KR20140031450A - Method for producing a statement comparison service, and apparatus applied to the same - Google Patents

Abstract

Disclosed are a method for providing a statement comparison service and an apparatus applied to the same. The method for providing a statement comparison service and the apparatus applied to the same according to the present invention are configured: to extract more than one statement corresponding to a determined service execution item from a predetermined data search pool after setting more than one among a statement generating subject (e.g. politician A) and a statement topic (e.g. policy issue a) as a service execution item when a user requests a statement comparison service; to generate a statement comparison result based on an statement intention analysis result from each of the extracted more than one statement; and to provide the generated statement comparison result in response to the request for the statement comparison service. As a result, the present invention allows a user to easily receive statement related information requested by the user, can provide changing points in time and detailed changes related to the corresponding statement, and can provide an reliability evaluation of the corresponding statement if necessary. [Reference numerals] (100) Terminal device; (200) Server device; (AA) User

Description

METHOD FOR PRODUCING A STATEMENT COMPARISON SERVICE, AND APPARATUS APPLIED TO THE SAME}

The present invention relates to a method for providing a speech comparison service and an apparatus applied thereto, and more particularly, to provide a speech comparison service including whether or not to change speech contents with respect to one or more speeches classified by a specific criterion among the speeches disclosed from the past to the present. The present invention relates to a method for providing a speech comparison service and an apparatus applied thereto.

In general, an information providing environment is provided through which a variety of information can be accessed through a medium such as the Internet. The user can check a specific person's remarks on a specific subject using the information providing environment.

For example, when a user wants to confirm a politician's remarks on a policy matter, it is possible to obtain desired information through a related information retrieval process.

In other words, the prior art has a method of sorting and providing search results related to the politician's remarks on a policy matter by 'accuracy' or 'latest order', so that the user has to review the search results one by one. There is a hassle to extract the politician's remarks on a policy matter from the search results.

In addition, according to the prior art, there is a limit to obtain the politician's remarks on a policy matter depending on the information retrieval ability of the user, so that a user who lacks the information retrieval ability is limited to the data at a specific search point. There is a problem that politicians are more likely to trust their comments on a policy issue.

In other words, there is a possibility that the politician's remarks regarding a policy matter may change at a certain point in time so that the remarks between the past and the present may be different, but the user may be able to change the remarks of the remarks that may exist due to the limitations of the prior art. There will be a problem in the prior art that is not easy to identify.

Accordingly, the present invention has been made to solve the above problems, and an object of the present invention is to provide a subject (eg, a politician) and a subject (eg, a policy matter) when a request for use of the speech comparison service is requested. Set one or more as service execution items, and then compare one or more remarks corresponding to the set service execution items from a predetermined data search pool and analyze the remarks of each remark on the extracted one or more remarks. A method of providing a speech comparison service for providing a speech comparison result generated after generating a result as a response to a request for using the speech comparison service, and an apparatus applied thereto.

In accordance with another aspect of the present invention, there is provided a method of providing a speech comparison service, wherein at least one of a speech generating subject and a speech topic is set as a service execution item from a request for using a speech comparison service in a server device. Extracting one or more remarks corresponding to a service execution item from a predetermined data search pool; analyzing the intention of each remark for the one or more remarks; and comparing the one or more remarks based on an analysis result Generating a speech comparison result and providing the speech comparison result in response to a request for using the speech comparison service.

Preferably, the method for providing a speech comparison service further includes at least one of a message indicating a speech content change and one or more times of speech content change in the speech comparison result when the speech content is changed among the one or more speeches through the speech comparison result. It further comprises a step.

Preferably, in the method of providing a speech comparison service, when the speech comparison result includes the speech content changing time point, the first and second speeches are classified and sorted based on the speech content changing time point. And extracting at least one service providing statement that satisfies a predetermined service provision criterion from the at least one statement, and further including the at least one service providing statement in the result of comparing the speaking.

Preferably, in the method of providing a speech comparison service, when the speech comparison result includes two or more times of changing the contents of the speech, the first and second relations of the one or more speeches are determined based on the time of changing two or more contents of the speech. And classifying and sorting one or more service providing remarks satisfying a predetermined service provision criterion from the one or more remarks, and further including the one or more service providing remarks in the remark comparison result. It is done.

