Multi-dimensional population data dynamic fusion analysis system and method

Abstract

The invention discloses a multi-dimensional population data dynamic fusion analysis system and method, and the system comprises a multi-source data fusion module which is used for receiving multi-source data and carrying out the alignment of the multi-source data, and obtaining the aligned data; and the intelligent analysis module is connected with the multi-source data fusion module and is used for receiving the aligned data and generating a bus scheduling or path optimization scheme based on the aligned data and the dynamic job-housing index model. The analysis accuracy and effect can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a multi-dimensional population data dynamic fusion analysis system and method. BACKGROUND

[0002] The population migration between regions is accelerating, and the traditional static data is difficult to capture the short-term scale migration factors.

[0003] At present, the population analysis can be fused with the "intelligent body graph" technology, which can construct a "population job and residence flow index" by associating employment, medical treatment and consumption factors, and identify the causal relationship between high-skilled talent migration and industrial growth.

[0004] However, the above method has the problem of low analysis accuracy. SUMMARY

[0005] The main purpose of the present application is to provide a multi-dimensional population data dynamic fusion analysis system and method, which can improve the analysis accuracy and effect.

[0006] In order to achieve the above purpose, in a first aspect, the present application provides a multi-dimensional population data dynamic fusion analysis system, comprising: A multi-source data fusion module is configured to receive multi-source data and align the multi-source data to obtain aligned data. An intelligent analysis module is connected to the multi-source data fusion module and configured to receive the aligned data and generate a bus scheduling or path optimization scheme based on the aligned data and a dynamic job and residence index model.

[0007] In an embodiment, the multi-source data fusion module comprises: A coordinate system dynamic conversion module is configured to convert the spatial data of the coordinate system of the multi-source data to a target coordinate system by querying a preset offset parameter database. A space-time alignment module is configured to process the time stamp and spatial position of the received multi-source data by time synchronization and space interpolation to obtain the aligned data.

[0008] In an embodiment, the coordinate system dynamic conversion module comprises: A normalization unit is configured to subtract the corresponding offset of the spatial data of the multiple coordinate systems from different data sources and normalize the spatial data to obtain reference data by querying the preset offset parameter database. A conversion unit is configured to add the offset of the target coordinate system to the coordinates of the reference data to convert to the target coordinate system.

[0009] In an embodiment, the space-time alignment module comprises: receive and parse timestamps and coordinates of the multi-source data, and align the timestamps of the multi-source data to a time interval of the weather data to obtain time-aligned data; perform spatial interpolation calculation on the coordinates of the multi-source data and the POI data to obtain spatial-aligned data; fuse the time-aligned data and the spatial-aligned data to obtain aligned data.

[0010] In an embodiment, the intelligent analysis module includes a dynamic job-housing index calculation module; The dynamic job-housing index calculation module includes: a first data acquisition unit configured to acquire historical commuting data of a target region; a parameter solving unit connected to the first data acquisition unit and configured to solve parameters of a dynamic job-housing index model based on the historical commuting data and a parameter estimation algorithm; a second data acquisition unit configured to acquire real-time meteorological data; a coefficient calculation unit connected to the second data acquisition unit and configured to calculate a dynamic weather influence coefficient based on the real-time meteorological data and a regression model; an index calculation unit connected to the parameter solving unit and the coefficient calculation unit and configured to calculate a weather-adaptive dynamic job-housing index by substituting the parameters and the dynamic weather influence coefficient into a job-housing index mathematical model.

[0011] In an embodiment, the intelligent analysis module includes a semantic compilation module; The semantic compilation module includes: a statement receiving unit configured to receive a natural language query statement input by a user; a semantic analysis unit connected to the statement receiving unit and configured to perform semantic analysis on the natural language query statement, identify and extract semantic constraint conditions; a semantic mapping unit connected to the semantic analysis unit and configured to map the semantic constraint conditions to corresponding spatial data query rules and behavior quantification rules to obtain mapped rules; a statement query unit connected to the semantic mapping unit and configured to generate executable spatial database query statements based on the mapped rules, so as to output corresponding spatial data visualization results through the executable spatial database query statements.

