Search device, search method, and program

Abstract

To provide an information processor method and program that efficiently acquire a search result by updating a search condition on the basis of a user's response to a question for generating the search condition using attribute information.SOLUTION: A search device comprises: a search target extraction section that refers to a data set having search target information in which an image is associated with one or more pieces of attribute information, and extracts the search target information having attribute information which matches the attribute information in a search condition; a score calculation section that, when the number of pieces of search target information does not fall within a search result range set in advance, refers to a knowledge base in which attribute information is hierarchically classified and calculates a score using a score function defined in advance for each attribute information included in the extracted search target information; a question generation section that selects attribute information on the basis of the calculated score and generates question information indicating a question to be presented to a user using the selected attribute information; and a search condition generation section that reflects attribute information, which is indicated by a response of the user to the question information, in the search condition to generate a new search condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a search device and a search method for performing a search based on search conditions, and also to a program for implementing these. [Background technology]

[0002] When searching for images of people or objects, search criteria must be created. However, since users cannot comprehend the vast amount of data, it is difficult to create optimal search criteria. As a result, it takes a great deal of effort and time to obtain the desired search results.

[0003] As a related technique, Patent Document 1 discloses a dialogue scenario generation system that generates scenario data that allows a user to continue a dialogue until the user obtains the FAQ data that the user desires.

[0004] According to the system of Patent Document 1, when the number of data to be searched is three or more, the combinations of the attributes of the data to be searched and their attribute values ​​are organized from the perspective of the attribute-attribute value pairs that are not included in the combinations.

[0005] In the system of Patent Document 1, if it is determined through dialogue between the user and the system that the user's intention is related to the combination, attribute values ​​of attributes not included in the combination are presented to the user as selection candidates, and scenario data is generated for selection to narrow down the data to be searched. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Laid-Open No. 2012-248161 Summary of the Invention [Problem to be solved by the invention]

[0007] However, the system in Patent Document 1 is a system that searches for the FAQ data desired by the user through dialogue between the user and the system, so it is difficult to apply it to searching for image data.In other words, since image data and the like often have similarities and overlaps, it is difficult to apply the system in Patent Document 1.

[0008] One object of the present invention is to provide a search device, a search method, and a program that update search conditions based on a user's response to a question and efficiently obtain search results. [Means for solving the problem]

[0009] In order to achieve the above object, a search device according to one aspect comprises: a search target extraction unit that uses search criteria having one or more pieces of attribute information to refer to a dataset having search target information in which images are associated with one or more pieces of attribute information, and extracts search target information having the attribute information that matches the attribute information of the search criteria; a score calculation unit that, when the number of pieces of extracted search target information is not within a predetermined search result range, refers to a knowledge base in which attribute information is hierarchically classified, and calculates a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation unit that selects attribute information based on the calculated score and generates question information representing a question to be presented to a user using the selected attribute information; a search condition generation unit that reflects attribute information represented by the user's answer to the question information in the search conditions to generate new search conditions; The present invention is characterized by having the following.

[0010] In order to achieve the above object, a search method according to one aspect of the present invention comprises: a search target extraction step of referring to a dataset having search target information in which an image is associated with one or more pieces of attribute information using search criteria having one or more pieces of attribute information, and extracting search target information having the attribute information that matches the attribute information of the search criteria; a score calculation step of, when the number of pieces of extracted search target information is not within a predetermined search result range, referring to a knowledge base in which attribute information is hierarchically classified, and calculating a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation step of selecting attribute information based on the calculated score and generating question information representing a question to be presented to a user using the selected attribute information; a search condition generating step of generating new search conditions by reflecting attribute information represented by the user's answer to the question information in the search conditions; The present invention is characterized by having the following.

[0011] Furthermore, in order to achieve the above object, a program according to one aspect of the present invention comprises: On the computer, a search target extraction step of referring to a dataset having search target information in which an image is associated with one or more pieces of attribute information using search criteria having one or more pieces of attribute information, and extracting search target information having the attribute information that matches the attribute information of the search criteria; a score calculation step of, when the number of pieces of extracted search target information is not within a predetermined search result range, referring to a knowledge base in which attribute information is hierarchically classified, and calculating a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation step of selecting attribute information based on the calculated score and generating question information representing a question to be presented to a user using the selected attribute information; a search condition generating step of generating new search conditions by reflecting attribute information represented by the user's answer to the question information in the search conditions; The present invention is characterized in that the following is executed. [Effects of the Invention]

[0012] One aspect is that search conditions can be updated based on the user's answers to questions, allowing for efficient retrieval of search results. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an example of a search device. [Figure 2] FIG. 2 is a diagram illustrating an example of a knowledge base. [Figure 3] FIG. 3 is a diagram for explaining the relationship between search target information and attribute information. [Figure 4] FIG. 4 is a diagram illustrating an example of a system having a search device. [Figure 5] FIG. 5 is a diagram illustrating an example of the operation of the search device. [Figure 6] FIG. 6 is a diagram illustrating an example of a computer that realizes the search device. [Figure 7] FIG. 7 is a diagram for explaining questions and answers. [Figure 8] FIG. 8 is a diagram for explaining the relationship between search target information and attribute information. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, embodiments will be described with reference to the drawings. In the drawings described below, elements having the same or corresponding functions are denoted by the same reference numerals, and repeated description thereof may be omitted.

[0015] (Embodiment) The configuration of a search device 10 in the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of a search device.

[0016] [Device configuration] The search device 10 shown in Fig. 1 can update search conditions based on a user's answer to a question and efficiently obtain search results. As shown in Fig. 1, the search device 10 includes a search target extraction unit 11, a score calculation unit 12, a question generation unit 13, and a search condition generation unit 14. The search device 10 is also connected to a knowledge base 15 via a network or the like.

[0017] The search target extraction unit 11 uses search criteria having one or more pieces of attribute information to refer to a dataset having search target information in which an image is associated with one or more pieces of attribute information, and extracts search target information having attribute information that matches the attribute information of the search criteria.

[0018] The case of extracting images will be described below. The search target extraction unit 11 extracts images based on search criteria. The images are, for example, images of people or objects. The images may be still images or moving images. Examples of still images include paintings, figures, clip art, and illustrations, and examples of moving images include video footage and animations, but the types of images are not limited to these. The search criteria have one or more pieces of attribute information that represent the characteristics of the image. When the attribute information represents the characteristics of an image of a person (hereinafter referred to as a person image), it may include, for example, gender, age, color of clothing, glasses, etc.

[0019] When extracting a person image using the attribute information of the search conditions as gender, age, clothing color, and glasses, the search target extraction unit 11 uses the gender, age, clothing color, and glasses to refer to one or more pieces of attribute information associated with each person image, and extracts a person image having the attribute information of gender, age, clothing color, and glasses.

[0020] The attribute information associated with each person image is hierarchically classified. The attribute information is hierarchically organized as shown in the knowledge base shown in Fig. 2. Fig. 2 is a diagram for explaining an example of the knowledge base. The knowledge base will be described in detail later.

[0021] The dataset has search target information in which a person ID, one or more pieces of attribute information, and a person image are associated, as shown in Fig. 3. Fig. 3 is a diagram for explaining the relationship between the search target information and the attribute information. The dataset in Fig. 3 has nine pieces of search target information.

[0022] The knowledge base will now be explained. In the knowledge base of Figure 2, the attribute information of age, gender, glasses, and clothing color is hierarchically classified. The age layer has attribute information for middle-aged and elderly people and young people in the lower layer. The middle-aged and elderly layer has attribute information for people in their 40s, 50s, and 60s in the lower layer. The young people layer has attribute information for people in their 20s and 30s in the lower layer.

[0023] Gender has attribute information of male and female in the lower layer. Glasses has attribute information of none (representing the state of not wearing glasses), corrective glasses (representing the state of wearing glasses to correct vision), and sunglasses (representing the state of wearing sunglasses) in the lower layer.

[0024] The clothing colors have attribute information of gray-black, orange, red, yellow, green, blue, and purple in the lower layer. The red color has attribute information of deep red, dark red, and light coral in the lower layer.

[0025] The true reds have the attribute information of true red (255,0,0), orange-red (255,69,0), and crimson (220,20,60) in the lower layers. The dark reds have the attribute information of dark red (139,0,0), brown (165,42,42), and fire brick (178,34,34) in the lower layers. The light corals have the attribute information of light coral (240,128,128), Indian red (205,92,92), and salmon (250,128,114) in the lower layers. The three numbers in parentheses represent RGB values.

[0026] However, the structure of the knowledge base is not limited to the structure shown in Fig. 2. Although the knowledge base 15 is provided outside the search device 10 in the example of Fig. 1, it may be provided inside the search device 10.

[0027] If the number of extracted search target information pieces is not within a predetermined search result range, the score calculation unit 12 refers to a knowledge base 15 in which attribute information is hierarchically classified, and calculates a score for each attribute information piece included in the extracted search target information piece using a predetermined score function.

[0028] The search result range is set in advance by the user. The search result range is information that indicates the range of the number of search target information that can be obtained by extraction that the user desires. There are two score functions: a contraction score function and an expansion score function.

[0029] The reduced score function is a function used to reduce the number of pieces of search target information when the number of pieces of search target information obtained by extraction is larger than the search result range. The score calculation unit 12 calculates a score using the reduced score function for attribute information that has attribute information (leaf nodes) in a lower layer (lower level). The reduced score function is, for example, Equation 1.

[0030] (Number 1) S1(i)=(w1×f1i(o))+(w2×f2i(d))+(w3×f3i(r)) S1(i): Reduced score i: Identifier that identifies attribute information w1: Weighting coefficient of element function f1i(o) f1i(o): A function that calculates the value for the order o in which attribute information is input. w2: Weighting coefficient of element function f2i(d) f2i(d): A function that calculates the value for the distance d from the leaf node. w3: Weighting coefficient of element function f3i(r) f3i(r): A function that calculates the division ratio r for the extracted attribute information

[0031] The expanded score function is a function used to expand the number of pieces of search target information when the number of pieces of search target information obtained by extraction is smaller than the search result range. The score calculation unit 12 refers to the knowledge base 15 and calculates a score for attribute information (node) in an upper layer (higher rank) or attribute information (node) in the same layer (same rank) using the expanded score function. The expanded score function is, for example, Equation 2.

[0032] (Number 2) S2(i)=(w1×f1i(o))+(w4×f4i(s)) S2(i): Expanded score w4: Weighting coefficient of element function f4i(s) f4i(s): A function that calculates the value for the attribute information similarity s

[0033] The element function f1i(o) is a function that returns a larger value the later the attribute information of the search condition is input. The reason why it returns a larger value the later the input order is, is because the later the attribute information is input, the higher the uncertainty becomes, so it is better to narrow down the search. The element function f1i(o) is, for example, Equation 3.

[0034] (Number 3) f1i(o)=1-1 / (o+1) o: Attribute information input order

[0035] For example, if the attribute information is entered in the order male, age 30s, and red, then male is entered first, so o=1. Age 30s is entered second, so o=2. Red is entered third, so o=3. Also, glasses is not entered, so o=4 (or ∞).

[0036] Then, using the element function f1i(o), a value is calculated for each attribute information. The calculation results are 1 / 2 for male, 2 / 3 for those in their 30s, 3 / 4 for red, and 4 / 5 (or ≒ 1) for those wearing glasses.

[0037] The weighting coefficient w1 is a value greater than 0 and equal to or less than 1. The weighting coefficient w1 of the element function f1i(o) is determined by experiment, simulation, or the like.

[0038] The element function f2i(d) is a function that calculates a value for the distance from a node to a leaf node in the knowledge base 15. The greater the distance between the node corresponding to the attribute information and the leaf node, the higher the ambiguity, and therefore the higher the possibility of narrowing down. The function f2i(d) is, for example, Equation 4.

[0039] (Number 4) f2i(d)=1-1 / (d+1) d: distance between a node and a leaf node

[0040] For example, if the attribute information is male, age 30, red, and glasses, then there is no leaf node below male in the knowledge base in Figure 2, so d = 0 is set. There is also no leaf node below 30's, so d = 0 is set. Red has a leaf node two levels below, so d = 2 is set. Glasses also has a leaf node one level below, so d = 1 is set.

[0041] Then, the element function f2i(d) is used to calculate a value for each attribute information. The calculation results are 0 for male, 0 for those in their 30s, 2 / 3 for red, and 1 / 2 for glasses.

[0042] The weighting coefficient w2 is a value greater than 0 and equal to or less than 1. The weighting coefficient w2 of the element function f2i(d) is determined by experiment, simulation, or the like.

[0043] The element function f3i(r) is a function that calculates the division ratio r for the extracted attribute information. The search target information extracted using the attribute information at the lower level is divided as evenly as possible. The more evenly the division, the higher the ability to narrow down the results. The function f3i(r) is, for example, equation 5.

[0044]

number

[0045] For example, the extracted search target information is divided as evenly as possible (standard division). If the nine pieces of extracted search target information shown in Figure 3 are divided into two, they will be divided into five pieces and four pieces. On the other hand, if the nine pieces of extracted search target information shown in Figure 3 are divided into three, they can be divided evenly into three pieces each.

[0046] Therefore, since there are three groups, k = 3 (j = 1, 2, 3). Also, the standard proportion of each group, s j So s1=3 / 9, s2=3 / 9, s3=3 / 9.

[0047] Next, we will explain the percentage rj of the number of search target information items for grapes to the total number. For example, if the attribute information is red, in the knowledge base of Figure 2, there are three attribute information items (true red, dark red, and light coral) in the layer below red.

[0048] The deep red substratum has three attributes (bright red, orange-red, crimson). The dark red substratum has three attributes (dark red, brown, firebrick). The light coral substratum has three attributes (light coral, Indian red, salmon).

[0049] Since the search target information related to person IDs 1 and 2 is associated with bright red and deep red, which are located below bright red, the proportion r1 of bright red in the total number is 2 / 9. Since the search target information related to person IDs 3, 4, 5, and 6 is associated with dark red, brown, and fire brick, which are located below dark red, the proportion r2 of dark red in the total number is 4 / 9. Since the search target information related to person IDs 7, 8, and 9 is associated with light coral and salmon, which are located below light coral, the proportion r3 of light coral in the total number is 3 / 9. Therefore, the element function f3i(r) when the attribute information is red is expressed as equation 6.

[0050]

number

[0051] Furthermore, when the attribute information is glasses, the element function f3i(r) is expressed as Equation 7.

[0052]

number

[0053] The weighting coefficient w3 is a value greater than 0 and equal to or less than 1. The weighting coefficient w3 of the element function f3i(r) is determined by experiment, simulation, or the like.

[0054] The element function f4i(s) first calculates the similarity by combining the attribute information of the search criteria with the attribute information at a higher or same node as the attribute information of the search criteria, and the maximum value of the calculated similarities is taken as the similarity s. The more similar the attribute information is, the more likely the user will select and respond with similar attribute information. The function f4i(s) is, for example, expressed as equation 8.

[0055] (Number 8) f4i(s)=s=maxSim(a n ,a m ) n, m: Identifiers that identify attribute information a n : Attribute information of search criteria a m : Attribute information at a higher or same node as the attribute information of the search criteria Sim(a n ,a i ): A function that calculates the similarity of attribute information (e.g., cosine function)

[0056] The similarity of combinations is calculated as follows, for example: Sim(male, 40s) = 0, Sim(30s, 40s) = 0.8, Sim(red, 40s) = 0, Sim(male, female) = 0.2, Sim(30s, female) = 0, Sim(red, female) = 0.3...

[0057] Next, calculate the maximum similarity for each attribute. If the attribute is in their 40s, then max{0,0.8,0}=0.8=f4i(0.8). If the attribute is female, then max{0.2,0,0.3}=0.3=f4i(0.3).

[0058] The weighting coefficient w4 is a value greater than 0 and equal to or less than 1. The weighting coefficient w4 of the element function f4i(s) is determined by experiment, simulation, or the like.

[0059] The question generation unit 13 selects attribute information based on the calculated score, and generates question information representing a question to be presented to the user using the selected attribute information. Specifically, the question generation unit 13 first compares the scores calculated for each attribute information and selects the attribute information corresponding to the highest score. Next, the question generation unit 13 generates question information representing a question to be presented to the user using the selected attribute information.

[0060] The search condition generating unit 14 reflects the attribute information included in the user's answer to the question information in the search conditions, and generates new search conditions.

[0061] In this manner, in the embodiment, the search conditions are updated based on the user's response to the question, and the search is performed using the updated search information, so that search results can be obtained efficiently.

[0062] [System Configuration] The configuration of the search device 10 in the embodiment will be described more specifically with reference to Fig. 4. Fig. 4 is a diagram showing an example of a system including a search device.

[0063] As shown in FIG. 4, a system 40 in this embodiment includes a search device 10, a knowledge base 15, and an input / output device 41.

[0064] The search device 10 is, for example, an information processing device such as a CPU (Central Processing Unit), a programmable device such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a circuit equipped with one or more of these, a server computer, a personal computer, or a mobile terminal.

[0065] The input / output device 41 has a user interface, and includes an input unit through which the user inputs information, and an output unit through which images, sounds, etc. are output to the user. The input unit is, for example, an input device having a keyboard, a mouse, a touch panel, etc. The output unit is, for example, an image display device using a liquid crystal, an organic EL (Electro Luminescence), or a CRT (Cathode Ray Tube). Furthermore, the image display device may also include an audio output device such as a speaker. The output unit may also be a printing device such as a printer.

[0066] The search target extraction unit 11, score calculation unit 12, question generation unit 13, search condition generation unit 14, and knowledge base 15 included in the search device 10 have already been described, so a description of these will be omitted.

[0067] [Device operation] The operation of the search device in the embodiment will be described with reference to FIG. 5. FIG. 5 is a diagram for explaining an example of the operation of the search device. In the following description, the diagram will be referenced as appropriate. In addition, in the embodiment, a search method is implemented by operating the search device. Therefore, the description of the search method in the embodiment will be replaced by the following description of the operation of the search device.

[0068] First, data is read from the knowledge base 15 (step A1). Next, the search target extraction unit 11 acquires initial search conditions at the start of the search (step A2). Specifically, in step A2 at the start of the search, document information created by the user is analyzed using a known document analysis tool, etc., to acquire attribute information of the search conditions. For example, a document such as "gender is male, age is around 30s, and clothing color is red" is acquired, analyzed, and attribute information of the search conditions such as gender: male, age: 30s, and clothing color: red is acquired.

[0069] Furthermore, in step A2 after the search conditions have been updated, the search target extraction unit 11 acquires the updated search information.

[0070] Next, the search target extraction unit 11 uses the attribute information of the search conditions to refer to the attribute information associated with the search target information, extracts search target information that matches one or more of the attribute information of the search conditions, and sets this search target information (dataset) (step A3).

[0071] Next, the search target extraction unit 11 uses a search condition having one or more attribute information to refer to a dataset having search target information in which an image is associated with one or more attribute information, and extracts search target information having attribute information that matches the attribute information of the search condition (step A4).

[0072] The score calculation unit 12 determines whether the number of pieces of search target information is within a preset search result range (step A5). If the number of pieces of search target information is not within the search result range, the score calculation unit 12 refers to a knowledge base in which attribute information is hierarchically classified, and calculates a score for each piece of attribute information included in the extracted search target information using a predetermined score function.

[0073] Specifically, when the number of pieces of search target information obtained by extraction is greater than the search result range (step A5: calculate reduced score), the score calculation unit 12 calculates a score for attribute information having attribute information (leaf node) in a lower layer (lower level) using a reduced score function (step A6). The reduced score function is, for example, Equation 1.

[0074] Next, the question generation unit 13 selects attribute information based on the calculated score, and generates question information representing a question to be presented to the user using the selected attribute information (step A7). Specifically, in step A7, the question generation unit 13 compares the scores calculated for each attribute information in step A6, and selects the attribute information corresponding to the highest score. Next, the question generation unit 13 generates question information representing a question to be presented to the user using the selected attribute information.

[0075] Furthermore, if the number of pieces of search target information obtained by extraction is smaller than the search result range (step A5: calculate expanded score), the score calculation unit 12 calculates a score for the attribute information (node) in the upper layer (higher rank) or the attribute information (node) in the same layer (same rank) using an expanded score function (step A8). The expanded score function is, for example, Equation 2.

[0076] Next, the question generation unit 13 selects attribute information based on the calculated score, and generates question information representing a question to be presented to the user using the selected attribute information (step A9). Specifically, in step A9, the question generation unit 13 compares the scores calculated for each attribute information in step A8, and selects the attribute information corresponding to the highest score. Next, the question generation unit 13 generates question information representing a question to be presented to the user using the selected attribute information.

[0077] Next, the question generation unit 13 outputs the question information to the input / output device 41 (step A10). Next, the search condition generation unit 14 acquires answer information representing the user's answer to the question information (step A11).

[0078] Next, the search condition generation unit 14 determines whether or not to update the search conditions (step A12). If the search conditions are to be updated (step A12: Yes), the search condition generation unit 14 reflects the attribute information in the search conditions and generates new search conditions (step A13). If the search conditions are not to be updated (step A12: No), the process proceeds to step A5 and question information is generated again.

[0079] Next, the search condition generation unit 14 updates the data set (step A14). Specifically, in step A14, the search condition generation unit 14 extracts search target information having the attribute information used in updating the search conditions, and sets the extracted search target information as a new data set.

[0080] Then, the process proceeds to step A2, where the search continues using the updated search criteria and the updated data set. If the number of extracted search target information pieces is within the search result range, the search process ends (step A5: search end).

[0081] [Effects of the embodiment] According to the embodiment described above, search conditions are updated based on the user's answers to questions, and the search is performed using the updated search information, so search results can be obtained efficiently. By updating the answers to questions and the search conditions, the user can also more accurately grasp the attribute information of the search target.

[0082] [program] The program in the embodiment may be any program that causes a computer to execute steps A1 to A14 shown in Fig. 5. By installing and executing this program on a computer, the search device and search method in the embodiment can be realized. In this case, the processor of the computer functions as a search target extraction unit 11, a score calculation unit 12, a question generation unit 13, and a search condition generation unit 14, and performs processing.

[0083] The program in the embodiment may be executed by a computer system constructed by a plurality of computers, in which case, for example, each computer may function as one of the search target extraction unit 11, score calculation unit 12, question generation unit 13, and search condition generation unit 14.

[0084] [Physical configuration] A computer that implements the search device by executing a program in the embodiment will now be described with reference to Fig. 6. Fig. 6 is a diagram illustrating an example of a computer that implements the search device in the embodiment.

[0085] As shown in FIG. 6, the computer 110 includes a CPU (Central Processing Unit) 11 1, a main memory 112, a storage device 113, an input interface 114, and a display A controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so that they can communicate data with each other. The computer 110 may include a GPU or an FPGA in addition to the CPU 111 or instead of the CPU 111.

[0086] The CPU 111 loads the program (code) of this embodiment stored in the storage device 113 into the main memory 112 and executes it in a predetermined order to perform various calculations. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory). The program of this embodiment is provided in a state stored in a computer-readable recording medium 120. The program of this embodiment may be distributed over the Internet connected via the communication interface 117. The recording medium 120 is a non-volatile recording medium.

[0087] Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0088] The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, reads programs from the recording medium 120, and writes processing results from the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and other computers.

[0089] Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as flexible disks, or optical recording media such as CD-ROMs (Compact Disk Read Only Memory).

[0090] The search device 10 in the embodiment can be realized by using hardware corresponding to each part, instead of a computer on which a program is installed. Furthermore, the search device 10 may be partially realized by a program and the remaining part by hardware. [Example]

[0091] In the embodiment, a case where a person image is searched for will be described. In the embodiment, it is assumed that the search result range is set to 1 or more and 2 or less.

[0092] The search target extraction unit 11 acquires search conditions (step A2). For example, the search condition attribute information acquired is gender: male, age: 30s, and clothing color: red.

[0093] Next, the search target extraction unit 11 uses the attribute information of male, 30s, and red as the attribute information of the search conditions, refers to the attribute information of each piece of search target information in the dataset, and extracts search target information having attribute information that matches the attribute information of the search conditions (step A4). In this embodiment, it is assumed that the search target information shown in Figure 3 is extracted.

[0094] Specifically, search target information that matches the search criteria (male, 30s, red) is extracted from the search target information shown in Fig. 3. In this embodiment, search target information corresponding to person image IDs 1, 2, and 7 is selected. The number of pieces of search target information extracted is three.

[0095] Next, the score calculation unit 12 determines whether the number of extracted pieces of search target information is within the search result range (step A5). The number of extracted pieces of search target information is three, which is greater than the search result range of two (3>2). Therefore, a reduced score is calculated (step A5: calculate reduced score).

[0096] Next, the score calculation unit 12 refers to the knowledge base 15 and calculates the reduced score of the attribute information in the lower node (step A6).

[0097] For each piece of attribute information, for example, the reduced score function S1(i) of Equation 9 is used to calculate the score shown in Equation 10.

[0098] (Number 9) S1(i)=(0.3×f1i(o))+(0.3×f2i(d))+(0.4×f3i(r))

[0099] (Number 10) S1 (red) = 0.3 x 3 / 4 + 0.3 x 2 / 3 + 0.4 x 7 / 9 ≒ 0.726 S1 (glasses)=0.3×1 +0.3×1 / 2+0.4×3 / 9≒0.583 ...

[0100] Next, the question generator 13 selects the attribute information with the highest score from the calculated scores. Since red has the highest score in equation 10, the question generator 13 selects the attribute information of red.

[0101] Next, the question generator 13 acquires attribute information of true reds, dark reds, and light corals, which are located below the attribute information of red.Then, the question generator 13 generates question information to be presented to the user, for example, to cause the output unit to display a message such as "Which red is this closest to, true reds, dark reds, or light corals?" (Step A7).

[0102] Next, the question generation unit 13 outputs the question information to the output device to present the question to the user (step A10). The question is displayed as shown in question display 71 in Fig. 7. However, the question is not limited to question display 71. Fig. 7 is a diagram for explaining questions and answers.

[0103] Next, the search condition generation unit 14 acquires answer information representing the user's answer to the question information (step A11). In this embodiment, it is assumed that the user answers "dark reds." The answer is displayed as shown in answer display 72 in FIG. 7. However, the answer is not limited to answer display 72.

[0104] Next, the search condition generation unit 14 determines whether to update the search conditions (step A12). If the search conditions are to be updated (step A12: Yes), the search condition generation unit 14 updates the red of the search conditions to dark red (step A13). If the search conditions are not to be updated (step A12: No), the process proceeds to step A5, where question information is generated again and the question is presented.

[0105] Next, the search condition generation unit 14 updates the data set (step A14). In this embodiment, search target information that does not have dark red is excluded. As shown in FIG. 8, the data set contains only search target information corresponding to person IDs 3 to 6.

[0106] Next, the process moves to step A2, where the search target extraction unit 11 acquires updated search conditions. As attribute information for the updated search conditions, gender: male, age: 30s, and clothing color: dark red are acquired.

[0107] Next, the search target extraction unit 11 sets the updated data set (step A3). Next, the search target extraction unit 11 extracts search target information having attribute information that matches the updated search criteria (male, 30s, dark red) from the updated data set (step A4). However, since no search target information is extracted, the number of extracted search target information pieces is 0.

[0108] Next, the score calculation unit 12 determines whether the number of extracted pieces of search target information is within the search result range (step A5). Since the number of extracted pieces of search target information is 0, which is smaller than the search result range of 1 (0<1), the expanded score is calculated (step A5: calculate expanded score).

[0109] Next, the score calculation unit 12 refers to the knowledge base 15 and calculates the expanded score of the attribute information at the higher or same node (step A8).

[0110] For each piece of attribute information, a score is calculated using, for example, the expanded score function S2(i) of Equation 11.

[0111] (Number 11) S2(i)=(0.5×f1i(o))+(0.5×f4i(s))

[0112] First, the element function f1i(o) for men is f1i(1) = 1 / 2 because men are the first to be entered. Also, the element function for people in their 30s is f1i(2) = 2 / 3 because people in their 30s are the second to be entered.

[0113] Next, the element function f4i(s) is calculated. The similarity is calculated by combining the attribute information of the search criteria with the attribute information of the higher or same node of the attribute information of the search criteria. The similarity is as follows: Sim(male, female) = 0.2, Sim(30s, female) = 0, Sim(male, 40s) = 0, Sim(30s, 40s) = 0.8.

[0114] Next, the maximum similarity between women (women as an extension of men) who are at the same rank as men is 0.2, and the maximum similarity between people in their 40s (40s as an extension of 30s) who are at the same rank as people in their 30s is 0.8.

[0115] Next, using the calculation results of the element functions f1i(o) and f4i(s), an expanded score function S2(i) is calculated for each attribute information as shown in Equation 12.

[0116] (Number 12) S2 (female) =0.5×1 / 2+0.5×0.2=0.35 S2 (40s)=0.5×2 / 3+0.5×0.8≒0.734

[0117] Next, the question generation unit 13 selects the attribute information with the highest score from the calculated scores. In Equation 12, the score for the 40s is the highest, so the attribute information for the 40s is selected.

[0118] Next, the question generator 13 acquires attribute information for people in their 40s. Then, the question generator 13 generates question information to be presented to the user, such as "Could you be in your 40s?" (Step A9).

[0119] Next, the question generator 13 outputs the question information to the output device to present the question to the user (step A10). The question is displayed as shown in question display 73 in Fig. 7. However, the question is not limited to question display 73.

[0120] Next, the search condition generation unit 14 acquires answer information representing the user's answer to the question information (step A11). In this embodiment, it is assumed that the user answers that he or she is in his or her 40s. The answer is displayed as shown in answer display 74 in FIG. 7. However, the answer is not limited to answer display 74.

[0121] Next, the search condition generation unit 14 determines whether to update the search conditions (step A12). If the search conditions are to be updated (step A12: Yes), the search condition generation unit 14 updates the search conditions by adding "40s" to the search conditions (step A13). If the search conditions are not to be updated (step A12: No), the process proceeds to step A5 and the question is presented again.

[0122] Next, the search condition generating unit 14 updates the data set (step A14). In this embodiment, search target information for people in their 40s is added. However, since information for people in their 40s already exists, it is not updated.

[0123] Next, the process proceeds to step A2, where the search target extraction unit 11 acquires updated search conditions. For example, the attribute information acquired for the updated search conditions is gender: male, age: 30s or 40s, and clothing color: dark red.

[0124] Next, the search target extraction unit 11 sets a data set (step A3). Next, the search target extraction unit 11 extracts search target information that matches the search criteria (male, 30s or 40s, dark red) from the data set (step A4). In this embodiment, person image IDs 4, 5, and 6 are selected. The number of extracted search target information is three.

[0125] Next, the score calculation unit 12 determines whether the number of extracted pieces of search target information is within the search result range (step A5). The number of extracted pieces of search target information is three, which is greater than the two set as the search result range (3>2). Therefore, the reduced score is calculated (step A5: calculate reduced score).

[0126] Next, the score calculation unit 12 refers to the knowledge base 15 and calculates the reduced scores of the attributes in the lower nodes (step A6).

[0127] For each piece of attribute information, a score is calculated using the reduced score function S1(i) of equation 9. Since the attribute information in the lower node is dark red and glasses, the element functions f1i(o) for dark red and glasses are calculated. Since dark red is the third input, f1i(3) = 3 / 4. Since glasses is not input, f1i(4 or ∞) = 1.

[0128] Next, calculate the element function f2i(d) for dark red and glasses. Since there is a leaf node one level below dark red, f2i(1) = 1 / 2. Since there is also a leaf node one level below glasses, f2i(1) = 1 / 2.

[0129] Next, the element functions f3i(r) for dark red and glasses are calculated. In this embodiment, the number of data is 4, the number of lower nodes is 3, and the standard division is 2, 1, 1, so the element functions f3i(r) for dark red and glasses are calculated as shown in Equation 13.

[0130]

number

[0131] Next, using the calculation results of the element functions f1i(o), f2i(d), and f3i(r), a reduced score function S1(i) is calculated for each attribute information as shown in Equation 14.

[0132] (Number 14) S1 (dark red)=0.3×3 / 4+0.3×1 / 2+0.4×1=0.775 S1(glasses)=0.3×1 +0.3×1 / 2+0.4×1=0.85 ...

[0133] Next, the question generator 13 selects the attribute information with the highest score from the calculated scores. Since the score for glasses is the highest in Equation 14, the attribute information for glasses is selected.

[0134] Next, the question generator 13 acquires attribute information of the glasses. Then, the question generator 13 generates question information to be presented to the user, such as "What kind of glasses do you wear? None, corrective glasses, sunglasses" (step A9).

[0135] Next, the question generation unit 13 outputs the question information to the output device to present the question to the user (step A10). The question is displayed as shown in question display 75 in Fig. 7. However, the question is not limited to question display 75.

[0136] Next, the search condition generation unit 14 acquires answer information representing the user's answer to the question information (step A11). In this embodiment, it is assumed that the user answers "sunglasses." The answer is displayed as shown in answer display 76 in FIG. 7. However, the answer is not limited to answer display 76.

[0137] Next, the search condition generation unit 14 determines whether to update the search conditions (step A12). If the search conditions are to be updated (step A12: Yes), the search condition generation unit 14 adds sunglasses to the search conditions (step A13). If the search conditions are not to be updated (step A12: No), the process proceeds to step A5, where question information is generated again and the question is presented.

[0138] Next, the search condition generation unit 14 updates the data set (step A14). In this embodiment, search target information that does not have sunglasses is excluded. The data set contains only search target information corresponding to person ID 6 shown in FIG. 8. FIG. 8 is a diagram for explaining the relationship between search target information and attribute information.

[0139] Next, the process proceeds to step A2, where the search target extraction unit 11 acquires updated search conditions. For example, the attribute information acquired for the updated search conditions may be: gender: male, age: 30s or 40s, clothing color: dark red, and glasses: sunglasses.

[0140] Next, the search target extraction unit 11 sets a data set (step A3). Next, the search target extraction unit 11 extracts search target information that matches the search criteria (male, 30s or 40s, dark red, sunglasses) from the data set (step A4). In this embodiment, a person image ID6 is selected. The number of extracted search target information items is one.

[0141] Next, the score calculation unit 12 determines whether the number of extracted pieces of search target information is within the search result range (step A5). Since the number of extracted pieces of search target information is 1 (=x), it is within the search result range (1≦x≦2). Therefore, the search process ends (step A5: search end).

[0142] [Note] The following supplementary notes are further provided with respect to the above-described embodiments. Some or all of the above-described embodiments can be expressed by (Supplementary Note 1) to (Supplementary Note 12) described below, but are not limited to the following descriptions.

[0143] (Appendix 1) a search target extraction unit that uses search criteria having one or more pieces of attribute information to refer to a dataset having search target information in which images are associated with one or more pieces of attribute information, and extracts search target information having the attribute information that matches the attribute information of the search criteria; a score calculation unit that, when the number of pieces of extracted search target information is not within a predetermined search result range, refers to a knowledge base in which attribute information is hierarchically classified, and calculates a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation unit that selects attribute information based on the calculated score and generates question information representing a question to be presented to a user using the selected attribute information; a search condition generation unit that reflects attribute information represented by the user's answer to the question information in the search conditions to generate new search conditions; A search device having the above configuration.

[0144] (Appendix 2) 10. The search device according to claim 1, when the number of pieces of extracted search target information is smaller than the search result range, the score calculation unit refers to the knowledge base and calculates a score using an expansion score function for expanding the search results for each piece of attribute information of a higher-level node or a same-level node. Search device.

[0145] (Appendix 3) 3. The search device according to claim 1, when the number of pieces of extracted search target information is greater than the search result range, the score calculation unit refers to the knowledge base and calculates a score using a reduction score function for reducing the search result for each piece of attribute information of a lower node; Search device.

[0146] (Appendix 4) 4. A search device according to any one of claims 1 to 3, The search target information is information in which identification information for identifying the search target information, the attribute information, and a person image related to the search target information are associated with each other. Search device.

[0147] (Appendix 5) a search target extraction step of referring to a dataset having search target information in which an image is associated with one or more pieces of attribute information using search criteria having one or more pieces of attribute information, and extracting search target information having the attribute information that matches the attribute information of the search criteria; a score calculation step of, when the number of pieces of extracted search target information is not within a predetermined search result range, referring to a knowledge base in which attribute information is hierarchically classified, and calculating a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation step of selecting attribute information based on the calculated score and generating question information representing a question to be presented to a user using the selected attribute information; a search condition generating step of generating new search conditions by reflecting attribute information represented by the user's answer to the question information in the search conditions; A search method having the following.

[0148] (Appendix 6) 10. The search method according to claim 5, In the score calculation step, if the number of pieces of extracted search target information is smaller than the search result range, the knowledge base is referenced and a score is calculated using an expansion score function for expanding the search results for each piece of attribute information of a higher-level node or a same-level node. How to search.

[0149] (Appendix 7) 7. The search method according to claim 5 or 6, In the score calculation step, if the number of pieces of information to be searched that have been extracted is greater than the range of search results, the knowledge base is referenced and a score is calculated using a reduction score function for reducing the search results for each piece of attribute information of a lower node. How to search.

[0150] (Appendix 8) 8. A search method according to any one of appendices 5 to 7, comprising: The search target information is information in which identification information for identifying the search target information, the attribute information, and a person image related to the search target information are associated with each other. How to search.

[0151] (Appendix 9) On the computer, a search target extraction step of referring to a dataset having search target information in which an image is associated with one or more pieces of attribute information using search criteria having one or more pieces of attribute information, and extracting search target information having the attribute information that matches the attribute information of the search criteria; a score calculation step of, when the number of pieces of extracted search target information is not within a predetermined search result range, referring to a knowledge base in which attribute information is hierarchically classified, and calculating a score for each piece of attribute information included in the extracted search target information using a predetermined score function; a question generation step of selecting attribute information based on the calculated score and generating question information representing a question to be presented to a user using the selected attribute information; a search condition generating step of generating new search conditions by reflecting attribute information represented by the user's answer to the question information in the search conditions; A program containing instructions to execute

[0152] (Appendix 10) 10. The program of claim 9, In the score calculation step, if the number of pieces of extracted search target information is smaller than the search result range, the knowledge base is referenced and a score is calculated using an expansion score function for expanding the search results for each piece of attribute information of a higher-level node or a same-level node. program.

[0153] (Appendix 11) 11. The program according to claim 9 or 10, In the score calculation step, if the number of pieces of information to be searched that have been extracted is greater than the range of search results, the knowledge base is referenced and a score is calculated using a reduction score function for reducing the search results for each piece of attribute information of a lower node. program.

[0154] (Appendix 12) 12. The program according to any one of appendices 9 to 11, The search target information is information in which identification information for identifying the search target information, the attribute information, and a person image related to the search target information are associated with each other. program.

[0155] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Industrial Applicability]

[0156] As described above, according to the present invention, search conditions can be updated based on the user's answers to questions, and search results can be obtained efficiently. The present invention is useful in fields where efficient search execution is required. [Explanation of symbols]

[0157] 10 Search Device 11 Search target extraction section 12 Score calculation section 13 Question generation part 14 Search Criteria Generation Unit 15 Knowledge Base 40 Systems 41 Input / Output Devices 110 Computer 111 CPU 112 main memory 113 Storage device 114 Input Interface 115 Display Controller 116 Data Reader / Writer 117 Communication Interface 118 Input Devices 119 Display Device 120 Recording Media 121 Bus

Claims

1. An acquisition means for acquiring search conditions related to a search target; an extraction means for extracting search target information from a data set using the search conditions; a selection means for selecting, from among attribute information identified in accordance with information included in the search criteria, attribute information to be used to increase the number of pieces of search target information based on a score calculated for the attribute information, when the number of pieces of extracted search target information is smaller than the search result range; an output means for outputting presentation information relating to the selected attribute information; an update means for updating the search conditions based on a user's input for the presented information; An information processing device comprising:

2. the output means outputs the presentation information related to the selected attribute information by referring to a database in which the attribute information is structurally classified. The information processing device according to claim 1 .

3. The search target information is information in which the attribute information is associated with an image related to the search target.

3. The information processing device according to claim 1 or 2.

4. a calculation means for calculating a score by referring to a database and using an expanded score function for expanding the search results for each of the attribute information of the higher-level node or the same-level node when the number of the extracted search target information pieces is smaller than the search result range; The information processing device according to claim 3 , further comprising:

5. when the number of pieces of extracted search target information is greater than the search result range, the calculation means refers to the database and calculates a score using a reduction score function for reducing the search result for each piece of attribute information of a lower node; The information processing device according to claim 4 .

6. The information processing device Obtain search criteria for the search target, extracting search target information from the dataset using the search conditions; If the number of pieces of extracted search target information is smaller than the search result range, select, from among the attribute information identified according to the information included in the search conditions, the attribute information to be used to increase the number of pieces of search target information based on a score calculated for the attribute information; outputting presentation information relating to the selected attribute information; updating the search criteria based on a user's input for the presented information; Information processing methods.

7. The information processing device, outputting the presentation information related to the attribute information selected by referring to a database in which the attribute information is structurally classified; The information processing method according to claim 6.

8. The search target information is information in which the attribute information is associated with an image related to the search target.

8. The information processing method according to claim 6 or 7.

9. On the computer, Obtain search conditions related to the search target, extracting search target information from a dataset using the search conditions; If the number of pieces of extracted information to be searched is smaller than the range of search results, the attribute information to be used to increase the number of pieces of information to be searched is selected from the attribute information identified in accordance with the information included in the search conditions based on a score calculated for the attribute information; outputting presentation information relating to the selected attribute information; updating the search conditions based on a user's input to the presented information; A program containing instructions.

10. The computer, outputting the presentation information related to the attribute information selected by referring to a database in which the attribute information is structurally classified; The program according to claim 9.

Images