Preferably, in the method of providing a speech comparison service, when the speech comparison result is included in the speech content change time, the first speech of one or more speeches corresponding to a previous time point with respect to the time of changing the speech content among the one or more speeches is included. Performing a second speech evaluation on one or more speeches corresponding to a later point in time of the evaluation and changing the speech content among the one or more speeches; and comparing the speech comparison result of the first speech evaluation and the second speech evaluation. It further comprises a step further comprising.

Preferably, at least one of the first speech evaluation and the second speech evaluation is executed using at least one of opinion statistics and information on whether speech is executed.

Preferably, the method of providing a speech comparison service further comprises the step of classifying the one or more speeches by a predetermined type and then verifying whether the one or more speeches are valid for each of the divided types.

Preferably, in the method of providing a speech comparison service, when the service execution item is set as the speech generating subject and the speech topic, the speech topic corresponding to the speech generating subject is one or more when the speech generating subject is input. It further comprises a step.

Preferably, the speech comparison service providing method further comprises the step of recommending at least one service execution item that satisfies a predetermined automatic recommendation guide condition upon request for use of the speech comparison service.

Preferably, the method for providing a speech comparison service further includes generating speech trend information based on the speech intent and the starting point of speech for the one or more speeches, and further including the speech trend information in the speech comparison result. It is characterized by.

Preferably, the method for providing a speech comparison service, when the speech generating subjects included in the service execution item is two or more, generates the speech comparing results for two or more speech generating subjects, or for the two or more speech generating subjects. Generating control analysis information on the corresponding relationship between each other, and further comprising the step of including the control analysis information in the speech comparison results.

In addition, the server apparatus for providing a speech comparison service according to the second aspect of the present invention for achieving the above object, after setting at least one of the speech generating subject and the subject to be a service execution item from the request for use of the speech comparison service An extraction unit for extracting one or more remarks corresponding to the service execution item from a predetermined data search pool, an analysis unit for analyzing the intention of each remark for the one or more remarks, and an analysis result for the one or more remarks And a provision unit configured to generate a speech comparison result by performing a comparison and to provide the speech comparison result as a response to a request for using the speech comparison service.

Preferably, the data retrieval pool is an information retrieval range based on a communication network or an information retrieval range for a separate database constructed to provide the speech comparison service.

Preferably, the server apparatus for providing a speech comparison service, when the data search pool is built through the database, if the predetermined up-date execution criteria are met, an up-update for the data search pool is executed. It further comprises a date unit.

Preferably, the analysis unit is characterized in that the analysis of the speech intention of each statement for the one or more statements based on a predetermined information resource semantic analysis model.

Therefore, in the present invention, when there is a request for using the speech comparison service, at least one of the speech generating subject (for example, A politician) and the speech topic (for example, a policy matter) is set as the service execution item, and then the corresponding service execution item is set. Extracts one or more remarks from a predetermined data retrieval pool, generates a remark comparison result based on the result of analyzing the remarks of the remarks of the remarks of the remarks one or more remarks, and then sends the generated remark comparison result to the remark comparison service. By providing a response to a request for using the service, the user can easily receive information on the requested speech, and can also provide a time point and a change history of the speech and, if necessary, a reliability evaluation of the speech. There is an advantage to this.

1 is a view showing an example comparison service providing system according to the present invention;
2 is a diagram illustrating an example of the server apparatus shown in FIG. 1;
3 is a diagram illustrating a speech comparison result screen generated by the server apparatus of FIG. 1 according to an embodiment;
4 is a diagram illustrating another example of a speech comparison result screen generated by the server apparatus illustrated in FIG. 1;
5 is a diagram illustrating an operation process of a speech comparison service providing system according to an embodiment of the present invention;
6 is a diagram illustrating another example of an operation process of a speech comparison service providing system according to the present invention;
7 is a view showing an operation process of a speech comparison service providing system according to an embodiment of the present invention;
8 is a view showing an operation process of a speech comparison service providing system according to an embodiment of the present invention;
9 is a view showing another example of the operation of the speech comparison service providing system according to the present invention;
FIG. 10 is a flowchart illustrating an operation process of a speech comparison service providing system according to an exemplary embodiment of the present invention.