[0012] In an embodiment, the intelligent analysis module includes a decision tree module; The decision tree module includes: a monitoring unit configured to monitor a dynamic job-housing index of a region in real time; a judgment unit connected to the monitoring unit and configured to judge whether the dynamic job-housing index falls into a preset abnormal interval; The judgment type determination unit is connected with the judgment unit, and is configured to determine an abnormal type according to a change mode of the dynamic job-housing index when the abnormality is determined.

[0013] In an embodiment, the judgment type determination unit comprises: The abnormal type determination unit is configured to classify the abnormal type as an external event affected type if the dynamic job-housing index suddenly decreases, and classify the abnormal type as a structural change type if the dynamic job-housing index continuously decreases. The decision unit is connected with the abnormal type determination unit, and is configured to trigger a corresponding early warning signal and execute a predefined decision scheme according to the abnormal type.

[0014] In an embodiment, the system further comprises a spatial data visualization module. The spatial data visualization module comprises: The color blindness friendly rendering unit is configured to receive the standardized data density value, calculate a color value corresponding to the standardized data density value in a color space, and output the color value in an RGB format. The voice interaction module is configured to receive a voice instruction of a user, parse a content of the voice instruction according to a predefined syntax protocol, and execute a corresponding visualization analysis operation through the content.

[0015] In a second aspect, an embodiment of the present application provides a multi-dimensional population data dynamic fusion analysis method, comprising: Receiving multi-source data, and aligning the multi-source data to obtain aligned data. Receiving the aligned data, and generating a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model.

[0016] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement steps of any of the above methods.

[0017] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement steps of any of the above methods.

[0018] In a fifth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement steps of any of the above methods.

[0019] The embodiment of the present application provides a multi-dimensional population data dynamic fusion analysis system and method, which comprises a multi-source data fusion module, a smart analysis module, and a dynamic job-housing index model. BRIEF DESCRIPTION OF DRAWINGS

[0020] The drawings constituting a part of the present application are used to provide a further understanding of the present application, so that other features, objects and advantages of the present application become more apparent. The schematic embodiment drawings of the present application and the description thereof are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 FIG. 1 is a structural schematic diagram of a multi-dimensional population data dynamic fusion analysis system provided by an embodiment of the present application; Figure 2 FIG. 2 is a flow schematic diagram of a multi-dimensional population data dynamic fusion analysis method provided by an embodiment of the present application; Figure 3 FIG. 3 is a schematic diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of protection of the present application.

[0022] The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0023] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined target, and can be implemented entirely or partially by using software, hardware (such as a processing circuit or a memory), or a combination thereof. Similarly, one processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be a part of an integral module or unit that includes the functions of the module or unit.

[0024] It should be understood that, in various embodiments of the present application, the size of the serial number of each process does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0025] It should be understood that, in the present application, "includes" and "has" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] It should be understood that, in the present application, "multiple" means two or more. "And / or" is only a description of the association between the associated objects, which means that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist together, and B exists alone. The character " / " generally represents that the associated objects before and after are in an "or" relationship. "Including A, B and C", "including A, B, C" means that A, B and C are all included, "including A, B or C" means that one of A, B and C is included, "including A, B and / or C" means that any one or any two or three of A, B and C is included.

[0027] It should be understood that, in the present application, "B corresponding to A", "B corresponding to A", "A corresponding to B" or "B corresponding to A" means that B is associated with A, and B can be determined according to A. Determining B according to A does not mean that B is determined only according to A, but also can be determined according to A and / or other information. The matching between A and B means that the similarity between A and B is greater than or equal to a preset threshold.

[0028] Depending on the context, "if" as used herein can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting".

[0029] The data involved in the present application can be authorized by the tested personnel or fully authorized by all parties, and the collection, transmission, use, etc. of the data meet the requirements of relevant laws, regulations and standards of relevant countries and regions. The embodiments / examples of the present application can be combined with each other.

[0030] The technical solutions of the present application will be described in detail below with specific examples. The following specific examples can be combined with each other, and the same or similar concepts or processes can not be described in detail in some examples.

