CN117094571A - Regional development status monitoring index determination method and device and electronic equipment - Google Patents
Regional development status monitoring index determination method and device and electronic equipment Download PDFInfo
- Publication number
- CN117094571A CN117094571A CN202311000729.4A CN202311000729A CN117094571A CN 117094571 A CN117094571 A CN 117094571A CN 202311000729 A CN202311000729 A CN 202311000729A CN 117094571 A CN117094571 A CN 117094571A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- dimension
- determining
- monitored
- year
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 323
- 238000011161 development Methods 0.000 title claims abstract description 124
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000011156 evaluation Methods 0.000 claims abstract description 126
- 238000012163 sequencing technique Methods 0.000 claims abstract description 27
- 230000018109 developmental process Effects 0.000 claims description 117
- 230000011218 segmentation Effects 0.000 claims description 18
- 238000005259 measurement Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 abstract description 10
- 230000008878 coupling Effects 0.000 abstract description 6
- 238000010168 coupling process Methods 0.000 abstract description 6
- 238000005859 coupling reaction Methods 0.000 abstract description 6
- 238000004422 calculation algorithm Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000005065 mining Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 239000010410 layer Substances 0.000 description 3
- 238000011002 quantification Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013278 delphi method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000011524 similarity measure Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/3332—Query translation
- G06F16/3334—Selection or weighting of terms from queries, including natural language queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides a method and a device for determining a regional development condition monitoring index and electronic equipment, and relates to the technical field of computers, wherein the method comprises the following steps: acquiring an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range; determining dimension sorting weights corresponding to the areas to be monitored in each monitoring dimension every year based on each target text; and determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension of the area to be monitored every year. The dimension sorting weight is determined through text analysis, subjective judgment opinion of the importance of different monitoring dimensions of regional development is obtained, and then the development condition monitoring index of the region to be monitored is determined according to the evaluation value of each monitoring dimension and the coupling of the dimension sorting weight, so that the dynamic monitoring of the development condition of the region based on the subjective opinion of a high-level decision maker is realized with low cost and high efficiency, and the accuracy and the efficiency of the dynamic monitoring of the development condition of the region are improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and an apparatus for determining a regional development status monitoring index, and an electronic device.
Background
Under the background of the new era, the multi-element comprehensive development of the economic, social and ecological aspects of the propulsion area becomes a common consensus, the realization of the target has the progressive dynamic evolution characteristic, and the policy is relied on to be optimized and regulated in time. The basis and premise of developing scientific regional management policies is effective assessment of regional development status. In actual operation, an effective approach and a common means for regional development status assessment are to construct a multi-index regional development comprehensive evaluation system, and to construct a comprehensive index based on a large number of basic indexes for easy expression and comparison. When the comprehensive index of the regional development state is constructed based on an index system, weight determination is the most core step, and the indicating capability of the comprehensive index on the regional development state is directly affected.
In the related art, the weight determining method in the comprehensive index algorithm is mainly divided into subjective weight determination and objective weight determination. The objective weight determination method generally determines weights based on statistical characteristics such as data fluctuation, so that universality is strong, operation is simple and popular, common methods comprise an entropy weight method, a principal component analysis method and the like, and the objective weight determination method has the defects that weights can be changed along with data and are not reflected in 'objective' weights, so that disputes exist on the embodying capability of index importance. Subjective weight determination methods, such as the delta method and the analytic hierarchy method, have the advantages of reflecting the wish (or subjectivity) of a decision maker, ensuring that the weight does not change along with data, but have the disadvantage of being difficult to scientifically convert from the wish of the decision maker to the weight value. Meanwhile, the subjective right determination method often requires a decision maker to have clear and consistent quantitative cognition, if the collected subjective information does not meet the right determination requirement, the range is further expanded or the scheme is adjusted to be collected again, so that the subjective opinion collection cost of the decision maker is further high, the subjective opinion is difficult to be practically applied to determining the weight among dimensions, and the efficiency of monitoring the regional condition is low.
Disclosure of Invention
The invention provides a method, a device and electronic equipment for determining a regional development condition monitoring index, which are used for solving the problem that the efficiency of monitoring the regional development condition is low in practical application although a subjective validation method is more scientific and basic.
The invention provides a method for determining a regional development condition monitoring index, which comprises the following steps:
acquiring an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range;
determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts;
and determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
According to the method for determining the regional development status monitoring index provided by the invention, the determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension each year based on each target text comprises the following steps:
aiming at each target text, performing word segmentation processing on the target text to obtain at least one word segmentation corresponding to the target text;
Counting word frequencies corresponding to the word segmentation;
determining at least one keyword corresponding to each monitoring dimension respectively based on each word frequency;
and determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year based on each keyword corresponding to each monitoring dimension.
According to the method for determining the regional development status monitoring index provided by the invention, the determining of at least one keyword corresponding to each monitoring dimension based on each word frequency comprises the following steps:
determining at least one high-frequency word based on each word frequency;
based on the high-frequency words and the core words selected based on the names of the monitoring dimensions, respectively determining similarity measurement values between any high-frequency word and the core words;
and determining each keyword corresponding to each monitoring dimension respectively based on each similarity measurement value.
