CN116187864A - Passenger transport service analysis and scheduling method, system and management and control platform - Google Patents

Abstract

The invention relates to the field of passenger service, in particular to a passenger service analysis and scheduling method, a system and a management and control platform, which are used for acquiring and preprocessing data information of passenger service to obtain a passenger service data center, synthesizing and carding evaluation factors of the passenger service by a fuzzy evaluation method according to the data information and the data center, setting calculation logic and reference values to obtain a passenger service model, constructing a passenger service analysis and scheduling system by combining the data information, acquiring a demand plan and a current task of the passenger service, processing nodes in a flow, and re-calculating by combining the passenger service analysis and scheduling system to obtain a scheduling result conforming to the passenger station data information.

Description

Passenger transport service analysis and scheduling method, system and management and control platform

Technical Field

The invention relates to the technical field of passenger transport service management and control, in particular to a passenger transport service analysis and scheduling method, a passenger transport service analysis and scheduling system and a passenger transport service management and control platform.

Background

The passenger stations are used as the most critical connection parts in the traffic network, and the effective monitoring and management of the passenger stations is the basis of the whole traffic transportation.

At present, passenger station systems and devices are more, and an automatic system is isolated. Each passenger station cannot master the real-time running situation of the passenger station in all aspects, and cannot sense the passenger flow, the equipment state, the environment of the passenger station, the emergency and the like in real time. In the face of increasing passenger traffic, equipment and system faults frequently occur, and emergency events are increased; the manager lacks intelligent technical means and cannot sense the occurrence of various emergencies in advance, so that the manager is not in charge of being faced with the emergencies.

Disclosure of Invention

Accordingly, the present invention is directed to a passenger service analysis and scheduling method, system and management and control platform, so as to solve the problem that in the prior art, due to the lack of an intelligent technical means, a manager of a passenger station cannot timely sense an emergency, so that the manager is not engaged in the emergency.

According to a first aspect of an embodiment of the present invention, there is provided a passenger transport service analysis and scheduling method, including:

Acquiring data information of passenger transport services;

preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information into a data center of a passenger transport service;

synthesizing the evaluation factors of the passenger service by adopting a fuzzy evaluation method according to the data information and the data of the data center, and combing the synthesized evaluation factors;

setting calculation logic and a reference value according to the carded evaluation factors to obtain a passenger transport service model;

constructing a passenger service analysis and scheduling system according to the data information and the passenger service model;

and acquiring a demand plan of the current passenger service and a processing node of the current task in the flow, and carrying out recalculation by combining a passenger service analysis and scheduling system to obtain a scheduling result which accords with passenger station data information.

Preferably, the data information includes: personnel information, equipment information, environment information, operation information, early warning information, ticket information and passenger transport information;

wherein the personnel information includes: passenger station personnel information, service personnel information, and people stream information.

Preferably, the preprocessing the data information to obtain preprocessed data information includes:

And carrying out data cleaning comparison on the data of the personnel information, the equipment information, the environment information, the operation information, the early warning information, the ticket information and the passenger information, and storing preset rules to obtain the preprocessed data information.

Preferably, the step of performing data cleaning and comparison on the data of the personnel information, the equipment information, the environment information, the operation information, the early warning information, the ticket information and the passenger information and storing a preset rule to obtain preprocessed data information specifically includes:

performing error correction, repeated item deletion, unified specification, correction logic, conversion structure, data compression, incomplete/empty value complement and discarded data/variable cleaning on the personnel information, equipment information, environment information, operation information, early warning information, ticket information and passenger information, and performing preset rule storage on the cleaned data to obtain processed data information; wherein, the storing of the preset rule includes: and (5) storing in a classification way.

Preferably, after the passenger service model is obtained, the method further comprises:

performing strong characteristic intelligent pairing on the evaluation factors according to the passenger service work requirements, and processing the evaluation factors by adopting a natural language processing method to obtain examination rules conforming to the passenger service work requirements;

And quantifying the examination rules into the passenger transport service model to obtain the passenger transport service model conforming to the examination rules.

Preferably, the natural language processing method includes:

the method comprises the steps of corpus acquisition, data preprocessing, feature engineering, feature selection, model training, model evaluation and production online.

Preferably, the system for analyzing and scheduling the passenger transport service is constructed according to the data information and the passenger transport service model, and specifically comprises the following steps:

and selecting camera people flow information, intelligent equipment information and service personnel positioning information as key elements, and selecting 12306 system information and personnel basic information as general elements according to the data information and the passenger transport service model to construct a passenger transport service analysis and scheduling system.