Hereinafter, a preferred embodiment of the speech comparison service providing system according to the present invention will be described in detail with reference to the accompanying drawings.

1 is a diagram illustrating an example comparison service providing system according to the present invention. As shown by way of example only in FIG. 1, the speech comparison service providing system can easily provide a user with one or more speeches classified according to a specific criterion among the speeches disclosed from the past to the present, and the implications for the one or more speeches. Can be analyzed and provided to the user.

That is, the speech comparison service providing system may provide a speech comparison result as a response when a request for providing speech comparison service is received from the terminal apparatus 100 and the terminal apparatus 100 handled by the user for using the speech comparison service. Server device 200 may be included.

The terminal device 100 may activate a speech comparison service provided from the server device 200 by connecting to a communication network (for example, a network including at least one of a wired network and a wireless network) and is dedicated to a specific user. The device 100 or the terminal device 100 that can be used in common.

If there is a request for using the speech comparison service from the terminal apparatus 100, the server apparatus 200 may provide the user with one or more speeches classified by a specific criterion as described above, or provide implications for the one or more speeches. In addition to this, it is also possible to provide the user with the implications for the one or more remarks while providing the user with the one or more remarks.

Here, the implications for one or more remarks are service contents additionally provided in addition to the remarks themselves, and include at least one of a remarks change point, remark evaluation, validity of remarks, remark trends, and control analysis. This will be described in detail.

Looking at the detailed configuration of the server device 200 with reference to Figure 2, the server device 200 sets at least one of the speech generating subject and the subject to the service execution items from the request to use the speech comparison service by the terminal device 100 Then, the extraction unit 210 extracts one or more remarks corresponding to the set service execution items from a predetermined data search pool, an analysis unit 220 and an analysis unit which analyzes the intentions of the respective remarks for the extracted one or more remarks. Comparing the one or more utterances based on the result analyzed by 220 to generate a speech comparison result as a result and to provide the generated speech comparison result in response to the requesting terminal device 100. It may include a providing unit 230.

Here, the person generating a speech refers to one or more of a specific person and a specific group that can generate publicly shareable speech.

When the service execution item is set as the statement generating subject (for example, when the service execution item is input as the A politician, the server apparatus 200 sets the A politician as the A speech generating subject), the extractor 210 generates the speech. One or more remarks corresponding to the subject are extracted from the data retrieval pool, and when a specific period or a specific point in time is set, the one or more remarks corresponding to the remark generating subject are based on the set specific period or a specific point in time. Can be extracted.

In addition, when the service execution item is set as the speech generating subject, the analysis unit 220 analyzes the speech intention of each speech for one or more speech corresponding to the speech generating subject and then provides the provision to the providing unit 230. The providing unit 230 generates a speech comparison result for providing to the terminal device 100 based on the received analysis result, and provides the generated speech comparison result to the terminal device 100.

The comparison results at this time may include one or more of the point of change of the statement, the evaluation of the statement, the validity of the statement, and the trend of the statement on the basis of the speaker.

The speech evaluation is preferably performed for each topic of speech that is performed for each speech or divided by the point of change of the speech content.

The speech trend may preferably include one or more of changes in the speech topic by time of the speech generating subject, an issue in question, and a specific point in time.

Meanwhile, as shown in FIG. 3 as an example, when the service execution item is set as the remark generating subject and the remark topic (for example, when the service execution item is input as A politician and a policy matter, the server apparatus 200 is A politician). Set as a spoken subject, a policy matters as a spoken subject), and the extractor 210 may extract one or more utterances corresponding to the generated topic and the spoken subject from the data search pool.

That is, as shown in FIG. 3, the extractor 210 extracts the first to fourth speeches, and the analyzer 220 may analyze the intention of each of the first to fourth speeches. have.

The analysis unit 220 is a first intention intention for the first statement, a first intention intention for the second statement, a second intention intention for the third statement and a second intention for the fourth statement. Can be analyzed.

