JP4127219B2 - Correspondence verification support method, apparatus and program - Google Patents

Description

  The present invention relates to a correspondence verification support method, apparatus, and program, and more particularly, to a correlation verification support method, apparatus, and program for verifying an associated scenario and video.

Research has been made such as automatically assigning subtitle display timing by associating a scenario with a video for the scenario, and giving information (metadata) for explaining the video (for example, Patent Document 1, Non-patent document 1).
Japanese Patent Application Laid-Open No. 10-254478 “Audio Original Optimal Collation Apparatus and Method” Yoshitomo Yanaginuma, Masao Sakauchi “Proposal of position matching method of drama video / sound / scenario document using DP matching” IEICE Transactions D-II Vol.J79-D-II No.5, pp.747- 755, May 1996

  However, in the conventional scenario and video associating technique, it is necessary to rely on the operator's visual inspection for determining whether the correspondence is correctly generated and for correcting the correspondence. Therefore, in order to acquire a correct correspondence relationship, it may be necessary to perform operations by a large number of operators. Therefore, when the total work including obtaining the correct correspondence, including the operator's work, is needed, there must be a method of generating multiple correspondence candidates and efficiently finding the correct correspondence from the multiple candidates. Become.

  The present invention has been made in view of the above points. The correspondence verification support method, apparatus, and program capable of verifying the correspondence between all scenarios and videos while reducing the number of sections that the operator should visually check. The purpose is to provide.

  FIG. 1 is a diagram for explaining the principle of the present invention.

The present invention (Claim 1) is a correspondence verification support method for verifying a correlated video and a scenario,
A sequence association candidate input process (step 1) for reading and inputting a sequence association candidate including at least one association candidate in which a video and a scenario are associated with each other from the storage unit;
A node detection process (step 2) for detecting a node from the sequence correspondence candidates;
A node / link value setting process (step 3) for setting a node value and a link value for each node and the combination of the nodes (hereinafter referred to as a link);
The link with the maximum link value is extracted from all the links, the link candidate having the link value closest to 1/2 of the link with the maximum link value is output to the display means, and the unnecessary series correspondence is output. A matching candidate presentation process (step 4) for requesting input of a candidate for attaching ;
The sequence association candidate selected by the operator is acquired, and a deletion process (step 5) for deleting from the sequence association candidate in the storage means is performed.
In the node / link value setting process (step 3),
The end node value is 1,
The node counter i is incremented by 1, and the node values of all the nodes linked from the node Ni are added to obtain the node value of Ni, and Ni is set as the link value for all the links linking the node Ni. The process is executed for all the nodes linked from the node Ni, and an algorithm for repeating the process until all the node values are set is executed.

The present invention (Claim 2) is a correspondence verification support method for verifying a correlated video and a scenario,
A sequence association candidate input process in which a sequence association candidate including at least one association candidate in which a video and a scenario are associated is read from the storage means and input;
A node detection process for detecting a node from the sequence correspondence candidates;
A link value that sets, as a link value, the sum of real time that can be deleted from the set of sequence association candidates by determining whether or not the link (hereinafter referred to as a link) of each node passes through the link. Setting process,
Extracting a link with the largest link value, outputting a matching candidate in the link to a display unit, and requesting an input of an unnecessary sequence matching candidate ;
The deletion process of acquiring the sequence association candidate selected by the operator and deleting it from the sequence association candidate in the storage means is performed.

In the present invention ( Claim 3), in the link value setting process,
For all links,
A candidate for association when a route that does not pass through a link is deleted from the series association candidate is obtained, and a sum of link times (L−) that is real time given to a link that has disappeared as a result is obtained.
Obtaining a sequence association candidate when a route passing through a link is deleted from the sequence association candidate, and obtaining a sum (L +) of link times, which is a real time assigned to a link that has disappeared as a result,
An algorithm is executed in which the sum of L− and L + is divided by the link time and the value is set as the link value .

  FIG. 2 is a principle configuration diagram of the present invention.