Preferably, the acquiring the data information of the passenger transport service includes:

a camera is adopted to acquire people flow information of a passenger station and personnel information of the passenger station;

and acquiring equipment information, environment information, operation information and early warning information of the passenger station according to the networking system/device.

According to a second aspect of an embodiment of the present invention, there is provided a passenger service analysis and scheduling system, comprising:

the acquisition module is used for acquiring data information of the passenger transport service;

The preprocessing module is used for preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information into a data center of the passenger transport service;

the synthesizing module is used for synthesizing the evaluation factors of the passenger service by adopting a fuzzy evaluation method according to the data information and the data of the data center, and combing the synthesized evaluation factors;

the calculation module is used for setting calculation logic and a reference value according to the carded evaluation factors to obtain a passenger transport service model;

the construction module is used for constructing a passenger transport service analysis and scheduling system according to the data information and the passenger transport service model;

and the recalculation module is used for acquiring a demand plan of the current passenger transport service and a processing node of the current task in the flow, and recalculating the data by combining a passenger transport service analysis and scheduling system to obtain a scheduling result which accords with the passenger transport station data information.

According to a third aspect of an embodiment of the present invention, there is provided a passenger service management and control platform, including:

the device comprises a communication module, a processor and a memory, wherein the memory stores program instructions;

the processor is configured to execute the program instructions stored in the memory and perform the method described above.

The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:

the invention adopts an intelligent processing means to construct a data center and a passenger service model, combines the processing nodes in the flow according to the demand plan and the current task of the passenger service to obtain the scheduling result according to the passenger station data information, obtains the scheduling result according to the passenger station data information by combining the processing nodes in the flow of the passenger service, and can early warn whether an emergency occurs or not when carrying out data analysis.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

FIG. 1 is a flow chart illustrating a method of passenger service analysis and scheduling according to an exemplary embodiment;

FIG. 2 is a diagram illustrating an automatic conversion relationship between 8 basic types, according to an example embodiment;

FIG. 3 is a schematic block diagram of a passenger service analysis and dispatch system, as shown in an exemplary embodiment.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.

Example 1

Referring to fig. 1, fig. 1 is a flowchart illustrating a passenger service analysis and scheduling method according to an exemplary embodiment, as shown in fig. 1, the method includes:

Step S01, acquiring data information of passenger transport services;

step S02, preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information into a data center of a passenger transport service;

s03, synthesizing the evaluation factors of the passenger service by adopting a fuzzy evaluation method according to the data information and the data of the data center, and combing the synthesized evaluation factors;

step S04, setting calculation logic and a reference value according to the carded evaluation factors to obtain a passenger transport service model;

s05, constructing a passenger transport service analysis and scheduling system according to the data information and the passenger transport service model;

step S06, obtaining a demand plan of the current passenger transport service and a processing node of the current task in the flow, and carrying out recalculation by combining a passenger transport service analysis and dispatch system to obtain a dispatch result which accords with passenger transport station data information.

It should be noted that, application scenarios applicable to the technical solution provided in this embodiment include, but are not limited to: passenger service places such as railway stations, automobile stations and the like.

It should be noted that the passenger service model includes a plurality of independent systems, for example: public toilet health system, personnel density system, waiting room temperature, humidity system, elevator operation system, etc. in passenger service. Wherein each system corresponds to a corresponding service model, collectively referred to as a passenger service model.

It can be appreciated that, in the technical solution provided in this embodiment, by acquiring data information of a passenger service and performing preprocessing, a data center of the passenger service is obtained, according to the data of the data information and the data center, a fuzzy evaluation method is adopted to synthesize evaluation factors of the passenger service, and the synthesized evaluation factors are combed, according to the combed evaluation factors, calculation logic and reference values are set, a passenger service model is obtained, and a passenger service analysis and scheduling system is constructed in combination with the data information, a processing node of a current passenger service requirement plan and a current task in a process is acquired, and a passenger service analysis and scheduling system is combined to perform recalculation, so as to obtain a scheduling result conforming to passenger station data information.

In specific practice, the data information includes: personnel information, equipment information, environment information, operation information, early warning information, ticket information and passenger transport information;

Wherein the personnel information includes: referring to table 1, table 1 is a classification and content of data information.

TABLE 1 classification and content of data information

/>

In specific practice, the "acquiring data information of the passenger transport service" in step S11 may have a plurality of implementation manners, where one implementation manner may be:

1. a camera is adopted to acquire people flow information of a passenger station and personnel information of the passenger station;

2. and acquiring equipment information, environment information, operation information and early warning information of the passenger station according to the networking system/device.

