CN113157924A - Smart city-oriented resident public demand response method - Google Patents
Smart city-oriented resident public demand response method Download PDFInfo
- Publication number
- CN113157924A CN113157924A CN202110495972.2A CN202110495972A CN113157924A CN 113157924 A CN113157924 A CN 113157924A CN 202110495972 A CN202110495972 A CN 202110495972A CN 113157924 A CN113157924 A CN 113157924A
- Authority
- CN
- China
- Prior art keywords
- demand
- record
- event
- resident
- resident demand
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000004044 response Effects 0.000 title claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims abstract description 46
- 230000004043 responsiveness Effects 0.000 claims abstract description 13
- 238000009826 distribution Methods 0.000 claims description 36
- 238000012546 transfer Methods 0.000 claims description 17
- 230000008520 organization Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 6
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 230000001364 causal effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 239000003607 modifier Substances 0.000 claims description 3
- 239000002243 precursor Substances 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- G06F16/35—Clustering; Classification
- G06F16/353—Clustering; Classification into predefined classes
-
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/313—Selection or weighting of terms for indexing
-
- 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
- G06F16/334—Query execution
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a resident public demand response method for a smart city, which comprises the following steps: analyzing the content similarity between every two normalized resident demand records to obtain the text information entropy in the target monitoring period; identifying all newly-increased demand vocabularies in a target monitoring period, and clustering all resident demand records containing the newly-increased demand vocabularies based on first record characteristics corresponding to each resident demand record containing the newly-increased demand vocabularies to obtain a first clustering record set; clustering each resident demand record in the first clustering record set based on the second record characteristic of each resident demand record to obtain a second clustering record set, and identifying the demand characteristic of the resident demand event corresponding to each second clustering record set; and determining the responsiveness of the resident demand event based on the event influence range corresponding to the resident demand event and the demand characteristics of the resident demand event, and generating a corresponding resource allocation list.
Description
Technology neighborhood
The invention relates to the field of smart cities and big data, in particular to a resident public demand response method for smart cities.
Background
The smart city is based on new generation information technologies such as Internet of things, cloud computing, mobile internet, big data, remote sensing and remote measuring, a space geographic information system and the like, dynamically acquires, senses, analyzes and integrates data of all aspects of the city in an Internet of things and interconnection mode, promotes networked sharing, intensive integration, collaborative development and efficient utilization of city information resources, develops related technologies of the smart city, can promote efficient and convenient operation of various industries such as traffic, communication, education, environment, energy, safety, management, service, culture, medical treatment, industry and the like of modern cities, and promotes intelligent and fine management level in the city operation management field.
The civil problems are basic problems related to production and life of people, in recent years, network civil appeal becomes a hotspot of social governance and public services, and the traditional method for analyzing the civil appeal is difficult to accurately analyze and judge massive civil appeal on the network, and is more difficult to accurately detect the civil events from massive appeal data in real time.
Disclosure of Invention
In view of the above, the present invention provides a public demand response method for residents in a smart city, which includes:
acquiring a plurality of resident demand records issued on an urban public service platform in a target monitoring period, normalizing the content similarity between each resident demand record to an interval [0,1], and analyzing to obtain the text information entropy of the target monitoring period based on the normalized content similarity;
when the text information entropy is determined to be smaller than a preset information entropy threshold value, comparing all resident demand records acquired in a target monitoring period with all historical resident demand records acquired in a historical monitoring period to identify all newly-increased demand vocabularies in the target monitoring period, and clustering all resident demand records containing the newly-increased demand vocabularies based on first record characteristics corresponding to each resident demand record containing the newly-increased demand vocabularies to obtain a first clustering record set;
extracting second record characteristics of each resident demand record in the first cluster record set to cluster each resident demand record in the first cluster record set again to obtain a second cluster record set, and analyzing all resident demand records in the second cluster record set to identify the demand characteristics of resident demand events corresponding to each second cluster record set, wherein the demand characteristics comprise recessive demand characteristics and dominant demand characteristics, and the second record characteristics are event layer characteristics of corresponding resident demand records and comprise event occurrence subjects, event time and event places of corresponding resident demand events;
determining an event influence range corresponding to the resident demand event based on the location name contained in each resident demand record in the second clustering record set, determining the responsiveness of the resident demand event based on the event influence range of the resident demand event and the demand characteristics of the resident demand event, and generating a corresponding resource configuration list for the resident demand event of which the responsiveness is greater than a preset responsiveness threshold;
and sending the event information and the resource configuration list of the resident demand event to a corresponding local service organization so that the local service organization can process the resident demand event.