According to the method for determining the regional development status monitoring index provided by the invention, the determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension each year based on each keyword corresponding to each monitoring dimension respectively comprises the following steps:
determining normalized word frequencies corresponding to the keywords based on the word frequencies of the keywords corresponding to the monitoring dimensions respectively;
Determining word frequency mean values corresponding to the monitoring dimensions based on the normalized word frequencies corresponding to the keywords;
and sequencing word frequency means corresponding to the monitoring dimensions, and determining the dimension sequencing weight of the region to be monitored corresponding to the monitoring dimensions every year.
According to the method for determining the regional development condition monitoring index provided by the invention, the determining the development condition monitoring index of the region to be monitored based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the region to be monitored every year comprises the following steps:
and determining the development condition monitoring index of the area to be monitored by adopting a high-dimensional sequencing weight method based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
According to the method for determining the regional development condition monitoring index provided by the invention, the method for determining the regional development condition monitoring index by adopting a high-dimensional sequencing weight method based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the region to be monitored every year comprises the following steps:
determining an optimal value and a worst value corresponding to a weighted sum of the evaluation values of all the monitoring dimensions under the dimension sorting based on the evaluation values of all the monitoring dimensions and the dimension sorting weight corresponding to the area to be monitored every year;
And calculating an average value based on the optimal value and the worst value, and determining the development condition monitoring index of the area to be monitored.
According to the method for determining the regional development status monitoring index provided by the invention, the determination of the optimal value and the worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions is based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the region to be monitored every year, and the determination comprises the following steps:
calculating an average evaluation value of the evaluation values when the sorting weights corresponding to the monitoring dimensions take different weight values based on the evaluation values of the monitoring dimensions corresponding to the area to be monitored every year and the dimension sorting weights;
and determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the average evaluation values.
The invention also provides a device for determining the regional development condition monitoring index, which comprises the following steps:
the acquisition module is used for acquiring an evaluation value of the area to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range;
the first determining module is used for determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts;
And the second determining module is used for determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method for determining the regional development status monitoring index as described above when executing the program.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of determining a regional development status monitoring index as described in any of the above.
According to the method, the device and the electronic equipment for determining the regional development condition monitoring index, the evaluation value of the region to be monitored in at least one monitoring dimension and the corresponding target text in each year are obtained within the target time range; according to each target text, determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year; and determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year. The dimension sorting weight is determined through text analysis, so that subjective judgment opinion of the importance of different monitoring dimensions of regional development is obtained, and then according to the evaluation value of each monitoring dimension and the coupling of the dimension sorting weight, the accurate determination of the development condition monitoring index of the region to be monitored is realized, the dynamic monitoring of the development condition of the region based on the subjective opinion of a high-level decision maker is realized with low cost and high efficiency, and the accuracy and the efficiency of the dynamic monitoring of the development condition of the region are improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for determining regional development status monitoring index according to the present invention;
FIG. 2 is a schematic view of a text of a target corresponding to a region to be monitored in a target time range every year according to the present invention;
FIG. 3 is a schematic diagram of the dimension ranking weights provided by the invention for each monitored dimension of an area to be monitored each year;
FIG. 4 is a second flow chart of the method for determining regional development status monitoring index according to the present invention;
FIG. 5 is a schematic diagram of a device for determining regional development status monitoring index according to the present invention;
fig. 6 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
To facilitate a clearer understanding of various embodiments of the present application, a description of the relevant background is provided first.
The comprehensive index is a powerful tool for developing multi-index comprehensive evaluation, can fully integrate a multi-dimensional evaluation view angle, gives quantitative evaluation to the comprehensive state of a target object, and has been widely focused and applied for a long time. The comprehensive index construction generally comprises three steps of index data processing, weight (index or dimension importance) determination and index aggregation. The most basic form is to aggregate multi-index data by a method of calculating an arithmetic or geometric mean (equal weight) to obtain a comprehensive index. In order to improve the distinguishing and evaluating effects of the comprehensive index algorithm on different evaluation targets, a series of comprehensive index algorithms are developed mainly by performing a great deal of exploration and improvement along two main directions of a weight determining method and an aggregation method.
In order to improve the scientificity of the weight determining method, on one hand, a main component analysis method, an entropy weight method, an objective weighting method (Criteria Importance Though Intercriteria Correlation, CRITIC) based on interlayer correlation and other series of algorithms and improvements thereof are provided by analyzing quantization weights of statistical characteristics (data fluctuation, inter-index correlation and the like) of a data matrix; on the other hand, by introducing priori knowledge required by weight quantification and application conversion approaches of optimization knowledge, models such as a Delphi method, a analytic hierarchy process, a fuzzy comprehensive evaluation method and the like are developed, and models such as a neural network and the like are introduced under the development wave of machine learning, so that scientific determination of more approaching reliable evaluation results is realized. Based on the improvement of the aggregation method, a series of novel comprehensive index models are provided, such as Z indexes considering the unreliable degree of data, two-dimensional and three-dimensional geometric calculation models for improving the inter-dimension coupling quantification mode, and the like. Meanwhile, the fusion mutual authentication of the method is also an important direction of the improvement and development of the comprehensive index model, such as the fusion of a classical right determining method and a fuzzy evaluation method, the fusion of a subjective and objective right determining model and the like.
