CN117672484A - Method for predicting fertility resource demand, terminal equipment and storage medium - Google Patents
Method for predicting fertility resource demand, terminal equipment and storage medium Download PDFInfo
- Publication number
- CN117672484A CN117672484A CN202311832819.XA CN202311832819A CN117672484A CN 117672484 A CN117672484 A CN 117672484A CN 202311832819 A CN202311832819 A CN 202311832819A CN 117672484 A CN117672484 A CN 117672484A
- Authority
- CN
- China
- Prior art keywords
- data
- fertility
- population
- model
- preset
- 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
- 230000035558 fertility Effects 0.000 title claims abstract description 210
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012417 linear regression Methods 0.000 claims abstract description 11
- 230000009193 crawling Effects 0.000 claims description 60
- 238000004458 analytical method Methods 0.000 claims description 43
- ZAKOWWREFLAJOT-ADUHFSDSSA-N [2,5,7,8-tetramethyl-2-[(4R,8R)-4,8,12-trimethyltridecyl]-3,4-dihydrochromen-6-yl] acetate Chemical group CC(=O)OC1=C(C)C(C)=C2OC(CCC[C@H](C)CCC[C@H](C)CCCC(C)C)(C)CCC2=C1C ZAKOWWREFLAJOT-ADUHFSDSSA-N 0.000 claims description 31
- 238000011985 exploratory data analysis Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000003058 natural language processing Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract 1
- 238000013507 mapping Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000846 Bartlett's test Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting fertility resource demands, terminal equipment and a storage medium, wherein the method for predicting fertility resource demands is used for processing different models according to the data characteristics of input data, respectively predicting population fertility numbers and population fertility structures in a preset time period, determining the linear relation between the historical population fertility resource numbers and the historical population fertility structures based on a linear regression model, and further determining the population fertility numbers in the preset time period and the fertility resource demand numbers corresponding to the population fertility structures according to the linear relation, so that the predicted fertility resource demand numbers are matched with the fertility resource demands corresponding to the population fertility numbers in the preset time period, and the technical effect of improving the fertility resource accuracy is achieved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method for predicting a fertility resource demand, a terminal device, and a storage medium.
Background
The fertility resource demand prediction refers to predicting the demand of matched resources related to population fertility, such as medical treatment, education, subsidy and the like, in a future period of time so as to plan and allocate resources in time according to the future change condition of population, thereby supporting normal operation and business development of society.
In the prediction scheme of related fertility resource requirements, fertility resource analysis and prediction are performed based on a traditional statistical method and an empirical rule, for example, the fertility condition is predicted and analyzed by counting the file establishment rate, wedding check times and wedding numbers of pregnant women, and the resource prediction is performed by combining related resource application conditions, such as newly-built hospital numbers of children and newly-increased learning digits. However, this approach relies on manually established rules and experience, and the relationship between resource application situation and fertility situation is uncertain, resulting in an inaccurate predicted number of fertility resource requirements.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The embodiment of the invention aims to solve the technical problem that the predicted demand quantity of the fertility resources is inaccurate by providing a prediction method, terminal equipment and a computer readable storage medium for the demand quantity of the fertility resources.
In order to achieve the above object, an embodiment of the present invention provides a method for predicting a demand for resources, where the method for predicting a demand for resources includes:
population data and population speaking data are obtained, the population data and the population speaking data are screened based on a first preset data label associated with a first model, the first data are obtained, the population data and the population speaking data are screened based on a second preset data label associated with a second model, and the second data are obtained;
Generating population fertility numbers of a preset time period by taking the first data as input data of the first model, and generating population fertility structures of a preset time period by taking the second data as input data of the second model;
determining a linear relationship of the number of historical population fertility resources to the number of historical population fertility and the historical population fertility structure based on a linear regression model;
and according to the linear relation, determining the population fertility amount and the fertility resource demand amount corresponding to the population fertility structure in the preset time period.
Optionally, before the step of generating the population fertility structure for a preset period of time by using the first data as input data of the first model, generating the population fertility number for a preset period of time, and using the second data as input data of the second model, the method includes:
performing exploratory analysis on the first data by adopting a preset exploratory analysis method to obtain a first analysis result, and performing exploratory analysis on the second data by adopting the preset exploratory analysis method to obtain a second analysis result;
determining a first candidate model according to the first analysis result and/or the number of the first preset data labels, and determining a second candidate model according to the second analysis result and/or the number of the second preset data labels;
Training each first candidate model, determining the first model according to the evaluation result of each first candidate model, training each second candidate model, and determining the second model according to the evaluation result of each second candidate model.
