JP2019117108A - Visit-destination recommendation device, visit-destination recommendation method and visit-destination recommendation program - Google Patents

Abstract

To recommend an appropriate destination to moving bodies of visitors or like which perform similar behavior.SOLUTION: A visit-destination recommendation device includes: selection means for selecting facilities through which the given moving body has not passed in a first route in the route passing through a first facility out of route information regarding the first route when passing through the first facility in an area where the given moving body is located, on the basis of route information including a plurality of facilities in routes where moving bodies have moved; and determining means for determining a second route which passes through the first facility and the facility selected as the destination based on map information showing a road map of a certain area.SELECTED DRAWING: Figure 2

Description

  The present invention relates to a visiting destination recommendation device that recommends a visiting destination to a mobile body such as a visitor from transit information in an arbitrary area, a visiting destination recommendation method, and a visiting destination recommendation program.

  Various methods have been proposed for recommending a visiting destination to a mobile object such as a visitor based on information such as population distribution (people flow pattern) in a given area. People flow patterns are also called transit information.

  Non-Patent Document 1 discloses a technical idea that analyzes migration behavior between areas in units of 250 m (meters) using mobile spatial statistics.

  Non-Patent Document 2 discloses a technical idea of probabilistically estimating a stop-down place with a hierarchical migration model based on questionnaire information.

  Patent Document 1 discloses a "merchandise information providing system" for supporting the purchase of a product in a real store. In patent document 1, a visitor's interest is grasped | ascertained by analyzing and estimating a flow line from a camera or GPS (Global Positioning System) information, and the recommendation goods are determined.

  Patent Document 2 discloses a "people flow analysis system" that supports efficient operation of a city. In Patent Document 2, a start point and an end point are displayed on a map, and a passing point is further displayed. Commercial operators, developers, and transport operators can compare the travel patterns of large areas passing through different transit points. The end point is, for example, a predetermined facility. According to Patent Document 2, it is possible to compare the entrance rate for each facility and further understand the migration pattern of the person using the predetermined facility. The migration pattern extracted by the migration pattern extraction processing can be used by a traffic operator for transportation planning, used by a commercial operator or the like for sightseeing planning and marketing, and can be used as a hint for promotion planning by developers. In patent document 2, it can further utilize for navigation of a sightseeing base, and recommendation of a tour course and a destination.

  Patent Document 3 discloses an "information providing system" capable of predicting a user's behavior pattern as accurately as possible, and selecting and providing information optimum for the user at individual time points. Patent Document 3 describes a method of determining the degree of interest for each unit section with respect to each unit block from the viewpoint of "which category each user visited and used a store belonging to which category". . In patent document 3, the stay coefficient calculated about each common common store is totaled as a value which shows the interest degree with respect to the store genre of the said common near store. In Patent Document 3, such a tabulation is performed for a predetermined period of time for a large number of users, and a visit use interest level table in which the count value is a degree of interest is created.

  In Patent Document 3, in order to determine the degree of interest under a specific condition, it is necessary to investigate the behavior of a large number of users and perform statistical analysis. So, in patent document 3, a questionnaire survey is performed with respect to many users who are in a specific time zone.

  Further, Patent Document 4 discloses a technical idea that presents content information suitable for the user. The information processing apparatus disclosed in Patent Document 4 includes a preference / condition-considered content evaluation unit. The preference / situation considered content evaluation unit calculates a combined similarity by combining the preference similarity by distance and the situation similarity. The synthetic similarity is a similarity between a request source user of a recommendation request and a user who has selected content information (search content information) in the past, and corresponds to a user value similarity. According to Patent Document 4, it is possible to recommend a user's preference and a candidate point suitable for the current situation of the user even in an area away from the user's activity area.

JP, 2015-022354, A WO 2016/067 369 WO 2009/075043 JP, 2015-056045, A

Pedestrian migration analysis in the central part of the city (part 2)-About the attributes of the residents in the central part-, Nagoya City Center Research Report, No. 117 2015. Forecast analysis model for detailed analysis and policy simulation of machinaka migration behavior, Journal of the Japan Society of Civil Engineers, Vol. 71, No. 5 323-335, 2015

  The prior art (patent documents 1 to 4 and non-patent documents 1 and 2) described above have the following problems.

  In patent document 1, since the information of a camera or GPS is utilized, an individual's action locus | trajectory is acquirable. However, the technique of Patent Document 1 is likely to be a violation of privacy because it leads to personal identification.

  In Non-Patent Document 1, it is possible to protect privacy because population distribution information such as mobile spatial statistics is used. However, in the method disclosed in Non-Patent Document 1, it is difficult to estimate fine migration behavior since the analysis granularity is rough.