The regional development condition monitoring index determination method provided by the invention is suitable for the situation that large-scale expert interview investigation is inconvenient to develop, and only relevant policy text data is needed, judgment comments of a high-level decision maker group on the importance of each dimension of the regional development condition can be obtained and used for regional development condition monitoring. The method aims to introduce a text mining technology, so that subjective opinions of a large-scale and high-level decision-making group can be extracted based on text materials such as policy texts, the importance of each dimension of regional development is judged according to the subjective opinion, the performance of each dimension of regional development is aggregated based on the importance ranking of each dimension, and the comprehensive index of regional development condition monitoring is determined.
The regional development status monitoring index determination method of the present invention is described below with reference to fig. 1 to 4.
FIG. 1 is a schematic flow chart of a method for determining a regional development status monitoring index according to the present invention, as shown in FIG. 1, the method includes steps 101-103; wherein,
and step 101, acquiring an evaluation value of the area to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range.
It should be noted that, the method for determining the regional development status monitoring index provided by the present invention is suitable for a scenario of dynamic monitoring of the regional development status in the fields of regional development planning, policy making, decision support, etc., and the execution subject of the method may be a regional development status monitoring index determining device, for example, an electronic device, or a control module in the regional development status monitoring index determining device for executing the method for determining the regional development status monitoring index.
Specifically, the target time range may be a monitoring period set according to actual conditions, for example, the target time range is 2000 to 2019. The number of the monitoring dimensions can also be set according to practical situations, for example, the number of the monitoring dimensions is 7; the monitoring dimension includes at least one of: economic development, innovation driving, external opening, social civilization, ecological civilization, folk welfare and safety guarantee. The target text can be a policy text or other text, and the target text can embody subjective opinion of a high-level decision maker. Fig. 2 is a schematic diagram of a target text corresponding to a region to be monitored every year in a target time range, and as shown in fig. 2, the target time range is from 2000 to 2020.
The evaluation value represents a series of specific socioeconomic indexes under each monitoring dimension, for example, the evaluation value of economic development is the labor productivity of the whole person, the total production of people per country (Gross Domestic Product, GDP), the energy consumption of the ten thousand yuan GDP or the water consumption of the ten thousand yuan GDP, the evaluation value of innovation driving is the proportion of the internal expenditure of the research and experimental development warp to GDP, the number of participants in the special subject activities of every ten thousand people science and science, the proportion of the technical market in the GDP or the full-time equivalent of the R & D personnel of every ten thousand people, the evaluation value of external opening is the total sum of goods import and export of people, the total sum of actual use of foreign materials or the business volume of every ten thousand people to the packing engineering, the evaluation value of social civilization is the total library stock of every ten thousand people, the building area of the mass culture facilities of every ten thousand people, the GDP proportion of education warp or the education period, the evaluation value of ecological civilization is the water and soil conservation degree, the fertilizer application intensity or the damage degree, the evaluation value of the raw and the welfare is the number of the health technical personnel of every ten people, the medical facility of every ten people, the medical use of the medical facility, the public land, the energy consumption of the food or the food safety of the food, the food and the food safety of the food is the food and the food safety index.
Based on the existing regional development monitoring index system (divided into two layers, namely a dimension layer and an index layer) and an index panel data set, the regional to be monitored is respectively aggregated with index values year by year and dimension by using other basic comprehensive index algorithms such as an entropy weight method, and the year by year evaluation value of each dimension of the regional to be monitored is obtained. The target text can be acquired from the text database, and the selection of the target text accords with three principles: firstly, the target text has the availability; secondly, the main body of the release text has strong enough representativeness; and thirdly, matching the text release time with the target time range. The principle can ensure the reliability and timeliness of the importance calculation result of each monitoring dimension in the regional development.
Step 102, determining a dimension sorting weight corresponding to the region to be monitored in each monitoring dimension every year based on each target text.
Specifically, the dimension sorting weight represents the performance weight of the region to be monitored corresponding to each monitoring dimension every year. According to the obtained multiple target texts, the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year can be further determined.
And step 103, determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year.
Specifically, the development condition monitoring index represents the comprehensive development condition of the area to be monitored corresponding to each monitoring dimension every year. According to the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year, the development condition monitoring index of the area to be monitored can be further determined.
According to the regional development condition monitoring index determination method provided by the invention, the evaluation value of the region to be monitored in at least one monitoring dimension and the corresponding target text in each year are obtained within the target time range; according to each target text, determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year; and determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year. The dimension sorting weight is determined through text analysis, so that subjective judgment opinion of the importance of different monitoring dimensions of regional development is obtained, and then according to the evaluation value of each monitoring dimension and the coupling of the dimension sorting weight, the accurate determination of the development condition monitoring index of the region to be monitored is realized, the dynamic monitoring of the development condition of the region based on the subjective opinion of a high-level decision maker is realized with low cost and high efficiency, and the accuracy and the efficiency of the dynamic monitoring of the development condition of the region are improved.
Optionally, the specific implementation manner of step 102 includes:
(1) And aiming at each target text, performing word segmentation processing on the target text to obtain at least one word segmentation corresponding to the target text.
Specifically, for each acquired target text, a content analysis method (ROST Content Mining) tool is adopted to perform word segmentation processing on the target text, continuous sentences are truncated into single words, and at least one word segment corresponding to the target text is obtained.
