JP2017016405A - Business analysis program, device and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the calculation accuracy of a work time or work volume in the case where non-routine business in which correspondence between business and performed work is not uniquely determined is included in an analysis object.SOLUTION: A method finds the distribution of words of business from business achievement information obtained by the execution of the analysis object business, and finds the topic distribution of the business from the distribution of words of the business and the distribution of words every topic (212-218). In addition, it finds the distribution of words of one work from work contents information on the one work of which the execution period is overlapped with that of the business, and finds the topic distribution of the work from the distribution of words of the work and the distribution of words every topic, calculates the degree of relation between the topic distributions of the business and the work, adds a value obtained by multiplying the work time of the work by the degree of relation to the work time of the business for each work of which the execution time is overlapped with that of the business, and thereby calculates the work time of the business (220-238).SELECTED DRAWING: Figure 6

Description

  The disclosed technology relates to a business analysis program, a business analysis device, and a business analysis method.

  2. Description of the Related Art Conventionally, techniques for measuring work time have been proposed for the purpose of business management, analysis, improvement, and the like. For example, based on information such as keywords and email addresses that have been set in advance, it is determined whether or not an operation on an arbitrary object on the computer is an operation related to a business to be investigated, and a history of operations related to the business to be investigated is logged. The technique of extracting as is proposed.

JP 2012-88857 A

  In general, tasks can be standardized such as data entry and slip arrangement and the same results can be obtained without depending on the worker, and processes such as research and surveys that are difficult to standardize and process of thinking and judgment And atypical work that requires The above-described technique is suitable for routine work, but when applied to atypical work, there is a problem that only a value lacking in accuracy can be obtained as the work time or work amount of the target atypical work.

  In other words, since the work to be carried out is not standardized and the work is carried out while repeating trial and error, it is rare that the work carried out corresponds completely to the work, It may happen that the work performed corresponds to multiple tasks. For example, in the survey work that is one of atypical work, when the work to search for materials is carried out, the materials browsed in the search work include many materials that are not related to the search object. It is not appropriate to include all work hours in the work time of the aforementioned survey work. On the other hand, there may be cases where materials that are not closely related to the survey object included in the browsed materials can be used for other survey work, and in this case, it is necessary to include a part of the search work time in another survey work. .

  As described above, in an atypical work, since the correspondence between the work and the work performed is not uniquely determined, it is difficult to accurately calculate the work time or the work amount even if the above-described technique is applied.

  In one aspect, an object of the present invention is to improve the calculation accuracy of work time or work amount when an atypical work whose correspondence between the work and the work performed is not uniquely determined is included in the analysis target.

  In one embodiment, a computer is caused to execute processing including the following processing. First, from the work history information including information related to the work contents of each of the plurality of work performed in performing the work to be analyzed and information on the work time or work amount of each of the plurality of work, First semantic component information representing contribution to a plurality of semantic contents in each is calculated. The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and each of the plurality of operations Based on the work time or work amount, the work time or work amount of the work to be analyzed is calculated.

  As one aspect, there is an effect that the calculation accuracy of the work time or the work amount is improved when the analysis target includes an atypical work whose correspondence between the work and the work performed is not uniquely determined.

It is a functional block diagram of a business analysis system. It is a schematic block diagram of a computer system that can function as a business analysis system. It is a chart which shows an example of the contents of business information DB. It is a chart which shows an example of the contents of work history information DB. It is a chart which shows an example of the contents of word distribution DB for every topic. It is a flowchart which shows the content of the work analysis process. It is explanatory drawing explaining the calculation of the relevance degree of the distribution of the topic of work and work.

  Hereinafter, an example of an embodiment of the disclosed technology will be described in detail with reference to the drawings. In the following embodiments, “business” means occupational work that is continuously performed every day. The “business” to be processed in the present embodiment is an “atypical business”. Hereinafter, the “non-standard business” is simply referred to as “business”. Further, in the following embodiments, “work” means individual work that is sequentially performed in performing the work. Usually, a certain task includes a plurality of tasks, and one task is performed by performing the tasks. Since atypical work is not standardized, in many cases, the worker does not accurately recognize each work to be performed in performing a certain work, and each work is not thought or judgment. The work content is determined and implemented through trial and error through the process.

  FIG. 1 shows a business analysis system 10 according to the present embodiment. The work analysis system 10 is a system that supports the execution of work by a worker (and the execution of work associated with the execution of the work), and performs processing for accumulating work and work information and analyzing the work. The business analysis system 10 includes a business performance support device 12 and a business management analysis device 18, and the business performance support device 12 and the business management analysis device 18 are connected to be communicable.

  The business execution support device 12 is used by a worker who performs a business. The work execution support device 12 provides the worker with functions (for example, a web browsing function, a document creation function, a drawing creation function, etc.) corresponding to the work performed by the worker (work to be performed). Process that supports the execution of work (work execution) by.

  The business performance support apparatus 12 includes a business information registration / update unit 14 and a work information collection / transmission unit 16. In the business analysis system 10, when a worker starts performing a certain business, information on the business to start the performance (business information) is input to the business performance support device 12 by the worker. In this case, the business information registration / updating unit 14 transmits the business information input by the worker to the business management analysis device 18 so that the transmitted business information is stored in the business management analysis device 18 (the business information DB (DataBase described later). ) 34).

  Further, in the business analysis system 10, when execution of a certain business is completed, additional information (for example, business product information) to the business information is designated or input to the business performance support apparatus 12 by the worker. In this case, the business information registration / updating unit 14 transmits the additional information to the business information specified or input by the worker to the business management analysis device 18 so that the business information registered in the business management analysis device 18 is obtained. Update.

  The work information collection / transmission unit 16 collects information on work performed by the worker using the work performance support apparatus 12 for each preset work unit. The unit of work may be one to several actions (for example, mouse gestures, keystrokes, etc.) in the operation by the operator, or may be a unit of switching of an active window, or a certain time. It is good also as a unit.