Optionally, the step of determining a first candidate model according to the first analysis result and/or the number of the first preset data labels, and determining a second candidate model according to the second analysis result and/or the number of the second preset data labels includes:
if the first analysis result shows that the first preset data labels have linear relations, deleting the preset data labels without the linear relations, and determining the first candidate model according to the number of the first preset data labels with the linear relations and/or the complexity of the linear relations;
if the second analysis result shows that the second preset data labels have a linear relation, deleting the preset data labels without the linear relation, and determining the second candidate model according to the number of the second preset data labels with the linear relation and/or the complexity of the linear relation.
Optionally, after the step of determining the population fertility number and the fertility resource demand number corresponding to the population fertility structure in the preset period according to the linear relationship, the method includes:
acquiring the number of the estimated newly-increased fertility resources in the preset time period;
and according to the difference value between the newly increased fertility resource quantity and the fertility resource demand quantity, matching decision suggestions of the fertility resource demand quantity corresponding to the difference value in a plan model library.
Optionally, after the step of matching the decision suggestion of the number of the fertility resources required corresponding to the difference in the plan model library according to the difference between the number of the newly added fertility resources and the number of the fertility resources required, the method includes:
when the current time is greater than or equal to the right endpoint time of the preset time period, acquiring the newly increased target fertility resource quantity in the preset time period;
and correcting the decision suggestion in the plan model library according to the target resource quantity and the suggested fertility resource quantity corresponding to the decision suggestion.
Optionally, after the step of obtaining the number of the new target fertility resources in the preset time period when the current time is greater than or equal to the right endpoint time of the preset time period, the method further includes:
Acquiring the actual population fertility number and the actual population fertility structure of the target population published in the preset time period;
adjusting model parameters of the first model based on the difference between the target population fertility amount and the population fertility amount, and adjusting model parameters of the second model based on the difference between the target population fertility structure and the population fertility structure.
Optionally, the step of obtaining the population data and the preprocessed population speaking data, screening the population data and the population speaking data based on a first preset data tag associated with a first model to obtain first data, and screening the population data and the population speaking data based on a second preset data tag associated with a second model to obtain second data includes:
inputting the first preset data label and the second preset data label into a pre-trained natural language processing model, generating data crawling parameters based on the natural language processing model, performing label matching on the received data label by the natural language processing model, and setting related labels successfully matched with the data label and the data label as the data crawling parameters;
Configuring a data crawling tool according to the data crawling parameters;
based on the configured data crawling tool, crawling the demographic data and the initial demographic data.
Optionally, after the step of crawling the demographic data and the initial demographic data based on the configured data crawling tool, the step of crawling includes:
acquiring a calculation formula associated with the initial population speech data and calculating variables of the calculation formula;
counting the calculated variable values corresponding to the calculated variables in the initial population speaking data;
and inputting the calculated variable value into the calculation formula to obtain the population speaking data.
In addition, in order to achieve the above object, the present invention further provides a terminal device, including: a memory, a processor and a prediction program of tocopheryl resource demand stored on said memory and executable on said processor, said prediction program of tocopheryl resource demand when executed by said processor implementing the steps of the method of predicting tocopheryl resource demand as described above.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a prediction program of a tocopheryl resource demand, which when executed by a processor, implements the steps of the method of predicting a tocopheryl resource demand as described above.
According to the method for predicting the fertility resource demand, the terminal equipment and the computer readable storage medium, different models are adopted for processing according to the data characteristics of input data, the population fertility number and the population fertility structure in a preset time period are respectively predicted, the linear relation between the historical population fertility number and the historical population fertility structure is based on a linear regression model, and the population fertility number and the population fertility demand number corresponding to the population fertility structure in the preset time period are determined according to the linear relation, so that the accuracy of the predicted fertility resource demand number is improved.
Drawings
FIG. 1 is a flow chart of a method for predicting demand for resources in a plant according to an embodiment of the present invention;
FIG. 2 is a flow chart of a second embodiment of a method for predicting demand for resources in a family of the present invention;
FIG. 3 is a flow chart of a third embodiment of a method for predicting demand for resources in fertility according to the present invention;
FIG. 4 is a flow chart of a fourth embodiment of a method for predicting demand for resources in fertility according to the present invention;
fig. 5 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the prediction scheme of related fertility resource requirements, fertility resource analysis and prediction are performed based on a traditional statistical method and an empirical rule, for example, the fertility condition is predicted and analyzed by counting the file establishment rate, wedding check times and wedding numbers of pregnant women, and the resource prediction is performed by combining related resource application conditions, such as newly-built hospital numbers of children and newly-increased learning digits. However, this approach relies on manually established rules and experience, and the relationship between resource application situation and fertility situation is uncertain, resulting in an inaccurate predicted number of fertility resource requirements.
In order to solve the above-mentioned drawbacks of the related art, the present invention provides a method for predicting the demand of fertility resources, which mainly comprises the following steps:
according to the method, different models are adopted for processing according to the data characteristics of input data, population fertility numbers and population fertility structures in a preset time period are respectively predicted, based on a linear regression model, linear relations among the historical population fertility numbers, the historical population fertility numbers and the historical population fertility structures are determined according to the linear relations, and accuracy of the predicted population fertility numbers is improved.
In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Referring to fig. 1, in an embodiment of the method for predicting a demand for resources in fertility according to the present invention, the method for predicting a demand for resources in fertility includes the following steps:
step S10: population data and population speaking data are obtained, the population data and the population speaking data are screened based on a first preset data label associated with a first model, the first data are obtained, the population data and the population speaking data are screened based on a second preset data label associated with a second model, and the second data are obtained;
in this embodiment, population data refers to statistics and metrics related to population fertility for describing and analyzing population quantity, composition, structure, growth, etc. Demographic speech data refers to user behavior data related to population fertility and content in the form of text, video, audio and the like related to population fertility, which is spontaneously generated by a user on a containing platform, and is data for describing the user's desire to fertility and related problems. Such as the user's opinion and emotion of fertility and other related problems. The first preset data tag is input data required for identifying a predicted population fertility number. The second preset data tag is input data required for identifying a predicted population fertility structure.
Optionally, the first preset data tag includes a first sub-preset data tag of screening demographic data and a second sub-preset data tag of screening demographic-to-talk data. The second preset data label comprises a third sub-preset data label for screening population data and a fourth sub-preset data label for screening population speaking data in the same way.
Optionally, in order to obtain effective population data and improve accuracy of fertility resource prediction, the first sub-preset data label of the present invention includes, but is not limited to: birth rate, mortality, immigrating and educating population, education level, life span, medical cost, birth subsidy/month income ratio, urban population density, and dominant income. The second sub-preset data label includes, but is not limited to, a fertility intent. The third sub-preset data label includes, but is not limited to: family members, family member age distribution, birth rate, mortality, immigrating and educating population, education level, life span, medical cost per capita, birth subsidy per month income ratio, urban population density, and dominant income per capita. The fourth sub-preset data label includes, but is not limited to, a fertility intent.
It will be appreciated that the more demographic and demographic data that is collected, the more likely it is to be helpful to improve the accuracy of the model predictions. Therefore, the data amount of each preset data label may be set to satisfy the preset number, and the step S10 is performed only when the data amounts of the preset data labels satisfy the preset number. For example, a preset number of 20 bars may be set.
Step S20: generating population fertility numbers in a preset time period by taking the first data as input data of the first model, and generating population fertility structures in a preset time period by taking the second data as input data of the second model;
in this embodiment, the first model is used to generate a population fertility number for a preset time period, and the second model is used to generate a population fertility structure for the preset time period, so as to predict the fertility resource demand number for the preset time period subsequently. The preset time period refers to a time period in the future, and which time period in the future the preset time period corresponds to can be preset. For example, the preset time period may be preset to be the annual population fertility number between the next 2024 and 2034 years.
It is understood that the population fertility structure refers to the proportion of men and women and/or the proportion of ages corresponding to each third sub-preset data tab within the preset time period.
Alternatively, as an alternative embodiment, when there is a linear relationship between the data corresponding to the first preset data label, a multiple regression model may be used as the first model, and if there is no linear relationship, a bayesian algorithm may be used as the first model.
Alternatively, if the number of classifications of the second preset data label can be determined, a K-Means algorithm may be used as the second model, if a tree classification rule such as classification drill-down needs to be explored, a decision tree algorithm may be used as the second model, and other cases a K-NN algorithm may be used as the second model.
Step S30: determining a linear relationship of the number of historical population fertility resources to the number of historical population fertility and the historical population fertility structure based on a linear regression model;
in this embodiment, the present invention obtains the number of the historical population fertility resources and the number of the historical population fertility and the structure of the historical population fertility in the historical period, inputs the obtained number of the historical population fertility resources and the structure of the historical population fertility into a linear regression model, analyzes the linear relationship between the number of the historical population fertility resources and the number of the historical population fertility and the structure of the historical population fertility, and further obtains the linear relationship between the number of the population fertility resources and the number of the population fertility and the structure of the population fertility.
Optionally, the linear relation is as follows:
Y＝aX+bZ1+cZ2+......nZn
wherein Y is the number of fertility resource requirements; a, b, c. n is a constant; x is the number of birth control of people; z1, Z2...zn is a data tag value for each data tag corresponding to a human oral fertility structure.
Step S40: and according to the linear relation, determining the population fertility amount and the fertility resource demand amount corresponding to the population fertility structure in the preset time period.
In this embodiment, after obtaining the linear relation based on the linear regression model, the population fertility number and population fertility structure of the predicted preset time period are input into the linear relation, so as to obtain the fertility resource demand number of the preset time period. The linear relation is obtained by analyzing the linear relation between the number of the fertility resources of the historical population and the fertility structures of the historical population based on the linear regression model, so that the accuracy of the fertility resource demand number obtained based on the linear relation is improved.
