistical period, and the progress state of the target service in the target statistical period is obtained to obtain the prediction execution information.

In this embodiment, if the service type is a first type, the service characteristic of the target service is obtained, and a candidate service similar to the target service is determined from a service database according to the service characteristic, where the candidate service is an already executed service, the first type is a duration between an initial service execution time of the target service and a current time and not exceeding a statistical period, then, according to a progress state of the candidate service in the first statistical period and historical service execution information of the target service, a progress state of the target service in the current statistical period is determined, the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to an execution process of the candidate service, and then, according to the progress state of the current statistical period and the progress state of the candidate service in a second statistical period, a progress state of the target service in the target statistical period is determined, so as to obtain predicted execution information, and the second statistical period is a statistical period corresponding to the target statistical period of the target service in the plurality of statistical periods corresponding to the execution process of the candidate service. The method comprises the steps that for a target service with a first service type, corresponding candidate services are obtained through service characteristics of the target service, progress states in a first statistic period and a second statistic period can be obtained from similar candidate services, the progress states of the candidate services can provide references for the progress states of the target service, and accuracy of progress state prediction of the target service in the target statistic period can be improved.

Further, determining key business characteristics from business characteristics, screening at least one initial business consistent with the key business characteristics from a business database according to the key business characteristics, obtaining business characteristics of each initial business, calculating similarity between the business characteristics of each initial business and the business characteristics of a target business, obtaining a similarity value corresponding to each initial business, finally obtaining a similarity value with the highest corresponding value in the similarity values, and taking the initial business corresponding to the similarity value with the highest value as a candidate business. The candidate service with the highest similarity to the target service can be obtained by determining the candidate service with the highest similarity to the target service through the key service characteristics in the service characteristics, so that the progress state of the candidate service with the highest similarity can provide a reference for the progress state of the target service.

In the above embodiments, it is mentioned that the target prediction algorithm may be determined according to the service type, and the progress state of the target service in the target statistics period is predicted according to the target prediction algorithm by using the historical service execution information to obtain the prediction execution information, and the following embodiments describe another possible implementation manner how to determine the target prediction algorithm according to the service type and predict to obtain the prediction execution information.

In another embodiment, as shown in fig. 7, the step S304 may include the following steps:

s502, if the service type is the second type, determining the progress state of the target service in a plurality of historical statistic periods according to the historical service execution information, wherein the second type is the time length of the target service between the initial service execution time and the current time exceeding the statistic period.

The second type is the duration of the time period between the initial service execution time and the current time of the target service exceeding the statistical period, the second type corresponds to the renewing service, and the renewing service stores the historical service execution information in the database. And determining the progress state of the target service in a plurality of historical statistic periods according to the historical service execution information, and optionally, inquiring a plurality of historical services with the same corresponding service name or service code from the data according to the service name or service code of the target service, determining the statistic period from the plurality of historical services, and obtaining the progress state in the plurality of historical statistic periods.

S504, determining the progress state of the target business in the current statistical period by using a genetic algorithm and the progress states in a plurality of historical statistical periods.

Optionally, the genetic algorithm is a heuristic optimization method, and when a plurality of historical statistical periods are obtained, an optimal model or parameter combination can be found by using the genetic algorithm, so as to predict the progress state of the current statistical period according to the progress states in the plurality of historical statistical periods.

S506, determining the progress state of the target business in the target statistical period according to the progress state of the current statistical period and the progress states of the target business in a plurality of historical statistical periods, and obtaining the prediction execution information.

Optionally, according to the progress state of the current statistics period and the progress state of the target service in a plurality of historical statistics periods, determining a progress increment value in each historical statistics period according to the plurality of historical statistics periods, averaging the plurality of progress increment values to obtain an average progress increment value in the historical statistics period, determining the progress increment value which is the same as the duration of the historical statistics period according to the progress state of the current statistics period and the historical service execution information, marking the progress increment value as the current progress increment value, carrying out weighted average on the current progress increment value and the average progress increment value to obtain the progress increment value in the target statistics period, and further obtaining the progress state of the target service in the target statistics period to obtain the predicted execution information.

