WO2015140860A1 - 施策推薦装置、施策推薦方法および施策推薦プログラム - Google Patents
施策推薦装置、施策推薦方法および施策推薦プログラム Download PDFInfo
- Publication number
- WO2015140860A1 WO2015140860A1 PCT/JP2014/006265 JP2014006265W WO2015140860A1 WO 2015140860 A1 WO2015140860 A1 WO 2015140860A1 JP 2014006265 W JP2014006265 W JP 2014006265W WO 2015140860 A1 WO2015140860 A1 WO 2015140860A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- measure
- combination
- success
- recommendation
- unit
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24575—Query processing with adaptation to user needs using context
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2457—Query processing with adaptation to user needs
- G06F16/24578—Query processing with adaptation to user needs using ranking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/101—Collaborative creation, e.g. joint development of products or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B23/00—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes
- G09B23/28—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes for medicine
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/70—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to mental therapies, e.g. psychological therapy or autogenous training
Definitions
- the present invention relates to a measure recommendation device, a measure recommendation method, and a measure recommendation program for recommending an appropriate measure to a person who fails to implement the measure.
- CBT cognitive behavioral therapy
- CBT-I cognitive behavioral therapy
- a task is given every day for one month, and the client corrects the behavior by continuously performing the given task. Therefore, in cognitive behavioral therapy, issues and measures recommended to clients are important factors.
- Non-Patent Document 1 As a general method for recommending information to the user, recommendation by collaborative filtering is described in Non-Patent Document 1. How to recommend a product that a person wants to a potential customer is an important factor for advertisers. Therefore, in the recommendation by collaborative filtering, the user's preference pattern is learned based on the Internet user's site browsing history, click history, and the like, and a product that the user is likely to like is recommended.
- Non-Patent Document 1 Recommendation by collaborative filtering described in Non-Patent Document 1 is a method that focuses on starting a new use or purchasing a new product. That is, the technique described in Non-Patent Document 1 recommends similar products to other users based on favorable facts obtained in the past.
- an object of the present invention is to provide a measure recommendation device, a measure recommendation method, and a measure recommendation program that can appropriately recommend the next best measure to a person who has not successfully implemented a measure.
- the measure recommendation device is based on the duration of the measure implemented by each user and the threshold or range of the duration used for determining whether each measure is successful or not.
- a measure result determination unit that determines a failure
- a combination generation unit that generates, for each user, a combination including a failure measure that is determined as a failure and a successful measure that is determined as a success based on the determination result;
- a measure that is recognized as failed is input, a combination of the generated measures that matches the failed measure is extracted from the generated combinations, and a measure recommendation that recommends a successful measure included in the extracted combination And a section.
- the measure recommendation method is a measure recommendation device in which the measure recommendation device determines whether the measure by each user is based on the duration of the measure implemented by each user and the threshold value or range of the duration used to determine the success or failure of each measure. The success or failure of the implementation is judged, and the measure recommendation device generates, for each user, a combination including the failure measure that is determined to be a failure and the success measure that is determined to be a success based on the determination result.
- a measure recognized as a failure is input by the measure recommendation device, a combination in which the input measure matches the failed measure is extracted from the generated combination, and the success included in the extracted combination It is characterized by recommending measures.
- the measure recommendation program allows a computer to execute the measure by each user based on the duration of the measure implemented by each user and the threshold value or range of the duration used for determining the success or failure of each measure.
- a process and a measure recognized as failed are input, a combination in which the input measure matches the failure measure is extracted from the generated combination, and a successful measure included in the extracted combination is recommended. It is characterized in that a measure recommendation process is executed.
- FIG. FIG. 1 is a block diagram showing a configuration example of a first embodiment of a measure recommendation device according to the present invention.
- the measure recommendation device 10 of this embodiment includes a measure result determination unit 11, a combination generation unit 12, a measure input unit 13, a measure recommendation unit 14, a determination condition storage unit 15, and a measure candidate storage unit 16. ing.
- the measure recommendation device 10 may include a measure history storage unit 20 described later.
- the measure recommendation device may be used by a user himself / herself for recommending a new measure to the user. Further, it is determined whether or not the measure taken by the user is a failure, and a person who recommends the next best measure to the user is described as an administrator.
- the measure recommendation device may be used by an administrator who determines success or failure of implementation of a measure by a user, and the administrator may recommend a second best measure to the user.
- the measure history storage unit 20 stores information for the measure result determination unit 11 to make a determination. Specifically, the measure history storage unit 20 stores the duration of the measure implemented by each user. In the following description, information indicating the duration of a measure implemented by each user may be referred to as an implementation history.
- FIG. 2 is an explanatory diagram illustrating an example of information stored in the measure history storage unit 20.
- the measure history storage unit 20 includes, for each user ID that identifies each user, a support measure ID that identifies the measure that the user has implemented, and a duration that indicates the period during which the measure has been implemented.
- the number of days is set for the duration, but the information indicating the duration is not limited to the number of days, and may be the number of months, years, hours, or the like.
- the measure history storage unit 20 may store not only the duration but also other information in association with each measure implemented by the user.
- FIG. 3 is an explanatory diagram showing examples of measures.
- the support measure ID and the measure contents are managed in association with each other.
- a measure identified by the support measure ID may be associated with a plurality of sub measures for realizing the measure.
- the support measure ID “003”
- the three sub-measures are associated with the measures identified by.
- the measure recommendation device 10 may confirm the presence or absence of the sub measure when the support measure ID is designated.
- the measure result determination unit 11 determines the success or failure of the implementation of the measure by each user based on the duration of the measure implemented by each user. At that time, the measure result determination unit 11 determines the success or failure of the implementation of the measure by each user based on the duration condition used for determining the success or failure of each measure.
- the duration condition is stored in the determination condition storage unit 15.
- the duration condition may be set for each measure, or may be set for the entire process. When the duration condition is set for each measure, it becomes possible to make a finer determination. In addition, when one continuation period condition is set for the entire process, the number of items set by the user or the administrator can be suppressed, so that it is possible to reduce the labor related to setting.
- FIG. 4 is an explanatory diagram illustrating an example of determination conditions stored in the determination condition storage unit 15.
- the determination condition storage unit 15 stores, for each measure, a threshold value of a continuation period that is determined to be successful in each measure as a condition for the continuation period.
- the measure result determination unit 11 determines that the measure has been successfully implemented when the duration of each measure executed by each user is equal to or greater than the set threshold value.
- the determination condition storage unit 15 is realized by, for example, a memory.
- the conditions used by the measure result determination unit 11 for determination are not limited to the threshold value for the duration.
- the measure result determination unit 11 may use, for example, a range of a continuous period determined as success as a condition.
- FIG. 5 is an explanatory diagram showing the result of determining the execution history illustrated in FIG. 2 using the conditions illustrated in FIG.
- the user identified by the user ID “A” continuously implemented the measure identified by the support measure ID “001” for 10 days.
- the threshold of the duration for determining that the implementation of the measure identified by the support measure ID “001” is successful is 25 days. Therefore, the measure identified by the support measure ID “001” implemented by this user is determined to have failed.
- the duration condition may be determined in advance by an administrator or the like based on past experience or the like, or may be calculated by the measure result determination unit 11.
- the measure result determination unit 11 may use, for example, the execution history illustrated in FIG. 2 to calculate the median value of the duration in which each measure is implemented, and set the median as the threshold value of the duration.
- the measure result determination unit 11 may calculate an average of durations in which each measure is implemented, and may use the average value as a threshold value of the duration.
- the median value is more preferably used as the threshold value of the duration because it is easily affected by biased data.
- the combination generation unit 12 generates, for each user, a combination including the measure determined to be unsuccessful and the measure determined to be successful based on the determination result by the measure result determination unit 11.
- a measure determined as failure may be referred to as a failure measure
- a measure determined as successful may be referred to as a success measure.
- This combination may include not only information for identifying a success measure and a failure measure, but also information associated with the success measure and information associated with the failure measure.
- FIG. 6 is an explanatory diagram showing an example of processing for generating a combination of a failure measure and a success measure.
- the combination generation unit 12 generates a combination based on the determination result illustrated in FIG. For example, focusing on the user identified by the user ID “A”, the failure measure is a measure identified by the support measure IDs “001” and “003”, and the success measure is identified by the support measure ID “002”. Measure.
- the combination generation unit 12 includes the combination of the measure identified by the support measure ID “001” and the measure identified by the support measure ID “002”, and the support measure. A combination of the measure identified by the ID “003” and the measure identified by the support measure ID “002” is generated. The same applies to other users.
- the combination generation unit 12 may generate a combination of overlapping failure measures and success measures.
- the same combination (first and second lines) is obtained from the user implementation history identified by the user ID “A” and the user implementation history identified by the user ID “C”. Has been generated.
- generation part 12 may leave one combination and delete the other overlapping combination, when the combination of the failure measure and the success measure which overlap is produced
- the measure candidate storage unit 16 stores a combination including the failure measure and the success measure generated by the combination generation unit 12.
- the measure candidate storage unit 16 is realized by, for example, a magnetic disk.
- the measure input unit 13 inputs a measure recognized as a failure by the administrator.
- the measure input unit 13 is realized by an input device such as a keyboard or a touch panel that receives input from a user or an administrator.
- the measure input unit 13 may be realized by a network interface that receives the input.
- the measure recommendation unit 14 extracts a combination in which the input measure matches the failed measure from the combinations generated by the combination generation unit 12 when the measure recognized as failed is input. And the measure recommendation part 14 extracts the success measure contained in the extracted combination, and outputs it as a recommendation result.
- the measure recommendation unit 14 may output the specified success measure as a recommendation result.
- the measure recommendation unit 14 may output all of the plurality of successful measures as recommendation results, and one successful measure based on a predetermined rule. You may output as a recommendation result.
- FIG. 7 is an explanatory diagram showing an example of a process for recommending a measure.
- Mr. A who fails to implement the measure identified by the support measure ID “001” inputs “001” identifying the failed measure via the measure input unit 13
- the measure recommendation unit 14 The combination with the support measure ID “001” is extracted, and the support measure IDs “002” and “003” of the success measures included in the combination are extracted. Then, the measure recommendation unit 14 recommends all the extracted measures to Mr. A. In the example shown in FIG. 7, a plurality of measures are searched, but the recommendation order is arbitrary.
- the measure result determination unit 11, the combination generation unit 12, and the measure recommendation unit 14 are realized by a CPU of a computer that operates according to a program (measure recommendation program).
- the program is stored in a storage unit (not shown) of the measure recommendation device 10, and the CPU reads the program and operates as the measure result determination unit 11, the combination generation unit 12, and the measure recommendation unit 14 according to the program. May be.
- each of the measure result determination unit 11, the combination generation unit 12, and the measure recommendation unit 14 may be realized by dedicated hardware.
- FIG. 8 is a flowchart showing an operation example of the measure recommendation device 10 of the present embodiment.
- the measure result determination unit 11 refers to the measure history stored in the measure history storage unit 20, and determines the success or failure of the implementation of the measure by each user (step S11).
- the combination generation unit 12 generates, for each user, a combination including the measure determined to be unsuccessful and the measure determined to be successful based on the determination result by the measure result determination unit 11 (step S12).
- generation part 12 memorize
- the measure recommendation unit 14 matches the input measure with the failed measure from among the combinations generated by the combination generation unit 12. A combination is extracted (step S14). And the measure recommendation part 14 extracts the success measure contained in the extracted combination, and outputs it as a recommendation result (step S15).
- the measure result determination unit 11 determines the duration of a measure implemented by each user and the threshold value or range of the duration used for determining whether each measure is successful. The success or failure of the implementation of the measure by each user is determined, and the combination generation unit 12 generates a combination including the failure measure and the successful measure for each user. Then, when a measure recognized as failed through the measure input unit 13 is input, the measure recommendation unit 14 extracts a combination in which the input measure matches the failed measure from the generated combinations, Recommend success measures included in the extracted combinations.
- Embodiment 2 a second embodiment of the measure recommendation device according to the present invention will be described.
- the measure recommendation unit 14 recommends all the successful measures corresponding to the failure measure from the combinations generated by the combination generation unit 12.
- a method for recommending a successful measure will be described based on total information obtained by further counting the combinations generated by the combination generation unit 12 so that a more suitable successful measure can be recommended.
- FIG. 9 is a block diagram showing a configuration example of the second embodiment of the measure recommendation device according to the present invention.
- the measure recommendation device 10a includes a measure result determination unit 11, a combination generation unit 12, a measure input unit 13, a measure recommendation unit 14, a determination condition storage unit 15, a measure candidate storage unit 16, and a combination. And a counting unit 17.
- the measure recommendation device of this embodiment is different from that of the first embodiment in that it further includes a combination tabulation unit 17.
- the combination generation unit 12 may perform the process of the combination totaling unit 17.
- the combination tabulation unit 17 generates tabulation information obtained by tabulating the combinations generated by the combination generation unit 12.
- the combination totalization unit 17 is realized by a CPU of a computer that operates according to a program (measure recommendation program).
- the measure recommendation unit 14 extracts total information in which the input measure matches the failure measure, and recommends a success measure using the extracted total information.
- the measure recommendation unit 14 may output at least one or more pieces of aggregate information together with the recommended success measure.
- the measure recommendation unit 14 may specify total information that is determined to be recommended more preferentially, and may select and recommend a successful measure corresponding to the specified total information. At this time, the measure recommendation unit 14 may use only one specific information or a plurality of total information. Further, the measure recommendation unit 14 may output the total information together with the recommended success measure.
- FIG. 10 is an explanatory diagram illustrating a first example of the process of counting the combinations.
- the combination tabulation unit 17 generates tabulation information by counting the number of users who have implemented the measure history from which the combination is generated.
- the measure recommendation unit 14 may output the number of users as total information together with the recommended success measure.
- the measure recommendation unit 14 may recommend success measures with a larger number of people in order from the extracted total information, or may recommend a success measure with the largest number of people.
- the measure recommendation unit 14 identifies the measure identified by the support measure ID “003”, the measure identified by the support measure ID “002”, and the support measure ID “005” in descending order of the number of people. Successive measures may be recommended in the order of measures taken. By performing such processing, the user and the manager can select a measure with many people who have succeeded in the past.
- FIG. 11 is an explanatory diagram showing a second example of the process of counting the combinations.
- the combination tabulation unit 17 sets priorities in descending order of the duration of success measures included in the combination (that is, sorts). When the combination of the failure measure and the success measure overlaps, the combination counting unit 17 may leave only the combination having a longer duration.
- the measure recommendation unit 14 may output the duration as aggregate information together with the recommended success measure. Further, in this case, it can be determined that the success measure corresponding to the total information having a longer duration should be recommended with higher priority. Therefore, the measure recommendation unit 14 may recommend a success measure with a longer duration in order from the extracted total information, or may recommend a success measure with the longest duration. By performing such processing, the user or the manager can select a measure with a high duration from past success examples.
- FIG. 12 is an explanatory diagram showing a third example of the process of counting the combinations.
- the combination tabulation unit 17 determines a period to be applied as a duration of the success measure included in the combination for the same combination of the failure measure and the success measure.
- the combination tabulation unit 17 may use an average value, a median value, a total value, or the like of durations as an applied period. In the example shown in FIG. 12, the average value of the duration is calculated as the duration applied as the duration.
- the measure recommendation unit 14 may output a period to be applied as aggregate information together with the recommended success measure. Further, in this case, it can be determined that the success measure corresponding to the aggregate information having a longer period to be applied should be recommended more preferentially. Therefore, the measure recommendation unit 14 may recommend a success measure with a longer applied period in order from the extracted total information, or may recommend a successful measure with the longest applied period. By performing such processing, the user and the manager can select a measure having high statistical continuity.
- generates is not limited to the total information mentioned above.
- the combination tabulation unit 17 may generate a plurality of types of tabulation information.
- the measure recommendation unit 14 may recommend a success measure by combining a plurality of types of aggregate information.
- a priority for applying the aggregate information may be determined in advance, and the measure recommendation unit 14 may recommend a successful measure according to the priority order.
- FIG. 13 is a flowchart showing an operation example of the measure recommendation device 10a of the present embodiment.
- the process in which the measure result determination unit 11 determines the success or failure of the implementation of the measure by each user and the combination generation unit 12 generates a combination of the fail measure and the successful measure for each user is illustrated in FIG. It is the same as the process of S11 and step S12.
- the combination tabulation unit 17 generates tabulation information obtained by tabulating the combinations generated by the combination generation unit 12 (step S21). Then, the combination tabulation unit 17 stores the generated tabulation information in the measure candidate storage unit 16 (step S22).
- the measure recommendation unit 14 matches the input measure with the failed measure from the total information generated by the combination totaling unit 17. Total information to be extracted is extracted (step S23). Then, the measure recommendation unit 14 extracts a success measure included in the extracted total information, and recommends a success measure using the extracted total information (step S24).
- the combination tabulation unit 17 generates tabulation information in which the combinations generated by the combination generation unit 12 are tabulated, and the measure recommendation unit 14 matches the input measure with the failed measure. Aggregate information is extracted and successful measures are recommended using the extracted aggregate information. At this time, the measure recommendation unit 14 outputs aggregate information or preferentially recommends a success measure.
- the combination totaling unit 17 generates the total information by counting the number of users who have implemented the policy history from which the combination is generated, and the policy recommendation unit 14 determines whether the input policy is A successful measure with a larger number of people may be recommended from the total information that matches the failed measure.
- combination tabulation unit 17 tabulates the durations of successful measures included in the combination in descending order, and the measure recommendation unit 14 determines the duration from the tabulation information in which the input measure matches the failure measure. Longer success measures may be recommended.
- the combination totaling unit 17 determines a period to be applied as the duration of the success measure included in the combination for the same combination of the failure measure and the success measure, and the measure recommendation unit 14 is input.
- a successful measure with a longer period of application may be recommended from the aggregated information that matches the failed measure.
- the measure recommendation unit 14 recommends all the successful measures corresponding to the failure measure from the combinations generated by the combination generation unit 12.
- information hereinafter referred to as priority
- the measure recommendation unit 14 recommends a success measure using the specified priority information.
- the measure recommendation unit 14 recommends a successful measure using a category into which each measure is classified.
- a method for recommending a successful measure based on a category into which each measure is classified so that a more suitable successful measure can be recommended will be described.
- FIG. 14 is a block diagram showing a configuration example of the third embodiment of the measure recommendation device according to the present invention.
- the measure recommendation device 10b of this embodiment includes a measure result determination unit 11, a combination generation unit 12, a measure input unit 13, a measure recommendation unit 14, a determination condition storage unit 15, a measure candidate storage unit 16, and a category. And an information storage unit 18.
- the measure recommendation device of this embodiment is different from that of the first embodiment in that it further includes a category information storage unit 18.
- the measure recommendation device 10b according to the present embodiment may include the combination tabulation unit 17 according to the second embodiment.
- the category information storage unit 18 stores a category into which each measure is classified.
- FIG. 15 is an explanatory diagram illustrating an example of categories stored in the category information storage unit 18.
- the measures identified by the support measure ID “001” and the support measure ID “003” are based on exogenous motivation, and the support measure ID “002” and the support measure ID “ The measure identified by “004” indicates that it is based on intrinsic motivation.
- the category used for the classification of measures is not limited to the above category.
- Other examples of categories include measures for specific persons and measures for unspecified majority, measures for qualitative evaluation and measures for quantitative evaluation.
- the category information storage unit 18 stores the priority of the category of successful measures defined for the category of failed measures.
- the priority of the intrinsic category may be set higher than the exogenous category.
- the priority of the external category may be set higher than the intrinsic category.
- this priority is an example.
- the relationship between a measure for a specific person and a measure for an unspecified majority, a measure for which qualitative evaluation is performed, and a measure for which quantitative evaluation is performed This relationship may also be defined in the same manner as the priority described above.
- the measure recommendation unit 14 recommends a successful measure according to the priority of the category stored in the category information storage unit 18 among the successful measures included in the extracted combination.
- the measure recommendation unit 14 specifies the priority of the category of the successful measure defined for the category of the failed measure as the priority information for each extracted combination, and uses the specified priority information to determine the success measure. Recommendation to.
- the measure recommendation unit 14 may output priority information together with the recommended success measure.
- the number and type of information to be output is arbitrary.
- the measure recommendation unit 14 may select and recommend a success measure that should be recommended with higher priority.
- the measure recommendation unit 14 may recommend a success measure using only one priority information, or may recommend a success measure using a plurality of priority information.
- FIG. 16 is an explanatory diagram showing an example in which categories are added to combinations of success measures and failure measures, respectively.
- the measure recommendation unit 14 may specify the combination illustrated in FIG. 16 using the combination generated by the combination generation unit 12 and the category information stored in the category information storage unit 18. Further, the combination generation unit 12 may generate a combination illustrated in FIG. 16 with reference to the category information storage unit 18.
- FIG. 17 is an explanatory diagram showing another example of recommending a measure. For example, when Mr. A who fails to implement the measure identified by the support measure ID “001” inputs “001” identifying the failed measure via the measure input unit 13, the measure recommendation unit 14 The combination with the support measure ID “001” is extracted, and the support measure IDs “002” and “003” of the success measures included in the combination are extracted.
- the measure recommendation unit 14 may recommend a measure identified by the support measure ID “002”, which is a measure classified into the “intrinsic” category, to Mr. A.
- the measure recommendation unit 14 specifies the priority information of the extracted combination based on the priority of the category of the successful measure defined for the category of the failed measure. Specifically, the measure recommendation unit 14 recommends a success measure of a category having a higher priority defined for the category of the fail measure among the success measures included in the extracted combination. This is because a measure classified into the same category as a failed measure is highly likely to fail even if it is recommended again. According to the present embodiment, since the priority of the category defined based on the causal relationship between the measures is used at the time of recommendation, in addition to the effect of the first embodiment, more to the user and the administrator Can recommend appropriate success measures.
- Embodiment 4 a fourth embodiment of the measure recommendation device according to the present invention will be described.
- the measure recommendation unit 14 recommends all the successful measures corresponding to the failure measure from the combinations generated by the combination generation unit 12.
- a method for recommending a success measure will be described in consideration of the attributes of the user who executed the measure history from which the combination was generated so that a more suitable success measure can be recommended.
- the measure recommendation unit 14 performs processing for specifying priority information for each extracted combination, and recommends a successful measure using the specified priority information.
- FIG. 18 is a block diagram showing a configuration example of the fourth embodiment of the measure recommendation device according to the present invention.
- the measure recommendation device 10c of this embodiment includes a measure result determination unit 11, a combination generation unit 12, a measure input unit 13, a measure recommendation unit 14, a determination condition storage unit 15, a measure candidate storage unit 16, and an attribute And an information storage unit 19.
- the measure recommendation device of the present embodiment is different from the first embodiment in that it further includes an attribute information storage unit 19.
- the measure recommendation device 10c of this embodiment may include the combination tabulation unit 17 of the second embodiment, or may include the category information storage unit 18 of the third embodiment.
- the attribute information storage unit 19 stores attribute information of each user.
- the attribute information in the present embodiment includes not only the user's own properties and characteristics but also the environment surrounding the user. Examples of attribute information include gender, age, household composition, smoking status, hospitalization history, exercise history, eating behavior, eating and dislikes, past failure measures and their duration, past success measures and their duration, etc. .
- the combination generation unit 12 generates, for each combination of the failure measure and the success measure, a combination in which attribute information of the user who has implemented the measure history from which the combination is generated is added. Specifically, when the combination generation unit 12 generates a combination of a failure measure and a success measure for each user, the combination generation unit 12 refers to the attribute information storage unit 19 to acquire the attribute information of the corresponding user, Add attribute information. The combination generation unit 12 stores the generated combination in the measure candidate storage unit 16.
- FIG. 19 is an explanatory diagram showing an example of a combination to which attribute information is added.
- the example shown in FIG. 19 indicates that attribute information including the gender of the user is added to each combination.
- the measure recommendation unit 14 is specified by the input identification information among the combinations in which the input measure matches the failed measure when the measure recognized as failed and the identification information of the user to be recommended are input.
- the similarity of user attribute information is specified as priority information for each extracted combination. Then, the measure recommendation unit 14 recommends a successful measure using the specified priority information.
- the measure recommendation unit 14 recommends, for example, successful measures included in a combination having a higher degree of similarity with user attribute information specified by the input identification information.
- the measure recommendation unit 14 refers to the attribute information storage unit 19, Get the attribute information of the user.
- attribute information may be input together with the identification information of the user via the measure input unit 13. In that case, the measure recommendation unit 14 may use the input attribute information.
- the measure recommendation unit 14 of this embodiment may also output priority information together with the recommended success measure.
- the number and type of information to be output is arbitrary.
- the measure recommendation unit 14 may select and recommend a success measure that should be recommended with higher priority.
- the measure recommendation unit 14 may recommend a success measure using only one priority information, or may recommend a success measure using a plurality of priority information.
- the measure recommendation unit 14 may determine that the degree of similarity increases as the number of matching attributes increases between the user attribute information and the attribute information added to the generated combination. Further, the measure recommendation unit 14 may weight each attribute, and may determine that the similarity is higher as the total weight of the matching attributes is larger. Further, the measure recommendation unit 14 may determine that the similarity is higher as the duration of the failed measure is closer to the duration of the failed measure added to the generated combination.
- FIG. 20 is an explanatory diagram showing still another example of recommending a measure.
- Mr. A who fails to implement the measure identified by the support measure ID “001” inputs “001” identifying the failed measure via the measure input unit 13
- the measure recommendation unit 14 displays the attribute information.
- the attribute information of Mr. A is acquired with reference to the storage unit 19.
- the information of Mr. A includes information such as “male (male)”, “with wife and child (married, with children)”, and “successful examples continued due to measures (praises) praised in the past”. Has been acquired.
- the measure recommendation unit 14 recommends a success measure included in the combination having the highest similarity with the user attribute information among the combinations including the failure measure that matches the input support measure ID “001”.
- the similarity of the combination in the first row is 5, which is higher than the similarity of the other combinations. Therefore, the measure recommendation unit 14 may recommend a measure identified by the support measure ID “003” to Mr. A as a successful measure included in the combination determined to have the highest similarity.
- the combination generation unit 12 displays the attribute information of the user who has executed the measure history from which the combination was generated. Generate the added combination. Then, the measure recommendation unit 14 is based on the similarity with the attribute information of the user specified by the input identification information when the measure recognized as failed and the identification information of the user to be recommended are input. The priority information of the combination in which the inputted measure matches the failed measure is specified. Specifically, the measure recommendation unit 14 recommends a successful measure included in a combination having a higher degree of similarity with the attribute information of the user specified by the input identification information.
- a successful measure implemented by a user with a close attribute is highly likely to succeed even if implemented by other users.
- a more appropriate success measure can be recommended in addition to the effects of the first embodiment. Therefore, the user can select a past success measure of a person similar to the user.
- FIG. 21 is a block diagram showing an outline of a measure recommendation device according to the present invention.
- the measure recommendation device according to the present invention is based on the duration of measures implemented by each user and the threshold value or range of the duration used for determining the success or failure of each measure (for example, stored in the measure history storage unit 20).
- a measure result determination unit 81 (for example, measure result determination unit 11) that determines success or failure of the measure execution by each user, and a measure that is determined to be unsuccessful based on the determination result.
- a combination generation unit 82 (for example, combination generation unit 12) that generates a combination including a certain failure measure and a success measure that is determined to be successful for each user, and a measure that has been recognized as failed are input.
- a policy recommendation unit 83 that extracts a combination in which the input measure matches the failure measure from the generated combination and recommends a success measure included in the extracted combination (measure recommendation unit 14). It is equipped with a.
- the measure recommendation unit 83 specifies priority information (for example, category priority, similarity to attribute information) used for determining a successful measure to be preferentially recommended for each extracted combination. Successful measures may be recommended using the prioritized information.
- priority information for example, category priority, similarity to attribute information
- the measure recommendation unit 83 may specify the priority information of the extracted combination based on the priority of the category of the successful measure defined for the category of the failed measure. According to such a configuration, the priority of the category defined based on the causal relationship between measures is used at the time of recommendation, so that a more appropriate success measure can be recommended to the user and the administrator.
- the combination generation unit 82 may generate a combination in which attribute information of the user who has implemented the measure history from which the combination is generated is added to each combination of the failure measure and the success measure. Good. Then, the measure recommendation unit 83, based on the similarity with the attribute information of the user specified by the input identification information, when the measure recognized as failed and the identification information of the user to be recommended are input. , Combination priority information in which the input measure matches the failure measure may be specified. According to such a configuration, it is possible to preferentially recommend a success measure implemented in the past by a user with a close attribute, and therefore it is possible to recommend a more appropriate success measure.
- the measure recommendation unit 83 may output at least one or more priority information together with the success measure when recommending the success measure. Further, the measure recommendation unit 83 may select and recommend a success measure that should be recommended more preferentially based on one or more pieces of priority information.
- the measure recommendation device includes a combination totaling unit (for example, the combination totaling unit 17) that generates totaling information (for example, information totaling the number of people and the period) that totalizes the combinations generated by the combination generating unit 82. Also good. Then, the measure recommendation unit 83 may extract aggregate information in which the input measure matches the failure measure, and may recommend a success measure using the extracted aggregate information.
- a combination totaling unit for example, the combination totaling unit 17
- totaling information for example, information totaling the number of people and the period
- the measure recommendation unit 83 may output at least one or more pieces of aggregate information together with the success measure when recommending the success measure. Further, the measure recommendation unit 83 is a successful measure corresponding to total information (for example, a large total number of people, a long duration, etc.) that is determined to be recommended more preferentially based on one or more total information. You may select and recommend.
- the combination tabulation unit may generate tabulation information by counting the number of users who have implemented the measure history from which the combination is generated. Further, the combination tabulation unit may tabulate in order from the longest duration of the success measures included in the combination. In addition, the combination tabulation unit may determine a period to be applied as a duration of the success measure included in the combination for the same combination of the failure measure and the success measure.
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Mathematical Optimization (AREA)
- Developmental Disabilities (AREA)
- Computational Mathematics (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Algebra (AREA)
- Medicinal Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Child & Adolescent Psychology (AREA)
- Mathematical Analysis (AREA)
- Hospice & Palliative Care (AREA)
- Psychiatry (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
Abstract
Description
図1は、本発明による施策推薦装置の第1の実施形態の構成例を示すブロック図である。本実施形態の施策推薦装置10は、施策結果判定部11と、組合せ生成部12と、施策入力部13と、施策推薦部14と、判定条件記憶部15と、施策候補記憶部16とを備えている。なお、施策推薦装置10は、後述する施策履歴記憶部20を備えていてもよい。
次に、本発明による施策推薦装置の第2の実施形態を説明する。第1の実施形態では、施策推薦部14は、組合せ生成部12により生成された組合せから、失敗施策に対応する全ての成功施策を推薦していた。一方、本実施形態では、より適した成功施策を推薦できるように、組合せ生成部12により生成された組合せをさらに集計した集計情報をもとに、成功施策を推薦する方法を説明する。
次に、本発明による施策推薦装置の第3の実施形態を説明する。第1の実施形態では、施策推薦部14は、組合せ生成部12により生成された組合せから、失敗施策に対応する全ての成功施策を推薦していた。以下の実施形態(第3の実施形態、第4の実施形態)では、施策推薦部14が、抽出された組合せごとに、優先的に推薦すべき成功施策の判断に用いられる情報(以下、優先情報と記す。)を特定する処理を行う。このとき、施策推薦部14は、特定された優先情報を用いて成功施策を推薦する。
次に、本発明による施策推薦装置の第4の実施形態を説明する。第1の実施形態では、施策推薦部14は、組合せ生成部12により生成された組合せから、失敗施策に対応する全ての成功施策を推薦していた。一方、本実施形態では、より適した成功施策を推薦できるように、組合せが生成されるもとになった施策履歴を実施したユーザの属性を考慮して、成功施策を推薦する方法を説明する。本実施形態でも、施策推薦部14が、抽出された組合せごとに優先情報を特定する処理を行い、特定された優先情報を用いて成功施策を推薦する。
11 施策結果判定部
12 組合せ生成部
13 施策入力部
14 施策推薦部
15 判定条件記憶部
16 施策候補記憶部
17 組合せ集計部
18 カテゴリ情報記憶部
19 属性情報記憶部
20 施策履歴記憶部
Claims (16)
- 各ユーザにより実施された施策の継続期間と、各施策の成功可否の判定に用いられる継続期間の閾値または範囲に基づいて、各ユーザによる施策の実施の成功又は失敗を判定する施策結果判定部と、
前記判定結果に基づいて、失敗と判定された施策である失敗施策と成功と判定された施策である成功施策とを含む組合せをユーザごとに生成する組合せ生成部と、
失敗したと認識された施策が入力されたときに、生成された組合せから、入力された施策が前記失敗施策に一致する組合せを抽出し、抽出された組合せに含まれる前記成功施策を推薦する施策推薦部とを備えた
ことを特徴とする施策推薦装置。 - 施策推薦部は、優先的に推薦すべき成功施策の判断に用いられる優先情報を、抽出された組合せごとに特定し、特定された優先情報を用いて成功施策を推薦する
請求項1記載の施策推薦装置。 - 施策推薦部は、失敗施策のカテゴリに対して定義される成功施策のカテゴリの優先度に基づいて、抽出された組合せの優先情報を特定する
請求項2記載の施策推薦装置。 - 組合せ生成部は、失敗施策と成功施策との各組合せに対して、当該組合せが生成されるもとになった施策履歴を実施したユーザの属性情報を付加した組合せを生成し、
施策推薦部は、失敗したと認識された施策および推薦対象のユーザの識別情報が入力されたときに、入力された識別情報により特定されるユーザの属性情報との類似度に基づいて、入力された施策が前記失敗施策に一致する組合せの優先情報を特定する
請求項2または請求項3のうちのいずれか1項に記載の施策推薦装置。 - 施策推薦部は、成功施策を推薦する際、当該成功施策とともに少なくとも1つ以上の優先情報を出力する
請求項2から請求項4のうちのいずれか1項に記載の施策推薦装置。 - 施策推薦部は、1つ以上の優先情報に基づいて、より優先的に推薦すべき成功施策を選択して推薦する
請求項2から請求項5のうちのいずれか1項に記載の施策推薦装置。 - 組合せ生成部によって生成された組合せを集計した集計情報を生成する組合せ集計部を備え、
施策推薦部は、入力された施策が失敗施策に一致する集計情報を抽出し、抽出された集計情報を用いて成功施策を推薦する
請求項1から請求項6のうちのいずれか1項に記載の施策推薦装置。 - 施策推薦部は、成功施策を推薦する際、当該成功施策とともに少なくとも1つ以上の集計情報を出力する
請求項7記載の施策推薦装置。 - 施策推薦部は、1つ以上の集計情報に基づいて、より優先的に推薦すべきと判断される集計情報に対応する成功施策を選択して推薦する
請求項7または請求項8記載の施策推薦装置。 - 組合せ集計部は、組合せが生成されるもとになった施策履歴を実施したユーザの人数をカウントして集計情報を生成する
請求項7から請求項9のうちのいずれか1項に記載の施策推薦装置。 - 組合せ集計部は、組合せに含まれる成功施策の継続期間が長い順に集計する
請求項7から請求項10のうちのいずれか1項に記載の施策推薦装置。 - 組合せ集計部は、失敗施策と成功施策が同一の組合せを対象に、当該組合せに含まれる成功施策の継続期間として適用される期間を決定する
請求項7から請求項11のうちのいずれか1項に記載の施策推薦装置。 - 施策推薦装置が、各ユーザにより実施された施策の継続期間と、各施策の成功可否の判定に用いられる継続期間の閾値または範囲に基づいて、各ユーザによる施策の実施の成功又は失敗を判定し、
前記施策推薦装置が、前記判定結果に基づいて、失敗と判定された施策である失敗施策と成功と判定された施策である成功施策とを含む組合せをユーザごとに生成し、
前記施策推薦装置が、失敗したと認識された施策が入力されたときに、生成された組合せから、入力された施策が前記失敗施策に一致する組合せを抽出し、抽出された組合せに含まれる前記成功施策を推薦する
ことを特徴とする施策推薦方法。 - 優先的に推薦すべき成功施策の判断に用いられる優先情報を、抽出された組合せごとに特定し、
特定された優先情報を用いて成功施策を推薦する
請求項13記載の施策推薦方法。 - コンピュータに、
各ユーザにより実施された施策の継続期間と、各施策の成功可否の判定に用いられる継続期間の閾値または範囲に基づいて、各ユーザによる施策の実施の成功又は失敗を判定する施策結果判定処理、
前記判定結果に基づいて、失敗と判定された施策である失敗施策と成功と判定された施策である成功施策とを含む組合せをユーザごとに生成する組合せ生成処理、および、
失敗したと認識された施策が入力されたときに、生成された組合せから、入力された施策が前記失敗施策に一致する組合せを抽出し、抽出された組合せに含まれる前記成功施策を推薦する施策推薦処理を実行させる
ための施策推薦プログラム。 - 施策推薦処理で、優先的に推薦すべき成功施策の判断に用いられる優先情報を、抽出された組合せごとに特定させ、特定させた優先情報を用いて成功施策を推薦させる
請求項15記載の施策推薦プログラム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016508321A JP6172781B2 (ja) | 2014-03-19 | 2014-12-16 | 施策推薦装置、施策推薦方法および施策推薦プログラム |
US15/122,286 US20160372000A1 (en) | 2014-03-19 | 2014-12-16 | Scheme recommendation device, scheme recommendation method, and scheme recommendation program |
EP14886648.6A EP3121785A4 (en) | 2014-03-19 | 2014-12-16 | Scheme recommendation device, scheme recommendation method, and scheme recommendation program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2014-055840 | 2014-03-19 | ||
JP2014055840 | 2014-03-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2015140860A1 true WO2015140860A1 (ja) | 2015-09-24 |
Family
ID=54143886
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2014/006265 WO2015140860A1 (ja) | 2014-03-19 | 2014-12-16 | 施策推薦装置、施策推薦方法および施策推薦プログラム |
Country Status (4)
Country | Link |
---|---|
US (1) | US20160372000A1 (ja) |
EP (1) | EP3121785A4 (ja) |
JP (1) | JP6172781B2 (ja) |
WO (1) | WO2015140860A1 (ja) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018191774A (ja) * | 2017-05-15 | 2018-12-06 | パナソニックIpマネジメント株式会社 | 気流制御システム及び気流制御方法 |
WO2019077898A1 (ja) * | 2017-10-17 | 2019-04-25 | Necソリューションイノベータ株式会社 | 睡眠改善支援システム、方法およびプログラム |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI625682B (zh) * | 2017-12-01 | 2018-06-01 | 財團法人工業技術研究院 | 參數最佳化方法、裝置以及非暫態電腦可讀取媒體 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002073815A (ja) * | 2000-08-24 | 2002-03-12 | Omron Corp | 健康生活支援装置 |
WO2007063605A1 (ja) * | 2005-12-02 | 2007-06-07 | Netman Co., Ltd. | 行動改善システム |
JP2011197797A (ja) * | 2010-03-17 | 2011-10-06 | Toshiba Corp | エネルギー削減装置 |
WO2012127757A1 (ja) * | 2011-03-22 | 2012-09-27 | 日本電気株式会社 | 履歴収集装置、推薦装置、履歴収集方法、およびコンピュータ読み取り可能な記録媒体 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6064980A (en) * | 1998-03-17 | 2000-05-16 | Amazon.Com, Inc. | System and methods for collaborative recommendations |
WO2001033410A2 (en) * | 1999-11-04 | 2001-05-10 | Strategic Data Corp. | Segment-based self-learning method and system |
US20030186202A1 (en) * | 2002-03-27 | 2003-10-02 | Susan Isenberg | System and method for behavior modification |
US8540516B2 (en) * | 2006-11-27 | 2013-09-24 | Pharos Innovations, Llc | Optimizing behavioral change based on a patient statistical profile |
US20110256517A1 (en) * | 2010-04-20 | 2011-10-20 | Alaster Drew Swanson | Computer aided real-time behavior coaching |
-
2014
- 2014-12-16 WO PCT/JP2014/006265 patent/WO2015140860A1/ja active Application Filing
- 2014-12-16 US US15/122,286 patent/US20160372000A1/en not_active Abandoned
- 2014-12-16 JP JP2016508321A patent/JP6172781B2/ja active Active
- 2014-12-16 EP EP14886648.6A patent/EP3121785A4/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002073815A (ja) * | 2000-08-24 | 2002-03-12 | Omron Corp | 健康生活支援装置 |
WO2007063605A1 (ja) * | 2005-12-02 | 2007-06-07 | Netman Co., Ltd. | 行動改善システム |
JP2011197797A (ja) * | 2010-03-17 | 2011-10-06 | Toshiba Corp | エネルギー削減装置 |
WO2012127757A1 (ja) * | 2011-03-22 | 2012-09-27 | 日本電気株式会社 | 履歴収集装置、推薦装置、履歴収集方法、およびコンピュータ読み取り可能な記録媒体 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3121785A4 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018191774A (ja) * | 2017-05-15 | 2018-12-06 | パナソニックIpマネジメント株式会社 | 気流制御システム及び気流制御方法 |
WO2019077898A1 (ja) * | 2017-10-17 | 2019-04-25 | Necソリューションイノベータ株式会社 | 睡眠改善支援システム、方法およびプログラム |
JPWO2019077898A1 (ja) * | 2017-10-17 | 2020-10-22 | Necソリューションイノベータ株式会社 | 睡眠改善支援システム、方法およびプログラム |
Also Published As
Publication number | Publication date |
---|---|
JP6172781B2 (ja) | 2017-08-02 |
EP3121785A1 (en) | 2017-01-25 |
US20160372000A1 (en) | 2016-12-22 |
JPWO2015140860A1 (ja) | 2017-04-06 |
EP3121785A4 (en) | 2017-08-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11107118B2 (en) | Management of the display of online ad content consistent with one or more performance objectives for a webpage and/or website | |
AU2017202248B2 (en) | Intent prediction based recommendation system | |
CN109690608B (zh) | 外推信任得分中的趋势 | |
JP6719727B2 (ja) | 購買行動分析装置およびプログラム | |
US20160162974A1 (en) | Personalized recommendation method and system, and computer-readable record medium | |
US11042810B2 (en) | Similarity learning-based device attribution | |
US20130332385A1 (en) | Methods and systems for detecting and extracting product reviews | |
US20190087837A1 (en) | Cloud-based System And Methods for Quantifying Engagement Around Topics | |
Zhu et al. | Popularity modeling for mobile apps: A sequential approach | |
US20180047115A1 (en) | Systems and Methods of Data Mining to Customize Software Trial Demonstrations | |
US20180189860A1 (en) | Item recommendation system, item recommendation method, and computer program product | |
US20110252463A1 (en) | Method and system for providing enterprise procurement network | |
JP2017509960A (ja) | コンテンツ推奨のための方法、装置およびシステム | |
US9911130B1 (en) | Attribution modeling using regression analysis | |
US20200043026A1 (en) | Decision support system and methods associated with same | |
JP6172781B2 (ja) | 施策推薦装置、施策推薦方法および施策推薦プログラム | |
JP2002334257A (ja) | レコメンドエンジン、レコメンド方法、レコメンドプログラム | |
Moraes et al. | The role of attributes in product quality comparisons | |
US11809437B1 (en) | System and method for providing information about users who performed internet-based activities | |
US8700625B1 (en) | Identifying alternative products | |
Kwak et al. | Integrating the reviewers’ and readers’ perceptions of negative online reviews for customer decision-making: a mixed-method approach | |
US20140278800A1 (en) | Systems, devices, and methods for generating location establishment severity identification | |
Ghosh et al. | Raw jute grading by multi-criteria decision making method | |
JP5945206B2 (ja) | 商品推薦装置及び方法及びプログラム | |
Wu et al. | Modeling uncertainty driven curiosity for social recommendation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 14886648 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2016508321 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 15122286 Country of ref document: US |
|
REEP | Request for entry into the european phase |
Ref document number: 2014886648 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2014886648 Country of ref document: EP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |