JP2019194901A - Destination conjecture device - Google Patents

Abstract

To set a destination of path finding while paying no attention to operation for inputting the destination.SOLUTION: A destination conjecture device includes: a retrieval information acquisition section for acquiring retrieval information including information on a retrieval term retrieved in a retrieval site; an attribution granting section for granting attribution information representing attribution of a retrieval term to the retrieval term; a retrieval term evaluation section for obtaining frequency of appearance of a retrieval term whose attribution is in common for each attribution; and a conjecture destination candidate extraction section for extracting a retrieval term related to a destination among retrieval terms included in attribution whose frequency of appearance satisfies a predetermined criterion as a conjecture destination candidate.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a destination estimation technique for estimating a destination set by a user.

  In a route search service provided by an in-vehicle navigation device, a website, or the like, it is necessary to set a destination when searching for a route. In general, destination setting for route search is performed by receiving an input of a destination from a user. Various destination input methods such as name input, address input, telephone number input, designation on the map, selection from destination setting history, etc. are adopted. Destination input using is also performed.

  Further, as described in Patent Document 1, a destination is input by a device other than a device that performs route search, for example, a mobile terminal device, and the input destination is transferred to a device that performs route search. It has also been proposed.

JP 2014-145751 A

  As described above, various methods can be used for inputting a destination when searching for a route, and further new methods have been proposed. This is considered to indicate that the conventional operation of inputting the destination is not always simple and feels troublesome for the user, and is seeking a method for reducing this burden.

  If the user avoids the task of inputting the destination for setting the destination, the opportunity to use the route search service decreases, and the convenience of the route search cannot be enjoyed. For this reason, if the destination of the route search can be set without being aware of the work of inputting the destination by the user, the route search service becomes more familiar, and it is expected that the opportunities for using the route search service will increase.

  Accordingly, an object of the present invention is to enable setting of a route search destination without being aware of the work of inputting the destination, for example.

  In order to solve the above-described problem, a destination estimation device according to claim 1 is a search information acquisition unit that acquires search information including information related to a search word searched on a search site, and the search word includes Included in the attribute assigning unit for attaching attribute information indicating the attribute of the search term, the search word evaluation unit for obtaining the appearance frequency of the search word having the same attribute for each attribute, and the attribute satisfying a predetermined criterion And a presumed destination candidate extraction unit that extracts a search word related to the destination as a presumed destination candidate.

  In order to solve the above-mentioned problem, a destination estimation method according to claim 7 is a destination estimation method using an information processing device, and includes search information including information related to a search term searched at a search site. Obtaining the search term, adding attribute information indicating the attribute of the search term to the search term, obtaining the appearance frequency of the search term having the same attribute for each attribute, and the appearance frequency being predetermined. And a presumed destination candidate extraction step of extracting a search word related to the destination as a presumed destination candidate among the search terms included in the attribute satisfying the criterion.

  In order to solve the above problem, a computer program according to an eighth aspect of the present invention provides a search information acquisition unit that acquires search information including information related to a search word searched at a search site, and the search word includes the search word. An attribute assigning unit that attaches attribute information indicating an attribute, a search word evaluation unit that calculates an appearance frequency of a search word that has the same attribute for each attribute, and a search word that is included in an attribute that satisfies the predetermined criterion The information processing apparatus is caused to function as an estimated destination candidate extraction unit that extracts a search word related to the destination as an estimated destination candidate.

  In order to solve the above problems, a recording medium according to a ninth aspect of the present invention is a recording medium that can be read by an information processing apparatus that records the computer program according to the eighth aspect.

It is a block diagram which shows the structural example of the route search system to which the destination estimation apparatus which is one Example of this invention is applied. It is a figure which shows the apparatus structural example of a route search system. It is a figure which shows the apparatus structural example of a route search system. It is a flowchart explaining extraction operation | movement of a presumed destination candidate. It is a figure explaining grouping by classification of a search term. It is a flowchart explaining the operation | movement which determines a presumed destination.

