JP2019082895A - Device to determine time to visit - Google Patents

Abstract

To determine visiting time, allowing efficient home visits for deliveries and the like.SOLUTION: A device to determine time to visit 10 is a device to determine visiting time for a plurality of homes to visit, and that comprises: a model storage section 12 for inputting information relating to homes to visit and storing a precision ratio focused model and a recall ratio focused model which can predict persons being at home when visiting in accordance with time; an acquisition section 13 for, for each of the plurality of homes to visit, acquiring information relating to homes to visit which is used for predicting if persons are at home when visiting; a visiting time determination section 14 for predicting, for at least any of the plurality of homes to visit, by the precision ratio focused model, and predicting, for at least any of the plurality of homes to visit, by the recall ratio focused model, and determining visiting time for each of the plurality of homes to visit, from preset conditions to visit and the results of those predictions; and an outputting section 15 for outputting information indicating the determined visiting time for each of the plurality of homes to visit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a visit time determination device that determines visit times for a plurality of visit destinations.

  As shown in Patent Document 1, it has been conventionally proposed to estimate the at-home time of a delivery destination and create a delivery schedule in delivery of a package.

JP, 2013-170050, A

  However, there is a possibility that efficient delivery can not be performed by merely estimating the at-home time of the delivery destination. For example, if the home times of a plurality of delivery destinations are concentrated in a certain time zone, while delivery becomes necessary in that time zone, delivery is possible although delivery is possible in other time zones. There was a risk that it would be a delivery schedule not to

  The present invention has been made in view of the above, and it is an object of the present invention to provide a visit time determination device capable of determining a visit time that enables efficient delivery visits and the like.

  In order to achieve the above object, the visit time determination device according to the present invention is a visit time determination device that determines visit times for a plurality of visit destinations, and inputs information related to the visit destinations and determines the time A model storage unit that stores two models for predicting the at-home location according to the visit destination, and that among the two models, a relevance ratio-oriented model having a high predictive accuracy rate and a recall rate-oriented model having a high predictive recall rate; A model that uses information acquired by the acquiring unit for at least one of an acquiring unit that acquires information related to the visiting destination used for predicting the at-home of the visiting destination for each of the plurality of visiting destinations, and The prediction by the relevance ratio-oriented model stored by the storage unit is performed, and storage is performed by the model storage unit using information acquired by the acquisition unit for at least one of the plurality of visit destinations. The visit time determination unit determines the visit time for each of the plurality of visit destinations based on the conditions of the visit set in advance and the result of the forecast by performing prediction based on the recall ratio-oriented model and the visit time determination unit And an output unit that outputs information indicating visit times for each of the determined plurality of visit destinations.

  In the visit time determination device according to the present invention, prediction based on the relevance ratio model is performed on at least one of a plurality of visit destinations, and prediction based on the recall ratio model is performed on at least one of the plurality of visit destinations. A visit time is determined for each of a plurality of visit destinations. Thus, visit times can be determined that allow for efficient visits that take into account both relevance and recall.

  According to the present invention, it is possible to determine a visit time that enables efficient visits taking into account both accuracy and recall.

It is a figure which shows the structure of the visit time determination apparatus which concerns on embodiment of this invention. It is a figure for demonstrating the relevance and recall of a prediction. It is a flowchart which shows the process performed with the visit time determination apparatus which concerns on embodiment of this invention. It is a figure which shows the hardware constitutions of the visit time determination apparatus which concerns on embodiment of this invention.

  Hereinafter, an embodiment of a visit time determination device according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference symbols, without redundant description.

  The visit time determination apparatus 10 which concerns on FIG. 1 at this embodiment is shown. The visit time determination device 10 is a device (system) that determines visit time (visit timing) for a plurality of visit destinations. Specifically, the visit time determination device 10 determines, as the visit time, a delivery time (timing) at which the delivery company delivers (delivers) the package to the delivery destination (visit destination). When delivering a package, a resident of the delivery destination needs to be at home. Therefore, the visit time determination device 10 predicts the home of the resident of the delivery destination and determines the delivery time. The visit time determination device 10 determines, for example, in which time zone of one hour unit each package is to be delivered, in one day (delivery date) unit.