In a further embodiment, the first record characteristic is a theme layer characteristic of the corresponding resident demand record, which is used for characterizing the event type of the corresponding resident demand event.
The resource configuration list comprises organization identifiers, the number of configuration personnel, the type of configuration personnel and the types and the numbers of software and hardware equipment.
In a further embodiment, comparing all the resident demand records acquired in the target monitoring period with all the historical resident demand records acquired in the historical monitoring period to identify all the newly added demand vocabularies in the target monitoring period includes:
extracting a first core demand vocabulary group of each resident demand record acquired in a target monitoring period, extracting a second core demand vocabulary group of each historical resident demand record acquired in a historical monitoring period, and comparing each first core demand vocabulary in the first core demand vocabulary group with a second core demand vocabulary in the second core demand vocabulary group to obtain a time interval period of each first core demand vocabulary;
determining the probability distribution obeyed by each first core requirement vocabulary based on the time interval period of occurrence of each first core requirement vocabulary and the total number of occurrences in the corresponding time interval period, and constructing a corresponding transfer cost function for each first core requirement vocabulary based on the probability distribution obeyed by each first core requirement vocabulary;
setting the novel state values of all the first core requirement vocabularies appearing in the historical resident requirement records as 0, carrying out state transfer on the first core requirement vocabularies based on the transfer cost function, obtaining the novel state values corresponding to the first core requirement vocabularies when the transfer cost is minimum, and taking all the first core requirement vocabularies with the novel state values of 1 as newly added requirement vocabularies in the target monitoring period.
In a further embodiment, the clustering all the resident demand records including the newly added demand vocabulary to obtain a first cluster record set based on the first record characteristics corresponding to each resident demand record including the newly added demand vocabulary includes:
performing document aggregation on all the resident demand records containing the newly added demand vocabulary to obtain a long document set in a target monitoring period, and identifying the subject vocabulary in the corresponding resident demand record based on the potential semantic relationship between each vocabulary in the corresponding resident demand record;
counting all subject words contained in each resident demand record to obtain a first subject word distribution probability corresponding to the resident demand record, counting each subject word in a long document set to obtain a document subject distribution probability of each subject word, and carrying out interval constraint on the first subject word distribution probability of the corresponding resident demand record based on the document subject distribution probability to obtain a second subject word distribution probability of the resident demand record;
and performing feature extraction on the topic words with the highest occurrence probability in the second topic word distribution probability to obtain first record features corresponding to the resident demand records, and performing event clustering on all the resident demand records based on feature similarity between the first record features of each resident demand record.
In a further embodiment, the extracting the second record characteristic of each resident demand record in the first clustering record set to cluster each resident demand record in the first clustering record set again to obtain the second clustering record set includes:
extracting all core verbs corresponding to the resident demand records in the first cluster record set and precursor modifiers of each core verb to obtain a first event element set corresponding to the resident demand records, traversing each event element vocabulary in the first event element set to judge whether an event attribute indicated by the corresponding event element vocabulary is a universal event attribute, and rejecting the event element vocabularies which have the universal event attribute in the first event element set;
extracting all feature vocabularies which have event semantic relations with event element vocabularies in the first event element set from the resident demand record to serve as a second event element set of the resident demand record, and performing feature extraction on the first event element set and the second event element set to obtain second record features corresponding to the resident demand record, wherein the event semantic relations comprise composition relations, causal relations, following relations and concurrent relations, and the second record features comprise event type features, event time features, event location features, event trigger type features, event trigger word sense features and trigger word distance features;
and analyzing the multidimensional feature vector based on the second record feature to obtain the feature similarity of each resident demand record in different event feature spaces, performing weighted fusion on the feature similarity of each resident demand record in different event feature spaces to obtain the multidimensional event feature similarity of each resident demand record, and clustering the resident demand records of which the multidimensional event feature similarity is greater than a preset similarity threshold to obtain a second clustering record set.