  In the method disclosed in Non-Patent Document 2, migration behavior is analyzed based on population distribution and questionnaire information based on a probabilistic behavior model. However, such an analysis method can not grasp the relationship between facilities in detail. Therefore, in the method disclosed in Non-Patent Document 2, based on the analysis result, the information becomes insufficient information to recommend the visiting destination to the visitor.

  Patent Document 2 merely discloses a technical idea that enables a business operator, a developer, and a traffic operator to grasp the migration pattern of a person. Therefore, Patent Document 2 does not appropriately recommend a visiting destination to a visitor from the traveling pattern.

  Patent Document 3 also discloses a technical idea of selecting and providing information optimum for the user. In order to realize that, in Patent Document 3, it is necessary to conduct a questionnaire survey on a large number of users.

  Patent Document 4 merely discloses the user's preference and the technical idea of recommending candidate points suitable for the current situation of the user, even in areas away from the user's activity area . Even in Patent Document 4, since the relationship between the facilities is not grasped, it is not performed to recommend an appropriate visiting place to the visitor.

  One of the objects of the present invention is a visiting recommendation device, a visiting recommendation method, and a visit, which can solve the above-mentioned problems and recommend an appropriate visit to a mobile object such as a visitor who performs similar actions. It is to provide a pre-recommendation program.

  In one aspect of the present invention, when the visiting destination recommendation device passes through the first facility in the area where the given moving object is located, based on route information including a plurality of facilities through which the moving object traveled. Selecting means for selecting a facility through which the given mobile unit has not passed via the first route in the route passing through the first facility among the route information with respect to the first route of A determination unit configured to determine a second route passing through one facility and the selected facility as a visit destination based on map information indicating a road map of the certain area;

  As another aspect of the present invention, a method for recommending a visit destination is a first method in a region where a given mobile unit is located based on transit information including a plurality of facilities via a route traveled by the information processing apparatus. With regard to the first route when passing through a facility, in the route passing through the first facility among the passing information, select a facility through which the given mobile body does not pass through the first route; A second route passing through the first facility and the selected facility as a visit destination is determined based on map information indicating a road map of the certain area.

  In another aspect of the present invention, the visiting destination recommendation program is configured to pass through a first facility in an area where a given mobile object is located based on route information including a plurality of facilities via a route traveled by the mobile object. A selection procedure for selecting a facility through which the given mobile unit has not passed via the first route in the route passing through the first facility among the route information with respect to the first route of A determination procedure of determining a second route passing through a facility and the selected facility as a visit destination based on map information indicating a road map of the certain area is executed by the computer.

  Furthermore, the present invention is also realized by a computer readable recording medium that records such a program.

  According to the present invention, it is possible to recommend an appropriate visiting place for a moving object such as a visitor who performs similar actions.

It is a block diagram showing composition of a visiting place recommendation system containing a visiting place recommendation device concerning one embodiment of the present invention. It is a block diagram which shows the main processing parts implement | achieved by a visiting place recommendation apparatus used for the visiting place recommendation system shown in FIG. It is a flowchart for demonstrating the general | schematic operation | movement of the visiting place recommendation apparatus shown in FIG. It is a figure showing an example of a pedestrian map of a town. It is a flowchart for demonstrating the operation | movement of a behavior analysis part used for the visiting place recommendation apparatus shown in FIG. It is a figure which shows an example of the information of the flow-style pattern stored as process information in the memory | storage device used for the visiting place recommendation system shown in FIG. It is a figure which shows an example of the plant | facility information stored as process information in the memory | storage device used for the visiting place recommendation system shown in FIG. It is a figure which shows the relationship between a people flow pattern and the business interest degree Bint calculated for every business type Btype. Among industries similarity score Bscore _i between the industry type Btype _j industry type Btype _i and the j in the _i, a _j is a diagram showing, in a table. It is the figure which tabulated and showed the flow pattern similarity score PFscore _{i, j} between the _i-th flow pattern PFi _{, T} and the j-th flow pattern _{PFj, T.} It is a block diagram which is used for the visiting place recommendation system shown in FIG. 1 and which shows the relationship between the policy determination part and a people flow simulator. It is a flowchart for demonstrating the operation | movement of the policy determination part used for the visiting place recommendation apparatus shown in FIG. It is a figure for demonstrating the example in which a migration recommendation determination means recommends a type of business based on the similarity between facilities (type of business / type similarity). It is a figure for demonstrating the example which a movement recommendation determination means recommends a type | mold from the similarity degree between groups (similarity degree between people flow patterns). It is a figure for demonstrating an example of the method a transfer recommendation determination means determines the place of transfer recommendation.

Embodiment
FIG. 1 is a block diagram showing a configuration of a visiting destination recommendation system 100 including a visiting destination recommendation device (described later) according to one embodiment of the present invention.

  The visiting destination recommendation system 100 shown in the figure outputs a data processing apparatus (information processing apparatus) 200 that processes data, a storage device 300 that stores programs and data to be described later, an input device 400 that inputs data, and data. And an output device 500.

  The output device 500 includes a display device such as a liquid crystal display (LCD) or a plasma display panel (PDP) or a printer. The output device 500 has a function of displaying various information such as an operation menu or the like and printing out the final result in accordance with an instruction from the data processing device 200.

  The storage device 300 includes memories such as a hard disk, a read only memory (ROM), and a random access memory (RAM). The storage device 300 has a function of storing processing information 310 and programs 320 necessary for various types of processing in the data processing apparatus 200.

  The data processing apparatus 200 includes a microprocessor such as a micro processing unit (MPU) and a central processing unit (CPU). The data processing device 200 has a function of reading various programs 320 from the storage device 300 and realizing various processing units that process data according to the programs 320.

  The data processing device 200 includes a human flow simulator 210 and a visiting destination recommendation device 220.

  In the illustrated visiting destination recommendation system 100, data required for the algorithm, the area where the visiting destination is to be recommended, such as the device mobile spatial statistics, the flow pattern at the time, map information, and facility information data are given. It is assumed that

  Here, the people flow pattern is a pattern that indicates movement on a people flow group basis throughout the city. The flow pattern may be given in advance by observation (measurement) or may be estimated by a flow pattern estimation system (not shown). In the present example, the flow pattern is not a pattern itself but a parameter supplied to the flow simulator 210. The parameters, when supplied to the flow simulator 210, produce from the flow simulator 210 data closest to the population distribution (flow pattern) in a given area. Specifically, “parameters” means “the number of people in the group, where did they come from (the departure point), when they came from (the departure time), where to go home (the arrival point), where to go Do it (passing point), it consists of staying time of passing value. The departure point and the arrival point may be the same.

  Map information shows the road map in the town.

  Facility information indicates a plurality of facilities in the city. Each of the plurality of facilities contains at least one type of industry. Industries include, for example, the restaurant, clothing, retail, and medical industries. For example, there are sushi, Chinese food, and Japanese-style pubs in the restaurant business. The clothing industry includes, for example, women's clothing and children's clothing. Retailers include, for example, convenience stores and supermarkets. The medical industry includes, for example, internal medicine and plastic surgery.

  These people flow patterns, map information, facility information and the like are stored in advance in the storage device 300 as processing information 310.

  The visiting destination recommendation device 220 of the visiting destination recommendation system 100 is a device for recommending a visiting destination to a visiting person from the flow pattern, the map information, and the facility information. In the embodiment described below, although a case where an appropriate visit destination is recommended mainly to a person who performs similar actions (visitor) is described as an example, the present invention is applied to a person (visitor). The present invention is not limited and is generally applicable to mobiles. In this case, the flow pattern can be replaced by the route information.

  FIG. 2 is a block diagram showing the main processing units implemented by the visited destination recommendation device 220. The visit destination recommendation device 220 includes an action analysis unit 600 and a measure determination unit 700.

  The general operation of the visiting recommendation device 220 will be described with reference to FIG.

  First, the behavior analysis unit 600 calculates relevance information of interest between facilities based on a plurality of people flow patterns and facility information (step S101).

  Subsequently, based on the map information and the relevance information of the interest between the facilities, the measure determination unit 700 visits a specific facility having a type of business that has not been stopped by a particular people flow group. The migration path is recommended as it is (step 102). In other words, the measure determination unit 700 recommends the migration route so that a specific facility having a business type not included in a given people flow pattern is a visiting destination.

  Returning to FIG. 2, the configuration of the visited destination recommendation device 220 will be described in more detail.

  The behavior analysis unit 600 includes interest degree calculation means 610 and similarity degree calculation means 620. The measure determination unit 700 includes a migration recommendation determination means 710.

  The degree-of-interest calculation means 610 calculates the degree of interest in the industry with respect to the industry included in the facility in the town based on the plurality of people flow patterns and the facility information. That is, the interest degree calculation means 610 calculates the type of business interest degree indicating what type of interest is shown to which type of business, from the movement history of each group of the people flow pattern and the type of business included in the facility which has stopped by.

  The similarity calculation means 620 calculates the inter-group similarity of the human flow pattern and the inter-facility similarity based on the industry interest level. The inter-group similarity and the inter-facility similarity are stored as processing information 310 in the storage device 300.

  The migration recommendation determining means 710 recommends the migration route based on the map information, the inter-group similarity, and the inter-facility similarity. In other words, the migration recommendation decision means 710 visits a place that seems to be highly interested in a people flow group performing similar actions based on the people's group similarity and the inter-facility similarity. Recommend as a destination. The migration recommendation information indicating the recommended migration route is stored as processing information 310 in the storage device 300.

  Therefore, the relevance information of the interest between the facilities consists of the combination of the business interest, the inter-group similarity, and the inter-facility similarity.

  In addition, the migration recommendation determining means 710 provides information on a joint campaign between facilities having a high degree of similarity based on the business interest degree and the inter-facility similarity. Specifically, for example, in the industry of clothing industry, it is assumed that the degree of similarity between a store of women's clothes and a store of children's clothes is high. In this case, the migration recommendation deciding means 710 carries out a campaign such as issuing a discount voucher for the other store (set sale) or giving preferential points to a person who purchased at one store.

  Next, the operation of the visited destination recommendation device 220 will be described in more detail.

  FIG. 4 is a view showing an example of a pedestrian map of a town. The illustrated pedestrian map is obtained from map information and a flow pattern.

In the illustrated example, two human flow groups are exemplified as the first human flow patterns PF _{1 and T} and the second human flow patterns PF _{2 and T} as the plurality of human flow patterns. Further, on a map, as a starting point, the first point of departure S _1, the second departure point S _2, 2 two points is depicted. In the illustrated example, the first starting point S ₁ is also the first arrival point, the second departure point S ₂ is also a second arrival point.

Furthermore, on the map, first to fifth facilities P ₁ , P ₂ , P ₃ , P ₄ , P ₅ and an n-th facility P _n are drawn as a plurality of facilities. In the illustrated example, the first facility P _1, as a store, has entered Chinese, tavern, and a children's clothing store. The second facility P _2, as the store, filled with sushi and tavern of the store. The third facility P _3, as the store, contains the internal medicine and shaping of the store. The fourth facility P _4, as a store, women's clothing, children's clothing, that contains the convenience stores and super stores. The facility P ₅ of the fifth, as the store, contains the women's clothing store. The n-th facility P _n includes a store for women's wear and children's wear as a store.

The first population flow pattern PF _{1, T} , which is the first population flow group, uses the second departure point S ₂ as the departure point, the second facility P ₂ and the fourth facility P ₄ as the transit location, and the second It is a people flow pattern which makes an arrival point S ₂ of this point an arrival point.

The second population flow pattern PF _{2, T} , which is the second population flow group, uses the first departure point S ₁ as the departure point, and the first facility P ₁ , the third facility P ₃ , and the fifth facility P. It is a people flow pattern which makes _1st arrival point S 1 an arrival point by making ₅ a transit point.

  The operation of the behavior analysis unit 600 will be described with reference to FIG.

  First, the degree-of-interest calculation means 610 calculates the degree of interest in the industry for the industry included in the facility of the town based on the flow pattern PF and the facility Ftype represented by the facility information (step S201). A specific example of the degree of business interest will be described later with reference to the drawings.

  Subsequently, the similarity calculating unit 620 calculates the inter-group similarity of the flow pattern from the business interest degree (step S202). A specific example of the inter-group similarity will also be described later with reference to the drawings.

  Finally, the similarity calculating unit 620 calculates the inter-facility similarity from the business interest degree (step S203). Inter-facility similarity will also be described later with reference to the drawings.

  FIG. 6 is a diagram showing an example of the information of the flow pattern stored in the storage device 300 as the processing information 310. As shown in FIG.

FIG. 6 shows an example in which there are _{first to} n-th human flow patterns PF _{1, T 1 to} PF _{n, T} as the plurality of human flow patterns. Generally, in the ith personal flow pattern PF _{i, T} (1 ≦ i ≦ n), the subscript i indicates a pattern identifier and the subscript T indicates a time zone {am / pm}. Each flow pattern is assumed to pass through any one selected from the _{first to n-th} facilities P _{1 to} P _n as transit points. Here, in the i-th facility P _i , the subscript i indicates a pattern identifier.

In the example shown in FIG. 6, for example, a first pedestrian flow pattern PF _{1, T} is via a pedestrian flow group consisting of 100 people, as waypoint, a second facility P ₂ and the fourth facility P ₄ It shows that you do. In addition, the second flow pattern PF _{2, T} is a flow group consisting of 200 people, via the first facility P ₁ , the third facility P ₃ , and the fifth facility P ₅ as transit points It shows that you do.

  FIG. 7 is a diagram showing an example of facility information stored in the storage device 300 as the processing information 310. As shown in FIG.

As shown in FIG. 7, the facility information includes first to n-th facilities P _{1 to} P _n and business type information indicating the type of business contained in each facility. Industry information is identified by an industry type Btype. The presence or absence of a store that has entered each facility is indicated by “1” and “0”, respectively.

In the example shown in FIG. 7, as the facility information, in the first of facility P _1, as industry (store), has entered the Chinese and the tavern of the store of food and beverage industry, that contains a children's clothing store as clothing industry Is shown. In addition, in the second of facility P _2, it is shown that as the industry (store), that contains the sushi and the tavern of the store of food and drink industry. The third facility P _3, as industries (stores), shows that it contains the internal medicine and shaping of the store of the medical industry. The fourth facility P _4, as industry (store), has entered the women's clothing and children's clothing store in the clothing industry, shows that it contains the convenience stores and super stores of retail. The facility P ₅ of the fifth, as industry (store), shows that it contains the women's clothing store in the clothing industry. The n th store P _n indicates that stores of women's clothes and children's clothes of the clothing industry are included as business types (stores).

In addition, as the facility information of the fourth facility P ₄ a is building, convenience stores and super stores on the first floor is, women's clothing store on the second floor is, is on the fourth floor contains the children's clothing store example Is shown.

  The pedestrian map shown in FIG. 4 is, for example, a diagram created from the information on the flow pattern shown in FIG. 6 and the facility information shown in FIG. 7.

  The business interest degree Bint calculated by the interest degree calculation means 610 will be described with reference to FIG.

  FIG. 8 is a diagram showing the relationship between the flow pattern and the business interest Bint calculated for each business type Btype.

As is clear from FIG. 8, the business interest degree Bint is calculated according to the following equation 1 from the information on the flow pattern PF shown in FIG. 6 and the facility information Ftype shown in FIG.

For example, the business interest degree Bint of the third people flow pattern PF3 _{, T} , which is the third people flow group, is calculated as follows. From FIG. 4 and FIG. 6, the third personal flow pattern PF _{3, T} is transmitted from the second facility P _{1 to} the second facility P ₂ with the first departure point S ₁ as the departure point. the arrival point S ₂ and arrival point, a pedestrian flow pattern consisting of 150 people. As shown in FIG. 7, in the first of facility P _1, Chinese, has entered the tavern, and a store of children's clothing, in the second of facility P _2, which contains the sushi and the tavern of the store. Therefore, the industry interest Bint of the third people flow pattern PF _{3, T} is, for each industry type Btype, equal to 150 for sushi, 150 for Chinese, and 300 for taverns (ie, 150 for taverns in facility P ₁ If, equal to the sum) of the 150 on the tavern in the facility _{P 2,} children's clothing is equal to 150.

ここで、Ｎは人流パターンＰＦの人数を示し、ｐ_ｋは第ｋの人流パターンＰＦ_ｋ、Ｔの第ｉの業種タイプＢtype_ｉの業種興味度を示し、ｑ_ｋは第ｋの人流パターンＰＦ_ｋ、Ｔの第ｊの業種タイプＢtype_ｊの業種興味度を示す。 Next, the inter-facility similarity calculated by the similarity calculation means 620 will be described. The inter-facility similarity consists of an inter-industry similarity score Bscore represented by the following equation 2.

Here, N represents the number of people flow pattern PF, _{p k} represents the industry degree of interest of the industry type Btype _i of the i-th of the people flow pattern _{PF k, T} of the _{k, q} k is the human flow pattern PF _k of the k-th _{, T} indicates the business interest level of the j-th business type Btype _j .

FIG. 9 is a diagram showing an inter-industry similarity score Bscore _{i, j} between the i-th industry type Btype _i and the j-th industry type Btype _j, which is calculated by the above equation 2, in the form of a table. The inter-business similarity score Bscore _{i, j} is stored in the area of the processing information 310 of the storage device 300 as the inter-facility similarity (see FIG. 2).

ここで、Ｎは業種タイプＢtypeの数を示し、ｐ_ｋは第ｋの業種タイプＢtype_ｋの第ｉの人流パターンＰＦ_ｉ，Ｔの業種興味度を示し、ｑ_ｋは第ｋの業種タイプＢtype_ｋの第ｊの人流パターンＰＦ_ｊ，Ｔの業種興味度を示す。 Next, the inter-group similarity of the flow pattern calculated by the similarity calculation means 620 will be described. The inter-group similarity of the people flow pattern consists of the people flow pattern similarity score PFscore expressed by the following equation 3.

Here, N denotes the number of sectors type Btype, _{p k} is a human flow pattern _{PF i} of the i industry type Btype _k of the _k, indicates the industry interestingness of _{T, q k} is industry type Btype _k of the k The industrial interest degree of the j-th human flow pattern PF _{j, T} is shown.

FIG. 10 shows the flow pattern similarity score PFscore _{i, j} between the _i-th flow pattern PF _{i, T} and the j-th flow pattern PF _{j, T} calculated by Equation 3 above. FIG. The flow pattern similarity score PFscore _{i, j} is stored as an inter-group similarity in the area of the processing information 310 of the storage device 300 (see FIG. 2).

  In other words, the flow pattern similarity score indicates the degree to which two flow patterns are similar in terms of the store of the type of business visited by a certain person. For example, the larger the similarity score, the higher the degree to which the two flow patterns are similar. Conversely, the smaller the similarity score is, the lower the degree to which the two flow patterns are similar. That is, by selecting two flow patterns with high similarity scores, it is possible to select a flow pattern that is similar from the viewpoint of the shop of the business type visited.

  From the above description, the behavior analysis unit 600 determines an area where a given mobile object is located based on transit information (for example, a human flow pattern) including a plurality of facilities via which a mobile object (for example, a person) travels. With regard to the first route when passing through the first facility in, as a selection means for selecting a facility where a given mobile unit has not passed through in the first route in the route passing through the first facility among the via information work.

  Next, with reference to FIG. 11 and FIG. 12, the operation of the measure determination unit 700 (the migration recommendation determination means 710) will be described. FIG. 11 is a block diagram showing the relationship between the measure determination unit 700 and the human flow simulator 210. FIG. 12 is a flowchart for explaining the operation of the measure determination unit 700 (the migration recommendation determination means 710).

Referring to FIG. 12, first, the migration recommendation determining unit 710 selects at least one people flow pattern PFi _{, T} having a low migration rate as a specific people flow group based on the map information (step S301).

Subsequently, based on the inter-facility similarity shown in FIG. 9 and the inter-group similarity shown in FIG. 10, the migration recommendation determining means 710 selects the top M recommended business types to be recommended to a specific people flow group PF _{i, T.} It selects (step S302). Here, the recommended type of industry to be recommended is a type of business having a high (similarity score × number of people).

Next, migratory recommendation determination unit 710 selects a plurality of particular facilities P _i with recommended industry selected, so that through each of the plurality of specific facilities P _i selected, specific human stream group PF _{i, A} plurality of bypass route candidates are added for _T and evaluated by the flow simulator 210 (step S303).

More specifically, as shown in FIG. 11, the migration recommendation determining means 710 selects a specific facility P _i to be added to the migration path and supplies it to the flow simulator 210. The people flow simulator 210 simulates the migration route to which the specific facility _Pi is added, and returns a positive reward and a negative reward to the measure determination unit 700 (migration recommendation determining means 710). Here, a positive reward is output when there is a recommendation effect. On the other hand, a negative reward is output when the movement distance of the flow pattern PF _{i, T} increases.

  Referring back to FIG. 12, the migration recommendation determining unit 710 determines P industries / facilities having a large sum of positive and negative rewards from among the plurality of migration path candidates (step S304). In other words, the migration recommendation determining unit 710 determines one recommended migration route so that at least one specific facility having a highly rewarded type of industry is the visiting destination from among the plurality of migration route candidates.

Next, with reference to FIG. 13 and FIG. 14, an example will be described in which the migration recommendation determining means 710 determines the migration recommendation type of industry when performing migration recommendation on a specific people flow group PFi _{, T.}

  FIG. 13 is a diagram for explaining an example in which the migration recommendation determining unit 710 recommends the type of business based on the inter-facility similarity (the type of business / type similarity).

The migration recommendation determining means 710 first uses the clothing industry (children's clothing) as a type of industry having high similarity to the current visit destination of a specific people flow group (in this example, the i-th people flow pattern) PF _{i, T} from FIG. ) And the medical industry (internal medicine, shaping). Here, since the medical business (internal medicine, plastic surgery) is the same as the current visit destination, the migration recommendation decision means 710 adds the clothing business (children's wear) to the candidate list.

  FIG. 14 is a diagram for explaining an example in which the migration recommendation determining unit 710 recommends the type of business based on the degree of similarity between groups (the degree of similarity between flow patterns).

The migration recommendation determining means 710 first selects the _second flow pattern PF2 _{, T} as a flow pattern having high similarity to the _i-th flow pattern PFi _{, T} from FIG. Subsequently, the migration recommendation determining means 710 determines whether the i-th people flow among the visit destinations of the second people flow pattern PF _{2, T} based on the information on the people flow pattern (see FIG. 6) stored in the storage device 300. The food and drink business (Chinese, tavern) and the clothing business (children's clothes) not visited by the pattern PF _{i, T} are added to the candidate list. Here, among these business categories (stores), the recommendation effect on the clothing industry (children's wear) is 1662, which is the highest. Therefore, when M = 1, the migration recommendation determining means 710 recommends the clothing industry (children's clothing) because the recommendation effect of the clothing industry (children's clothing) is the highest.

  Next, with reference to FIG. 15, an example of a method for the migration recommendation determination means 710 to determine the location of migration recommendation when recommending the clothing industry (child clothes) will be described.

FIG. 15 selects the _i-th people flow pattern PF _{i, T} as a specific people flow group, and recommends the detour place to the i-th people flow pattern PF _{i, T} when recommending the clothing industry (children's clothes) It is a figure which shows an example to do.

As apparent from FIG. 6, pedestrian flow pattern PF _{i, T} of the current i-th, through a pedestrian flow group consisting of 300 people, as waypoint, property P ₅ of the third facility P ₃ and fifth It shows that you do.

Referring to "the current PF _{i, T} " in FIG. 15, the ith population flow pattern _i , the first population flow pattern PF _{i, T} takes the first departure point S ₁ as the departure point and the third facility P ₃ and as a fifth stopover facilities P ₅ of the first arrival point S ₁ to the arrival point, it is a human flow pattern.

First, when recommending the clothing industry (children's clothes) to the i-th people flow pattern PF _{i, T} , the migration recommendation determining means 710 selects a plurality of facility candidates (in this example, the first facility P ₁ , the _first facility P ₁ , A plurality of migration path candidates are added so as to pass through each of the _four facilities P ₄ and the n-th facility P _n ).

In this example, the first traveling route candidate uses the first departure point S ₁ as a departure point, the first facility P ₁ , the third facility P ₃ and the fifth facility P ₅ as transit points. 1 of the arrival point S ₁ and arrival point, a migration path. The second traveling route candidate uses the first departure point S ₁ as a departure point, the third facility P ₃ , the fifth facility P ₅ and the fourth facility P ₄ as transit points, and a second arrival point It is a migration route with S ₂ as the arrival point. The third travel route candidate uses the first departure point S ₁ as a departure point, the third facility P ₃ , the fifth facility P ₅ and the n-th facility P _n as a transit point, and the first arrival point It is a migration path with S ₁ as the arrival point.

Next, the migration recommendation determining means 710 acquires the movement distance evaluated by the flow simulator 210 for the first to third migration route candidates. In the case of this example, in the first migration route candidate, the movement distance of “+100 m” is added to the _ith flow pattern PF _{i, T.} In the second traveling route candidate, the movement distance of “+50 m” is added to the _ith flow pattern PF _{i, T.} In the third traveling route candidate, the moving distance “+500 m” is added to the _ith flow pattern PF _{i, T.}

And the migration recommendation determination means 710 recommends the migration place where the reward is the largest. In this example, the sum of the i-th person flow pattern PF _i, fourth second migratory path candidates to add facilities P ₄ are positive and negative reward _T of the maximum. Therefore, the migration recommendation determining means 710 determines and recommends the second migration route candidate as one recommended migration route for the i-th people flow group.

  Thus, the measure determination unit 700 serves as a determination means for determining the second route passing through the first facility and the selected facility as the visit destination based on the map information indicating the road map of the certain area. .

  As apparent from the above description, according to the present embodiment, it is possible to recommend an appropriate visiting place to a visitor who performs similar action. The reason for this is that when making a travel recommendation for a popular group, we recommend the visit destination so that the recommendation effect is a positive reward and the physical distance is a negative reward so that the expected value reward is maximized. It is from.

  The present invention is not limited to the above embodiment as it is, and at the implementation stage, the constituent elements can be modified and embodied without departing from the scope of the invention. In addition, various inventions can be formed by an appropriate combination of a plurality of components.

  Each part of the visiting destination recommendation device may be realized using a combination of hardware such as an information processing device and software. In the combination of hardware and software, a visiting recommendation program is developed in RAM (random access memory), and processor hardware such as a central processing unit (CPU) is operated based on the visiting recommendation program. Thus, each unit is realized as various means. Further, the visiting destination recommendation program may be recorded on a recording medium and distributed. The visiting destination recommendation program recorded in the recording medium is read into the memory via a wired, wireless, or recording medium itself, and operates a processor (CPU) or the like. Incidentally, examples of the recording medium include an optical disk, a magnetic disk, a semiconductor memory device, a hard disk and the like.

  If the said embodiment is described in another expression, the computer which operates as a visiting place recommendation apparatus is based on the visiting place recommendation program developed in the RAM, and the behavior analysis unit 600 (interesting degree calculation means 610, similarity degree calculation means 620) It can implement | achieve by making it operate as a combination of and the policy determination part 700 (the migration recommendation determination means 710).

  Further, the specific configuration of the present invention is not limited to the above-described embodiment, and changes in the scope without departing from the scope of the present invention are included in the present invention.

  Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. The configurations and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention.

DESCRIPTION OF SYMBOLS 100 visiting destination recommendation system 200 data processing device 210 human flow simulator 220 visiting destination recommendation device 300 storage device 310 processing information 320 program 400 input device 500 output device 600 behavior analysis unit 610 interest degree calculation unit 620 similarity calculation unit 700 measure determination unit 710 Means of recommending travel recommendations

Claims (10)

Based on the route information including a plurality of facilities via which the moving object has traveled, the first one of the route information regarding the first route when passing through the first facility in the area where the given moving object is located, Selecting means for selecting a facility through which the given mobile unit has not passed via the first route in the route via one facility;
A determination unit configured to determine a second route passing through the first facility and the selected facility as a visit destination based on map information indicating a road map of the certain area;
A visiting recommendation device comprising: The moving object is a person, and the transit information is a flow pattern which is movement on a flow group basis in the certain area, and each of the plurality of facilities includes a store of at least one type of business. Yes,
The selection means is
Interest degree calculation means for calculating the degree of interest in the industry for the type of industry included in the facility in the area based on the plurality of people flow patterns and the facility information indicating the plurality of facilities in the area;
And a similarity calculation unit configured to calculate the inter-group similarity of the flow pattern and the inter-facility similarity based on the business interest degree.
The determination means takes, as the visit destination, a specific facility having a store of a business type not included in a given people flow pattern, based on the map information and the inter-group similarity and the inter-facility similarity. As described above, the migration recommendation decision means for recommending migration routes is provided.
The visiting destination recommendation device according to claim 1. The migration recommendation determining means provides information on a joint campaign between facilities having high similarity based on the business interest degree and the inter-facility similarity.
The visiting destination recommendation device according to claim 2. The said migration recommendation determination means is
Select a people flow group with a low transfer rate as the specific people flow group,
Selecting at least one recommended industry type to be recommended based on the inter-group similarity and the inter-facilities similarity for the specific people flow group;
Selecting a plurality of specific facilities having the selected recommended type of industry, and adding candidate migration path candidates for the specific people flow group to pass each of the selected plurality of specific facilities;
From the plurality of migration path candidates, one recommended migration path is determined such that one specific facility having a highly rewarded type of industry is the visit destination.
The visiting destination recommendation device according to claim 2 or 3. Based on the route information including a plurality of facilities via which the mobile unit has traveled by the information processing apparatus, the route information regarding the first route when passing through the first facility in the area where the given mobile unit is located Selecting a facility through which the given mobile unit has not passed by the first route in the route via the first facility of
Determining a second route passing through the first facility and the selected facility as a visit destination based on map information indicating a road map of the area;
Recommendation method of visiting place. The moving object is a person, and the transit information is a flow pattern which is movement on a flow group basis in the certain area, and each of the plurality of facilities includes a store of at least one type of business. Yes,
Based on the plurality of people flow patterns and facility information indicating a plurality of facilities in the certain area, the degree of interest in the industry for the industry included in the facilities in the certain area is calculated;
Calculate the inter-group similarity and the inter-facility similarity of the flow pattern based on the business interest degree,
Based on the map information and the inter-group similarity and the inter-facility similarity, an excursion route is made such that a specific facility having a store of a business type not included in a given people flow pattern is the visit destination. Recommend
The visiting destination recommendation method according to claim 5. Conduct a joint campaign between facilities having high similarity based on the business interest degree and the inter-facility similarity.
The visiting destination recommendation method according to claim 6. Select a people flow group with a low transfer rate as the specific people flow group,
Selecting at least one recommended industry type to be recommended based on the inter-group similarity and the inter-facilities similarity for the specific people flow group;
Selecting a plurality of specific facilities having the selected recommended type of industry, and adding a plurality of candidate migration paths for the specific people flow group to pass each of the selected plurality of specific facilities;
From the plurality of candidate migration routes, one recommended migration route is determined such that one specific facility having a highly rewarded type of industry is the visit destination.
The visiting destination recommendation method according to claim 6 or 7. Based on the route information including a plurality of facilities via which the moving object has traveled, the first one of the route information regarding the first route when passing through the first facility in the area where the given moving object is located, A selection procedure for selecting a facility through which the given mobile unit has not passed via the first route in the route via one facility;
A determination procedure of determining a second route passing through the first facility and the selected facility as a visit destination based on map information indicating a road map of the area;
Visiting destination recommendation program that causes a computer to execute. The moving object is a person, and the transit information is a flow pattern which is movement on a flow group basis in the certain area, and each of the plurality of facilities includes a store of at least one type of business. Yes,
The selection procedure is performed by the computer
An interest degree calculation procedure for calculating the type of business interest for the type of business included in the facility in the area based on the plurality of people flow patterns and the facility information indicating the plurality of facilities in the area;
Execute a similarity calculation procedure for calculating the inter-group similarity of the flow pattern and the inter-facility similarity based on the business interest degree;
The determination procedure includes, on the computer, a specific facility having a store of a business type not included in a given people flow pattern based on the map information and the inter-group similarity and the inter-facility similarity. Execute a migration recommendation decision procedure for recommending migration routes to be a visit destination,
The visiting destination recommendation program according to claim 9.

Images