  An embodiment of the present invention will be described. A destination estimation apparatus according to an embodiment of the present invention includes a search information acquisition unit that acquires search information including information related to a search word searched on a search site, and attribute information that indicates an attribute of the search word in the search word An attribute assigning unit, a search word evaluation unit that obtains the appearance frequency of a search word having the same attribute for each attribute, and a destination among the search terms included in the attribute that the appearance frequency satisfies a predetermined criterion And an estimated destination candidate extraction unit that extracts a search term as an estimated destination candidate.

  Since the user only has to select a destination from the extracted estimated destination candidates, the user is freed from the operation of inputting the destination.

  Here, the search information includes information on a date and time when the search term is searched, and includes an estimated destination determination unit that determines an estimated destination from the estimated destination candidates based on the date and time information. Also good.

  Alternatively, a position information acquisition unit that acquires position information indicating a position for each time of the user and an estimated destination determination unit that determines an estimated destination from the estimated destination candidates based on the position information Also good.

  Also, a preference information processing unit that performs processing on user preference information related to user preferences, and an estimated destination determination unit that determines an estimated destination from the estimated destination candidates based on the user preference information. Good.

  The search word evaluation unit obtains a temporal appearance tendency of the search word for each classification based on the date and time information, and the estimated destination determination unit determines that the appearance tendency of the estimated destination candidate is in advance. It may be determined whether or not the pattern matches a predetermined pattern.

  In addition, a user characteristic evaluation unit that classifies a user's behavior characteristic into a predetermined pattern in relation to the position information and the search term, and the inferred destination determination unit, based on the behavior characteristic pattern, The estimated destination may be determined from the estimated destination candidates.

  A destination estimation method according to an embodiment of the present invention includes a step of acquiring search information including information related to a search word searched on a search site, and attaching attribute information indicating an attribute of the search word to the search word A step of obtaining an appearance frequency of a search word having the same attribute for each step, and an estimated destination word among search words included in an attribute having the appearance frequency satisfying a predetermined criterion And a presumed destination candidate extraction step for extracting as.

  A computer program according to an embodiment of the present invention includes a search information acquisition unit that acquires search information including information related to a search word searched on a search site, and attaches attribute information indicating an attribute of the search word to the search word An attribute assigning unit, a search word evaluation unit that obtains the appearance frequency of a search word that has the same attribute for each attribute, and infers a search word related to a destination among search words included in an attribute that the appearance frequency satisfies a predetermined criterion The information processing apparatus is caused to function as an estimated destination candidate extraction unit that extracts as a destination candidate.

  A recording medium according to an embodiment of the present invention is a recording medium that records the above-described computer program.

  FIG. 1 is a block diagram illustrating a configuration example of a route search system 10 to which a destination estimation apparatus according to an embodiment of the present invention is applied. As shown in the figure, the route search system 10 includes a destination estimation device 100, a search device 210, a position information acquisition device 220, an estimated destination presentation device 230, and a route search device 240.

  The search device 210 is an information processing device that can use the Internet 310 and includes a Web browser unit 211 and a search list creation unit 212. The web browser unit 211 can be configured by general-purpose web browser software. In the present embodiment, the user uses the web browser unit 211 to access the general-purpose search site 300 and perform a keyword search. Since the search device 210 is an information processing device that the user uses on a daily basis, the keywords used for the search include not only keywords related to the route search but also various keywords related to hobbies, life, work, and the like.

  The search list creation unit 212 acquires keywords used for the search by the Web browser unit 211 accessing the search site 300 and stores them in a list format. However, keyword storage is not limited to a list format. The search list includes information on the date and time when the search was performed together with the keyword. The search list creation unit 212 can be realized as add-on software for the Web browser unit 211, for example. Since the URL of the general-purpose search site 300 is known, the keyword input on the search site 300 can be easily acquired.

  Note that, when a linked Web page is displayed as a search result, the search list may include the time when the Web page was browsed.

  The position information acquisition device 220 is a device that moves together with the user, acquires position information indicating the position of the user for each time by a GPS (Global Positioning System) function, access point information, etc., and attaches date and time information. Record as location information list. However, the storage of position information is not limited to the list format. Specifically, it can be configured by a mobile phone, a smartphone, an in-vehicle navigation device, or the like.