In this embodiment, if the service type is a second type, determining a progress state of the target service in a plurality of historical statistical periods according to the historical service execution information, where the second type is a time period in which a time period between an initial service execution time and a current time of the target service exceeds the statistical period, determining a progress state of the target service in the current statistical period by using a genetic algorithm and the progress states in the plurality of historical statistical periods, and then determining a progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress states of the target service in the plurality of historical statistical periods, so as to obtain the predicted execution information. The progress state of the current statistical period is determined by using a genetic algorithm according to the progress states of the plurality of historical statistical periods aiming at the target business with the business type of the second type, so that the progress state of the target business in the historical statistical period can be fully utilized, and the progress state of the current statistical period can be determined more accurately by using the genetic algorithm.

The above embodiment refers to determining the predicted resource consumption information of the target service in the target statistics period according to the predicted execution information and the historical resource consumption information corresponding to the target service, and the following embodiment describes one possible implementation of determining the predicted resource consumption information.

In another embodiment, as shown in fig. 8, another resource prediction method is provided, and the step S206 may include the following steps, based on the above embodiment:

s602, obtaining total resources pre-configured for a target service.

The total resources which are preconfigured by the target service are total resources which are required to be consumed by executing or completing the target service, the total resources are preconfigured when the target service is established, and the total resources are stored in a database corresponding to the target service as fields in the database. Optionally, the total resources preconfigured for the target service are obtained, and the resource value corresponding to the total resource field can be obtained by querying in the database according to the service name or service code of the target service.

S604, calculating to obtain a first resource value according to the resource value corresponding to the total resource and the forecast execution information, and subtracting the historical resource consumption value indicated by the historical resource consumption information to obtain forecast resource consumption information.

Optionally, multiplying the progress state of the target service included in the prediction execution information in the target statistics period by a resource value corresponding to the total resource to obtain a first resource value. In addition, the historical resource consumption value indicated by the historical resource consumption information is the resource consumption value in the current statistical period for the target service with the first type of service type, and is the sum of the corresponding resource consumption values of each statistical period in the historical statistical period and the resource consumption value in the current statistical period for the target service with the second type of service type. After the historical resource consumption value indicated by the historical resource consumption information is obtained, subtracting the historical resource consumption value from the first resource value to obtain a predicted resource consumption value in the target statistical period, and taking the predicted resource consumption value and the corresponding target statistical period as predicted resource consumption information.

Optionally, when calculating the predicted resource consumption information, the relevant input data of the predicted resource consumption information obtained by calculation may be selected according to a preset selection rule, as shown in fig. 9, one of the selection rules is shown in fig. 9, each selection rule corresponds to a code, the relevant input data is determined according to a field corresponding to the code, and finally the predicted resource consumption value is obtained by calculation according to the number-taking rule.

Optionally, after the predicted resource consumption value is obtained by calculation, the resource consumption value and the corresponding target statistical period may be displayed in a visual interface of the computer as predicted resource consumption information, in addition to this, the resource consumption value in the current statistical period may be displayed, and the resource consumption value in the historical statistical period may be displayed, as shown in fig. 10, and fig. 10 is a result display interface of the resource prediction method.

In this embodiment, a total resource pre-configured for the target service is obtained, a first resource value is calculated according to a resource value corresponding to the total resource and the predicted execution information, and a historical resource consumption value indicated by historical resource consumption information is subtracted to obtain predicted resource consumption information. The first resource value is obtained through calculation through the total resources and the predicted execution information, and the predicted resource consumption information is subtracted from the historical resource consumption value, so that the accuracy of the predicted execution information obtained through prediction is higher, and the accuracy of the predicted resource consumption information obtained through calculation is improved.

Based on the same inventive concept, the embodiment of the application also provides a resource prediction device for realizing the above-mentioned resource prediction method. The implementation of the solution provided by the apparatus is similar to the implementation described in the above method, so the specific limitation in the embodiments of one or more resource prediction apparatus provided below may be referred to the limitation of the resource prediction method hereinabove, and will not be repeated here.

In one embodiment, as shown in fig. 11, there is provided a resource prediction apparatus including: the system comprises an acquisition module, a prediction module and a determination module, wherein:

In another embodiment, another resource prediction apparatus is provided, where, on the basis of the foregoing embodiment, the prediction module includes an obtaining unit and a prediction unit, and the prediction unit includes:

The acquisition unit is used for acquiring the service type of the target service, wherein the service type is used for indicating whether the duration between the initial service execution time and the current time of the target service exceeds the duration of the statistical period;

the prediction unit is used for determining a target prediction algorithm according to the service type, and predicting the progress state of the target service in the target statistical period by utilizing the historical service execution information according to the target prediction algorithm to obtain prediction execution information.