According to the technical scheme provided by the embodiment, the population fertility amount and the population fertility structure in the preset time period are respectively predicted by adopting different models according to the data characteristics of the input data, the linear relation between the historical population fertility amount and the historical population fertility structure is based on the linear regression model, and the population fertility amount and the population fertility requirement amount corresponding to the population fertility structure in the preset time period are determined according to the linear relation, so that the accuracy of the predicted obtained fertility resource requirement amount is improved.
Referring to fig. 2, in the second embodiment, based on the first embodiment, before the step S20, it includes:
step S50: performing exploratory analysis on the first data by adopting a preset exploratory analysis method to obtain a first analysis result, and performing exploratory analysis on the second data by adopting the preset exploratory analysis method to obtain a second analysis result;
in this embodiment, exploratory analysis refers to a process of preliminary exploration and understanding of a data set in data analysis. Its main objective is to identify patterns, trends, outliers and potential relationships of data through visual and descriptive statistical methods, and to understand the associations and interactions between variables. The invention respectively performs exploratory analysis on the first data and the second data, and aims to explore the relation between variables, so that corresponding candidate models are selected according to analysis results.
Alternatively, a KMO (Kaiser-Meyer-Olkin, bartlet test) test and a Bartlett (Bartlett's test of sphericity, bartlet sphericity test) test may be set as the preset exploratory analysis method. And (3) calculating KMO values between each variable and other variables in the first data and the second data respectively, wherein if the KMO values are larger than 0.5, linear relations exist between the current variable and the other variables, further, a Bartlett check value of the variable with the linear relations is calculated by adopting Bartlett check, if the Bartlett check value is larger than a critical value, the variable with the linear relations is shown to have substantial linear relations, and if the Bartlett check value is smaller than the critical value, the variable with the linear relations is shown to have no substantial linear relation. The output analysis result is the result of whether the linear relation exists and/or the variable of the linear relation exists. Therefore, the first analysis result and the second analysis result are the identification of whether the linear relation exists between the preset data labels and/or the preset target data labels with the linear relation.
Step S60: determining a first candidate model according to the first analysis result, and determining a second candidate model according to the second analysis result;
in this embodiment, a candidate model is selected according to the analysis result, and a model actually used for prediction is determined in the candidate model, so as to improve accuracy of model prediction.
Optionally, if the first analysis result is that there is a linear relationship, mapping the corresponding first candidate model according to the output number of preset target data labels with the linear relationship, and if the first analysis result is that there is no linear relationship, directly mapping the corresponding first candidate model. Similarly, if the second analysis result is that the linear relationship exists, mapping the corresponding second candidate model according to the output number of the preset target data labels with the linear relationship, and if the second analysis result is that the linear relationship does not exist, directly mapping the corresponding second candidate model.
Optionally, as an alternative implementation manner, if the first analysis result is that a linear relationship exists in the first preset data label, deleting the preset data label without the linear relationship, mapping the corresponding first candidate model according to the number of preset target data labels with the linear relationship and/or the complexity of the linear relationship, if the second analysis result is that a linear relationship exists in the second preset data label, deleting the preset data label without the linear relationship, and mapping the corresponding second candidate model according to the number of preset target data labels with the linear relationship and/or the complexity of the linear relationship.
In this embodiment, the more preset target data labels having a linear relationship, the more complex the linear relationship is characterized. During training, only data with linear relation are input into the candidate model to predict, and the model actually used for prediction is determined according to the evaluation result of the candidate model.
Alternatively, as an alternative implementation manner, when the model performs actual prediction, only the data corresponding to the preset target data label with the linear relationship can be input into the model, and the data without the linear relationship can be input into the model, so that the accuracy of model prediction is improved.
Step S70: training each first candidate model, determining the first model according to the evaluation result of each first candidate model, training each second candidate model, and determining the second model according to the evaluation result of each second candidate model.
In this embodiment, the prediction results of the candidate models are evaluated by training each candidate model and calculating a preset evaluation index, so as to obtain the evaluation results. The evaluation index may be an accuracy rate, a recall rate, etc., which is not particularly limited in this embodiment. And determining the candidate model with the optimal evaluation result as the model for actually predicting, thereby improving the accuracy of prediction. It should be noted that the evaluation indexes of the candidate models should be consistent.
Alternatively, the candidate models may be trained and validated using cross-validation, grid search, etc., and the performance of each model on the evaluation index compared to select the optimal model.
In the technical scheme provided by the embodiment, a first analysis result is obtained by adopting a preset exploratory analysis method to perform exploratory analysis on first data, a second analysis result is obtained by adopting a preset exploratory analysis method to perform exploratory analysis on second data, then a first candidate model is determined according to the first analysis result, a second candidate model is determined according to the second analysis result, then each first candidate model is trained, and according to the evaluation result of each first candidate model, a first model is determined, each second candidate model is trained, and according to the evaluation result of each second candidate model, a second model is determined. And determining a model for actually predicting the candidate model with the optimal evaluation result, thereby improving the accuracy of prediction.