  The work information collected by the work information collection / transmission unit 16 includes information indicating the work type, information indicating the start and end dates of the work, and information related to the work content (hereinafter referred to as work content information). . For example, if the work is a web search, the information related to the work content includes the search word specified by the worker and the information on the web page browsed by the worker. For example, if the work is a document or drawing creation A created document or drawing file. Then, the work information collection / transmission unit 16 transmits the collected work information to the work management analysis apparatus 18 to register the transmitted work information in the work management analysis apparatus 18 (a work history information DB 36 described later).

  The business management analysis device 18 includes a business information management unit 20, a work history information management unit 22, a morpheme analysis unit 24, a word distribution calculation unit 26, a topic appearance distribution calculation unit 28, a work time calculation unit 30, and a storage unit 32. Yes. The storage unit 32 stores a business information DB 34, a work history information DB 36, and a word distribution DB 38 for each topic.

  The business information management unit 20 receives the business information from the business information registration update unit 14 of the business performance support apparatus 12 and registers the received business information in the business information DB 34 stored in the storage unit 32. As shown in FIG. 3, the business information DB 34 is provided with fields of “business ID”, “title”, “description”, “status”, “start date / time”, “end date / time”, and “business result information”. Each business information is registered in each record.

  In the “business ID” field of the business information DB 34, a business ID for identifying each business is assigned by the business information management unit 20 when new business information is registered (when the business is started). Granted and set. In the “title” field, the title of the business included in the business information received from the business information registration update unit 14 at the start of business execution is set. In the “description” field, an explanatory text representing the content of the business included in the business information received from the business information registration / update unit 14 at the start of business execution is set. In the “status” field, information indicating the progress status of the work included in the work information appropriately received from the work information registration / updating unit 14 is set.

  In the “start date / time” field, the date / time when the business information is received from the business information registration / update unit 14 at the start of business execution is set by the business information management unit 20. In the “end date and time” field, the date and time when the business information is received from the business information registration / update unit 14 when the business is completed is set by the business information management unit 20. In the “work result information” field, information on work results (for example, reports obtained by performing the work) included in the work information received from the work information registration / updating unit 14 at the end of the work is registered. Is done. The business result information is an example of information related to the business content in the disclosed technology.

  FIG. 3 shows an example in which information including text is registered in the “business result information” field of the business information DB 34, but the business result information includes, for example, image information and audio information. Other types of information may be used. Each time the business information management unit 20 receives business information from the business information registration / update unit 14, the received business information is registered in the business information DB 34, so that the business performance support apparatus 12 is used for the business information DB 34. The business information of the business performed in this way is stored and stored. In addition to registering the business information received from the business information registration / updating unit 14 in the business information DB 34, the business information management unit 20 stores the instructed business information in response to an instruction from the word distribution calculation unit 26 or the like. Processing of reading out from the information DB 34 and transferring it is also performed.

  The work history information management unit 22 receives the work information from the work information collection / transmission unit 16 of the work performance support apparatus 12 and stores the received work information as work history information in the work history information DB 36 stored in the storage unit 32. sign up. As shown in FIG. 4, the work history information DB 36 includes fields of “work ID”, “work type”, “work start date / time”, “work end date / time”, “work time”, and “work content information”. The information of each work is registered in each record.

  In the “work ID” field of the work history information DB 36, a work ID for identifying each work is assigned and set by the work history information management unit 22 when the work information is registered. In the “work type” field, the work type included in the work information received from the work information collection / transmission unit 16 of the work performance support apparatus 12 is set. The work history information management unit 22 sets the work start date and time included in the work information received from the work information collection and transmission unit 16 in the “work start date and time” field. The work history information management unit 22 sets the work end date and time included in the work information received from the work information collection and transmission unit 16 in the “work end date and time” field.

  In the “work time” field, the work history information management unit 22 calculates a value (= work time) obtained by subtracting the work start date and time from the work end date and time included in the work information received from the work information collection and transmission unit 16. Is set. In the “work content information” field, work content information included in the work information received from the work information collection / transmission unit 16 is registered. The work content information is an example of information related to the work content in the disclosed technology.

  4 shows an example in which information including text is registered in the “work content information” field of the work history information DB 36. However, the work content information may be other information such as audio information. It may be in the form of information. Each time the work history information management unit 22 receives work information, the work history information DB 36 registers the received work information as work history information in the work history information DB 36, so that the work performance support apparatus 12 is used for the work history information DB 36. The work history information of the work carried out is accumulated and stored. In addition to registering the work information received from the work information collection / transmission unit 16 in the work history information DB 36, the work history information management unit 22 is instructed according to an instruction from the word distribution calculation unit 26 or the like. A process of reading information from the work history information DB 36 and transferring it is also performed.

  The morpheme analysis unit 24 receives work result information or work content information as a morpheme analysis target from the word distribution calculation unit 26, extracts words included in the transferred information, and counts the number of appearances of each word. Perform morphological analysis. Then, the word distribution calculation unit 26 hands over the word extracted by the morphological analysis process and the number of appearances of each word to the word distribution calculation unit 26 that is a request source of the morphological analysis. In the morpheme analysis process, a word (referred to as a stop word) that does not reflect the content of information to be subjected to morpheme analysis, such as a symbol or an overly general word, is to be delivered to the word distribution calculation unit 26. It is preferable to perform stop word processing to be excluded from. However, the above stop word processing is not essential and can be omitted.

  The word distribution calculation unit 26 acquires, from the business information management unit 20, business result information of a business to be calculated when calculating a word distribution in a specific business in a business analysis process described later. Next, the word distribution calculation unit 26 hands over the business result information acquired from the business information management unit 20 to the morpheme analysis unit 24 and requests execution of the morpheme analysis processing. When the word distribution calculation unit 26 obtains the result of the morphological analysis process (the word that appears in the work result information and the information indicating the number of appearances of each word) from the morpheme analysis unit 24, the word distribution calculation unit 26 performs a specific work based on the obtained information. The word distribution (appearance frequency of each word in the work result information) is calculated.

  In addition, the word distribution calculation unit 26 acquires the work content information of the calculation target work from the work history information management unit 22 when calculating the word distribution in a specific work in the task analysis process described later. Next, the word distribution calculation unit 26 hands over the work content information acquired from the work history information management unit 22 to the morpheme analysis unit 24 and requests execution of the morpheme analysis process. When the word distribution calculation unit 26 acquires the result of the morpheme analysis process (information indicating the word appearing in the work content information and the number of appearances of each word) from the morpheme analysis unit 24, the word distribution calculation unit 26 performs a specific work based on the acquired information. The word distribution (appearance frequency of each word in the work content information) is calculated.

  The topic appearance distribution calculation unit 28 obtains the word distribution of the business to be analyzed calculated by the word distribution calculation unit 26 when calculating the topic distribution in the business to be analyzed in the business analysis processing described later. Then, based on the acquired word distribution of the business to be analyzed and the word distribution for each topic stored in the word distribution DB 38 for each topic, the distribution of topics in the business to be analyzed is calculated. Details of the topic will be described later. The word distribution for each topic stored in the word distribution DB 38 for each topic is calculated by the word distribution calculation unit 26.

  Further, the topic appearance distribution calculation unit 28 acquires the word distribution of the specific task calculated by the word distribution calculation unit 26 when calculating the topic distribution in the specific task in the task analysis process described later. Then, based on the acquired word distribution of the specific work and the word distribution for each topic stored in the word distribution DB 38 for each topic, the distribution of the topic in the specific work is calculated.

  The work time calculation unit 30 determines the relevance between the topic distribution in the analysis target task calculated by the topic appearance distribution calculation unit 28 and the topic distribution in a specific task calculated by the topic appearance distribution calculation unit 28. calculate. Further, the work time calculation unit 30 is based on the calculated relevance and the work time of the specific work stored in the work history information DB 36, and the work time that has contributed to the work to be analyzed among the work time of the specific work. Is calculated. Then, the work time calculation unit 30 calculates the work time of the work to be analyzed by performing the above-described processing for each work in which the execution period overlaps with the work to be analyzed.

  The business management analysis device 18 is an example of a business analysis device according to the disclosed technology, and the topic appearance distribution calculation unit 28 is an example of a first calculation unit (and a third calculation unit) in the disclosed technology. The work time calculation unit 30 is an example of a second calculation unit in the disclosed technology, and the word distribution calculation unit 26 is an example of a fourth calculation unit in the disclosed technology.

  The business analysis system 10 can be realized by a computer system 40 shown in FIG. The computer system 40 shown in FIG. 2 includes a business management analysis server 70 and a plurality of business performance support terminals 44 connected to the business management analysis server 70 via the network 42. The network 42 may be the Internet, but the network 42, the business management analysis server 70, and a plurality of business performance support terminals 44 may form an intranet installed in a certain company. In this case, the network 42 is connected to the Internet 48 via the firewall 46.

  The business performance support terminal 44 is used by a worker who performs business (implements work), and as shown in FIG. 2, a CPU 50, a memory 52, a storage unit 54, an input unit 56 including a keyboard and a mouse, a display unit, and the like. 58 and a communication interface (I / F) unit 60. The CPU 50, the memory 52, the storage unit 54, the input unit 56, the display unit 58, and the communication I / F unit 60 are connected to each other via a bus 62. The business execution support terminal 44 is connected to the network 42 via the communication I / F unit 60.

  An application program 64, a business information registration / update program 66, and a work information collection / transmission program 68 are installed in the storage unit 54 of the business performance support terminal 44. The CPU 50 executes the application program 64 to provide the worker with a function (for example, a web browsing function) according to the task performed by the worker (work to be performed), and perform the task (work) by the worker. To support the implementation). The CPU 50 functions as the business information registration / update unit 14 by executing the business information registration / update program 66, and functions as the work information collection / transmission unit 16 by executing the work information collection / transmission program 68. As a result, the business performance support terminal 44 functions as the business performance support device 12.

  On the other hand, the business management analysis server 70 includes a CPU 72, a memory 74, a storage unit 76, an input unit 78, a display unit 80, a medium read / write device (R / W) 82, and a communication I / F unit 84. The CPU 72, the memory 74, the storage unit 76, the input unit 78, the display unit 80, the medium read / write device 82, and the communication I / F unit 84 are connected to each other via a bus 86. The medium read / write device 82 reads information written on the recording medium 88 and writes information on the recording medium 88. The business management analysis server 70 is connected to the network 42 via the communication I / F unit 84.

  The storage unit 76 can be realized by an HDD (Hard Disk Drive), a flash memory, or the like. The storage unit 76 stores a business information DB 34, a work history information DB 36, and a word distribution DB 38 for each topic. The storage unit 76 stores a business information management program 90, a work history information management program 92, and a business analysis program 94. In these programs 90, 92, and 94, the recording medium 88 on which the programs 90, 92, and 94 are written is set in the medium read / write device 82, and the medium read / write device 82 reads the programs 90, 92, and 94 from the recording medium 88. Is stored in the storage unit 76. The CPU 72 reads out the programs 90, 92, and 94 from the storage unit 76, expands them in the memory 74, and sequentially executes processes included in the programs 90, 92, and 94.

  The CPU 72 functions as the business information management unit 20 by executing the business information management program 90. The CPU 72 functions as the work history information management unit 22 by executing the work history information management program 92. The task analysis program 94 includes a morphological analysis process 96, a word distribution calculation process 98, a topic appearance distribution calculation process 100, and a work time calculation process 102. The CPU 72 functions as the morpheme analysis unit 24 by executing the morpheme analysis process 96. The CPU 72 functions as the word distribution calculation unit 26 by executing the word distribution calculation process 98. Further, the CPU 72 functions as the topic appearance distribution calculating unit 28 by executing the topic appearance distribution calculating process 100. The CPU 72 functions as the work time calculation unit 30 by executing the work time calculation process 102.

  As a result, the business management analysis server 70 that has executed the programs 90, 92, 94 functions as the business management analysis device 18, and the computer system 40 functions as the business analysis system 10. The business analysis program 94 is an example of a business analysis program related to the disclosed technology.

  Next, the operation of this embodiment will be described. As explained earlier, atypical work is carried out by repeating trial and error, and the correspondence with the work performed is not uniquely determined. It was difficult to calculate.

  For example, in the case of routine work, a keyword specific to each work is set in advance, and the work corresponding to the work performed is determined based on whether or not the keyword is included in the information of the work performed. It is logically possible to do this. However, in this technology, the accuracy of determination of the corresponding work depends on the setting accuracy of the keyword, and it is difficult to set keywords accurately in advance for non-standard work where the work to be performed is not standardized. , Judgment accuracy of the corresponding business is greatly insufficient. In addition, the work performed in atypical work may correspond to multiple atypical work, but the above technology is based on the assumption that work and work correspond one-to-one. Is not considered when it corresponds to multiple atypical tasks.

  On the other hand, in recent years, topic models have attracted attention as techniques for estimating potential topics, fields, and rough meanings hidden in various data (discrete data), that is, topics by information processing (machine learning). In the topic model, there is an idea that a topic is considered as a probability corresponding to each word appearing in the discrete data, and the discrete data is represented by a mixture of a plurality of topics (for example, LDA: Latent Dirichlet Allocation). This way of thinking is considered to have a high affinity with the calculation of working hours of non-standard work.

  In other words, it is considered that each work carried out in carrying out a certain routine job potentially includes a plurality of semantic contents (multiple types of work corresponding to) with a certain distribution (contribution ratio). Can do. Further, it can be considered that the atypical business itself potentially includes a plurality of semantic contents with a certain distribution (contribution ratio). Here, the above semantic content can be handled equivalently to a topic in the concept of representing discrete data by a mixture of a plurality of topics. The relevance of the distribution of a plurality of topics (meaning content) potentially included in a certain work to the distribution of a plurality of topics (meaning content) potentially included in the work to be analyzed It can be considered that this corresponds to the proportion of work corresponding to the work to be analyzed.

  Based on the above, in the present embodiment, when the business management analysis apparatus 18 calculates the work time of a certain business (the business to be analyzed), the business analysis processing shown in FIG. 6 is performed. In step 200 of the task analysis process, the word distribution calculation unit 26 determines whether the word distribution for each topic is stored in the word distribution DB 38 for each topic. If the determination in step 200 is affirmed, the process proceeds to step 212. If the determination in step 200 is negative, the process proceeds to step 202.

  The word distribution for each topic stored in the word distribution DB 38 for each topic includes information representing the appearance frequency of words appearing in discrete data in which only individual topics are potentially included for a plurality of topics. . For example, in FIG. 5, for each topic of “Cloud”, “Openstack”, and “Amazon (registered trademark)”, the frequency of occurrence of each word appearing in discrete data that potentially includes only the individual topic is individually The information associated with the name of the topic is shown. Below, when the determination of step 200 is denied, the aspect which produces the word distribution for every topic from the work information memorize | stored in work information DB34 is demonstrated with reference to step 202-step 210. FIG.

  First, in step 202, the word distribution calculation unit 26 instructs the business information management unit 20 to transfer business result information of a plurality of completed businesses used to create a word distribution for each topic. The business result information of a plurality of tasks transferred from the unit 20 is acquired.

  In the next step 204, the word distribution calculation unit 26 sets a corresponding topic for each business for which business result information is acquired from the business information management unit 20 based on the acquired business result information. For example, topics for individual tasks can be set as follows.

  For example, correspondence information that associates a word having an appearance frequency equal to or higher than a threshold in business result information of a business that potentially includes only one topic is set in advance for each of a plurality of topics. Then, the word with the highest appearance frequency in the work result information of the task setting target work is obtained, and the topic associated with the found word with the highest appearance frequency in the correspondence information is associated with the topic setting work. Set as topic. By performing the above-described processing for each of a plurality of business operations for which business result information has been acquired, topics corresponding to the plurality of business operations for which business result information has been acquired are set.

  In addition, a topic model includes a technique for presuming a topic as a latent variable and estimating it by an EM algorithm on the assumption that one topic is included in discrete data (for example, UM: Unigram Mixture). ). By applying this technique, a topic for each job may be estimated and set.

  In step 206, the word distribution calculation unit 26 divides the business result information of each business acquired from the business information management unit 20 into a plurality of groups with different corresponding topics based on the topics set for each business. . Thereby, business result information having the same corresponding topic belongs to the same group. Then, the word distribution calculation unit 26 passes all the business result information belonging to one group to the morpheme analysis unit 24 to request execution of the morpheme analysis process, and acquires the result of the morpheme analysis process from the morpheme analysis unit 24 Are sequentially performed for each group. Thereby, the word which appeared in work content information and the information showing the appearance frequency of each word are acquired for every individual group from which a corresponding topic differs.

  In the next step 208, the word distribution calculation unit 26 converts the number of appearances of each word acquired from the morphological analysis unit 24 for each group (for each topic) into the appearance frequency of each word, thereby for each group (for each topic). Create a word distribution of In step 210, the word distribution calculation unit 26 registers the created information indicating the word distribution for each topic in the word distribution DB 38 for each topic. Note that the above word distribution for each topic is an example of “a distribution of words belonging to individual semantic contents obtained in advance for a plurality of semantic contents” in the disclosed technique.

  In addition, it is considered that the accuracy of the word distribution for each topic created by the above process is improved as the amount of information used for creating the word distribution for each topic is larger. For this reason, instead of the business information stored in the business information DB 34 as data used to create the word distribution for each topic, any discrete data (for example, document data) accessible via the Internet 48, that is, a larger amount of data May be used.

  In addition, the word distribution once created for each topic can be basically used repeatedly, but depending on the type of topic, the word distribution for each topic may change over time. As an example, for technical terms such as “cloud”, “Openstack”, and “Amazon” shown in FIG. 5, the word distribution may change over time depending on the technical trend. For such a topic, once the word distribution for each topic is once created, the processing from step 202 to step 210 is periodically performed to periodically determine the word distribution for each topic stored in the word distribution DB 38 for each topic. You may make it update automatically.

  In the next step 212, the word distribution calculation unit 26 instructs the business information management unit 20 to transfer the business result information of the business to be analyzed. Get from 20.

  The work to be analyzed is not limited to a completed work, and may be a work in progress. Further, the task to be analyzed may be specified by operating the input unit 78 by an operator, for example. Also, for the business to be analyzed, for example, work that is in progress and work that has been completed and whose work time has not been calculated are displayed as candidates for analysis, and the operator selects the business to be analyzed from the displayed candidates. You may do it. Furthermore, for example, if there is one task that is a candidate for analysis, the task may be automatically selected as the task to be analyzed.

  In step 214, the word distribution calculation unit 26 hands over the business result information of the business to be analyzed acquired from the business information management unit 20 to the morpheme analysis unit 24 and requests execution of the morpheme analysis process. In addition, when the morpheme analysis process by the morpheme analysis unit 24 is completed, the word distribution calculation unit 26 acquires the result of the completed morpheme analysis process (the number of appearances of each word in the business to be analyzed) from the morpheme analysis unit 24.

  In step 216, the word distribution calculation unit 26 converts the number of appearances of each word in the analysis target job acquired from the morpheme analysis unit 24 into the appearance frequency of each word, thereby calculating the word distribution in the analysis target job. create.

In the next step 218, the topic appearance distribution calculation unit 28 calculates the topic distribution in the analysis target job based on the word distribution in the analysis target job and the word distribution for each topic. Then, the topic appearance distribution calculation unit 28 stores in the memory 74 information representing the distribution of topics in the calculated business to be analyzed. The word distribution in the business to be analyzed can be expressed as P ₀ (w | T) when considered as the distribution of words under the condition T. If the word distribution for each topic is Pw, The topic distribution P ₀ t in the business can be obtained by the following equation (1).
P ₀ t = Pw / P ₀ (w | T) (1)

  Note that the information representing the distribution of topics in the business to be analyzed obtained in step 218 is an example of second semantic component information representing contributions to a plurality of semantic contents (topics) in the business to be analyzed in the disclosed technology. .

  In the next step 220, the word distribution calculation unit 26 first instructs the business information management unit 20 to transfer the start date / time and end date / time of the business to be analyzed, thereby starting and ending date / time of the business to be analyzed. Is acquired from the business information management unit 20. The start date / time and end date / time of the business to be analyzed may be acquired at the same time when the business result information of the business to be analyzed is acquired in step 212 described above. Next, the word distribution calculation unit 26 notifies the work history information management unit 22 of the start date / time and end date / time of the task to be analyzed, and forwards the work content information of all tasks that overlap with the task to be analyzed. Instruct. Then, the word distribution calculation unit 26 acquires from the work history information management unit 22 the work content information of all work whose execution time overlaps with the work to be analyzed.

  In step 222, the work time calculation unit 30 substitutes 0 into a predetermined storage area on the memory 74 for storing the work time of the work to be analyzed. In step 224, the word distribution calculation unit 26 selects work content information of one work as a processing target from the work content information of each work acquired from the work history information management unit 22 in the previous step 220. .

  In the next step 226, the word distribution calculation unit 26 hands over the work content information of the work selected as the processing target in step 224 to the morpheme analysis unit 24 and requests execution of the morpheme analysis process. In addition, when the morpheme analysis process by the morpheme analysis unit 24 is completed, the word distribution calculation unit 26 acquires the result of the completed morpheme analysis process (the number of appearances of each word in the processing target process) from the morpheme analysis unit 24.

  In step 228, the word distribution calculation unit 26 creates the word distribution in the processing target work by converting the number of appearances of each word in the processing target work acquired from the morpheme analysis unit 24 into the appearance frequency of each word. .

In the next step 230, the topic appearance distribution calculation unit 28 calculates the topic distribution in the processing target work based on the word distribution in the processing target work and the word distribution for each topic. Then, the topic appearance distribution calculation unit 28 stores information representing the distribution of topics in the calculated work to be processed in the memory 74. Note that the word distribution in the work to be processed can be expressed as P _i (w | T) when considered as the word distribution under the condition T (i is a code for identifying each work, and i = 1,2,3, ...). Also, a word distribution for each topic putting the Pw, the distribution P _i t topic in the working of the processing target can be calculated by the following (2).
P _i t = Pw / P _i (w | T) (2)

  Note that the information representing the distribution of topics in the work to be processed obtained in step 230 is an example of first semantic component information representing contributions to a plurality of semantic contents (topics) in the work to be processed in the disclosed technique. .

In the next step 232, the work time calculation unit 30 calculates the degree of association between the topic distribution in the work to be analyzed calculated in step 218 and the topic distribution in the work to be processed calculated in step 230. The degree of relevance between the topic distribution P ₀ t in the business to be analyzed and the topic distribution P _i t in the work to be processed is, for example, the following (3) using the cosine similarity (vector inner product) of the topic vector as the relevance: It can be obtained by an expression.
Relevance (P ₀ t, P _i t) = cos (P ₀ t, P _i t) (3)

As an example, the topic vector of the task to be analyzed is (0,2,0,1,0,5,0,2), the topic vector of the task to be processed is (0,3,0,3,0,4, 0), the relevance (cosine similarity) is calculated as follows.
Relevance (work to be analyzed, work to be processed) =
(0,2,0,1,0,5,0,2) ・ (0,3,0,3,0,4,0) = 0.29 / √0.34√0.34 = 0.85

  Note that the degree of relevance is not limited to the application of cosine similarity (inner product of vectors) of topic vectors as described above. You may apply.

  In the next step 234, the work time calculation unit 30 compares the degree of association between the topic distribution of the business to be analyzed calculated in step 232 and the topic distribution of the work to be processed with a preset threshold value. It is determined whether or not the topic distribution is related. For example, 0 can be applied as the threshold value. In this case, if the degree of relevance> 0 (if there is a slight relevance between both topic distributions), it is determined that there is a relevance. In addition, when the above relevance is used as a coefficient for multiplying the work time of the work to be processed as shown in equation (4) described later, the work time of the work with relevance = 0 is included in the work time of the work to be analyzed. Not. Therefore, when the threshold value = 0 and the work time of the work to be processed is included in the work time of the work to be analyzed according to the later-described equation (4), the determination in step 234 can be omitted.

  Further, the threshold used for the determination in step 234 may be a value greater than 0 (threshold> 0). In this case, if the strength of the relationship between the topic distributions is equal to or greater than the threshold, it is determined that there is a relationship. It will be. The size of the threshold value when threshold value> 0 may be obtained, for example, by performing an experiment, for example, depending on the number of topics included in at least one topic distribution of the task to be analyzed and the task to be processed The threshold value may be adjusted accordingly.

  If the determination in step 234 is negative, it can be determined that the work to be processed is not related to the work to be analyzed, so the process returns to step 224, and another work whose work content information has been acquired in step 220 is returned to step 224. The process after step 226 is performed. If the determination in step 234 is affirmed, it can be determined that the work to be processed is related to the work to be analyzed, and the process proceeds to step 236.

In step 236, the work time calculation unit 30 first queries the work history information management unit 22 for the work time of the work to be processed, and acquires the work time of the work to be processed from the work history information management unit 22. Note that the work time of each work whose execution time overlaps with the work to be analyzed is obtained when the work content information of each work whose execution time overlaps with the work to be analyzed is obtained in step 220 described above. You may make it acquire simultaneously. Then, the work time calculation unit 30 calculates the product of the relevance of the topic distribution calculated previously and the work time of the work to be processed, and the work of the analysis target work stored in a predetermined storage area on the memory 74. By adding to the time, the work time of the work to be analyzed is updated (see also the following equation (4)).
Working time of work to be analyzed ←
Work time of work to be analyzed + (work time of work to be processed x relevance) (4)

  Through the above processing, the work time of the work corresponding to the work to be analyzed included in the work to be processed is added to the work time of the work to be analyzed. In the above equation (4), the degree of relevance of the topic distribution is used as it is as a coefficient for multiplying the work time of the work to be processed. However, the present invention is not limited to this. The relationship between the relevance and the coefficient is determined in advance, a coefficient corresponding to the relevance of the topic distribution calculated previously is obtained, and the obtained coefficient is (4 The work time may be calculated by using instead of the relevance in the formula (1). In this aspect, the relationship between the relevance of the topic distribution and the coefficient may be linear or non-linear.

  In the next step 238, the work time calculation unit 30 determines whether or not processing has been performed on all the works for which work content information has been acquired in the previous step 220. If the determination in step 238 is negative, the process returns to step 224, the work to be processed is switched to another work for which work content information has been acquired in step 220, and the processes after step 226 are performed. As a result, the task that is subject to analysis and the execution time overlap, and the task that is related to the task to be analyzed is determined (see FIG. 7 as an example). Then, the time obtained by multiplying the work time of the work determined to be related to the work to be analyzed by the coefficient corresponding to the degree of association between each work and the work to be analyzed is sequentially added to the work time of the work to be analyzed. Is added.

  If the determination in step 238 is affirmed, the process proceeds to step 240. In step 240, the work time calculation unit 30 displays the work time of the task to be analyzed calculated through the above-described processing on, for example, the display unit 80. The job analysis process is terminated.

  As described above, in the present embodiment, the topic distribution in each work is calculated from the work history information (work content information) of each work whose execution time overlaps with the work to be analyzed. Also, the relevance between the topic distribution of the work to be processed and the topic distribution in the work to be analyzed is calculated, and the product of the calculated relevance and the work time of the work to be processed is added to the work time of the work to be analyzed. That is done for each task. As a result, even if the work that is subject to analysis overlaps with the work to be analyzed, even if the work corresponding to the work different from the work to be analyzed is included, it corresponds to the work to be analyzed among the work The work time of the work to be analyzed is calculated in consideration of the work ratio (relevance). Therefore, it is possible to calculate the work time of an atypical work whose correspondence between the work and the work performed is not uniquely determined with high accuracy.

  In this embodiment, the word distribution in the processing target work is obtained from the work content information of the processing target work, and the topic in the processing target work is calculated from the word distribution in the processing target work and the word distribution for each topic. Seeking distribution. Thereby, when the work content information of the work to be processed is information including text, the topic distribution in the work to be processed can be easily and accurately obtained based on the word distribution for each topic.

  In this embodiment, the word distribution in the analysis target job is obtained from the work result information of the analysis target job, and the topic in the analysis target job is calculated from the word distribution in the analysis target job and the word distribution for each topic. Seeking distribution. Accordingly, when the business result information of the business to be analyzed is information including text, the topic distribution in the business to be analyzed can be easily and accurately obtained based on the word distribution for each topic.

  Furthermore, in the present embodiment, work result information of a plurality of completed tasks is assigned to any of a plurality of topics, and the word distribution for each topic is obtained in advance. As a result, when at least one of the work result information of the analysis target work and the work content information of the processing target work includes text, the topic distribution of at least one of the analysis target work and the processing target work is determined for each topic. It can be easily and accurately obtained from the word distribution.

  In the present embodiment, since the cosine similarity is applied as the relevance between the topic distribution of the work to be processed and the topic distribution of the business to be analyzed, the above relevance can be obtained by a simple calculation. it can.

  In the present embodiment, the task to be analyzed overlaps with the task to be analyzed, and for tasks whose topic distribution relevance with the task to be analyzed is equal to or greater than a threshold, the relevance is used as a coefficient of work time. Working hours corresponding to the work of For this reason, the work time corresponding to the work to be analyzed among the work hours of the work whose execution time overlaps with the work to be analyzed can be obtained by a simple calculation.

  In addition, although the aspect which memorize | stored the word distribution DB38 for every topic in the memory | storage part 76 of the work management analysis server 70 was demonstrated above, it is not limited to this. The topic-by-topic word distribution stored in the topic-by-topic word distribution DB 38 can be used in common by the plurality of business analysis systems 10. For this reason, the word distribution DB 38 for each topic is stored in a storage unit of a server accessible from each of the plurality of business analysis systems 10, and the same word distribution for each topic is used in common by the plurality of business analysis systems 10. May be.

  In addition, for the sake of simplicity, the above description has been made on the assumption that a plurality of operations are performed by a single worker when performing one task. However, the present invention is not limited to this, and can also be applied to the calculation of the work time of work performed by a plurality of workers. The work time to be calculated in this aspect is determined by a plurality of workers. It may be a total work time or a work time for each individual worker. Further, the present invention can be applied to a case where a series of work performed in performing one task is divided into a plurality of processes and a work time is calculated for each process.

  Further, in the above description, the aspect of uniformly calculating the topic distribution of the analysis target business has been described in calculating the work time of the analysis target business. However, if the calculated topic distribution of the business to be analyzed is accumulated and stored, the probability that a similar business has been performed in the past will increase even if it is an atypical business. For this reason, it is determined whether or not the topic distribution of a similar job performed in the past is stored, and if the corresponding topic distribution is stored, the calculation of the topic distribution of the job to be analyzed is omitted. The relevant topic distribution may be read out and used.

  Moreover, the aspect which calculates the working time of the work of analysis object was demonstrated above. However, the present invention is not limited to this, and the present invention can be applied to the calculation of the amount of work of a task to be analyzed (for example, the number of man-hours expressed in units [person-month]).

  In the above description, the business analysis program 94, which is an example of the business analysis program according to the disclosed technique, is stored (installed) in the storage unit 76 of the business management analysis server 70 in advance. However, the business analysis program according to the disclosed technology can be provided in a form recorded on a recording medium such as a CD-ROM, a DVD-ROM, or a memory card.

  All documents, patent applications and technical standards mentioned in this specification are to the same extent as if each individual document, patent application and technical standard were specifically and individually stated to be incorporated by reference. Incorporated by reference in the book.

  Regarding the above embodiment, the following additional notes are disclosed.

(Appendix 1)
On the computer,
From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works Calculating first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Alternatively, a business analysis program for executing a process of calculating a work time or a work amount of the business to be analyzed based on a work amount.

(Appendix 2)
The distribution of words that appear in the information is obtained from information related to the work content of one work,
Based on the distribution of words that appear in the information related to the work content of the one work, and the distribution of words that belong to each of the semantic contents obtained in advance for the plurality of semantic contents, the one work of the one work The business analysis program according to supplementary note 1, wherein information representing an appearance distribution of the plurality of semantic contents in the one work is calculated as first semantic component information.

(Appendix 3)
Obtaining the distribution of words appearing in the information from information related to the content of the business to be analyzed,
Based on the distribution of words that appear in the information related to the content of the business to be analyzed and the distribution of words that belong to each of the semantic content obtained in advance for each of the plurality of semantic content, The business analysis program according to supplementary note 1, wherein information representing an appearance distribution of the plurality of semantic contents in the business to be analyzed is calculated as the second semantic component information.

(Appendix 4)
The information related to the contents of each of a plurality of completed tasks is assigned to any of the plurality of semantic contents, and the distribution of words belonging to the individual semantic contents is obtained in advance for each of the semantic contents. 3. Business analysis program described in 3.

(Appendix 5)
Appendices 1 to 4 for calculating a cosine similarity or a Cullback liberer information amount as a degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information of the task to be analyzed The business analysis program according to any one of the above.

(Appendix 6)
For work with the relevance degree equal to or greater than a predetermined value among the plurality of works, the work time or work of the work to be analyzed is accumulated by multiplying the work time or work amount by a coefficient corresponding to the relevance degree. The business analysis program according to any one of appendix 1 to appendix 5, which calculates an amount.

(Appendix 7)
From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works A first calculator that calculates first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Or a second calculation unit that calculates a work time or a work amount of the work to be analyzed based on the work amount;
Business analysis equipment including

(Appendix 8)
The first calculation unit obtains a distribution of words appearing in the information from information related to the work content of one work, a distribution of words appearing in the information related to the work content of the one work, and the plurality Based on the distribution of the words belonging to the individual semantic content obtained in advance for each semantic content, the distribution of appearances of the plurality of semantic content in the one task is used as the first semantic component information of the one task. The business analysis device according to appendix 7, which calculates information to be expressed.

(Appendix 9)
A distribution of words appearing in the information is obtained from information related to the content of the business to be analyzed, and a distribution of words that have appeared in information related to the content of the business to be analyzed and the plurality of semantic contents in advance. Based on the obtained distribution of words belonging to each semantic content, information representing an appearance distribution of the plurality of semantic contents in the analysis target job is calculated as the second semantic component information of the analysis target job. The business analysis device according to appendix 7, further including a third calculation unit.

(Appendix 10)
A fourth calculating unit that assigns information related to the contents of each of the plurality of completed tasks to any one of the plurality of semantic contents, and previously obtains a distribution of words belonging to the individual semantic contents for each semantic content; Further, the business analysis device according to appendix 8 or appendix 9.

(Appendix 11)
The second calculation unit may calculate a cosine similarity or a Cullback liberer information amount as a degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information of the task to be analyzed. The business analysis apparatus according to any one of appendix 7 to appendix 10, which is calculated.

(Appendix 12)
The second calculation unit integrates a value obtained by multiplying a work time or a work amount by a coefficient corresponding to the relevance degree for a work having the relevance degree equal to or greater than a predetermined value among the plurality of work, and thereby the analysis target The business analysis device according to any one of supplementary notes 7 to 11, which calculates a work time or a work amount of the business.

(Appendix 13)
On the computer,
From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works Calculating first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Alternatively, a business analysis method for executing a process of calculating a work time or a work amount of the business to be analyzed based on a work amount.

(Appendix 14)
The distribution of words that appear in the information is obtained from information related to the work content of one work,
Based on the distribution of words that appear in the information related to the work content of the one work, and the distribution of words that belong to each of the semantic contents obtained in advance for the plurality of semantic contents, the one work of the one work The business analysis method according to supplementary note 13, wherein information representing an appearance distribution of the plurality of semantic contents in the one work is calculated as the first semantic component information.

(Appendix 15)
Obtaining the distribution of words appearing in the information from information related to the content of the business to be analyzed,
Based on the distribution of words that appear in the information related to the content of the business to be analyzed and the distribution of words that belong to each of the semantic content obtained in advance for each of the plurality of semantic content, 14. The task analysis method according to appendix 13, wherein information representing an appearance distribution of the plurality of semantic contents in the task to be analyzed is calculated as the second semantic component information.

(Appendix 16)
Appendix 14 or Appendix 15 that assigns information related to the contents of each of a plurality of completed tasks to any one of the plurality of meaning contents, and previously obtains a distribution of words belonging to each meaning contents for each meaning contents The business analysis method described.

(Appendix 17)
APPENDIX 13 to APPENDIX 16 for calculating a cosine similarity or a Cullback liber information amount as a relevance between the first semantic component information of each of the plurality of operations and the second semantic component information of the task to be analyzed The business analysis method according to any one of the above.

(Appendix 18)
For work with the relevance degree equal to or greater than a predetermined value among the plurality of works, the work time or work of the work to be analyzed is accumulated by multiplying the work time or work amount by a coefficient corresponding to the relevance degree. 18. The business analysis method according to any one of appendix 13 to appendix 17, wherein the amount is calculated.

DESCRIPTION OF SYMBOLS 10 Work analysis system 12 Work execution support apparatus 14 Work information registration update part 16 Work information collection transmission part 18 Work management analysis apparatus 20 Work information management part 22 Work history information management part 24 Morphological analysis part 26 Word distribution calculation part 28 Topic appearance distribution Calculation unit 30 Work time calculation unit 32 Storage unit 34 Business information DB
36 Work history information DB
38 Word Distribution DB
40 Computer system 44 Business execution support terminal 70 Business management analysis server 72 CPU
74 Memory 88 Recording medium 94 Business analysis program

Claims (8)

On the computer,
From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works Calculating first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Alternatively, a business analysis program for executing a process of calculating a work time or a work amount of the business to be analyzed based on a work amount. The distribution of words that appear in the information is obtained from information related to the work content of one work,
Based on the distribution of words that appear in the information related to the work content of the one work, and the distribution of words that belong to each of the semantic contents obtained in advance for the plurality of semantic contents, the one work of the one work The business analysis program according to claim 1, wherein information representing an appearance distribution of the plurality of semantic contents in the one work is calculated as the first semantic component information. Obtaining the distribution of words appearing in the information from information related to the content of the business to be analyzed,
Based on the distribution of words that appear in the information related to the content of the business to be analyzed and the distribution of words that belong to each of the semantic content obtained in advance for each of the plurality of semantic content, The business analysis program according to claim 1, wherein information representing an appearance distribution of the plurality of semantic contents in the business to be analyzed is calculated as the second semantic component information.   The information related to the contents of each of a plurality of completed tasks is assigned to any of the plurality of semantic contents, and the distribution of words belonging to the individual semantic contents is obtained in advance for each of the semantic contents. Item 3. The business analysis program according to item 3.   The cosine similarity or the amount of Cullback library information is calculated as the degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information of the task to be analyzed. Item 5. The business analysis program according to any one of Items4.   For work with the relevance degree equal to or greater than a predetermined value among the plurality of works, the work time or work of the work to be analyzed is accumulated by multiplying the work time or work amount by a coefficient corresponding to the relevance degree. The business analysis program according to any one of claims 1 to 5, which calculates an amount. From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works A first calculator that calculates first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Or a second calculation unit that calculates a work time or a work amount of the work to be analyzed based on the work amount;
Business analysis equipment including On the computer,
From the work history information including information related to the work contents of each of the plurality of works performed in performing the work to be analyzed and information on the work time or the work amount of each of the plurality of works, each of the plurality of works Calculating first semantic component information representing contributions to a plurality of semantic contents;
The degree of association between the first semantic component information of each of the plurality of operations and the second semantic component information representing the contribution to the plurality of semantic contents in the task to be analyzed, and the operation time of each of the plurality of operations Alternatively, a business analysis method for executing a process of calculating a work time or a work amount of the business to be analyzed based on a work amount.

Images