In specific practice, in step S12, "preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information in a data center of a passenger service" may have multiple implementation manners, where one implementation manner may be:

and carrying out data cleaning comparison on the personnel information, the equipment information, the environment information, the operation information, the early warning information, the ticket information and the passenger information, storing preset rules to obtain preprocessed data information, and storing the preprocessed data information into a passenger service data center.

It should be noted that, the data cleaning and comparison are performed by using related techniques, such as: mathematical statistics, data mining, or predefined cleaning rules translate dirty data into data that meets data quality requirements. For example: personnel information only needs to acquire information related to passenger transport services such as personnel identity information, working time, working track, occupation and the like, and the following steps are filtered: height, weight, etc. information not related to passenger traffic services.

The data cleaning comparison mainly comprises the following steps: error correction, duplicate term deletion, unified specification, correction logic, conversion structure, data compression, incomplete/null value complement and data/variable discarding cleaning, and storing the cleaned data in a preset rule to obtain processed data information, and storing the preprocessed data information in a data center of passenger transport service; for example: passenger station personnel information and service personnel information of personnel information are integrated and stored in the same data table, and people flow information is stored in another data table for classified storage.

Wherein, the storing of the preset rule includes: and (5) storing in a classification way.

It should be noted that, the storage of the preset rule may be a storage mode which is desired to be implemented by a user, such as classified storage, storage according to information content, and the like.

It should be noted that the number of the substrates,

1. correcting errors

Erroneous data is a type of problem that often occurs in the context of data sources. The form of the data error includes:

(1) Data value errors: the data is directly erroneous, e.g., exceeds a fixed set of domains, exceeds extrema, misspellings, property errors, source errors, etc.

(2) Data type errors: the storage type of the data does not conform to the actual situation, such as numerical storage of the date type of the passenger service, storage of the time stamp as a character string, and the like.

(3) Data coding errors: coding errors for data storage, for example: UTF-8 was written as UTF-80.

(4) Data format errors: data storage format problems such as half-angle full-angle characters, chinese-English characters and the like.

(5) Data anomaly errors: the numerical data is input into full-angle numerical characters, a carriage return operation is arranged behind the character string data, the date crosses the boundary, and invisible characters are arranged in front of and behind the data.

(6) Dependency conflict: some data fields store dependencies, such as: the passenger station staff and the job number should meet the corresponding relation, but there may be a problem that the two are not matched.

(7) Multi-value errors: in most cases, each field stores a single value, but there are also cases where one field stores multiple values, some of which may not be in compliance with the actual business rules.

2. Deleting duplicate items

For various reasons, duplicate records or duplicate fields (columns) may be present in the data, requiring deduplication processing for these duplicate items (rows and columns). The basic idea is "sorting and merging", i.e. sorting and computing the similarity.

Common ordering algorithms: insert ordering, bubble ordering, select ordering, fast ordering, heap ordering, merge ordering, radix ordering, hill ordering.

Common algorithm for judging similarity: the basic field matching algorithm normalizes Euclidean distance, hamming distance, included angle cosine, jacquard distance, mahalanobis distance, manhattan distance, minkowski distance, euclidean distance, chebyshev distance, correlation coefficient, information entropy. For repeated data items, service confirmation and arrangement are needed to be carried out as much as possible to extract rules. In the cleaning conversion stage, deletion decisions are not made as easily as possible for repeated data items, and particularly important or business-significant data cannot be filtered out, so that the work of checking and repeated confirmation is indispensable.

For example: the job numbers of the collected 3 workers at the passenger station are 10139, 10138 and 10139, the names are Zhang san, the roles are cleaning staff, ticket vending staff and blank values, the three elements are processed by adopting an bubbling sequencing algorithm, and the three elements are 10138-Zhang san-ticket vending staff and 10139-Zhang san-cleaning staff after sequencing. The output result through the basic field matching algorithm is: 10138-Zhang San-Ticket vendor, 10139-Zhang San-cleaning agent. The 10139-Zhang Sanzhang-value is deleted, and the data of the job item with business significance is reserved.

3. Unified specification

Because the data source system is scattered in each service line, the requirements, understanding and specifications of different service lines on data are different, and the description specifications of the same data object are completely different, the data specifications are required to be unified and the consistent content is abstracted in the cleaning process.

The rules of the data fields may be generally unified from several aspects:

(1) The names should first be consistent for the same data object. For example: for this field of people stream information, possible names include: passenger flow volume, passenger flow density, personnel information, etc.