Referring to fig. 3, in a third embodiment, based on any of the above embodiments, before the step S10, the method includes:
step S80: inputting the first preset data label and the second preset data label into a pre-trained natural language processing model, generating data crawling parameters based on the natural language processing model, performing relevant label matching on the received data label by the natural language processing model, and setting relevant labels successfully matched with the data label and the data label as the data crawling parameters;
In this embodiment, the first preset data tag and the second preset data tag are input into the pre-trained natural language processing model, the pre-trained natural language processing model performs relevant tag matching on the received data tag, and the relevant tag successfully matched with the data tag and the data tag are set as data crawling parameters, so that comprehensive population data and initial population speaking data are obtained, and accuracy of fertility resource prediction is improved. The related tag includes not only a word similar to the data tag but also a variable word for calculating the data tag and a word similar to the variable word.
Optionally, as an alternative embodiment, after determining the relevant tag successfully matched with the data tag, the hierarchical relationship between the data tag and the relevant tag may be further determined, and then the data crawling depth of a web page is determined according to the hierarchical relationship.
In this embodiment, the hierarchical relationship may be determined from semantic differences between the data tag and all relevant tags. The higher the hierarchy of related tags with lower semantic differences to the data tags, the lower the hierarchy corresponding to related tags with greater semantic differences to the data tags. The higher the hierarchy is, the deeper the corresponding data crawling depth is, the lower the hierarchy is, the shallower the corresponding data crawling depth is, so that the matching degree of the crawled population data and the initial population speaking data with the preset data label is high, and the prediction accuracy is further improved.
For example, the hierarchical relationship between the data tag a and the relevant tag B, C, D is in a decreasing trend, so the data crawling depth of the data tag a is set to be 5, the data crawling depth of the relevant tag B is set to be 3, the data crawling depth of the relevant tag C is set to be 2, and the data crawling depth of the relevant tag D is set to be 1. When the data crawling tool crawls a webpage, if the crawling depth is 5, the crawling depth of the data corresponding to the data tag A is continuously performed on the webpage, and the next sub-link webpage entering the webpage is clicked until the crawling depth is 5, the crawling of the webpage is stopped, and the crawling of the next webpage is continuously performed.
Optionally, as an optional implementation manner, in order to avoid that the data crawling tool crawls too long in a web page and crawls too much useless data, the crawling depth of the web page may be redetermined according to the data crawling parameter corresponding to the data crawled by the current page each time when crawling the current page, which is not limited in this embodiment.
Step S90: configuring a data crawling tool according to the data crawling parameters;
step S100: based on the configured data crawling tool, crawling the demographic data and the initial demographic data.
In this embodiment, the data crawling tool crawls according to the configured data crawling parameters. And when the data amount crawled by each data crawling parameter is greater than or equal to the preset amount, ending the data crawling, and carrying out the prediction of the next step. For example, the preset number may be 20 bars.
Optionally, the time for the data crawling tool to crawl the web page can be set, so that the user reading behavior is simulated, and the situation that the data crawling tool is recognized and cannot continue crawling the web page is avoided.
The initial demographic data is decentralized and is an utterance describing the fertility intent of the individual user. Thus, prior to making the predictions, statistics need to be made on the initial demographic data to obtain demographic data that matches the pre-set data tag.
Optionally, after the step of crawling the population data and the initial population data based on the configured data crawling tool, a calculation formula associated with the initial population data and each calculation variable of the calculation formula may be obtained, and calculation variable values corresponding to the calculation variables are counted in the initial population data, so that the calculation variable values are input into the calculation formula to obtain the population data, and the step S10 is further performed.
In this embodiment, the calculation formula for the initial demographic data association includes, but is not limited to, a fertility intent. And calculating to obtain numerical values corresponding to the fertility willingness corresponding to different time periods, namely the human voice data, and then executing the step S10 to predict the population fertility amount and population fertility structure.
In the technical scheme provided by the embodiment, the first preset data tag and the second preset data tag are input into the pre-trained natural language processing model, the data crawling parameters are generated based on the natural language processing model, then the data crawling tool is configured according to the data crawling parameters, and enough population speaking data is crawled based on the configured data crawling tool, so that the accuracy rate of the fertility resource prediction is improved.
Referring to fig. 4, in a fourth embodiment, after step S40, based on any of the above embodiments, the method includes:
step S110: acquiring the number of the estimated newly-increased fertility resources in the preset time period;
step S120: and according to the difference value between the newly increased fertility resource quantity and the fertility resource demand quantity, matching decision suggestions of the fertility resource demand quantity corresponding to the difference value in a plan model library.