  The destination estimation device 100 is a device that estimates a destination desired by a user based on a search list or the like created by the search device 210. Information that can execute a computer program including a CPU, a memory, a communication device, and the like. It can be configured using a processing device. Since the destination estimation device 100 estimates the destination based on the search information at the search site 300, the user does not need to input the destination.

  The destination estimation device 100 includes a search list acquisition unit 110, a position information acquisition unit 120, an estimation destination candidate extraction unit 130, a user characteristic evaluation unit 140, and an estimation destination determination unit 150.

  The search list acquisition unit 110 acquires a search list from the search device 210 at a predetermined timing. There may be a plurality of search devices 210 to be acquired. However, the data to be acquired is not limited to the list format. The position information acquisition unit 120 acquires a position information list from the position information acquisition device 220 at a predetermined timing. There may be a plurality of acquisition target position information acquisition devices 220. However, the data to be acquired is not limited to the list format.

  The estimated destination candidate extraction unit 130 is a block that extracts candidates for estimated destinations based on the search list acquired by the search list acquisition unit 110, and includes a search term extraction unit 131, a search term attribute assignment unit 132, and a search term. An evaluation unit 133, an estimated destination candidate extraction unit 134, and a dictionary DB 135 are provided.

  The search term extraction unit 131 performs a process of extracting a search term from the keywords recorded in the search list. The date and time information of the extraction source keyword is also inherited in the extracted search term. That is, the keyword input by the user is not necessarily limited to one word, and a plurality of words or a sentence may be input. The search word extraction unit 131 extracts a search word from the keywords recorded in the search list using an existing sentence analysis technique or the like. The search term is not limited to a word, and is made to correspond to a term registered in a dictionary DB 135 described later.

  The search term attribute assigning unit 132 performs processing for assigning an attribute to each search term extracted by the search term extracting unit 131. The attribute includes a classification and a destination flag, and the dictionary DB 135 is referred to when the attribute is given. The dictionary DB 135 is a database in which information on classification and destination flags is recorded in advance for each term. The dictionary DB 135 may be provided outside the destination estimation apparatus 100.

  In the dictionary DB 135, the classification is hierarchized, for example, “leisure” → “skiing” → “ski resort”. For example, if the term is related to leisure in general, the classification is “leisure”. If the term is related to skiing in general, the classification is “ski”, a child classification of “leisure”, and the term is specified. If it relates to a ski resort, the classification is “ski resort” which is a child classification of “ski”. By classifying the classifications in advance, the parent classification terms and the child classification terms can be grasped by referring to the dictionary DB 135.

  A plurality of classifications can be set for one term. For example, as the classification of the term “snowfall information”, two classifications such as “skiing” and “climate” can be set.

  The destination flag is a flag indicating whether or not the term can be a destination in order to determine whether or not the term is related to the destination. For example, the term “ski” cannot be a destination, but the term “AA ski area” can be a destination. Here, it is assumed that ON of the destination flag indicates a term that can be a destination.

  The search word evaluation unit 133 evaluates the search word group to which the attribute is given by the search word attribute assigning unit 132, and performs a process for obtaining the appearance frequency that is an index indicating the appearance frequency for each classification and the temporal appearance tendency. . Specifically, grouping is performed for each classification given to the search word, the appearance frequency is totaled for each classification, and the appearance tendency is classified based on the search date information attached to the search word. As for the appearance tendency, for example, patterns such as regular appearance, intermittent appearance, appearance on weekends, appearance at the end of the day, rapid increase immediately before, and the respective determination criteria are determined in advance, and one or more applicable patterns are determined. It can be classified by selecting.

  The estimated destination candidate extraction unit 134 performs a process of extracting, from the search terms included in the classification having a high appearance frequency, a search term whose destination flag is on as an estimated destination candidate. A plurality of estimated destination candidates can be extracted. For example, an estimated destination candidate is extracted from a higher number of appearance frequencies for a predetermined number of classifications, or an estimated destination candidate for a classification whose appearance frequency exceeds a reference value. Candidates can be extracted.