(2) Type (2): the data types of the same data object must be uniform and the representation methods are uniform. For example, the type of shift date of the passenger station and the type of timestamp of the passenger flow need to be distinguished.

(3) Units: for numeric fields, units need to be uniform. For example: tens of thousands, hundreds of thousands, millions, etc. of units measure.

(4) Format: under the same type, different representation formats may also produce differences. For example, the date of the surveillance video, the date of the server, the date of the computer, and the date format abbreviations for the dates on the smart device are all different.

(5) Length: the same field length must be consistent.

(6) Decimal place number: decimal digits are particularly important for numeric fields, and particularly when the data size is large, a large deviation occurs due to the difference in the number of digits.

(7) The counting method comprises the following steps: the counting methods such as a numerical value type and the like, a scientific counting method and the like are unified.

(8) Abbreviation rule: abbreviations for common fields, such as unity for units, name, date, month, etc. For example: monday is expressed as Monday or Mon or M, the smart Device is abbreviated as Device or D, and the degree Celsius is abbreviated as C or DEG C.

(9) Value range: for both discrete and continuous variables, a uniform range constraint should be applied according to business rules.

(10) Constraint: whether or not to allow unification of control, uniqueness, foreign key constraints, primary keys, etc.

4. Correction logic

In a multi-data source environment, there is a high probability of data anomalies or collisions.

For such data contradiction, firstly, the logic, condition and caliber of each source system are defined, then a set of rules conforming to the acquisition logic of each system is defined, and the acquisition logic of the abnormal source system is corrected.

In some cases, there may be an error in data collection caused by an error in the business rule, where the wrong collection logic needs to be corrected from the source, and then data cleaning and conversion are performed.

5. Data transformation

Data transformation is an important step in the data cleaning process, which is the standard processing of one piece of data, and is involved in almost all data processing processes. Common content for data conversion includes: data type conversion, data semantic conversion, data value range conversion, data granularity conversion, table/data splitting, row-column conversion, data discretization, refining new fields, attribute construction, data compression, and the like.

(1) Data type conversion

When data comes from different data sources, incompatibility of the different types of data source data types may cause a system error. At this time, the data types of different data sources need to be uniformly converted into a compatible data type.

Basic data types are eight types of byte/short/char/int/long/float/double. The size of the opened memory space is different for different types of data, so that the value range of each type is different. Between different types, the conversion can be achieved under conditions that meet data compatibility, typically in several ways:

1. Automatic type conversion: the type with small capacity is automatically converted into the data type with large capacity; according to the definition of automatic type conversion, the automatic conversion relationship between 8 basic types is referred to in fig. 2, and fig. 2 is a diagram showing the automatic conversion relationship between 8 basic types according to an exemplary embodiment.

2. Forced type conversion: converting the data type with large capacity into the data type with small capacity;

3. implicit mandatory type conversion (initialization): when the variable is initialized, the int type can be implicitly and forcedly converted into low-level byte and short type;

4. other types of transformations: packaging class, character string, basic type direct conversion.

(2) Data semantic conversion

In a conventional data warehouse, a dimension table, a fact table and the like may exist based on the third paradigm, and many fields in the fact table need to be combined with the dimension table to perform semantic parsing. For example, if the business meaning of field M is a browser type, its value is classified as 1/2/3/4/5, and these 5 digits are difficult to understand as business language if not converted, and are not interpreted and applied later.

(3) Data granularity conversion

Business systems typically store detail data, some systems even store time-stamp based data, and the data in the data warehouse is analyzed without requiring very detail data, typically, the business system data is aggregated according to different granularity requirements in the data warehouse.

(4) Table/data splitting

Some fields may store multiple data information, for example, the timestamp contains information of year, month, day, hour, minute, second, etc., and some rules require splitting part or all of the time attributes, so as to meet the data aggregation requirement under multiple granularities. Likewise, there may be multiple fields within a table, and there may be cases where the table fields are split.

(5) Line-column conversion

In some cases, the column and row data in the table may need to be transformed (also referred to as transposed), e.g., the relationship between the user and term is mutually column and can be transformed before collaborative filtering computation, which can be used to satisfy both project-based and user-based similarity recommendation computation.

(6) Data discretization

The attribute of continuous value is discretized into a plurality of intervals to help reduce the value number of one continuous attribute. For example, for people traffic this field, to facilitate statistics, it is possible to divide into several different intervals according to business experience: 0 to 500, 501 to 1000, 1001 to 1500, 1501 to 2000, greater than 2000, or 1, 2, 3, 4, 5, respectively.

(7) Data normalization

Because of the different business meanings of the fields themselves, there are times when it is necessary to eliminate the significant differences between values caused by different orders of magnitude between variables. For example, the sales are discretized to eliminate the inability to perform multi-column composite calculations between different sales due to magnitude relationships. The data normalization process may also be used to account for the impact of higher individual value attributes on the clustering results.

(8) Refining new fields

In many cases, new fields, also called compound fields, need to be extracted based on business rules. These fields are usually generated based on a single field, but complex operations or even complex algorithm models are required to obtain new indexes.

(9) Attribute construction

In some modeling processes, it may also be desirable to construct new attributes from existing sets of attributes. For example: the characteristic properties 'long' and 'wide' of a region of a passenger station can be constructed to be the 'area' property of the region. Knowing the daily on-duty time of the passenger station, the one week on-duty time attribute can be constructed.

6. Data compression

Data compression refers to a technical method for reorganizing data according to a certain algorithm and mode on the premise of keeping the integrity and accuracy of an original data set and not losing useful information.

Complex data analysis and data computation on large-scale data generally take a lot of time, so that data reduction and compression are required before the complex data analysis and data computation, the data size is reduced, interactive data mining is possible, and information feedback is performed on the data according to comparison before and after the data mining. This is obviously more efficient in data mining on reduced data sets and the mined results are substantially the same as those obtained using the original data set.

The meaning of data compression is not only embodied in the data calculation process, but also beneficial to reducing the storage space, improving the transmission, storage and processing efficiency, reducing the redundancy and storage space of data, and has very important meaning for a bottom big data platform.

There are several ways of data compression that can be chosen:

(1) Data aggregation: the data is aggregated for use, for example, if all the data is aggregated, then it is more convenient to base the data on coarser granularity.

(2) Dimension reduction: manually eliminating redundant attributes through correlation analysis, so that the dimension (field) participating in calculation is reduced; dimension aggregation may also be performed using principal component analysis, factor analysis, etc., resulting in a data dimension that is also less involved in the computation.

(3) Data block reduction: the original data is replaced by clustering or a parameter model, and the mode is common in the mode that a plurality of models are comprehensively used for machine learning and data mining.

(4) Data compression: data compression includes both lossless compression and lossy compression types. Data compression is commonly used for disk files, video, audio, images, and the like.

7. Complement incomplete/empty value

Many systems have incomplete data for various subjective and objective reasons, which includes three cases of row missing, column missing, and field missing. A row miss refers to the loss of an entire data record, a column miss refers to the loss of an entire column of data, and a field miss refers to the value in the field being a null value. The null value is also divided into two cases:

(1) Missing values. A missing value refers to data that would have been necessary to exist, but actually no data. For example, a passenger service person learns that this field is everyone, so if the system forced verification is not to be empty.

(2) Null value. Null refers to the fact that there may be a null, so null is not necessarily a data problem. Such as a passenger station personnel skill certificate, only a portion of the witness has the string, so that users with no skill certificates may also be present and may be empty.

The filling process for missing values and null values mainly involves two ways:

(1) Manually filling possible values;

(2) Filling possible values with rules: some missing values may be derived from the present data source or other data sources, which may be populated with states and features of the data distribution, using mode, median, average, maximum, minimum values, or using neighbor analysis or even more complex probability estimates instead of missing values.

8. Discarding data/variables

For abnormal data in the data, including missing values, null values, error values, incomplete data records and the like, there is another method, namely discarding, besides cleaning, converting and lifting by using the method. Discarding is also a way to improve the quality of the data. The types of discarded data include two types:

(1) Whole deletion refers to deleting samples containing missing values. In some cases, there may be a large number of data records with some fields missing for various reasons, which may result in less complete data, which may need to be used with care. Therefore, this is only suitable for cases where critical variables are missing, or where samples containing invalid or missing values have a small specific gravity.

(2) Variable deletion, if the invalid and missing values of a variable are numerous and the variable is not particularly important to the problem under study, then deletion of the variable may be considered.

In specific practice, after "the passenger service model is obtained" in step S13, the method further includes:

performing strong characteristic intelligent pairing on the evaluation factors according to the passenger service work requirements, and processing the evaluation factors by adopting a natural language processing method to obtain examination rules conforming to the passenger service work requirements;

and quantifying the examination rules into the passenger transport service model to obtain the passenger transport service model conforming to the examination rules.