In this embodiment, a complete model library of plans is pre-built according to the population business scenario, so as to provide decision suggestions for relevant enterprises or departments. And obtaining and summarizing the predicted newly-increased fertility resource quantity in a preset time period, so as to calculate the difference value between the newly-increased fertility resource quantity and the predicted fertility resource demand quantity, and determining the decision suggestion of the fertility resource from a plan model library according to the difference value. The decision advice includes the number of tocopheryl resources established for each time period within a preset time period. It will be appreciated that the number of tocopheryl construction provided by the decision advice matches the number of population fertility in a predetermined time period, and that the relevant enterprises, departments or institutions can plan with reference to the number of tocopheryl construction output by the decision advice, thereby accommodating the growth of the number of population fertility and meeting the demand for tocopheryl in a future time period.
Optionally, as an optional implementation manner, when the difference is greater than a preset difference, the decision suggestion of the number of the fertility resource requirements corresponding to the difference is matched in the plan model library, and when the difference is less than the preset difference, the decision suggestion is not required to be given. It will be appreciated that the difference is less than the predetermined difference, which indicates that the estimated newly increased amount of tocopheryl resources has reached the tocopheryl resource demand required to meet the population's tocopheryl number over the future time period, without causing a shortage of tocopheryl resources.
Optionally, as an optional implementation manner, after the step of matching, in a plan model library, the decision suggestion of the number of resources required by the new number of resources, the step of matching, in the plan model library, the number of resources required by the new number of resources comprises: when the current time is greater than or equal to the right endpoint time of the preset time period, the newly increased target fertility resource quantity in the preset time period is obtained, and then the decision advice in the plan model library is corrected according to the target resource quantity and the advice fertility resource quantity corresponding to the decision advice, so that the feasibility of the plan model library is gradually improved, the accuracy of the subsequently outputted decision advice is improved, and the contribution is made to social development.
Optionally, as an optional implementation manner, after the step of obtaining the number of the new target fertility resources in the preset time period when the current time is greater than or equal to the right endpoint time of the preset time period, the method further includes: the method comprises the steps of obtaining the actual population fertility amount and the actual population fertility structure of a target population, according to the difference between the population fertility amount and the population fertility amount, adjusting model parameters of a first model, and according to the difference between the population fertility structure and the population fertility structure, adjusting model parameters of a second model, so that the prediction accuracy of the first model and the second model is improved.
In the technical solution provided in this embodiment, after the population fertility number and the fertility resource demand number corresponding to the population fertility structure in the preset time period are determined according to the linear relationship, the new fertility resource number predicted in the preset time period is obtained, so that the decision suggestion of the fertility resource demand number corresponding to the difference is matched in the plan model library according to the difference between the new fertility resource number and the predicted fertility resource demand number, so as to facilitate planning and allocating resources in time according to future variation conditions of the population, and thus support normal operation and business development of society.
Referring to fig. 5, fig. 5 is a schematic diagram of a terminal structure of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 5, the terminal may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), a mouse, etc., and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the terminal structure shown in fig. 5 is not limiting of the terminal and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 5, an operating system, a network communication module, a user interface module, and a prediction program of the demand for resources for birth may be included in a memory 1005 as a computer storage medium.
In the terminal shown in fig. 5, the network interface 1004 is mainly used for connecting to a background server and performing data communication with the background server; the processor 1001 may be configured to call a prediction program of the tocopheryl resource demand stored in the memory 1005 and perform the following operations:
population data and population speaking data are obtained, the population data and the population speaking data are screened based on a first preset data label associated with a first model, the first data are obtained, the population data and the population speaking data are screened based on a second preset data label associated with a second model, and the second data are obtained;
generating population fertility numbers of a preset time period by taking the first data as input data of the first model, and generating population fertility structures of a preset time period by taking the second data as input data of the second model;
Determining a linear relationship of the number of historical population fertility resources to the number of historical population fertility and the historical population fertility structure based on a linear regression model;
and according to the linear relation, determining the population fertility amount and the fertility resource demand amount corresponding to the population fertility structure in the preset time period.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
performing exploratory analysis on the first data by adopting a preset exploratory analysis method to obtain a first analysis result, and performing exploratory analysis on the second data by adopting the preset exploratory analysis method to obtain a second analysis result;
determining a first candidate model according to the first analysis result and/or the number of the first preset data labels, and determining a second candidate model according to the second analysis result and/or the number of the second preset data labels;
training each first candidate model, determining the first model according to the evaluation result of each first candidate model, training each second candidate model, and determining the second model according to the evaluation result of each second candidate model.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
if the first analysis result shows that the first preset data labels have linear relations, deleting the preset data labels without the linear relations, and determining the first candidate model according to the number of the first preset data labels with the linear relations and/or the complexity of the linear relations;
if the second analysis result shows that the second preset data labels have a linear relation, deleting the preset data labels without the linear relation, and determining the second candidate model according to the number of the second preset data labels with the linear relation and/or the complexity of the linear relation.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
acquiring the number of the estimated newly-increased fertility resources in the preset time period;
and according to the difference value between the newly increased fertility resource quantity and the fertility resource demand quantity, matching decision suggestions of the fertility resource demand quantity corresponding to the difference value in a plan model library.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
when the current time is greater than or equal to the right endpoint time of the preset time period, acquiring the newly increased target fertility resource quantity in the preset time period;
and correcting the decision suggestion in the plan model library according to the target resource quantity and the suggested fertility resource quantity corresponding to the decision suggestion.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
acquiring the actual population fertility number and the actual population fertility structure of the target population published in the preset time period;
adjusting model parameters of the first model based on the difference between the target population fertility amount and the population fertility amount, and adjusting model parameters of the second model based on the difference between the target population fertility structure and the population fertility structure.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
inputting the first preset data label and the second preset data label into a pre-trained natural language processing model, generating data crawling parameters based on the natural language processing model, performing label matching on the received data label by the natural language processing model, and setting related labels successfully matched with the data label and the data label as the data crawling parameters;
Configuring a data crawling tool according to the data crawling parameters;
based on the configured data crawling tool, crawling the demographic data and the initial demographic data.