In a further embodiment, the determining the event influence range of the corresponding residential demand event based on the location name included in each residential demand record in the second set of clustering records comprises:
extracting all place names contained in each resident demand record in the second clustering record set, and carrying out hierarchical clustering on all the place names based on the actual position characteristics of each place name and the text position of each place name in the corresponding resident demand record to form a corresponding regional structure tree;
mapping each place name in the area structure tree to a corresponding position point in the urban space, carrying out statistics on the position point mapped by each place name according to the hierarchy to obtain the multistage regional distribution characteristics of each resident demand event, and determining the event influence range of the corresponding resident demand event based on the multistage regional distribution characteristics.
In a further embodiment, the analyzing all the resident demand records in the second clustering record set to identify the demand characteristics of the resident demand event corresponding to each second clustering record set includes:
and analyzing the characteristic vocabulary representing the user demand contained in each resident demand record in the second clustering record set to obtain the dominant demand characteristic of the urban residents, and analyzing the context information of each event element vocabulary to obtain the implicit demand characteristic of the urban residents.
The multi-level regional distribution characteristics are used for representing the regional range of the concentrated occurrence of the corresponding resident demand events. The trigger word distance characteristic is the number of spaced words between each core verb in the corresponding resident demand record and the vocabulary of the event subject representing the corresponding resident demand event.
The embodiment provided by the invention has the following beneficial effects:
through analyzing resident demand records in a related platform, on the premise that resident demand records in a target monitoring period have newly added demand vocabularies, clustering the resident demand records with the same theme, clustering the resident demand records with the same event occurrence subject, the occurrence time and the occurrence place in a cluster set again, clustering the resident demand records feeding back the same resident demand event together, analyzing the cluster set obtained through secondary clustering to obtain the event emergency degree of the resident demand event, and sending the resident demand event with higher emergency degree to a local service organization. Therefore, the method and the system can analyze the demand of the public messages and are beneficial to accelerating the intelligent conversion of service type government affairs.
Drawings
Fig. 1 is a flowchart illustrating a method for responding to public demand of residents of a smart city according to an exemplary embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention.
Referring to fig. 1, the public demand response method for residents in a smart city according to the present invention may specifically include the following steps:
s1, acquiring a plurality of resident demand records issued on an urban public service platform in a target monitoring period, normalizing the content similarity between each resident demand record to an interval [0,1], and analyzing the text information entropy of the target monitoring period based on the normalized content similarity, wherein the content similarity is obtained by analyzing the similarity between each vocabulary contained in different resident demand records.
Optionally, the calculation formula of the text information entropy is:
wherein M is text information entropy, i and j are data indexes recorded by resident demand, SijNormalized content similarity between the ith and jth resident demand records, n being the resident in the target monitoring periodTotal number of demand records.
The more similar the content of the resident demand records in the target monitoring period represented by the formula is, the smaller the text information entropy is; the more dissimilar the content between the resident demand records in the target monitoring period, the larger the text information entropy. The target monitoring period is a time period preset by the system.
Optionally, the resident demand record is appeal data related to the livelihood, and may be public complaint records issued by residents, including community water cut, illegal building and congestion events caused by road construction.
S2, when the text information entropy is determined to be smaller than the preset information entropy threshold value, comparing all the resident demand records acquired in the target monitoring period with all the historical resident demand records acquired in the historical monitoring period to identify all the newly added demand words in the target monitoring period, and clustering all the resident demand records containing the newly added demand words based on the first record characteristics corresponding to each resident demand record containing the newly added demand words to obtain a first clustering record set.
Optionally, when the text information entropy is determined to be smaller than the preset information entropy threshold, the resident demand events indicating that similar subjects are fed back by a plurality of resident demand records in the target monitoring period are represented. The preset information entropy threshold value is a numerical value preset by the system and used for judging the text information entropy of all resident demand records in the target monitoring period.