[0031] Please refer to Figure 1 , Figure 1 A structural schematic diagram of a multi-dimensional population data dynamic fusion analysis system provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the system includes: Figure 1 A multi-source data fusion module, configured to receive multi-source data and align the multi-source data to obtain aligned data; An intelligent analysis module, connected with the multi-source data fusion module, configured to receive the aligned data and generate a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model.

[0032] Specifically, taking the optimization of bus scheduling during morning and evening peak hours (in the Zhongguancun area of Beijing) as an example, Mobile phone signaling data from China Mobile, including user location, timestamp, and mobile trajectory, POI data from Gaode Map, marking office buildings, residential areas, bus stops, and weather data from the meteorological bureau API, including rainfall, visibility, etc. are taken as input data, i.e. multi-source data.

[0033] Then, the multi-source data is aligned, including coordinate system alignment, i.e. converting all data to the WGS84 coordinate system to ensure spatial consistency, time alignment, i.e. time interpolation of mobile phone signaling data based on whole-minute time, synchronization with weather data, and spatial alignment, i.e. gridding of signaling data (500m×500m) and spatial correlation with POI points. The output is a set of aligned structured data, including the number of people in each grid, POI types, weather conditions, etc.

[0034] Then, the dynamic job-housing index model (D-J Index Pro) is used to identify the job-housing flow trend in the Zhongguancun area during morning and evening peak hours. It is detected that the R_dj index in the software park area is lower than 0.5 during the evening peak, indicating that there are many stranded populations and insufficient transport capacity, and the weather data (such as rainfall) is further confirmed to reduce commuting efficiency.

[0035] Finally, the output scheme is output, such as suggesting the addition of a bus line, the increase of the existing bus frequency, the increase of 200% during the evening peak, etc. ​

[0036] In an embodiment, the multi-source data fusion module comprises: a coordinate system dynamic conversion module for converting the spatial data of the coordinate system of the multi-source data to a target coordinate system by querying a preset offset parameter database; and a space-time alignment module for processing the timestamps and spatial positions of the received multi-source data through time synchronization and space interpolation to obtain aligned data.

[0037] The coordinate system dynamic conversion module comprises: a normalization unit for subtracting corresponding offsets from the spatial data of multiple coordinate systems from different data sources and normalizing to obtain reference data by querying a preset offset parameter database; and a conversion unit for converting the coordinates of the reference data by adding the offsets of the target coordinate system to convert to the target coordinate system.

[0038] The space-time alignment module comprises: receiving and analyzing the timestamps and coordinates of the multi-source data, aligning the timestamps of the multi-source data to the time interval of the weather data to obtain time-aligned data; performing space interpolation calculation on the coordinates of the multi-source data and the POI data to obtain spatially aligned data; and fusing the time-aligned data and the spatially aligned data to obtain the aligned data.

[0039] Specifically, a certain city traffic management center needs to integrate online car trajectory data (GCJ02 coordinate system), municipal road network data (CGCS2000 coordinate system), and real-time weather event data (WGS84 coordinate system) to analyze the impact of rain on urban traffic. All data need to be fused and aligned to the CGCS2000 coordinate system and unified analysis is performed with a 5-minute time window.

[0040] First, input the online car trajectory data (GCJ02 coordinate system): including vehicle ID, latitude and longitude (116.4080, 39.9042), speed, direction, timestamp, municipal road network data (CGCS2000 coordinate system): including road ID, geometric shape, traffic flow, and weather data (WGS84 coordinate system): including area ID, weather state (heavy rain), visibility, and timestamp.

[0041] Then, perform normalization processing: read the preset offset parameter database. For example, it is learned by querying that the latitude offset of the GCJ02 coordinate system is +0.0060 and the longitude offset is +0.0065. Normalize the online car trajectory point: subtract the longitude offset and latitude offset from the original coordinates (116.4080, 39.9042) respectively to obtain the WGS84 reference coordinates (116.4015, 39.8982).

[0042] Afterwards, the target coordinate system is CGCS2000. Query the database to obtain the offset (e.g., latitude + 0.0001, longitude + 0.0001) relative to WGS84. Add the normalized WGS84 reference coordinate (116.4015, 39.8982) to the target offset to obtain the final target coordinate system coordinate (116.4016, 39.8983). Output all spatial data unified to the CGCS2000 coordinate system.