For example, it is possible that the first intention to say 'negative' and the second intention to mean 'positive', and furthermore, the first intention to say 'the opinion containing the first specific meaning' and the second It is also possible to mean "an opinion with a second specific meaning."

To this end, the analysis unit 220 analyzes and executes the intention of each remark for one or more remarks based on a predetermined information resource semantic analysis model.

As an example of an information resource semantic analysis model, “A politician, a phrase corresponding to a specific statement, argued as follows. "A policy matters should take precedence over other policy matters and must be implemented within this year." In "A politicians", "a policy matters" and "policy matters" are recognized as individual names. Others, than, 'priority', 'be', 'this year', 'in', 'must', 'enforcement', 'should', 'should' are distinguished by non-object names, not individual names.

Then, after recognizing the pattern formed between the object name and the non-object name, the label stored in advance in correspondence with the recognized pattern is extracted.

Here, since the label includes the meaning of the corresponding syntax, when the label is extracted as described above, it is possible to determine the meaning of the corresponding syntax.

In addition, various methods for achieving the information resource semantic analysis model have been serviced to the commercialization level, and thus a detailed description of the configuration of the analysis unit 220 will be omitted.

Referring to FIG. 3 again, by making a third remark on '2011.12', the subject A reproducer maintains a first remark on the remark a topic and then changes it to a second remark on '2011.12'. .

In this case, the providing unit 230 may set the starting point of the third speech corresponding to the '2011.12' as the speech content changing time, and then display the factor for the set speech content changing time on the speech comparison result screen. Do.

As shown in FIG. 3, the providing unit 230 displays a factor for the point of time of the change of the statement together with one or more remarks, or a message indicating the change of the remarks without displaying one or more remarks on the remark comparison result screen; It is also possible to display one or more of the factors for the point of change of speech on the speech comparison result screen.

One or more services that satisfy the predetermined service provision criteria after sorting the front and rear relationships of the first to fourth statements based on the point of time when the contents of the statement change, It is possible to extract the offer remarks and include the extracted one or more service provision remarks in the remark comparison result.

For example, when the service providing criteria is a speech that is distinguished before and after the change of the speech content as the service provision speech, the speech that may be the service provision speech in the example of FIG. 3 is the second speech and the third speech. This is true.

That is, only the second remark and the third remark are set as the service provision remarks and included in the remark comparison result, and the first remark and the fourth remark may be excluded from the remark comparison result.

The provider 230 may include the speech evaluation in the speech comparison result.

For example, as an example, the providing unit 230 may include a first remark evaluation for one or more remarks corresponding to a previous point in time, and at least one remark corresponding to a later point in time when the remarks change point is changed. A second speech assessment can be carried out.

The provider 230 may execute the first speech evaluation and the second speech evaluation by using one or more of opinion statistics collected as corresponding to each speech and information on whether or not each speech is executed.

Meanwhile, the server device 200 further divides one or more remarks extracted from the extractor 210 by a predetermined type, and further includes a verification unit (not shown) for verifying validity of one or more remarks by the divided types. It may include.

For example, the first type among the predetermined types corresponds to contents registered in a media directly operated by a specific person such as Twitter or blog of a specific person, or contents included in a document (eg, policy development document) including a specific person's name and a specific person's signature. It may be equivalent to.

The second type among the predetermined types may be remarks that can be judged as a cited portion such as "" or "" of specific news content.

In addition, the third type among the predetermined types may be content registered by a specific person as spoken by a general user rather than a specific person.

That is, the verification unit (not shown) may perform verification for each statement by using the above-described attribute of each type.

For example, a speech corresponding to the first type is registered as a valid speech without performing verification, and a speech corresponding to the second type is registered as a valid speech when 10 or more news items containing the same content are found. And, the speech corresponding to the third type may be registered as a valid speech when 10 or more general users start to speak the same contents.

In addition, the provision unit 230 may calculate the speech efficiency based on the verification result provided from the verification unit (not shown) and reflect the speech efficiency in the speech comparison result. Such utilization of speech efficiency can be used to determine the public opinion generation process or the impact of public opinion on the subject.