(2) And counting word frequencies corresponding to the word segments.
Specifically, the ROST Content Mining tool can count the word frequency corresponding to each word segment, i.e., the frequency of occurrence of each word segment in the target text.
(3) And determining at least one keyword corresponding to each monitoring dimension respectively based on each word frequency.
Specifically, according to the word frequency corresponding to each word, at least one keyword corresponding to each monitoring dimension can be determined.
(4) And determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year based on each keyword corresponding to each monitoring dimension.
Specifically, based on each keyword corresponding to each monitoring dimension, a dimension sorting weight corresponding to each monitoring dimension in each year of the area to be monitored can be determined.
According to the method for determining the regional development condition monitoring index, word segmentation processing is carried out on the target text aiming at each target text, so that at least one word corresponding to the target text is obtained; counting word frequencies corresponding to the word segmentation; determining at least one keyword corresponding to each monitoring dimension respectively based on each word frequency; based on the keywords corresponding to the monitoring dimensions, determining the dimension sorting weight of the area to be monitored in each monitoring dimension every year, and further determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sorting weight of the monitoring dimensions corresponding to the area to be monitored every year. By counting the word frequency of each word, a target range is provided for the subsequent determination of the corresponding keywords of each monitoring dimension in the target text, the analysis efficiency of the keywords is improved, and the accuracy and the efficiency of dynamic monitoring of the regional development condition can be improved.
Optionally, the determining, based on each word frequency, at least one keyword corresponding to each monitored dimension includes:
(a) At least one high frequency word is determined based on each of the word frequencies.
Specifically, based on the word frequency corresponding to each word, determining the word corresponding to the word frequency larger than a preset threshold as a high-frequency word, thereby obtaining a plurality of high-frequency words. The preset threshold is a preset threshold, for example, the preset threshold is 300, that is, the word segmentation with the word frequency greater than 300 is determined as the high-frequency word.
(b) And respectively determining a similarity measurement value between any high-frequency word and the core word based on each high-frequency word and the core word selected based on the name of each monitoring dimension.
It should be noted that the core word is selected from a plurality of high-frequency words based on the name of the monitoring dimension. And (3) judging the similarity between all the high-frequency words and the core words selected based on the names of the monitoring dimensions by adopting a co-word analysis technology, wherein the stronger the similarity is, the closer the association between the high-frequency words and the monitoring dimensions is indicated.
Specifically, the co-occurrence frequency of the high-frequency word and the core word in all paragraphs of the target text and the word frequency of the high-frequency word and the core word in the target text are counted, then the influence of the word frequency of the two words in the word pair (including the high-frequency word and the core word) on the co-occurrence frequency is removed, and the co-occurrence frequency is converted into a similarity metric value by using an Ochiia coefficient (Ochiia Coefficient).
The similarity measure between two words (noted as a and B) based on the Ochiia coefficients is calculated using formula (1), formula (1) being expressed as:
wherein,representing co-occurrence frequency of A and B words, F A And F B Representing the respective word frequencies of word a and word B.
And (3) respectively determining similarity measurement values between any high-frequency word and core words by adopting the formula (1) according to the obtained multiple high-frequency words and the core words selected based on the names of the monitoring dimensions.
(c) And determining each keyword corresponding to each monitoring dimension respectively based on each similarity measurement value.
Specifically, according to the similarity measurement value between any high-frequency word and core word, a screening principle is adopted to select a plurality of keywords corresponding to each monitoring dimension, wherein the screening principle comprises at least one of the following: a) For each monitoring dimension, determining high-frequency words with similarity measurement values larger than a target threshold value as keywords, namely, presenting high similarity with core words of each monitoring dimension only, and limiting 'high similarity' to be that the similarity with the core words is positioned in the first 10% of all the high-frequency words; b) Similarity with other core words of the monitoring dimension is lower than that with the core words of the monitoring dimension; c) The keywords have clear connotation and meaning.
It should be noted that, the correspondence between the monitoring dimensions and the keywords is "one-to-many" and "one-to-many", which is helpful for comprehensively and comprehensively covering the area to develop the keywords corresponding to each monitoring dimension in the target text, and to develop word frequency statistics and importance ranking.
Optionally, the method of screening the keywords closer to the core word by adopting the co-word analysis technology can also be used for determining the expansion word, and the core word and the expansion word jointly form the keywords corresponding to each dimension. Table 1 shows keywords for each monitoring dimension, and as shown in Table 1, the number of monitoring dimensions is 7, and the keywords include core words and expansion words.
TABLE 1 keywords for each monitoring dimension
Optionally, the determining, based on the keywords corresponding to the monitoring dimensions, a dimension sorting weight corresponding to the to-be-monitored region in each monitoring dimension each year includes:
1) And determining the normalized word frequency corresponding to each keyword based on the word frequency of each keyword corresponding to each monitoring dimension.
Specifically, a Term Frequency-inverse document Frequency (Term Frequency-Inverse Document Frequency, TF-IDF) model is used for normalizing the Term Frequency of each keyword corresponding to each monitoring dimension respectively, so that the normalized Term Frequency corresponding to each keyword is obtained, the influence of the Term Frequency dimension is eliminated, and the comparability of calculation results among different years is provided.
The normalized word frequency is calculated by using a formula (2), and the formula (2) is expressed as:
wherein, Normalized word frequency, d, representing keyword i in target text of the t-th year t Target text representing the t-th year, +.>Representing word frequency of keyword i in target text of the t-th year, and N represents total number of keywords of all monitoring dimensions.
2) And determining word frequency average values corresponding to the monitoring dimensions based on the normalized word frequencies corresponding to the keywords.
Specifically, on the basis of the normalized word frequency calculation result, the total word frequency of all keywords in a single monitoring dimension is summarized. Because the key words under a single monitoring dimension are difficult to distinguish the importance degrees, the influence of the number of the key words is eliminated by adopting a frequency-based arithmetic average algorithm. And calculating word frequency average values corresponding to the monitoring dimensions by adopting a frequency-based arithmetic average algorithm according to the normalized word frequencies corresponding to the keywords corresponding to the monitoring dimensions.
3) And sequencing word frequency means corresponding to the monitoring dimensions, and determining the dimension sequencing weight of the region to be monitored corresponding to the monitoring dimensions every year.
Specifically, the word frequency mean value corresponding to each monitoring dimension is ranked from large to small or from small to large, namely the importance (weight) ranking of each monitoring dimension is represented, so that the dimension ranking weight corresponding to each monitoring dimension in the area to be monitored every year is determined. Fig. 3 is a schematic diagram of a dimension sorting weight corresponding to each monitoring dimension in the region to be monitored provided by the present invention each year, as shown in fig. 3, for example, a sorting result of the word frequency average value corresponding to each monitoring dimension in the region to be monitored in 2000 from large to small is sequentially dimension 1, dimension 7, dimension 6, dimension 3, dimension 4, dimension 5, and dimension 2, and a dimension sorting weight corresponding to dimension 1 to dimension 7 is sequentially 1, 7, 4, 5, 6, 3, and 2.
Optionally, the specific implementation manner of step 104 includes:
and determining the development condition monitoring index of the area to be monitored by adopting a high-dimensional sequencing weight method based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
Specifically, according to the dimension sorting weight of each monitoring dimension, the evaluation values of each monitoring dimension are aggregated by a high-dimension sorting weight method, so as to obtain the development condition monitoring index of the area to be monitored. The novel comprehensive index algorithm of the high-dimensional sorting weight method is used for determining the development condition monitoring index by only using the importance sorting of the monitoring dimension (dimension sorting weight), so that the requirement of weight quantification is reduced, meanwhile, the problem of accuracy caused by specific weight values is avoided, and the accuracy and the efficiency of the development condition monitoring index of the region to be monitored are improved.
Optionally, the determining the development condition monitoring index of the area to be monitored by using a high-dimensional ranking weight method based on the evaluation value and the dimension ranking weight of each monitoring dimension corresponding to the area to be monitored every year includes:
1) And determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the area to be monitored every year.
Specifically, the optimal value represents a maximum value corresponding to a weighted sum of evaluation values of each monitoring dimension, and the worst value represents a minimum value corresponding to a weighted sum of evaluation values of each monitoring dimension. According to the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the areas to be monitored every year, the optimal value and the worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions can be further determined.
2) And determining a development condition monitoring index of the area to be monitored based on the optimal value and the worst value.
Specifically, calculating an average value, namely a development condition monitoring index of the area to be monitored, according to the optimal value and the worst value by adopting a formula (3); wherein, formula (3) is expressed as:
wherein,development monitoring index, which indicates the dimensional ordering weight k of the region m to be measured, < >>Indicating the optimal value of the area to be measured corresponding to each monitoring dimension +.>And representing the worst value of the region to be measured corresponding to each monitoring dimension.
Optionally, the determining, based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year, the optimal value and the worst value corresponding to the weighted sum of the evaluation values of each monitoring dimension includes:
a) And taking the average evaluation value of the evaluation values when different weight values are taken by the sorting weights corresponding to the monitoring dimensions based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the areas to be monitored every year.
Specifically, according to the listed monitoring dimensions from the monitoring dimension corresponding to the largest ranking weight to all the monitoring dimensions, calculating the average evaluation value of the evaluation values when the ranking weights corresponding to the included monitoring dimensions take different weights.
According to the evaluation value and dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year, for example, the dimension sorting weight is fixed in time, adoptingCalculating an average evaluation value of the evaluation values of the first j monitoring dimensions, wherein k p Representing the monitored dimensions corresponding to the dimension sorting weights of k sorting weights p (descending order of weight values), j representing the number of monitored dimensions from 1 to the total number of monitored dimensions, and +.>Indicating that the region m to be monitored is k p Evaluation value of dimension.
b) And determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the average evaluation values.
Specifically, the average evaluation values are ranked from large to small or from small to large, the maximum average evaluation value is determined as the optimal value corresponding to the weighted sum of the evaluation values of the monitoring dimensions, and the minimum average evaluation value is determined as the worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions.