  The user characteristic evaluation unit 140 is a block that evaluates individual user characteristics, and includes a template matching unit 141, a preference information processing unit 142, and a template DB 143.

  The template matching unit 141 performs a process of classifying the user's behavior characteristics based on the search word, the appearance frequency of the classification, the appearance tendency, and the position information. The user behavior characteristics are determined with reference to a template DB 143 in which a model of the user behavior characteristics is recorded together with a criterion.

  The model of behavior characteristics is, for example, “A place searched on the weekend visits the next weekend” “A searched place visits the next day” “A place that is not searched normally visits that place” “Excursions on Sunday” “Looking for places to visit long-term”, “Searching for a map to visit that place”, “Visit to the place searched in the morning in the afternoon”, “Not relevant to search and movement”, etc. For each model, a criterion based on the search word, the appearance frequency of the classification, the appearance tendency, and the position information is determined.

  The template matching unit 141 includes information regarding a search term to which date / time information used in the process of the estimated destination candidate extraction unit 130 extracting the estimated destination candidate, and user date / time information acquired by the position information acquisition unit 120. Classification is performed by discriminating one or a plurality of types applicable to the behavioral characteristics of the user from the attached position information.

  For example, if a search related to a golf course is classified as an appearance trend that appears on the weekend, if the location information of the golf course is often obtained on the next weekend, It will be classified into the behavioral characteristic of “visiting on the weekend”.

  The preference information processing unit 142 performs processing for preference information related to user preferences. For example, when the user has registered a preference target in advance, the target is recorded as preference information. The preference object can be, for example, “skiing”, “fishing”, etc., and it is desirable to correspond to the classification and terminology of the dictionary DB 135.

  In addition, the preference information processing unit 142 updates the preference information based on information related to the search terms used in the process of the estimated destination candidate extraction unit 130 extracting the estimated destination candidates. For example, when “baseball” is not included in the preference registered by the user and “baseball” is significantly increased, “baseball” can be added to the preference information. On the contrary, when “fishing” is recorded in the preference information, if no search for “fishing” has been performed for a long time, “fishing” may be deleted from the preference information.

  The estimated destination determination unit 150 is a block that determines one or a plurality of estimated destinations from the estimated destination candidates extracted by the estimated destination candidate extraction unit 130, and includes an evaluation control unit 151 and a factor evaluation unit 152. Yes.

  The evaluation control unit 151 performs a process of determining the estimated destination based on the appearance frequency of the estimated destination candidate in the search and the evaluation taking into consideration various factors performed by the factor evaluating unit 152. The factor evaluation unit 152 evaluates the estimated destination candidate for each factor of the user's preference, behavior characteristic, and appearance tendency. However, the factors evaluated by the factor evaluation unit 152 are merely examples, and are not limited to this example.

  In the evaluation of the user's preference factor, the preference information updated by the preference information processing unit 142 is referred to, and in the evaluation of the behavior characteristic factor, the user's behavior characteristic type classified by the template matching unit 141 is referred to, and the appearance In the evaluation of the tendency factor, the appearance tendency classified by the search word evaluation unit 133 is referred to.

  The estimated destination presentation device 230 presents the estimated destination determined by the destination estimation device 100 to the user. The estimated destination can be presented, for example, by displaying the estimated destination on the screen. When there is only one estimated destination, an instruction as to whether or not to set the estimated destination as a destination for route search is accepted. When there are a plurality of estimated destinations, one of the estimated destinations is selected. It is desirable to accept an instruction as to whether it is set as a route search destination, or any of the estimated destinations is not set as a route search destination.

  The route search device 240 is a device that performs a route search for a destination set by the user. The route search device 240 can be configured by an in-vehicle navigator device, a service server that provides a route search service, or the like.

  The route search system 10 described above can be realized with various device configurations in implementation. For example, as shown in FIG. 2A, a route search system 10 is configured by a PC, a smartphone, and an in-vehicle navigator device connected to the Internet 310, and the PC functions as the search device 210. The in-vehicle navigator device can function as the destination estimation device 100, the position information acquisition device 220, the estimated destination presentation device 230, and the route search device 240 by functioning as the information acquisition device 220.