Specifically, comparing all the resident demand records acquired in the target monitoring period with all the historical resident demand records acquired in the historical monitoring period to identify all the newly added demand vocabularies in the target monitoring period includes:
extracting a first core demand vocabulary group of each resident demand record acquired in a target monitoring period, extracting a second core demand vocabulary group of each historical resident demand record acquired in a historical monitoring period, and comparing each first core demand vocabulary in the first core demand vocabulary group with a second core demand vocabulary in the second core demand vocabulary group to obtain a time interval period of each first core demand vocabulary;
determining the probability distribution obeyed by each first core requirement vocabulary based on the time interval period of occurrence of each first core requirement vocabulary and the total number of occurrences in the corresponding time interval period, and constructing a corresponding transfer cost function for each first core requirement vocabulary based on the probability distribution obeyed by each first core requirement vocabulary;
setting the novel state values of all the first core requirement vocabularies appearing in the historical resident requirement records as 0, carrying out state transfer on the first core requirement vocabularies based on the transfer cost function, obtaining the novel state values corresponding to the first core requirement vocabularies when the transfer cost is minimum, and taking all the first core requirement vocabularies with the novel state values of 1 as newly added requirement vocabularies in the target monitoring period.
Optionally, the first core requirement vocabulary is a core verb in the corresponding resident requirement record, and is used for representing an event type of the corresponding resident requirement event; the second core requirement vocabulary is a core verb in the corresponding historical resident requirement record and used for representing the event type of the corresponding resident requirement event.
Optionally, constructing a corresponding calculation formula of the transfer cost function for each first core requirement vocabulary based on the probability distribution obeyed by each first core requirement vocabulary comprises:
P(st,st+1)＝C(st,st+1)-lnF(st,st+1)
wherein, P(s)t,st+1) For the transfer cost function, t is the time index, stIs a novel state value, s, of the first core requirement vocabulary at time tt+1Is a novel state value, C(s), of the first core requirement vocabulary at time t +1t,st+1) For the first core requirement vocabulary from stIs transferred to st+1The transfer cost of F(s)t,st+1) A probability distribution for the first core requirement vocabulary obeying.
Optionally, the first core requirement vocabulary is from stIs transferred to st+1The transfer cost of (c) is:
wherein s istIs a novel state value, s, of the first core requirement vocabulary at time tt+1A new state value of the first core requirement vocabulary at the time t +1, mu is a transfer cost parameter preset by the system, NcIs the total number of occurrences of the first core requirement vocabulary c within the corresponding time interval period.
Optionally, the first record characteristic is a theme layer characteristic of the corresponding resident demand record, which is used for characterizing the event type of the corresponding resident demand event.
Specifically, the clustering all the resident demand records containing the newly added demand vocabulary to obtain a first cluster record set based on the first record characteristics corresponding to each resident demand record containing the newly added demand vocabulary includes:
performing document aggregation on all resident demand records containing newly-added demand vocabularies to obtain a long document set in a target monitoring period, and identifying topic vocabularies in the corresponding resident demand records based on the potential semantic relation between every vocabulary in the corresponding resident demand records, wherein the topic vocabularies are core verbs used for representing event types in the corresponding resident demand records;
counting all subject words contained in each resident demand record to obtain a first subject word distribution probability corresponding to the resident demand record, counting each subject word in a long document set to obtain a document subject distribution probability of each subject word, and carrying out interval constraint on the first subject word distribution probability of the corresponding resident demand record based on the document subject distribution probability to obtain a second subject word distribution probability of the resident demand record;
and performing feature extraction on the topic words with the highest occurrence probability in the second topic word distribution probability to obtain first record features corresponding to the resident demand records, and performing event clustering on all the resident demand records based on feature similarity between the first record features of each resident demand record.
S3, extracting second record characteristics of each resident demand record in the first cluster record set to cluster each resident demand record in the first cluster record set again to obtain a second cluster record set, and analyzing all resident demand records in the second cluster record set to identify demand characteristics of resident demand events corresponding to each second cluster record set, wherein the demand characteristics comprise recessive demand characteristics and dominant demand characteristics, and the second record characteristics are event layer characteristics of corresponding resident demand records and comprise event occurrence subjects, event time and event places of corresponding resident demand events.
Specifically, the extracting of the second record feature of each resident demand record in the first clustering record set to re-cluster each resident demand record in the first clustering record set to obtain the second clustering record set includes:
extracting all core verbs corresponding to the resident demand records in the first cluster record set and precursor modifiers of each core verb to obtain a first event element set corresponding to the resident demand records, traversing each event element vocabulary in the first event element set to judge whether an event attribute indicated by the corresponding event element vocabulary is a universal event attribute, and rejecting the event element vocabularies which have the universal event attribute in the first event element set;
extracting all feature vocabularies which have event semantic relations with event element vocabularies in the first event element set from the resident demand record to serve as a second event element set of the resident demand record, and performing feature extraction on the first event element set and the second event element set to obtain second record features corresponding to the resident demand record, wherein the event semantic relations comprise composition relations, causal relations, following relations and concurrent relations, and the second record features comprise event type features, event time features, event location features, event trigger type features, event trigger word sense features and trigger word distance features;
and analyzing the multidimensional feature vector based on the second record feature to obtain the feature similarity of each resident demand record in different event feature spaces, performing weighted fusion on the feature similarity of each resident demand record in different event feature spaces to obtain the multidimensional event feature similarity of each resident demand record, and clustering the resident demand records of which the multidimensional event feature similarity is greater than a preset similarity threshold to obtain a second clustering record set.
Optionally, the trigger distance feature is a number of spaced words between each core verb in the corresponding resident demand record and a vocabulary of the event subject characterizing the corresponding resident demand event. The event element vocabulary with the generic event attribute is the event element vocabulary with the top type concept in the corresponding resident demand record, such as people, places, countries and organizations, and has universality and no reference value.
Optionally, the preset similarity threshold is a numerical value preset by the system and used for judging whether the resident demand events represented by each resident demand record are the same or not.
Specifically, the analyzing all the resident demand records in the second clustering record set to identify the demand characteristics of the resident demand event corresponding to each second clustering record set includes:
analyzing feature vocabularies representing user requirements contained in each resident requirement record in the second clustering record set to obtain explicit requirement features of urban residents, and analyzing context information of each event element vocabulary to obtain implicit requirement features of the urban residents, wherein the explicit requirement features are user requirement features directly recorded in corresponding resident requirement records, and the implicit requirement features are user requirement features obtained by presumption of the context information of each event element vocabulary;
the characteristic vocabulary characterizing the user requirement may be a vocabulary in a sentence segment after a specific word, such as "urgent need … …" or "request … …".
S4, determining an event influence range corresponding to the resident demand event based on the place name contained in each resident demand record in the second clustering record set, determining responsiveness of the resident demand event based on the event influence range of the resident demand event and the demand characteristics of the resident demand event, and generating a corresponding resource configuration list for the resident demand event with the responsiveness greater than a preset responsiveness threshold, wherein the responsiveness is used for representing the event emergency degree of the corresponding resident demand event.
Specifically, the determining of the event influence range of the corresponding residential demand event based on the location name included in each residential demand record in the second set of clustering records includes:
extracting all place names contained in each resident demand record in the second clustering record set, and carrying out hierarchical clustering on all the place names based on the actual position characteristic of each place name and the text position of the place name in the corresponding resident demand record to form a corresponding region structure tree, wherein the actual position characteristic is the actual longitude and latitude size of the corresponding place name;
mapping each place name in the area structure tree to a corresponding position point in an urban space, carrying out statistics on the position point mapped by each place name according to a hierarchy to obtain a multi-level region distribution characteristic of each resident demand event, and determining an event influence range of the corresponding resident demand event based on the multi-level region distribution characteristic, wherein the event influence range is used for representing the geographical distribution range of the corresponding resident demand event.
Optionally, the counting, according to a hierarchy, of the location points mapped by each location name includes counting, according to a corresponding region, a corresponding county, and a corresponding street of each location point.
Optionally, the multi-level geographical distribution characteristic is used for characterizing a regional scope in which the corresponding residential demand events occur in a set, wherein the regional scope includes a wide-area event scope and a local event scope. The resource configuration list comprises organization identifiers, the number of configuration personnel, the type of configuration personnel and the types and the numbers of software and hardware equipment.
Optionally, the preset responsiveness threshold is a value preset by the system for judging whether emergency processing is required for the corresponding residential demand event.
Alternatively, in one embodiment, the system may set a higher responsiveness for resident demand events with a wider range of event impact, a greater total number of resident demand records, and a more urgent event type.
And S5, sending the event information of the resident demand event and the resource configuration list to a corresponding local service organization for the local service organization to process the resident demand event.
Optionally, the event information includes an event type, an event location, and an event time of the residential demand event. The local service organizations include street offices, community service centers, and other regulatory organizations that provide services to the public.
According to the resident public demand response method for the smart city, the resident demand records in the related platform are analyzed, on the premise that the resident demand records in the target monitoring period have newly added demand vocabularies, the resident demand records with the same theme are clustered, the resident demand records with the same event occurrence subject, the same event occurrence time and the same event occurrence place in the cluster set are clustered again, so that the resident demand records feeding back the same resident demand event are clustered together, the event emergency degree of the resident demand event is obtained through the cluster set analysis obtained through secondary clustering, and the resident demand event with the higher emergency degree is sent to the local service organization. The method can accurately and timely detect the public messages of residents and the sudden civil demands reflected by the appeal records, and is favorable for accelerating the intelligent conversion of service type government affairs.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A public demand response method for residents in a smart city, the method comprising:
acquiring a plurality of resident demand records issued on an urban public service platform in a target monitoring period, normalizing the content similarity between each resident demand record to an interval [0,1], and analyzing to obtain the text information entropy of the target monitoring period based on the normalized content similarity;
when the text information entropy is determined to be smaller than a preset information entropy threshold value, comparing all resident demand records acquired in a target monitoring period with all historical resident demand records acquired in a historical monitoring period to identify all newly-increased demand vocabularies in the target monitoring period, and clustering all resident demand records containing the newly-increased demand vocabularies based on first record characteristics corresponding to each resident demand record containing the newly-increased demand vocabularies to obtain a first clustering record set;
extracting second record characteristics of each resident demand record in the first cluster record set to cluster each resident demand record in the first cluster record set again to obtain a second cluster record set, and analyzing all resident demand records in the second cluster record set to identify the demand characteristics of resident demand events corresponding to each second cluster record set, wherein the demand characteristics comprise recessive demand characteristics and dominant demand characteristics, and the second record characteristics are event layer characteristics of corresponding resident demand records and comprise event occurrence subjects, event time and event places of corresponding resident demand events;
determining an event influence range corresponding to the resident demand event based on the location name contained in each resident demand record in the second clustering record set, determining the responsiveness of the resident demand event based on the event influence range of the resident demand event and the demand characteristics of the resident demand event, and generating a corresponding resource configuration list for the resident demand event of which the responsiveness is greater than a preset responsiveness threshold;
and sending the event information and the resource configuration list of the resident demand event to a corresponding local service organization so that the local service organization can process the resident demand event.
2. The method according to claim 1, wherein the first record characteristic is a subject-level characteristic of the corresponding resident demand record, which is used for characterizing an event type of the corresponding resident demand event.
3. The method of claim 1 or 2, wherein the resource configuration list comprises organization identifiers, number of configuration personnel, type of configuration personnel, and type and number of hardware and software devices.
4. The method according to claim 3, wherein comparing all the resident demand records acquired in the target monitoring period with all the historical resident demand records acquired in the historical monitoring period to identify all the newly added demand vocabulary in the target monitoring period comprises:
extracting a first core demand vocabulary group of each resident demand record acquired in a target monitoring period, extracting a second core demand vocabulary group of each historical resident demand record acquired in a historical monitoring period, and comparing each first core demand vocabulary in the first core demand vocabulary group with a second core demand vocabulary in the second core demand vocabulary group to obtain a time interval period of each first core demand vocabulary;
determining the probability distribution obeyed by each first core requirement vocabulary based on the time interval period of occurrence of each first core requirement vocabulary and the total number of occurrences in the corresponding time interval period, and constructing a corresponding transfer cost function for each first core requirement vocabulary based on the probability distribution obeyed by each first core requirement vocabulary;
setting the novel state values of all the first core requirement vocabularies appearing in the historical resident requirement records as 0, carrying out state transfer on the first core requirement vocabularies based on the transfer cost function, obtaining the novel state values corresponding to the first core requirement vocabularies when the transfer cost is minimum, and taking all the first core requirement vocabularies with the novel state values of 1 as newly added requirement vocabularies in the target monitoring period.
5. The method according to claim 4, wherein the clustering all the resident demand records containing the newly added demand vocabulary to obtain a first cluster record set based on the first record characteristics corresponding to each resident demand record containing the newly added demand vocabulary comprises:
performing document aggregation on all the resident demand records containing the newly added demand vocabulary to obtain a long document set in a target monitoring period, and identifying the subject vocabulary in the corresponding resident demand record based on the potential semantic relationship between each vocabulary in the corresponding resident demand record;
counting all subject words contained in each resident demand record to obtain a first subject word distribution probability corresponding to the resident demand record, counting each subject word in a long document set to obtain a document subject distribution probability of each subject word, and carrying out interval constraint on the first subject word distribution probability of the corresponding resident demand record based on the document subject distribution probability to obtain a second subject word distribution probability of the resident demand record;
and performing feature extraction on the topic words with the highest occurrence probability in the second topic word distribution probability to obtain first record features corresponding to the resident demand records, and performing event clustering on all the resident demand records based on feature similarity between the first record features of each resident demand record.
6. The method of claim 5, wherein the extracting of the second record features of each resident demand record in the first cluster record set to re-cluster each resident demand record in the first cluster record set to obtain the second cluster record set comprises:
extracting all core verbs corresponding to the resident demand records in the first cluster record set and precursor modifiers of each core verb to obtain a first event element set corresponding to the resident demand records, traversing each event element vocabulary in the first event element set to judge whether an event attribute indicated by the corresponding event element vocabulary is a universal event attribute, and rejecting the event element vocabularies which have the universal event attribute in the first event element set;
extracting all feature vocabularies which have event semantic relations with event element vocabularies in the first event element set from the resident demand record to serve as a second event element set of the resident demand record, and performing feature extraction on the first event element set and the second event element set to obtain second record features corresponding to the resident demand record, wherein the event semantic relations comprise composition relations, causal relations, following relations and concurrent relations, and the second record features comprise event type features, event time features, event location features, event trigger type features, event trigger word sense features and trigger word distance features;
and analyzing the multidimensional feature vector based on the second record feature to obtain the feature similarity of each resident demand record in different event feature spaces, performing weighted fusion on the feature similarity of each resident demand record in different event feature spaces to obtain the multidimensional event feature similarity of each resident demand record, and clustering the resident demand records of which the multidimensional event feature similarity is greater than a preset similarity threshold to obtain a second clustering record set.
7. The method according to claim 6, wherein determining the event impact range of the corresponding residential demand event based on the location name contained in each residential demand record in the second set of clustered records comprises:
extracting all place names contained in each resident demand record in the second clustering record set, and carrying out hierarchical clustering on all the place names based on the actual position characteristics of each place name and the text position of each place name in the corresponding resident demand record to form a corresponding regional structure tree;
mapping each place name in the area structure tree to a corresponding position point in the urban space, carrying out statistics on the position point mapped by each place name according to the hierarchy to obtain the multistage regional distribution characteristics of each resident demand event, and determining the event influence range of the corresponding resident demand event based on the multistage regional distribution characteristics.
8. The method according to claim 7, wherein analyzing all the resident demand records in the second set of clustered records to identify the demand characteristics of the resident demand event corresponding to each second set of clustered records comprises:
and analyzing the characteristic vocabulary representing the user demand contained in each resident demand record in the second clustering record set to obtain the dominant demand characteristic of the urban residents, and analyzing the context information of each event element vocabulary to obtain the implicit demand characteristic of the urban residents.
9. The method as claimed in claim 8, wherein the multi-level regional distribution characteristic is used to characterize the regional scope where the corresponding residential demand events occur collectively.
10. The method of claim 9, wherein the trigger distance characteristic is a number of spaced words between each core verb in the corresponding resident demand record and a vocabulary of an event body characterizing the corresponding resident demand event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110495972.2A CN113157924A (en) | 2021-05-07 | 2021-05-07 | Smart city-oriented resident public demand response method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110495972.2A CN113157924A (en) | 2021-05-07 | 2021-05-07 | Smart city-oriented resident public demand response method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113157924A true CN113157924A (en) | 2021-07-23 |
Family
ID=76873647
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110495972.2A Pending CN113157924A (en) | 2021-05-07 | 2021-05-07 | Smart city-oriented resident public demand response method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113157924A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062107A (en) * | 2022-06-10 | 2022-09-16 | 浙江嘉兴数字城市实验室有限公司 | Social scene automatic identification and inspection plan dynamic generation method thereof |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109460938A (en) * | 2018-11-23 | 2019-03-12 | 中国城市和小城镇改革发展中心 | A kind of city intelligent central control system and its method |
| CN110162771A (en) * | 2018-11-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | The recognition methods of event trigger word, device, electronic equipment |
| CN112148828A (en) * | 2020-09-30 | 2020-12-29 | 广元量知汇科技有限公司 | Emergency management method based on smart community |
-
2021
- 2021-05-07 CN CN202110495972.2A patent/CN113157924A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162771A (en) * | 2018-11-22 | 2019-08-23 | 腾讯科技（深圳）有限公司 | The recognition methods of event trigger word, device, electronic equipment |
| CN109460938A (en) * | 2018-11-23 | 2019-03-12 | 中国城市和小城镇改革发展中心 | A kind of city intelligent central control system and its method |
| CN112148828A (en) * | 2020-09-30 | 2020-12-29 | 广元量知汇科技有限公司 | Emergency management method based on smart community |
Non-Patent Citations (2)
| Title |
|---|
| 刘卓: "融合时空信息的社交媒体事件检测方法研究", 《中国优秀硕士学位论文 信息科技辑》 * |
| 麦丞程 等: "公共服务热线中基于地域自适应的突发事件实时检测方法", 《计算机学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062107A (en) * | 2022-06-10 | 2022-09-16 | 浙江嘉兴数字城市实验室有限公司 | Social scene automatic identification and inspection plan dynamic generation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Disaster early warning and damage assessment analysis using social media data and geo-location information | |
| Xu et al. | Participatory sensing-based semantic and spatial analysis of urban emergency events using mobile social media | |
| Ikawa et al. | Location inference using microblog messages | |
| Ghahremanlou et al. | Geotagging twitter messages in crisis management | |
| CN109189917B (en) | City functional zone division method and system integrating landscape and social characteristics | |
| CN108428341A (en) | A kind of emergency traffic management and dispatching method and system based on human-computer fusion | |
| CN105677793A (en) | Site database establishing method and device, and candidate riding site recommending method and device | |
| CN111708774B (en) | Industry analytic system based on big data | |
| CN109670843A (en) | Data processing method, device, computer equipment and the storage medium of complaint business | |
| Tounsi et al. | A systematic review of natural language processing applications for hydrometeorological hazards assessment | |
| CN114510566B (en) | Method and system for mining, classifying and analyzing hotword based on worksheet | |
| CN112799155B (en) | Environment monitoring method based on big data | |
| KR101982756B1 (en) | System and Method for processing complex stream data using distributed in-memory | |
| CN116013084B (en) | Traffic management and control scene determining method and device, electronic equipment and storage medium | |
| Kershaw et al. | Towards tracking and analysing regional alcohol consumption patterns in the UK through the use of social media | |
| CN111190982A (en) | Shared bicycle management method and system based on big data | |
| WO2021114615A1 (en) | Method, apparatus, and device for visualization of behavior risk identification, and storage medium | |
| CN106056515A (en) | Community grid event cluster feature extraction method | |
| Wu et al. | Mining typhoon victim information based on multi-source data fusion using social media data in China: a case study of the 2019 Super Typhoon Lekima | |
| CN113157924A (en) | Smart city-oriented resident public demand response method | |
| CN113157925A (en) | Intelligent government affair analysis system based on big data | |
| CN112231381A (en) | Spatial data information collaboration platform based on WEBGIS and construction method thereof | |
| CN111798352A (en) | Enterprise state supervision method, device, equipment and computer readable storage medium | |
| CN106157651B (en) | A kind of traffic radio traffic information broadcasting system based on voice semantic understanding | |
| CN116028467A (en) | Intelligent service big data modeling method, system, storage medium and computer 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210723 |