WO2022219810A1 - Information presentation device, information presentation method, and program - Google Patents

Abstract

An information presentation device according to one aspect of the present invention comprises: a specification unit that receives, from among a plurality of task types serving as classifications for classifying tasks in terms of each of a plurality of classification viewpoints, a subject task type that is a task type specified by a searcher; a classification unit that obtains a task log relating to the subject task type by classifying a plurality of task logs, which each indicate a record relating to association between an object and a task, in terms of a classification viewpoint corresponding to the subject task type; a calculation unit that calculates an evaluation indicator of the subject task type for each object on the basis of the task log relating to the subject task type; an order assignment unit that assigns an order to the object on the basis of the result of calculating the evaluation indicator of the subject task type; and an assignment result presentation unit that presents the result of assigning the order to the searcher.

Description

Information presentation device, information presentation method, and program

Embodiments of the present invention relate to an information presentation device, an information presentation method, and a program.

For example, problems related to accounting-related regulations may occur when registering in-house systems for purchase applications for office supplies. When looking for a place to consult about a problem, from the perspective of being able to mutually communicate with each other with as little effort as possible "the type and situation of the work in which the problem occurred" and "the type of work and the solution in line with the situation" It is effective to look for personnel who are not only familiar with the problem of "accounting-related regulations" themselves, but also have extensive experience in a specific type of work (hereinafter referred to as "work type") of "application for purchase of office supplies". It is believed that there is. The same is true when considering members to be assigned to projects such as new business studies and disaster response.

People who are looking for human resources such as consultants or suitable persons for projects (hereinafter referred to as "searchers") often search for human resources such as consultation persons or suitable persons for projects based on their own memories or acquaintances. It is done. However, with this method, acquaintances do not immediately respond to the searcher's request and introduce candidates or other acquaintances, and it takes time to obtain candidates.

In addition, the human resources that can be found are limited to the extent that the explorer himself or his acquaintances can grasp. Furthermore, it is becoming more difficult than ever to grasp who has a wealth of experience in what type of work. The reason for this is that there is a growing trend for each human resource to perform multiple types of work, in order to respond to the shortage of the labor force and to utilize the diversity of values and skills of human resources. Furthermore, when human resources gather in the same geographical location to carry out their work, there are many opportunities to see and hear the work content and conversations of people around them, and it is possible to see who is doing what kind of work frequently. can be sensed naturally on a daily basis. However, in recent years, there has been a growing trend for personnel belonging to the same organization to work in different locations, which is a factor that makes it difficult to grasp.

It is not actually possible for a searcher to recruit human resources who have a lot of experience in a specific type of work on an organization's bulletin board, chat, or other communication tool, and to apply for a human resource who is aware of the wealth of experience. It is done. In this method, it is a premise that the candidate to be searched for will be able to obtain an application if he or she is aware of the recruitment. However, in reality, it is difficult to read a large number of recruitments posted at various times by human resources who are focusing on the execution of their own work, and to find one that corresponds to themselves from among them. In addition, even if a human resource finds a job offer with the possibility of applying, especially at the stage where there are few applicants, it is not possible to grasp whether the person has a lot of experience by comparing with other applicants. It is difficult to judge whether

Non-Patent Document 1 discloses a method of searching for experts on a specific topic. In the method disclosed in Non-Patent Document 1, documents that explicitly hold authors are continuously accumulated, and a person (searcher) who is looking for an expert inputs a word as a search condition, and the word is Extract authors of documents related to .

The method disclosed in Non-Patent Document 1 is a method of supporting the selection or search of suitable personnel only when deriving areas in which each person has knowledge based only on information handled in business, and is applicable. Target is limited to desk work.

Furthermore, the method disclosed in Non-Patent Document 1 supports the search of experts on specific topics by searching for information related to words specified by the searcher as search conditions from the accumulated information. However, certain types of businesses do not always deal with information containing specific words or words related thereto. Moreover, it is not necessarily the case that only a particular type of business deals with information containing a particular word or words related thereto. For this reason, it is difficult to specify a word exactly corresponding to a specific type of work as a search condition. Furthermore, it is not possible to confirm the validity of whether or not the information highly evaluated for its relevance to the word designated as the search condition was created or exchanged in the type of business intended by the searcher.

Patent Document 1 discloses a method of acquiring and accumulating terminal operation logs for the purpose of grasping and analyzing the actual business and displaying them in an easy-to-understand manner for people. Non-Patent Literature 2 and Non-Patent Literature 3 disclose a method of estimating the type of work performed by a person from a terminal operation log. Non-Patent Literature 4 discloses a method of estimating the type of work performed by a person from an image captured by a camera installed at the place where the work is performed. Non-Patent Document 5 discloses a method of estimating the type of work performed by a person from information obtained by a sensor such as an accelerometer worn by the person. The estimation results obtained by these methods may contain errors, and the estimation results may be uncertain.

Japanese Patent Application Laid-Open No. 2020-123048

The purpose of the present invention is to provide a technique for presenting suitable objects such as suitable persons.

An information presentation device according to an aspect of the present invention is a target task type, which is a task type specified by a searcher from among a plurality of task types that are classification destinations when tasks are classified according to each of a plurality of classification viewpoints. and a classifying unit that obtains a work log related to the target work type by classifying a plurality of work logs showing records related to objects and work from a classification point of view corresponding to the target work type. a calculation unit for calculating an evaluation index of the target work type for each object based on a work log related to the target work type; A rank assignment unit that assigns ranks, and an assignment result presentation unit that presents the result of assigning the ranks to the searcher.

According to the present invention, a technique is provided for presenting suitable objects such as suitable persons.

FIG. 1 is a block diagram showing an information processing system according to an embodiment. FIG. 2 is a functional block diagram of the information presentation device shown in FIG. 3 is a diagram showing information stored in a business log storage unit shown in FIG. 2. FIG. 4A is a diagram showing information stored in a control information storage unit shown in FIG. 2. FIG. 4B is a diagram showing information stored in a control information storage unit shown in FIG. 2. FIG. 4C is a diagram showing information stored in a control information storage unit shown in FIG. 2. FIG. 5 is a diagram showing information stored in a classification result storage unit shown in FIG. 2. FIG. 6 is a diagram showing information stored in a calculation result storage unit shown in FIG. 2. FIG. 7 is a diagram showing information stored in an uncertainty information storage unit shown in FIG. 2. FIG. 8 is a diagram showing information stored in an allocation result storage unit shown in FIG. 2. FIG. FIG. 9 is a block diagram showing the hardware configuration of the information presentation device shown in FIG. FIG. 10 is a flow chart showing the operation of the information presentation device shown in FIG. FIG. 11 is a flow chart showing processing of the rank assigning unit shown in FIG. FIG. 12 is a flow chart showing processing of the rank assigning unit shown in FIG. FIG. 13 is a flow chart showing processing of the rank assigning unit shown in FIG. FIG. 14 is a flow chart showing processing of the rank assigning unit shown in FIG. FIG. 15 is a flow chart showing processing of the rank assigning unit shown in FIG.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

(1) Configuration (1-1) Information Processing System FIG. 1 schematically shows a configuration example of an information processing system 10 according to an embodiment of the present invention. The information processing system 10 shown in FIG. 1 supports search and selection of personnel with extensive work experience. The information processing system 10 includes an information presentation device 11 and a business log acquisition device 12 . The information presentation device 11 may communicate with the business log acquisition device 12 . The information presentation device 11 may be connected to the business log acquisition device 12 via a communication network, or may be connected by an API (Application Programming Interface).