  In this case, the keyword searched by the user using the PC or smartphone is acquired for determining the estimated destination. In addition, the location where the smartphone is moved and the location where the vehicle is moved by the vehicle equipped with the in-vehicle navigator device are acquired as position information. The estimated destination is determined by the in-vehicle navigator device, and the route search to the destination is also performed by the in-vehicle navigator device.

  Further, as shown in FIG. 2B, a route search system 10 is configured by a PC, a smartphone, an in-vehicle navigator device, and a destination guessing service server connected to the Internet 310, and the PC functions as the search device 210. Are made to function as the search device 210 and the position information acquisition device 220, and the in-vehicle navigator device is made to function as the position information acquisition device 220, the estimated destination presentation device 230, and the route search device 240, and the destination estimation service server is used as the destination estimation device 100. Can function as.

  That is, a destination estimation service server that performs a destination estimation service is provided independently of the in-vehicle navigator device. In this case, the estimated destination is determined by the destination estimation service server, the estimated destination is transferred to the in-vehicle navigator device, and the route search is performed. The keyword searched by the user on the PC or smartphone is acquired for determining the guess destination, and the location moved by carrying the smartphone and the location moved by the car equipped with the in-vehicle navigator device is acquired as position information. This is the same as the example shown in FIG.

  Also, as shown in FIG. 3A, a route search system 10 is configured by a PC, a smartphone, and an in-vehicle navigator device connected to the Internet 310, respectively, and the PC functions as a search device 210 and a destination estimation device 100. The smartphone can function as the search device 210 and the position information acquisition device 220, and the in-vehicle navigator device can function as the position information acquisition device 220, the estimated destination presentation device 230, and the route search device 240.

  In this case, the estimated destination is determined by the PC, the estimated destination is transferred to the in-vehicle navigator device, and the route search is performed. The keyword searched by the user on the PC or smartphone is acquired for determining the guess destination, and the location moved by carrying the smartphone and the location moved by the car equipped with the in-vehicle navigator device is acquired as position information. This is the same as the example shown in FIG.

  Further, as shown in FIG. 3B, a route search system 10 is configured by a PC, a smartphone, and an in-vehicle navigator device connected to the Internet 310, respectively, and the PC functions as the search device 210. 100, the search device 210, the position information acquisition device 220, and the estimated destination presentation device 230, and the route search service server can function as the route search device 240.

  In this case, the smartphone determines the estimated destination, requests the route search service server to search the route, and the smartphone displays the searched route. The keyword searched by the user on the PC or smartphone is acquired for determining the guess destination, and the location moved by carrying the smartphone and the location moved by the car equipped with the in-vehicle navigator device is acquired as position information. This is the same as the example shown in FIG. Note that the device configurations shown in FIGS. 2 and 3 are examples, and the route search system 10 may be realized with other device configurations.

  Next, operation | movement of the destination estimation apparatus 100 which comprises the route search system 10 is demonstrated. The operation of the destination estimation device 100 can be divided into an estimation destination candidate extraction operation and an estimation destination determination operation. The operation of extracting the estimated destination candidate is an operation of extracting the estimated destination candidate from the acquired search list. The estimated destination determination operation is an operation for determining an estimated destination from the estimated destination candidates in consideration of various factors. Note that the user characteristic evaluation unit 140 performs the user behavior characteristic template matching operation and the user preference information processing appropriately according to the above-described criteria.

  In the operation example described below, the estimated destination candidates are extracted in advance, and the estimated destination is determined from the estimated destination candidates when setting the destination. Thereby, it is possible to save the trouble of extracting the estimated destination for each destination setting, and to determine the estimated destination suitable for the date and time of the destination setting. However, the timing for extracting the estimated destination candidate and the timing for determining the estimated destination can be arbitrarily determined.

  First, the extraction operation of the estimated destination candidate will be described with reference to the flowchart of FIG. The extraction operation of the estimated destination candidate needs to be performed at a predetermined timing because the keyword needs to be accumulated to some extent in the search list (S101). The predetermined timing can be, for example, regular or when the size of the search list reaches a predetermined amount.