Optionally, the prediction unit may include:

the query subunit is used for acquiring the service characteristics of the target service if the service type is the first type, and determining candidate services similar to the target service from the service database according to the service characteristics, wherein the candidate services are already executed, and the first type is the time length between the initial service execution time and the current time of the target service, and the time length of the time length does not exceed the statistical period;

the first determining subunit is configured to determine, according to a progress status of the candidate service in a first statistical period and historical service execution information of the target service, the progress status of the target service in a current statistical period, where the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to an execution process of the candidate service;

The first prediction subunit is configured to determine, according to a progress status of the current statistical period and a progress status of the candidate service in a second statistical period, a progress status of the target service in the target statistical period, to obtain prediction execution information, where the second statistical period is a statistical period corresponding to the target statistical period of the target service in a plurality of statistical periods corresponding to an execution process of the candidate service.

Optionally, the query subunit is specifically configured to: determining key business characteristics from the business characteristics; screening at least one initial service consistent with the key service characteristics from the service database according to the key service characteristics; acquiring service characteristics of each initial service, calculating the similarity between the service characteristics of each initial service and the service characteristics of the target service, and obtaining a similarity value corresponding to each initial service; and obtaining the similarity value with the highest corresponding value in the similarity values, and taking the initial service corresponding to the similarity value with the highest value as a candidate service.

Optionally, the prediction unit may further include:

a statistics subunit, configured to determine, according to the historical service execution information, a progress status of the target service in a plurality of historical statistics periods if the service type is a second type, where the second type is a duration of time between an initial service execution time and a current time of the target service that exceeds the statistics period;

The second determining subunit is used for determining the progress state of the target business in the current statistical period by utilizing a genetic algorithm and the progress states in a plurality of historical statistical periods;

and the second prediction subunit is used for determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress states of the target service in the plurality of historical statistical periods to obtain prediction execution information.

In another embodiment, another resource prediction apparatus is provided, where, on the basis of the above embodiment, the above determining module includes a resource obtaining unit and a calculating unit, where:

the resource acquisition unit is used for acquiring total resources pre-configured for the target service;

and the calculation unit is used for calculating to obtain a first resource value according to the resource value corresponding to the total resource and the forecast execution information, and subtracting the historical resource consumption value indicated by the historical resource consumption information to obtain forecast resource consumption information.

The respective modules in the above-described resource prediction apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:

acquiring historical service execution information of a target service, wherein the historical service execution information is used for indicating a historical progress state of the target service; predicting the progress state of the target business in a future target statistical period according to the historical business execution information to obtain prediction execution information; and determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service.

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring a service type of a target service, wherein the service type is used for indicating whether the duration between the initial service execution time and the current time of the target service exceeds the duration of a statistical period; and determining a target prediction algorithm according to the service type, and predicting the progress state of the target service in the target statistical period by utilizing the historical service execution information according to the target prediction algorithm to obtain prediction execution information.

if the service type is the first type, acquiring the service characteristics of the target service, and determining candidate services similar to the target service from a service database according to the service characteristics, wherein the candidate service is the service which has been executed, and the first type is the time length between the initial service execution time and the current time of the target service, wherein the time length does not exceed the time length of the statistical period; determining the progress state of the target service in the current statistical period according to the progress state of the candidate service in the first statistical period and the historical service execution information of the target service, wherein the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service; and determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress state of the candidate service in the second statistical period, so as to obtain prediction execution information, wherein the second statistical period is a statistical period corresponding to the target statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service.

determining key business characteristics from the business characteristics; screening at least one initial service consistent with the key service characteristics from the service database according to the key service characteristics; acquiring service characteristics of each initial service, calculating the similarity between the service characteristics of each initial service and the service characteristics of the target service, and obtaining a similarity value corresponding to each initial service; and obtaining the similarity value with the highest corresponding value in the similarity values, and taking the initial service corresponding to the similarity value with the highest value as a candidate service.

if the service type is the second type, determining the progress state of the target service in a plurality of historical statistic periods according to the historical service execution information, wherein the second type is the time length of the time length between the initial service execution time and the current time of the target service exceeding the statistic period; determining the progress state of the target business in the current statistical period by utilizing a genetic algorithm and the progress states in a plurality of historical statistical periods; and determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress states of the target service in a plurality of historical statistical periods to obtain prediction execution information.

acquiring total resources pre-configured for a target service; and calculating to obtain a first resource value according to the resource value corresponding to the total resource and the forecast execution information, and subtracting the historical resource consumption value indicated by the historical resource consumption information to obtain forecast resource consumption information.