Further, the processor 1001 may call a prediction program of the tocopheryl resource demand stored in the memory 1005, and further perform the following operations:
acquiring a calculation formula associated with the initial population speech data and calculating variables of the calculation formula;
counting the calculated variable values corresponding to the calculated variables in the initial population speaking data;
and inputting the calculated variable value into the calculation formula to obtain the population speaking data.
In addition, in order to achieve the above object, the present invention further provides a terminal device, including: a memory, a processor and a prediction program of tocopheryl resource demand stored on said memory and executable on said processor, said prediction program of tocopheryl resource demand when executed by said processor implementing the steps of the method of predicting tocopheryl resource demand as described above.
In addition, in order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a prediction program of a tocopheryl resource demand, which when executed by a processor, implements the steps of the method of predicting a tocopheryl resource demand as described above.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system 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 system. 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 system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising instructions for causing a terminal device (which may be a mobile phone, a computer) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A method for predicting the demand for a tocopheryl resource, the method comprising:
population data and population speaking data are obtained, the population data and the population speaking data are screened based on a first preset data label associated with a first model, the first data are obtained, the population data and the population speaking data are screened based on a second preset data label associated with a second model, and the second data are obtained;
generating population fertility numbers of a preset time period by taking the first data as input data of the first model, and generating population fertility structures of a preset time period by taking the second data as input data of the second model;
determining a linear relationship of the number of historical population fertility resources to the number of historical population fertility and the historical population fertility structure based on a linear regression model;
And according to the linear relation, determining the population fertility amount and the fertility resource demand amount corresponding to the population fertility structure in the preset time period.
2. The method of claim 1, wherein the step of generating the population fertility status for a predetermined period using the first data as input data for the first model, and generating the population fertility status for a predetermined period using the second data as input data for the second model, comprises, prior to the step of:
performing exploratory analysis on the first data by adopting a preset exploratory analysis method to obtain a first analysis result, and performing exploratory analysis on the second data by adopting the preset exploratory analysis method to obtain a second analysis result;
determining a first candidate model according to the first analysis result and/or the number of the first preset data labels, and determining a second candidate model according to the second analysis result and/or the number of the second preset data labels;
training each first candidate model, determining the first model according to the evaluation result of each first candidate model, training each second candidate model, and determining the second model according to the evaluation result of each second candidate model.
3. The method according to claim 2, wherein the step of determining a first candidate model from the first analysis result and/or the number of first preset data labels and determining a second candidate model from the second analysis result and/or the number of second preset data labels comprises:
if the first analysis result shows that the first preset data labels have linear relations, deleting the preset data labels without the linear relations, and determining the first candidate model according to the number of the first preset data labels with the linear relations and/or the complexity of the linear relations;
if the second analysis result shows that the second preset data labels have a linear relation, deleting the preset data labels without the linear relation, and determining the second candidate model according to the number of the second preset data labels with the linear relation and/or the complexity of the linear relation.
4. The method of claim 1, wherein said step of determining said population fertility number and said population fertility structure corresponding fertility resource requirement number within said predetermined time period based on said linear relationship comprises, after said step of:
Acquiring the number of the estimated newly-increased fertility resources in the preset time period;
and according to the difference value between the newly increased fertility resource quantity and the fertility resource demand quantity, matching decision suggestions of the fertility resource demand quantity corresponding to the difference value in a plan model library.
