Information processing device, data generation method, and program

Abstract

An information processing device according to the present disclosure is provided with: a management unit (11) for managing, in mutual association, a plurality of objects, at least one attribute whereby the objects are classified, and a certainty factor indicating the probability that an object has the attribute; a calculation unit (12) for using an attribute that has been designated as a search condition and a certainty factor that can be designated as a search condition for the attribute, and a certainty factor that is managed in association with an attribute identical or similar to the attribute designated as a search condition, in order to calculate a score indicating a degree of conformity of an object to the search conditions; a sorting unit (13) for sorting the scores so as to line up the plurality of objects in order of the sorted scores; a specifying unit (14) for specifying a certainty factor by which to change the order of the objects on the basis of a shift in the scores, of the plurality of objects, that change in accordance with a shift in the certainty factor that can be designated as a search condition; and a display control unit (15) for generating display data for displaying, in mutual association, the attribute that was designated as a search condition and the certainty factor by which the order of the objects is changed.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an analysis system, a data generation method, and a program. [Background technology]

[0002] In recent years, with the widespread use of surveillance cameras, they are installed in various locations. Footage captured by surveillance cameras is used, for example, in the investigation of various crimes. Specifically, police may search for a suspicious person based on eyewitness information from a huge amount of footage.

[0003] Patent Document 1 discloses the configuration of an information processing device that searches for target people according to search conditions that specify attributes in categories such as gender, hair color, and clothing color. The information processing device of Patent Document 1 specifies a degree of certainty that indicates the likelihood of satisfying the search conditions along with the search conditions that specify attributes, and displays people that satisfy the search conditions and the degree of certainty. For example, if "male" is specified as the attribute and 90% is specified as the degree of certainty, the information processing device displays as search results people whose degree of certainty that they are classified as "male" is 90% or more. In other words, the information processing device does not display people whose degree of certainty that they are classified as "male" is less than 90%. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2020 / 255307 Summary of the Invention [Problem to be solved by the invention]

[0005] By specifying the attributes and confidence levels disclosed in Patent Document 1 and displaying people who exceed the specified confidence level in descending order of confidence level, search results that are easy for the user to analyze can be obtained. For example, by clarifying the impact that changes in confidence level have on changes in search results, it becomes possible to analyze the relationship between confidence level and search results. In such cases, there is a need for the development of a tool or device that allows users to easily recognize the impact that changes in confidence level have on changes in search results.

[0006] An object of the present disclosure is to provide an information processing device, an analysis system, a data generation method, and a program that enable easy recognition of the effect that a change in confidence factor has on a change in search results. [Means for solving the problem]

[0007] An information processing device according to a first aspect of the present disclosure comprises: a management means for managing a plurality of objects, at least one attribute by which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search criteria using an attribute specified as a search criteria, a confidence level that can be specified as a search criteria for that attribute, and a confidence level that is managed in association with an attribute that is identical to or similar to the attribute specified as the search criteria; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; an identification means for identifying a confidence level for changing the order of the objects based on a change in the scores of the plurality of objects, which changes in accordance with a change in the confidence level that can be specified as the search criteria; and a display control means for generating display data that displays the attribute specified as the search criteria in association with the confidence level for changing the order of the objects.

[0008] An analysis system according to a second aspect of the present disclosure comprises an information processing device having: a management means for managing a plurality of objects, at least one attribute by which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search conditions using an attribute specified as a search condition, a confidence level that can be specified as a search condition for that attribute, and a confidence level that is managed in association with an attribute that is the same as or similar to the attribute specified as the search condition; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; an identification means for identifying a confidence level for changing the order of the objects based on a change in the scores of the plurality of objects, which changes in accordance with a change in the confidence level that can be specified as the search condition; and a display device for displaying the display data in association with the attribute specified as the search condition.

[0009] A data generation method according to a third aspect of the present disclosure manages a plurality of objects, at least one attribute by which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; calculates a score indicating the degree of match of the object with the search criteria using an attribute specified as a search criteria, the confidence level that can be specified as a search criteria for that attribute, and the confidence level that is managed in association with an attribute that is identical to or similar to the attribute specified as the search criteria; sorts the scores and arranges the plurality of objects in order of the sorted scores; identifies a confidence level for changing the order of the objects based on the progress of the scores of the plurality of objects, which changes in accordance with the progress of the confidence level that can be specified as the search criteria; and generates display data that displays the attribute specified as the search criteria in association with the confidence level for changing the order of the objects.

[0010] A program according to a fourth aspect of the present disclosure causes a computer to: manage multiple objects, at least one attribute by which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; calculate a score indicating the degree to which the object matches the search criteria using an attribute specified as a search criteria, the confidence level that can be specified as a search criteria for that attribute, and the confidence level associated with an attribute that is identical to or similar to the attribute specified as the search criteria; sort the scores and arrange the multiple objects in order of the sorted scores; identify a confidence level for changing the order of the objects based on the progress of the scores of the multiple objects, which changes in accordance with the progress of the confidence level that can be specified as the search criteria; and generate display data that displays the attribute specified as the search criteria in association with the confidence level for changing the order of the objects. [Effects of the Invention]

[0011] The present disclosure can provide an information processing device, an analysis system, a data generation method, and a program that can easily recognize the effect that a change in confidence factor has on a change in search results. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a configuration diagram of an information processing device according to a first embodiment. [Figure 2] FIG. 2 is a diagram showing a processing flow of a data generating method according to the first embodiment. [Figure 3] FIG. 10 is a configuration diagram of an information processing device according to a second embodiment. [Figure 4] FIG. 10 is a diagram illustrating data managed in a management unit according to the second embodiment. [Figure 5] FIG. 10 is a diagram showing a screen image according to the second embodiment. [Figure 6] FIG. 10 is a diagram illustrating the change of order in the result display area according to the second embodiment. [Figure 7]FIG. 10 is a diagram showing the relationship between the confidence level and the score of each object according to the second embodiment. [Figure 8] FIG. 11 is a diagram showing the transition of the rank of an object when the confidence level is 0 and the rank of an object when the confidence level is 1 according to the second embodiment. [Figure 9] FIG. 10 is a diagram showing a flow of processing for identifying intersections of line segments according to the second embodiment. [Figure 10] FIG. 10 is a diagram showing a screen image according to the second embodiment. [Figure 11] 1A and 1B are configuration diagrams of information processing devices according to respective embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0013] Embodiment 1 Hereinafter, embodiments of the present invention will be described with reference to the drawings. A configuration example of an information processing device 10 according to the first embodiment will be described with reference to Fig. 1. The information processing device 10 may be a computer device that operates when a processor executes a program stored in a memory.

[0014] The information processing device 10 has a management unit 11, a calculation unit 12, a sorting unit 13, an identification unit 14, and a display control unit 15. The management unit 11, the calculation unit 12, the sorting unit 13, the identification unit 14, and the display control unit 15 may be software or modules that perform processing by a processor executing a program stored in a memory. Alternatively, the management unit 11, the calculation unit 12, the sorting unit 13, the identification unit 14, and the display control unit 15 may be hardware such as a circuit or a chip.

[0015] The management unit 11 manages a plurality of objects, at least one attribute into which each object is classified, and a confidence level indicating the probability that the object has the attribute, in association with each other.

[0016] The object may be a person, an animal, a building, a structure, etc. Alternatively, the object may be a means of transportation such as a car, a bicycle, a train, etc.

[0017] The attributes by which objects are classified may be properties classified within categories such as gender, age, and clothing color. For example, in the gender category, male and female may be used as attributes. In the age category, age may be used as an attribute, such as teens, twenties, and thirties. In the clothing color category, colors such as red, blue, and yellow may be used. In the clothing color category, the same color may be further classified, for example, bright red, deep red, etc.

[0018] The confidence indicates the probability that the object has the attribute, or in other words, the confidence indicates the likelihood that the object has the specified attribute. The confidence may be expressed, for example, as a percentage (%) or as a decimal number greater than or equal to 0 and less than or equal to 1. When the confidence is expressed as a decimal number greater than or equal to 0 and less than or equal to 1, the confidence increases as the value increases.

[0019] The management unit 11 may hold a database that associates objects, attributes into which the objects are classified, and confidence levels that indicate the probability that the objects have the attributes.

[0020] The calculation unit 12 calculates a score indicating the degree of match of the object with the search criteria. Specifically, the calculation unit 12 uses an attribute specified as a search criterion, a confidence level of the attribute that can be specified as a search criterion, and a confidence level managed in association with an attribute that is the same as or similar to the attribute specified as a search criterion.

[0021] The search conditions may be input by, for example, a user of the information processing device 10. Alternatively, the search conditions may be input to the information processing device 10 from another computer device via a network. Alternatively, the information processing device 10 may determine the search conditions by analyzing voice, text, images, or the like.

[0022] The confidence level that can be specified as a search criterion may be, for example, a value that falls within a range of values ​​that can be set as a confidence level. For example, if the confidence level is expressed as a percentage, the confidence level that can be specified as a search criterion may be a value between 0 and 1. Alternatively, the confidence level that can be specified as a search criterion may be a value between any value between 0 and 1 and any value between 0 and 1.

[0023] The certainty factors associated with attributes that are the same as or similar to the attributes specified as search conditions are managed in the management unit 11. That is, the calculation unit 12 uses the attributes specified as search conditions to extract, from the database held by the management unit 11, certainty factors associated with attributes that are the same as or similar to the attributes specified as search conditions.

[0024] The score indicating the degree of match of the object with the search criteria may be such that the larger the value, the higher the degree of match of the object with the search criteria. For example, when multiple attributes and their certainties are specified as search criteria, the calculation unit 12 may calculate an overall score for the object by summing the score values ​​calculated for each attribute. In other words, the score for the object is a value obtained by taking multiple attributes into consideration or combining multiple attributes.

[0025] The sorting unit 13 sorts the scores and arranges the multiple objects in the order of the sorted scores. Sorting the scores may mean sorting from highest score to lowest score, or from lowest score to highest score. Sorting the multiple objects by the sorting unit 13 may be rephrased as, for example, sorting the multiple objects by the sorting unit 13 creating a ranking of the multiple objects in the order of their scores.

[0026] The identification unit 14 identifies a degree of certainty for changing the order of objects based on the transition of the scores of multiple objects that change according to the transition of the certainty that can be specified as a search condition. When the certainty specified as a search condition changes, the score of each object also changes. Therefore, when the score of an object changes, the order of objects arranged in order of score also changes. The identification unit 14 identifies a degree of certainty that is specified when the order of objects is changed.

[0027] The display control unit 15 generates display data that associates the attributes specified as search conditions with the confidence levels for changing the order of the objects. The display data may be displayed by a display device that is used as an integrated device with the information processing device 10, or by a display device that receives the display data via a network.

[0028] Next, the flow of processing of the data generating method in the information processing device according to the first embodiment will be described with reference to FIG.