The work log acquisition device 12 acquires and accumulates work logs that indicate the relationship between personnel and work. Specifically, the work log indicates records related to the execution of work by personnel. The work log is recorded as the work is carried out by personnel. The business log acquisition device 12 transmits the accumulated business logs to the information presentation device 11 . Alternatively, the business logs accumulated by the business log acquisition device 12 may be transferred to the information presentation device 11 using a recording medium such as a USB (Universal Serial Bus) memory.

In the example of FIG. 1, business log acquisition devices 12-1, 12-2, and 12-3 are shown. The business log acquisition device 12-1 acquires a business log whose business log type is terminal operation. For example, the business log acquisition device 12-1 operates on a computer terminal used by a user, observes events occurring in the computer terminal and contents displayed on the screen, and acquires them as a business log. The business log acquisition device 12-2 acquires a business log whose business log type is video. The business log acquisition device 12-3 acquires a business log whose business log type is the acceleration sensor.

The information presentation device 11 receives and accumulates business logs from the business log acquisition device 12 . The information presentation device 11 receives a presentation request from the searcher. The request for presentation includes information indicating the type of work specified by the searcher, and is an instruction requesting the presentation of personnel with extensive work experience in the type of work. In response to the presentation request, the information presentation device 11 refers to the accumulated business logs to search for suitable personnel, ranks the personnel obtained by the search, and presents them to the searcher.

In the example shown in FIG. 1, the business log acquisition device 12 is provided as a separate device from the information presentation device 11. Alternatively, the information presentation device 11 may have the function of the business log acquisition device 12 .

Examples of business types include application for purchase of office supplies, inspection of delivery of office supplies, inventory of office supplies, planning of new services, customer proposals for new services, allocation of resources for service provision, construction arrangements for resources for service provision, etc. include. The business type may be subdivided by the type of service. Further, the work type may be subdivided according to the software used in the work, such as work using spreadsheet software, mail transmission/reception work, specific in-house system registration work, and the like.

The example of the work type mentioned above is a work type related to desk work. Examples of work types may include work types related to fieldwork. Examples of work types related to fieldwork include equipment installation, equipment inspection, equipment repair, surveying, and the like.

In addition, there are multiple categories categorized from different perspectives, such as "work to register in a specific internal system with a purchase application for office supplies", which is a combination of "office supply purchase application work" and "specific internal system registration work". A combination of business types is also treated as a business type.

(1-2) Information Presentation Device FIG. 2 schematically shows an example of the functional configuration of the information presentation device 11. As shown in FIG. As shown in FIG. 2, the information presentation device 11 includes an acquisition unit 101, a designation unit 102, a classification unit 103, a work execution amount calculation unit 104, a rank allocation unit 105, an allocation result presentation unit 106, a control information presentation unit 107, a work A log storage unit 111 , a control information storage unit 112 , a classification result storage unit 113 , a calculation result storage unit 114 , an uncertainty information storage unit 115 and an allocation result storage unit 116 are provided.

The acquisition unit 101 serves as an interface for the business log acquisition device 12 shown in FIG. The acquisition unit 101 receives a business log from the business log acquisition device 12 shown in FIG. 1 and stores it in the business log storage unit 111 .

FIG. 3 shows an example of information stored in the business log storage unit 111. FIG. The upper part of FIG. 3 shows the business logs whose business log type is the operation terminal. Each business log includes an ID, a time stamp, an operator, an operation target application, operation target window identification information, and information indicating the display contents of the operation target window. In the middle part of FIG. 3, business logs whose business log type is video are shown. Each business log includes information indicating an ID, video file name, frame number, time stamp, and person to be photographed. The business log is associated with the actual video data by the video file name and frame number. The lower part of FIG. 3 shows a business log whose business log type is an accelerometer. Each business log contains information indicating an ID, a sensor identification number, a time stamp, a signal value, and a wearer.

The designation unit 102 receives input of the work type designated by the searcher, and sends information indicating the work type designated by the searcher to the classification unit 103 . In the following, the work type specified by the searcher is also referred to as the target work type. The target work type may be a single work type designated by the searcher, or may be multiple work types designated by the searcher. For example, the specifying unit 102 presents the selectable work types to the searcher, and specifies the work type selected by the searcher as the target work type.

Multiple business types are prepared as classification destinations when business is classified according to each of the multiple classification perspectives. For example, the first classification viewpoint includes "business trip application" and "purchase application", the second classification viewpoint includes "internal system use" and "email transmission/reception", and the third classification viewpoint includes "equipment inspection ”, “troubleshooting”, “equipment transportation”, etc. The specifying unit 102 may present the searcher with selectable work types for each of a plurality of classification viewpoints. The searcher may select a business type for one classification viewpoint, or may select a business type for each of two or more classification viewpoints.

The classification unit 103 classifies the business logs stored in the business log storage unit 111 from a classification viewpoint corresponding to the target business type, and stores the classification result in the classification result storage unit 113 . If the target task type is a single task type specified by the searcher, the classification unit 103 classifies the task log according to the classification method corresponding to the classification viewpoint to which the target task type belongs. Specifically, the classification unit 103 uses the control information related to the plurality of work types included in the classification viewpoint to which the target work type belongs to classify the work logs into the plurality of work types included in the classification viewpoint to which the target work type belongs. Classify. Control information is prepared for each business type and stored in the control information storage unit 112 . Control information for a certain business type includes information for determining whether or not a business log corresponds to the business type.

The control information may include rules that explicitly describe conditions for determining whether a business log corresponds to a business type. Alternatively, the control information may include samples of business logs. For example, the control information includes a sample of the business log included in the business trip application, a sample of the business log included in the business type of purchase request, and a sample of the business log included in the device inspection business type. including. Alternatively, the control information may include documents such as manuals that describe the content and procedures of the business.

4A to 4C schematically show examples of control information stored in the control information storage unit 112. FIG. The task type determination rule shown in FIG. 4A is used to classify task logs whose task log type is terminal operation. The business type determination rule is a rule for determining whether a business log corresponds to the business type "business trip application" and a rule for determining whether a business log corresponds to the business type "purchase application". including. The control information may include a sample work log as shown in FIG. 4B, or a work manual as shown in FIG. 4C.

For a business log whose business log type is video, the classification unit 103 refers to the video data and control information specified by the video file name and frame number to estimate the type of business performed by the person to be photographed. Categorize business logs based on results. For the business log whose business log type is the accelerometer, the classification unit 103 estimates the business type performed by the wearer by referring to the time change pattern of the signal value and the control information, and classifies the business log based on the estimation result. classify.

The classification method described here is an example, and other classification methods may be used. The classification method may be based on a method of determining the business type of business logs of a single business log type, or based on a method of determining the business type of business logs of multiple business log types. good too.

For example, if the control information is difficult for humans to understand, the control information storage unit 112 may further store information describing conditions for creating the control information.