When the ranking weight corresponding to each monitoring dimension is known (assumed to be k), the optimal value And worst value->The optimal value corresponding to each monitoring dimension can be obtained through dual linear programming deduction, namely, the optimal value corresponding to each monitoring dimension is calculated by adopting a formula (4), and the worst value corresponding to each monitoring dimension is calculated by adopting a formula (5); wherein,
according to the regional development condition monitoring index determination method provided by the invention, the average evaluation value of the evaluation values when the sorting weights corresponding to the monitoring dimensions take different weight values is calculated according to the evaluation values of the monitoring dimensions corresponding to the region to be monitored every year and the dimension sorting weights; based on each average evaluation value, determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of each monitoring dimension; and determining a development condition monitoring index of the area to be monitored based on the optimal value and the worst value. Through the coupling of the evaluation value of each monitoring dimension and the dimension sequencing weight, a brand new thought can be provided for subjective determination, the dynamic monitoring of the regional development condition based on the subjective opinion of a high-level decision maker is realized with low cost and high efficiency, and the accuracy and the efficiency of the dynamic monitoring of the regional development condition are improved.
FIG. 4 is a second flowchart of the method for determining regional development status monitoring index according to the present invention, as shown in FIG. 4, the method includes steps 401-413; wherein,
Step 401, acquiring an evaluation value of an area to be monitored in at least one monitoring dimension and a corresponding target text every year in a target time range. The target time range may be a monitoring period set according to actual conditions, for example, the target time range is 2000 to 2019; the number of the monitoring dimensions can also be set according to practical situations, for example, the number of the monitoring dimensions is 7; the monitoring dimension includes at least one of: economic development, innovation driving, external opening, social civilization, ecological civilization, civil welfare and safety guarantee; the target text can be a policy text or other text, and can embody subjective opinion of a high-level decision maker; the evaluation value represents a series of specific socioeconomic performance metrics that are subordinate to each monitored dimension.
Step 402, performing word segmentation processing on the target text aiming at each target text to obtain at least one word segmentation corresponding to the target text. Specifically, the ROST Content Mining tool is adopted to perform word segmentation processing on the target text, and continuous sentences are cut into single words to obtain at least one word segment corresponding to the target text.
Step 403, counting word frequencies corresponding to the segmented words. Specifically, the ROST Content Mining tool can count the word frequency corresponding to each word segment, i.e., the frequency of occurrence of each word segment in the target text.
Step 404, determining at least one high frequency word based on each word frequency. Specifically, the word segment corresponding to the word frequency greater than the preset threshold value is determined as the high-frequency word, for example, the preset threshold value is 300, that is, the word segment with the word frequency greater than 300 is determined as the high-frequency word.
Step 405, determining similarity measurement values between any high-frequency word and core word based on each high-frequency word and the core word selected based on the name of each monitoring dimension. Specifically, a co-word analysis technology is adopted to judge the similarity between all the high-frequency words and the core words selected based on the names of all the monitoring dimensions, namely, the co-occurrence frequency of the high-frequency words and the core words in all the paragraphs of the target text is counted, and the word frequencies of the high-frequency words and the core words in the target text are respectively converted into similarity measurement values by using an Ochiia coefficient (Ochiia Coefficient).
Step 406, determining each keyword corresponding to each monitoring dimension based on each similarity measurement value. Specifically, according to the similarity measurement value between any high-frequency word and core word, a screening principle is adopted to select a plurality of keywords corresponding to each monitoring dimension respectively, so as to obtain a plurality of keywords corresponding to each monitoring dimension respectively.
Step 407, determining the normalized word frequency corresponding to each keyword based on the word frequency of each keyword corresponding to each monitoring dimension. Specifically, the word frequency of each keyword corresponding to each monitoring dimension is normalized by adopting a TF-IDF model, and the normalized word frequency corresponding to each keyword is obtained.
Step 408, determining a word frequency mean value corresponding to each monitoring dimension based on the normalized word frequency corresponding to each keyword. Specifically, an arithmetic average algorithm based on frequency is adopted to eliminate the influence of the number of keywords. And calculating word frequency average values corresponding to the monitoring dimensions by adopting a frequency-based arithmetic average algorithm according to the normalized word frequencies corresponding to the keywords corresponding to the monitoring dimensions.
Step 409, sorting word frequency means corresponding to each monitoring dimension, and determining a dimension sorting weight corresponding to each monitoring dimension in each year of the area to be monitored. Specifically, the word frequency mean value corresponding to each monitoring dimension is ranked from large to small or from small to large, namely the importance (weight) ranking of each monitoring dimension is represented, so that the dimension ranking weight corresponding to each monitoring dimension in the area to be monitored every year is determined.
Step 410, calculating an average evaluation value of the evaluation values when the sorting weights corresponding to the monitoring dimensions take different weight values based on the evaluation values of the monitoring dimensions corresponding to the area to be monitored every year and the dimension sorting weights. Specifically, according to the evaluation value of each monitored dimension and the dimension sorting weight corresponding to each year of the area to be monitored, for example, the sorting weight in the dimension sorting weight is p, adoptingAn average evaluation value of the evaluation values of the included monitoring dimensions in the case where the various monitoring dimensions are included is calculated.
In step 411, the average evaluation values are ranked, and a maximum average evaluation value and a minimum average evaluation value are determined.
Step 412, determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of each monitoring dimension based on the maximum average evaluation value and the minimum average evaluation value. Specifically, the maximum average evaluation value is determined as the optimal value corresponding to each monitoring dimension, and the minimum average evaluation value is determined as the worst value corresponding to each monitoring dimension.