In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

In one embodiment, the computer program when executed by the processor further performs the steps of:

In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:

It should be noted that, the data (including, but not limited to, data for analysis, data stored, data displayed, etc.) referred to in the present application are all data fully authorized by each party, and the collection, use, and processing of the relevant data are required to meet the relevant regulations.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims

1. A method of resource prediction, the method comprising:

according to the historical service execution information, predicting the progress state of the target service in a future target statistical period to obtain prediction execution information;

2. The method according to claim 1, wherein predicting the progress status of the target service in the future target statistics period according to the historical service execution information to obtain predicted execution information includes:

acquiring a service type of the target service, wherein the service type is used for indicating whether the duration between the initial service execution time and the current time of the target service exceeds the duration of a statistical period;

and determining a target prediction algorithm according to the service type, and predicting the progress state of the target service in the target statistical period by utilizing the historical service execution information according to the target prediction algorithm to obtain the prediction execution information.

3. The method according to claim 2, wherein determining a target prediction algorithm according to the service type, and predicting, according to the target prediction algorithm, a progress state of the target service in the target statistics period using the historical service execution information, to obtain the prediction execution information, includes:

If the service type is a first type, acquiring service characteristics of the target service, and determining candidate services similar to the target service from a service database according to the service characteristics, wherein the candidate services are already executed, and the first type is a time length between an initial service execution time and a current time of the target service, wherein the time length does not exceed a statistical period;

determining the progress state of the target service in a current statistical period according to the progress state of the candidate service in a first statistical period and the historical service execution information of the target service, wherein the first statistical period is a statistical period corresponding to the current statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service;

and determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress state of the candidate service in a second statistical period, so as to obtain the prediction execution information, wherein the second statistical period is a statistical period corresponding to the target statistical period of the target service in a plurality of statistical periods corresponding to the execution process of the candidate service.

4. A method according to claim 3, wherein said determining candidate services from a service database that are similar to said target service based on said service characteristics comprises:

determining key business features from the business features;

screening at least one initial service consistent with the key service features from the service database according to the key service features;

acquiring service characteristics of each initial service, calculating similarity between the service characteristics of each initial service and the service characteristics of the target service, and obtaining a similarity value corresponding to each initial service;

5. The method according to claim 2, wherein determining a target prediction algorithm according to the service type, and predicting, according to the target prediction algorithm, a progress state of the target service in the target statistics period using the historical service execution information, to obtain the prediction execution information, includes:

if the service type is a second type, determining the progress state of the target service in a plurality of historical statistic periods according to the historical service execution information, wherein the second type is the time length of the time length between the initial service execution time and the current time of the target service exceeding the statistic period;

Determining the progress state of the target business in the current statistical period by utilizing a genetic algorithm and the progress states in the historical statistical periods;

and determining the progress state of the target service in the target statistical period according to the progress state of the current statistical period and the progress states of the target service in a plurality of historical statistical periods, so as to obtain the prediction execution information.

6. The method according to claims 1 to 5, wherein determining the predicted resource consumption information of the target service in the target statistical period according to the predicted execution information and the historical resource consumption information corresponding to the target service includes:

acquiring total resources pre-configured for the target service;

and calculating to obtain a first resource value according to the resource value corresponding to the total resource and the forecast execution information, and subtracting the historical resource consumption value indicated by the historical resource consumption information to obtain the forecast resource consumption information.

7. A resource prediction apparatus, the apparatus comprising:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring historical service execution information of a target service, and the historical service execution information is used for indicating a historical progress state of the target service;

The prediction module is used for predicting the progress state of the target service in a future target statistical period according to the historical service execution information to obtain prediction execution information;

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.