In specific practice, a natural language processing method includes:

the method comprises the steps of corpus acquisition, data preprocessing, feature engineering, feature selection, model training, model evaluation and production online.

In specific practice, the system for analyzing and scheduling the passenger transport service is constructed according to the data information and the passenger transport service model, and specifically comprises the following steps:

and selecting camera people flow information, intelligent equipment information and service personnel positioning information as key elements, and selecting 12306 system information and personnel basic information as general elements according to the data information and the passenger transport service model to construct a passenger transport service analysis and scheduling system.

The evaluation factor is a basic index for evaluating a passenger service, for example: (1) public toilet health status; (2) waiting room hygiene; (3) The personnel density (4) has complete cleaning facilities and good operation; (5) charging early warning of cleaning facilities; (6) the passenger station has a degree of mechanized equipment; (7) the passenger station has an automation degree; (8) The temperature of the waiting room is proper, the air circulation condition (9) the toilet temperature is proper, and the air circulation condition is realized; (10) failure rate of elevator, etc.

Synthesizing the evaluation factors of the passenger transport service by using a fuzzy evaluation method according to the data information (data such as internal environment monitoring, video analysis, equipment management, 12306 system and the like) of the passenger transport station and the constructed data center of the passenger transport service, and combing the synthesized evaluation factors;

And setting calculation logic and a reference value according to the carded evaluation factors to form a three-dimensional multidimensional data model. And according to the working requirements of the passenger service, carrying out strong characteristic intelligent pairing on the evaluation factors, extracting and analyzing by adopting a natural language processing method, generating an inspection rule, quantifying the inspection rule into a corresponding passenger service model, and comparing the inspection rule with a value filled in the passenger service operation process in the system, wherein the comparison is the difference or the gap between the data information actually obtained and the data information of a preset value, and in the practical application, the preset value is obtained by accumulating and continuously correcting for a long time according to the practical situation, so as to finally form the passenger service model conforming to the inspection rule.

It should be noted that, the service models of all the systems obtained in the present invention are passenger transport service models conforming to the inspection rule, and if there are individual passenger transport service models not within the inspection rule, the calculation logic and the reference value are changed to satisfy the inspection rule.

The passenger service analysis and scheduling system obtains the current passenger service demand plan from the camera, the intelligent device, the 12306 system and the basic database, obtains the information such as the personnel flow information, the service personnel status, the intelligent device status and the like, and finally obtains the scheduling result of all the current tasks in the whole process through passenger service priority ranking, passenger service cleaning personnel scheduling, intelligent robot scheduling, other passenger service scheduling and mutual coordination. And (3) directly obtaining a dispatching result suitable for the passenger station in the actual service process by recalculating through adjusting a dispatching rule. And finally, the scheduling result is presented in an intelligent analysis result report, scheduling is carried out according to the report, and the coordinated operation adjustment of directors, equipment and the like is carried out.

For example: 1. out-inbound scene: a passenger flow triggering threshold value can be set in the system, when the passenger flow of the entrance recognized by the intelligent analysis camera exceeds the threshold value, the system sends out reminding and early warning, the intelligent cleaning robot working on the passenger passing aisle is automatically scheduled to avoid, and the intelligent cleaning robot automatically returns to a defined avoidance area to give way for the passenger, so that accidents are avoided; meanwhile, reminding passenger service personnel to prepare service; when the passenger on the channel is lower than the threshold value, automatically scheduling the intelligent cleaning robot to start to work again, and simultaneously relieving the related early warning. The passenger flow trigger threshold in the outbound scene is an evaluation factor in the scene, and the service model of the outbound scene can be obtained by setting calculation logic between the passenger flow threshold and the intelligent cleaning robot and continuously correcting in practice.

2. Waiting room scene: when the intelligent analysis camera recognizes that the personnel density in the waiting room exceeds the threshold value, the system sends out reminding and early warning, all robots in the waiting room are avoided nearby, personnel cleaning is changed into personnel cleaning, and meanwhile, the ventilation intensity of the ventilation system is increased, and the ventilation intensity is required to be adjusted under the condition of ensuring comfort. The evaluation factor in the scene is the personnel density, and the service model in the waiting room scene is obtained by setting the calculation logic between the personnel density and the robot, the ventilation system and the like and continuously correcting the personnel density.