The retrieval search range of the extractor 210 may be an information retrieval range based on a communication network or an information retrieval range for a separate database constructed to provide a remark comparison service.

When the server device 200 includes the data search pool as a separate database built to provide the speech comparison service, the server apparatus 200 executes the update on the data search pool when a predetermined up-date execution criterion is met. It is preferable to further include an up-date portion (not shown).

For example, the update criteria may be set to execute an update that adds remarks for a particular person to the data search pool if news for that person lasts more than 10 times a day. Even if news for more than 10 days a week lasts, you can set up an update that adds remarks on that particular topic to the search pool.

In addition, when the server apparatus 200 includes the data retrieval pool as a separate database constructed to provide the speech comparison service, the server apparatus 200 speaks when it is assumed that the service execution item requested for the service is set as the speech generating subject and the speech topic. The apparatus may further include a service input guide unit for guiding a user with one or more speech topics corresponding to the input speech generating subject upon input of the generating subject.

Furthermore, the service input guide unit may also provide a function of recommending at least one of the subject and the subject of speech to satisfy the predetermined automatic recommendation guide condition to the user.

The automatic recommendation guideline condition is a condition for automatically recommending to a user who wants to use the service by automatically selecting one or more of a related remark generating subject and a remarking topic when the related news explodes or is viewed more than a predetermined number of times. It is called.

Referring to FIG. 4, a case in which a statement generating subject is 2 or more for a statement of a subject included in a service execution item will be described.

At this time, the providing unit 230 generates a speech comparison result for each of two or more speech generating subjects, or generates control analysis information on a correspondence relationship between two or more speech generating subjects, and generates the result of the control analysis information. It can be included in.

Referring to FIG. 4 as an example, the A-speaking generating entity has a change point of the speaking content at '2011.12', when the third speaking is made, and it is determined that the speaking of the changed content is maintained.

On the other hand, the B-speaking subject continues the second intention while continuing the first to fourth remarks.

Therefore, in the control analysis information, the current remarks on the topic a of the subject A and the subject B are the same as the second intention, and the subject A is the last to change the existing statement to the current statement. It may be necessary to judge the statement change history.

5 is a diagram illustrating an operation process of a speech comparison service providing system according to an exemplary embodiment of the present invention. As shown only by way of example in FIG. 5, the method of providing a speech comparison service includes a service for at least one of a speech generating subject and a speech topic from a request for using the speech comparison service provided from the terminal apparatus 100 in the server apparatus 200. The execution item is set (S100).

Thereafter, the server device 200 extracts one or more remarks corresponding to the set service execution item from the data search pool (S102).

The server device 200 analyzes the intention of each utterance for the extracted one or more utterances, and then generates a result of comparing the correlations between the utterances based on the analysis result (S104 to S108).

Thereafter, the server apparatus 200 provides the speech comparison result generated in step S108 as a response to the terminal apparatus 100 that has made a request for using the speech comparison service (S110).

If there is an end of use of the speech comparison service, the performance of the above-mentioned processes is also terminated (S112).

6 is a diagram illustrating an operation process of a speech comparison service providing system according to an exemplary embodiment of the present invention. As shown only as an example in FIG. 6, the server apparatus 200 starts a verification process for verifying validity of one or more remarks extracted from the data retrieval pool (S200).

Subsequently, the server apparatus 200 classifies one or more remarks extracted from the data retrieval pool by a predetermined type, and then applies a verification process corresponding to each classified type (S202 and S204).

When determining whether the extracted one or more utterances are valid (S206), if an invalid utterance does not occur, all of them are treated as having passed the verification and registered as one or more uttered utterances as valid utterances (S208).

After that, if it is set as the speech verification completion, the execution of the above-mentioned verification processes is also terminated (S210).

In the step S206, when an invalid statement occurs, the process of registering the verified statement as a valid statement is performed with the exception of the unverified statement not included in the registration object (S212).

7 is a diagram illustrating another example of an operation of the speech comparison service providing system according to the present invention. As shown only as an example in FIG. 7, the server apparatus 200 generates a result of analyzing the intention of each statement of the one or more remarks found to correspond to the service execution item, and then generates one or more remarks based on the result. The comparison is performed (S300 and S302).

Thereafter, when one of the one or more remarks has a remark that changes the remark content, it is determined whether to remark the change of the remark content, and then it is determined whether to perform remark filtering based on the determined remark content change time (S304 to S308).

When the server apparatus 200 is set to perform the utterance filtering in a predetermined service deployment process, the server apparatus 200 classifies the one or more utterances based on the point of time when the contents of the utterance is changed, and then sorts the front and rear relations. At least one service providing statement that satisfies a predetermined service providing criterion is extracted from the statement (S310).

At least one service providing statement extracted at step S301 is reflected in the result of comparing speech (S312).

8 is a diagram illustrating another example of an operation of the speech comparison service providing system according to the present invention. As shown only by way of example in FIG. 8, the server apparatus 200 generates a result of analyzing the intention of each statement for one or more statements found to correspond to the service execution item (S400).

Subsequently, when the server apparatus 200 is set to perform the speech evaluation application in a predetermined service deployment process (S402), the first speech evaluation and the speech for one or more speeches corresponding to the previous time point for the point of change of the speech content are changed. The second speech evaluation of one or more speeches corresponding to the later time point is executed at the time of changing the content (S404).

Thereafter, the server device 200 generates the results of the first speech evaluation and the second speech evaluation executed in the step S404 and reflects the generated evaluation result in the speech comparison result (S406 and S408).

9 is a diagram illustrating another example of an operation of the speech comparison service providing system according to the present invention. As shown by way of example only in FIG. 9, the server apparatus 200 generates a result of analyzing the intention of each statement for one or more statements found to correspond to the service execution item (S500).

Subsequently, when the server apparatus 200 is set to perform a speech trend analysis in a predetermined service deployment process (S502), the server apparatus 200 generates the speech trend information based on the speech intention and the starting point of the speech for the one or more speeches. (S504).

Thereafter, the server device 200 reflects the speech trend information generated in step S504 in the speech comparison result (S506).

FIG. 10 is a flowchart illustrating an operation process of a speech comparison service providing system according to an exemplary embodiment of the present invention. As shown only by way of example in FIG. 10, the server apparatus 200 sets a service execution item for at least one of a speech generating subject and a speech topic from a use request for a speech comparison service provided from the terminal apparatus 100 ( S600).

Thereafter, the server apparatus 200 executes a control analysis for comparing the plurality of speech generating subjects when the speech generating subjects of the set service execution items are two or more (S602 and S604).

If the control analysis of step S604 is set to generate control analysis information on the correspondence relationship between the two or more speech generating subjects, the control analysis information is generated according to the set as a result Integrated speech comparison results are generated based on the generated control analysis information (S606 and S608).

Thereafter, the server device 200 provides the generated speech comparison result to the terminal device 100 requesting the service (S610).

If there is an end of use of the speech comparison service, the execution of the above-mentioned processes is also terminated (S612).

If the speech generating subject is not 2 or more in step S602, a speech comparison result is generated through the processes mentioned in FIG. 5 (S614).

When the control analysis of step S604 is set to generate a speech comparison result for each of two or more speech generating subjects, a speech comparison result corresponding to each of two or more speech generating subjects is generated according to the set (S616).

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims It can be understood that

In addition, the present invention, if there is a request for use of the speech comparison service, at least one of the speech generating subject (for example, A politician) and the speech topic (for example, a policy matter) is set as the service execution item, and then the corresponding service execution item is set. Extracts one or more remarks from a predetermined data retrieval pool, generates a remark comparison result based on the result of analyzing the remarks of the remarks of the remarks of the remarks one or more remarks, and then sends the generated remark comparison result to the remark comparison service. In order to provide a response to the use request for the present invention, it is an invention that is industrially available because there is not only a possibility of commercialization or sales but also a degree that can be clearly realized in reality.