The present invention (Claim 4) is a correspondence verification support apparatus for verifying a correlated video and a scenario,
Sequence association candidate input means 1 for reading and inputting a sequence association candidate including at least one association candidate in which a video and a scenario are associated with each other;
Node detection means for detecting a node from the sequence correspondence candidates;
A node / link value setting means 2 for setting a node value and a link value for each node and a combination of the nodes (hereinafter referred to as a link);
The link with the maximum link value is extracted from all the links, the link candidate having the link value closest to 1/2 of the link with the maximum link value is output to the display means, and the unnecessary series correspondence is output. Association candidate presenting means 3 for requesting input of attachment candidates;
A deletion means 5 for acquiring a series association candidate selected by the operator and deleting it from the series association candidates in the storage means;
The node / link value setting means 2
The end node value is 1,
The node counter i is incremented by 1, and the node values of all the nodes linked from the node Ni are added to obtain the node value of Ni, and Ni is set as the link value for all the links linking the node Ni. Means for executing an algorithm for all nodes linked from the node Ni and repeating the process until all node values are set is included.

The present invention (Claim 5) is a correspondence verification support apparatus for verifying a correlated video and a scenario,
A sequence association candidate input means for reading and inputting a sequence association candidate including at least one association candidate in which a video and a scenario are associated with each other;
Node detection means for detecting a node from the sequence correspondence candidates;
For binding of each node (hereinafter referred to as link), by determining whether or not to pass through the link, to set the sum of the actual time can be deleted from the set of sequences correspondence candidate as a link value and lapis lazuli link value setting means,
The link with the maximum link value is extracted, it is determined whether there are a plurality of links having the maximum link value, and if there are, the association candidates in any link among the links having the maximum link value To the display means, and in the case of single, the correspondence candidate presenting means for outputting the correspondence candidates in the link to the display means;
Delete means for acquiring a series association candidate selected by the operator and deleting it from the series association candidates in the storage means;

Further, according to the present invention (claim 6), in the node / link value setting means ,
For all links,
A candidate for association when a route that does not pass through a link is deleted from the series association candidate is obtained, and a sum of link times (L−) that is real time given to a link that has disappeared as a result is obtained.
Obtaining a sequence association candidate when a route passing through a link is deleted from the sequence association candidate, and obtaining a sum (L +) of link times, which is a real time assigned to a link that has disappeared as a result,
Means for dividing the sum of L- and L + by the link time and setting the value as the link value ;

The present invention (Claim 7) is a correspondence verification support program for causing a computer to function as each means constituting the correlation verification support apparatus according to any one of Claims 4 to 6.

  As described above, according to the present invention, even when there are candidates for associating a vast number of scenarios with videos, the burden on the operator can be reduced by presenting several correspondence candidates to the operator.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

  FIG. 3 shows the configuration of the correspondence verification support apparatus according to the embodiment of the present invention.

  The correspondence verification support apparatus shown in the figure includes a sequence association candidate reading unit 1, a node / link value setting unit 2, a candidate presenting unit 3, an operator input reading unit 4, a sequence association correcting unit 5, and the number of sequence association candidates. It comprises a count unit 6, a sequence association candidate storage unit 7, a sequence association result storage unit 8, a display device 9, and an input device 10.

  The sequence association candidate reading unit 1 reads the sequence association candidate from the sequence association candidate storage unit 7 and determines a node and a link.

  The node / link value setting unit 2 sets a value for each node / link from the sequence association candidate, the node, and the link.

  The candidate presentation unit 3 determines a candidate to be presented to the operator using the value of the node / link, and outputs the candidate to the display device 9.

  The operator input reading unit 4 acquires an input from an operator sent via the input device 10.

  The sequence association candidate correction unit 5 deletes the sequence association candidate using the input from the operator.

  The sequence association candidate number counting unit 6 counts the number of remaining sequence association candidates as a result of the reduction by the sequence association candidate correction unit 5, and when the number of sequence association candidates becomes 1, The remaining series association candidates are written in the association result storage unit 8.

  The series association candidate storage unit 7 stores a group of association candidates as shown in FIG. In FIG. 4, there are five sets of association candidates from A to E. In the following, A, B, etc. are referred to as “sequence association candidates”, and (a, b) therein are “association candidates”. Call it.

  The sequence association result storage unit 8 stores the finally remaining sequence association candidates.

  The display device 9 is a display or the like that presents candidates passed from the candidate presentation unit 3.

  The input device 10 inputs candidates for series association to be deleted by the user.

  Next, the operation in the above configuration will be described.

  FIG. 5 is a flowchart of the overall operation in one embodiment of the present invention.

  Step 101) The sequence association candidate reading unit 1 reads a sequence association candidate set from the sequence association candidate storage unit 7, temporarily stores it in a storage means (not shown), and the sequence association A node is detected for a set of candidates. For example, the above example is represented by a route diagram as shown in FIG. When expressed in a route diagram, the branching portion becomes a node.

