Summary of the invention
Based on this, present description provides the performance estimating methods and device of OD demand analysis algorithm.
According to this specification embodiment in a first aspect, providing a kind of performance estimating method of OD demand analysis algorithm, institute
The method of stating includes:
Obtain the OD demand of each user;
By the OD Demand mapping at OD requirement matrix;
The OD requirement matrix is launched into OD requirement vector, and calculate from the calculated target of OD demand analysis algorithm to
The similarity of amount and the OD requirement vector carries out Performance Evaluation to the OD demand analysis algorithm according to the similarity.
Optionally, the step of obtaining the OD demand of each user include:
Obtain the IP address and end address of user;
The IP address and end address are converted into starting point longitude and latitude and terminal longitude and latitude respectively;
The OD demand of user is established according to the starting point longitude and latitude and terminal longitude and latitude.
Optionally, before the OD need to be mapped to OD requirement matrix, the method also includes:
Duplicate removal processing is carried out to the OD demand;And/or
OD demand not in the region is filtered.
Optionally, the step of being filtered to the OD demand not in the region include:
Obtain the longitude and latitude range in the region;
The starting point longitude and latitude and terminal longitude and latitude are compared with the longitude and latitude range;
If at least one of the starting point longitude and latitude and terminal longitude and latitude be not within the scope of the longitude and latitude, to corresponding
OD demand be filtered.
Optionally, include: to the step of OD demand progress duplicate removal processing
The OD demand is divided into the OD demand of each period by the time generated according to the OD demand;
Duplicate removal processing is carried out to the OD demand of each period respectively.
Optionally, the step of obtaining the OD demand of each user include:
The OD demand of the user is established according to the inhabitation way address and work address of user;And/or
The shipping address for obtaining the user identifies certain types of address, according to described from the shipping address
The OD demand of the user is established in certain types of address;And/or
Continuous report sequence living is filtered out from the digital map navigation data of the user, is extracted in continuous report sequence living
It reports for the first time living point and tail report point living, and establishes the OD demand of the user according to point and tail the report point living living of reporting for the first time.
Optionally, the similarity is cosine similarity.
According to the second aspect of this specification embodiment, a kind of capability evaluating device of OD demand analysis algorithm, institute are provided
Stating device includes:
Module is obtained, for obtaining the OD demand of each user;
Mapping block is used for the OD Demand mapping into OD requirement matrix;
Evaluation module for the OD requirement matrix to be launched into OD requirement vector, and is calculated by OD demand analysis algorithm
The similarity of calculated object vector and the OD requirement vector, according to the similarity to the OD demand analysis algorithm into
Row Performance Evaluation.
According to the third aspect of this specification embodiment, a kind of computer readable storage medium is provided, is stored thereon with meter
Calculation machine program realizes method described in power any embodiment when the program is executed by processor.
According to the fourth aspect of this specification embodiment, a kind of computer equipment is provided, including memory, processor and deposit
The computer program that can be run on a memory and on a processor is stored up, the processor realizes any reality when executing described program
Apply method described in example.
Using this specification example scheme, first by extracting the true OD demand of user, one is then constructed very
Real OD matrix, the similitude finally compared between the matrix and the obtained OD matrix of OD demand analysis algorithm carry out verification algorithm
Validity, eliminate artificial intervention consumption, improve assessment efficiency.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
This specification can be limited.
Specific embodiment
Example embodiments are described in detail here, and the example is illustrated in the accompanying drawings.Following description is related to
When attached drawing, unless otherwise indicated, the same numbers in different drawings indicate the same or similar elements.Following exemplary embodiment
Described in embodiment do not represent all embodiments consistent with this specification.On the contrary, they are only and such as institute
The example of the consistent device and method of some aspects be described in detail in attached claims, this specification.
It is only to be not intended to be limiting this explanation merely for for the purpose of describing particular embodiments in the term that this specification uses
Book.The "an" of used singular, " described " and "the" are also intended to packet in this specification and in the appended claims
Most forms are included, unless the context clearly indicates other meaning.It is also understood that term "and/or" used herein is
Refer to and includes that one or more associated any or all of project listed may combine.
It will be appreciated that though various information may be described using term first, second, third, etc. in this specification, but
These information should not necessarily be limited by these terms.These terms are only used to for same type of information being distinguished from each other out.For example, not taking off
In the case where this specification range, the first information can also be referred to as the second information, and similarly, the second information can also be claimed
For the first information.Depending on context, word as used in this " if " can be construed to " ... when " or
" when ... " or " in response to determination ".