3. Public lavatory scene: an environmental threshold value can be set in the system, when the sensor detects that the ammonia gas and hydrogen sulfide gas values of the air exceed the threshold value, the system sends out reminding and early warning, and intelligently reminds relevant cleaning staff to clean the public toilet, so that the public toilet environment is kept good, and comfortable experience is brought to passengers; when the sensor detects that the smoke or the temperature and the humidity exceed the threshold value, the system sends out reminding and early warning, and intelligently reminds relevant safety management personnel to check the public toilet, so that relevant potential safety hazards are eliminated. The evaluation factors in the present scenario include: the method comprises the steps of setting calculation logic and reference values among evaluation factors, and continuously updating and correcting in practical application to obtain a service model in a public toilet scene by means of ammonia gas, hydrogen sulfide gas threshold values, smog, humiture and the like of air.

5. Elevator usage scenario: the elevator system can set a personnel threshold, special personnel can be set at the upper end and the lower end of the escalator to watch in actual passenger transport service, the escalator runs continuously for approximately 24 hours, the system can set the elevator to be in a sleep mode without watching personnel and switch to the sleep mode under the condition of extremely small passenger flow, namely, the elevator is closed when no person passes, the elevator is changed into a working mode from the sleep mode when the person passes is detected, and the elevator is not used in the sleep mode after a period of time, so that a user experiences high-quality service. If the passenger flow is tens of people or less in a passenger service center, the operation of the elevator can be selected to be closed, so that customers walk stairs, the loss of the elevator is saved, and the elevator is energy-saving and environment-friendly. The evaluation factors in the present scenario include: and the personnel threshold value is updated and corrected continuously in practical application by setting calculation logic and a reference value between the personnel threshold value and the elevator use scene, so that a service model under the elevator use scene is obtained.

It should be noted that, in the practical application process, the evaluation factors to be considered are many, and the evaluation factors of various scenes in the embodiment are only exemplified and not represented, and other evaluation factors adopting the method are all within the protection scope of the application.

The invention relates to a passenger service data center, which is characterized in that a passenger service data center is obtained by acquiring and preprocessing the passenger service data information, a fuzzy evaluation method is adopted to synthesize the passenger service evaluation factors according to the passenger service data center data, the synthesized evaluation factors are combed, a calculation logic and a reference value are set according to the combed evaluation factors to obtain a passenger service model, a passenger service analysis and scheduling system is constructed by combining the passenger service data information, a current passenger service demand plan and a current task processing node in a process are obtained, and the passenger service analysis and scheduling system is combined to perform recalculation to obtain a scheduling result conforming to the passenger service data information.

Example two

Referring to fig. 3, fig. 3 is a schematic block diagram of a passenger service analysis and dispatch system according to an exemplary embodiment, as shown in fig. 3, a passenger service analysis and dispatch system 300, comprising:

an acquisition module 301, configured to acquire data information of a passenger service;

the preprocessing module 302 is configured to preprocess the data information to obtain preprocessed data information, and store the preprocessed data information in a data center of a passenger service;

the synthesizing module 303 is configured to synthesize the evaluation factors of the passenger service by using a fuzzy evaluation method according to the data information and the data of the data center, and comb the synthesized evaluation factors;

the calculation module 304 is configured to set calculation logic and a reference value according to the carded evaluation factor, so as to obtain a passenger transport service model;

a construction module 305, configured to construct a passenger service analysis and dispatch system according to the data information and the passenger service model;

and the recalculation module 306 is used for acquiring the demand plan of the current passenger service and the processing nodes of the current task in the flow, and recalculating the data by combining the passenger service analysis and dispatch system to obtain a dispatch result conforming to the passenger station data information.

It should be noted that, application scenarios applicable to the technical solution provided in this embodiment include, but are not limited to: passenger service places such as railway stations, automobile stations and the like.

It may be understood that, in the technical solution provided in this embodiment, the acquiring module 301 is configured to acquire data information of a passenger service, the preprocessing module 302 is configured to perform preprocessing to obtain a data center of the passenger service, and the synthesizing module 303 is configured to synthesize an evaluation factor of the passenger service by using a fuzzy evaluation method according to the data information and data of the data center, and comb the synthesized evaluation factor; the computing module 304 is used for setting computing logic and reference values according to the carded evaluation factors to obtain a passenger service model, the construction module 305 is used for combining data information to construct a passenger service analysis and scheduling system, the recalculation module 306 is used for processing nodes of a current passenger service demand plan and a current task in a process and combining the passenger service analysis and scheduling system to recalculate to obtain a scheduling result conforming to passenger station data information.

Example III

A passenger service management and control platform is shown according to an exemplary embodiment, comprising:

the device comprises a communication module, a processor and a memory, wherein the memory stores program instructions;

the processor is used for executing the program instructions stored in the memory and executing the obstacle fusion method under the multi-camera overlapping vision.