A case where a business type is designated for each of a plurality of classification viewpoints will be described. For example, it is assumed that a task type c ⁱ _si is specified for the classification viewpoint C ⁱ and a task type c ^j _sj is specified for the classification viewpoint C ^j . In the following, the business type obtained by combining the business type c ⁱ _ri and the business type c ^j _rj is expressed as c ^i,j _ri,rj .

The classification unit 103 independently applies the classification method corresponding to the classification viewpoint C ⁱ and the classification method corresponding to the classification viewpoint C ^j to all the business logs stored in the business log storage unit 111 . Specifically, the classification unit 103 classifies all work logs ^into work types c ⁱ ₁ , c ⁱ ₂ , . . . , c ⁱ _ri, . . . , and all task logs are classified ^into task types c ^j ₁ , c ^j ₂ , . . . , c ^j _rj, . . . classified into Then, the classification unit 103 obtains the intersection of the work logs classified into the work types c ⁱ _ri and the work logs classified into the work types c ^j _rj to obtain the work related to the combined work types c ^i,j _ri,rj . get log. In this way, the classification unit 103 classifies the business logs stored in the business log storage unit 111 into business types c ^i,j _1,1 , c ^i,j _1,2 , . . . , c ^i,j _ri,1 , c ^i,j _ri,2 , . . . , c ^i,j _ri,rj , . . . , c ^i,j _ri+1,1 , c ^i,j _ri+1,2 , . . . classified into

The business logs are business types c ^i,j _1,1 , c ^i,j _1,2 , . . . , c ^i,j _ri,1 , c ^i,j _ri,2 , . . . , c ^i,j _ri,rj , . . . , c ^i,j _ri+1,1 , c ^i,j _ri+1,2 , . . . will be classified as In a description that uses only the result without considering the intermediate process of applying the classification method, the classification method corresponding to the classification viewpoint C classifies the business types c ₁ , c ₂ , . . . , c _r , . . . Business logs are treated as those classified into

Although the case where business types are specified for two classification viewpoints has been described, the same applies to cases where business types are specified for three or more classification viewpoints.

FIG. 5 schematically shows an example of classification results obtained by the classification unit 103. FIG. As shown in FIG. 5, for example, a business log whose ID is "30134" is classified into the business type "business trip application" from the classification point of view 1, and is classified into the business type "internal system use" from the classification point of view 2. From viewpoint 3, it is not classified into any business type.

The work execution amount calculation unit 104 calculates the work execution amount for each combination of the personnel and the work type in the classification result obtained by the classification unit 103 , and stores the calculation result in the calculation result storage unit 114 . The amount of work performed is an evaluation index that quantifies the work performed by a human resource, and corresponds to the richness of work experience. The amount of work performed may be the number of work logs. For example, if 15 work logs of Personnel ¹ are included in the work logs classified into Work Type C1, the amount of work performed is 15 for the combination of Personnel ¹ and Work Type C1. The amount of work performed may be obtained by aggregating attribute data such as time stamps included in the work log.

FIG. 6 schematically shows an example of calculation results obtained by the work implementation amount calculation unit 104. FIG. The calculation results shown in the upper part of FIG. 6 are obtained when the business type of classification viewpoint 1 and the business type of classification viewpoint 2 in FIG. 5 are designated as search targets. In the example shown in FIG. 6, the amount of work performed is 116 for the combination of the human resource 1 and the composite work type of the work type "business trip application" and the work type "internal system use". The calculation result shown in the lower part of FIG. 6 is obtained when the business type of classification viewpoint 3 in FIG. 5 is designated as a search target. In the example shown in FIG. 6, the amount of work performed is 20 for the combination of the personnel 1 and the work type "equipment inspection".

The rank assignment unit 105 assigns ranks to personnel based on the amount of work performed for the target work type included in the calculation results, and stores the assignment results in the assignment result storage unit 116 . For example, the rank assigning unit 105 assigns ranks to personnel in descending order of the amount of work performed for the target work type.

The rank assignment unit 105 may use the uncertainty information stored in the uncertainty information storage unit 115 for rank assignment. Specifically, the rank assigning unit 105 may obtain a correction value for the amount of work performed by correcting the amount of work performed for the target work type based on the uncertainty information. The rank assigning unit 105 assigns ranks to personnel in descending order of the correction value of the amount of work performed (the amount of work performed after correction).

Furthermore, the rank assigning unit 105 calculates the probability of occurrence of a reversal in the amount of work performed between the ranks based on the calculation result of the amount of work performed and the uncertainty information, and groups the ranks based on the calculated probabilities. good too.

Uncertainty information is created in advance for each classification method and stored in the uncertainty information storage unit 115 . Uncertainty information is information that indicates the tendency of classification errors by a classification method. The uncertainty information is generated, for example, by experimentally classifying business logs for which the correct business type is known. The uncertainty information is generated based on the ratio of erroneously classified business logs in the classified business type as a result of trial execution of business log classification. The uncertainty information includes the ratio distribution of the amount of work performed with respect to the combination of the work type estimated by the classification method and the correct work type.

The business log used to generate the uncertainty information may be part of the business log stored in the business log storage unit 111 . The correct business type of the business log may be assigned by, for example, manually examining the business log, or the business log may be obtained by intentionally performing only a specific type of business by dividing the time period. It may be given by

FIG. 7 schematically shows an example of uncertainty information stored in the uncertainty information storage unit 115. As shown in FIG. In the example shown in FIG. 7, the uncertainty information storage unit 115 stores the uncertainty information of the classification method corresponding to the first classification viewpoint, the uncertainty information of the classification method corresponding to the second classification viewpoint, and uncertainty information of the classification method corresponding to the third classification viewpoint. The value λ ⁱ _ri→r′i is calculated from the work logs for which the correct work type is c ⁱ _r′i included in the work logs classified into the work type c ⁱ _ri by the classification method corresponding to the classification viewpoint C ⁱ . is divided by the amount of work performed calculated from the work log classified into the work type c ⁱ _ri by the classification method corresponding to the classification viewpoint C ⁱ .

FIG. 8 schematically shows an example of rank assignment result information stored in the assignment result storage unit 116. FIG. In the example shown in FIG. 8, personnel 5 is first, personnel 4 is second, personnel 3 is third, personnel 2 is fourth, and personnel 1 is fifth. 1st to 3rd place ( personnel 5, 4, 3) belong to the 1st place group, 4th place (personnel 2) belongs to the 4th place group, and 5th place (personnel 1) belongs to the 5th place group.

If the rank assigning unit 105 does not correct the amount of work performed and group the ranks, it is sufficient for the amount of work performed calculation unit 104 to calculate the amount of work performed for each target work type for each personnel. For example, when the target work type includes a work type c ⁱ _si belonging to the classification viewpoint C ⁱ and a work type c ^j _sj belonging to the classification viewpoint C ^j , the classification unit 103 obtains a work log related to the work type c ⁱ _si . to obtain the business log related to the business type c ^j _sj , and the intersection of the business log related to the business type c ⁱ _si and the business log related to the business type c ^j _sj to obtain the business log related to the target business type get as The work performance amount calculation unit 104 calculates the work performance amount of the target work type for each personnel based on the work log related to the target work type obtained by the classification unit 103 .