  If it is time to perform the extraction operation of the estimated destination candidate (S101: Yes), the search list acquisition unit 110 acquires the search list from the search list creation unit 212 of the search device 210 (S102).

  Then, the search term extraction unit 131 of the estimated destination candidate extraction unit 130 extracts a search term from the keywords recorded in the search list (S103). As described above, search terms can be extracted using existing sentence analysis techniques.

  When the search term is extracted, the search term attribute assigning unit 132 gives an attribute to each search term with reference to the dictionary DB 135 (S104). The attributes given to the search term include a classification and a destination flag. A plurality of classifications may be assigned to one search term.

  Next, the search word evaluation unit 133 counts the appearance frequency for each search word classification and classifies the appearance tendency based on the search date and time attached to the search word (S105). In counting up the appearance frequency, grouping is performed for each search word classification.

  Since the classification is hierarchized, for example, grouping as shown in FIG. 5 can be performed. In this figure, “AA ski resort”, “BB ski resort”, “ski board”, “rental ski”, “snow cover information”, “XX baseball field”, “CC ramen”, “DD town lunch”, “ramen” are extracted as search terms. Take the case as an example. Note that the search word surrounded by a square indicates that the destination flag is ON, that is, it can be a destination.

  Here, “AA ski resort” and “BB ski resort” are classified as “ski resort”, “ski board” and “rental ski” are classified as “ski equipment”, and “snow cover information” is “ski”. ”And“ climate ”,“ XX baseball field ”is classified as“ baseball field ”,“ CC ramen ”and“ DD town lunch ”are classified as“ restaurant ”, and“ ramen ” Shall be classified as “food”.

  In the dictionary DB 153, “ski” is set as the parent classification of the classification “ski resort” and “skiing equipment”, “baseball” is set as the parent classification of the classification “baseball field”, and the parent classification of “ski” and “baseball”. It is assumed that “leisure” is set and “food” is set as the parent category of the classification “restaurant”. The classification inclusion relationship shown in the figure is based on this parent-child relationship.

  For example, the frequency of appearance can be counted by paying attention to the classification of the lowest layer. At this time, the frequency of appearance of the search word included in the parent classification is assumed to be succeeded to the child classification. For example, for “ski resort”, which is the lowest category for the classification leisure, the search word appearance frequency is 2 (AA ski resort, BB ski resort), but the search term for the “ski” parent category is Appearance frequency 1 (snowfall information) can be added to be 3. Since the classification “climate” itself is the lowest layer, the appearance frequency for “climate” is 1. By performing similar aggregation for each classification, the aggregation frequency for each classification can be aggregated.

  Further, by referring to the search date / time information of the search word, it is possible to determine the appearance tendency such as regular appearance, intermittent appearance, weekend appearance, appearance at the end of the holidays, and a sudden increase for each classification.

  Finally, the estimated destination candidate extraction unit 134 extracts a search word whose destination flag is on from search words included in the classification having a high appearance frequency (S106). The extracted search term is extracted as a guess destination candidate.

  In the example shown in FIG. 5, “AA ski resort”, “BB ski resort”, and “CC ramen” included in the classification with the appearance frequency of 3 are extracted as the estimated destination candidates. “Ski board” and “rental ski” are included in the classification with the appearance frequency of 3, but are not extracted because the destination flag is off.

  Next, the operation for determining the estimated destination will be described with reference to the flowchart of FIG. The operation of determining the estimated destination is preferably performed when the estimated destination presentation device 230 is activated. For example, when the in-vehicle navigator device is caused to function as the estimated destination presentation device 230, the estimated destination is determined by including the information at that time in the factor evaluation when the automobile engine is started. For this reason, when the user starts the engine, the estimated destination is automatically presented.

  When the smartphone functions as the estimated destination presentation device 230, the estimated destination is automatically presented when a route search application is launched. In either case, the user can set the destination for route search without being aware of the work of inputting the destination.

