JP2007080085A - Information gathering controller and information gathering control method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce an amount of gathered information and to reduce the power consumption of an information acquisition device. <P>SOLUTION: The information gathering controller 10 arranged in a service provision system 1 for determining an operation on the basis of information gathered from the information acquisition device 50 and a service logic, performing the determined operation and providing a service comprises: a prediction part 11 for predicting the information to be gathered from the information acquisition device 50 at the present time on the basis of the information gathered from the information acquisition device 50 in the past; an importance deriving part 12 for analyzing the service logic by using a predicted result and deriving the importance of the gathering of the information from the information acquisition device 50 to be utilized in the service logic; and an information gathering control part 13 for controlling information gathering from the information acquisition device 50 on the basis of the derived importance. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention is arranged in a service providing system that determines a service operation based on information collected from one or more information acquisition devices and one or more service logics, and provides the service by performing the determined service operation. The present invention relates to an information collection control device and an information collection control method in the service providing system.

  2. Description of the Related Art Conventionally, a technique for controlling an information collection operation (see Non-Patent Document 1 below) has been proposed for the purpose of improving the efficiency of information collection when collecting information about an external target using a plurality of information acquisition devices. Yes.

In addition, as a technique for improving the efficiency of information collection, for example, continuous information such as the position of a certain object is periodically measured using an information acquisition device such as GPS (Global Positioning System), and a radio band is set. In a system that reproduces the above continuous values by calculation from some of the collected information, keeping the deviation between the true value of the object and the value calculated by the system below a certain threshold On the other hand, techniques aimed at reducing the amount of wireless bandwidth used and the amount of power consumed by the information acquisition device have been proposed. In this technique, a model that predicts a future value based on values acquired by measurement by the system from the past to the present is used, and a value at the time of next information collection is predicted by the model. Then, compare the predicted value with the actual value to find the difference between them, and if the difference is large, increase the frequency of measurement, and if the difference is small, decrease the frequency of measurement. As a result, the number of times of measurement is reduced as compared with the case where the information acquisition device always performs measurement at the maximum frequency possible. As a result, the purpose of improving the efficiency of information collection is achieved.
Ankur Jain and Edward Y. Chang: "Adaptive sampling for SensorNetworks," in Proc. International workshop on Data Management for sensornetworks (2004).

  However, the information collection from the information acquisition device, depending on the use of the collected information, does not necessarily reduce the difference between the true value of the measurement target and the value obtained by the calculation as in the above example. There is no need to keep. For example, in a service providing system that determines the operation of each service based on information collected from an external information acquisition device and a plurality of service logics given in advance, and collects the information from the information acquisition device Information with a low importance level (for example, information with a small influence on the operation of each service logic or information with a small number of services to be referred to) does not cause a problem even when the above-mentioned divergence is large. In such a case, it is not necessary to keep the deviation between the true value of the measurement target and the value obtained by the calculation below a certain value. Therefore, by suppressing the collection frequency and measurement quality of information of low importance as described above, the amount of information collected by the service providing system (hereinafter referred to as “collected information amount”) and the amount of power consumed by the information acquisition device are reduced. There was room for further reduction.

  Therefore, an object of the present invention is to provide an information collection control device and an information collection control method that can reduce the amount of collected information and the power consumption of the information acquisition device.

  In order to achieve the above object, an information collection control device according to the present invention determines a service operation based on information collected from one or more information acquisition devices and one or more service logics, and determines the determined service operation. An information collection control device arranged in a service providing system that provides a service by performing information on the information collected from the information acquisition device based on information collected from the information acquisition device in the past. Predicting means for predicting, analyzing the service logic using a prediction result by the predicting means, and collecting information from one or more information acquisition devices used in the service logic based on the analysis result Importance deriving means for deriving importance, and information for controlling information collection from the information acquisition device based on the importance derived by the importance deriving means Characterized in that a collecting control means.