  Step 102) The node / link value setting unit 2 sets values for each node and the connection (link) between the nodes. Hereinafter, these set values are referred to as a node value and a link value, respectively.

  Step 103) The candidate presentation unit 3 outputs the association candidate (Ni) read in Step 101 to the display device 9 based on the link value set in Step 102.

  Step 104) When the operator designates an unnecessary sequence association candidate from the input device 10, the operator input reading unit 4 receives an input from the operator and passes the result to the sequence association candidate correcting unit 5. The sequence association candidate correction unit 5 deletes the sequence association candidate designated by the operator.

  In this process, for example, when an association candidate (a, b) is presented, the operator's decision is to determine whether the association between a and b is correct. In the case of "", only those in which the association (a, b) exists in the sequence association candidates remain as the sequence association candidates, and the others are deleted. On the other hand, when the operator determines that “correspondence is not correctly associated”, only those that do not have the association (a, b) among the series association candidates are left as candidates.

  Step 105) The sequence association candidate number counting unit 6 confirms the number of sequence association candidates. If the number is 1, the process ends. If not, the sequence returns to Step 101.

  Next, the process of step 101 will be described in detail.

  FIG. 7 is a flowchart of node detection processing according to an embodiment of the present invention.

  Step 201) The sequence association candidate reading unit 1 searches for association candidates included in the plurality of sequence association candidates read from the sequence association candidate storage unit 7, and sets them as S1, S2,. The set is Si (S = S1, S2,..., Ss).

  Step 202) As initial values, i = 0 and j = 0.

  Step 203) i is incremented (i = i + 1).

  Step 204) Among the sequence association candidates, the association candidate positioned next to Si is examined.

  Step 205) It is determined whether or not all the association candidates examined in Step 204 are the same. If they are the same, the process proceeds to step 207, and if they are different, the process proceeds to step 206.

  Step 206) Si is set as the node Nj and j is incremented (j = j + 1).

  Step 207) It is determined whether all the elements of S have been checked. If not, the process proceeds to Step 203. If all are checked, the process proceeds to Step 208.

  Step 208) A link is established between the nodes N based on the sequence association candidates.

  Next, the detailed operation of step 102 will be described. As one form of step 102, the number of sequence association candidates passing through the node is set as the value of each node.

  FIG. 8 is a flowchart (part 1) of the node value / link value setting process in the embodiment of the invention.

  Step 301) The node / link value setting unit 2 sets the value of the terminal node to 1.

  Step 302) i = 0.

  Step 303) Increment i (i = i + 1).

Step 304) Check whether all node values are set in all nodes linked from the node Ni. If all the node values are set, the process proceeds to step 305, and if not, the process proceeds to step 307 .

  Step 305) The node values of all nodes linked from the node Ni are added to obtain the node value of Ni.

  Step 306) A link value Ni is set for all links linking the node Ni.

  Step 307) It is confirmed whether or not node values have been set for all the nodes. If node values have been set, the processing is terminated. Otherwise, the routine proceeds to Step 302.

  Next, another mode for carrying out the above step 102 will be described.

  In this form, for each node value and link value, the sum of real time that can be deleted from the set of sequence correspondence candidates by determining whether or not the node or link passes is determined as the node value and link value. It is to set. This form will be described with reference to FIG.

  FIG. 9 is a diagram for explaining node value / link value setting processing (part 2) according to the embodiment of the present invention. In the figure, the number given to the link value indicated by the arrow represents the real time of the link.

  When the operator determines whether or not to pass the thick line link in FIG. 9, the total time disappearing when it is determined to pass is “16”, and the total time disappearing when it is determined not to pass is “ 10 ”, and a total time of“ 26 ”is deleted. Such processing is calculated for all links as shown in FIG. This process will be described with reference to FIG.

  FIG. 11 is a flowchart (part 2) of the node value / link value setting process according to the embodiment of the present invention.

  Step 401) The link / node value setting unit 2 performs the following processing for all links.

  Step 402) Obtain a sequence association candidate when a route that does not pass through the link is deleted from the sequence association candidate.

  Step 403) As a result, the sum of the link times of the lost links is obtained, and this is set to “L−”.

From step 404) sequence correspondence candidate obtains the series association candidates when removing through Ru path the link.

  Step 405) As a result, the sum of the link times of the lost links is obtained and set to “L +”.

Step 406) The sum of L− and L + is divided by the link time to obtain the link value of the link.
Step 407) It is confirmed whether or not the link value has been set for all links. If the link value has been set, the process is terminated. Otherwise, the process returns to Step 402.

  Next, the candidate presentation process in step 103 will be described.

  In step 103, a series association candidate is presented to the operator according to the link value set in step 102, and an association candidate to be urged by the operator is selected.

  FIG. 12 is a flowchart (part 1) of the association candidate selection process presented to the operator according to the embodiment of the present invention. Here, a case where the number of routes is set as the node value and the link value in the above-described step 102 will be described.

  Step 501) The candidate presentation unit 3 obtains the maximum value of the link from the link value set in Step 102 and substitutes it in Max.

  Step 502) Find the link (Li) whose link value is closest to Max / 2.

  Step 503) It is determined whether or not there is a node having a link whose link Li has the link value Max / 2. If there is a node, the process proceeds to Step 504. If not, the process proceeds to Step 505.

  Step 504) An arbitrary association candidate included in the link Li is presented to the operator.

  Step 505) It is determined whether or not there are a plurality of links whose link value is Max / 2. If there are, the process proceeds to Step 506, and if not, the process proceeds to Step 507.

  Step 506) The candidate for the link Li having the maximum link value among the plurality of links is presented to the operator.

  Step 507) One of the association candidates is presented to the operator from among the links Li.

  Next, the operation in the case where the link value is set in the above-described step 102 in real time that can delete the video will be described.

  FIG. 13 is a flowchart (part 2) of the association candidate selection process presented to the operator in the embodiment of the present invention.

  Step 601) The candidate presentation unit 3 searches for a link having the maximum link value.

  Step 602) It is determined whether or not there are a plurality of links having the maximum link value.

  Step 603) The correspondence candidates in the link are presented to the operator.

  Step 604) The correspondence candidate in an arbitrary link among the links having the maximum link value is presented to the operator.

  The operator designates a candidate to be deleted from the association candidate presented as described above from the input device 10.

  As a result, the operator input reading unit 4 passes the sequence association candidate instructed by the operator to the sequence association candidate correction unit 5.

  The subsequent processing is as described in steps 104 and 105 in FIG.

  Embodiments of the present invention will be described below with reference to the drawings.

  In the present embodiment, the association between a baseball video and a scenario will be described as an example.

  An example in which the node / link value setting unit 2 sets the number of paths as the node value and the link value in step 102 will be described with reference to FIG.

  FIG. 14 is a flowchart (part 1) of the association candidate selection process presented to the operator according to an embodiment of the present invention. In the following example, it is assumed that the number of occurrences of each event has been obtained from the baseball scorebook, and the sequence association candidates as shown in FIG. 15 are read, and the node is shown in the route diagram image as shown in FIG. Detected.

  Step 701) The candidate presentation unit 3 obtains the number of occurrences for each event from the information accompanying the video.

  Step 702) With respect to an event having the i-th occurrence frequency, the number of association candidates with the event is obtained.

  Step 703) It is determined whether or not the value is 1. If it is 1, it is not necessary to make a determination that the number of candidates is 1, so the process proceeds to step 705, and if not, the process proceeds to step 704.

  Step 704) The correspondence candidate with the event is presented to the operator and prompted to input the correct one.

  Step 705) It is determined whether the number of occurrences of the event is equal to or less than a predetermined threshold value. If it is equal to or less than the threshold value, the process proceeds to Step 606. Otherwise, the process ends.

  Step 706) Increment i (i = i + 1) and go to Step 702.

  When the candidate presenting unit 3 presents the association candidate to the operator from the links, any event may be used as long as the operator can determine whether or not the correct association is made. For example, in the case of baseball, if the count is displayed in the telop in the video, or if the announcer utters "throwing the fourth pitcher pitch ..." The operation for reducing the burden on the operator is shown below.

  FIG. 17 is a flowchart (part 2) of the association candidate selection process presented to the operator according to the embodiment of this invention.

  Step 801) The number of occurrences of an event existing in the link is counted in advance. Note that the method of counting the number of times an event has occurred can be realized by, for example, searching a score book corresponding to a video section, extracting an event, and counting the number of times.

  Step 802) It is determined whether or not there is an event whose occurrence count is 1. If it exists, the process proceeds to step 803, and if it does not exist, the process proceeds to step 804.

  Step 803) It is determined whether or not the event whose occurrence count is 1 is a type of event that can be detected with high accuracy (for example, a hitting sound). As a determination method, an event obtained by event detection and its accuracy (for example, information such as “hit sound / high, catch sound / low”) are set in a table (not shown), There is a method of judging from the table and scenario information. If the event can be detected with high accuracy, the process proceeds to step 806; otherwise, the process proceeds to step 805.

  Step 804) N adjacent events existing in the link are grouped into a new event.

  Step 805) It is determined whether or not there are a plurality of events whose occurrence count is 1 among events of a kind that cannot be detected with such a high degree of accuracy (for example, a catching sound). If there are a plurality of events, the procedure proceeds to Step 809. Step 810 is entered.

  Step 806) It is determined whether or not there are a plurality of events that can be detected with high accuracy and the number of occurrences is 1. If there are a plurality of events, the process proceeds to Step 809; otherwise, the process proceeds to Step 810.

  Step 807) It is determined whether there is an event with the occurrence count of 1. If there is an event, the process proceeds to Step 808, and if not, the process proceeds to Step 811.

  Step 808) Among the new events created by grouping together the adjacent n events in Step 804, an event containing the largest number of events that can be detected with high accuracy is searched.

  Step 809) Among them, any one event is presented to the operator and the process is terminated.

  Step 810) Present the event to the operator and finish.

  Step 811) Increment n (n = n + 1) and proceed to Step 804.

  Note that the sequence association candidate reading unit 1, the node / link value setting unit 2, the candidate presenting unit 3, the operator input reading unit 4, the sequence association candidate correcting unit 5, the sequence association of the correspondence verification support apparatus shown in FIG. The processing of the candidate count unit 6 may be constructed as a program, installed in a computer used as a correspondence verification support apparatus, executed by a control unit such as a CPU, or distributed via a network.

  In addition, the constructed program is stored in a hard disk connected to a computer used as a correspondence verification support device, a flexible disk, a CD-ROM or other portable storage medium, and is installed in the computer when it is executed. It is also possible to do.

  The present invention is not limited to the above-described embodiments and examples, and various modifications and applications are possible within the scope of the claims.

  The present invention can be applied to a system for associating a scenario with a video.

It is a figure for demonstrating the principle of this invention. It is a principle block diagram of this invention. It is a block diagram of the correspondence verification support apparatus in one embodiment of this invention. It is an example of the series correlation candidate memory | storage part in one embodiment of this invention. It is a flowchart of the whole operation | movement in one embodiment of this invention. It is a figure for demonstrating the node detection in one embodiment of this invention. It is a flowchart of the node detection process in one embodiment of this invention. It is a flowchart (the 1) of the node value and link value setting process in one embodiment of this invention. It is a figure for demonstrating the node value and link value setting process (the 2) in one embodiment of this invention. It is a figure for demonstrating the sum of the real time which can be deleted from the set of the series matching candidate in one embodiment of this invention. It is a flowchart (the 2) of the setting process of the node value and link value in one embodiment of this invention. It is a flowchart (the 1) of the matching candidate selection process shown to the operator in one embodiment of this invention. It is a flowchart (the 2) of the matching candidate selection process shown to the operator in one embodiment of this invention. It is a flowchart (the 1) of the matching candidate selection process shown to the operator of one Example of this invention. It is the group of the matching candidate acquired by the candidate presentation part of one Example of this invention. It is a figure which shows the node detection of one Example of this invention. It is a flowchart (the 2) of the matching candidate selection process shown to the operator of one Example of this invention.

Explanation of symbols

1 Sequence association candidate input means, sequence association candidate reading unit 2 node / link value setting unit, node / link value setting unit 3 sequence association candidate presentation unit, candidate presentation unit 4 operator input reading unit 5 deletion unit, sequence correspondence Addition candidate modification unit 6 Sequence association candidate count unit 7 Storage means, sequence association candidate storage unit 8 Sequence association result storage unit 9 Display device 10 Input device

Claims (7)