  Subsequently, the function of the visit time determination device 10 according to the present embodiment will be described. As shown in FIG. 1, the visit time determination apparatus 10 is configured to include a model generation unit 11, a model storage unit 12, an acquisition unit 13, a visit time determination unit 14, and an output unit 15.

  The model generation unit 11 is a functional unit that inputs information related to the delivery destination and generates a model that predicts the at-home location of the delivery destination according to the time. The model inputs information on the delivery destination and information on the time of the prediction target as an explanatory variable, and outputs a score indicating the possibility of the delivery destination at home at the time of the prediction target. For example, the higher the score, the higher the possibility that the delivery destination is at home. As the information related to the delivery destination input to the model, for example, it is possible to use information indicating the at-home situation of the delivery destination past the predicted time, that is, information indicating the result of at home or absence of the delivery destination. The past performance may be, for example, information on at home (deliverable) or absent (deliverable) at the time of past delivery. More specifically, it is possible to use the value of the past number of times of at home / (the number of times of at home + the number of absences), which is a value of the ratio of the number of times of at home in the past . In addition, the above information may be information associated with a time relating to the result, for example, a month, a day of the week, and a time of day. In addition, as the information related to the delivery destination input to the model, information other than the above information, for example, information indicating the location of the delivery destination, and attributes such as the age and gender of the resident may be used.

  Moreover, as information concerning the time of prediction object, the information which shows the time of the month of prediction object, a day of the week, and the 1st can be used, for example. Moreover, as information input into a model as an explanatory variable, it is not restricted to said thing, Arbitrary information which may affect a home condition may be included. For example, information indicating the weather at the time to be predicted may be input to the model as an explanatory variable. When the information is input to the model, the information is acquired and used in the same manner as the information related to the delivery destination, etc. in the generation of the model below and the prediction using the model. .

  The model generation unit 11 acquires learning data for generating a model. The learning data is information corresponding to information used as an explanatory variable and a target variable of the model. These pieces of information can use information in the past actual delivery. The information corresponding to the information used as the explanatory variable of the model is the information related to the delivery destination in the actual delivery and the information related to the actual delivery time. The information corresponding to the information used as the objective variable of the model is information indicating whether the delivery destination was at home or absent at the actual delivery. The information used as the objective variable is, for example, quantified as 1 when the delivery destination is at home and 0 when the delivery destination is absent. This indicates that if the score output (calculated) from the model is large (close to 1), it indicates that the possibility of being at home is high, and if the score is small (close to 0), it can be absent It indicates that the sex is high.

  The above information for one delivery is regarded as one sample which is learning data, and the model generation unit 11 acquires a plurality of samples (for example, several thousand samples) that can generate a model appropriately. For example, a manager or the like of the visit time determination device 10 generates the above sample based on the past delivery, and inputs the sample to the visit time determination device 10. The model generation unit 11 receives and acquires the input sample. The model generation unit 11 generates a model by machine learning using, for example, a sample. The generation of a model by machine learning can be performed as in the past.

  In the present embodiment, two models, that is, a relevance-weighted model and a recall-weighted model, are used as the models described above. Here, the accuracy rate and the recall rate of the prediction will be described. FIG. 2 shows a combination of prediction and results. In FIG. 2, a to d show the numbers in each case. That is, a is the number when it was predicted to be at home and was actually at home, b was the number when it was predicted to be absent and was actually at home, c was predicted to be at home and was actually absent The number of cases, d is the number of cases predicted to be absent and actually absent. The accuracy rate is a value represented by a / (a + c), and is a value indicating how much you are at home and how much you are really at home. The recall rate is a value represented by a / (a + b), which is a value indicating how much of the person who is actually at home can be covered.

  The relevance ratio-oriented model is a model having a high relevance ratio of prediction (prediction with home) among two models. The recall rate-oriented model is a model having a high recall rate of prediction (prediction with home) among the two models. Although the above-mentioned model outputs (calculates) a score, the relevance ratio and the recall ratio are those when home and absence are judged based on the score. For example, when the score is equal to or greater than a preset threshold, it is determined that the user is at home, and when the score is less than the threshold, the absence is determined.

  Assuming that learning data at the time of creating a model is based on the information at the time of actual delivery as described above, the samples are usually more at home (positive example) and absent (negative example) Will be reduced. For example, a positive example is a sample of about 80%. A precision-weighted model can be generated by generating a model using a sample with a relatively small proportion of positive examples, and a reproduction-oriented setting by using a sample with a relatively large proportion of positive examples Models can be generated.

  Therefore, the model generation unit 11 acquires samples as described above, adjusts the number of samples acquired according to the generated model, and generates a relevance-weighted model and a recall-weighted model. For example, the model generation unit 11 generates a recall emphasis model by using the acquired sample as it is. On the other hand, the model generation unit 11 increases the number of negative examples among the acquired samples, and generates a relevance-weighted model using the samples in which the negative examples are increased. The increase of negative cases, for example, doubles negative cases by using one negative case as two identical negative cases, or artificially increases negative cases by conventional techniques based on existing negative cases. Is done. In addition to the above, positive cases are increased from the acquired samples or negative cases are reduced to generate a recall-oriented model, or positive examples are reduced from the acquired samples to generate a relevance-oriented model. It is also possible to

  Also, instead of adjusting the number of samples, each model may be generated by changing the penalty for misprediction in machine learning. For example, a precision weighted model may be generated by giving a greater penalty to prediction errors of negative examples than in generating a recall weighted model. The model generation unit 11 outputs the generated relevance ratio emphasis model and the recall ratio emphasis model to the model storage unit 12.

  The model storage unit 12 is a functional unit that receives the relevance ratio emphasis model and the recall ratio emphasis model from the model generation unit 11 and stores the two input models. The two models stored by the model storage unit 12 are used when the delivery time determination unit 14 determines the delivery time.

  The acquisition unit 13 is a functional unit that acquires information related to the delivery destination used for the at-home prediction of the delivery destination for each of a plurality of delivery destinations for which delivery time is to be determined (there is a package to be delivered). The acquisition unit 13 acquires information indicating the at-home status of the delivery destination in the past as the information related to the delivery destination.

  For example, as in the case of generation of a sample of learning data (only information corresponding to explanatory variables), a delivery destination having a package to be delivered on the day when the administrator of the visit time determination device 10 etc. The above information is generated for each delivery destination for which the delivery time is to be determined, and is input to the visit time determination device 10. The acquisition unit 13 receives and acquires the input information. The acquisition unit 13 outputs the acquired information to the visit time determination unit 14.

  The visit time determination unit 14 is a functional unit that determines a delivery time for each of a plurality of delivery destinations using the relevance ratio-oriented model and the recall ratio-oriented model stored by the model storage unit 12. The visit time determination unit 14 uses the information acquired by the acquisition unit 13 for at least one of the plurality of delivery destinations to perform prediction with the relevance ratio-oriented model, and obtains for at least one of the plurality of delivery destinations. Using the information acquired by the unit 13, the prediction based on the recall ratio model is performed, and the delivery time is determined for each of the plurality of delivery destinations from the conditions of the delivery (visit) set in advance and the result of the prediction. Do. The visit time determination unit 14 is configured to perform both prediction by the relevance ratio-oriented model and prediction by the recall ratio-oriented model using information acquired by the acquisition unit 13 for at least any of the plurality of delivery destinations. From the condition of delivery and the result of the prediction, the delivery time is determined for each of the plurality of delivery destinations. The visit time determination unit 14 predicts each of a plurality of delivery destinations by the relevance ratio-oriented model, determines whether the delivery time can be determined from the delivery conditions and the result of the prediction, and can not determine the delivery time. For each of the delivery destinations determined as above, the prediction based on the recall ratio model is performed, and the delivery time is determined for each of the delivery destinations from the conditions of the delivery and the result of the prediction. Specifically, the visit time determination unit 14 determines the delivery time as follows.

  The visit time determination unit 14 stores, as a condition for delivery, information indicating a standard delivery amount, which is a capability capable of delivery per unit time (for example, one hour). The standard delivery amount is, for example, the number of deliverables (the number of packages) that the delivery company can deliver in the unit of time. The standard delivery amount is set in advance by a manager or the like of the visit time determination device 10 and is input to the visit time determination device 10. The standard delivery amount may be set according to the time zone (day of the week and time of day). The standard delivery amount may be, for example, a value of (average delivery amount or median value in the relevant time zone in the delivery target area) × (provision level of delivery person). The proficiency of a delivery clerk is the ratio of the performance of the delivery clerk to the average of all the delivery clerks responsible for the area. The standard delivery amount is used as an initial value of an allocation upper limit described later for each unit time (time zone) as described below.

  The visit time determination unit 14 inputs information related to the delivery destination from the acquisition unit 13 for each of the plurality of delivery destinations for which the delivery time is to be determined. In addition, the visit time determination unit 14 reads out the relevance ratio emphasis model and the recall ratio emphasis model stored by the model storage unit 12. The visit time determination unit 14 calculates, for each of the delivery destinations, a score based on the relevance ratio-oriented model for each time zone of the delivery date. Specifically, the visit time determination unit 14 calculates score by inputting information related to the delivery destination and information related to the time zone (time to be predicted) as an explanatory variable. As described above, the score for each time zone (for example, 9 o'clock, 10 o'clock, etc.) is a value indicating the possibility of staying at the delivery destination.

  The visit time determination unit 14 assigns, for each delivery destination, a time zone having the highest score among the calculated scores of each time zone. That is, the visit time determination unit 14 (temporarily) determines that the package is to be delivered to the delivery destination in the allocated time zone. The visit time determination unit 14 compares, for each time zone, the number of assigned delivery destinations with the standard delivery amount, which is the initial value of the allocation upper limit. When the number of assigned destinations for all the time zones is less than or equal to the standard delivery amount, the visit time determination unit 14 determines the assigned time zones as the delivery times for each of the delivery destinations. .

  When the number of delivery destinations allocated for any of the time zones exceeds the standard delivery amount, the visit time determination unit 14 determines the time until the number of delivery destinations allocated falls below the standard delivery amount. Remove the assignment from the delivery destination assigned to the band in descending order of score (cancel the assignment). That is, the visit time determination unit 14 excludes the delivery destination having a low possibility of being at home from the delivery targets of the time zone. The visit time determination unit 14 determines the allocated time zone as the delivery time for the delivery destinations for which the assignment has not been removed.

  The visit time determination unit 14 determines that the number of delivery destinations allocated by the score based on the relevance ratio-oriented model is less than or equal to the standard delivery amount among the delivery date times for each delivery destination for which allocation has been removed. The score based on the recall ratio focused model is calculated for each time zone in which the user is present The calculation of the score by the recall priority model is performed similarly to the calculation of the score by the relevance ratio model. The visit time determination unit 14 assigns the time slot having the highest score among the calculated scores of each time slot for each delivery destination (performs reassignment). As the score used for this allocation, not only the score by the recall rate-oriented model but also the score by the relevance rate-oriented model may be used. For example, the score used for assignment may be α (score according to the relevance ratio-oriented model) + (1−α) (score according to the recall ratio emphasis model) (0 ≦ α <1). Here, α is a parameter set in advance.

  The visit time determination unit 14 compares, for each time zone, the number of assigned delivery destinations (including the assignment by the score based on the accuracy rate model) and the standard delivery amount. When the number of assigned destinations for all the time zones is less than or equal to the standard delivery amount, the visit time determination unit 14 determines the assigned time zones as the delivery times for each of the delivery destinations. .

  When the number of delivery destinations allocated for any of the time zones exceeds the standard delivery amount, the visit time determination unit 14 eases the upper limit of the allocation for each time zone. For example, a new allocation upper limit is calculated by multiplying the current allocation upper limit by a coefficient which exceeds 1 set in advance. The visit time determination unit 14 removes all allocations and performs the above allocation to the delivery destination time zone again using the new allocation upper limit. Specifically, allocation based on the score by the relevance ratio-oriented model and allocation based on the score by the recall ratio-oriented model are performed. The visit time determination unit 14 repeats the above until allocation is completed for all delivery destinations. The calculation of the score may be performed only once at the beginning. The visit time determination unit 14 outputs, to the output unit 15, information indicating the delivery time for each of the determined delivery destinations.

  The output unit 15 is a functional unit that outputs information indicating visit times for each of the plurality of delivery destinations determined by the visit time determination unit 14. The output unit 15 inputs information indicating the delivery time for each delivery destination from the visit time determination unit 14. The output unit 15 displays and outputs the information, for example, on a display device included in the visit time determination device 10. Based on this output, the information is referred to by the administrator of the visit time determination device 10 and used for delivery. Alternatively, the output unit 15 may perform output other than display, and may transmit and output to other devices or other modules. The above is the function of the visit time determination device 10 according to the present embodiment.

  Subsequently, processing (operation method performed by the visit time determination device 10) executed by the visit time determination device 10 according to the present embodiment will be described using the flowchart of FIG. In this processing, first, the model generation unit 11 generates a relevance-weighted model and a recall-weighted model, which are two models for predicting the home of the delivery destination (S01). The generation of the model does not have to be performed each time the delivery time is determined, and may not be performed once the model is created. Subsequently, the acquisition unit 13 acquires information related to the delivery destination used for the home prediction of the delivery destination (S02).

  Subsequently, the visit time determination unit 14 calculates, for each delivery destination, a score based on the relevance ratio-oriented model for each time zone of the delivery date (S03). Subsequently, the visiting time determination unit 14 allocates, for each delivery destination, a time zone having the highest score among the calculated time zone scores (S04). Subsequently, the delivery time assignment unit 14 cancels the delivery destination assignment based on the assignment upper limit (S05). If there is no assignment to be canceled, the following processing of S09 is performed on the assumption that all delivery destinations have been assigned.

  Subsequently, for each delivery destination for which the assignment has been canceled by the visit time determination unit 14, the number of delivery destinations allocated in the assignment according to the score based on the relevance ratio model is within the assignment upper limit within the time zone of delivery date. The score based on the recall-weighted model is calculated for each time zone that is on (S06). Subsequently, the visiting time determination unit 14 assigns, for each delivery destination, a time zone having the highest score among the calculated time zone scores (S07). For all time zones, when the number of assigned destinations is less than or equal to the allocation upper limit, that is, when all the destinations can be assigned (YES in S08), the delivery time by the visit time determination unit 14 For the above, the assigned time zone is determined as the delivery time. Then, the information which shows the delivery time with respect to each delivery destination is output by the output part 15 (S09).

  On the other hand, after S07, if the number of assigned destinations for all time zones is not less than or equal to the allocation upper limit, ie, if all delivery destinations have not been assigned (NO at S08), a visit The upper limit of allocation of each time zone is relaxed by the time determination unit 14 (S10). Subsequently, all the allocations of the delivery destinations are cancelled, and the processing of S04 to S08 is repeated again. In the processes of S04 to S08, it is not necessary to repeatedly calculate the score (S06) based on the recall ratio-oriented model. The above is the processing executed by the visit time determination device 10 according to the present embodiment.

  In the present embodiment, the prediction based on the relevance ratio model is performed on at least one of the plurality of delivery destinations, and the prediction based on the recall ratio model is performed on the at least one of the plurality of delivery destinations. Delivery times are determined for each. Thus, delivery times can be determined that allow for efficient visits that take into account both relevance and recall.

  Specifically, as in the present embodiment, first, allocation is performed based on prediction with a relevance ratio-based model, and for delivery destinations not assigned by allocation based on prediction with a accuracy ratio-based model, prediction using a recall ratio-based model Assignment may be made based on That is, it is possible to determine which model's prediction to use based on the gap (supply and demand gap) between the assigned upper limit and the assigned delivery destination (package) based on the standard delivery amount for each time zone. According to this configuration, the allocation based on the prediction based on the relevance ratio model can perform the delivery that is less likely to be absent when the delivery is performed (perform delivery shown in FIG. 2 with less withdrawal). Can) The allocation based on the prediction based on the relevance ratio-oriented model using the delivery capacity not used in the subsequent allocation can prevent itself from not delivering despite being at home (as shown in FIG. 2, opportunity loss). Can prevent that).

  The demand for packages to be delivered varies greatly depending on the time of day, the day of the week, or seasonal factors such as Chinese yuan. By determining the delivery time as described above, when the demand is tight, emphasis is on the accuracy of the forecast, and if there is available delivery, a place that may be at home (a delivery destination that may be present) You can also go around. That is, it is possible to determine the delivery time that leads to efficient delivery in line with delivery efficiency, while incorporating fluctuations in demand. However, how to use the prediction and recall ratio-oriented model by the relevance ratio-oriented model is not necessarily limited to the above. For example, for a certain delivery destination, only prediction with a relevance ratio-oriented model may be performed, and for another delivery destination, only prediction with a recall ratio-oriented model may be performed. Even in this case, in the entire determination of the delivery time, both prediction by the relevance ratio-oriented model and prediction by the recall ratio-oriented model are performed.

  Further, as the information (information to be input to the model) related to the delivery destination used for the prediction as in the present embodiment, information indicating the at-home situation of the delivery destination in the past may be used. The at-home condition of the delivery destination in the past can be reliably obtained by the past delivery results and the like, and the at-home prediction of the delivery destination can be appropriately performed. Therefore, according to this configuration, it is possible to properly and reliably determine the delivery time. However, it is not necessary to necessarily use the information which shows the at-home condition of the past delivery destination as information which concerns on a delivery destination, and information other than the above may be used.

  In addition, as in the present embodiment, the visit time determination device 10 may include the model generation unit 11 that is configured to generate a model. Also, as described above, two models may be generated by adjusting the number of samples. According to this configuration, two appropriate models for determining the delivery time can be prepared, and the present invention can be implemented appropriately and reliably. However, generation of a model does not necessarily have to be performed in the visit time determination device 10, and a model generated by another device or the like may be stored in the model storage unit 12 in advance. In addition, a model may be generated by methods other than those described above.

  In the present embodiment, the delivery time is determined as the visit time to be determined. However, the visit time determined in the present invention does not necessarily have to be the delivery time. That is, the present invention does not necessarily assume delivery of a package, but may assume any situation as long as it determines visit times for a plurality of visit destinations. Moreover, although the model of this embodiment calculates a score, you may classify home or absence.

  Note that the block diagram used in the description of the above embodiment shows blocks in units of functions. These functional blocks (components) are realized by any combination of hardware and / or software. Moreover, the implementation means of each functional block is not particularly limited. That is, each functional block may be realized by one physically and / or logically coupled device, or directly and / or indirectly two or more physically and / or logically separated devices. It may be connected by (for example, wired and / or wireless) and realized by the plurality of devices.

  For example, the visit time determination device 10 according to the embodiment of the present invention may function as a computer that performs the processing of the visit time determination device 10 according to the present embodiment. FIG. 4 is a diagram showing an example of a hardware configuration of the visit time determination device 10 according to the present embodiment. The above-described visit time determination device 10 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007 and the like.

  In the following description, the term "device" can be read as a circuit, a device, a unit, or the like. The hardware configuration of the visit time determination device 10 may be configured to include one or more of the devices shown in the figure, or may be configured without some devices.

  Each function in the visit time determination device 10 performs a calculation by causing the processor 1001 to read a predetermined software (program) on hardware such as the processor 1001 and the memory 1002, and performs communication by the communication device 1004, the memory 1002, and This is realized by controlling reading and / or writing of data in the storage 1003.

  The processor 1001 operates, for example, an operating system to control the entire computer. The processor 1001 may be configured by a central processing unit (CPU: Central Processing Unit) including an interface with a peripheral device, a control device, an arithmetic device, a register, and the like. For example, each function of the visit time determination device 10 may be realized by the processor 1001.

  Also, the processor 1001 reads a program (program code), a software module or data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processing according to these. As a program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, each function of the visit time determination device 10 may be realized by a control program stored in the memory 1002 and operated by the processor 1001. The various processes described above have been described to be executed by one processor 1001, but may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The program may be transmitted from the network via a telecommunication line.

  The memory 1002 is a computer readable recording medium, and includes, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). It may be done. The memory 1002 may be called a register, a cache, a main memory (main storage device) or the like. The memory 1002 can store a program (program code), a software module, etc. that can be executed to implement the method according to one embodiment of the present invention.

  The storage 1003 is a computer readable recording medium, and for example, an optical disc such as a CD-ROM (Compact Disc ROM), a hard disc drive, a flexible disc, a magneto-optical disc (for example, a compact disc, a digital versatile disc, Blu-ray A (registered trademark) disk, a smart card, a flash memory (for example, a card, a stick, a key drive), a floppy (registered trademark) disk, a magnetic strip, and the like may be used. The storage 1003 may be called an auxiliary storage device. The above-mentioned storage medium may be, for example, a database including the memory 1002 and / or the storage 1003, a server or any other suitable medium.

  The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also called, for example, a network device, a network controller, a network card, a communication module, or the like. For example, each function of the above-described visit time determination device 10 may be realized by the communication device 1004.

  The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, and the like) that receives an input from the outside. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs output to the outside. The input device 1005 and the output device 1006 may be integrated (for example, a touch panel).

  In addition, devices such as the processor 1001 and the memory 1002 are connected by a bus 1007 for communicating information. The bus 1007 may be configured by a single bus or may be configured by different buses among the devices.

  In addition, the visit time determination device 10 includes hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA). It may be configured to include, and part or all of each functional block may be realized by the hardware. For example, processor 1001 may be implemented in at least one of these hardware.

  As mentioned above, although this embodiment was described in detail, it is clear for persons skilled in the art that this embodiment is not limited to the embodiment described in this specification. This embodiment can be implemented as a modification and a change mode, without deviating from the meaning and range of the present invention which become settled by statement of a claim. Therefore, the description of the present specification is for the purpose of illustration and does not have any limitation on the present embodiment.

  The notification of information is not limited to the aspects / embodiments described herein, and may be performed in other manners. For example, notification of information may be physical layer signaling (for example, Downlink Control Information (DCI), Uplink Control Information (UCI)), upper layer signaling (for example, Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, It may be implemented by broadcast information (MIB (Master Information Block), SIB (System Information Block)), other signals, or a combination thereof. Moreover, RRC signaling may be called an RRC message, and may be, for example, an RRC connection setup (RRC Connection Setup) message, an RRC connection reconfiguration (RRC Connection Reconfiguration) message, or the like.

  As long as there is no contradiction, the processing procedure, sequence, flow chart, etc. of each aspect / embodiment described in this specification may be reversed. For example, for the methods described herein, elements of the various steps are presented in an exemplary order and are not limited to the particular order presented.

  The input / output information or the like may be stored in a specific place (for example, a memory) or may be managed by a management table. Information to be input or output may be overwritten, updated or added. The output information etc. may be deleted. The input information or the like may be transmitted to another device.

  The determination may be performed by a value (0 or 1) represented by one bit, may be performed by a boolean value (Boolean: true or false), or may be compared with a numerical value (for example, a predetermined value). Comparison with the value).

  Each aspect / embodiment described in this specification may be used alone, may be used in combination, and may be switched and used along with execution. In addition, notification of predetermined information (for example, notification of "it is X") is not limited to what is explicitly performed, but is performed by implicit (for example, not notifying of the predetermined information) It is also good.

  Software may be called software, firmware, middleware, microcode, hardware description language, or any other name, and may be instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules. Should be interpreted broadly to mean applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, etc.

  Also, software, instructions, etc. may be sent and received via a transmission medium. For example, software may use a wireline technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or a website, server or other using wireless technology such as infrared, radio and microwave When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

  The information, signals, etc. described herein may be represented using any of a variety of different techniques. For example, data, instructions, commands, information, signals, bits, symbols, chips etc that may be mentioned throughout the above description may be voltage, current, electromagnetic waves, magnetic fields or particles, optical fields or photons, or any of these May be represented by a combination of

  The terms described in the present specification and / or the terms necessary for the understanding of the present specification may be replaced with terms having the same or similar meanings. For example, the channels and / or symbols may be signals. Also, the signal may be a message. Also, the component carrier (CC) may be called a carrier frequency, a cell or the like.

  The terms "system" and "network" as used herein are used interchangeably.

  In addition, the information, parameters, and the like described in the present specification may be represented by absolute values, may be represented by relative values from predetermined values, or may be represented by corresponding other information. . For example, radio resources may be indexed.

  The names used for the parameters described above are in no way limiting. In addition, the formulas etc. that use these parameters may differ from those explicitly disclosed herein. Since various channels (eg PUCCH, PDCCH etc.) and information elements (eg TPC etc.) can be identified by any suitable names, the various names assigned to these various channels and information elements can be Is not limited.

  The terms "determining", "determining" as used herein may encompass a wide variety of operations. "Judgment", "decision" are, for example, judging, calculating, calculating, processing, processing, deriving, investigating, looking up (for example, a table) (Searching in a database or another data structure), ascertaining may be regarded as “decision”, “decision”, etc. Also, "determination" and "determination" are receiving (e.g. receiving information), transmitting (e.g. transmitting information), input (input), output (output), access (accessing) (for example, accessing data in a memory) may be regarded as “judged” or “decided”. Also, "judgement" and "decision" are to be considered as "judgement" and "decision" that they have resolved (resolving), selecting (selecting), choosing (choosing), establishing (establishing), etc. May be included. That is, "judgment" "decision" may include considering that some action is "judged" "decision".

  The terms "connected", "coupled" or any variants thereof mean any direct or indirect connection or coupling between two or more elements, It can include the presence of one or more intermediate elements between two elements that are “connected” or “coupled”. The coupling or connection between elements may be physical, logical or a combination thereof. As used herein, the two elements are by using one or more wires, cables and / or printed electrical connections, and radio frequency as some non-limiting and non-exclusive examples. It can be considered "connected" or "coupled" to one another by using electromagnetic energy such as electromagnetic energy having wavelengths in the region, microwave region and light (both visible and invisible) regions.

  As used herein, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

  Where the designations "first", "second" etc. are used herein, any reference to such elements does not generally limit the quantity or order of those elements. These designations may be used herein as a convenient way of distinguishing between two or more elements. Thus, reference to the first and second elements does not mean that only two elements can be taken there, or that in any way the first element must precede the second element.

  As long as "includes", "including", and variations thereof are used in the present specification or claims, these terms as well as the term "comprising" Is intended to be comprehensive. Further, it is intended that the term "or" as used in the present specification or in the claims is not an exclusive OR.

  In the present specification, a plurality of devices are also included unless it is a device clearly having only one context or technically. Throughout this disclosure, unless the context clearly indicates otherwise, it is intended to include the plural.

  DESCRIPTION OF SYMBOLS 10 ... Visit time determination apparatus, 11 ... Model generation part, 12 ... Model storage part, 13 ... Acquisition part, 14 ... Visit time determination part, 15 ... Output part, 1001 ... Processor, 1002 ... Memory, 1003 ... Storage, 1004 ... Communication device, 1005 ... input device, 1006 ... output device, 1007 ... bus.

Claims (4)

A visit time determination device that determines visit times for a plurality of visit destinations,
It is two models which input the information concerning the visit destination and predict the visit at home according to the time, and among the two models, the accuracy rate priority model with the high accuracy rate of prediction and the recall rate of the prediction are high A model storage unit that stores a recall-oriented model;
An acquisition unit configured to acquire information related to the visit destination used for the home prediction of the visit destination for each of the plurality of visit destinations;
With regard to at least one of the plurality of visit destinations, prediction is performed by the relevance ratio-oriented model stored by the model storage unit using the information acquired by the acquisition unit, and at least one of the plurality of visit destinations The information acquired by the acquisition unit is used to make predictions based on the recall ratio-oriented model stored by the model storage unit, and the plurality of visit destinations are determined from the conditions of the visit set in advance and the results of the prediction. A visit time determination unit that determines a visit time for each of them;
An output unit that outputs information indicating visit times for each of the plurality of visit destinations determined by the visit time determination unit;
A visit time determination device comprising:   The visit time determination unit performs prediction with a relevance ratio-oriented model for each of the plurality of visit destinations, and determines whether the visit time can be determined from the condition of the visit and the result of the prediction, and the visit time is The visit according to claim 1, wherein for each visit determined to be undecidable, prediction based on a recall ratio model is performed, and the visit time is determined for each visit from the condition of the visit and the result of the prediction. Time determination device.   The visit time determination device according to claim 1, wherein the acquisition unit acquires information indicating a home condition of a past visit destination as the information related to the visit destination.   Acquiring a plurality of samples including information relating to a visit destination which is learning data for generating the relevance ratio-oriented model and the recall ratio-oriented model, and information indicating whether the user is at home according to the time of the visit destination; The visit time determination according to any one of claims 1 to 3, further comprising: a model generation unit configured to adjust the number of samples according to a model to be generated to generate the relevance ratio-oriented model and the recall ratio-oriented model. apparatus.

Images