Step 413, determining the development status monitoring index of the area to be monitored based on the optimal value and the worst value. Specifically, according to the optimal value and the worst value, calculating an arithmetic average value of the optimal value and the worst value to obtain a development condition monitoring index of the area to be monitored.
The regional development condition monitoring index determining apparatus provided by the present invention will be described below, and the regional development condition monitoring index determining apparatus described below and the regional development condition monitoring index determining method described above may be referred to correspondingly.
Fig. 5 is a schematic structural diagram of a device for determining a regional development status monitoring index according to the present invention, and as shown in fig. 5, a device 500 for determining a regional development status monitoring index includes: an acquisition module 501, a first determination module 502 and a second determination module 503; wherein,
an obtaining module 501, configured to obtain an evaluation value of an area to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range;
a first determining module 502, configured to determine, based on each target text, a dimension sorting weight corresponding to each monitoring dimension in the area to be monitored every year;
a second determining module 503, configured to determine a development status monitoring index of the area to be monitored based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year.
The invention provides a regional development condition monitoring index determining device, which is characterized in that an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year are obtained in a target time range; according to each target text, determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year; and determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year. The dimension sorting weight is determined through text analysis, so that subjective judgment opinion of the importance of different monitoring dimensions of regional development is obtained, and then according to the evaluation value of each monitoring dimension and the coupling of the dimension sorting weight, the accurate determination of the development condition monitoring index of the region to be monitored is realized, the dynamic monitoring of the development condition of the region based on the subjective opinion of a high-level decision maker is realized with low cost and high efficiency, and the accuracy and the efficiency of the dynamic monitoring of the development condition of the region are improved.
Optionally, the first determining module 502 is specifically configured to:
aiming at each target text, performing word segmentation processing on the target text to obtain at least one word segmentation corresponding to the target text;
counting word frequencies corresponding to the word segmentation;
determining at least one keyword corresponding to each monitoring dimension respectively based on each word frequency;
and determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year based on each keyword corresponding to each monitoring dimension.
Optionally, the first determining module 502 is further configured to:
determining at least one high-frequency word based on each word frequency;
based on the high-frequency words and the core words selected based on the names of the monitoring dimensions, respectively determining similarity measurement values between any high-frequency word and the core words;
and determining each keyword corresponding to each monitoring dimension respectively based on each similarity measurement value.
Optionally, the first determining module 502 is further configured to:
determining normalized word frequencies corresponding to the keywords based on the word frequencies of the keywords corresponding to the monitoring dimensions respectively;
determining word frequency mean values corresponding to the monitoring dimensions based on the normalized word frequencies corresponding to the keywords;
And sequencing word frequency means corresponding to the monitoring dimensions, and determining the dimension sequencing weight of the region to be monitored corresponding to the monitoring dimensions every year.
Optionally, the second determining module 503 is specifically configured to:
and determining the development condition monitoring index of the area to be monitored by adopting a high-dimensional sequencing weight method based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
Optionally, the second determining module 503 is further configured to:
determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the area to be monitored every year;
and determining a development condition monitoring index of the area to be monitored based on the optimal value and the worst value.
Optionally, the second determining module 503 is further configured to:
based on the evaluation values of all the monitoring dimensions and the dimension sorting weights corresponding to the areas to be monitored every year, taking the average evaluation value of the evaluation values when the sorting weights corresponding to the monitoring dimensions are different in weight value;
and determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the average evaluation values.
Fig. 6 is a schematic physical structure of an electronic device according to the present invention, as shown in fig. 6, the electronic device 600 may include: processor 610, communication interface (Communications Interface) 620, memory 630, and communication bus 640, wherein processor 610, communication interface 620, and memory 630 communicate with each other via communication bus 640. The processor 610 may invoke logic instructions in the memory 630 to perform a region development condition monitoring index determination method comprising: acquiring an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range; determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts; and determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
Further, the logic instructions in the memory 630 may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the method for determining a regional development status monitoring index provided by the above methods, the method comprising: acquiring an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range; determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts; and determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for determining a regional development status monitoring index, comprising:
acquiring an evaluation value of a region to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range;
determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts;
and determining a development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
2. The method for determining the regional development status monitoring index according to claim 1, wherein determining the dimension ranking weight of the region to be monitored corresponding to each monitoring dimension each year based on each target text comprises:
aiming at each target text, performing word segmentation processing on the target text to obtain at least one word segmentation corresponding to the target text;
counting word frequencies corresponding to the word segmentation;
determining at least one keyword corresponding to each monitoring dimension respectively based on each word frequency;
and determining the dimension sorting weight of the region to be monitored corresponding to each monitoring dimension every year based on each keyword corresponding to each monitoring dimension.
3. The method for determining the regional development status monitoring index according to claim 2, wherein the determining at least one keyword corresponding to each of the monitoring dimensions based on each of the word frequencies includes:
determining at least one high-frequency word based on each word frequency;
based on the high-frequency words and the core words selected based on the names of the monitoring dimensions, respectively determining similarity measurement values between any high-frequency word and the core words;
and determining each keyword corresponding to each monitoring dimension respectively based on each similarity measurement value.