5. The method of claim 4, wherein said step of matching decision suggestions of said number of tocopheryl needs corresponding to said differences in a plan model library based on differences in said number of newly added tocopheryl resources and said number of tocopheryl needs comprises:
when the current time is greater than or equal to the right endpoint time of the preset time period, acquiring the newly increased target fertility resource quantity in the preset time period;
and correcting the decision suggestion in the plan model library according to the target resource quantity and the suggested fertility resource quantity corresponding to the decision suggestion.
6. The method of claim 5, wherein after the step of obtaining the number of the new target tocopheryl resources in the preset time period when the current time is greater than or equal to the right endpoint time of the preset time period, further comprising:
acquiring the actual population fertility number and the actual population fertility structure of the target population published in the preset time period;
Adjusting model parameters of the first model based on the difference between the target population fertility amount and the population fertility amount, and adjusting model parameters of the second model based on the difference between the target population fertility structure and the population fertility structure.
7. The method of claim 1, wherein the steps of obtaining demographic data and pre-processed demographic data, and screening the demographic data and the demographic data based on a first pre-set data tag associated with a first model to obtain first data, and screening the demographic data and the demographic data based on a second pre-set data tag associated with a second model to obtain second data, comprise, prior to the step of:
inputting the first preset data label and the second preset data label into a pre-trained natural language processing model, generating data crawling parameters based on the natural language processing model, performing label matching on the received data label by the natural language processing model, and setting related labels successfully matched with the data label and the data label as the data crawling parameters;
configuring a data crawling tool according to the data crawling parameters;
Based on the configured data crawling tool, crawling the demographic data and the initial demographic data.
8. The method of claim 7, wherein the step of crawling the demographic data and the initial demographic data based on the configured data crawling tool comprises:
acquiring a calculation formula associated with the initial population speech data and calculating variables of the calculation formula;
counting the calculated variable values corresponding to the calculated variables in the initial population speaking data;
and inputting the calculated variable value into the calculation formula to obtain the population speaking data.
9. A terminal device, characterized in that the terminal device comprises: memory, a processor and a resource demand prediction program of a terminal device stored on the memory and executable on the processor, which when executed by the processor, implements the steps of the method for predicting fertility resource demands according to any one of claims 1 to 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a resource demand prediction program of a terminal device, which when executed by a processor, implements the steps of the method for predicting fertility resource demand according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311832819.XA CN117672484A (en) | 2023-12-27 | 2023-12-27 | Method for predicting fertility resource demand, terminal equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311832819.XA CN117672484A (en) | 2023-12-27 | 2023-12-27 | Method for predicting fertility resource demand, terminal equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117672484A true CN117672484A (en) | 2024-03-08 |
Family
ID=90071450
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311832819.XA Pending CN117672484A (en) | 2023-12-27 | 2023-12-27 | Method for predicting fertility resource demand, terminal equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117672484A (en) |
-
2023
- 2023-12-27 CN CN202311832819.XA patent/CN117672484A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11810671B2 (en) | System and method for providing health information | |
| US20230297890A1 (en) | Customizable machine learning models | |
| US11561986B1 (en) | Applied artificial intelligence technology for narrative generation using an invocable analysis service | |
| US9268766B2 (en) | Phrase-based data classification system | |
| WO2021093821A1 (en) | Intelligent assistant evaluation and recommendation methods, system, terminal, and readable storage medium | |
| Johnson et al. | Multilevel learning in the adaptive management of waterfowl harvests: 20 years and counting | |
| US20190155894A1 (en) | Automated form generation system | |
| US20210200948A1 (en) | Corpus cleaning method and corpus entry system | |
| US20220044148A1 (en) | Adapting prediction models | |
| CN111506723B (en) | Question-answer response method, device, equipment and storage medium | |
| CA2833779A1 (en) | Predictive modeling | |
| US20200279182A1 (en) | Method and system for automatically producing plain-text explanation of machine learning models | |
| US20170046748A1 (en) | Method and system for personifying a brand | |
| CN111160959B (en) | User click conversion prediction method and device | |
| CN110990627A (en) | Knowledge graph construction method and device, electronic equipment and medium | |
| CN111179055B (en) | Credit line adjusting method and device and electronic equipment | |
| US11921568B2 (en) | Methods and systems for determining stopping point | |
| CN117672484A (en) | Method for predicting fertility resource demand, terminal equipment and storage medium | |
| Langan et al. | Benchmarking factor selection and sensitivity: a case study with nursing courses | |
| Mansingh et al. | Exploring the antecedents of the quality of life of patients with sickle cell disease: using a knowledge discovery and data mining process model-based framework | |
| KR20220006580A (en) | Visit Prediction | |
| CN116453702B (en) | Data processing method, device, system and medium for autism behavior feature set | |
| Wong et al. | A new test for tail index with application to Danish fire loss data | |
| US20240118867A1 (en) | Method for digital twin based data merging | |
| CN116451787B (en) | Content risk identification method, device, system and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |