WO2004070630A1 - Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection - Google Patents

Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection Download PDF

Info

Publication number
WO2004070630A1
WO2004070630A1 PCT/JP2003/001352 JP0301352W WO2004070630A1 WO 2004070630 A1 WO2004070630 A1 WO 2004070630A1 JP 0301352 W JP0301352 W JP 0301352W WO 2004070630 A1 WO2004070630 A1 WO 2004070630A1
Authority
WO
WIPO (PCT)
Prior art keywords
additional information
solution
stored
combination
degree
Prior art date
Application number
PCT/JP2003/001352
Other languages
English (en)
Japanese (ja)
Inventor
Yuiko Ohta
Nobuhiro Yugami
Original Assignee
Fujitsu Limited
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujitsu Limited filed Critical Fujitsu Limited
Priority to PCT/JP2003/001352 priority Critical patent/WO2004070630A1/fr
Publication of WO2004070630A1 publication Critical patent/WO2004070630A1/fr

Links

Classifications

    • 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

Definitions

  • the present invention relates to a solution recommendation system and a solution recommendation device for presenting a user with a solution that meets a condition entered by a user.
  • a solution recommendation system is used in which a solution recommendation device is input and presented to a mobile terminal or the like used by a user as a solution of a product or service (hereinafter abbreviated as a product) that meets the conditions.
  • solution recommendation systems include, for example, a system in which the desired price, CPU grade, memory capacity, etc. are entered to support the purchase of PCs, and a list of PCs meeting the conditions is displayed.
  • Other examples include a search system for real estate properties, a travel planning support system, a car estimation system, and a book and CD search system.
  • a user searches for a product or the like, selects a favorite product or the like from the presented solutions (presented solutions) (this selected solution is referred to as a selected solution), Purchase products, etc., or request a power log to get more detailed information.
  • the basic information (basic information) on the product such as price, contents, and characteristics, is the information that will determine the product, etc., from the presented solution.
  • users are often influenced by information (additional information) other than basic information, such as evaluations of the purchaser's usability and over-the-top sales.
  • a solution is created by adding additional information to the basic information. For example, general solutions are rearranged in the order of usability evaluation, and the top 10 cases are presented as presented solutions.
  • Solution recommendation system The operator expects the effect that the transaction will be activated by presenting the solution including the additional information, and by paying the provider of the additional information for the product when the product is purchased. In some cases, the additional information provider is prompted to provide the additional information. If the solution presented by the solution recommendation system is a single item, such as a book or CD (books and CDs can be traded independently), the additional information provider and the selected solution are fully supported And payment will be made appropriately.
  • PCs each part of CP Us memory, hard disk, etc. can be dealt with independently
  • travel railway companies, airlines, hotels, optional players, etc. can be dealt with independently
  • automobiles optional If the solution is composed of a combination of multiple items, such as the power navigation system and the evening party, etc., the combination of the product with additional information and the product in the selected solution Therefore, unless the combination of the product, etc. to which the additional information was provided by chance and the combination of the product, etc. in the selection solution match in the past, select the additional information provider and There is no known method for associating the solution, and the contribution of the additional information provider to the selected solution is unknown. It was not. Disclosure of the invention
  • An object of the present invention is to provide a solution recommendation system that presents a solution based on a user's condition input, and when a solution is configured by combining a plurality of items, a user selects a solution selected from the presented solutions. It is an object of the present invention to provide a solution recommendation system and a solution recommendation device having a function of calculating an influence level (contribution level) given by additional information and numerically indicating a contribution level of the additional information provider to the selected solution. .
  • a terminal connected to a network and used by a user to input a condition, and a condition connected to the network and receiving the input through the terminal are received.
  • One element is selected for each item from a plurality of elements corresponding to each of the plurality of items so as to match, a plurality of combinations of the elements selected for each item are created as a plurality of presentation solutions, and the Transmitting the plurality of presented solutions; and receiving one selected solution selected from the plurality of presented solutions via the terminal.
  • a solution recommendation device the plurality of items, the plurality of elements corresponding to the plurality of items, and the attribute information corresponding to the plurality of elements corresponding to each of the plurality of items;
  • a basic information database that includes a table and a second table that stores the combination possibilities between elements corresponding to different items, and one element from a plurality of elements corresponding to each of a plurality of items Is selected for each item, and a plurality of combinations of the elements selected for each item, additional information for each combination, and information for specifying a provider of each additional information are stored in association with each other, and
  • the degree of coincidence between the combination of the elements in the selected solution and each combination stored in the additional information database is calculated.
  • the object is to provide a first table in which a plurality of items, the plurality of elements corresponding to the plurality of items, and attribute information corresponding to the plurality of elements,
  • a basic information database including a second table in which the combination possibilities between the elements corresponding to the different items are associated with each other, and a plurality of items corresponding to different items are selected for each item from the corresponding plurality of elements.
  • a storage unit having an additional information data pace including an identifier to be changed, a condition input unit to which a condition is input, and attribute information stored in the first table and a second table according to the condition.
  • a solution presentation unit that selects one element for each item from a plurality of elements corresponding to each of the items, and creates and outputs a plurality of combinations of the elements selected for each item as a plurality of presentation solutions; and A selected solution selected from the presented solutions is input; a selected solution input unit; a combination of elements in the selected solution; Calculating the degree of coincidence of each combination stored in the additional information database, and calculating the degree of contribution of each combination stored in the additional information database to the selected solution using the degree of coincidence. And a contribution calculating unit that calculates a contribution of the additional information provider specified by the information that specifies the provider of the additional information to the selected solution.
  • FIG. 1 is a diagram illustrating a configuration example of a solution recommendation system according to the first embodiment.
  • FIG. 2 is a diagram illustrating an example of a configuration of basic information DB in the first embodiment.
  • FIG. 3 is a diagram illustrating an example of a data configuration of the additional information DB in the first embodiment.
  • FIG. 4 is a diagram illustrating an example of a general configuration of a general solution and a presented solution according to the first embodiment.
  • FIG. 5 is a block diagram illustrating a configuration example of the solution recommendation device according to the first embodiment.
  • FIG. 6 is a flowchart showing a process performed by the solution recommendation device according to the first embodiment.
  • FIG. 5 is a diagram showing a specific example of the basic information DB in the first embodiment.
  • FIG. 8 is a diagram illustrating a specific example of the additional information DB in the first embodiment.
  • FIG. 9 is a table summarizing the degree of coincidence and contribution in the first embodiment.
  • FIG. 10 is a table summarizing the degrees of contribution calculated in the first embodiment. 6
  • FIG. 11 is a flowchart showing the processing performed by the solution recommendation device in the second embodiment.
  • FIG. 12 is a table summarizing specific examples of the ratio of the appearance frequencies of the presented solutions in the second embodiment.
  • FIG. 13 is a table summarizing the calculation results of the average value and the standard deviation in the second embodiment.
  • FIG. 14 is a table summarizing the weights calculated in the second embodiment.
  • FIG. 15 is a flowchart showing a process performed by the solution recommendation device according to the third embodiment.
  • FIG. 16 is a table summarizing specific examples of the appearance frequency ratio of the general solution in the third embodiment.
  • FIG. 17 is a table summarizing the weights calculated in the third embodiment. BEST MODE FOR CARRYING OUT THE INVENTION
  • FIG. 1 is a diagram illustrating a configuration example of a solution recommendation system according to the first embodiment of the present invention.
  • Solution recommendation device 1 for presenting solutions via network 7 Terminal 8 for users to enter conditions and browse presented solutions 8, Terminal for additional information provider to input additional information 9 are connected to each other.
  • Terminal 9 for inputting caro information and the solution recommendation device 1 are connected to a dedicated network separate from the network 7.
  • a basic information database (basic information DB) 3 in which basic information is stored in advance, and additional information and an additional information provider are stored in association with each other in advance.
  • the additional information database (additional information DB) 4 is stored.
  • the storage device 2 stores the general solution 5 and the presented solution 6 in addition.
  • the basic information DB3, the additional information DB4, the general solution 5, and the presented solution 6 stored in the storage device 2 will be described.
  • FIG. 2 is a diagram illustrating an example of a data configuration of the basic information: DB 3 stored in the storage device 2.
  • the basic information D B3 basic information that is a basic explanation about a product or the like is stored. For example, for each product, attribute information such as the name, price, structure, and content of the product and the like, and connectivity information between products are included.
  • FIG. 2A is a product definition table in which a plurality of items 21, a plurality of elements 22 belonging to the item 21, and an attribute 23 corresponding to each element 22 are stored.
  • Item (IJ 21 stores the classification of the product or service that is the basis of the combination that makes up the solution.
  • Element (I u ) 22 stores the specific product name / service in that classification. For example, if it is a hamburger shop, item 1 burger class, element One Malberger, Element I 12 Big Burger, Item 1 2 Drinks, Item 1 3 Side menu.
  • the number of items 21, elements 22, and attributes 23 is not limited. There may be more, or only one.
  • the user uses the terminal 9 to input a condition for the attribute, and the solution recommendation device 1 presents a combination of the elements 22 extracted from each item 21 as a solution so as to match the given condition. Therefore, it may be necessary to determine whether a combination between the elements 22 is possible.
  • Figure 2B is a table that defines the possible combinations between elements 22.
  • the combination possibilities are stored for each element 22 included in the item I i and item 1 2.
  • ⁇ indicates that combination is possible, and X indicates that combination is not possible.
  • FIG. 3 is a diagram showing an example of a data configuration of the additional information DB 4 stored in the storage device 2. Additional information for the combination of element 23 of each item 21 is stored together with information for identifying the additional information provider.
  • Each entry has an ID 31 for identifying row data, each item (element 22 corresponding to IJ 21, additional information (Ali) 32, additional information provider (AlPi) which is information for identifying the information provider. ) 33 is stored that is, in FIG. 3, item I i of Retsude Isseki of CMBu CMB 2i -. ⁇ ⁇ 'elements Ii corresponding to the item Ii
  • the row data is identified by ID 31 and the combination of element 22 corresponding to each item 21 Matching is specified.
  • the additional information provided by the additional information provider 33 is stored in the additional information 32.
  • the additional information 32 stores the number of sales for the combination and the numerical value of the evaluation such as the evaluation value regarding usability.
  • the additional information provider 33 stores information specifying the information provider such as a name and an identification number.
  • FIG. 4 is a diagram showing an example of a general configuration of a general solution 5 and a presentation solution 6. Stores a combination of elements 22 of item 21. In each entry, an ID 41 that identifies the row data and an item 22 corresponding to each item (12 1) are stored. In other words, in FIG.
  • S 2 i ⁇ ' is one of element I or element I i 2 , ⁇ ⁇ ⁇ corresponding to item I i
  • the ID 41 identifies a row and a line, and each item The combination of elements 2 2 corresponding to 2 1 is specified.
  • a general solution having a data configuration shown in FIG. 4 is first obtained based on the conditions input by the user and the basic information stored in the 'basic information DB 3 shown in FIG. Then, based on the additional information stored in the additional information DB 4 in FIG. 3, a general solution 5 to a presentation solution 6 having the data configuration shown in FIG. 4 are generated. Further, based on the selected solution selected by the user from the presented solution 6, the degree of influence of the additional information on the selected solution is calculated, and the contribution of the additional information provider is calculated.
  • the processing of the solution recommendation system according to the first embodiment of the present invention is performed mainly by the solution recommendation device 1.
  • FIG. 5 is a block diagram illustrating a configuration example of the solution recommendation device according to the first embodiment of the present invention.
  • the solution recommendation device 1 has access to a request input unit 51 having an interface to the network 7 for receiving conditions input by the user, the basic information DB 3 and the additional information DB 4, and Creates solution 5 and solution 6 and sends it to the terminal used by the user Network 7 and solution presenting interface to storage device 2
  • Solution presenter 52 and receives solution selected from solution presented
  • select solution input unit 53 with an interface to network 7, additional information DB 4, general solution 5, presentation solution 6 to calculate the contribution of the additional information to the storage solution 2 and the contribution calculation unit 54 with an interface to the storage device 2 to calculate the contribution of the additional information to the selected solution. It has a contribution calculation unit 55.
  • the request input unit 51 and the solution presentation unit 52 are connected to transmit the condition received by the request input unit 51 to the solution presentation unit 52.
  • the selection solution input unit 53 and the contribution calculation unit 54 are connected.
  • the contribution calculation unit 55 calculates the contribution based on the contribution calculated by the contribution calculation unit 54, so that the contribution calculation unit 54 and the contribution calculation unit 55 are connected.
  • FIG. 6 is a flowchart illustrating a process performed by the solution recommendation apparatus 1 according to the first embodiment.
  • the solution recommendation device 1 receives the condition input by the user in the request input unit 51 (S61).
  • the user uses the terminal 8 to input a desired condition for the attribute (A T J.
  • the input condition is transmitted via the network 7.
  • the solution recommending device 1 refers to the basic information DB 3 and the additional information DB 4 of the storage device 2 and creates a general solution 5 and a presented solution 6 in the solution presenting section 52 (S62).
  • step S62 the basic information DB3 in FIG. 2 is searched so as to match the condition entered for attribute 23, and a combination of elements 22 is created as general solution 5.
  • an appropriate solution is presented to the user from the general solution 5 with reference to the additional information DB4.
  • a method of presenting the presentation solution 6 with reference to the additional information DB4 is shown in, for example, Japanese Patent Application No. H13-3-349531, which is a prior application.
  • the solution recommending device 1 transmits the presented solution 6 created in step S62 to the terminal used by the user from the solution presenting unit 52 (S63).
  • the user can confirm the received presentation solution 6 on the terminal 8 and select a solution from the presentation solutions 6.
  • the selected solution selected by the user is transmitted to the solution recommending device 1 via the network 7.
  • the solution recommendation device 1 receives the selected solution at the selected solution input unit 53 (S64).
  • the solution recommendation device 1 extracts an element 22 for each item 21 from the selected solution received in step S64 in the contribution degree calculation unit 54 (S65). For example, if the selection solution is the one corresponding to the ID of 1 in FIG. 4, “S i S 1 2 , S i 3 ” is received. Next, select solution Then, elements are extracted for each item from (S65). Using an example of step S 64 as it is, with respect to items 1 ⁇ but, S 12 to item 1 2, S 13 to item 1 3 is it its being extracted.
  • the solution recommendation device 1 calculates the number of items 21 that match the extracted element 22 with respect to the row data of the additional information DB 4 as the matching degree (S66).
  • the additional information has an effect on the creation of the presented solution, and considering that the selected solution is selected from the presented solutions, the more the rows and columns of the additional information DB 4 match the selected solution, the more This is because it can be considered that the degree of influence on the selected solution in the row day is large.
  • Step S 66 is, for example, select solutions "Su, S 12, S 13", if the result is row data Gyode Isseki is the ID of FIG. 3 1, and CMBi have S 12 and CMB 12, S 13 and comparing the CMB 13, the matching number with the degree of matching.
  • each line of the additional information DB 4 is calculated (S67).
  • the contribution Ci of each line data is n ID (i) 31 ( ⁇ ⁇ is a natural number), and the additional information corresponding to each ID (i) 31 is AI. If the degree of coincidence is Mi
  • the degree of coincidence M i is normalized by the additional information AI i.
  • the additional information provider AIP i shown in Fig. 3 extracts the ID 31 that matches the additional information provider, and calculates the contribution Ci and the additional information A Is calculated by calculating the sum of the products of all the IDs 31 extracted.
  • the user shall be able to enter conditions regarding price, number of CPU clocks, and memory capacity.
  • the PC is set as the base, and if the performance of the main body is unsatisfactory, the upgrade of CPU and memory can be selected as long as replacement is possible.
  • FIG. 7 is a diagram illustrating a specific example of the basic information DB 3 in the first embodiment.
  • the basic information DB includes three table data: a product definition table (Fig. 7A;), a body-to-CPU replacement possibility definition table (Fig. 7B), and a body-memory addition possibility definition table (Fig. 7C).
  • Fig. 7A a product definition table
  • Fig. 7B a body-to-CPU replacement possibility definition table
  • Fig. 7C body-memory addition possibility definition table
  • Each entry in FIG. 7A stores a product 71, a price 72 of the product, a CPU clock frequency 73, and a memory capacity 74.
  • the product 71 has the following items: main body 711, CPU replacement 712, and additional memory 713.
  • the main body 711 stores the data of the base PC as a base, and in FIG. 7A, four elements from PC0 to PC3 are described. Data of price 72, number of clocks 73, and memory capacity 74 is stored for each element. For example, you can see that PC0 of the main body 711 costs 100,000 yen, has a clock frequency of 1.0 GHz, and a memory capacity of 256 MB.
  • the CPU replacement 712 is an upgrade menu that can be selected when the user is not satisfied with the sound of the main body 711.
  • FIG. 7A three elements from CPU0 to CPU2 are described. For each element, the price 72, and the number of clocks after the upgrade are stored. For example, referring to CPU0 of CPU Replacement 712, it can be seen that to replace it with a 1.2 GHz CPU, '40, 000 yen should be added.
  • the additional memory 713 is another upgrade menu that can be selected when the specifications of the main body 711 are not satisfied.
  • FIG. 7A three elements from M0 to M2 are described. For each element, the price is 72 and the amount of additional memory is stored.
  • M0 of the memory addition 713 it can be seen that the memory addition of 128 MB can be achieved by adding 100,000 yen.
  • the memory additions Ml and M2 are cases where there is a price difference due to the presence or absence of the manufacturer's brand ⁇ ECC (Error Check and Correct) function, for example.
  • ECC Error Check and Correct
  • FIG. 7B is a diagram showing the possibility of replacement between the main body 711 and the CPU replacement 712.
  • “ ⁇ ” is stored for combinations that can be replaced with a CPU
  • “X” is stored for combinations that are not possible.
  • the main unit PC can be replaced with a 1.2 GHz CPU 0, but cannot be replaced with a 1.5 GHz ⁇ 1.8 GHz CPU.
  • FIG. 7C is a diagram showing the possibility of replacement between the main body 711 and the memory storage 713.
  • ⁇ is stored for combinations that can add memory
  • X is stored for combinations that cannot be added. For example, it can be seen that 128 MB of memory M0 and 256 MB of memory M1 can be added to PC 1, but 256 MB of memory M2 cannot be added.
  • the additional information DB 4 in the present embodiment will be described.
  • the number of items sold is used as the additional information.
  • FIG. 8 is a diagram illustrating an example of a data configuration of the additional information DB in the first embodiment.
  • Each entry in FIG. 8 stores an ID 81 for identifying a row and a line, a main body 711, a CPU exchange 712, an additional memory 713, a sales number 82 of this combination, and an additional information provider 83.
  • the main body 711, the CPU replacement 712, and the additional memory 713 are the items of the product 71 in the basic information DB 3 in FIG. 7, and if there are other items of the product 71, they are added.
  • information provider A sold a total of 10 combinations of ID 81 (ie, main unit PC0, no CPU replacement, additional memory MO). Similarly, it can be seen that the information provider B sold a total of 15 ID 81 combinations.
  • step S64 in FIG. 6 the solution recommendation device 1 receives the selected solution (S64).
  • S64 For example, And “Main unit PC2, CPU replacement CPU1, No additional memory” shall be selected.
  • elements are extracted for each item from the selected solution (S65).
  • the elements “PC2”, “CPU 1”, and “None” are extracted for the items “main body 711”, “(? ! replace?”) And “memory addition”.
  • the number of items that match the extracted elements is calculated as the degree of coincidence with respect to the row data of the additional information DB 4 (S66).
  • the degree of coincidence is set in the same manner.
  • FIG. 9 is a table summarizing the degree of coincidence in the first embodiment.
  • the column 91 of the match degree 91 in FIG. 9 indicates the match degree calculated in step S66 corresponding to each ID 81.
  • the contribution of each line is calculated using equation (1).
  • the contribution degree of the combination having the ID 81 of 4 is 2 2 ⁇ 0 * (10 + 15 + 5) + 2 * It is calculated as (5 + 10 + 10) + 1 * (1 + 6 + 13) + 2 * (7 + 8) 100.
  • the contribution 72 can be calculated for the remaining ID 81 in the same manner, and the results are summarized as shown in FIG.
  • the degree of contribution of each additional information provider is calculated (S68).
  • additional information provider A sells 10 combinations with ID 1, 5 combinations with ID 4, 1 combination with ID 7, and 7 combinations with ID 10 Therefore, the contribution X A is calculated by calculating the product of the contribution 92 and the number of units sold 82 for each ID corresponding to the information provided by the additional information provider A, and calculating the sum of the products.
  • FIG. 10 is a table summarizing the degrees of contribution calculated in the first embodiment.
  • the sum of the contributions of A, B, and C is 1 and the contribution can be calculated as a percentage, and the variance of the consideration can be made based on this contribution.
  • the first embodiment described above it is possible to calculate the contribution of the additional information to the selected solution and the contribution of each additional information provider. Then, by distributing the compensation set by the operator of the solution recommendation system in accordance with the calculated contribution, it becomes possible to appropriately distribute the compensation. If the account number etc. of the transfer destination is registered for each additional information provider as information of the additional information provider, it is possible to automatically perform the distribution processing of the consideration according to the degree of contribution. .
  • the second embodiment uses the same system configuration as in FIG. 1, and the configuration of the solution recommendation device 1 in the system uses the same configuration as in FIG. 2, but the processing in the solution recommendation device 1 is the first embodiment. And different.
  • the direct influence degree between the selected solution and the additional information additional information is calculated as the contribution, but in the second embodiment, the information is created by the influence of the additional information.
  • the indirect influence of the selected solution and the additional information is calculated as the contribution by considering the influence of the presented solution 6 and the selected solution as weights.
  • the processing performed by the solution recommendation apparatus 1 will be described to explain the processing of the solution recommendation system in the second embodiment.
  • FIG. 11 is a flowchart showing a process performed by the solution recommendation device 1 according to the second embodiment.
  • the same steps as those in the first embodiment are assigned the same step numbers.
  • the description of the steps having the same step number is the same as that of each process in FIG. 6 in the first embodiment, and the description is omitted.
  • the solution recommendation device 1 receives the condition input by the user through the request input unit 51 (S61). Subsequently, the solution recommendation device 1 refers to the basic information DB 3 and the additional information DB 4 of the storage device 2, and creates a general solution 5 and a presentation solution 6 in the solution presentation section 52 (S62). Then, the solution recommendation device 1 transmits the presented solution 6 created in step S62 to the terminal used by the user from the solution presenting unit 52 (S63). Then, the solution recommendation device 1 receives the selected solution at the selected solution input unit 53 (S64), and the solution recommendation device 1 receives the selected solution from the step S64 at the contribution calculation unit 54. The element is extracted for each item included in the product 71 of the basic information DB 3 (S65). The above processing is the same as the processing in FIG. 6 in the first embodiment.
  • the ratio of the appearance frequency of each element in the presented solution is calculated for each item (S111).
  • the frequency of each element 32 was calculated for each column data item (item 21), and the frequency of each element 32 was divided by the total number of column data items. Find it.
  • the average value and the standard deviation of the appearance frequency are calculated for each item (S112).
  • a weight is calculated to reflect the influence of the elements included in the selected solution on each row of the additional information DB due to the presence of the presented solution (S113).
  • the normal distribution of the mean and standard deviation calculated in step S112 is assumed as the weight, and the upper probability is used. This means that when the frequency of appearance is higher than the average value, the probability that the element is included in the selection solution is high. Conversely, if that element is included in the choice solution, the additional information has a small effect.
  • step s 1 13 if the ratio of the current frequency is higher than the average value, the weight is reduced, and if the current frequency ratio is lower than the average value, the weight is increased.
  • N (0, 1) is called a standard normal distribution. If the correspondence between a random variable according to the standard normal distribution and its upper probability is stored in a storage device 2 (not shown) as a tabular data, step S 1 1 Calculation of 3 is possible.
  • step S113 when the weight of each element included in the selected solution can be calculated, then in each row, the sum of the weights corresponding to the elements that match the element extracted from the selected solution is matched. It is calculated as a degree (S114).
  • the row data with Caro information DB in FIG. 3 item I if ⁇ and item 1 2 agrees with the elements of the selected solution, the sum of the weights corresponding to the item I i and item I i is the Gyode Isseki It is calculated as the degree of coincidence with.
  • step S67 the contribution is calculated based on equation (1), as in the first embodiment.
  • step S68 the contribution of each additional information provider is calculated (S68).
  • step S68 as in the first embodiment, the additional information provider AIP i in FIG. 3 extracts an ID (i) 31 that matches the additional information provider, and extracts row data for each of the IDs 31.
  • the contribution of each additional information provider is calculated by calculating the product of the contributions Ci and the additional information AIi, and taking the sum of the products of all the extracted IDs 31.
  • FIG. 7 is used as a specific example of the basic information DB 3 and FIG. 8 is used as a specific example of the additional information DB 4 . It is assumed that “Main unit PC 2, CPU replacement CPU1 ⁇ No additional memory” is selected as the selection solution.
  • FIG. 12 is a table summarizing specific examples of the ratio of the appearance frequencies of the presented solutions in the second embodiment.
  • the ratios of the appearance frequencies of PC0, PC1, and PC2 are 1/4, 1/4, and 1/2, respectively. This means that, for example, when eight solutions are presented, two PC0s, two PC1s, and four PC2s are included. Similar information can be read for other items.
  • step S64 in FIG. 11 The description starts with step S64 in FIG. 11 to calculate the degree of coincidence.
  • the solution recommendation device 1 receives the selected solution (S64).
  • the user receives “Main unit PC 2, CPU replacement CPU 1, no additional memory” as a choice solution.
  • elements are extracted for each item from the selected solution (S65).
  • PC2”, “CPU1”, and “None” are extracted for the items “body 711”, “CPU replacement 712”, and “memory addition”, respectively.
  • FIG. 13 is a table summarizing the calculation results of the average value and the standard deviation in step S112 in the second embodiment. For example, the average value of the appearance frequency ratio of the main body 711 is 1/3, and the standard deviation is 1/72).
  • the weight for PC2 among the elements extracted from the selected solution is calculated.
  • FIG. 14 is a table summarizing the data of the weights calculated in step S113 in the second embodiment. Referring to FIG. 14, the weights for the elements included in the selected solution received in step S64 can be obtained.
  • the sum of the weights corresponding to the elements that match the elements extracted from the selected solution is calculated as the degree of coincidence (S114).
  • the degree of coincidence is 0 because none of the elements included in the selected solution is included.
  • the CPU 1 and no additional memory match the selection. Therefore, referring to FIG. 14, the sum of 0.5, which is the weight of CPU 1, and 0.14, which is the weight without adding a memory, is set as the degree of coincidence.
  • the sum of the corresponding weights obtained in FIG. 14 for the rows and columns including elements that match the selected solution is calculated as a match.
  • the degree of coincidence is calculated for all data, the degree of contribution and the degree of contribution are calculated in steps S67 and S68 as in the first embodiment.
  • the degree of influence of the additional information on the selected solution is calculated by taking the influence of the additional information on the presented solution as a weight, and as a result, the additional information provider The degree of contribution can be calculated appropriately.
  • the impact of additional information on the selected solution is not calculated directly, but the effect of the additional information on the selected solution is considered by taking into account the effect of the presented solution that served as a decision material for the user.
  • the payment to the additional information provider can be made fair.
  • the weight is calculated based on the ratio of the appearance frequency of each element in the presented solution.
  • the weight is calculated based on the ratio of the appearance frequency of each element in the general solution and the presented solution. The difference in the appearance frequency ratio of each element is considered to indicate the degree of influence given by the additional information, and the difference is quantified and calculated as a weight.
  • FIG. 15 is a flowchart showing a process performed by the solution recommendation device according to the third embodiment.
  • the same steps as those in the first embodiment are assigned the same step numbers.
  • the description of the steps having the same step number is the same as each processing in FIG. 6 in the first embodiment, and the description is omitted.
  • the solution recommendation device 1 receives the condition input by the user through the request input unit 51 (S61). Subsequently, the solution recommendation device 1 refers to the basic information DB 3 and the additional information DB 4 of the storage device 2, and creates a general solution 5 and a presentation solution 6 in the solution presentation unit 52 (S62).
  • the solution recommending device 1 transmits the presented solution 6 created in step S62 to the terminal used by the user from the solution presenting unit 52 (S63). Subsequently, the solution recommendation device 1 receives the selected solution at the selected solution input unit 53 (S64).
  • the above processing is the same as the processing in FIG. 6 in the first embodiment o
  • Step S111 is the same process as step S111 of FIG. 11 in the second embodiment.
  • the ratio of the appearance frequency of each element in the general solution is calculated (S151).
  • General The solution is processed in the same manner as in step S111.
  • the information of the information of the carburetor (KL information) is calculated for each item (S152).
  • KL information is a numerical value for checking the difference from another distribution of interest based on one distribution, and becomes 0 if there is no difference between the two distributions. The difference between the two distributions is considered to be due to the additional information.
  • the KL information amount indicates the degree of influence given by the additional information. If the value is large, the degree of influence given by the additional information is large. Therefore, this numerical value is used as a weight. Assuming that the reference distribution is P, its probability density is Pi, its target distribution is Q, its probability density is qi, and the number of data points is ⁇ ( ⁇ is a natural number),
  • ⁇ is the distribution of each element 23 in the proposed solution
  • Q is the distribution of the corresponding element in the general solution
  • qi is the It is applied in the same way as the frequency of appearance.
  • step S152 When the weight for each item has been calculated in step S152, the sum of the weights corresponding to the elements that match the elements extracted from the selected solution is calculated as the degree of coincidence in each row (S114). This is the same as the processing in step S114 in FIG. 11 in the second embodiment.
  • step S114 Since the degree of coincidence has been calculated for each row in step S114, the contribution of each row is calculated (S67). This is the same as in the first embodiment,
  • FIG. 16 is a table summarizing a specific example of the appearance frequency ratio of the general solution in the third embodiment.
  • the appearance frequency ratios of PC0, PC1, and PC2 are 1/2, 1/4, and 1/4, respectively. This means that, for example, when eight solutions are presented, four PC0s, two PC1s, and two PC2s are included. You can read the same for other items as well.
  • Fig. 16 shows a numerical example of a general solution, which differs from Fig. 12 which is a numerical example of a presented solution.
  • step S64 in FIG. 15 the description starts with step S64 in FIG. 15 as the calculation of the degree of coincidence.
  • the solution recommendation device 1 receives the selected solution (S64).
  • the user receives “Main unit PC 2, CPU replacement CPU 1, no additional memory” as a choice solution.
  • the ratio of the appearance frequency of each element in the presented solution is calculated for each item (S111).
  • Fig. 12 is used as a numerical example.
  • the ratio of the appearance frequency of each element in the general solution is calculated (S151).
  • Figure 16 shows an example of the numerical values.
  • the KL information amount is calculated, and the weight for each item of the selected solution is calculated (S152).
  • the KL information amount S (P, Q) for the main body 711 is
  • FIG. 17 is a table summarizing the data of the weights calculated in step S152 in the third embodiment.
  • the weight for each item can be obtained.
  • the sum of the weights corresponding to the elements that match the elements extracted from the selected solution is calculated as the degree of coincidence (S114).
  • the degree of coincidence is zero for the data with IDs 1, 2, and 3 because none of the elements included in the selected solution are included.
  • the CPU 1 and no additional memory match the selected solution. Therefore, referring to Fig. 17, the sum of 1.06, which is the weight of main unit 711, and the weight of 0.09, which is the weight without additional memory, is equal to 1.15. Set as degrees.
  • the sum of the corresponding weights obtained in Fig. 17 is calculated as a match for the row data containing elements that match the selected solution.
  • the degree of coincidence is calculated for all data, the degree of contribution and the degree of contribution are calculated in steps S67 and S68, as in the first embodiment.
  • the weight of the effect of the attached information on the presented solution is used as a weight to determine the degree of influence of the additional information on the selected solution. Calculation, and as a result, the degree of contribution of the additional information provider can be appropriately calculated. Instead of directly calculating the degree of influence that the additional information has on the selected solution as in the first embodiment, the additional information The impact of the choice solution can be reflected more appropriately, and the payment to the additional information provider can be fair.
  • the present invention can be implemented by creating a process performed in the solution recommendation apparatus described in the embodiment of the present invention as a program and causing the computer to execute the process.
  • the contribution of the additional information provider can be quantified, and the quantified contribution can be used.
  • payment of an appropriate price is executed to the additional information provider.
  • motivation to collect more additional information can be given to the additional information provider, and by enriching the additional information, it is possible to promote active transaction. it can.
  • the provider of additional information can be expected to pay an appropriate price, which motivates them to actively provide additional information.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

L'invention concerne un système de recommandation offrant des informations supplémentaires notamment d'utilisation, en plus des informations de base, comme informations à présenter à un utilisateur à la recherche d'informations de produits. Il est possible de calculer une considération appropriée en fonction du degré de contribution du fournisseur d'informations supplémentaires. Le système de recommandation possède une fonction permettant de calculer de façon mécanique le degré de contribution, par exemple, la contribution de cette information supplémentaire lorsqu'un utilisateur sélectionne un produit.
PCT/JP2003/001352 2003-02-10 2003-02-10 Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection WO2004070630A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2003/001352 WO2004070630A1 (fr) 2003-02-10 2003-02-10 Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2003/001352 WO2004070630A1 (fr) 2003-02-10 2003-02-10 Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection

Publications (1)

Publication Number Publication Date
WO2004070630A1 true WO2004070630A1 (fr) 2004-08-19

Family

ID=32843989

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2003/001352 WO2004070630A1 (fr) 2003-02-10 2003-02-10 Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d'un fournisseur d'information supplementaire dans une selection

Country Status (1)

Country Link
WO (1) WO2004070630A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6167383A (en) * 1998-09-22 2000-12-26 Dell Usa, Lp Method and apparatus for providing customer configured machines at an internet site
JP2002288503A (ja) * 2001-03-23 2002-10-04 Casio Comput Co Ltd 販売促進システム、販売促進方法、及びそのプログラム
JP2002342370A (ja) * 2001-05-11 2002-11-29 Nippon Telegr & Teleph Corp <Ntt> 情報検索提供装置、情報検索提供方法及びそのプログラムを記録した記録媒体

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6167383A (en) * 1998-09-22 2000-12-26 Dell Usa, Lp Method and apparatus for providing customer configured machines at an internet site
JP2002288503A (ja) * 2001-03-23 2002-10-04 Casio Comput Co Ltd 販売促進システム、販売促進方法、及びそのプログラム
JP2002342370A (ja) * 2001-05-11 2002-11-29 Nippon Telegr & Teleph Corp <Ntt> 情報検索提供装置、情報検索提供方法及びそのプログラムを記録した記録媒体

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Harufumi OKAMOTO et al., "CBR o Mochiita Product Configuration", Information Processing Society of Japan Dai 61 Kai (Heisei 12 Nen Koki) Zenkoku Taikai Koen Ronbunshu (1), 03 October 2000, pages 177 to 180 *
Manabu NAGAI, *Konomi no Shohin o Jidoteki ni Suisen suru Recommendation", Nikkei Multimedia for Business, 15 January 1999, No. 43, pages 144 to 145 *

Similar Documents

Publication Publication Date Title
US10127285B2 (en) Customizable ranking of search engine results in multi-tenant architecture
CN100428221C (zh) 用于网络服务的信誉系统
US7478054B1 (en) Sharing information about purchases
US20200219203A1 (en) Computerized transaction management module for blockchain networks
US20190188776A1 (en) Data structure systems and methods that receive and genericize recipes
US20110022606A1 (en) Processes for assessing user affinities for particular item categories of a hierarchical browse structure
US20030144852A1 (en) Providing highly automated procurement services
US20040220845A1 (en) System and method of automated package tracking
US20140052578A1 (en) Promoter system and method for processing product and service data
US20190188775A1 (en) Database systems and methods of maintaining and enabling retail purchases through recipes
US10489841B1 (en) Fulfillment option optimization
CN113312527B (zh) 采购数据处理方法、装置、计算机设备和存储介质
Chen et al. Integrated order scheduling and packing
KR20220013734A (ko) 소비량 예측을 통한 주문 필요 식자재의 맞춤형 스마트 주문 서비스 제공 방법
WO2002003268A1 (fr) Intelligence d&#39;achats fondee sur les attributs
US7233955B2 (en) System and method for searching and retrieving information regarding related goods and services
KR102382802B1 (ko) 와인플랫폼 시스템 및 운영방법
Sudharson et al. A Survey on Reader's Society: New Social Network of Book Swapping Platform
WO2002042977A2 (fr) Echange d&#39;informations sur des achats
KR20180005714A (ko) 거래 지원 시스템
US20090132491A1 (en) Data Processing System And Method
US20050119947A1 (en) Gift recommending method and system
JP2005216239A (ja) 薬品調達支援システムおよびその方法
WO2004070630A1 (fr) Systeme de recommandation et appareil presentant une fonction de numerisation de la contribution d&#39;un fournisseur d&#39;information supplementaire dans une selection
CN114240201A (zh) 一种基于供应链背景下的智慧数据中台

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): JP US

NENP Non-entry into the national phase

Ref country code: JP

WWW Wipo information: withdrawn in national office

Country of ref document: JP