In the correspondence verification support method for verifying the associated video and scenario,
A sequence association candidate input process in which a sequence association candidate including at least one association candidate in which a video and a scenario are associated is read from the storage means and input;
A node detection process for detecting a node from the sequence correspondence candidates;
A node / link value setting process for setting a node value and a link value for each node and a combination of the nodes (hereinafter referred to as a link);
The link having the maximum link value is extracted from all the links, the association candidate in the link having the link value closest to ½ of the link having the maximum link value is output to the display means, and the unnecessary series A matching candidate presentation process that requests input of matching candidates;
A deletion process of obtaining a sequence association candidate selected from the operator and deleting from the sequence association candidate in the storage means;
And
In the node link value setting process,
The end node value is 1,
The node counter i is incremented by 1, and the node values of all the nodes linked from the node Ni are added to obtain the node value of Ni, and Ni is set as the link value for all the links linking the node Ni. A correspondence verification support method characterized by executing an algorithm for all nodes linked from the node Ni and repeating the process until all node values are set. In the correspondence verification support method for verifying the associated video and scenario,
A sequence association candidate input process in which a sequence association candidate including at least one association candidate in which a video and a scenario are associated is read from the storage means and input;
A node detection process for detecting a node from the sequence correspondence candidates;
A link value that sets, as a link value, the sum of real time that can be deleted from the set of sequence association candidates by determining whether or not the link (hereinafter referred to as a link) of each node passes through the link. Setting process,
Extracting a link having the maximum link value, outputting a matching candidate in the link to a display unit, and requesting an input of an unnecessary sequence matching candidate ;
A deletion process of obtaining a sequence association candidate selected from the operator and deleting from the sequence association candidate in the storage means;
A correspondence verification support method characterized by In the link value setting process,
For all links,
Obtaining a correspondence candidate when a route that does not pass through a link is deleted from the series correspondence candidate, and obtaining a sum (L−) of link time that is a real time given to a link that has disappeared as a result,
Obtaining a series association candidate when a route passing through a link is deleted from the series association candidate, and obtaining a sum of link times (L +) that is a real time given to a link that has disappeared as a result,
Executes an algorithm for dividing the sum of L− and L + by a link time and setting the value as a link value
The correspondence verification support method according to claim 2 . A correspondence verification support device for verifying a correlated video and a scenario,
A sequence association candidate input means for reading and inputting a sequence association candidate including at least one association candidate in which a video and a scenario are associated with each other;
Node detecting means for detecting a node from the sequence correspondence candidates;
A node / link value setting means for setting a node value and a link value for each node and a combination of the nodes (hereinafter referred to as a link);
The link having the maximum link value is extracted from all the links, the association candidate in the link having the link value closest to ½ of the link having the maximum link value is output to the display means, and the unnecessary series An association candidate presenting means for requesting input of an association candidate;
A deletion unit that acquires the sequence association candidate selected from the operator and deletes the sequence association candidate from the storage unit;
Have
The node / link value setting means includes:
The end node value is 1,
The node counter i is incremented by 1, and the node values of all the nodes linked from the node Ni are added to obtain the node value of Ni, and Ni is set as the link value for all the links linking the node Ni. A correspondence verification support apparatus including means for executing an algorithm for all nodes linked from the node Ni and repeating the process until all node values are set. A correspondence verification support device for verifying a correlated video and a scenario,
A sequence association candidate input means for reading and inputting a sequence association candidate including at least one association candidate in which a video and a scenario are associated with each other;
Node detecting means for detecting a node from the sequence correspondence candidates;
For binding of each node (hereinafter referred to as link), by determining whether or not to pass through the link, sets the sum of the actual time can be deleted from the set of sequences correspondence candidate as a link value Link value setting means;
The link having the maximum link value is extracted, it is determined whether there are a plurality of links having the maximum link value, and if there are, the association in an arbitrary link among the links having the maximum link value. A candidate is output to the display means, and if it is singular, an association candidate presenting means for outputting an association candidate in the link to the display means and requesting input of an unnecessary series association candidate ;
A deletion unit that acquires the sequence association candidate selected from the operator and deletes the sequence association candidate from the storage unit;
A correspondence verification support apparatus characterized by comprising: The link value setting means includes
For all links,
Obtaining a correspondence candidate when a route that does not pass through a link is deleted from the series correspondence candidate, and obtaining a sum (L−) of link time that is a real time given to a link that has disappeared as a result,
Obtaining a series association candidate when a route passing through a link is deleted from the series association candidate, and obtaining a sum of link times (L +) that is a real time given to a link that has disappeared as a result,
6. The correspondence verification support apparatus according to claim 5 , further comprising means for dividing the sum of L- and L + by a link time and setting the value as a link value . A correspondence verification support program for causing a computer to function as each means constituting the correspondence verification support apparatus according to any one of claims 4 to 6 .

Images