4. The method according to claim 2, wherein determining the dimension ranking weight of the region to be monitored corresponding to each monitoring dimension each year based on each keyword corresponding to each monitoring dimension, comprises:
determining normalized word frequencies corresponding to the keywords based on the word frequencies of the keywords corresponding to the monitoring dimensions respectively;
determining word frequency mean values corresponding to the monitoring dimensions based on the normalized word frequencies corresponding to the keywords;
and sequencing word frequency means corresponding to the monitoring dimensions, and determining the dimension sequencing weight of the region to be monitored corresponding to the monitoring dimensions every year.
5. The regional development condition monitoring index determining method according to any one of claims 1 to 4, wherein the determining the development condition monitoring index of the region to be monitored based on the evaluation value and the dimension ranking weight of each of the monitoring dimensions corresponding to each year of the region to be monitored includes:
and determining the development condition monitoring index of the area to be monitored by adopting a high-dimensional sequencing weight method based on the evaluation value and the dimension sequencing weight of each monitoring dimension corresponding to the area to be monitored every year.
6. The method for determining a regional development condition monitoring index according to claim 5, wherein the determining the development condition monitoring index of the region to be monitored by using a high-dimensional ranking weight method based on the evaluation value and the dimensional ranking weight of each monitoring dimension corresponding to the region to be monitored every year comprises:
determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to the area to be monitored every year;
and determining a development condition monitoring index of the area to be monitored based on the optimal value and the worst value.
7. The method according to claim 6, wherein determining the optimal value and the worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the evaluation values and the dimension sorting weights of the monitoring dimensions corresponding to each year of the area to be monitored comprises:
calculating an average evaluation value of the evaluation values when the sorting weights corresponding to the monitoring dimensions take different weight values based on the evaluation values of the monitoring dimensions corresponding to the area to be monitored every year and the dimension sorting weights;
and determining an optimal value and a worst value corresponding to the weighted sum of the evaluation values of the monitoring dimensions based on the average evaluation values.
8. A regional development condition monitoring index determining apparatus, comprising:
the acquisition module is used for acquiring an evaluation value of the area to be monitored in at least one monitoring dimension and a target text corresponding to each year in a target time range;
the first determining module is used for determining dimension sorting weights corresponding to the areas to be monitored in the monitoring dimensions every year based on the target texts;
and the second determining module is used for determining the development condition monitoring index of the area to be monitored based on the evaluation value and the dimension sorting weight of each monitoring dimension corresponding to the area to be monitored every year.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of determining the regional development status monitoring index of any one of claims 1 to 7 when the program is executed by the processor.
10. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the regional development status monitoring index determination method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311000729.4A CN117094571A (en) | 2023-08-09 | 2023-08-09 | Regional development status monitoring index determination method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311000729.4A CN117094571A (en) | 2023-08-09 | 2023-08-09 | Regional development status monitoring index determination method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117094571A true CN117094571A (en) | 2023-11-21 |
Family
ID=88776451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311000729.4A Pending CN117094571A (en) | 2023-08-09 | 2023-08-09 | Regional development status monitoring index determination method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117094571A (en) |
-
2023
- 2023-08-09 CN CN202311000729.4A patent/CN117094571A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111324642A (en) | Model algorithm type selection and evaluation method for power grid big data analysis | |
| Kou et al. | An integrated expert system for fast disaster assessment | |
| Tian et al. | A fuzzy TOPSIS model via chi-square test for information source selection | |
| CN107016068A (en) | Knowledge mapping construction method and device | |
| Kou et al. | Multi-criteria decision analysis for emergency medical service assessment | |
| KR20180072167A (en) | System for extracting similar patents and method thereof | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN112668822A (en) | Scientific and technological achievement transformation platform sharing system, method, storage medium and mobile phone APP | |
| CN110968651A (en) | Data processing method and system based on grey fuzzy clustering | |
| CN115879829A (en) | Evaluation expert screening method applied to platform innovation capability examination and verification | |
| CN116644184A (en) | Human Resource Information Management System Based on Data Clustering | |
| Chaudhary et al. | Comparative analysis of entropy weight method and c5 classifier for predicting employee churn | |
| CN113837578B (en) | Grid supervision, management and evaluation method for power supervision enterprise | |
| CN115310752A (en) | Energy big data-oriented data asset value evaluation method and system | |
| Tiruneh et al. | Feature selection for construction organizational competencies impacting performance | |
| CN113011788A (en) | Emergency decision-making method for marine traffic accident, terminal equipment and storage medium | |
| Prabadevi et al. | A decision model for ranking Asian Higher Education Institutes using an NLP-based text analysis approach | |
| Wu et al. | SOUA: Towards Intelligent Recommendation for Applying for Overseas Universities | |
| CN112162972A (en) | Human resource bidirectional recommendation system based on data mining and privacy protection technology | |
| CN116127194A (en) | Enterprise recommendation method | |
| CN116756373A (en) | Project review expert screening method, system and medium based on knowledge graph update | |
| CN117094571A (en) | Regional development status monitoring index determination method and device and electronic equipment | |
| CN109063944A (en) | City banking index analysis method and device based on big data analysis technology | |
| CN112506930B (en) | Data insight system based on machine learning technology | |
| CN113705920A (en) | Generation method of water data sample set for thermal power plant and terminal 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 |