[0043] The ride-hailing trajectory data, road network data, and weather data that have completed coordinate system conversion are first time-aligned: the timestamp of the weather data is the whole point (e.g., 2024-07-18T17: 00: 00Z), while the timestamp of the trajectory data is continuous (e.g., 2024-07-18T17: 03: 21Z).

[0044] The time-space alignment module takes the time interval (17: 00-17: 05) of the weather data as the reference window. All trajectory data points within this 5-minute period (e.g., 17: 01: 10, 17: 03: 21, 17: 04: 55) are attributed to this time window, and the unified time is marked as 2024-07-18T17: 00: 00Z.

[0045] The system spatially correlates (spatially interpolates) the converted trajectory point (116.4016, 39.8983) with the road network data. Through calculation, it is determined that the trajectory point is located on the "North Third Ring Road" and contributes the attribute (e.g., speed) of the point to the current traffic state calculation of the road. At the same time, according to the coordinates of the trajectory point, it is matched with the "heavy rain" area in the weather data, and the weather label of "heavy rain" is marked for the data point.

[0046] Finally, the time-aligned data (unified time window) and the spatially aligned data (associated with specific roads and weather areas) are fused to output the aligned data.

[0047] In an embodiment, the intelligent analysis module includes a dynamic job-housing index calculation module; The dynamic job-housing index calculation module includes: A first data acquisition unit for acquiring historical commuting data of a target area; A parameter solving unit connected to the first data acquisition unit, configured to solve the parameters of the dynamic job-housing index model based on the historical commuting data and a parameter estimation algorithm; A second data acquisition unit for acquiring real-time meteorological data; A coefficient calculation unit connected to the second data acquisition unit, configured to calculate the dynamic weather influence coefficient based on the real-time meteorological data and a regression model; An index calculation unit, connected with the parameter solving unit and the coefficient calculation unit, is configured to substitute the parameters and the dynamic weather influence coefficient into the job-housing index mathematical model to calculate a weather-adaptive dynamic job-housing index.

[0048] Specifically, assume that a traffic operation department of a certain large city wants to establish a system that can dynamically reflect real commuting demand, especially in heavy rain, to predict the job-housing distribution change in the evening peak in advance, so as to optimize bus scheduling and avoid large-scale commuting congestion.

[0049] The first data acquisition unit obtains historical commuting data of the evening peak (17:00-19:00) on weekdays in the past 6 months from the city traffic data center, including millions of anonymized commuting records such as commuting start and end points (grid coordinates), commuting mode (bus, subway, self-driving), and commuting time.

[0050] After receiving the historical commuting data, the parameter solving unit uses a parameter estimation algorithm to solve the core parameters of the dynamic job-housing index model. The algorithm analyzes the patterns in the commuting data, for example, it is found that residents are highly sensitive to commuting time when choosing a commuting mode. Through calculation, the key parameter values representing “commuting resistance” and “destination attractiveness” in the model are determined. A set of calibrated baseline model parameters suitable for the commuting rules of the city are output.

[0051] The second data acquisition unit, on a certain weekday in the afternoon, obtains the latest weather data by accessing the real-time API of the meteorological bureau. It shows that there is a strong convective cloud cluster over the city, and it is expected that there will be persistent heavy rain during the evening peak (17:00-19:00), and the expected rainfall will reach 30 mm / h, and the visibility will drop to below 2 km.

[0052] The coefficient calculation unit inputs the “heavy rain” and “low visibility” data obtained in real time into a pre-trained regression model. The regression model is trained according to the correlation between “weather conditions” and “actual commuting behavior changes” in historical data. After model analysis, it is concluded that such intensity of rainfall will significantly increase the willingness of residents to take public transportation, while reducing the willingness to drive, and the overall commuting efficiency will decrease. A quantitative dynamic weather influence coefficient (for example, Γ = 0.75) is calculated. This coefficient less than 1 means that weather factors will have a significant negative impact on normal commuting in the evening peak.

[0053] The index calculation unit substitutes the reference model parameters and the dynamic weather influence coefficient into the job-housing index mathematical model for comprehensive calculation. The model comprehensively considers the reference commuting rule and the negative influence of weather, and simulates and calculates the dynamic job-housing index of each region in the city at the beginning of the evening peak (17:00). A dynamic job-housing index distribution map of the whole city is generated. The map clearly shows that, due to the rainfall, the predicted value of the index of the central business district (CBD) is only 0.32 (far lower than the normal sunny day of 0.6 or above), which indicates that a large number of off-duty personnel will be stranded due to the inconvenience of transportation and cannot leave the workplace in time.

[0054] In an embodiment, the intelligent analysis module includes a semantic compiling module; The semantic compiling module includes: A sentence receiving unit configured to receive a natural language query sentence input by a user; A semantic analysis unit connected with the sentence receiving unit and configured to perform semantic analysis on the natural language query sentence, identify and extract semantic constraint conditions; A semantic mapping unit connected with the semantic analysis unit and configured to map the semantic constraint conditions to corresponding spatial data query rules and behavior quantification rules to obtain mapped rules; A sentence query unit connected with the semantic mapping unit and configured to generate executable spatial database query statements based on the mapped rules, and output corresponding spatial data visualization results through the executable spatial database query statements.

[0055] Specifically, a high-end chain fitness brand plans to open a new store in a certain large city. The market team is not a GIS expert, but they want to use the system to quickly find the area that best meets the distribution of their target customer group. They input a simple natural language query to the system.

[0056] The market analyst inputs the following natural language query statement in the search box of the system: "Find the area where high-income women aged 25 to 40 who often exercise are concentrated in the city center." The semantic analysis unit performs word segmentation, part-of-speech tagging, and semantic role labeling on the input sentence, and identifies the key limiting conditions. The following structured semantic constraint conditions are parsed: spatial range constraint: city center (built-in or further defined geographic range in the system), population attribute constraint: age: 25 to 40, gender: female, income level: high (the system needs to quantify it to a specific value, such as "monthly income > 20000 yuan"), behavior characteristic constraint: exercise habit: often (the system needs to quantify it to a specific frequency, such as "exercising ≥ 2 times per week").

[0057] The semantic mapping unit maps the abstract semantic conditions extracted in the previous step to specific fields and calculation rules in the system database, generating the following mapped rules: Spatial data query rule: Map "city center" to WHERE district IN ('Tianhe District', 'Yuexiu District', 'Haizhu District').

[0058] Behavioral quantification rule: Quantification of "frequent gym visits": WHERE fitness_visit_count >= 8 (Assume system definition: In the past month, stay in a POI category "gym" within a 500-meter range for more than 1 hour, count as 1 valid visit. 8 times means "more than 2 times a week").

[0059] Quantification of "high income": WHERE average_monthly_consumption>20000 (Label user consumption data by cooperating with a commercial data platform).

[0060] The statement query unit combines all the above rules to automatically generate a complete and immediately executable spatial database query statement. The generated query logic: Select all residential grids located in the specified area of the city center, and meet (age 25-40, female, monthly consumption more than 20,000, and gym visit times more than 8 times in the past month). The system executes this query to find all grid units that meet the conditions from the population grid database.

[0061] The execution result of the statement query unit is not a dry data table, but a direct generation of a spatial visualization result.

[0062] Form of expression: In the electronic map on the system interface, the grid units that meet the conditions are rendered into a deep red heat map.

[0063] Analysis conclusion: The map clearly shows 3 core hotspots: large high-end residential areas adjacent to the financial city, newly built apartment buildings around the famous creative industry park, and bustling areas near large shopping centers in the city center.

[0064] Business decision: The marketing team does not need to understand complex SQL or GIS operations, but can intuitively see the distribution of target customers through a natural language sentence.

[0065] Final decision: Prioritize finding shops in the financial city residential area with the most concentrated heat, and layout targeted marketing ads at the center of the above three hotspots.

[0066] In an embodiment, the intelligent analysis module includes a decision tree module; The decision tree module includes: a monitoring unit for real-time monitoring of the dynamic job-housing index of the region; A judging unit, connected with the monitoring unit, is configured to judge whether the dynamic job-housing index falls into a preset abnormal interval; A judging type determining unit, connected with the judging unit, is configured to determine an abnormal type according to a change mode of the dynamic job-housing index when the abnormality is determined.