100: terminal device 200: server device
210: extraction unit 220: analysis unit
230: Offering

Claims (15)

Setting at least one of a speech generating subject and a topic to be a service execution item from a use request for a speech comparison service in a server device, and then extracting at least one speech corresponding to the service execution item from a predetermined data search pool;
Analyzing the intention of each remark for the one or more remarks; And
Executing the comparison of the one or more utterances based on the analysis result to generate a utterance comparison result and providing the utterance comparison result in response to a request for use of the utterance comparison service; How to provide comparative services. The method according to claim 1,
The method of providing a speech comparison service may further include including, in the speech comparison result, at least one of a message indicating a speech content change and a speech content change time point when the speech content is changed among the one or more speeches through the speech comparison result. A method of providing a speech comparison service further comprising. The method of claim 2,
The method of providing a speech comparison service may include: when the speech comparison result includes the speech content changing time, sorting the front and rear relations of the one or more speech based on the speech content changing time, and then sorting the speech content from the one or more speeches. Extracting at least one service providing statement that satisfies a predetermined service providing criterion; And
Comprising the one or more service providing remarks in the remarks comparison result; further comprising a speech comparison service providing method further comprising. The method of claim 2,
In the method of providing a speech comparison service, when the speech comparison result includes two or more times of changing the contents of the speech, the front and rear relations of the one or more speeches are divided and sorted based on the two or more contents of the contents change. Extracting one or more service provision statements that satisfy a predetermined service provision criterion from the one or more statements; And
Comprising the one or more service providing remarks in the remarks comparison result; further comprising a speech comparison service providing method further comprising. The method of claim 2,
The method of providing a speech comparison service may include: a first speech evaluation of one or more speeches corresponding to a previous time point with respect to the time of changing the speech contents among the one or more speeches when the speech comparison result includes the timing of changing the speech contents; Executing a second speech evaluation on one or more speeches corresponding to a later time point with respect to the time of changing the speech content among the one or more speeches; And
And further comprising the first remarks and the second remarks in the remark comparison result. 6. The method of claim 5,
The method of claim 1, wherein at least one of the first speech evaluation and the second speech evaluation is executed using at least one of opinion statistics and information on whether speech is executed. The method according to claim 1,
The method of providing a speech comparison service further includes: classifying the one or more speeches by a predetermined type and then verifying whether the one or more speeches are valid for each of the divided types. . The method according to claim 1,
The method of providing a speech comparison service may include: when the service execution item is set as the speech generating subject and the speech subject, guiding one or more speech topics corresponding to the speech generating subject when the speech generating subject is input; A method of providing a speech comparison service further comprising. The method according to claim 1,
The method of providing a speech comparison service further comprises: recommending at least one service execution item that satisfies a predetermined automatic recommendation guide condition when a request for using the speech comparison service is performed. . The method according to claim 1,
The method of providing a speech comparison service may further include generating speech trend information based on the speech intent and starting point of speech for the one or more speeches, and further including the speech trend information in the speech comparison result. How to provide speech comparison service. The method according to claim 1,
The method of providing a speech comparison service, when the speech generating subjects included in the service execution item is two or more, generates the speech comparison results for two or more speech generating subjects, or mutually responds to the two or more speech generating subjects. Generating control analysis information on the relationship and including the control analysis information in the speech comparison result; further comprising a speech comparison service providing method. An extracting unit configured to set at least one of a statement generating subject and a remark topic as a service execution item from a request for using a speech comparison service and extract one or more remarks corresponding to the service execution item from a predetermined data search pool;
An analysis unit for analyzing the intention of speaking each of the at least one statement; And
And a provider configured to execute the comparison of the one or more utterances based on an analysis result to generate a utterance comparison result and provide the utterance comparison result in response to a request for use of the utterance comparison service. Server device for providing speech comparison service. 13. The method of claim 12,
The data retrieval pool is an information retrieval range based on a communication network or a server device for providing a remark comparison service, characterized in that the retrieval range for a separate database constructed to provide the remark comparison service. The method of claim 13,
The server apparatus for providing a speech comparison service may include: an up-update unit configured to execute an update on the data search pool when the data search pool is built through the database and meets a predetermined up-date execution criterion; Server apparatus for providing a speech comparison service, characterized in that it further comprises. 13. The method of claim 12,
The analysis unit server apparatus for providing a speech comparison service, characterized in that for analyzing the speech intention of each statement for the one or more statements based on a predetermined information resource semantic analysis model.

Images