It should be noted that, the implementation manner and the beneficial effects of each module in the embodiment may refer to the description of the related steps in the first embodiment, and the embodiment is not repeated.

It is to be understood that the same or similar parts in the above embodiments may be referred to each other, and that in some embodiments, the same or similar parts in other embodiments may be referred to.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.

It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.

In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like.

In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims (10)

1. A passenger service analysis and dispatch method, comprising:

acquiring data information of passenger transport services;

preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information into a data center of a passenger transport service;

Synthesizing the evaluation factors of the passenger service by adopting a fuzzy evaluation method according to the data information and the data of the data center, and combing the synthesized evaluation factors;

setting calculation logic and a reference value according to the carded evaluation factors to obtain a passenger transport service model;

constructing a passenger service analysis and scheduling system according to the data information and the passenger service model;

and acquiring a demand plan of the current passenger service and a processing node of the current task in the flow, and carrying out recalculation by combining a passenger service analysis and scheduling system to obtain a scheduling result which accords with passenger station data information.

2. The method of claim 1, wherein the data information comprises: personnel information, equipment information, environment information, operation information, early warning information, ticket information and passenger transport information;

wherein the personnel information includes: passenger station personnel information, service personnel information, and people stream information.

3. The method of claim 2, wherein preprocessing the data information to obtain preprocessed data information comprises:

and carrying out data cleaning comparison on the data of the personnel information, the equipment information, the environment information, the operation information, the early warning information, the ticket information and the passenger information, and storing preset rules to obtain the preprocessed data information.

4. The method of claim 3, wherein the data of the personnel information, the equipment information, the environment information, the operation information, the early warning information, the ticket information and the passenger information are subjected to data cleaning comparison and stored with a preset rule to obtain the preprocessed data information, specifically:

performing error correction, repeated item deletion, unified specification, correction logic, conversion structure, data compression, incomplete/empty value complement and discarded data/variable cleaning on the personnel information, equipment information, environment information, operation information, early warning information, ticket information and passenger information, and performing preset rule storage on the cleaned data to obtain processed data information; wherein, the storing of the preset rule includes: and (5) storing in a classification way.

5. The method of claim 1, wherein after the obtaining the passenger service model, further comprising:

performing strong characteristic intelligent pairing on the evaluation factors according to the passenger service work requirements, and processing the evaluation factors by adopting a natural language processing method to obtain examination rules conforming to the passenger service work requirements;

and quantifying the examination rules into the passenger transport service model to obtain the passenger transport service model conforming to the examination rules.

6. The method of claim 5, wherein the natural language processing method comprises:

the method comprises the steps of corpus acquisition, data preprocessing, feature engineering, feature selection, model training, model evaluation and production online.

7. The method according to claim 1, wherein said constructing a passenger service analysis and dispatch system based on said data information and said passenger service model comprises:

and selecting camera people flow information, intelligent equipment information and service personnel positioning information as key elements, and selecting 12306 system information and personnel basic information as general elements according to the data information and the passenger transport service model to construct a passenger transport service analysis and scheduling system.

8. The method of claim 1, wherein the obtaining data information for the passenger service comprises:

a camera is adopted to acquire people flow information of a passenger station and personnel information of the passenger station;

and acquiring equipment information, environment information, operation information and early warning information of the passenger station according to the networking system/device.

9. A passenger service analysis and dispatch system, comprising:

the acquisition module is used for acquiring data information of the passenger transport service;

The preprocessing module is used for preprocessing the data information to obtain preprocessed data information, and storing the preprocessed data information into a data center of the passenger transport service;

the synthesizing module is used for synthesizing the evaluation factors of the passenger service by adopting a fuzzy evaluation method according to the data information and the data of the data center, and combing the synthesized evaluation factors;

the calculation module is used for setting calculation logic and a reference value according to the carded evaluation factors to obtain a passenger transport service model;

the construction module is used for constructing a passenger transport service analysis and scheduling system according to the data information and the passenger transport service model;

and the recalculation module is used for acquiring a demand plan of the current passenger transport service and a processing node of the current task in the flow, and recalculating the data by combining a passenger transport service analysis and scheduling system to obtain a scheduling result which accords with the passenger transport station data information.

10. A passenger service management and control platform, comprising:

the device comprises a communication module, a processor and a memory, wherein the memory stores program instructions;

the processor is configured to execute program instructions stored in the memory and perform the method according to any one of claims 1 to 8.

Images