The allocation result presentation unit 106 presents the allocation result obtained by the rank allocation unit 105 to the searcher. For example, the allocation result presenting unit 106 displays the allocation result on the display device.

The control information presentation unit 107 acquires control information from the control information storage unit 112 and presents the control information to the searcher. For example, the control information presenting unit 107 displays the control information on the display device. The control information presenting unit 107 may present to the searcher, in place of or in addition to the control information, information describing conditions for preparing the control information.

The information presentation device 11 having the above configuration can present to the searcher personnel who have extensive experience in the type of work specified by the searcher.

FIG. 9 schematically shows a hardware configuration example of the information presentation device 11. As shown in FIG. In the example shown in FIG. 9 , the information presentation device 11 includes a processor 151 , a RAM (Random Access Memory) 152 , a program memory 153 , a storage device 154 and an input/output interface 155 . Processor 151 communicates with RAM 152 , program memory 153 , storage device 154 and input/output interface 155 .

The processor 151 includes a general-purpose circuit such as a CPU (Central Processing Unit) or GPU (Graphics Processing Unit). RAM 152 is used by processor 151 as a working memory. RAM 152 includes volatile memory such as SDRAM. Program memory 153 stores programs executed by processor 151, including a search program. The program includes computer-executable instructions. A ROM, for example, is used as the program memory 153 . A partial area of the storage device 154 may be used as the program memory 153 .

The processor 151 expands the program stored in the program memory 153 to the RAM 152, interprets and executes the program. The search program, when executed by processor 151 , causes processor 151 to perform a series of processes described with respect to information presentation device 11 .

The program may be provided to the information presentation device 11 while being stored in a computer-readable recording medium. In this case, the information presentation device 11 has a drive for reading data from the recording medium, and acquires the program from the recording medium. Examples of recording media include magnetic disks, optical disks (CD-ROM, CD-R, DVD-ROM, DVD-R, etc.), magneto-optical disks (MO, etc.), and semiconductor memories. Also, the program may be distributed through a network. Specifically, the program may be stored in a server on the network, and the information presentation device 11 may download the program from the server.

The storage device 154 stores data such as business logs. The storage device 154 includes non-volatile memory such as HDD (Hard Disk Drive) or SSD (Solid State Drive).

The input/output interface 155 includes a communication module for communicating with an external device and a plurality of terminals for connecting peripheral devices. Communication modules include wired modules and/or wireless modules. Examples of peripherals include displays, keyboards, and mice. The processor 151 receives the input of the target task type via the input/output interface 155 . The processor 151 outputs allocation results via the input/output interface 155 .

The processor 151 may include a dedicated circuit such as ASIC (Application Specific Integrated Circuit) or FPGA (field-programmable gate array) instead of or in addition to the general-purpose circuit.

(2) Operation of Information Presentation Apparatus (2-1) Overall Flow FIG. 10 schematically shows an example of an information presentation method executed by the information presentation apparatus 11. As shown in FIG.

In step S10 of FIG. 10, the control information presentation unit 107 determines whether or not an instruction to present control information has been received from the searcher. If the control information presentation unit 107 has received the instruction (step S10; Yes), the flow proceeds to step S11. In step S11, the control information presentation unit 107 acquires control information from the control information storage unit 112 and presents the control information to the searcher.

For example, the designation unit 102 displays on the display device a user interface screen for designating the type of work to be searched. The user interface screen includes buttons for instructing display of control information. The control information presentation unit 107 displays control information on the display device when the button is clicked.

When the control information presentation unit 107 does not receive the instruction (step S10; No) or after the process of step S11 is executed, the flow proceeds to step S12. In step S12, the designation unit 102 receives an input of the target work type from the searcher. The target business type includes at least one business type specified by the searcher.

In step S13, the classification unit 103 classifies the business logs stored in the business log storage unit 111 from a classification viewpoint corresponding to the target business type. When the target task type includes task types c ⁱ _si belonging to classification viewpoint C ⁱ and task types c ^j _sj belonging to classification viewpoint C ^j , the classification unit 103 determines the classification method and classification viewpoint C ^j corresponding to classification viewpoint C ⁱ . independently apply the classification methods corresponding to , and combine the obtained classification results to obtain the final classification result.

In step S14, the work execution amount calculation unit 104, based on the work log stored in the work log storage unit 111 and the classification result obtained by the classification unit 103, determines the type of work performed by the personnel and the work type in the classification result. Calculate the work to be done for each of the combinations. The work performance amount calculated by the work performance amount calculation unit 104 includes the work performance amount for each combination of the personnel and the target work type.

In step S15, the rank assigning unit 105 assigns ranks to personnel based on the calculation result of the amount of work performed. For example, the rank assigning unit 105 assigns ranks to personnel in descending order of the amount of work performed for the target work type. The rank assigning unit 105 may correct the amount of work performed based on the uncertainty information regarding the classification viewpoint corresponding to the target work type, and assign ranks to personnel in descending order of the corrected amount of work performed. Furthermore, the rank assigning unit 105 calculates the probability that the evaluation index will be reversed between the ranks based on the uncertainty information and the calculation result of the amount of work performed, and groups the ranks based on the calculated probabilities. may Rank assignment will be described later.

In step S16, the allocation result presentation unit 106 presents the allocation result obtained by the rank allocation unit 105 to the searcher. For example, the allocation result presenting unit 106 displays the allocation result on the display device. When the ranks are grouped, the allocation result presenting unit 106 further presents the results of grouping the ranks.

In the example shown in FIG. 10, the classification process shown in step S13 is executed after the searcher designates the type of work to be searched. Alternatively, the classification process may be performed before the job type to be searched is specified by the searcher. In this case, the classification unit 103 independently applies classification methods corresponding to all classification viewpoints, and stores the classification results for each classification method obtained thereby in the classification result storage unit 113 . When a business log is newly added to the business log storage unit 111, the classification unit 103 classifies the added business log. By doing so, it is not necessary to perform the classification process every time the searcher designates the type of work to be searched. When the searcher specifies a business type for each of a plurality of classification viewpoints, the classification unit 103 acquires classification results relating to these classification viewpoints from the classification result storage unit 113, and uses the acquired classification results to create a composite classification. Generate classification results for perspectives.

(2-2) Ranking Allocation FIG. 11 schematically shows an example of the rank allocating operation in rank allocating section 105 . Specifically, FIG. 11 schematically shows the operation when the rank assignment unit 105 assigns ranks to personnel based on the work performance amount calculation results obtained by the work performance amount calculation unit 104 and the uncertainty information. showing.

(2-2-1) Calculation of Uncertainty Information In step S20 of FIG. 11, the rank assigning unit 105 acquires uncertainty information regarding the target task type.

When a business type is designated for a single classification viewpoint, the rank assigning unit 105 acquires uncertainty information related to the business type that matches the designated business type from the uncertainty information storage unit 115. do.

For example, assume that a task type c ⁱ _si is specified for a classification point of view C ⁱ . Further, the business logs are classified into business types c ⁱ ₁ , c ⁱ ₂ , . . . , c ⁱ _ri, . . . shall be classified as The rank assignment unit 105 acquires the uncertainty information of the classification method corresponding to the classification viewpoint ^Ci from the uncertainty information storage unit 115 . Specifically, rank assigning section 105 obtains values λ ⁱ _1→si , λ ⁱ _2→si , . . . , λ ⁱ _si→si , . . . to get The rank assigning unit 105 uses the acquired uncertainty information as it is as the uncertainty information regarding the target task type.