[0067] In an embodiment, the judging type determining unit comprises: An abnormal type determining unit is configured to classify the abnormal type as an external event influenced type if the dynamic job-housing index has a sudden drop, and classify the abnormal type as a structural change type if the dynamic job-housing index has a sustained drop; A decision unit, connected with the abnormal type determining unit, is configured to trigger a corresponding early warning signal and execute a predefined decision scheme according to the abnormal type.

[0068] Specifically, a certain large city operation and management center uses the system to monitor the job-housing balance of the whole city in real time. The core function of the decision tree module is to act as a "digital sentry" and stand guard 7x24 hours. Once an abnormal job-housing index is found, the module automatically determines the nature of the situation and starts the corresponding response scheme to ensure the smooth operation of the city.

[0069] The monitoring unit obtains the whole region index data generated by the dynamic job-housing index calculation module every 5 minutes. The index values of key regions such as transportation hubs, core business districts, and large residential areas are focused on.

[0070] The judging unit compares the real-time monitored index value with the preset abnormal interval. The preset rule is that the system sets the normal threshold of the core business district index in the evening peak (18:00) on weekdays to be higher than 0.5. If the index is lower than 0.4, it is determined to be "abnormal"; if it is lower than 0.3, it is determined to be "serious abnormality".

[0071] Scenario A: sudden drop (external event influenced type), event: at 18:05 on Wednesday evening, the monitoring unit found that a major subway transfer station in the city suddenly failed, causing the line to be out of service. The dynamic job-housing index around the hub dropped from 0.55 to 0.25 within 15 minutes.

[0072] Abnormal type determining unit analysis: the index presents a sudden and cliff-like drop. This mode is consistent with the characteristics caused by external events such as sudden traffic paralysis. The unit classifies it as an external event influenced type of abnormality.

[0073] The decision unit automatically triggers the predefined different decision schemes according to the determined abnormal type.

[0074] For scenario A (external event influenced type): Trigger early warning signal: send a red level early warning to the municipal transportation commission, subway operating company, and traffic police command center, indicating "a large-scale commuter congestion has occurred in XX hub."

[0075] Execute pre-decision plan: Bus dispatch: automatically generate and issue instructions to urgently dispatch 50 standby buses to the hub to open a temporary bus evacuation line.

[0076] Traffic control: notify the traffic police platform to implement temporary traffic control on the roads around the hub to ensure the priority of bus vehicles.

[0077] Information release: push early warning and alternative travel plan through public App and social media.

[0078] Objective: rapid response, relieve acute congestion, and guide the crowd.

[0079] In an embodiment, the system further comprises a spatial data visualization module; The spatial data visualization module comprises: A color-blind friendly rendering unit for receiving the standardized data density values and calculating the color values corresponding to the standardized data density values in the color space, outputting the color values in RGB format; A voice interaction module for receiving the user's voice instructions, parsing the content of the voice instructions according to the predefined syntax protocol, and executing the corresponding visualization analysis operation through the content.

[0080] Specifically, in a heavy rain weather, officials of the municipal emergency command center need to quickly grasp the waterlogging situation and population gathering risk in low-lying areas of the city. The officials need to obtain key information efficiently and barrier-free through visualization and voice interaction.

[0081] The color-blind friendly rendering unit inputs the population gathering risk density values of each grid calculated by the system intelligent analysis module and standardizes them to floating-point numbers between 0 and 1 (where 1 represents the highest risk). The unit receives these standardized density values, and for each density value, the unit does not directly select red in the traditional RGB color space, but calculates in the CIE Lab color space. For low-risk areas (density value ~0.2): the unit calculates a bright light blue-green color. This color has a high brightness (L value), and the hue contains both blue and green (a is negative, b is negative), which is in sharp contrast to high-risk colors. For high-risk areas (density value ~0.9): the unit calculates a deep dark blue color. Its brightness (L value) is very low, and the hue is biased towards pure blue (b value is strongly negative), avoiding the use of red.

[0082] The final calculated RGB color value is output and sent to the graphics rendering engine.

[0083] Visualization: On the city map, safe areas are displayed as a striking light blue-green, while high-risk flooded areas are displayed as a strong dark blue, with a smooth blue-green gradient between the two.