[0029] First, the management unit 11 associates and manages multiple objects, at least one attribute by which each object is classified, and a confidence level indicating the probability that the object has the attribute (S11). Next, the calculation unit 12 calculates a score using the attribute specified as a search condition, the confidence level that the attribute can be specified as a search condition, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as a search condition (S12). The score indicates the degree to which the object matches the search condition (S12).

[0030] Next, the sorting unit 13 sorts the scores and arranges the multiple objects in the order of the sorted scores (S13). Next, the identification unit 14 identifies the confidence level for changing the order of the objects based on the transition of the scores of the multiple objects that changes according to the transition of the confidence level that can be specified as a search condition (S14). Next, the display control unit 15 generates display data that displays the attributes specified as search conditions in association with the confidence level for changing the order of the objects (S15).

[0031] As described above, the information processing device 10 identifies a certainty factor that will result in changing the order of objects sorted in score order when the certainty factor of a specified attribute changes. Furthermore, the information processing device 10 generates display data for displaying the certainty factor that will result in changing the order of objects on a display device. This allows an analyst or the like who analyzes the data to easily recognize the impact of a change in the certainty factor on the order of objects sorted in score order by visually checking the display data.

[0032] 1, the configuration in which the management unit 11 is included in the information processing device 10 has been described, but for example, the management unit 11 may be included in a device different from the information processing device 10. In this case, the calculation unit 12 of the information processing device 10 may acquire information managed by the management unit 11 included in the other device via a network.

[0033] (Embodiment 2) Next, a configuration example of the information processing device 20 according to the second embodiment will be described with reference to FIG. 3. The information processing device 20 has a configuration in which a search condition acquisition unit 21 is added to the information processing device 10. The information processing device 20 is connected to a display device 30. The display device 30 may be used integrally with the information processing device 20, that is, the display device 30 may be included in the information processing device 20. Alternatively, the information processing device 20 may communicate with the display device 30 via a network. The display device 30 displays the received display data. The display device 30 may be referred to as, for example, a display device or the like.

[0034] The management unit 11, calculation unit 12, sorting unit 13, identification unit 14, and display control unit 15 that constitute the information processing device 20 are similar to those of the information processing device 10, and therefore detailed description thereof will be omitted. Below, functions, operations, etc. of the information processing device 20 that are different from those of the information processing device 10, or detailed functions, operations, etc. of the information processing device 20 and the information processing device 10 will be described.

[0035] The search condition acquisition unit 21 acquires search conditions. For example, the search condition acquisition unit 21 may acquire search conditions input by a user of the information processing device 20 via an input interface or the like. The user may input attributes and certainty factors by text input or voice input using, for example, a keyboard, a touch panel, a microphone, or the like. For example, when a user inputs search conditions, an eyewitness to the person being searched for may determine the certainty factor, which is an attribute by which the person being searched for is classified. In this case, the input search conditions are determined according to the subjective opinion of the eyewitness.

[0036] Alternatively, the search condition acquisition unit 21 may specify search conditions using an input image. For example, when a user searches for or retrieves a person, the user inputs image data showing the person into the information processing device 20. The search condition acquisition unit 21 may specify attributes of the person displayed in the image by performing image analysis processing or image recognition processing on the input image data, and further calculate the certainty of the attributes.

[0037] The image analysis process or image recognition process may be performed using, for example, a learning model generated to learn attributes related to people and confidence levels indicating the probability that a person has those attributes, using multiple image data showing people as training data. The search condition acquisition unit 21 applies the input image data to the generated learning model to acquire the attributes of people displayed in the images and the confidence levels indicating the probability that the person has those attributes.

[0038] Next, the data managed by the management unit 11 will be described with reference to FIG. 4. FIG. 4 shows a database that uses people as objects and manages the attributes of people. h_1 to h_6 shown in the person column are identification information for identifying people. For example, the attribute of male or female is set in the gender category. For example, ages such as 30s, 40s, and 50s are set in the age category. For example, colors such as bright red, deep red, maroon, and navy blue are set in the clothing color category. For the glasses category, "Yes" is set if the person wears glasses, and "No" is set if the person does not wear glasses. The numerical values ​​shown next to each attribute indicate the probability that the person has that attribute or the certainty that the person has that attribute. Furthermore, the clothing color category may be divided into upper body clothing color, lower body clothing color, hat color, shoe color, etc. Attributes and certainty may be set for each of the upper body clothing color, lower body clothing color, hat color, and shoe color.

[0039] As shown in FIG. 4, for example, the certainty factor that person h_1 is male is 0.7, the certainty factor that person h_1 is in their 30s is 0.8, the certainty factor that person h_1 is wearing bright red clothing is 0.9, and the certainty factor that person h_1 is not wearing glasses is 0.9. Attributes and certainty factors are similarly associated with each other for other people. The certainty factor, expressed using a decimal point less than 1, indicates a higher certainty factor as the value increases. For example, this may be rephrased as saying that person h_1 has a 70 percent probability of being male and an 80% probability of being in their 30s.

[0040] Here, the persons h_1 to h_6 may be persons appearing in a video captured by a surveillance camera. For example, the management unit 11 may acquire video data captured by a surveillance camera and identify multiple persons, attributes related to the persons, and the certainty of the attributes from the video data. Specifically, similar to the search condition acquisition unit 21, the management unit 11 may acquire the attributes of the persons included in the video and the certainty indicating the probability that the person has the attribute by applying the video data to a learning model. Furthermore, the management unit 11 may manage the video in which each person appears in the form of a still image or a video. The management unit 11 may manage the video in which each person appears in the video in association with the attributes and certainty of each person appearing in the video. Furthermore, the management unit 11 may manage the frame images constituting the video in which each person appears in the video in association with the attributes and certainty of each person appearing in the frame image. For example, when person h_1 is designated, the management unit 11 may extract still image data in which person h_1 appears.

[0041] Alternatively, a computer device other than the information processing device 20 may execute an analysis process on video data captured by a surveillance camera, and identify the attributes of a person included in the video data and a certainty factor indicating the probability that the person has that attribute. In this case, the management unit 11 may acquire the attributes of a person included in the video data and a certainty factor indicating the probability that the person has that attribute from the computer device that analyzed the video data via a network. Alternatively, a user of the information processing device 20 may input the analysis results of the computer device that analyzed the video data to the information processing device 20. Furthermore, the management unit 11 may acquire video data in which a person appears from the computer device that analyzed the video data.

[0042] Next, a screen image generated by the display control unit 15 will be described with reference to Fig. 5. Fig. 5 shows a display screen 31 displayed on the display device 30. The display screen 31 has a search condition designation area 32 and a result display area 34. For example, a user of the information processing device 20 sets an attribute and a confidence level in the search condition designation area 32. Fig. 5 shows that the user of the information processing device 20 has set male and 30s as attributes, and further shows that red has been set as the color of clothing.

[0043] 5 further shows that the user of the information processing device 20 sets the confidence level for each attribute using a slide bar on which a numerical value between 0 and 1 can be set. The black circle on the slide bar indicates the confidence level set by the user. The user can change the confidence level for each attribute by moving the black circle on the slide bar along the numerical values ​​between 0 and 1.

[0044] For example, the user sets the attributes and certainty of the person to be searched for according to instructions from a witness who saw the person to be searched for. When specifying search criteria using an input image, the input image may be displayed in the search criteria designation area 32. In this case, the certainty of each attribute is set based on the input image.

[0045] The result display area 34 shows that the people to be searched are arranged in order of the scores calculated based on the confidence level set for each attribute. For example, the result display area 34 shows that the person on the far left has the highest score, and people with decreasing scores are displayed as they move to the right. #1 to #6 are identification information that identify the people. For example, #1 to #6 indicate h_1 to h_6.

[0046] The black rectangle on the slide bar in the search condition specification area 32 indicates the confidence value that changes the order of people displayed in the result display area 34. In other words, the rectangle on the slide bar indicates the confidence threshold that changes the order of people displayed in the result display area 34. The confidence threshold may also be displayed on a bar different from the confidence setting slide bar. For example, a confidence threshold bar may be displayed below the confidence setting slide bar.

[0047] For example, assume that the certainty of the attributes of age and clothing color are located at the positions indicated by the black circles in FIG. 5. In this case, FIG. 5 shows that when the certainty of gender is changed from 0 to 1, the order of people displayed in the result display area 34 changes for the three values ​​on the gender slide bar in the search condition specification area 32. O1 to O5 displayed in the search condition specification area 32 represent #1 to #5. Furthermore, if the certainty of at least one of the attributes of age and clothing color is located at a position different from that shown in FIG. 5, the position of the threshold displayed on the gender slide bar also changes from the position shown in FIG. 5. Furthermore, if the certainty of the attribute of age is located at a position different from that shown in FIG. 5, the positions of the thresholds displayed on the slide bars for the attributes of gender and age may also change from the positions shown in FIG. 5. Alternatively, if the certainty of any one of the multiple attributes set as search conditions is changed, the positions of the thresholds displayed on the slide bars for all attributes set as search conditions may also change.

[0048] For example, the confidence value indicated by the leftmost black rectangle on the gender slide bar indicates that the order of #2 and #3 is swapped. Specifically, as shown in FIG. 6, the display order of #2 and #3 is swapped in the result display area 34. The upper diagram in FIG. 6 shows the order when the confidence is located to the left of the leftmost black rectangle on the gender slide bar. The lower diagram in FIG. 6 shows the order when the confidence is located to the right of the leftmost black rectangle on the gender slide bar. Furthermore, the confidence value indicated by the middle black rectangle on the gender slide bar indicates that the order of #2 and #4 is swapped, and the confidence value indicated by the rightmost black rectangle indicates that the order of #1 and #3 is swapped.

[0049] Like gender, the black rectangle on the age slide bar indicates the confidence value for changing the order of people displayed in the result display area 34. In other words, assuming that the confidence values ​​for gender and clothing color are at the positions of the black circles in Fig. 5, the black rectangle on the clothing color slide bar indicates the confidence value for changing the order of people displayed in the result display area 34. Like gender and age, the black rectangle on the clothing color slide bar indicates the confidence value for changing the order of people displayed in the result display area 34.

[0050] Next, a description will be given of the score calculation process executed by the calculation unit 12. The calculation unit 12 calculates the score for each person managed by the management unit 11 using the following formula 1.

[0051] TIFF0007761056000001.tif8115

[0052] p j q : Confidence of the jth attribute of the search condition (query condition) p j h : Confidence of the jth attribute to be searched Sim(f j q ,f j h ): Similarity between the jth attribute of the search criteria and the jth attribute of the search target

[0053] The jth attribute of the search criteria is, for example, an attribute set in the jth category displayed in the search criteria specification area 32 in Fig. 5. In Fig. 5, categories are counted in order from the top. For example, in Fig. 5, male, set in the first category, is the first attribute, and 30s, set in the second category, is the second attribute.

[0054] The jth attribute to be searched is, for example, the attribute set in the jth category shown in the database of Fig. 4. In Fig. 4, the categories are counted in order from the left, excluding people. For example, in Fig. 4, the attribute set in the gender category is the first attribute, the attribute set in the age category is the second attribute, the attribute set in the clothing color category is the third attribute, and the attribute set in the glasses category is the fourth attribute.

[0055] The order of categories displayed in the search condition specification area 32 of Fig. 5 and the order of categories shown in the database of Fig. 4 may be predetermined so that the same categories are set in the same order. In other words, the first category displayed in the search condition specification area of ​​Fig. 5 and the first category excluding the person category shown in the database of Fig. 4 may be predetermined as a gender category.

[0056] Sim(f j q ,f j h ) may be, for example, an existing similarity function or may be defined in advance by the user. For example, similarity values ​​may be set for all combinations of attributes that can be set to the same category, such as Sim(Male, Male) = 1.0, Sim(Red, True Red) = 0.95, Sim(Red, Deep Red) = 0.70. A similarity value of 1.0 indicates that the attributes match, and as the value decreases from 1.0, the similarity between the two attributes decreases.

[0057] Also, Sim(f j q ,f jh ) calculates the similarity between the j-th attribute of the search criteria and the j-th attribute of the search target, and the similarity of attributes set in different categories does not have to be calculated. In other words, the similarity of Sim (male, navy blue) is not calculated. Alternatively, the similarity of attributes set in different categories may be set to a low value. Also, even if two attributes can be set to the same category, if there is clearly no similarity between them, the similarity may not be calculated. For example, the similarity of Sim (teens, fifties) does not have to be calculated. Alternatively, the similarity of two attributes that can be set to the same category but are clearly not similar may be set to a low value.

[0058] For example, suppose the following search conditions are entered in the search condition specification area 32 in Figure 5: (Male, 0.9), (30s, 0.8), (40s, 0.2), and (Red, 0.7). The left side of the parentheses indicates the attribute, and the right side indicates the confidence level. Also, in Figure 5, for example, only the 30s is specified in the age category, but multiple age groups may be set.

[0059] In this case, the calculation unit 12 calculates the scores of the people h_1 to h_4 managed in Fig. 4 as follows: Calculation of the scores of h_5 and h_6 will be omitted.

[0060] S(h1) = 0.9 × 0.7 × Sim(Male, Male) + 0.8 × 0.8 × Sim(30s, 30s) + 0.7 × 0.9 × Sim(Red, True Red) = 0.9 × 0.7 × 1.0 + 0.8 × 0.8 × 1.0 + 0.7 × 0.9 × 0.95 = 1.8685

[0061] S(h2) = 0.9 × 0.9 × Sim(Male, Female) + 0.8 × 0.6 × Sim(30s, 30s) + 0.7 × 0.9 × Sim(Red, Deep Red) = 0.9 × 0.9 × 0.0 + 0.8 × 0.6 × 1.0 + 0.7 × 0.9 × 0.7 = 0.921

[0062] S(h3)=0.9×0.9×Sim(male, male)+0.2×0.8×Sim(40s, 40s)+0.7×0.7×Sim(red, maroon)=0.9×0.9×1.0+0.2×0.8×1.0+0.7×0.7×0.8=1.362

[0063] S(h4) = 0.9 × 0.8 × Sim(Male, Male) + 0.7 × 0.6 × Sim(Red, Navy Blue) = 0.9 × 0.8 × 1.0 + 0.7 × 0.6 × 0.0 = 0.72

[0064] Assume that for people h_5 and h_6, h_5 has a higher score than h_6, and h_5 and h_6 have lower scores than h_4. In this case, the scores of people h_1 to h_6 are h_1, h_3, h_2, h_4, h_5, and h_6 in descending order of score. Thus, the sorting unit 13 sorts h_1 to h_6 in descending order of score, and the display control unit 15 generates display data to display h_1, h_3, h_2, h_4, h_5, and h_6 in the result display area 34 in this order.

[0065] Next, using Figure 7, we calculate the confidence level (p j q ) and the relationship between the scores of each object will be described. S(O1) indicates the score of person h_1 calculated by the calculation unit 12. S(O2) to S(O6) also indicate the scores of people h_2 to h_6. FIG. 7 shows the transition of the score of each person when the certainty of male changes from 0 to 1, assuming that, for example, male, age 30s, and red clothing are specified as attributes and the certainty of age 30s and red clothing is located at the position of the black circle in FIG. 5.

[0066] When the attribute is male and the certainty of male is 0, the scores are arranged in descending order as h_1, h_2, h_3, h_4, h_5, and h_6 in the sorting unit 13. When the attribute is male and the certainty of male is 1, the scores are arranged in descending order as h_3, h_1, h_4, h_2, h_5, and h_6 in the sorting unit 13.

[0067] P1, P2, and P3 indicate the confidence levels at the intersections of the lines showing the progression of each person's score. For example, persons h_2 and h_3 are swapped in order at confidence level P1. Furthermore, persons h_2 and h_4 are swapped in order at confidence level P2. Persons h_1 and h_3 are swapped in order at confidence level P3.

[0068] The identification unit 14 may identify the intersections of the line segments by solving an equation using the equation of a straight line representing each line segment, y=ax+b (a and b are positive numbers). For example, the identification unit 14 may identify the intersections of the line segments by identifying line segments having intersections and solving an equation using the equation of the straight line of the identified line segments. In other words, the identification unit 14 may solve only the equations of combinations of line segments having intersections, rather than solving equations of all combinations of line segments. Alternatively, the identification unit 14 may identify the intersections of the line segments using the Bentley-Ottmann algorithm.

[0069] Fig. 8 shows the rank of the object when the confidence level is 0 and the change in the rank of the object when the confidence level is 1. Here, the process of the identification unit 14 identifying a combination of line segments having an intersection will be described with reference to Fig. 8.

[0070] The identification unit 14 selects h_1, which has the highest ranking of the object when the certainty is 0. Furthermore, the identification unit 14 extracts objects that are ranked lower than h_1 when the certainty is 0 and that are ranked higher than h_1 when the certainty is 1. Here, h_3 is present as a corresponding object. As with h_1, the identification unit 14 also extracts corresponding objects for h_2 to h_6. Here, for h_2, h_3 and h_4 are extracted as objects that are ranked lower than h_2 when the certainty is 0 and that are ranked higher than h_2 when the certainty is 1.

[0071] The determination unit 14 calculates the intersection of the line segment h_1 with the line segment h_3, and further calculates the intersection of the line segment h_2 with the line segments h_3 and h_4, thereby determining the degree of certainty that the order of the objects will be swapped. This allows the determination unit 14 to minimize the number of line segments used to calculate the intersection.

[0072] Alternatively, for an object h_i (i is an integer from 1 to 6), the identification unit 14 extracts an object that is ranked higher than h_i at the time when the certainty level is 0 or an object that is ranked higher than h_i at the time when the certainty level is 1. Furthermore, the identification unit 14 may extract objects excluding objects that are ranked higher than h_i at the time when the certainty levels are 0 and 1 from the extracted objects.

[0073] For example, for h_1, h_3 is extracted as an object ranked higher than h_1 at the time when the confidence level is 0 or an object ranked higher than h_1 at the time when the confidence level is 1. For h_1, there is no object ranked higher than h_1 at the time when the confidence level is 0 and 1. Therefore, h_3 is extracted for h_1.

[0074] For h_2, h_1, h_3, and h_4 are extracted as objects ranked higher than h_2 when the confidence level was 0 or objects ranked higher than h_2 when the confidence level was 1. Also, h_1 is an object ranked higher than h_2 when the confidence levels were 0 and 1. Therefore, for h_2, h_3 and h_4 are extracted from h_1, h_3, and h_4, excluding h_1.

[0075] For h_3, h_1 and h_2 are extracted as objects ranked higher than h_3 when the confidence level is 0 or objects ranked higher than h_3 when the confidence level is 1. For h_3, there is no object ranked higher than h_3 when the confidence levels are 0 and 1. Therefore, h_1 and h_2 are extracted for h_3.

[0076] For h_4, h_1, h_2, and h_3 are extracted as objects ranked higher than h_4 when the confidence level is 0 or higher than h_4 when the confidence level is 1. Also, h_1 and h_3 are objects ranked higher than h_4 when the confidence levels are 0 and 1. Therefore, h_2 is extracted for h_4.

[0077] For h_5 and h_6, no object is extracted.

[0078] The identification unit 14 may calculate an intersection of a certain line segment in this manner. For example, when calculating an intersection of h_1, the identification unit 14 calculates an intersection of a line segment with h_3 extracted in association with h_1. Furthermore, when calculating an intersection of h_3, the identification unit 14 calculates an intersection of line segments h_1 and h_2 extracted in association with h_3. In this way, the identification unit 14 can also calculate an intersection of any line segment.

[0079] The display control unit 15 generates display data so that the certainty of the intersection selected by the identification unit 14 is displayed on a slide bar in the search condition designation area 32 in Fig. 5. Furthermore, the display control unit 15 outputs the display data to the display device 30, and the display device 30 displays the received display data.

[0080] Here, the flow of the process of identifying the intersections of line segments according to the second embodiment will be described with reference to Fig. 9. First, the sorting unit 13 sorts the y coordinates of the left and right endpoints of each set of line segments in Fig. 7 (S21). Specifically, in Fig. 7, the sorting unit 13 sorts the y coordinates of each line segment with a confidence level of 0 as the left endpoint, and sorts the y coordinates of each line segment with a confidence level of 1 as the right endpoint.

[0081] Next, the specifying unit 14 determines the target O of the left end point. i The identification unit 14 selects the target O in descending order of the y-coordinate value, in other words, in descending order of the score (S22). i That is, the specification unit 14 may first select the target O1 with the highest score.

[0082] Next, the specifying unit 14 determines whether the y coordinate of the left end point is O i Object smaller than O j The y coordinate of the right end point is O i Objects greater than O j Next, the specification unit 14 extracts all O i The determination unit 14 determines whether or not all O at the left end point are selected (S24). i If not, i=i+1 is set and the process from step S23 onwards is repeated. i If you select j Selected O extracted i The intersections of the line segments are identified (S25).

[0083] Here, in step S23, the identification unit 14 i Regarding O at the time of confidence 0 i Object O has a higher ranking than j Or at confidence level 1, i Object O has a higher ranking than k Furthermore, the specification unit 14 may extract O j and O k Among these, O at confidence levels 0 and 1 i Object O has a higher ranking than m It is also possible to extract objects excluding the above.

[0084] Here, the confidence thresholds in the screen image of Fig. 5 may be shown as in Fig. 10. The confidence thresholds shown in Fig. 10 collectively display the multiple confidence thresholds shown in Fig. 5. In other words, as shown in Fig. 10, the display control unit 15 may narrow down the display to some thresholds rather than displaying all of the confidence thresholds identified by the identification unit 14.

[0085] As described above, when the certainty of an attribute specified as a search condition is changed, the information processing device 20 according to the second embodiment can specify a certainty threshold value for changing the order of objects displayed in the result display area 34. Furthermore, by displaying the certainty threshold value in the search condition specification area 32, the information processing device 20 allows the user to use the certainty threshold value when analyzing the relevance between the certainty level and the search results.

[0086] Furthermore, even when multiple attributes are specified as search conditions, the information processing device 20 can display a certainty threshold for each attribute in the search condition specification area 32. This allows the user to analyze the relevance between the certainty and the search results in more detail.

[0087] FIG. 11 is a block diagram showing a configuration example of an information processing device 10 and an information processing device 20 (hereinafter referred to as information processing device 10, etc.). Referring to FIG. 11, the information processing device 10, etc. includes a network interface 1201, a processor 1202, and a memory 1203. The network interface 1201 may be used to communicate with a network node (e.g., eNB, MME, P-GW, etc.). The network interface 1201 may include, for example, a network interface card (NIC) conforming to the IEEE 802.3 series. Here, eNB stands for evolved Node B, MME stands for Mobility Management Entity, and P-GW stands for Packet Data Network Gateway. IEEE stands for Institute of Electrical and Electronics Engineers.

[0088] The processor 1202 reads and executes software (computer programs) from the memory 1203 to perform the processing of the information processing device 10 and the like described using flowcharts in the above-described embodiments. The processor 1202 may be, for example, a microprocessor, an MPU, or a CPU. The processor 1202 may include multiple processors.

[0089] The memory 1203 is configured by a combination of volatile memory and non-volatile memory. The memory 1203 may include storage located remotely from the processor 1202. In this case, the processor 1202 may access the memory 1203 via an I / O (Input / Output) interface (not shown).

[0090] 11, the memory 1203 is used to store a group of software modules. The processor 1202 reads and executes these software modules from the memory 1203, thereby performing the processing of the information processing device 10 and the like described in the above-described embodiment.

[0091] As explained using FIG. 11, each of the processors possessed by the information processing device 10 in the above-described embodiment executes one or more programs including a group of instructions for causing a computer to perform the algorithm explained using the drawings.

[0092] In the above examples, the program includes instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The program may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable medium or tangible storage medium includes random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The program may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable medium or communication medium includes electrical, optical, acoustic, or other forms of propagated signals.

[0093] The present disclosure is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the present disclosure.

[0094] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a management means for managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute, in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search criteria using an attribute designated as a search criteria, a confidence level of the attribute that can be designated as a search criteria, and a confidence level associated with an attribute that is the same as or similar to the attribute designated as the search criteria and managed; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; a specifying means for specifying a degree of certainty that changes the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the degree of certainty that can be specified as the search condition; and a display control means for generating display data that displays the attribute designated as the search condition in association with a degree of certainty for changing the order of the objects. (Appendix 2) The identification means An information processing device as described in Appendix 1, which uses lines to show the change in score for each object relative to the change in confidence that can be specified as the search condition, and identifies the confidence associated with the intersection of the intersecting line segments as the confidence that will change the order of the objects. (Appendix 3) The identification means An information processing device as described in Appendix 2, wherein, when a first certainty level, a second certainty level, or both levels can be specified as the search conditions, intersecting line segments are identified by comparing the order of the objects when the first certainty level is specified with the order of the objects when the second certainty level is specified. (Appendix 4) The identification means An information processing device as described in Appendix 3, which determines that a line segment related to an object included in both an object of the plurality of objects that has a lower score than a first object when the first certainty level is specified and an object of the plurality of objects that has a higher score than the first object when the second certainty level is specified intersects with a line segment related to the first object. (Appendix 5) The identification means The information processing device according to claim 3, wherein, among the plurality of objects, objects having a higher score than a first object in the first certainty factor or objects having a higher score than the first object in the second certainty factor are excluded, and it is determined that a line segment related to the remaining object intersects with a line segment related to the first object. (Appendix 6) The identification means 6. The information processing device according to any one of appendices 1 to 5, wherein, when a first attribute and a second attribute are specified as the search conditions, a value of the second attribute is determined, and the first certainty factor for changing the order of the objects is identified based on a change in the score of the plurality of objects, which changes in accordance with a change in the first certainty factor for the first attribute. (Appendix 7) 7. The information processing device according to claim 6, wherein the first certainty factor for changing the order of the objects changes in accordance with a change in the certainty factor of the second attribute. (Appendix 8) The display control means An information processing device according to any one of appendices 1 to 7, which generates display data that displays multiple objects arranged in order of score based on an attribute specified as a search condition and a certainty factor specified as a search condition for that attribute. (Appendix 9) an information processing device having: a management means for managing a plurality of objects, at least one attribute by which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search criteria using an attribute specified as a search criteria, a confidence level that can be specified as a search criteria for that attribute, and a confidence level that is managed in association with an attribute that is the same as or similar to the attribute specified as the search criteria; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; an identification means for identifying a confidence level for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the confidence level that can be specified as the search criteria; and a display control means for generating display data for displaying the attribute specified as the search criteria in association with the confidence level for changing the order of the objects; and a display device that displays the display data. (Appendix 10) The display control means generating display data that displays a plurality of objects arranged in order of score based on the attribute specified as a search condition and the certainty factor specified as a search condition for the attribute; The display device includes: 10. The analysis system of claim 9, which displays the display data. (Appendix 11) managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; A data generation method for generating display data that displays attributes designated as the search conditions in association with degrees of certainty for changing the order of the objects. (Appendix 12) managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; A non-transitory computer-readable medium storing a program that causes a computer to generate display data that associates and displays attributes specified as the search conditions with the confidence level for changing the order of the objects.

[0095] The present invention is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the invention. [Explanation of symbols]

[0096] 10. Information processing equipment 11 Management Department 12 Calculation section 13 Sorting section 14 Specific part 15 Display control unit 20 Information processing equipment 21 Search condition acquisition section 30 Display device 31 Display screen 32 Search criteria specification area 34 Results display area

Claims

1. a management means for managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute, in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search criteria using an attribute designated as a search criteria, a confidence level of the attribute that can be designated as a search criteria, and a confidence level associated with an attribute that is the same as or similar to the attribute designated as the search criteria and managed; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; a specifying means for specifying a degree of certainty that changes the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the degree of certainty that can be specified as the search condition; a display control means for generating display data for displaying the attribute designated as the search condition in association with the degree of certainty of changing the order of the objects; The identification means Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; An information processing device that determines that a line segment related to an object included in both an object of the plurality of objects that has a lower score than a first object when the first certainty level is specified and an object of the plurality of objects that has a higher score than the first object when the second certainty level is specified intersects with a line segment related to the first object.

2. A management means for managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute, in association with each other; a calculation means for calculating a score indicating the degree of match of the object with the search criteria using an attribute designated as a search criteria, a confidence level of the attribute that can be designated as a search criteria, and a confidence level associated with an attribute that is the same as or similar to the attribute designated as the search criteria and managed; a sorting means for sorting the scores and arranging the plurality of objects in order of the sorted scores; a specifying means for specifying a degree of certainty that changes the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the degree of certainty that can be specified as the search condition; a display control means for generating display data for displaying the attribute designated as the search condition in association with the degree of certainty of changing the order of the objects; The identification means Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; An information processing device that excludes objects that have higher scores than the first object in the first certainty factor and the second certainty factor from among the plurality of objects that have a higher score than the first object in the first certainty factor or objects that have a higher score than the first object in the second certainty factor, and determines that line segments related to the remaining objects intersect with a line segment related to the first object.

3. The identification means 3. The information processing device according to claim 1, wherein when a first attribute and a second attribute are specified as the search conditions, a certainty factor for the second attribute is determined, and the first certainty factor for changing the order of the objects is identified based on a change in the scores of the plurality of objects that changes in accordance with a change in the first certainty factor for the first attribute.

4. The information processing apparatus according to claim 3 , wherein the first certainty factor for changing the order of the objects changes in accordance with a change in the certainty factor of the second attribute.

5. The display control means The information processing device according to claim 1 , wherein display data is generated to display a plurality of objects arranged in order of score based on an attribute specified as a search condition and a certainty factor specified as a search condition for the attribute.

6. An information processing device, managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; generating display data that associates and displays the attributes designated as the search conditions with the confidence levels for changing the order of the objects; When determining the confidence level, Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; A data generation method that determines that a line segment related to an object that is included in both of the plurality of objects, one of which has a lower score than a first object when the first certainty level is specified, and one of which has a higher score than the first object when the second certainty level is specified, intersects with a line segment related to the first object.

7. An information processing device, managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; generating display data that associates and displays the attributes designated as the search conditions with the confidence levels for changing the order of the objects; When determining the confidence level, Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; A data generation method comprising: excluding, from among the plurality of objects that have a higher score than a first object in the first certainty level, or objects that have a higher score than the first object in the second certainty level, objects that have a higher score than the first object in the first certainty level and the second certainty level; and determining that line segments related to the remaining objects intersect with a line segment related to the first object.

8. managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; generating display data that associates and displays the attributes designated as the search conditions with the confidence levels for changing the order of the objects; When determining the confidence level, Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; A program that causes a computer to execute the following steps: when the first certainty level is specified, identify that a line segment associated with an object that is included in both of the plurality of objects and has a lower score than the first object when the first certainty level is specified, and when the second certainty level is specified, an object that has a higher score than the first object intersects with a line segment associated with the first object.

9. A system for managing a plurality of objects, at least one attribute into which each of the objects is classified, and a confidence level indicating the probability that the object has the attribute, in association with each other; Calculating a score indicating the degree of match of the object with the search criteria using the attribute specified as a search criteria, the confidence level of the attribute that can be specified as a search criteria, and the confidence level associated with an attribute that is the same as or similar to the attribute specified as the search criteria and managed; sorting the scores and arranging the plurality of objects in order of the sorted scores; Identifying a certainty factor for changing the order of the objects based on a transition in the scores of the plurality of objects that changes in accordance with a transition in the certainty factor that can be specified as the search condition; generating display data that associates and displays the attributes designated as the search conditions with the confidence levels for changing the order of the objects; When determining the confidence level, Using lines, the transition of the score for each object relative to the transition of the certainty that can be specified as the search condition is indicated, and the certainty associated with the intersection of the line segments is identified as the certainty that changes the order of the objects; When a first certainty level, a second certainty level, and a third certainty level can be designated as the search condition, the order of the objects when the first certainty level is designated is compared with the order of the objects when the second certainty level is designated, thereby identifying intersecting line segments; A program that causes a computer to execute the following: among the plurality of objects, objects that have a higher score than a first object in the first certainty level, or objects that have a higher score than the first object in the second certainty level, excluding objects that have a higher score than the first object in the first certainty level and the second certainty level, and determining that line segments related to the remaining objects intersect with a line segment related to the first object.

Images