When task types are specified for two classification viewpoints, the rank assigning unit 105 selects from the uncertainty information storage unit 115 the uncertainties related to the two task types that match the specified two task types. Information is acquired, and uncertainty information related to the target task type is calculated from the acquired uncertainty information.

For example, it is assumed that a task type c ⁱ _si is specified for the classification viewpoint C ⁱ and a task type c ^j _sj is specified for the classification viewpoint C ^j . Further, the business logs are classified into business types c ^i,j _1,1 , c ^i,j _1,2 , . . . , c ^i,j _ri,1 , c ^i,j _ri,2 , . . . , c ^i,j _ri,rj , . . . c ^i,j _ri+1,1 , c ^i,j _ri+1,2 , . . . shall be classified as The rank assigning unit 105 acquires the uncertainty information of the classification method corresponding to the classification viewpoint C ⁱ and the uncertainty information of the classification method corresponding to the classification viewpoint C ^j from the uncertainty information storage unit 115 . The uncertainty information of the classification method corresponding to the classification viewpoint C ⁱ has the values λ ⁱ _1→si , λ ⁱ _2→si , . . . , λ ⁱ _si→si , . . . , and the uncertainty information of the classification method corresponding to the classification viewpoint C ^j has the values λ ^j _1→sj , λ ^j _2→sj , . . . , λ ^j _sj→sj , . . . including. The rank assigning unit 105 calculates λ ^i,j _{ri→si,rj→sj} according to the following equation.

where λ ^i,j _{ri→si,rj→sj} for r _i =1,2, . . . , s _i , . . . , r _j =1,2, . . . , s _j , . . . , is calculated for each combination of r _i and r _j . The value λ ^i,j _{ri→si,rj→sj} indicates the ratio of the correct business types c ^i,j _si,sj among the business logs classified into the business types c ^i,j _ri,rj .

When task types are designated for three or more classification viewpoints, the order assigning unit 105 retrieves the uncertainty information about the task types that respectively match the designated task types from the uncertainty information storage unit 115. and calculate the uncertainty information related to the target business type from the obtained uncertainty information.

For example, let C ¹ , C ² , C ³ , . . . and The rank assigning unit 105 applies the process described for the case where the business types are specified for the two classification viewpoints C ¹ and C ² to the classification viewpoints C 1 and C 2 , thereby obtaining the combined classification viewpoints C ¹ and C 2 . Calculate the uncertainty information for the corresponding classification method. The rank assigning unit 105 applies the process described for the case where the business types are specified for the two classification viewpoints C ^1,2 and C ³ to the classification viewpoints C 1,2 and C 3 , thereby obtaining the combined classification viewpoints C ^1, 2 and C 3 . Calculate the uncertainty information of the classification methods corresponding to ² and 3. The rank assigning unit 105 repeats the process described for the case where the business types are specified for the two classification viewpoints, thereby obtaining composite classification viewpoints C ^{1, 2, 3, . . .} Calculate the uncertainty information of the classification method corresponding to

In the description that uses only the result without considering the intermediate process of applying the classification method, the classification method corresponding to the composite classification viewpoint C classifies the business types c ₁ , c ₂ , . . . , c _r , . . . , the value of uncertainty information for the target task type is expressed as _λr→s . Here, the value λr _{→s indicates} the ratio of the correct task type cs among the task logs whose task type estimation result is _cr .

(2-2-2) Calculating the probability distribution and correction value of the amount of work performed for each personnel In step S21, the rank assigning unit 105 calculates the probability distribution of the amount of work performed and the correction value for all personnel to be searched. Determine whether or not the calculation has been performed. If the probability distribution and correction value of the amount of work performed have not been calculated for any of the personnel (step S21; No), the flow proceeds to step S22.

In step S22, the rank allocation unit 105 selects the personnel h to be processed. In step S23, the rank assigning unit 105 calculates the probability distribution and correction value of the amount of work performed for the personnel h.

The work log of human resource h is divided into work types c ₁ , c ₂ , . . . , c _r , . . . classified as Let ^{nh r be the number of work logs of human resource h classified into work type c r, and n h} _{be the} ^total . The total ^nh is expressed as follows.

Further, _let w ^hr be the amount of work performed for work type c _r of human resource h, and w ^h be the total. The total w ^h is expressed as follows.

Note that the type of work each work log belongs to is estimated by the classification method, so _n ^hr is the estimated value of the number of work logs, and w ^hr is the estimated value of the amount of work performed _. is.

A case will be described where the number of business logs is used as the amount of work performed. Then w ^h _r =n ^h _r for any r. The probability distribution _{φ hr} (x ^hr ) of the number x _hr of the number x ^hr of the _n ^hr business logs classified into each business type _cr is the _average ^{μ hr} ₌ n ^h _r λ _r→s , variance (σ ^h _r ) ² =n ^h _r λ _r→s (1−λ _r→s ), which is considered to follow a binomial distribution.

The probability distribution ψ ^h (x ^h ) of the number x ^h of the n ^h task logs of the human resource h whose original task type is c _s is given by the task types c ₁ , c ₂ , . . . , c _r , . . . n ^h ₁ , n ^h ₂ , . . . , n ^h _r , . . . out of the business logs whose original business type is c _s is the probability distribution of the sum x ^h =Σ _r x ^h _r , and the probability distributions φ ^h ₁ , φ ^h ₂ , . . . , φ ^h _r , . . . is the convolution of Here, the convolution φ ^hr _′ *φ ^hr _″ of two arbitrary probability distributions ^{φ hr} _{′ and} φ ^hr _″ is ^obtained by the following is represented as

φ ^h ₁ , φ ^h ₂ , . . . , φ ^h _r , . . . , φ ^h ₁ *φ ^h ₂ * . . . *φ ^h _r *. . . obtains the convolution of φ ^h ₁ and φ ^h ₂ , φ ^h ₁ *φ ^h ₂ , and then the convolution of φ ^h ₁ * φ ^h ₂ and φ ^h ₃ , φ ^h ₁ * φ ^h ₂ * φ ^h ₃ , and so on. It is calculated by repeating the convolution of two probability distributions as follows.

Alternatively, n ^h ₁ , n ^h ₂ , . . . , n ^h _r , . . . is sufficiently large, the probability distribution φ ^h _r (x ^h _r ) regarded as a binomial distribution is assumed to be a normal distribution with the same mean and variance,

, and by exploiting the reproducibility properties of the normal distribution, φ ^h ₁ , φ ^h ₂ , . . . , φ ^h _r , . . . The probability distribution ψ ^h (x ^h ), which is the convolution of , is calculated as follows.

However, since the normal distribution is a probability distribution in which random variables are continuous values, the probability distribution ψ ^h (x ^h ) is obtained as the probability distribution of discrete values x ^h as follows.

The estimated value of the amount of work performed for work type c _s of human resource h is w ^h _s =n ^h _s , but its correction value w′ ^h _s is the expected value of ψ ^h (x ^h ) and is calculated as follows. be.

We will explain the case of using attribute data such as timestamps included in the business log as the amount of work performed.

If the uncertainty information is the distribution of the ratio of the number of business _logs for each combination of the business type of the estimation result and the correct business type when performing classification on a trial basis, The _value of ^ρhr _{= whr /} ^nhr is calculated from ^nhr and _whr , and the ^{probability distribution φhr} ( ^xhr _{) regarding} the number of task ^logs _xhr is calculated as the _amount of work performed y ^Transform into a probability distribution _{φ hr} (y ^hr ) with ^hr = _ρ ^hr x _hr and _let φ ^h ₁ , ^{φ h 2} _, . . . , φ ^h _r , . . . As the convolution probability distribution of , the probability distribution ψ ^h (y ^h ) of the work execution amount y ^h of the work log whose original work type is c _s among all the work logs of the personnel h is calculated. For example, when φ ^hr (x _hr ) is approximated by a normal distribution, φ ^hr (y _hr ) and _ψ ^h ( _y ^h ) are ^{as follows} .

However, the calculation method when using the probability distribution of continuous values as the probability distribution of discrete values is the same.

The estimated value of the amount of work performed for the work type c _s of the human resource h is w ^h _s , and its correction value w′ ^h _s is calculated by the following formula as the expected value of ψ ^h (y ^h ).

Alternatively, if the uncertainty information holds the ratio distribution of the amount of work performed for each combination of the work type of the estimation result and the work type of the correct answer when performing classification on a trial basis, The probability distribution of the work execution amount itself may be calculated as an appropriate probability distribution family with the value as a parameter. Examples of suitable families of probability distributions include binomial and normal distributions.

FIG. 12 schematically shows an example of the process of calculating the probability distribution and correction value shown in step S23 of FIG. In step S30 of FIG. 12, the rank assigning unit 105 determines whether or not probability distributions have been calculated for all task types belonging to the classification viewpoint.

If the probability distribution has not been calculated for any business type (step S30; No), the flow proceeds to step S31. In step S31, the rank assigning unit 105 selects one task type _cr from task types for which the probability distribution has not been calculated.

In step _S32 , the rank ^assigning unit 105 ^calculates the _probability distribution _{φ hr} ⁽ _x ^h _r ).

In step S33, the rank assigning unit ₁₀₅ calculates ρ ^hr from the number of task logs _n ^hr and the amount of work performed w ^hr for the task type _{cr .} where ρ ^hr ₌ w ^hr / _n ^hr _.

In step S34, the rank assigning unit 105 ^converts the probability distribution φ ^hr (x _hr ) into the _probability distribution ^{φ hr} _{( y} ^hr ) _regarding the amount of work performed y ^hr . The flow then returns to step S30.

If probability distributions have been calculated for all business types (step S30; Yes), the flow proceeds to step S35.

In step S35, the rank assigning unit 105 calculates the probability distribution ψ ^h (y ^h ) of the total value y ^h of the attribute data of the work logs whose original work type is c _s among all the work logs of the human resource h.

In step S36, the rank assigning unit 105 calculates a correction value w' ^h _s of the amount of work performed as an expected value of ψ ^h (y ^h ).

In the above description, in order to explain an example of the conversion method of the probability distribution, ^xh is the number of business logs whose original business type is ^cs , and _yh is the number of business logs whose original business type is _cs . However, in the following description, it will not be distinguished between the number and the aggregated value of the attribute data, and both cases will be expressed as ^xh .

Referring to FIG. 11 again, in step S24, the rank assigning unit 105 calculates, for each x within 0≦x≦wh, the probability p ^h (x) that the amount of work performed by the personnel _h is greater than or equal to x. Rank assigning section 105 calculates probability p _h (x) as follows.

When the calculation of the probability distribution and the correction value has been completed (step S21; Yes), the flow proceeds to step S25.

FIG. 13 schematically shows an example of the probability calculation process shown in step S24 of FIG. In step S40 of FIG. 13, the rank assigning unit 105 sets x to 0. In step S41, the rank assigning unit 105 determines whether x is greater than ^wh .

If x is less than or equal to ^wh (step S41; No), the flow proceeds to step S42. In step S42, the rank assigning unit 105 calculates the probability _ph (x) that the amount of work performed is x or more based on the probability distribution ^ψh (xh) of the amount of work performed for the target work type of the personnel ^h . In step S43, the rank assigning unit 105 increases x by one. After that, the flow returns to step S41.

If x is greater than ^wh (step S41; Yes), the flow ends.

(2-2-3) Rank Assignment Based on Correction Value of Work Amount of Work Performed Referring to FIG. 11 again, in step S25, the rank assigning unit 105 assigns ranks to personnel in descending order of the correction value of the amount of work performed. In the following, a human resource (k-th human resource) to which rank k is assigned will be referred to as human resource h(k).

(2-2-4) Calculation of Probability of No Reversal of Work Quantity Between Ranks In step S26, has the rank assigning unit 105 calculated the probability of no reversal of work quantity for all ranks? determine whether or not If probabilities have not been calculated for any of the ranks (step S26; No), the flow proceeds to step S27.

In step S27, the rank assigning unit 105 selects one rank among the ranks for which probabilities have not been calculated. Let H be a set of personnel for which the probability of no reversal in the amount of work performed between ranks is to be calculated, and |H| be the number of personnel included in the set H.

In step S28, the rank assigning unit 105 calculates the probability that the amount of work performed will not reverse.

A method of calculating the probability _Pk that the amount of work performed for the work type _cs does not reverse between the 1st to kth personnel and the (k+1)th and subsequent personnel will be described.

First, the minimum value of the amount of work performed for the work type c _s of the 1st to k-th personnel is greater than or equal to x and less than x+ ₁ . As described above, the probability q _k (x) that there is at least one person who is exactly x, not all of whom are x+1 or more, can be expressed by the following formula.

Here, the minimum value of the total amount of work performed by the 1st to k-th personnel, regardless of the type of work, is

Then, since the probability that the minimum value of the work performance amount of the work type c _s of the 1st to k-th personnel is greater than τ ^k _min is zero, q _k (τ ^k _min ) can be obtained as shown in the following formula. .

Rank assigning section 105 calculates the value of q _k (τ ^k _min ) using the above formula. Thereafter, rank assigning section 150 assigns q _k (τ ^k _min −1), q _k (τ ^k _min −2), . . . , q _k (0) are calculated in order.

Furthermore, the probability that the amount of work performed for work type c _s is less than x is

is. When the minimum value of the work performance amount of the work type cs of the 1st to k-th personnel is ₀ or more and less than 1, when it is 1 or more and less than 2, . . . If ^τ km _min or more and less than ^τ km _min +1, they are mutually exclusive. Therefore, the probability _Pk that there is no reversal in the amount of work performed for the work type _cs between the 1st to kth personnel and the (k+1)th and subsequent personnel can be calculated by the following formula.

FIG. 14 schematically shows an example of the probability calculation process shown in step S28 of FIG. In step S50 of FIG. 14, the rank assigning unit 105 calculates the minimum value τ ^k _min of the total amount of work performed by the 1st to k-th personnel regardless of the work type. In step S51, the rank assigning unit 105 sets x to τ ^k _min .

In step S52, the rank assigning unit 105 calculates q _k (τ ^k _min ) for the probability q _k (x) that the minimum value of the work performance amount of the work type c _s of the 1st to k-th personnel is x or more and less than x+1. Calculate In step S53, the rank assigning unit 105 sets v to q _k (τ ^k _min ).

If x>0 (step S54; Yes), the flow proceeds to step S55. In step S55, the rank assigning unit 105 reduces x by one.

In step S56, the rank assigning unit 105 calculates u by the following formula.

In step S57, the rank assigning unit 105 calculates q _{x (x) by q x (} x)=u−ν. In step S58, the rank assigning unit 105 sets ν to u.

If x≦0 (step S54; No), the flow proceeds to step S59. In step S59, the rank assigning unit 105 calculates the probability _Pk .

The processing for calculating the probability Pk described above is performed with _k =1, 2, . . . , |H| ₋₁ , for each rank k, the probability P _k Calculate the value of

Alternatively, as the probability _Pk , the probability that there is no reversal in the amount of work performed for the work type _cs between the k-th personnel and the k+1-th personnel may be used. The probability that the amount of work performed by the k+1st personnel for work type c _s is less than x is 1−p _h(k+1) (x), and if the amount of work performed for work type c _s by the kth personnel is 0 , 1, then . . . , w ^h(k) are mutually exclusive. Therefore, the probability _Pk can be calculated by the following formula.

Referring to FIG. 11 again, if probabilities have been calculated for all ranks (step S26; Yes), the flow proceeds to step S29.

(2-2-5) Grouping of Orders In step S29, the order assigning unit 105 assigns probabilities P ₁ , P ₂ , . . . , P _k , . . . Group ranks based on Let _H0 be a set of human resources to be grouped according to rank.

The order grouping is performed by repeating a process including a step of determining whether division is necessary, a step of determining a division position if division is to be performed as a result of the determination, and a step of determining whether or not to apply the division. Executed by The division position is information indicating between what number of personnel and what number of personnel to divide.

FIG. 15 schematically shows the rank grouping operation of the rank assigning unit 105. FIG. In step S60 of FIG. 15, the rank assigning unit 105 groups all the ranks into one group.

In step S61, the rank assigning unit 105 determines whether group division is necessary. If division is unnecessary (step S61; No), the flow ends.

If division is necessary (step S61; Yes), the flow proceeds to step S62. In step S62, the rank assigning unit 105 determines the dividing positions of the groups. For example, the rank assigning unit 105 decides to divide the group between the kth rank and the k+1th rank.

In step S63, the rank assigning unit 105 determines whether or not to apply division. If division is not applied (step S63; No), the flow ends.

When division is applied (step S63; No), the flow proceeds to step S64. In step S64, the rank assigning unit 105 divides the group at the determined division position. The flow returns to step S61.

A method of determining whether division is necessary, a method of determining division positions, and a method of determining whether division is to be applied will be described below. Then, the division up to a certain point in time results in between positions k ₁ and k ₁ +1, between positions k ₂ and k ₂ +1, . . . , _km and _km +1. Also, at this time, m+1 groups, that is, a set of human resources are represented as follows.

(2-2-5-1) Method for Determining Necessity of Division In the first determination method, the searcher specifies the maximum number k _max of the number of persons to be selected together with the type of work to be searched. The rank assigning unit 105 determines that division is necessary when the number |H _{1 to k1} | of personnel belonging to the highest group is greater than k _max , and division is unnecessary when it is equal to or less than k _max . It is determined that This makes it possible to present the most meaningful selection criteria to the searcher after considering classification errors when selecting k _max or less human resources.

In the second determination method, the searcher specifies the maximum value k _max of the number of people to be selected together with the type of work to be searched. The rank assignment unit 105 determines that division is necessary when the k _max rank and the k _max +1 rank belong to the same group, and determines that the division is necessary when the k _max rank and the k _max +1 rank belong to different groups. , it is determined that division is unnecessary. As a result, if the searcher selects a person ranked k _max and does not select a person ranked k _max +1, the searcher is informed that there is a more meaningful selection criterion after considering the classification error. can be presented.

In the third determination method, the searcher specifies the minimum value k _min and the maximum value k _max of the number of people to be selected together with the type of work to be searched. Rank assigning section 105 determines that division is necessary when the k _min rank and k _max rank belong to the same group, and divides when the k _min rank and k _max rank belong to different groups. determined to be unnecessary. As a result, when selecting human resources from k _min to k _max people, it is possible to present searchers with options for how to determine the number of people that are meaningful in consideration of classification errors.

In the fourth determination method, the searcher specifies the minimum value k _min and maximum value k _max of the number of people to be selected, along with the type of work to be searched. If the k _max rank and the k _max +1 rank belong to the same group, or if the k _min rank and the k _max rank belong to the same group, the rank assigning unit 105 determines that division is necessary, Otherwise, it is determined that division is unnecessary. The fourth determination method has the effects of both the second determination method and the third determination method.

In the fifth determination method, the searcher specifies the maximum value _mmax of the number of groups together with the business type to be searched. The rank assigning unit 105 determines that division is necessary when the number of groups is less than m _max , and determines that division is unnecessary when the number of groups is greater than or equal to m _max .

Determination of necessity of division may be made using a combination of any of the first to fourth determination methods and the fifth determination method. As the determination condition, a disjunction of the conditions in the determination method to be combined may be used, or a concatenation thereof may be used.

The rank assigning unit 105 does not need to determine whether division is necessary. That is, the process of step S61 may be deleted in the flow shown in FIG. In this case, whether or not to continue the division depends on the division application determination.

(2-2-5-2) Method of determining division position “Division of group at division position k” means between k-th and k+1-th personnel (between k-th personnel and k+1-th personnel) shall mean to split the group. Furthermore, let _Kc be a set of ranks that are not applied as division positions. In the initial state where no division has been performed, K _c ={1, 2, . . . , k, . . . , |H ₀ |−1}.

Probability _Pk is the probability that there will be no reversal in the amount of work performed between the 1st to kth personnel and the k+1th and subsequent personnel, or between the kth personnel and the k+1th personnel. A probability _Pk is calculated for each rank between 1st and 2nd, between 2nd and 3rd, and so on. Here, even if the possibility of misclassification is taken into account, reversal is less likely to occur between ranks with a larger value of probability _Pk , and the difference in ranks is significant. Conversely, the smaller the value of the probability _Pk , the more likely a reversal occurs due to a classification error, and the difference in the order is meaningless.

The rank assigning unit 105 selects k that maximizes the probability P _k from the set K _c as the division position. Alternatively, when the groups H _{ka to kb} are divided at the division position k′ by the previous division to generate the groups H _{ka to k′} and H _{k′+1 to kb} , the rank assigning unit 105 assigns the ranks _ka ~ k'-1, k'+1 ~ k _b -1, recalculate and update the probability P _k that a reversal does not occur in the amount of work performed, and then set the k at which the probability P _k is the maximum as the division position You may choose.

(2-2-5-3) Determining Method of Division Application The searcher specifies the minimum value P _min of the probability that the reversal will not occur together with the type of work to be searched. The rank assigning unit 105 determines to apply the division when the probability that the inversion does not occur at the determined division position is equal to or greater than P _min , and determines not to apply the division when the probability is less than P _min .

The rank assigning unit 105 does not have to determine division application. That is, the process of step S63 may be deleted in the flow shown in FIG. In this case, whether or not to continue the division is entrusted to the determination of necessity of division.

At first, the method of group division was explained assuming that all human resources belonged to the same group. Conversely, a method of sequentially integrating groups assuming that all personnel belong to different groups may be used. In this case, the rank assigning unit 105 integrates the groups in descending order of the probability _Pk of no reversal of the amount of work performed.

(3) Effects The information presentation device 11 classifies a plurality of work logs from a classification point of view corresponding to the target work type, which is the work type specified by the searcher, thereby obtaining work logs related to the target work type. , Based on the work log related to the target work type, calculate the amount of work performed by each personnel, assign a rank to the personnel based on the calculation result of the amount of work performed for the target work type, and rank the assigned result is presented to the explorer. As a result, it is possible to present to the searcher personnel who have extensive work experience in the target work type.

A work log is automatically recorded as work is performed, and the amount of work performed, which indicates the richness of work experience, is calculated from the work log. As a result, it is not necessary for the person in charge of the work, his superior, or the person in charge of human resources to update the database by explicitly registering the work report in the database. Furthermore, it becomes possible to search for the right person based on the latest status.

As business logs, it is possible to use not only information handled in business, but also video data and sensor data. Instead of using the business logs as they are, they are classified into business types, and based on the classification result, the amount of work performed for the target business type is calculated. As a result, the information presentation method according to the embodiment can be applied to work other than desk work.

Ranking is performed based on the amount of work performed for the target work type. As a result, the information presentation method according to the embodiment can be applied to a work system in which each person has multiple work types.

The information presentation device 11 may present to the searcher control information prepared for each type of work or information describing conditions for preparing the control information. As a result, the searcher can confirm whether the type of work to be specified is the type of work intended by the searcher. As a result, it becomes possible for the searcher to specify his/her intended business type. The information presentation device 11 may receive a task type designated for each of a plurality of classification viewpoints. As a result, it is possible to designate a business type that is close to the searcher's intention.

The information presentation device 11 corrects the calculation result of the amount of work performed based on the uncertainty information indicating the tendency of classification errors from the classification viewpoint corresponding to the target work type, and ranks the personnel based on the corrected calculation result. may be assigned. As a result, even if the calculation result of the amount of work performed is uncertain due to the classification error, the influence of the classification error can be mitigated.

Furthermore, based on the uncertainty information, the information presentation device 11 may calculate the probability of a reversal in the amount of work performed between ranks, and group the ranks based on the calculated probabilities. As a result, each group will include people who can be considered to have the same level of work experience. As a result, it becomes possible for the searcher to easily compare the richness of work experience of human resources.

(4) Modification Work is not limited to occupational activities, and may be any activities. The amount of work performed is an example of an evaluation index relating to the performance of work by human resources. For example, if the business log is a record of test results such as an in-house qualification test or an external qualification test, the evaluation index is based on the test results. Also, human resources are only an example of objects. An object may be, for example, a document, a vocabulary, or the like. For example, it is possible for a person to easily grasp in what type of work a document or vocabulary is used in place of what type of work a human resource performs well.

It should be noted that the present invention is not limited to the above embodiments, and can be variously modified in the implementation stage without departing from the scope of the invention. Further, each embodiment may be implemented in combination as appropriate, in which case the combined effect can be obtained. Furthermore, various inventions are included in the above embodiments, and various inventions can be extracted by combinations selected from the disclosed plurality of components. For example, even if some components are deleted from all the components shown in the embodiments, if the problem can be solved and effects can be obtained, the configuration in which these components are deleted can be extracted as an invention.

DESCRIPTION OF SYMBOLS 10... Information processing system 11... Information presentation apparatus 12... Business log acquisition apparatus 101... Acquisition part 102... Designation part 103... Classification part 104... Work performance amount calculation part 105... Rank assignment part 106... Allocation result presentation part 107... Control information Presentation unit 111 Business log storage unit 112 Control information storage unit 113 Classification result storage unit 114 Calculation result storage unit 115 Uncertainty information storage unit 116 Allocation result storage unit 151 Processor 152 RAM
153 Program memory 154 Storage device 155 Input/output interface

Claims (8)

1. a designation unit that receives a target work type, which is a work type designated by a searcher from among a plurality of classification viewpoints, which is a classification destination when the work is classified according to each of the plurality of classification viewpoints;
   a classification unit that obtains a work log related to the target work type by classifying a plurality of work logs indicating records related to objects and work from a classification point of view corresponding to the target work type;
   a calculation unit that calculates an evaluation index of the target work type for each object based on a work log related to the target work type;
   a rank assigning unit that assigns a rank to the object based on the calculation result of the evaluation index of the target task type;
   an assignment result presenting unit that presents the result of assigning the ranking to the searcher;
   Information presentation device.
2. The designation unit receives, as the target business type, a first business type belonging to a first classification viewpoint and a second business type belonging to a second classification viewpoint different from the first classification viewpoint,
   The classification unit obtains a first business log related to the first business type from the plurality of business logs, and obtains a second business log related to the second business type from the plurality of business logs. obtaining the intersection of the first business log and the second business log as the business log related to the target business type;
   The information presentation device according to claim 1.
3. The rank assigning unit corrects the calculation result based on uncertainty information indicating a tendency of classification errors from the classification viewpoint corresponding to the target task type, and assigns the object to the object based on the corrected calculation result. assign ranks,
   The information presentation device according to claim 1 or 2.
4. The uncertainty information is generated based on the ratio of misclassified business logs in the business type to be classified in the result of trial implementation of business log classification,
   The information presentation device according to claim 3.
5. The rank assigning unit calculates a probability of occurrence of a reversal in the evaluation index between the ranks based on the uncertainty information and the calculation result, groups the ranks based on the calculated probability,
   The allocation result presentation unit presents the allocation result of the ranking including the grouping result of the ranking to the searcher.
   5. The information presentation device according to claim 3 or 4.
6. a control information storage unit, prepared for each of the plurality of work types, storing control information for determining whether or not the work log corresponds to the work type;
   a control information presenting unit that presents the searcher with information describing the control information or conditions for preparing the control information;
   further comprising
   wherein the classification unit classifies the plurality of business logs based on the control information related to the business type included in the classification viewpoint corresponding to the target business type;
   The information presentation device according to any one of claims 1 to 5.
7. Receiving a target work type, which is a work type specified by a searcher, from among a plurality of work types to be classified when the work is classified according to each of the plurality of classification viewpoints;
   Obtaining a work log related to the target work type by classifying a plurality of work logs indicating records related to objects and work from a classification point of view corresponding to the target work type;
   calculating an evaluation index for the target work type for each object based on a work log related to the target work type;
   assigning ranks to the objects based on the calculation results of the evaluation index for the target task type;
   presenting the ranking assignment result to the searcher;
   An information presentation method comprising:
8. A program for causing a computer to function as each unit included in the information presentation device according to any one of claims 1 to 6.
   

Images