As shown in Figure 1, being the performance estimating method flow chart of the OD demand analysis algorithm of this specification one embodiment, institute
State method can include:
Step 102: obtaining the OD demand of each user;
Step 104: by the OD Demand mapping at OD requirement matrix;
Step 106: the OD requirement matrix being launched into OD requirement vector, and calculates and is calculated by OD demand analysis algorithm
Object vector and the OD requirement vector similarity, according to the similarity to the OD demand analysis algorithm carry out performance
Assessment.
In a step 102, OD demand refers to user from departure place (starting point) to the record between destination (terminal).In reality
Border application in, can by a region division be multiple blocks, the longitude and latitude of each block within the scope of certain longitude and latitude,
And analyze the OD demand between each block.For example, upper sea region (30.676166 < latitude < 31.876342 120.980728 <
Longitude < 122.013431).As shown in Fig. 2, be this specification one embodiment different blocks between OD demand schematic diagram.Figure
In, region S is divided in order to which totally 9 blocks, the starting point of demand OD1 are located at block S1 to S1 to S9, it is area that terminal, which is located at block S5,
The OD demand of block S1 to block S5;The beginning and end of demand OD2 is respectively positioned on block S5, is the OD demand inside block S5;Area
The starting point of block OD3 is located at block S5, and terminal is located at block S9, is the OD demand of block S5 to block S9.
The OD demand of available multiple users can carry out each user to its OD demand whithin a period of time
Data acquisition.It may include the identification information of user in OD demand, identification information can be the cell-phone number of user, SIM card number etc.
Information.It can also include the geographical location information of user departure place and the geographical location information of destination, geography in OD demand
Location information can be latitude and longitude information, and perhaps number information of coordinate information or place block etc. is used to characterize geographical position
The information set.
In one embodiment, the IP address and end address of available user;Respectively by the IP address and
End address is converted to starting point longitude and latitude and terminal longitude and latitude;Establish user's according to the starting point longitude and latitude and terminal longitude and latitude
OD demand.For example, for user A, available its IP address OAWith end address DA, and by IP address and end address
It is respectively converted into longitude and latitude, it may be assumed thatWithAssuming that user identifier is SA, then an OD of user A can be established
Demand are as follows:It is understood that in practical applications, the form of the OD demand of foundation is unlimited
In this, it is above only as an example.
Further, for the OD demand of acquisition, duplicate removal processing can also be carried out to the OD demand;And/or to not existing
OD demand in the region is filtered.Wherein, duplicate removal refers to the duplicate OD demand for removing the same user.In duplicate removal
When, the OD demand can be divided into the OD demand of each period according to the time that the OD demand generates;Respectively to each
The OD demand of a period carries out duplicate removal processing.
For example, user A can be obtained respectively in the OD demand of nearest 3 day morning 7:30~9:30 (assuming that respectively OD1,
OD2And OD3) and user A nearest 16:30~18:30 in 3 day afternoon OD demand (assuming that respectively OD4, OD5And OD6).So
Afterwards, for the OD demand of 7:30~9:30, from OD1, OD2And OD3In filter out identical OD demand;For 16:30~18:30
OD demand, from OD4, OD5And OD6In filter out identical OD demand.Assuming that OD2And OD3For identical OD demand, and OD4,
OD5And OD6For identical OD demand, then the OD demand of 7:30~9:30 is OD after duplicate removal1, OD2;16:30~18:30 after duplicate removal
OD demand be OD4。
In order to obtain the OD demand in specific region, the OD demand of original generation can be filtered, be removed trans-regional
OD demand.Specifically, the longitude and latitude range in the available region;By the starting point longitude and latitude and terminal longitude and latitude with
The longitude and latitude range is compared;If at least one of the starting point longitude and latitude and terminal longitude and latitude be not in the longitude and latitude
Within the scope of, corresponding OD demand is filtered.As shown in Fig. 2, demand OD4 is in the S of region to another other than the S of region
The OD demand in region, since it has exceeded the range of region S,, can need to when the OD demand to region S is analyzed
OD4 is asked to filter out.
In one embodiment, following at least one mode can be used to obtain the OD demand of each user:
Mode one:
The OD demand of the user is established according to the inhabitation way address and work address (that is, duty residence data) of user.?
In the method, inhabitation way address and work address that available each user pre-registers.Inhabitation way address and work address
Data source can be questionnaire survey or user for certain application programs (for example, Alipay, wechat etc.) registration information
When the information etc. that pre-enters.API can be encoded by the geographical location of map software (for example, Amap)
(Application Programming Interface, application programming interface) is by address conversion at longitude and latitude, last structure
Build residence to place of working OD demand.
Mode two:
The shipping address for obtaining the user identifies certain types of address, according to described from the shipping address
The OD demand of the user is established in certain types of address.It in this mode, can be using the textual classification model pre-established
To carry out identification classification to the particular address in shipping address.Wherein, particular address can be residence address, work address,
School address etc..It is then possible to by the geographical location of map software (for example, Amap) encode API by address conversion at
Longitude and latitude finally constructs residence to place of working or residence to the OD demand of school.In practical applications, text classification
FastTest textual classification model can be used in model.
Mode three:
Continuous report sequence living is filtered out from the digital map navigation data of the user, is extracted in continuous report sequence living
It reports for the first time living point and tail report point living, and establishes the OD demand of the user according to point and tail the report point living living of reporting for the first time.Report work refers to
Using the location information of the client acquisition user of user terminal installation, collected each position constitutes the report sequence living of user
Column.It can identify that continuous whole report sequence living, such as the adjacent work of report twice are recorded in 5S according to report live time interval
Can be regarded as within (time is adjustable), has the report of front and back serial relation living, if it exceeds this time threshold then thinks that front and back is reported twice
Relevance living is not strong.After identifying a continuous whole report work sequence, first longitude and latitude for reporting point (starting point) living can be taken
The longitude and latitude position of degree position and the last one report point (terminal) living carrys out an OD demand of structuring user's.
For example, when user drives, if opening navigation, the position of the continuous report of user of navigation meeting, this frequency
Interval can be very short, but after user arrives at the destination, terminates navigation, then navigation would not continue the record of report of user.
Therefore, the report generated in a navigation procedure sequence living can regard continuous whole report sequence living as.
This specification embodiment can carry out aid decision, such as duty residence data, digital map navigation by multiple data sources
Data and shipping address data etc..Contain a large amount of people true OD demand on and off duty, digital map navigation number in the data of duty residence
There is a large amount of trip requirements of user in, and cover user from residence to work unit in shipping address data, occupy
Residence is to the true OD demand such as school.Therefore, the embodiment of the present invention passes through geographical location parsing, text classification, sequence terminus
The technological means such as identification can extract the true OD demand of people from above-mentioned more parts of data.In addition, this specification embodiment
Direct extraction of the evaluation method from multiple data sources to true OD demand, thus its not only in the sense with given in magnitude
It correctly explains, while eliminating artificial intervention consumption and data coverage is wide.
At step 104, the OD can need to be mapped to OD requirement matrix.OD requirement matrix can be with all traffic
Region is divided by row (starting point where block) and column (block where terminal) sequence, between any two block resident or vehicle
Travel amount (OD amount) is the matrix of element.The element of symmetric position can distinguish different directions between two blocks in the matrix (square matrix)
Travel amount.
The OD requirement matrix of one embodiment is as shown in Figure 3.As can be seen that region shown in figure includes 3 blocks,
Number is respectively 1,2 and 3, wherein the OD demand (the first row first row of matrix) inside block 1 is 1, block 1 to block 2
OD demand (the first row secondary series of matrix) be 0, the OD demand of block 1 to block 3 (the first row third of matrix arranges)
It is 2, the OD demand (the second row first row of matrix) of block 2 to block 1 is 3, and so on.
In step 106, the OD requirement matrix is launched into OD requirement vector, can be and be unfolded line by line, is also possible to
Be unfolded by column, if the OD requirement vector obtained in step 104 with by calculating OD demand analysis algorithm calculated object vector
Expansion mode is consistent.
In one embodiment, cosine similarity can be used.The calculation formula of cosine similarity is as follows:
In formula, Sim is similarity, and A is the OD requirement vector obtained after the OD requirement matrix is unfolded, and B is object vector,
AiAnd BiI-th of element of respectively vector A and vector B, n are the summation of element in OD requirement vector.
The overview flow chart of the performance estimating method of the OD demand analysis algorithm of one embodiment is as shown in Figure 4.In this reality
It applies in example, obtains duty residence data, shipping address and the digital map navigation data of each user first, then shipping address is carried out
Classification parsing, and to map navigation data carries out beginning and end identification, to receiving after duty residence data and classification parsing
Address carries out geocoding parsing, then to the shipping address after the duty residence data and classification parsing after parsing, Yi Jigen
It is filtered according to the beginning and end that digital map navigation data obtain and duplicate removal, creates true OD requirement matrix, finally, calculating true
The similarity between vector that the real corresponding vector of OD requirement matrix and algorithm to be assessed obtain.
Using this specification example scheme, first by extracting the true OD demand of user, one is then constructed very
Real OD matrix, the similitude finally compared between the matrix and the obtained OD matrix of OD demand analysis algorithm carry out verification algorithm
Validity, eliminate artificial intervention consumption, improve assessment efficiency.
Various technical characteristics in above embodiments can be arbitrarily combined, as long as there is no punchings for the combination between feature
Prominent or contradiction, but as space is limited, is not described one by one, thus the various technical characteristics in above embodiment it is any into
Row combination also belongs to the range of this disclosure.
As shown in figure 5, being the block diagram of the capability evaluating device of the OD demand analysis algorithm of this specification one embodiment, institute
State device can include:
Module 502 is obtained, for obtaining the OD demand of each user;
Mapping block 504, for the OD need to be mapped to OD requirement matrix;
Evaluation module 506 for the OD requirement matrix to be launched into OD requirement vector, and is calculated and is calculated by OD demand analysis
The similarity of the calculated object vector of method and the OD requirement vector, according to the similarity to the OD demand analysis algorithm
Carry out Performance Evaluation.
The specific details of the realization process of the function of modules and effect, which are shown in, in above-mentioned apparatus corresponds to step in the above method
Realization process, details are not described herein.
For device embodiment, since it corresponds essentially to embodiment of the method, so related place is referring to method reality
Apply the part explanation of example.The apparatus embodiments described above are merely exemplary, wherein described be used as separation unit
The module of explanation may or may not be physically separated, and the component shown as module can be or can also be with
It is not physical module, it can it is in one place, or may be distributed on multiple network modules.It can be according to actual
The purpose for needing to select some or all of the modules therein to realize this specification scheme.Those of ordinary skill in the art are not
In the case where making the creative labor, it can understand and implement.
The embodiment of this specification device can be applied on a computing device, such as server or intelligent terminal.Device
Embodiment can also be realized by software realization by way of hardware or software and hardware combining.Taking software implementation as an example,
As the device on a logical meaning, being will be corresponding in nonvolatile memory by the processor of file process where it
Computer program instructions are read into memory what operation was formed.For hardware view, as shown in fig. 6, being this specification device
A kind of hardware structure diagram of place computer equipment, in addition to processor 602 shown in fig. 6, memory 604, network interface 606, with
And except nonvolatile memory 608, server or electronic equipment in embodiment where device are set generally according to the computer
Standby actual functional capability can also include other hardware, repeat no more to this.
Correspondingly, this specification embodiment also provides a kind of computer storage medium, is stored with journey in the storage medium
Sequence realizes the method in any of the above-described embodiment when described program is executed by processor.
Correspondingly, this specification embodiment also provides a kind of computer equipment, including memory, processor and is stored in
On reservoir and the computer program that can run on a processor, the processor realize any of the above-described implementation when executing described program
Method in example.
It wherein includes storage medium (the including but not limited to disk of program code that the application, which can be used in one or more,
Memory, CD-ROM, optical memory etc.) on the form of computer program product implemented.Computer-usable storage medium packet
Permanent and non-permanent, removable and non-removable media is included, can be accomplished by any method or technique information storage.Letter
Breath can be computer readable instructions, data structure, the module of program or other data.The example packet of the storage medium of computer
Include but be not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM),
Other kinds of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory
(EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), digital versatile disc
(DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices or any other non-biography
Defeated medium, can be used for storage can be accessed by a computing device information.
Those skilled in the art will readily occur to the disclosure after considering specification and practicing specification disclosed herein
Other embodiments.The disclosure is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes
Or adaptive change follow the general principles of this disclosure and including the disclosure it is undocumented in the art known in often
Knowledge or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim point out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
The foregoing is merely the preferred embodiments of the disclosure, not to limit the disclosure, all essences in the disclosure
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of disclosure protection.