[0084] When an official needed to quickly compare the situation in different areas, he didn't need to manually operate the mouse and keyboard. He simply spoke into the system microphone and gave the voice command: "System, compare and analyze the population density changes in the West Bus Station and University Town areas over the past hour." The voice interaction module receives an audio stream and converts it into text using a speech recognition engine. The module then parses the text according to a predefined syntax protocol. action( <action>) : The core verb is identified as "compare".

[0085] Target ( <target>) : identified that the target is "population density change".

[0086] filter ( <filter>) : the area condition is identified as "West City Bus Station" and "University City Area", and the time condition is "past one hour".

[0087] The module converts this parsing result into executable commands inside the system, and the system automatically performs the following operations: retrieves historical population density data of "West City Bus Station" and "University City Area" in the past one hour from the database. Calls the color-blind friendly rendering unit to generate time series dynamic heat maps for the two areas respectively. Displays the dynamic contrast visualization view of the two areas side by side on the command large screen, and displays the density change trend in the form of a line chart.

[0088] The embodiment of the present application provides a multi-dimensional population data dynamic fusion analysis system, comprising: a multi-source data fusion module, configured to receive multi-source data, and align the multi-source data to obtain aligned data; and an intelligent analysis module, connected with the multi-source data fusion module, configured to receive the aligned data, and generate a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model. The present application can improve the analysis accuracy and effect.

[0089] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0090] The following is a device embodiment of the present application, and for details not described in detail, reference can be made to the corresponding method embodiments described above.

[0091] Figure 2 A flowchart of a multi-dimensional population data dynamic fusion analysis method provided by an embodiment of the present application is shown, comprising: S201: receiving multi-source data, and aligning the multi-source data to obtain aligned data; S202: receiving the aligned data, and generating a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model.

[0092] The embodiment of the present application provides a multi-dimensional population data dynamic fusion analysis method, comprising: a multi-source data fusion module receiving multi-source data, and aligning the multi-source data to obtain aligned data; and an intelligent analysis module receiving the aligned data, and generating a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model. The present application can improve the analysis accuracy and effect.

[0093] The present application Figure 3 A schematic diagram of a computer device is provided. As shown in Figure 3 As shown, the computer device 3 of this embodiment includes a processor 301, a memory 302, and a computer program 303 stored in the memory 302 and executable on the processor 301. The processor 301 implements the steps in each of the above multi-dimensional population data dynamic fusion analysis method embodiments when executing the computer program 303, for example Figure 2 As shown, the steps 201 to 202.

[0094] The present application also provides a readable storage medium, and the readable storage medium stores a computer program. The computer program is executed by a processor to implement the multi-dimensional population data dynamic fusion analysis method provided by the various embodiments.

[0095] The readable storage medium can be a computer storage medium or a communication medium. The communication medium includes any medium that facilitates the transfer of a computer program from one place to another. The computer storage medium can be any available medium that can be accessed by a general or special purpose computer. For example, the readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). In addition, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0096] The present application also provides a program product, and the program product includes execution instructions stored in a readable storage medium. At least one processor of a device can read the execution instructions from the readable storage medium, and the at least one processor executes the execution instructions to make the device implement the multi-dimensional population data dynamic fusion analysis method provided by the various embodiments.

[0097] In the embodiments of the above apparatus, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the present application can be directly embodied as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0098] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit the technical solutions; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing embodiments can still be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.< / filter> < / target> < / action>

Claims

1. A multi-dimensional population data dynamic fusion analysis system, characterized in that, The application relates to a public transport intelligent scheduling system. The system comprises: a multi-source data fusion module for receiving multi-source data and aligning the multi-source data to obtain aligned data; 2. The multi-dimensional population data dynamic fusion analysis system of claim 1, wherein, an intelligent analysis module connected with the multi-source data fusion module, for receiving the aligned data and generating a public transport scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model. The multi-source data fusion module comprises: a coordinate system dynamic conversion module for converting spatial data of a coordinate system of the multi-source data to a target coordinate system by querying a preset offset parameter database; 3. The multi-dimensional population data dynamic fusion analysis system of claim 2, wherein, a time-space alignment module for processing a timestamp and a spatial position of the multi-source data received by time synchronization and spatial interpolation to obtain the aligned data. The coordinate system dynamic conversion module comprises: a normalization unit for subtracting corresponding offsets of spatial data of multiple coordinate systems from different data sources and normalizing the spatial data to obtain reference data by querying the preset offset parameter database; 4. The multi-dimensional population data dynamic fusion analysis system of claim 2, wherein, a conversion unit for adding offsets of the target coordinate system to coordinates of the reference data to convert to the target coordinate system. The time-space alignment module comprises: a unit for receiving and analyzing the timestamp and the coordinates of the multi-source data, aligning the timestamp of the multi-source data to a time interval of weather data to obtain time-aligned data; a unit for performing spatial interpolation calculation on the coordinates of the multi-source data and POI data to obtain spatial-aligned data; 5. The multi-dimensional population data dynamic fusion analysis system of claim 1, wherein, a unit for fusing the time-aligned data and the spatial-aligned data to obtain the aligned data. The intelligent analysis module comprises a dynamic job-housing index calculation module. The dynamic job-housing index calculation module comprises: a first data acquisition unit for acquiring historical commuting data of a target area; a parameter solving unit connected with the first data acquisition unit, for solving parameters of the dynamic job-housing index model based on the historical commuting data and a parameter estimation algorithm; a second data acquisition unit for acquiring real-time meteorological data; a coefficient calculation unit connected with the second data acquisition unit, for calculating a dynamic weather influence coefficient based on the real-time meteorological data and a regression model; 6. The multi-dimensional population data dynamic fusion analysis system of claim 1, wherein, an index calculation unit connected with the parameter solving unit and the coefficient calculation unit, for substituting the parameters and the dynamic weather influence coefficient into a job-housing index mathematical model to calculate a weather-adaptive dynamic job-housing index. The intelligent analysis module comprises a semantic compilation module. The semantic compilation module comprises: a sentence receiving unit for receiving a natural language query sentence input by a user; a semantic analysis unit connected with the sentence receiving unit, for performing semantic analysis on the natural language query sentence, identifying and extracting semantic constraint conditions; a semantic mapping unit connected with the semantic analysis unit, for mapping the semantic constraint conditions into corresponding spatial data query rules and behavior quantization rules to obtain mapped rules; 7. The multi-dimensional population data dynamic fusion analysis system of claim 1, wherein, a sentence query unit connected with the semantic mapping unit, for generating an executable spatial database query sentence based on the mapped rules, and outputting corresponding spatial data visualization results through the executable spatial database query sentence. The intelligent analysis module comprises a decision tree module. The decision tree module comprises: a monitoring unit configured to monitor a dynamic job-housing index of a region in real time; a judging unit connected to the monitoring unit and configured to determine whether the dynamic job-housing index falls into a preset abnormal interval; a judging type determining unit connected to the judging unit and configured to determine an abnormal type according to a change mode of the dynamic job-housing index when the dynamic job-housing index is determined to be abnormal.

8. The multi-dimensional population data dynamic fusion analysis system of claim 7, wherein, The judging type determining unit comprises: an abnormal type determining unit configured to classify the abnormal type as an external event affected type if the dynamic job-housing index suddenly decreases, and classify the abnormal type as a structural change type if the dynamic job-housing index continuously decreases; a decision unit connected to the abnormal type determining unit and configured to trigger a corresponding early warning signal and execute a predefined decision scheme according to the abnormal type.

9. The multi-dimensional population data dynamic fusion analysis system of claim 1, wherein, The system further comprises a spatial data visualization module; The spatial data visualization module comprises: a color blindness friendly rendering unit configured to receive a standardized data density value, calculate a color value corresponding to the standardized data density value in a color space, and output an RGB format color value; a voice interaction module configured to receive a voice instruction of a user, parse a content of the voice instruction according to a predefined syntax protocol, and execute a corresponding visualization analysis operation through the content.

10. A multi-dimensional population data dynamic fusion analysis method, characterized in that, comprise: receiving multi-source data, and aligning the multi-source data to obtain aligned data; receiving the aligned data, and generating a bus scheduling or path optimization scheme based on the aligned data and a dynamic job-housing index model.

Images