  In the operation of determining the estimated destination, the factor evaluation unit 152 performs an evaluation in consideration of various factors for each of the estimated destination candidates having a high appearance frequency, and the evaluation control unit 151 performs the estimation purpose having a high overall evaluation. Land candidates are determined for estimation purposes. In this example, the evaluation is performed in consideration of the preference factor, the behavior characteristic factor, and the appearance tendency factor, but other factor evaluation may be employed.

  First, the estimated destination candidate obtained by the above-described estimated destination extraction operation is acquired (S201). Also, current information is acquired (S202). Current information can include date and time, day of the week, and the like. Information such as temperature and weather may be included depending on the factor evaluation to be adopted.

  In the preference factor evaluation (S203), the preference information processing unit 142 refers to the user's preference information that is updated, and points are added to the estimated destination candidate that matches the preference information. Whether it matches the preference information can be determined by referring to the classification including the parent classifier classification of the estimated destination candidate.

  In the behavior characteristic factor evaluation (S204), points are added to the estimated destination candidates that match the user's behavior characteristics classified by the template matching unit 141. For example, if the user's behavior characteristic is “A place searched on the weekend comes next weekend”, the search frequency for the estimated destination candidate is high last weekend, and the current information is the weekend, the behavior characteristic is Points are added to the estimated destination candidate as a match. In this case, if the current information is a weekday, points will not be added.

  In the appearance tendency factor evaluation (S205), points are added to the estimated destination candidate indicating the characteristic that the appearance tendency is likely to be set as the destination. For example, points are added to the estimated destination candidates classified as “steadily appearing” or “rapid increase”.

  The evaluation control unit 151 comprehensively evaluates the appearance frequency and each factor evaluation (S206), and determines an estimated destination (S207). For example, the points according to the appearance frequency are added to the points of each factor evaluation, and the estimated destination candidate having the highest total point is determined as the estimated destination. At this time, a plurality of estimated destination candidates may be determined as estimated destinations in descending order of the total points. Of course, various methods can be used for comprehensive evaluation of the appearance frequency and each factor evaluation.

  For example, when the user has searched for “AA Ski Area” among “AA Ski Area”, “BB Ski Area”, and “CC Ramen” extracted as the estimated destination candidates, the appearance tendency factor evaluation is performed. Since points are added, if other factor evaluations are equivalent, “AA ski area” is determined as the estimated destination.

  In addition, when the user's behavior characteristics are classified into types such as “going leisure on weekends” and “eating out on weekdays”, if the destination setting date is a weekday, the behavior characteristic factor evaluation of “CC ramen” When the destination setting date is a weekend, the behavior characteristic factor evaluation of “AA ski resort” and “BB ski resort” is high.

  As described above, in the route search system 10 of the present embodiment, the user extracts the estimated destination candidate based on the search term used for the daily search, not for the route search. For this reason, there is no need to be aware of the work of inputting the destination. In addition, since the estimated destination is determined from the extracted estimated destination candidates based on information at the time of the route search, the user's behavior characteristics, etc., the user can search for the route without being aware of the work of inputting the destination. You can set your destination.

  Note that the estimated destination candidate extracted by the operation of extracting the estimated destination candidate may be presented to the user. Even in this case, since the user only has to select a destination from the candidates, the user is freed from the task of inputting the destination.

DESCRIPTION OF SYMBOLS 10 Route search system 100 Destination estimation apparatus 110 Search list acquisition part 120 Location information acquisition part 130 Prediction destination candidate extraction part 131 Search word extraction part 132 Search word attribute provision part 133 Search word evaluation part 134 Prediction destination candidate extraction part 135 Dictionary DB
140 User characteristic evaluation unit 141 Template matching unit 142 Preference information processing unit 143 Template DB
150 Estimated destination determination unit 151 Evaluation control unit 152 Factor evaluation unit

Claims (1)

A search information acquisition unit for acquiring search information including information on search terms searched on the search site;
An attribute assigning unit for attaching attribute information indicating an attribute of the search term to the search term;
For each attribute, a search word evaluator that obtains the appearance frequency of search words that have the same attribute,
An estimated destination candidate extraction unit that extracts a search term related to a destination as an estimated destination candidate among search terms included in an attribute whose appearance frequency satisfies a predetermined criterion;
A destination estimation apparatus comprising:

Images