  The information collection control method according to the present invention provides a service by determining a service operation based on information collected from one or more information acquisition devices and one or more service logics, and performing the determined service operation. An information collection control method in a service providing system, wherein a prediction step of predicting information collected from the information acquisition device at the present time based on information collected from the information acquisition device in the past, and the prediction step The importance of collecting the information from one or more information acquisition devices used in the service logic is analyzed based on the result of the analysis of the service logic And an information collection system in which information collection from the information acquisition apparatus is controlled based on the importance derived in the importance deriving step. Characterized by a step.

  According to these inventions, based on information collected from the information acquisition device in the past, information currently collected from the information acquisition device is predicted, and the service logic is analyzed using the prediction result to analyze the service logic. The importance of collecting information from one or more information acquisition devices used in the service logic is derived, and information collection from the information acquisition device is controlled based on the derived importance. Here, “control of information collection from the information acquisition device” refers to changing the frequency of information collection from the information acquisition device, or the quality of information acquisition in the information acquisition device (for example, position measurement in a GPS positioning device). Or, changing the accuracy is included. For example, the control includes reducing the frequency of information collection from the information acquisition device when the derived importance is low, and increasing the frequency of information collection from the information acquisition device when the derived importance is high. .

  Thus, deriving the importance of collecting information from one or more information acquisition devices used in the service logic, and controlling information collection from the information acquisition device based on the derived importance Thus, it is possible to control information collection according to the degree of importance, and it is possible to reduce the amount of collected information and the power consumption of the information acquisition apparatus.

  In the information collection control device according to the present invention, the service logic is described in the form of a Bayes decision tree, and the importance degree deriving means updates the prior probabilities of the nodes in the Bayes decision tree based on the prediction result by the prediction means. The service logic is analyzed by calculating the value of the information at the node based on the updated prior probability of the node, and the value of the information at the node obtained by the analysis is It is desirable that the degree of importance of collecting information is derived from the corresponding information acquisition unit. In the information collection control method according to the present invention, the service logic is described in the form of a Bayes decision tree, and the prior probability of the nodes in the Bayes decision tree is determined based on the prediction result in the prediction step in the importance derivation step. Updated, the value of information at the node is calculated based on the updated prior probability of the node, the service logic is analyzed, and based on the value of information at the node obtained by the analysis, It is desirable to derive the importance of collecting information from the information acquisition means corresponding to the node.

  In such a case, when analyzing the service logic described in the form of the Bayes decision tree, there is an advantage that the importance can be obtained immediately by analyzing the Bayes decision tree.

  According to the present invention, it is possible to reduce the amount of collected information and the power consumption of the information acquisition apparatus. Thereby, it is possible to increase the number of services that the system can provide simultaneously while maintaining the total cost of the entire system.

  Hereinafter, an information collection control apparatus according to an embodiment of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 schematically shows a configuration example of a service providing system 1 including an information collection control device 10 according to the present invention. The service providing system 1 includes a server 100 and various information acquisition devices 50a, 50b,... 50n (hereinafter collectively referred to as “information acquisition device 50”).

  The server 100 includes an information collection control device 10 and a service logic storage unit 20. Among these, the service logic storage unit 20 stores a plurality of service logics 21a, 21b,... 21n (hereinafter collectively referred to as “service logic 21”) written in the form of a Bayesian decision tree. In the following, a case where there are a plurality of service logics 21 will be described, but there may be a case where only one service logic 21 exists. An example of the service logic 21 will be described later with reference to FIGS. The server 100 periodically refers to information collected by communication with the information acquisition device 50, and executes a service according to the collected information and the service logic 21. Examples of the information acquisition device 50 include a terminal device having a GPS (Global Positioning System) that acquires position information, a temperature sensor, a humidity sensor, or a site on the Internet where weather forecast information or stock price information is registered. Can be mentioned.

  The information collection control device 10 in the server 100 includes a prediction unit 11 (corresponding to the prediction unit according to the present invention), an importance level deriving unit 12 (corresponding to the importance level deriving unit according to the present invention), and an information collection control unit 13 ( Corresponding to the information collection control means according to the present invention).

  The prediction unit 11 predicts current information based on information collected in the past from the information acquisition device 50. Here, a case where position information in a predefined two-dimensional coordinate system is acquired by using position positioning means such as GPS provided in a portable terminal carried by a certain user will be described as an example. For example, it is assumed that the user exists at the coordinates [20 m, 30 m] at the previous positioning and exists at the coordinates [20 m, 40 m] at the previous positioning. At this time, the moving speed can be calculated from the coordinates at the time of the previous and previous measurement, and the current position can be predicted from the previous position. With this prediction, the probability distribution of the user's position is found such that the probability of being within a circle of 5 m radius of [20 m, 50 m] is 0.8, and the probability of being other than that is 0.2. Such prediction is performed using a known prediction technique.

  The importance level deriving unit 12 derives the importance level of each information acquisition device in each service using the service logic 21 stored in the service logic storage unit 20 and the predicted value obtained by the prediction by the prediction unit 11. Specific processing operations will be described later.

  Before describing the degree-of-importance derivation processing operation, a service operation determination method in the server 100, which is a premise of the present invention, will be described. Here, it is assumed that the service logic 21 is described in the form of a Bayesian decision tree. Examples of service logic 21 described by a Bayesian decision tree are shown in FIGS. In the following, service operation determination using a Bayesian decision tree will be described using the service logic (1) for the umbrella preparation recommended service shown in FIG. 2 as an example. In this service logic (1), a probability relating to whether or not the current weather is rain is inferred using a state whether or not the humidity is high and a state whether or not the weather forecast is rain. Then, based on the probability obtained by the inference, it is determined whether or not a message for recommending umbrella preparation should be displayed on the user terminal. Such a determination is made periodically without any explicit instruction from the user.

  Each node indicated by an ellipse in FIG. 2 represents a state variable used for determining service operation. For example, a node described as high humidity (H) represents a state variable expressing whether or not the humidity is high, and the state variable takes two values, high (True) and low (False). The arrow between the nodes indicates that the state represented by the parent node (the original node from which the arrow appears) directly affects the state represented by the child node. In the service logic (1), whether or not the humidity is high has a direct influence on the state where it rains.

  Such an influence between nodes is expressed in the form of a conditional probability table. The conditional probability table is described for each node, and represents a probability distribution of values taken by the state of the node relative to the state of the parent node. For example, in service logic (1), the value that the state of raining (R) takes is affected by the values of its parent nodes H (high humidity) and W (weather forecast is rain), and its conditional probability Each row in the table shows the probability (P (R | H, W)) that R (rain falls) is true for each set of values taken by H (high humidity) and W (weather forecast is rain). Represents. For example, for a pair where H (high humidity) is True and W (weather forecast is rain) is True, the probability (P (R | H, W)) that R (rains) is True is 0.95. It is expressed.

  On the other hand, a predetermined probability (prior probability) is given to a node that does not have a parent (that is, a node that does not have an incoming arrow). For example, in service logic (1), the probability of high humidity P (H) = 0.2 is expressed.

  By using the conditional probability table and the value of the prior probability, it is possible to calculate probabilities that other states can take when evidence for some states is obtained. For example, the probability of raining and the probability of not falling (P (R | H)) can be calculated when evidence is given for a condition of high humidity (H = True). Such a probability can be obtained from a value inside the Bayesian decision tree by a known calculation algorithm.

  The rectangle in the service logic represents a decision-making option in the decision tree. The rectangle in service logic (1) (that is, operation (A)) indicates two operations that recommend to carry an umbrella (a1) and do nothing (a2). In addition, diamonds in the service logic indicate utility values in the state after determining the actual operation to be performed. The utility values here are expressed in a table format as shown at the right end of FIG. 2, and each row indicates the selected action and the value of the state variable that affects the utility at that time (the value of the state variable of the parent node of the utility). The utility value for the pair is shown.

ここでr_iは、雨が降るという状態変数のとり得る各値を示す。傘の持ち出しを推奨する動作（a₁）及び何もしないという動作（a₂）の期待効用は、次のように求められる。
EU(a₁) = 0.2134×10 + 0.7866×6 = 6.8536
EU(a₂) = 0.2134×(-7) + 0.7866×9 = 5.5856 In service operation judgment using a Bayesian decision tree, the utility expected when EU inputs each node's evidence using currently available information and performs each operation with that evidence obtained (EU) Calculate Then, the operation having the largest utility (EU) obtained by the calculation is executed. For example, in the service logic (1), the expected utility before information is obtained is obtained using the following equation (1).

Here, r _i represents each possible value of the state variable that rains. The expected utility of the action (a ₁ ) that recommends taking out an umbrella and the action (a ₂ ) that does nothing is calculated as follows.
EU (a ₁ ) = 0.2134 × 10 + 0.7866 × 6 = 6.8536
EU (a ₂ ) = 0.2134 × (-7) + 0.7866 × 9 = 5.5856

  “0.2134” here is a group in which H (high humidity) is True and W (weather forecast is rain) is True, a group in which H is True and W is False, a group in which H is False and W is True, and It is obtained by the sum of the probabilities that R (raining) is true for each pair of H = False and W = False. That is, 0.2 × 0.1 × 0.95 + 0.2 × 0.9 × 0.6 + 0.8 × 0.1 × 0.9 + 0.8 × 0.9 × 0.02 = 0.2134. On the other hand, “0.7866” is obtained as 1−0.2134.

In the above case, the expected utility EU (a ₁ ) of the action (a ₁ ) that recommends taking out the umbrella is larger than the expected utility EU (a ₂ ) of the action that does nothing (a ₂ ). The recommended operation is performed. As such an operation, for example, information (such as a message recommending to take out an umbrella) is transmitted to the terminal device to perform screen display, voice notification, or the like. Along with this, a transmission unit for transmitting information to the terminal device is required in the server 100.

  The service described by each service logic obtains evidence about some nodes of the service logic from the information acquisition device 50. For example, the information acquisition device 50 used in the service logic (1) is a humidity sensor included in the user terminal and a weather forecast site on the Internet.

  Subsequently, the operation of the importance level deriving unit 12 will be described in more detail. First, the probability distribution of the current value is input from the prediction unit 11 using information collected at the time of past determination. The importance level deriving unit 12 updates the distribution of prior probabilities for the possible values of each node according to the result. For example, since the previous weather forecast was sunny, the probability that the current forecast was rain was 0.1, the humidity at the time of the previous information collection was low and the humidity did not tend to rise, so the probability of high humidity was 0.2 Be changed. Based on these values, the value of information by collecting each information is calculated as follows.

  The value of a piece of information is calculated as the “increase in expected utility” due to obtaining that information relative to before obtaining that information. This “increase in expected utility” is obtained by analyzing the Bayesian decision tree as follows.

First, the expected utility MEU of the action determined by the service logic based on the logic before obtaining information is calculated. This expected utility MEU is the expected utility of the operation adopted at the time of the service operation determination. When no evidence is input in the service logic (1), the expected utility EU (a ₁ ) (= 6.8536) It corresponds to.

  Subsequently, the maximum expected utility when the humidity sensor information and the weather forecast information are respectively obtained is calculated. This maximum expected utility is calculated using the probability value (obtained by the inference algorithm) when evidence is obtained. For example, in service logic (1), the maximum expected utility when humidity information is obtained is obtained as follows.

When humidity is high (H = True):
EU (a ₁ | H = True) = 0.635 × 10 + 0.365 × 6 = 8.54
EU (a ₂ | H = True) = 0.635 × (-7) + 0.365 × 9 = 1.16
In this case, the maximum expected utility MEU (H = True) is 8.54. “0.635” here is based on the premise that H (high humidity) is True, H (high humidity) is True and W (weather forecast is rain), and H is True and W is False. The sum of the probabilities that R (raining) is true for each pair. That is, it is obtained as 0.1 × 0.95 + 0.9 × 0.6 = 0.635. On the other hand, “0.365” is obtained as 1−0.635.

When humidity is low (H = False):
EU (a ₁ | H = False) = 0.108 × 10 + 0.892 × 6 = 6.432
EU (a ₂ | H = False) = 0.108 × (-7) + 0.892 × 9 = 7.272
In this case, the maximum expected utility MEU (H = False) is 7.272. “0.108” here is based on the premise that H (high humidity) is False, H (high humidity) is False and W (weather forecast is rain) is True, and H is False and W is False. The sum of the probabilities that R (raining) is true for each pair. That is, it is obtained as 0.1 × 0.9 + 0.9 × 0.02 = 0.108. On the other hand, “0.892” is obtained as 1−0.108.

  Since the prior probability shows that the probability of high humidity is 0.2 and the probability of low is 0.8, when making a decision by obtaining evidence about whether the humidity is high (ie, collecting information from a humidity sensor) Expected utility is the sum of the value obtained by multiplying the probability of high humidity by the maximum expected utility when humidity is high, and the value obtained by multiplying the probability of low humidity and the maximum expected utility when humidity is low. can get.

The gain of the maximum expected utility by obtaining the humidity information (hereinafter referred to as “value of information”) is different from the maximum expected utility when the humidity information is not obtained as in the following formula (2). Can be obtained.

  By calculating the above equation (2), the first term on the right side becomes 8.54 × 0.2 + 7.272 × 0.8 = 7.5256. Since the value of the first term on the right side is higher than the MEU value (6.8536), it can be seen that the utility expected when the humidity information is obtained is higher than the utility before obtaining the humidity information. By obtaining humidity information from the humidity sensor as to whether or not the humidity is high, the expected information value VPI (H) is 7.5256−6.8536 = 0.672.

Similarly, the utility by checking the weather forecast is obtained.
If the weather forecast is rain (W = True):
EU (a ₁ | W = True) = 0.91 × 10 + 0.09 × 6 = 9.64
EU (a ₂ | W = True) = 0.91 × (-7) + 0.09 × 9 = -5.56
In this case, the maximum expected utility MEU (W = True) is 9.64. “0.91” here is based on the premise that W (weather forecast is rain) is True, H (high humidity) is True and W (weather forecast is rain) is True, and H is False and W is It is obtained by the sum of the probabilities that R (raining) will be True for each True pair. That is, it is obtained as 0.2 × 0.95 + 0.8 × 0.9 = 0.91. On the other hand, “0.09” is obtained as 1−0.91.
If the weather forecast is not rain (W = False):
EU (a ₁ | W = False) = 0.136 × 10 + 0.864 × 6 = 6.544
EU (a ₂ | W = False) = 0.136 × (-7) + 0.864 × 9 = 6.824
In this case, the maximum expected utility MEU (W = False) is 6.824. “0.136” here is based on the assumption that W (weather forecast is rain) is False, H (high humidity) is True and W (weather forecast is rain) is False, and H is False and W is It is obtained by the sum of the probabilities that R (raining) is true for each of the false pairs. That is, it is obtained as 0.2 × 0.6 + 0.8 × 0.02 = 0.136. On the other hand, “0.864” is obtained as 1−0.136.

  Then, the expected value of the maximum expected utility when obtaining the weather forecast information can be calculated, and the value is 9.64 × 0.1 + 6.824 × 0.9 = 7.1056. Accordingly, the value VPI (H) of information expected by confirming the weather forecast regarding whether the weather forecast is rain or not is 7.1056−6.8536 = 0.252.

  The value of the information value VPI (H) derived as described above is set as the importance of each information acquisition device. That is, the value VPI (H) when the humidity sensor information is obtained is the importance of the humidity sensor, and the value VPI (H) when the weather forecast information is obtained is the importance of the weather forecast information site.

  Similarly, the importance of each information acquisition device in the service logics (2) and (3) shown in FIGS. 3 and 4 can be derived. The service logic (2) refers to an indoor positioning device that obtains information about whether or not the user is in a conference room and an in-house system that obtains information about whether or not there is a conference reservation for the user to participate. Also in this example, it is assumed that a conditional probability table is given as in the case of the service logic (1). With reference to the value, the value of obtaining information from each information acquisition device can be calculated. Here, although explanation of the derivation process is omitted, it is assumed that the importance of the indoor positioning device in the service logic (2) is 0.347 and the importance of the in-house system is 0.452. The service logic (3) in FIG. 4 obtains information on whether or not he / she is at his / her seat from the indoor positioning device in the same manner as the service logic (2). Assume that the importance of indoor positioning device in service logic (3) is 0.462. The derived importance is used in later explanation.

  Next, the information collection control unit 13 will be described. The information collection control unit 13 inputs the importance of each information acquisition device in each service obtained from the importance derivation unit 12, and performs information collection processing to collect information at a frequency proportional to the ratio of the importance. Control. However, an information acquisition apparatus used for a plurality of services has the importance obtained by adding up the importance in all service logics using the information acquisition apparatus.

  As an example, a frequency determination method in the case where services described in the three service logics shown in FIGS. First, by analyzing the service logic (1), the importance 0.672 of the information from the humidity sensor and the importance 0.252 of the information from the weather forecast site are derived. Subsequently, by analyzing the service logic (2), the importance 0.347 of the indoor positioning device and the importance 0.452 of the in-house system are derived, and by analyzing the service logic (3), the importance of the indoor positioning device A degree of 0.462 is derived.

  From the above results, the importance of the humidity sensor is 0.672, the importance of the weather forecast site is 0.252, the importance of information from the in-house system is 0.452, and the importance of the indoor positioning device is The importance in the service logics (2) and (3) to be used is added to be 0.347 + 0.462 = 0.809.

  Then, the frequency of information collection from each information acquisition device is determined according to the importance ratio of each information acquisition device. For example, if the importance level is 1, assuming that the measurement frequency is once every 60 seconds, the measurement frequency of the humidity sensor is 60 / 0.672 = 89, so it is determined once every 89 seconds. Similarly, the measurement frequency of the weather forecast site is determined once every 238 seconds, the measurement frequency of the indoor positioning device is once every 74 seconds, and the measurement frequency from the in-house system is once every 132 seconds.

  Next, the information collection control operation in the present embodiment will be described with reference to FIGS.

  First, the prediction unit 11 predicts current information based on information collected in the past from the information acquisition device 50 (S1 in FIG. 5). Here, a case will be described as an example in which position information is acquired using position positioning means such as GPS provided in a portable terminal carried by the user. It is assumed that the user exists at a coordinate [20m, 30m] in a predetermined two-dimensional coordinate system at the previous positioning and exists at a coordinate [20m, 40m] at the previous positioning. At this time, the moving speed can be calculated from the coordinates at the time of the previous and previous measurement, and the current position can be predicted from the previous position. With this prediction, the probability distribution of the user's position is found such that the probability of being within a circle of 5 m radius of [20 m, 50 m] is 0.8, and the probability of being other than that is 0.2.

  Next, using the service logic 21 stored in the service logic storage unit 20 and the value predicted by the prediction unit 11, the importance level determination unit 12 derives the importance level of each information acquisition device in each service ( S2 in FIG. A flowchart of the importance degree derivation process is shown in FIG. That is, the prior probability of the node in the Bayes decision tree is updated based on the prediction result in S1 of FIG. 5 (S21 of FIG. 6), and the value of the information in the node is calculated based on the updated prior probability of the node. (S22). Then, based on the obtained value of information in the node, the importance of collecting information from the information acquisition device 50 corresponding to the node is derived (S23).

  Next, the information collection control unit 13 determines the frequency of information collection from each information acquisition device according to the derived importance (S3 in FIG. 5). A flowchart of the information collection frequency determination process is shown in FIG. The information collection control unit 13 acquires each importance level of the information acquisition device 50 from the importance level deriving unit 12, and adds the importance levels in all the service logics that use the information acquisition device 50 to each information acquisition device. The obtained value is set as the importance of each information acquisition device (S31 in FIG. 7), and the frequency of information collection is determined according to the ratio of the importance (S32).

  Then, the information collection control unit 13 controls the information collection operation from each information acquisition device so as to collect information at the determined frequency (S4 in FIG. 5). Information collection control is performed as described above.

  According to the embodiment described above, the importance of collecting information from the information acquisition device used in the service logic is derived, and information collection from the information acquisition device is controlled based on the derived importance. As a result, it is possible to control information collection according to the degree of importance, and it is possible to reduce the amount of collected information and the power consumption of the information acquisition apparatus.

  Note that information collection includes (1) a case in which an information acquisition request is periodically transmitted to the information acquisition device, and (2) only the frequency with which collection is desired is transmitted to the information acquisition device, and the information acquisition device is in accordance with the frequency. There are two methods for realizing information transmission, but information collection may be realized by either method. However, when the information acquisition device has a function of periodically acquiring information at the instructed frequency and transmitting the acquired information, the method of realizing the above (2) adopts the total communication amount. It is desirable from the aspect of.

  In the above embodiment, the information collection control device and the service logic storage unit are arranged in a single server. However, as shown in FIG. 8, the information collection control device 10 and the service logic storage unit 20 are arranged. A configuration in which the information acquisition device 50 is arranged in a single terminal device 200 may be adopted. In this case, examples of the information acquisition device 50 include a GPS device provided in the terminal device 200, indoor positioning means, and a temperature sensor.

It is a figure which shows the functional structure of the service provision system in one Embodiment of this invention. It is a figure which shows the service logic of the preparation recommendation service of an umbrella. It is a figure which shows the service logic of an automatic manner mode service. It is a figure which shows the service logic of the message completion notification service. It is a flowchart which shows information collection control operation | movement. It is a flowchart which shows the derivation | leading-out process of importance. It is a flowchart which shows the frequency determination process of information collection. It is a figure which shows the functional structure of the service provision system in another embodiment of this invention.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 1 ... Service provision system, 10 ... Information collection control apparatus, 11 ... Prediction part, 12 ... Importance derivation part, 13 ... Information collection control part, 20 ... Service logic storage part, 21 ... Service logic, 50 ... Information acquisition apparatus, 100 ... server, 200 ... terminal device.

Claims (4)

Information collection control disposed in a service providing system that determines a service operation based on information collected from one or more information acquisition devices and one or more service logics and provides the service by performing the determined service operation A device,
Based on information collected from the information acquisition device in the past, prediction means for predicting information collected from the information acquisition device at the present time;
The service logic is analyzed using the prediction result by the prediction means, and the importance of deriving the importance of collecting information from one or more information acquisition devices used in the service logic based on the analysis result Degree derivation means;
Information collection control means for controlling information collection from the information acquisition device based on the importance derived by the importance derivation means;
An information collection control device. The service logic is described in the form of a Bayesian decision tree,
The importance degree derivation means includes:
Updating the prior probability of the node in the Bayesian decision tree based on the prediction result by the predicting means, and calculating the value of the information in the node based on the updated prior probability of the node; Parse and
Deriving the importance of collecting information from the information acquisition means corresponding to the node based on the value of the information in the node obtained by the analysis,
The information collection control device according to claim 1. An information collection control method in a service providing system that provides a service by determining a service operation based on information collected from one or more information acquisition devices and one or more service logics and performing the determined service operation. And
Based on information collected from the information acquisition device in the past, a prediction step in which information collected from the information acquisition device at the present time is predicted,
The service logic is analyzed using the prediction result in the prediction step, and the importance of collecting information from one or more information acquisition devices used in the service logic is derived based on the analysis result. Importance derivation step,
An information collection control step in which information collection from the information acquisition device is controlled based on the importance derived in the importance derivation step;
An information collection control method. The service logic is described in the form of a Bayesian decision tree,
In the importance derivation step,
The prior probability of the node in the Bayes decision tree is updated based on the prediction result in the prediction step, and the value of the information in the node is calculated based on the updated prior probability of the node, so that the service Logic is parsed,
Based on the value of information in the node obtained by analysis, the importance of collecting information from the information acquisition means corresponding to the node is derived.
The information collection control method according to claim 3.

Images